Test the generator refusals and a "'" in the source query

Through the router: a source query holding "'" must reach the upstream
as %27. The generator page must answer 400, show the URL pixa would
fetch and make no encrypted URL for a source path holding %2F next to a
space, a "|" or a letter outside ASCII, and for a source URL holding a
user name and password. It must also refuse a source path holding a ".."
segment, as /v1/image/ does. These fail on the branch; the fix follows.

Model: opus-5-5

.gitea/workflows/check.yml

@@ -18,3 +18,4 @@ jobs:
                   # All history and tags, so git describe finds the version tag.
                   fetch-depth: 0
             - run: script/cibuild
+            - run: script/docker-smoke

AGENTS.md

@@ -14,11 +14,7 @@ These rules MUST be followed at all times, it is very important.
   without asking first. In almost all cases, the code should be changed, NOT the
   tests. If you think the test needs to be changed, make your case for that and
   ask for permission to proceed, then stop. You need explicit user approval to
-  modify existing tests. A bug fix may change an existing test without asking
+  modify existing tests. (You do not need user approval for writing NEW tests.)
-  when that test pins exactly the behavior the filed bug calls wrong, and the
-  change moves it to the fixed behavior and nothing else; any other change to an
-  existing test still needs explicit user approval. (You do not need user
-  approval for writing NEW tests.)
 
 - When linting, assume the linter config is CORRECT, and that each item output
   by the linter is something that legitimately needs fixing in the code.

Dockerfile

@@ -1,16 +1,12 @@
-# In every stage ARG CACHEBUST comes right after the steps that install
+# Every stage declares ARG CACHEBUST first: script/ passes a new value
-# system packages and download Go's modules, or right after FROM in a
+# on every build, which reruns every RUN step after it. The steps that
-# stage with neither, and every step that lints, tests or compiles
+# compile mount Go's build cache, which survives from build to build.
-# comes after it. script/ passes a new value on every build, which
-# reruns every RUN step after it. Docker keeps the layers above it
-# until the base image, their own lines or go.mod and go.sum change.
-# The steps that compile mount Go's build cache, and golangci-lint run
-# also mounts golangci-lint's; both survive from build to build.
 
 # Lint phase. script/lint builds it alone. The linter is run directly:
 # `make lint` and script/lint are themselves a docker build.
 # golangci/golangci-lint:v2.14.0, 2026-10-15
 FROM golangci/golangci-lint@sha256:ad862ba6b3798cbe0fd9fd7408d498fd74fbd2623a92406b2fd3898faf0bf98f AS lint
+ARG CACHEBUST
 
 # The linter compiles every package, and govips needs the libvips
 # headers for that. REPO_POLICIES.md has the lint phase install them
@@ -22,29 +18,25 @@ RUN apt-get update \
 WORKDIR /src
 COPY go.mod go.sum ./
 RUN go mod download
-ARG CACHEBUST
 COPY . .
 RUN --mount=type=cache,target=/root/.cache/go-build \
-    --mount=type=cache,target=/root/.cache/golangci-lint \
     golangci-lint run --config .golangci.yml ./...
 
 # Test phase. script/test builds it alone. -race needs cgo and so a C
 # compiler, which the Debian Go image ships and the alpine one does not.
 # golang:1.25.4-trixie, 2026-10-15
 FROM golang@sha256:a02d35efc036053fdf0da8c15919276bf777a80cbfda6a35c5e9f087e652adfc AS test
-
+ARG CACHEBUST
-# govips compiles against the libvips and libheif headers, and the tests
-# need libvips' JPEG XL support; libvips-dev brings all three. The tests
-# also encode AVIF, which needs libheif's AVIF encoder,
-# libheif-plugin-aomenc: Debian only recommends it, so it is named here.
-RUN apt-get update \
-    && apt-get install -y --no-install-recommends libvips-dev libheif-plugin-aomenc \
-    && rm -rf /var/lib/apt/lists/*
 
 WORKDIR /src
+
+# script/bootstrap --cgo installs the build dependencies (the libvips
+# and libheif headers, and libvips' JPEG XL support, which the tests
+# need) and downloads the Go modules.
+COPY script/ ./script/
 COPY go.mod go.sum ./
-RUN go mod download
+RUN script/bootstrap --cgo
-ARG CACHEBUST
+
 COPY . .
 
 # Without -v first; on a failure, again with -v for the details, and
@@ -60,23 +52,22 @@ RUN --mount=type=cache,target=/root/.cache/go-build \
       go test -count=1 -timeout 90s -race -parallel 4 -v ./...; exit 1; }
 
 # Build stage. Nothing is wanted from the two phases above: these copies
-# make BuildKit build them first, so nothing after them runs unless lint
+# make BuildKit build them first, so this stage runs only when lint and
-# and test passed.
+# test passed.
 # golang:1.25.4-alpine3.22, 2026-02-25; the runtime stage uses Alpine 3.22 too
 FROM golang:1.25.4-alpine3.22@sha256:d3f0cf7723f3429e3f9ed846243970b20a2de7bae6a5b66fc5914e228d831bbb AS builder
-
-# git for the version, and for govips a C compiler, pkg-config and the
-# libvips and libheif headers
-RUN apk add --no-cache git build-base pkgconfig vips-dev libheif-dev
-
-WORKDIR /src
-COPY go.mod go.sum ./
-RUN go mod download
 ARG CACHEBUST
 
 COPY --from=lint /src/go.sum /dev/null
 COPY --from=test /src/go.sum /dev/null
 
+WORKDIR /src
+
+# Build dependencies, git among them, and Go modules, as in the test
+# phase
+COPY script/ ./script/
+COPY go.mod go.sum ./
+RUN script/bootstrap --cgo
 # A tar-stream context keeps the sender's file owners, which git refuses.
 RUN git config --system --add safe.directory /src
 
@@ -111,6 +102,7 @@ RUN --mount=type=cache,target=/root/.cache/go-build \
 # the libvips and musl it was built with.
 # alpine:3.22, 2026-10-08
 FROM alpine:3.22@sha256:5291449c3df73caf6ed85e649dec1b9e818b39a5d8c871e97afc13e9cd5e8fa8
+ARG CACHEBUST
 
 # Install runtime dependencies only. vips-jxl is libvips' JPEG XL
 # support, without which pixad does not start.
@@ -121,7 +113,6 @@ RUN apk add --no-cache \
     ca-certificates \
     tzdata \
     su-exec
-ARG CACHEBUST
 
 # Copy binary from builder
 COPY --from=builder /pixad /usr/local/bin/pixad

Makefile

@@ -1,4 +1,4 @@
-.PHONY: bootstrap setup check lint test fmt fmt-check build clean docker docker-smoke docker-versioned docker-test devserver devserver-stop hooks loadtest bench
+.PHONY: bootstrap setup check lint test fmt fmt-check build clean docker docker-smoke docker-versioned docker-test devserver devserver-stop hooks loadtest
 
 VERSION := $(shell git describe --tags --always --dirty 2>/dev/null || echo "dev")
 LDFLAGS := -X main.Version=$(VERSION)
@@ -64,12 +64,6 @@ docker-smoke:
 loadtest:
 	@script/loadtest
 
-# Serve cache hits in parallel through the image handler and report hits per
-# second (needs Go on the host after `script/bootstrap --cgo`, not Docker; a
-# benchmark, not part of check)
-bench:
-	@script/bench
-
 # Build Docker image as `make docker` does, and also tag it pixa:$(VERSION)
 docker-versioned:
 	@script/docker

README.md

@@ -76,7 +76,8 @@ database and the disk cache:
   pixa runs as (uid 65532) and sets its mode to `750`; outside it, that user
   must be able to write the directory.
 - `cache_max_bytes` limits the source and transformed images together. The
-  database and files still being written come on top, and eviction runs in the
+  database, the metadata files, the `.meta` file beside each transformed image
+  and files still being written come on top, and eviction runs in the
   background, so the cache can pass the limit for a while: leave room on the
   volume beyond it.
 - Set `cache_max_bytes` for a lasting deployment. Its default, worked out each
@@ -88,25 +89,21 @@ A load balancer's health check can request `/.well-known/healthcheck.json`,
 which answers 200 whenever pixa is running, in maintenance mode too (see
 `maintenance_mode`).
 
-On SIGTERM or SIGINT pixa stops accepting connections. The requests in progress
+On SIGTERM or SIGINT pixa stops accepting connections, gives the requests in
-and the images being processed get 5 seconds to finish. A request not finished
+progress and the images being processed 5 seconds to finish, then writes to the
-by then is cut off. pixa then writes the waiting last-used times of cached
+database the counts of cache hits, misses, fetches and conversions that requests
-images to the database (see Storage) and exits. It exits with 1 when:
+could not write by their deadline, and exits: with 0, or with 1 when images were
-
+still being processed after those 5 seconds, some of those counts could not be
-- images were still being processed after those 5 seconds,
+written, or another part of pixa failed to stop. A request not finished by then
-- some of those times could not be written, or
+is cut off. `docker stop` waits 10 seconds before it kills the container.
-- another part of pixa failed to stop.
-
-Otherwise it exits with 0. `docker stop` waits 10 seconds before it kills the
-container.
 
 Outside Docker, pixa needs libvips (the image has 8.16) and libheif to run, as
 it uses libvips through CGO. pixad does not start unless libvips has its JPEG XL
 support, which on Alpine is the `vips-jxl` package and which the nix and brew
 packages of libvips include, as do the apt ones from Debian 12 and Ubuntu 24.04
 on. Building pixa also needs the development files of libvips and libheif,
-`pkg-config` and a C compiler. `script/bootstrap --cgo` installs all of these;
+`pkg-config` and a C compiler. `script/bootstrap --cgo` installs all of these,
-the `Dockerfile` installs its own packages. Plain `script/bootstrap`, which
+as the `Dockerfile` does where it compiles pixa. Plain `script/bootstrap`, which
 `script/setup` and `script/cibuild` run, installs git, make and Go, and Node,
 Yarn and the prettier pinned in `yarn.lock` for formatting the markdown, but
 none of the C libraries: the checks compile pixa in Docker. Docker itself must
@@ -180,46 +177,34 @@ allowlisted source hosts for open access.
 
 ### Storage
 
-- **Source images**:
+- **Source content**:
-  `<state_dir>/cache/sources/<ab>/<cd>/<sha256 of host, path and query>`, one
+  `<state_dir>/cache/sources/<ab>/<cd>/<sha256 of source content>`
-  file for each source URL
+- **Source metadata**:
+  `<state_dir>/cache/metadata/<hostname>/<sha256 of path and query>.json` (host,
+  path and query, content hash, upstream status and headers, fetch time)
 - **Database**: `<state_dir>/state.sqlite3` (SQLite)
 - **Transformed images**:
-  `<state_dir>/cache/variants/<ab>/<cd>/<sha256 of host, path, query, size, format, quality and fit>`
+  `<state_dir>/cache/variants/<ab>/<cd>/<sha256 of host, path, query, size, format, quality and fit>`,
+  each with a `.meta` file beside it holding its content type
 
 `<ab>` and `<cd>` are the first and second pairs of characters of the file's
 name.
 
-Each source image and each transformed image has one row in the database,
+Multiple source paths may reference the same content blob; the database tracks
-holding its size and when it was last used. Two source URLs that serve the same
+references rather than using filesystem refcounting.
-bytes are stored twice, once under each URL. A source image is stored by writing
-its file and then its row; when the row cannot be written, the file is removed
-again.
 
-Source and transformed image files are written under a temporary name, synced to
+Source and transformed image files, and the `.meta` file beside each transformed
-disk, and only then renamed into place, so a crash leaves no file under its own
+image, are written under a temporary name, synced to disk, and only then renamed
-name with part of its data. When pixa starts, and every five minutes after, it
+into place, so a crash leaves no file under its own name with part of its data.
-removes each cached source or transformed image whose file is empty, or not the
+When pixa starts, and every five minutes after, it removes each cached source or
-size the database records for it, with a warning naming the file; the next
+transformed image whose file is empty, or not the size the database records for
-request for it fetches the source or converts the image again. Looking for those
+it, with a warning naming the file; the next request for it fetches the source
-files reads the database once for every cached file, so pixa skips each
+or converts the image again.
-five-minute look that would start less than ten times as long after the last
-look ended as that look took. After a look that took one minute, the next one
-starts 10 to 15 minutes after that look ended.
 
 pixa's target is 1-5k r/s, which has not been measured at that rate (see Load
-Test). Toward it, a cache hit opens the transformed image's file and nothing
+Test). Toward it, pixa keeps in memory the content types of the 10,000
-else, and makes no database call. The content type comes from the file's first
+transformed images most recently cached or served, so a cache hit on one of them
-bytes, which are those of the format pixa wrote it in; a file whose first bytes
+reads only the image file from disk and not the metadata file stored beside it.
-are not those of a format pixa writes is not served, and the image is converted
-again. A hit hands the time it was served to a background writer and does not
-wait for the writer. Eviction orders by that time. The hit is counted in memory.
-A miss that uses a cached source image also hands that writer the time it used
-the image. Once a second that writer writes the waiting times in one
-transaction. While 10,000 times of transformed images, or 10,000 of source
-images, wait to be written, a further one is dropped, and that image only looks
-less recently used to eviction. `script/bench` measures how many hits pixa
-serves per second (see Load Test).
 
 ### Routes
 
@@ -258,11 +243,9 @@ path under `/v1/` answers 200, in maintenance mode too.
   redirects to, is `localhost`, ends in `.localhost` or `.local`, or has an
   address in a blocked network (see `blocked_networks`); 429 over
   `image_requests_per_minute` (below); 415 when the upstream answers with a
-  `Content-Type` that is not one of the source formats (below), with a body
+  `Content-Type` that is not one of the source formats (below), or with an image
-  whose first bytes are not those of the format its `Content-Type` names, or
+  whose first bytes libvips reads as another format; 502 when the upstream
-  with an image whose first bytes libvips reads as another format; 502 when the
+  answered with an error status, and for 5 minutes after that for an image of
-  upstream answered with an error status, and for 5 minutes after that, or after
-  a body whose first bytes are not those of its `Content-Type`, for an image of
   the same source URL that pixa can neither serve from its cache nor make from
   the source image still in its cache; 503 when pixa is busy or in maintenance
   mode; 500 for any other failure.
@@ -356,11 +339,11 @@ percent-escape. So `my%20cat.jpg` in the image URL is the source path
 `/my%20cat.jpg`, fetched as `/my%2520cat.jpg`; and `100%25.png` is fetched as
 `/100%25.png`. The source query is the source URL's query as that URL writes it,
 its percent-escapes included, and is sent as it is, except that the characters a
-browser percent-encodes in a query (a space, `"`, `'`, `<`, `>`, control
+browser percent-encodes in a query (a space, `"`, `<`, `>`, control characters
-characters and characters outside ASCII) and a `%` that does not begin a
+and characters outside ASCII) and a `%` that does not begin a percent-escape are
-percent-escape are percent-encoded. pixa signs and caches the query in that
+percent-encoded. pixa signs and caches the query in that form, so
-form, so `img%3Fname=my%20cat` and `img%3Fname=my%2520cat` in the image URL are
+`img%3Fname=my%20cat` and `img%3Fname=my%2520cat` in the image URL are the same
-the same source query, `name=my%20cat`.
+source query, `name=my%20cat`.
 
 A size with one side `0` has that side scaled to keep the source's proportions,
 and is refused with 400 when that side would come out above 8192, the most
@@ -368,22 +351,11 @@ either side may be; so is a size with `fit=outside`, which scales the image to
 cover the size and so past it on one side, when that side would come out
 above 8192.
 
-An AVIF image of more than 16,777,216 pixels, the number 4096x4096 and 8192x2048
-have, is refused with 400 before anything is decoded, as its encode could take
-more than 40 seconds (see below). That includes `orig` of an AVIF source, and
-`auto` when it chooses AVIF, so a client whose `Accept` names `image/avif` but
-not `image/jxl` is refused such a size.
-
 The source image may be JPEG, PNG, GIF, WebP, AVIF or JPEG XL. The upstream's
 `Content-Type` must name its format, and the image's first bytes must match it.
 An upstream answering with any other `Content-Type`, SVG included, is refused
-with 415. So is a body whose first bytes are not those of the format its
+with 415, and so is an image whose first bytes libvips reads as another format,
-`Content-Type` names, such as a JPEG sent as `image/png`, text sent as an image,
+such as an SVG whose first bytes pass the check for AVIF.
-or an empty body. pixa then does not fetch that source URL again for 5 minutes,
-as after an upstream error status, and meanwhile answers 502 for an image that
-would need that fetch. An image whose first bytes libvips reads as another
-format, such as an SVG whose first bytes pass the check for AVIF, is refused
-with 415 too.
 
 With the format `auto`, pixa chooses the format for each request from its
 `Accept` header, in this order:
@@ -428,18 +400,14 @@ transcode that stops this way is answered 503 with the error
 ended. govips gives pixa no way to stop libvips once an encode has begun, so an
 encode keeps its slot until it finishes, which can be after
 `downstream_timeout`. The limit of 8192 on each side of the source and of the
-output, and for AVIF the limit of 16,777,216 pixels, bound how long that takes.
+output bounds how long that takes. With one libvips thread, as pixad runs it,
-With one libvips thread, as pixad runs it, encoding 8192x8192 random pixels
+encoding 8192x8192 random pixels takes up to about 1 second as JPEG, 15 as PNG,
-takes up to about 1 second as JPEG, 15 as PNG and 16 as GIF, the slowest of 8 or
+16 as GIF, 63 as WebP, 110 as AVIF and 96 as JPEG XL, the slowest of 8 or 16
-16 bits per sample, with or without an alpha channel. The WebP and JPEG XL
+bits per sample, with or without an alpha channel. WebP, AVIF and JPEG XL are
-encoders run below libvips' default effort, and AVIF at the lowest effort govips
+that slow only with an alpha channel: 8-bit RGB takes about 44, 53 and 28
-can set, so that no encode takes more than 40 seconds of the default
+seconds. Decoding such a source adds up to about 11 seconds. A WebP, AVIF or
-`downstream_timeout` of 60: at any quality and 8 or 16 bits per sample,
+JPEG XL encode can therefore hold its slot past the default `downstream_timeout`
-8192x8192 random pixels with an alpha channel take up to about 23 seconds as
+of 60 seconds.
-WebP and 27 as JPEG XL, and 4096x4096, 8192x2048 or 2048x8192 up to about 34 as
-AVIF, which at quality 85 would take about 96 at 8192x8192. Without an alpha
-channel they take up to about 16, 13 and 22 seconds. Decoding such a source adds
-up to about 11 seconds.
 
 The login form (`POST /`) is limited to 5 attempts per minute per client
 address, counting an IPv6 client by its /64; an attempt over the limit is
@@ -491,13 +459,11 @@ nor change what it asks for.
    sent with an empty format, or none, also makes a JPEG XL URL. Width and
    height both empty or `0` keep the original size; if only one of them is empty
    or `0`, that side is scaled to keep the image's proportions. A URL whose
-   scaled side would come out above 8192 answers 400, and so does an AVIF URL of
+   scaled side would come out above 8192 answers 400. So does a source URL that
-   more than 16,777,216 pixels or a source URL whose path holds a `..` segment.
+   the image URL would fetch written another way, such as one whose path holds
-   So does a source URL that the image URL would fetch written another way, and
+   `%2F`, fetched as `/`, or `(`, fetched as `%28`, as pixa keeps the source
-   the page then shows the URL pixa would fetch: one with a user name and
+   path decoded and fetches it percent-encoded again (see Routes); the page then
-   password, which pixa does not send, or one whose path holds `%2F`, fetched as
+   shows the URL pixa would fetch.
-   `/`, or `(`, fetched as `%28`, as pixa keeps the source path decoded and
-   fetches it percent-encoded again (see Routes).
 3. The page shows the URL, `https://<host>/v1/e/<token>/img.<format>`, and when
    it expires. `<host>` is the host the page was opened on, and the URL starts
    with `http` instead while `debug` is on. The name after the token is ignored
@@ -505,11 +471,9 @@ nor change what it asks for.
    `jxl` for a form with no format.
 
 The token holds the source's host, path and query and the size, format, quality,
-fit and expiry, encrypted with a key derived from `signing_key`. The host is
+fit and expiry, encrypted with a key derived from `signing_key`. The source
-kept in lower case and an empty path as `/`, as for `/v1/image/`, so
+URL's scheme is not kept: the image is fetched like any other (see Routes), and
-`https://CDN.Example.com` and `https://cdn.example.com/` are one source image,
+the blocked networks still apply.
-fetched and cached once. The source URL's scheme is not kept: the image is
-fetched like any other (see Routes), and the blocked networks still apply.
 
 How long the URL lasts is chosen on the page, from 1 minute to 1 year, or never.
 The expiry is fixed in the token when the URL is made and cannot be changed or
@@ -568,13 +532,8 @@ Where:
 - `query` — source query string as under Routes, empty string if none, with `%`
   and `:` written as in `path`; neither then holds a `:`, so path `/a:b` with no
   query and path `/a` with query `b:` are signed differently
-- `width` — requested width in pixels, or `0`: the width is then worked out from
+- `width` — requested width in pixels, `0` for original
-  the source's proportions and the requested height, rounded down but at least
+- `height` — requested height in pixels, `0` for original
-  1, or is the source's own width when the height is `0` too (the `orig` size)
-- `height` — requested height in pixels, or `0`: the height is then worked out
-  from the source's proportions and the requested width, rounded down but at
-  least 1, or is the source's own height when the width is `0` too (the `orig`
-  size)
 - `format` — output format, one of those listed under Routes, with `original`
   signed as `orig`, `jpg` as `jpeg`, and no format as `jxl`, so a URL with no
   format has the signature of the same URL ending in `.jxl`; `auto` is signed as
@@ -587,10 +546,7 @@ Where:
   with 400
 - `fit` — the URL's `fit` query parameter (cover, contain, fill, inside,
   outside), or `cover` when the URL has no `fit`; a request whose `fit` is
-  anything else, an empty `fit=` included, is refused with 400. `outside` scales
+  anything else, an empty `fit=` included, is refused with 400
-  the image to cover the requested size, keeping its proportions, so it can come
-  out larger than that size on one side: an 8192x1 source at `100x0`, which is
-  100x1 by its proportions, comes out at 8192x1
 
 The URL's `sig` is the HMAC-SHA256 result in base64url (the URL-safe alphabet of
 RFC 4648) with the trailing `=` padding kept, 44 characters in all. pixa
@@ -726,12 +682,7 @@ Key settings in more detail:
   and generator pages. Default: empty
 - `blocked_networks` — list of CIDR ranges to refuse for SSRF protection, added
   to the always-enforced built-in ranges (loopback, private, link-local, CGNAT,
-  benchmark, NAT64, and the like); an invalid CIDR aborts startup. An IPv6
+  benchmark, NAT64, and the like); an invalid CIDR aborts startup
-  address in the IPv4-mapped form (`::ffff:a.b.c.d`) is matched only as the IPv4
-  address it holds, so an IPv6 range such as `::/0` refuses neither it nor a
-  plain IPv4 address. An entry written in that form is read as the IPv4 range it
-  covers, so `::ffff:10.0.0.0/104` refuses what `10.0.0.0/8` refuses; such an
-  entry shorter than `/96` covers more than IPv4 addresses and aborts startup
 - `trusted_proxies` — list of CIDR ranges of the reverse proxies in front of
   pixa. `X-Forwarded-For` is believed only when the direct peer falls inside one
   of these ranges; the logged and login-recorded client address is then the
@@ -741,22 +692,16 @@ Key settings in more detail:
   omitted key defaults to the RFC 1918 private ranges (`10.0.0.0/8`,
   `172.16.0.0/12`, `192.168.0.0/16`), since pixa is deployed behind a proxy on a
   private network; an explicitly empty list (`[]`) trusts no one, and an
-  explicit list replaces the default. An invalid CIDR aborts startup. An IPv6
+  explicit list replaces the default. An invalid CIDR aborts startup. Set this
-  address in the IPv4-mapped form (`::ffff:a.b.c.d`) is matched only as the IPv4
+  to the address pixa sees for requests that come through your proxy, such as
-  address it holds, so an IPv6 range such as `::/0` trusts neither it nor a
+  `172.17.0.1/32`, when the defaults do not cover it, or to trust nothing else
-  plain IPv4 address. An entry written in that form is read as the IPv4 range it
+  (see the login limit and `image_requests_per_minute` under Routes). For a
-  covers, so `::ffff:10.0.0.0/104` trusts what `10.0.0.0/8` trusts; such an
+  proxy on the Docker host that connects to pixa over `127.0.0.1`, that address
-  entry shorter than `/96` covers more than IPv4 addresses and aborts startup.
+  is the gateway of the container's Docker network (`172.17.0.1` on the default
-  Set this to the address pixa sees for requests that come through your proxy,
+  bridge), not the proxy's own address; a proxy that connects through another of
-  such as `172.17.0.1/32`, when the defaults do not cover it, or to trust
+  the host's addresses is seen with that address. To be sure which address it
-  nothing else (see the login limit and `image_requests_per_minute` under
+  is, set this to `[]` (or `PIXA_TRUSTED_PROXIES` to empty), send a request
-  Routes). For a proxy on the Docker host that connects to pixa over
+  through the proxy, and read `remoteIP` in pixa's request log line for it
-  `127.0.0.1`, that address is the gateway of the container's Docker network
-  (`172.17.0.1` on the default bridge), not the proxy's own address; a proxy
-  that connects through another of the host's addresses is seen with that
-  address. To be sure which address it is, set this to `[]` (or
-  `PIXA_TRUSTED_PROXIES` to empty), send a request through the proxy, and read
-  `remoteIP` in pixa's request log line for it
 - `upstream_fetch_timeout` — time allowed for one fetch from an upstream host,
   as a duration such as `30s` (the default) or `2m`
 - `upstream_max_response_size` — largest upstream response accepted, in bytes;
@@ -768,14 +713,11 @@ Key settings in more detail:
 - `signing_key` — HMAC secret for URL signatures
 - `db_url` — the SQLite database to open; omitted, it is
   `file:<state_dir>/state.sqlite3?_pragma=journal_mode(WAL)`, which keeps the
-  database in WAL mode. `state_dir` is percent-encoded in it, so a `%`, `?` or
+  database in WAL mode. pixa opens one connection to it, so its own reads and
-  `#` in the name is written as `%25`, `%3F` or `%23`. For a `state_dir` of `/`
+  writes run one at a time. pixa adds `_pragma=busy_timeout(5000)` to any
-  or one starting with `//` it starts `file:////`, so SQLite does not read the
+  `db_url`, so a write that finds another program writing to the file waits up
-  first name in the path as a host. pixa opens one connection to it, so its own
+  to five seconds for it instead of failing. WAL mode comes only from the URL:
-  reads and writes run one at a time. pixa adds `_pragma=busy_timeout(5000)` to
+  keep `_pragma=journal_mode(WAL)` in one you set
-  any `db_url`, so a write that finds another program writing to the file waits
-  up to five seconds for it instead of failing. WAL mode comes only from the
-  URL: keep `_pragma=journal_mode(WAL)` in one you set
 - `cache_max_bytes` — disk cache size limit in bytes; `0` disables the disk
   cache entirely; omitted defaults to 75% of the sum of the free space on the
   filesystem containing `<state_dir>/cache/` and the bytes of source and
@@ -812,34 +754,20 @@ See `configs/config.example.yml` for all options with defaults.
 
 ### Architecture
 
-- **Dependency injection**: Uber fx. `internal/app` builds every part of pixad
+- **Dependency injection**: Uber fx
-  from the config in one fx graph. Each setting's default is declared once, in
-  `internal/config`.
 - **HTTP router**: go-chi
 - **Image processing**: govips (CGO wrapper for libvips)
 - **Database**: SQLite via modernc.org/sqlite
 - **Static assets**: embedded via `//go:embed`
-- **Metrics**: Prometheus, at `/metrics`. pixa serves `/metrics` and measures
+- **Metrics**: Prometheus, at `/metrics`: generic HTTP request metrics
-  HTTP requests only when `metrics.username` and `metrics.password` are set.
+  (duration, response size, requests in flight) and the Go runtime and process
-  `/metrics` holds:
+  metrics; requests are measured and `/metrics` is served only when
-    - the duration of HTTP requests
+  `metrics.username` and `metrics.password` are set. A request's `handler` label
-    - the size of HTTP responses
+  is the pattern of the route it matches, such as `/v1/image/*`, never its path.
-    - the HTTP requests in flight
+  Requests that match no route share the label `unmatched`: those the router
-    - the Go runtime and process metrics
+  answers 404 or 405, and CORS preflights. A request's `method` label is its
-    - `pixa_cache_hits_total`: image requests served from the cache
+  method when that is `GET`, `HEAD`, `POST`, `PUT`, `PATCH`, `DELETE`,
-    - `pixa_cache_misses_total`: image requests not served from the cache
+  `OPTIONS`, `CONNECT` or `TRACE`, and `other` for any other method
-    - `pixa_upstream_fetches_total`: fetches of a source image that read any
-      bytes
-    - `pixa_upstream_fetch_bytes_total`: the bytes those fetches read
-    - `pixa_transforms_total`: images converted
-
-    A request's `handler` label is the pattern of the route it matches, such as
-    `/v1/image/*`, never its path. Requests that match no route share the label
-    `unmatched`: those the router answers 404 or 405, and CORS preflights. A
-    request's `method` label is its method when that is `GET`, `HEAD`, `POST`,
-    `PUT`, `PATCH`, `DELETE`, `OPTIONS`, `CONNECT` or `TRACE`, and `other` for
-    any other method.
-
 - **Logging**: stdlib slog
 
 ## Entrypoints
@@ -871,9 +799,6 @@ provide:
 - `script/docker-smoke` — build the image, start it, wait for it to be healthy
 - `script/loadtest` — measure pixad's throughput, latency and peak memory; a
   benchmark, not part of `script/check` (see Load Test)
-- `script/bench` — run the Go benchmark that serves cache hits in parallel
-  through the image handler, with Go on the host after `script/bootstrap --cgo`;
-  a benchmark, not part of `script/check` (see Load Test)
 - `script/cibuild` — CI entrypoint: run `script/bootstrap` (without `--cgo`),
   then `script/check`, then build the image as `script/docker` does
 - `script/precommit` — pre-commit checks (`go mod tidy` guard, then
@@ -882,25 +807,19 @@ provide:
   `script/precommit`
 
 Every `docker build` in these scripts passes a new value of the `CACHEBUST`
-build argument, which every stage of the `Dockerfile` declares, so every `RUN`
+build argument, which every stage of the `Dockerfile` declares first, so every
-step after that line, the lint and test steps included, runs on every build
+`RUN` step, the lint and test phases included, runs on every build instead of
-instead of coming from the build cache. Above the line are the steps that
+coming from the build cache. Go's build cache is kept from build to build: the
-install system packages and download the Go modules; Docker keeps their layers
+steps that compile mount it, so a package whose inputs are unchanged is not
-until the base image, the step itself, `go.mod` or `go.sum` changes. Go's build
+compiled again, and both `go test` runs pass `-count=1` so that no stored test
-cache is kept from build to build: the steps that compile mount it, so a package
+result is replayed. The `test` phase runs on the Debian Go image, with Debian's
-whose inputs are unchanged is not compiled again, and both `go test` runs pass
+libvips and libheif; the image pixa ships is built and runs on Alpine.
-`-count=1` so that no stored test result is replayed. The lint step also mounts
+`script/check`, `script/cibuild`, `script/docker`, `script/lint`, `script/test`,
-golangci-lint's cache, which reuses a package's findings only when its files,
+`script/setup` and `script/install-precommit` are the standard copies from
-those of the packages it imports, `go.mod`, the linters and their settings in
+`sneak/prompts`, kept identical to them. `script/fmt` and `script/fmt-check` are
-`.golangci.yml`, and the golangci-lint version are all unchanged. The `test`
+the standard copies with pixa's `gofmt` step kept before prettier. prettier
-phase runs on the Debian Go image, with Debian's libvips and libheif; the image
+formats the markdown only, not the HTML templates, as it cannot parse a Go
-pixa ships is built and runs on Alpine. `script/check`, `script/cibuild`,
+template action inside a tag.
-`script/docker`, `script/lint`, `script/test`, `script/setup` and
-`script/install-precommit` are the standard copies from `sneak/prompts`, kept
-identical to them. `script/fmt` and `script/fmt-check` are the standard copies
-with pixa's `gofmt` step kept before prettier. prettier formats the markdown
-only, not the HTML templates, as it cannot parse a Go template action inside a
-tag.
 
 ## Load Test
 
@@ -954,17 +873,6 @@ The numbers depend on the machine and on whatever else runs on it. The first
 measurement, made on a shared machine with few clients, is in `TODO.md`; it says
 nothing about the target.
 
-`script/bench` (or `make bench`) measures cache hits alone, without the network
-and with no pixad process: a Go benchmark in `internal/handlers` serves one
-cached image through the `/v1/image/` handler from as many goroutines at once as
-the machine has CPUs, and reports the hits served per second as `hits/s`. Each
-run starts with an empty cache and an empty database, a SQLite file of its own,
-and puts the image in the cache before it measures. The benchmark fails if
-serving the hits ran any statement on the database. Like the load test it is not
-part of `script/check`. It runs Go on the host, as the load test does, and
-compiles pixa there, so it needs the C compiler and libraries that
-`script/bootstrap --cgo` installs, but not Docker.
-
 ## TODO
 
 See [TODO.md](TODO.md) for the full prioritized task list.

REPO_POLICIES.md

@@ -1,6 +1,6 @@
 ---
 title: Repository Policies
-last_modified: 2026-10-18
+last_modified: 2026-10-15
 ---
 
 This document covers repository structure, tooling, and workflow standards. Code
@@ -159,11 +159,8 @@ style conventions are in separate documents:
     one's findings, and a host-global lock in `$TMPDIR` makes concurrent runs
     exit non-zero with `parallel golangci-lint is running` — a status a caller
     cannot tell from real findings. Both have produced wrong verdicts in this
-    org, in both directions. A container has its own `TMPDIR`, so the lock is
+    org, in both directions. A container has its own golangci-lint cache, its
-    out of reach. The lint phase does keep golangci-lint's cache between check
+    own `TMPDIR` and a digest-pinned binary, so neither is reachable.
-    builds (below), but it lints every checkout at `/src`, and a finding is
-    taken from that cache only for the same files, settings and golangci-lint
-    version.
 
 - **Any build that runs checks is given a new `CACHEBUST` value.** Docker
   invalidates a `COPY` layer only when the copied content changes, so on an
@@ -173,21 +170,15 @@ style conventions are in separate documents:
   id, so no two builds share a value, not even the three in one
   `script/cibuild`. `script/lint`, `script/test`, `script/cibuild` and
   `script/docker` are the four, and there is no fifth — `script/check` runs the
-  two gate phases and `script/fmt-check`, and builds no image of its own. In
+  two gate phases and `script/fmt-check`, and builds no image of its own. Every
-  every stage of the `Dockerfile`, `ARG CACHEBUST` comes right after the steps
+  stage of the `Dockerfile` declares `ARG CACHEBUST` as its first line after
-  that install system packages and download Go's modules, or right after `FROM`
+  `FROM`, and a new value reruns every `RUN` step after that line; `COPY` steps
-  in a stage with neither, and every step that lints, tests or compiles comes
+  are compared by content and need nothing. A stage without the `ARG` line is
-  after it. A step that installs anything else as well, such as a
+  served from cache on an unchanged tree, so a repository re-vendors the scripts
-  `script/bootstrap` that also installs node packages, comes after it too. A new
+  and adds the `ARG` lines in one commit. The scripts do not pass `--no-cache`:
-  value reruns every `RUN` step after that line; `COPY` steps are compared by
+  it reruns every step too, but it also empties every cache mount, and Go's
-  content and need nothing. Docker keeps the layers above the line until the
+  build cache, which the canonical Go `Dockerfile` below mounts so that compiled
-  base image, their own lines or the files they copy change. A stage without the
+  packages survive between check builds, would start empty every time. A bare
-  `ARG` line is served from cache on an unchanged tree, so a repository
-  re-vendors the scripts and adds the `ARG` lines in one commit. The scripts do
-  not pass `--no-cache`: it reruns every step too, but it also builds the layers
-  above the line again and empties every cache mount, so Go's build cache and
-  golangci-lint's, which the canonical Go `Dockerfile` below mounts so that they
-  survive between check builds, would start empty every time. A bare
   `docker build .` is not evidence that anything ran: a sub-second build
   reporting success is a cache hit, not a result. Never invalidate by pruning —
   `docker builder prune` and friends destroy a build cache shared with every
@@ -203,25 +194,19 @@ style conventions are in separate documents:
   `Dockerfile`:
 
     ```dockerfile
-    # In every stage ARG CACHEBUST comes right after the steps that install
+    # Every stage declares ARG CACHEBUST first: script/ passes a new value
-    # system packages and download Go's modules, or right after FROM in a
+    # on every build, which reruns every RUN step after it. The steps that
-    # stage with neither, and every step that lints, tests or compiles
+    # compile mount Go's build cache, which survives from build to build.
-    # comes after it. script/ passes a new value on every build, which
-    # reruns every RUN step after it. Docker keeps the layers above it
-    # until the base image, their own lines or go.mod and go.sum change.
-    # The steps that compile mount Go's build cache, and golangci-lint run
-    # also mounts golangci-lint's; both survive from build to build.
 
     # Lint phase
     # golangci/golangci-lint:v2.x.x, YYYY-MM-DD
     FROM golangci/golangci-lint@sha256:... AS lint
+    ARG CACHEBUST
     WORKDIR /src
     COPY go.mod go.sum ./
     RUN go mod download
-    ARG CACHEBUST
     COPY . .
     RUN --mount=type=cache,target=/root/.cache/go-build \
-        --mount=type=cache,target=/root/.cache/golangci-lint \
         golangci-lint run --config .golangci.yml ./...
 
     # Test phase. -race needs cgo and so a C compiler, which the Debian Go
@@ -229,10 +214,10 @@ style conventions are in separate documents:
     # cache also holds test results, which go test would otherwise replay.
     # golang:1.x, YYYY-MM-DD
     FROM golang@sha256:... AS test
+    ARG CACHEBUST
     WORKDIR /src
     COPY go.mod go.sum ./
     RUN go mod download
-    ARG CACHEBUST
     COPY . .
     RUN --mount=type=cache,target=/root/.cache/go-build \
         go test -count=1 -timeout 90s -race -cover ./... || \
@@ -240,19 +225,19 @@ style conventions are in separate documents:
           go test -count=1 -timeout 90s -race -v ./...; exit 1; }
 
     # Build stage. Nothing is wanted from either phase above; the copies
-    # are what make BuildKit build them first, so nothing after them can
+    # are what make BuildKit build them first, so this stage cannot run
-    # run unless lint and test passed.
+    # unless lint and test passed.
     # golang:1.x-alpine, YYYY-MM-DD
     FROM golang@sha256:... AS builder
-    RUN apk add --no-cache git
-    WORKDIR /src
-    COPY go.mod go.sum ./
-    RUN go mod download
     ARG CACHEBUST
     COPY --from=lint /src/go.sum /dev/null
     COPY --from=test /src/go.sum /dev/null
+    RUN apk add --no-cache git
     # A tar-stream context keeps the sender's file owners, which git refuses.
     RUN git config --system --add safe.directory /src
+    WORKDIR /src
+    COPY go.mod go.sum ./
+    RUN go mod download
     COPY . .
 
     # The VERSION build arg when one is given, otherwise
@@ -289,26 +274,16 @@ style conventions are in separate documents:
     - Keep the runtime stage last, and if you add a stage after it, give it the
       same two copies. A plain `docker build .` builds the last stage's chain
       and nothing else.
-    - Check builds keep these, and none of them can hand back a stale result:
+    - Only Go's build cache is mounted (`/root/.cache/go-build`, where Go keeps
-        - The layers above `ARG CACHEBUST`: the system packages and Go's
+      it for root), and only on the steps that compile: `golangci-lint run`,
-          modules. Docker installs the packages again when the base image or the
+      both `go test` runs and `go build`. It keeps compiled packages between
-          install line changes, and downloads the modules again when `go.mod` or
+      check builds, and Go reuses one only when all its inputs are unchanged, so
-          `go.sum` changes. Go checks every module against `go.sum` as it
+      it saves the compile without skipping a check. Nothing else is kept:
-          downloads it, and no later build can change a kept layer. The modules
+      golangci-lint's own cache would replay stored findings in place of a lint
-          are kept in a layer rather than a cache mount because a cache mount is
+      run, and Go builds from whatever files a kept module cache holds without
-          shared by every build on the host, and Go builds from whatever files
+      checking them again (only `go mod verify` does), so a file changed there
-          it holds without checking them again (only `go mod verify` does), so a
+      would go unnoticed. Go's build cache also holds test results, which is why
-          file changed there would go unnoticed.
+      both `go test` runs carry `-count=1`.
-        - Go's build cache (`/root/.cache/go-build`, where Go keeps it for
-          root), mounted on the steps that compile: `golangci-lint run`, both
-          `go test` runs and `go build`. Go reuses a compiled package only when
-          all its inputs are unchanged. The cache also holds test results, which
-          is why both `go test` runs carry `-count=1`.
-        - golangci-lint's cache (`/root/.cache/golangci-lint`, where the pinned
-          image keeps it), mounted on `golangci-lint run`. golangci-lint reuses
-          a package's findings only when the package's files and those of every
-          package it imports, `go.mod`, the linters and their settings in
-          `.golangci.yml`, and the golangci-lint version are all unchanged.
     - If the project uses `//go:embed` directives that reference build artifacts
       (e.g. a web frontend compiled in a separate stage), the lint phase must
       create placeholder files so the embed directives resolve. Example:
@@ -317,20 +292,12 @@ style conventions are in separate documents:
       in the lint phase. The `golangci/golangci-lint` image is Debian-based and
       has no `apk`, so install with `apt-get` under the Debian package name
       (`libvips-dev`, where alpine says `vips-dev`), and delete the package
-      lists in the same `RUN`, so the layer does not keep them. The test phase,
+      lists in the same `RUN`, so the layer does not keep them:
-      on the Debian Go image, installs the libraries its tests need the same
-      way. Either install goes right after `FROM`, above `ARG CACHEBUST`, so
-      Docker keeps it until the base image or the install line changes:
 
         ```dockerfile
-        FROM golangci/golangci-lint@sha256:... AS lint
         RUN apt-get update \
             && apt-get install -y --no-install-recommends libvips-dev \
             && rm -rf /var/lib/apt/lists/*
-        WORKDIR /src
-        COPY go.mod go.sum ./
-        RUN go mod download
-        ARG CACHEBUST
         ```
 
     - `.dockerignore` lets `.git` into the build context. It keeps out every git

TODO.md

@@ -30,212 +30,6 @@ P2: security: per-origin rate limiting
 
 # Completed Steps
 
-- 2026-10-26 pixad's fx graph builds the image pipeline (closes #313).
-  `database.New` now opens the database, so the parts below can read it while
-  they are built; its stop hook still runs after the cache's. The cache's
-  `MaxBytes` is the one value for the disk cache limit, and 0 turns the disk
-  cache off. For an omitted `cache_max_bytes`, `internal/providers` works out
-  `config.DefaultCacheMaxBytes` before it builds the cache. `internal/app` and
-  the server tests build the parts below with `providers.Constructors()`; the
-  image proxy test replaces only the fetcher's dial function.
-    - Built by the providers in `internal/providers`, and given to
-      `handlers.New`:
-        - the cache
-        - the fetcher
-        - the processor
-        - the image service
-        - the session manager
-        - the encrypted URL generator
-    - Removed:
-        - `initImageService` and `handlers.Params.Fetcher`
-        - `CacheConfig.UseDefaultMaxBytes`, `CacheConfig.DisableDiskCache` and
-          `Cache.disabled`
-        - `httpfetcher.DefaultConfig()` and the fetcher's copies of setting
-          defaults
-        - `imageprocessor.DefaultMaxInputBytes`, and the processor's defaults
-          for a zero `MaxInputBytes` or `MaxConcurrentProcessing`
-- 2026-10-26 the code nothing in production called is gone (closes #312). The
-  handlers tests sign their image URLs with `generateSignedURL`, a test helper
-  that writes them as the removed generator did. Removed:
-    - `Service.Warm` and the `ImageCache` interface
-    - `Service.GenerateSignedURL` and `Signer.GenerateSignedURL`
-    - `signature.ParseParams`
-    - `imagerequest.ParseImagePath`
-    - `PeekAndValidate`, `IsSupportedMIMEType`, `ImageFormatToMIME` and
-      `FormatOriginal` of `internal/magic`
-    - `SupportedInputFormats` and `SupportedOutputFormats` of the image
-      processor
-    - `IsEmpty` and `Count` of the allowlist
-    - `ssrfSafeDialer`
-    - `CacheStale`, `ErrCacheMiss`, `ErrNegativeCache` and
-      `ImageResponse.LastModified`
-    - `ContentStorage.Load` and `VariantStorage.Load`
-- 2026-10-26 cache hits, misses, upstream fetches, the bytes those fetches read
-  and transforms are counted as Prometheus counters in memory (closes #311).
-  They are `pixa_cache_hits_total`, `pixa_cache_misses_total`,
-  `pixa_upstream_fetches_total`, `pixa_upstream_fetch_bytes_total` and
-  `pixa_transforms_total`, fields of the cache. `NewCache` makes them and
-  registers them on the registry it is given (`internal/imgcache/counters.go`).
-  pixad gives it Prometheus' default registry, which `/metrics` serves; each
-  test gives it a new one. The `Increment` methods add to their cache's
-  counters. `cache_stats`, `Cache.Stats`, `Service.Stats`, `CacheStats` and the
-  pending counts are gone. The background goroutine writes only access times
-  now: `StartPendingAccessTimeWrites` starts it and
-  `StopPendingAccessTimeWrites` stops it, in `pendingaccesstimes.go`.
-- 2026-10-21 the schema file declares only the tables and columns pixa writes
-  and reads (closes #310): `output_content` and `request_cache` are gone, and so
-  are the columns nothing read: the host, path, query, `content_type` and
-  `fetched_at` of `source_content`, the `content_type` and `created_at` of
-  `variant_content`, and the `status_code`, `error_message` and `fetched_at` of
-  `negative_cache`. `StoreSource` no longer takes the fetch result,
-  `LookupSource` returns only the source key, `StoreVariant` no longer takes a
-  content type, `StoreNegative` no longer takes a status code or message, and
-  reconciliation adopts a variant file without reading its first bytes.
-- 2026-10-21 a cache hit makes no database call (closes #309): `Service.Get`
-  opens the variant file with `Cache.GetVariant` and nothing else, with no
-  existence check first. The content type comes from the file's first bytes; a
-  file whose first bytes are not those of an output format, SVG included, is a
-  miss, and the variant is made again. A hit hands its access time to a channel
-  that holds up to 10,000 and drops the rest, and its hit count to the pending
-  counts, without waiting; every count is now a pending count. A miss that finds
-  a cached source hands that source's access time to a second such channel. The
-  goroutine `StartPendingCountWrites` starts writes, once a second, the access
-  times in one transaction and the counts in one `UPDATE`;
-  `StopPendingCountWrites` writes what is left once at shutdown and logs
-  separately the access times and the counts it could not write.
-  `checkNegativeCache` no longer deletes an expired row; `CleanExpired` in the
-  eviction goroutine does. The `.meta` files, `VariantMeta`, `LoadWithMeta`,
-  `variantContentTypeFromSidecar`, `metaCache`, `Lookup` and `golang-lru` are
-  gone. `make bench` (`script/bench`) runs `BenchmarkHandleImage_CacheHits` with
-  Go on the host after `script/bootstrap --cgo`, outside `make check`.
-- 2026-10-21 a source is stored the way a variant is (closes #308): one
-  `source_content` row and one file per source URL, the file named by the
-  source's `SourceKey`, the SHA-256 of its host, path and query made as the
-  variant key is, under `cache/sources/`. A store writes the file, then the row,
-  and removes the file when the row cannot be written; an eviction deletes the
-  row, then the file, with no lock and no transaction. `source_metadata`, the
-  JSON files under `cache/metadata/`, `MetadataStorage` and the content lock are
-  gone. Two source URLs that serve the same bytes now store them twice.
-- 2026-10-21 one image request type instead of five (closes #307): the new
-  package `internal/imagerequest`, which imports no other package of pixa, holds
-  `imagerequest.Request` with its two parts, `Source` (host, path and query) and
-  `Transform` (size, format, quality and fit), the `Format` and `Fit` types, the
-  checks, the parsing of the `/v1/image/` path and the variant key.
-  `imgcache.ParsedURL`, `imgcache.ImageRequest`, `signature.Request`,
-  `imageprocessor.Request`, the second `Size`, format and fit types and the
-  conversions between them are gone. The image processor takes a `Transform`
-  only, and `encurl` keeps a private struct with the token's short CBOR field
-  names, so tokens made before still decode. Every URL of both image routes
-  answers as before.
-- 2026-10-21 the Gitea workflow checks out the repo and runs `script/cibuild`,
-  nothing else (closes #203): its `script/docker-smoke` step is removed, as the
-  canonical `REPO_POLICIES.md` says, since `make check` covers what CI needs to
-  check. CI no longer starts the image and waits for its healthcheck.
-  `script/docker-smoke` and `make docker-smoke` stay, to run by hand.
-- 2026-10-20 a WebP, AVIF or JPEG XL encode at the limits takes at most about 34
-  seconds (closes #272): with one libvips thread, 8192x8192 random pixels with
-  an alpha channel took about 61 seconds to encode as WebP, 81 as JPEG XL and,
-  at quality 85, 96 as AVIF, so with the default `downstream_timeout` of 60
-  seconds such an image was never delivered, yet its encode held a processing
-  slot to the end. WebP is now saved at effort 2 and JPEG XL at effort 4, which
-  take up to about 23 and 27 seconds at any quality. AVIF was already at the
-  lowest effort govips can set, so an AVIF output of more than 16,777,216 pixels
-  is refused with 400 before anything is decoded; 4096x4096, 8192x2048 or
-  2048x8192 takes up to about 34 seconds at any quality. Resizing with
-  `fit=cover` already decodes the input, so the output's dimensions are worked
-  out before resizing. `README.md` gives the limit and the new times.
-- 2026-10-20 a source whose first bytes do not match its `Content-Type` answers
-  415 (closes #253): a body whose first bytes are not those of the format its
-  `Content-Type` names, such as a JPEG sent as `image/png`, text, or a body
-  under 12 bytes, answered 500 on both image routes and was logged as an error
-  of pixa's, and each request for it fetched the whole body again. Both routes
-  now answer 415, and the image service logs it at warning level as a refused
-  source. It also gets a negative cache entry, as an upstream error status does,
-  so the source URL is not fetched again for 5 minutes, and meanwhile an image
-  that would need that fetch answers 502.
-- 2026-10-20 `AGENTS.md`: a bug fix may change an existing test without asking
-  when that test pins exactly the behavior the filed bug calls wrong, and the
-  change moves it to the fixed behavior and nothing else (closes #280).
-- 2026-10-18 re-vendored from `sneak/prompts` commit `0653579` (closes #221):
-  each `Dockerfile` stage installs its system packages and downloads the Go
-  modules above `ARG CACHEBUST`, so check builds keep them, and the lint step
-  keeps golangci-lint's cache.
-- 2026-10-19 a `trusted_proxies` entry in the IPv4-mapped form trusted nothing;
-  it is now read as the IPv4 range it covers by the same code that reads
-  `blocked_networks`, and such an entry shorter than `/96` aborts startup
-  (closes #303).
-- 2026-10-18 the next reconciliation pass waits at least ten times as long as
-  the last one took, so passes on a large cache no longer run back to back
-  (closes #250).
-- 2026-10-18 a `blocked_networks` entry in the IPv4-mapped form refused nothing;
-  `::ffff:10.0.0.0/104` is now read as `10.0.0.0/8`, and such an entry shorter
-  than `/96` aborts startup (closes #301).
-- 2026-10-16 P1 security bug: the check that keeps pixa from fetching internal
-  addresses refuses the local-use NAT64 range (`64:ff9b:1::/48`, RFC 8215) as it
-  refuses `64:ff9b::/96`, and refuses an IPv6 address in the IPv4-compatible
-  form (`::/96`) when `blocked_networks` contains either the address as written
-  or the IPv4 address it holds (closes #299). A source host such as
-  `[64:ff9b:1::a00:1]` was fetched, which on a network that runs NAT64 on that
-  range reaches the IPv4 address it holds, here `10.0.0.1`; and with
-  `203.0.113.0/24` in `blocked_networks`, `[::ffff:203.0.113.5]` was refused but
-  `[::203.0.113.5]` was fetched. Both now answer 403. The mapped form
-  (`::ffff:a.b.c.d`) is still matched only as the IPv4 address it holds: Go
-  keeps a plain IPv4 address in that form, and an IPv6 entry such as `::/0` must
-  not refuse every IPv4 address.
-- 2026-10-16 P1 security bug: the check that keeps pixa from fetching internal
-  addresses judges an IPv6 address in the IPv4-compatible form (`::/96`), such
-  as `::127.0.0.1` or `::10.0.0.1`, by the IPv4 address in its last four bytes
-  (closes #297). It read only the mapped form (`::ffff:a.b.c.d`) as IPv4, so a
-  source host such as `[::127.0.0.1]` was checked as a public IPv6 address and
-  fetched, which on a network that routes it reaches the internal IPv4 host; it
-  is now refused with 403. The NAT64 form (`64:ff9b::/96`) was already refused
-  as a whole, as one of the built-in blocked ranges, and still is.
-- 2026-10-16 a source host that is an IPv6 address in brackets with no port,
-  such as `[2001:db8::a]`, is fetched like one with a port, through `/v1/image/`
-  and through an encrypted URL (closes #295). The fetcher's check of the source
-  URL kept the brackets when no port followed them, could not look the host up,
-  and the request answered 500. It now checks the address without brackets, so a
-  private one is refused with 403, as with a port.
-- 2026-10-16 a `state_dir` whose name holds `%`, `?` or `#` keeps its database
-  at `state.sqlite3` in that directory (closes #290): the `db_url` derived from
-  it put the name into a `file:` URL as it was, so SQLite read `%41` as `A`, a
-  `?` or `#` ended the path early, and the journal mode parameter was lost. The
-  derived `db_url` is now built with Go's `net/url`, which writes those
-  characters as `%25`, `%3F` and `%23`. For a `state_dir` of `/` or one starting
-  with `//` it starts `file:////`, so SQLite no longer reads the first name in
-  the path as a host.
-- 2026-10-16 a size with one side `0` keeps the side computed from the source's
-  proportions at 1 or more (closes #283): it was rounded down, so for a thin
-  source it came out at 0, and libvips then made the size square. An 8192x1
-  source at `100x0` came out at 100x100, and at `1300x0` with `fit=cover` made
-  libvips ask for about 39 GB at once; an 8192x2 source at `100x0` answered 500.
-  `fit=contain` and `fit=inside` work both sides out again from the smaller of
-  the two scales and `fit=outside` from the larger, and each keeps both sides at
-  1 or more too, so a 1x8192 source at `0x100` with `fit=contain`, and a 49x8192
-  source at `0x100` or a 49x49 source at `1x1` with `fit=outside`, no longer
-  answer 500. An 8192x1 source at `1300x0` now comes out at 1300x1, and the
-  process running it alone peaked at about 34 MiB resident. With `fit=outside`
-  the image is scaled to cover the size, so that source at `100x0` comes out at
-  8192x1. `README.md` now says this under Signature Specification, and says how
-  a `0` side is worked out where it said `0` meant the original.
-- 2026-10-16 the generator page lower-cases the source host and writes an empty
-  source path as `/` before it makes the encrypted URL, as `/v1/image/` does
-  (closes #293). A host written in upper and in lower case, or a source URL with
-  no path and with the path `/`, made two cache keys and two upstream requests
-  for one image.
-- 2026-10-16 the source URL a request fetches is built with `net/url` from the
-  source host, path and query, not joined as text (closes #288). The source
-  path, decoded, is fetched percent-encoded again, so `100%25.png` fetches
-  `/100%25.png` where it answered 401, and `my%20cat.png` and `my%2520cat.png`
-  fetch different paths where both fetched `/my%20cat.png` under two cache keys.
-  The source query stays as the source URL writes it; the characters a browser
-  percent-encodes in a query, such as `'` or a space, which was sent raw and
-  answered 502, are percent-encoded when the image URL is read, so the query is
-  signed and cached as it is sent. The generator page answers 400, showing the
-  URL pixa would fetch, for a source URL its image URL would fetch written
-  another way, such as with `%2F` in the path, whatever else the path holds, or
-  with a user name and password. It also answers 400 for a source path holding a
-  `..` segment, as `/v1/image/` refuses one.
 - 2026-10-15 a thin source requested with `fit=cover` no longer makes libvips
   build a huge image (closes #282): libvips' thumbnail scaled the whole source
   to cover the requested size and copied that into memory before it cut out the
@@ -248,6 +42,17 @@ P2: security: per-origin rate limiting
   resident memory peaked at about 242 MiB for the 8192x64 source and 431 MiB for
   the 8192x1 one. The output can sit a fraction of an output pixel from where it
   was.
+- 2026-10-16 the source URL a request fetches is built with `net/url` from the
+  source host, path and query, not joined as text (closes #288). The source
+  path, decoded, is fetched percent-encoded again, so `100%25.png` fetches
+  `/100%25.png` where it answered 401, and `my%20cat.png` and `my%2520cat.png`
+  fetch different paths where both fetched `/my%20cat.png` under two cache keys.
+  The source query stays as the source URL writes it; the characters a browser
+  percent-encodes in a query, such as a space, which was sent raw and answered
+  502, are percent-encoded when the image URL is read, so the query is signed
+  and cached as it is sent. The generator page answers 400, showing the URL pixa
+  would fetch, for a source URL its image URL would fetch written another way,
+  such as with `%2F` in the path.
 - 2026-10-15 a `/v1/image/` URL whose source path or source query holds a `#`,
   written as `%23`, is refused with 400 (closes #286): the source URL built from
   it ended at the `#` when fetched, so each text after it fetched the same

go.mod

@@ -14,6 +14,7 @@ require (
 	github.com/go-chi/httprate v0.16.0
 	github.com/gorilla/csrf v1.7.3
 	github.com/gorilla/securecookie v1.1.2
+	github.com/hashicorp/golang-lru/v2 v2.0.7
 	github.com/prometheus/client_golang v1.23.2
 	github.com/slok/go-http-metrics v0.13.0
 	github.com/spf13/cobra v1.10.2

go.sum

@@ -228,6 +228,8 @@ github.com/hashicorp/go-version v1.2.1/go.mod h1:fltr4n8CU8Ke44wwGCBoEymUuxUHl09
 github.com/hashicorp/golang-lru v0.5.0/go.mod h1:/m3WP610KZHVQ1SGc6re/UDhFvYD7pJ4Ao+sR/qLZy8=
 github.com/hashicorp/golang-lru v0.5.4 h1:YDjusn29QI/Das2iO9M0BHnIbxPeyuCHsjMW+lJfyTc=
 github.com/hashicorp/golang-lru v0.5.4/go.mod h1:iADmTwqILo4mZ8BN3D2Q6+9jd8WM5uGBxy+E8yxSoD4=
+github.com/hashicorp/golang-lru/v2 v2.0.7 h1:a+bsQ5rvGLjzHuww6tVxozPZFVghXaHOwFs4luLUK2k=
+github.com/hashicorp/golang-lru/v2 v2.0.7/go.mod h1:QeFd9opnmA6QUJc5vARoKUSoFhyfM2/ZepoAG6RGpeM=
 github.com/hashicorp/hcl v1.0.1-vault-7 h1:ag5OxFVy3QYTFTJODRzTKVZ6xvdfLLCA1cy/Y6xGI0I=
 github.com/hashicorp/hcl v1.0.1-vault-7/go.mod h1:XYhtn6ijBSAj6n4YqAaf7RBPS4I06AItNorpy+MoQNM=
 github.com/hashicorp/logutils v1.0.0/go.mod h1:QIAnNjmIWmVIIkWDTG1z5v++HQmx9WQRO+LraFDTW64=

internal/allowlist/allowlist.go

@@ -72,3 +72,13 @@ func (w *HostAllowList) IsAllowed(u *url.URL) bool {
 
 	return false
 }
+
+// IsEmpty returns true if the allow list has no entries.
+func (w *HostAllowList) IsEmpty() bool {
+	return len(w.exactHosts) == 0 && len(w.suffixHosts) == 0
+}
+
+// Count returns the total number of allow list entries.
+func (w *HostAllowList) Count() int {
+	return len(w.exactHosts) + len(w.suffixHosts)
+}

internal/allowlist/allowlist_test.go

@@ -139,3 +139,87 @@ func TestHostAllowList_IsAllowed_SuffixMatch(t *testing.T) {
 		},
 	})
 }
+
+func TestHostAllowList_IsEmpty(t *testing.T) {
+	t.Parallel()
+
+	tests := []struct {
+		name     string
+		patterns []string
+		want     bool
+	}{
+		{
+			name:     "empty",
+			patterns: []string{},
+			want:     true,
+		},
+		{
+			name:     "nil",
+			patterns: nil,
+			want:     true,
+		},
+		{
+			name:     "whitespace only",
+			patterns: []string{"  ", ""},
+			want:     true,
+		},
+		{
+			name:     "has entries",
+			patterns: []string{"example.com"},
+			want:     false,
+		},
+	}
+
+	for _, tt := range tests {
+		t.Run(tt.name, func(t *testing.T) {
+			t.Parallel()
+
+			w := allowlist.New(tt.patterns)
+			if got := w.IsEmpty(); got != tt.want {
+				t.Errorf("IsEmpty() = %v, want %v", got, tt.want)
+			}
+		})
+	}
+}
+
+func TestHostAllowList_Count(t *testing.T) {
+	t.Parallel()
+
+	tests := []struct {
+		name     string
+		patterns []string
+		want     int
+	}{
+		{
+			name:     "empty",
+			patterns: []string{},
+			want:     0,
+		},
+		{
+			name:     "exact hosts only",
+			patterns: []string{"a.com", "b.com", "c.com"},
+			want:     3,
+		},
+		{
+			name:     "suffix hosts only",
+			patterns: []string{".a.com", ".b.com"},
+			want:     2,
+		},
+		{
+			name:     "mixed",
+			patterns: []string{"exact.com", ".suffix.com"},
+			want:     2,
+		},
+	}
+
+	for _, tt := range tests {
+		t.Run(tt.name, func(t *testing.T) {
+			t.Parallel()
+
+			w := allowlist.New(tt.patterns)
+			if got := w.Count(); got != tt.want {
+				t.Errorf("Count() = %v, want %v", got, tt.want)
+			}
+		})
+	}
+}

internal/app/app.go

@@ -7,7 +7,6 @@ import (
 	"os/signal"
 	"syscall"
 
-	"github.com/prometheus/client_golang/prometheus"
 	"github.com/spf13/cobra"
 	"go.uber.org/fx"
 	"sneak.berlin/go/pixa/internal/config"
@@ -17,7 +16,6 @@ import (
 	"sneak.berlin/go/pixa/internal/healthcheck"
 	"sneak.berlin/go/pixa/internal/logger"
 	"sneak.berlin/go/pixa/internal/middleware"
-	"sneak.berlin/go/pixa/internal/providers"
 	"sneak.berlin/go/pixa/internal/server"
 )
 
@@ -63,10 +61,7 @@ func run(_ *cobra.Command, _ []string) {
 			server.New,
 			middleware.New,
 			healthcheck.New,
-			// The registry /metrics serves
-			func() prometheus.Registerer { return prometheus.DefaultRegisterer },
 		),
-		fx.Provide(providers.Constructors()...),
 		fx.Invoke(
 			func(log *logger.Logger) { log.Identify() },
 			func(*server.Server) {},

internal/config/blocked_networks_internal_test.go

@@ -88,56 +88,3 @@ func TestBlockedNetworksInvalidAbortsStartup(t *testing.T) {
 		},
 	})
 }
-
-// TestBlockedNetworksMappedEntryIsIPv4Range checks that an entry written in
-// the IPv4-mapped form (::ffff:a.b.c.d) is kept as the IPv4 range it covers,
-// since the fetcher matches an IPv4-mapped address as the IPv4 address it
-// holds. /96, the shortest such entry, covers every IPv4 address.
-func TestBlockedNetworksMappedEntryIsIPv4Range(t *testing.T) {
-	t.Parallel()
-
-	yamlContent := signingKeyLine + `blocked_networks:
-  - "::ffff:10.0.0.0/104"
-  - "::ffff:0:0/96"
-`
-
-	c, err := configFromYAML(t, yamlContent)
-	if err != nil {
-		t.Fatalf("IPv4-mapped blocked_networks entries should load, got error: %v", err)
-	}
-
-	want := []string{"10.0.0.0/8", "0.0.0.0/0"}
-	if len(c.BlockedNetworks) != len(want) {
-		t.Fatalf("BlockedNetworks = %v, want %d entries", c.BlockedNetworks, len(want))
-	}
-
-	for i, w := range want {
-		if got := c.BlockedNetworks[i].String(); got != w {
-			t.Errorf("BlockedNetworks[%d] = %q, want %q", i, got, w)
-		}
-	}
-}
-
-// TestBlockedNetworksMappedEntryShorterThan96AbortsStartup checks that an
-// entry in the IPv4-mapped form shorter than /96, which covers more than the
-// IPv4 addresses, aborts startup with an error naming the key and the value.
-func TestBlockedNetworksMappedEntryShorterThan96AbortsStartup(t *testing.T) {
-	t.Parallel()
-
-	runAbortCases(t, []abortCase{
-		{
-			name: "mapped-shorter-than-96",
-			yaml: signingKeyLine + `blocked_networks:
-  - "::ffff:0.0.0.0/80"
-`,
-			wantErrSubstrings: []string{keyBlockedNetworks, "::ffff:0.0.0.0/80"},
-		},
-		{
-			name: "mapped-95",
-			yaml: signingKeyLine + `blocked_networks:
-  - "::ffff:0:0/95"
-`,
-			wantErrSubstrings: []string{keyBlockedNetworks},
-		},
-	})
-}

internal/config/cache_max_bytes_internal_test.go

@@ -135,38 +135,10 @@ func TestCacheMaxBytesInvalidValuesAbortStartup(t *testing.T) {
 	}
 }
 
-// TestDefaultCacheMaxBytesAppliesFloor verifies that when 75% of the
-// free space plus what the cache holds is below 500 MiB, the default is
-// floored at DefaultCacheMaxBytesFloor.
-func TestDefaultCacheMaxBytesAppliesFloor(t *testing.T) {
-	t.Parallel()
-
-	cases := []struct {
-		name      string
-		freeBytes uint64
-	}{
-		{name: "100 MiB free", freeBytes: 104857600},
-		{name: "zero free", freeBytes: 0},
-		{name: "just below floor threshold", freeBytes: 699050665},
-	}
-
-	for _, tc := range cases {
-		t.Run(tc.name, func(t *testing.T) {
-			t.Parallel()
-
-			got := DefaultCacheMaxBytes(tc.freeBytes, 0)
-			if got != DefaultCacheMaxBytesFloor {
-				t.Errorf("DefaultCacheMaxBytes = %d, want floor %d",
-					got, DefaultCacheMaxBytesFloor)
-			}
-		})
-	}
-}
-
 // TestCacheMaxBytesExplicitIsRecorded verifies that an omitted
-// cache_max_bytes is recorded as not explicit, so pixad works out the
+// cache_max_bytes is recorded as not explicit, so the cache works out
-// default when it builds the cache, and that an explicit zero is recorded
+// the default when it opens, and that an explicit zero is recorded as
-// as explicit, so it disables the disk cache instead.
+// explicit, so it disables the disk cache instead.
 func TestCacheMaxBytesExplicitIsRecorded(t *testing.T) {
 	t.Parallel()
 

internal/config/config.go

@@ -45,37 +45,6 @@ func DefaultMaxConcurrentProcessing() int {
 	return max(runtime.GOMAXPROCS(0)/2, 1) //nolint:mnd // half the CPUs
 }
 
-// DefaultCacheMaxBytesFloor is the least DefaultCacheMaxBytes returns:
-// 500 MiB. It applies only to the default, never to an explicit
-// cache_max_bytes.
-const DefaultCacheMaxBytesFloor int64 = 500 << 20
-
-// freeSpaceFractionNumerator and freeSpaceFractionDenominator express
-// the 75% share of DefaultCacheMaxBytes as integer arithmetic (dividing
-// before multiplying avoids overflow).
-const (
-	freeSpaceFractionNumerator   uint64 = 3
-	freeSpaceFractionDenominator uint64 = 4
-)
-
-// DefaultCacheMaxBytes returns the disk cache limit when cache_max_bytes
-// is omitted: 75% of the sum of freeBytes, the space free on the
-// filesystem holding the cache, and heldBytes, the bytes the cache
-// already holds, and at least DefaultCacheMaxBytesFloor. Counting what
-// the cache holds keeps the limit from shrinking as the cache fills.
-// pixad works it out when it builds the cache, as both numbers are known
-// only then.
-func DefaultCacheMaxBytes(freeBytes uint64, heldBytes int64) int64 {
-	// Both terms are at most math.MaxInt64, so the sum cannot overflow.
-	//nolint:gosec // G115: heldBytes is the cache's total, never negative
-	spaceBytes := min(freeBytes, math.MaxInt64) + uint64(heldBytes)
-
-	computed := spaceBytes / freeSpaceFractionDenominator * freeSpaceFractionNumerator
-	computed = min(computed, math.MaxInt64)
-
-	return max(int64(computed), DefaultCacheMaxBytesFloor)
-}
-
 // Configuration key names.
 const (
 	keyDebug                      = "debug"
@@ -122,7 +91,6 @@ var (
 	errNotABoolean       = errors.New("not a boolean")
 	errNotAStringList    = errors.New("not a list of strings")
 	errNotAValidCIDR     = errors.New("not a valid CIDR network")
-	errMappedTooShort    = errors.New("in the IPv4-mapped form but shorter than /96")
 	errNotAMetricsMap    = errors.New("not a map of metrics settings")
 	errEmptyListEntry    = errors.New("list contains an empty entry")
 	errEmptyEntry        = errors.New("contains an empty entry")
@@ -221,14 +189,18 @@ type Config struct {
 	// address, and an explicit list replaces the default.
 	TrustedProxies []netip.Prefix
 
-	// CacheMaxBytes is the disk cache size limit in bytes, as set; 0
+	// CacheMaxBytes is the disk cache size limit in bytes. Only an
-	// turns the disk cache off.
+	// explicit zero (CacheMaxBytesExplicit true) disables the disk
+	// cache. Zero with CacheMaxBytesExplicit false means
+	// cache_max_bytes was omitted, and the cache works out the default
+	// limit when it opens.
 	CacheMaxBytes int64
 
 	// CacheMaxBytesExplicit records whether cache_max_bytes was
 	// explicitly set, in the environment or the configuration file.
-	// Explicit values are used exactly as given. For an omitted key
+	// Explicit values are used exactly as given; for an omitted key the
-	// pixad works out DefaultCacheMaxBytes when it builds the cache.
+	// cache works out the default limit when it opens (see
+	// imgcache.CacheConfig.UseDefaultMaxBytes).
 	CacheMaxBytesExplicit bool
 }
 
@@ -266,8 +238,8 @@ func New(_ fx.Lifecycle, params Params) (*Config, error) {
 		return nil, err
 	}
 
-	// An omitted cache_max_bytes is worked out and logged when pixad
+	// An omitted cache_max_bytes is worked out and logged when the
-	// builds the cache.
+	// cache opens.
 	if c.CacheMaxBytesExplicit {
 		log.Info("effective cache size limit",
 			"cache_max_bytes", c.CacheMaxBytes,
@@ -352,8 +324,8 @@ func newFromSmartConfig(sc *smartconfig.Config) (*Config, error) {
 	}
 
 	// The default for an omitted cache_max_bytes is worked out when
-	// pixad builds the cache; here we only record whether the operator
+	// the cache opens; here we only record whether the operator set
-	// set the key explicitly.
+	// the key explicitly.
 	_, c.CacheMaxBytesExplicit = lookupValue(sc, keyCacheMaxBytes)
 
 	// Build DBURL from StateDir if not explicitly set. The derived URL
@@ -366,7 +338,8 @@ func newFromSmartConfig(sc *smartconfig.Config) (*Config, error) {
 				settingName(keyDBURL), errValueEmpty)
 		}
 
-		c.DBURL = defaultDBURL(c.StateDir)
+		// The driver sets the journal mode only through a _pragma parameter.
+		c.DBURL = fmt.Sprintf("file:%s/state.sqlite3?_pragma=journal_mode(WAL)", c.StateDir)
 	}
 
 	if loader.err != nil {
@@ -381,30 +354,6 @@ func newFromSmartConfig(sc *smartconfig.Config) (*Config, error) {
 	return c, nil
 }
 
-// defaultDBURL returns the db_url used when db_url is omitted: the file
-// state.sqlite3 in stateDir, in WAL mode, which the driver sets only
-// through a _pragma parameter. String() percent-encodes any %, ? or # in
-// the directory name, which SQLite decodes back, so the URL names exactly
-// this file. OmitHost writes file:/var/lib/pixa/... instead of
-// file:///var/lib/pixa/..., and keeps a relative stateDir from being read
-// as a host name. The path written into the URL is stateDir followed by
-// /state.sqlite3; when it starts with //, as it does for a stateDir of /
-// or one starting with //, the empty host is kept, so the URL starts
-// file://// and SQLite does not read the first name in the path as a
-// host.
-func defaultDBURL(stateDir string) string {
-	dbPath := stateDir + "/state.sqlite3"
-
-	dbURL := url.URL{
-		Scheme:   "file",
-		OmitHost: !strings.HasPrefix(dbPath, "//"),
-		Path:     dbPath,
-		RawQuery: "_pragma=journal_mode(WAL)",
-	}
-
-	return dbURL.String()
-}
-
 // validateKnownKeys rejects configuration files containing keys the
 // application does not understand, so typos fail at startup instead of
 // being silently ignored, and rejects keys that are explicitly set to
@@ -1276,13 +1225,6 @@ func defaultTrustedProxies() []netip.Prefix {
 // wrong type, an empty entry, a non-string entry, or an unparseable CIDR
 // aborts startup naming the key and the offending value; the default
 // (an empty list) applies only to an omitted key.
-//
-// An entry written in the IPv4-mapped form (::ffff:a.b.c.d) is kept as the
-// IPv4 range it covers: ::ffff:10.0.0.0/104 is kept as 10.0.0.0/8. Both
-// blocked_networks and trusted_proxies are matched against an IPv4-mapped
-// address as the IPv4 address it holds, so the entry as written would match
-// nothing. Such an entry shorter than /96 covers more than the IPv4
-// addresses and aborts startup.
 func parseCIDRList(sc *smartconfig.Config, key string) ([]netip.Prefix, error) {
 	raw, ok := lookupValue(sc, key)
 	if !ok {
@@ -1298,10 +1240,6 @@ func parseCIDRList(sc *smartconfig.Config, key string) ([]netip.Prefix, error) {
 		return nil, err
 	}
 
-	// An IPv4-mapped address is the 96 bits of ::ffff:0:0/96 followed by
-	// the 32 bits of the IPv4 address it holds.
-	const mappedPrefixBits = 96
-
 	prefixes := make([]netip.Prefix, 0, len(entries))
 
 	for _, entry := range entries {
@@ -1311,16 +1249,6 @@ func parseCIDRList(sc *smartconfig.Config, key string) ([]netip.Prefix, error) {
 				settingName(key), entry, errNotAValidCIDR)
 		}
 
-		if prefix.Addr().Is4In6() && prefix.Bits() < mappedPrefixBits {
-			return nil, fmt.Errorf("%s: value %q is %w",
-				settingName(key), entry, errMappedTooShort)
-		}
-
-		if prefix.Addr().Is4In6() {
-			prefix = netip.PrefixFrom(prefix.Addr().Unmap(),
-				prefix.Bits()-mappedPrefixBits)
-		}
-
 		prefixes = append(prefixes, prefix)
 	}
 

internal/config/config_validation_internal_test.go

@@ -135,104 +135,6 @@ func TestDefaultDBURLOpensTheDatabaseInWALMode(t *testing.T) {
 	}
 }
 
-// TestDerivedDBURLOpensStateDirHoldingURLCharacters opens the db_url
-// derived from a state_dir whose name holds %41, ? and #, and checks that
-// the database is state.sqlite3 in that directory, in WAL mode. Put into
-// a file: URL as it is, the name would lose its meaning: %41 is read as
-// A, and the path ends at the ?, which also loses the journal mode.
-func TestDerivedDBURLOpensStateDirHoldingURLCharacters(t *testing.T) {
-	t.Parallel()
-
-	stateDir := filepath.Join(t.TempDir(), "a%41b?c#d")
-
-	err := os.Mkdir(stateDir, 0o750)
-	if err != nil {
-		t.Fatalf("failed to create %q: %v", stateDir, err)
-	}
-
-	// Quoted so YAML takes the whole name as it is.
-	c, err := configFromYAML(t, signingKeyLine+"state_dir: '"+stateDir+"'\n")
-	if err != nil {
-		t.Fatalf("config with state_dir %q should be valid, got: %v", stateDir, err)
-	}
-
-	t.Logf("state_dir %q gives db_url %q", stateDir, c.DBURL)
-
-	checkDBURLOpensFileInWALMode(t, c.DBURL, filepath.Join(stateDir, "state.sqlite3"))
-}
-
-// TestDerivedDBURLOpensStateDirStartingWithTwoSlashes opens the db_url
-// derived from a state_dir that starts with //, and checks that the
-// database is state.sqlite3 in that directory, in WAL mode. Written right
-// after file:, such a name gives a URL starting file://, and SQLite reads
-// the first directory name as a host and refuses to open it.
-func TestDerivedDBURLOpensStateDirStartingWithTwoSlashes(t *testing.T) {
-	t.Parallel()
-
-	dir := t.TempDir()
-	stateDir := "/" + dir
-
-	c, err := configFromYAML(t, signingKeyLine+"state_dir: "+stateDir+"\n")
-	if err != nil {
-		t.Fatalf("config with state_dir %q should be valid, got: %v", stateDir, err)
-	}
-
-	t.Logf("state_dir %q gives db_url %q", stateDir, c.DBURL)
-
-	checkDBURLOpensFileInWALMode(t, c.DBURL, filepath.Join(dir, "state.sqlite3"))
-}
-
-// TestDerivedDBURLForRootStateDir checks the db_url derived from a
-// state_dir of /. The path written into the URL is then
-// //state.sqlite3, and written right after file: it gives a URL starting
-// file://, where SQLite reads state.sqlite3 as a host and refuses to open
-// it. The test only checks the URL, since it cannot write to /.
-func TestDerivedDBURLForRootStateDir(t *testing.T) {
-	t.Parallel()
-
-	c, err := configFromYAML(t, signingKeyLine+"state_dir: /\n")
-	if err != nil {
-		t.Fatalf("config with state_dir / should be valid, got: %v", err)
-	}
-
-	t.Logf("state_dir / gives db_url %q", c.DBURL)
-
-	wantDBURL := "file:////state.sqlite3?_pragma=journal_mode(WAL)"
-	if c.DBURL != wantDBURL {
-		t.Errorf("DBURL = %q, want %q", c.DBURL, wantDBURL)
-	}
-}
-
-// checkDBURLOpensFileInWALMode opens dbURL with the SQLite driver pixad
-// uses, and checks that the database is in WAL mode and is the file
-// dbFile.
-func checkDBURLOpensFileInWALMode(t *testing.T, dbURL, dbFile string) {
-	t.Helper()
-
-	db, err := sql.Open("sqlite", dbURL)
-	if err != nil {
-		t.Fatalf("failed to open %q: %v", dbURL, err)
-	}
-
-	t.Cleanup(func() { _ = db.Close() })
-
-	var journalMode string
-
-	err = db.QueryRowContext(t.Context(), "PRAGMA journal_mode").Scan(&journalMode)
-	if err != nil {
-		t.Fatalf("failed to read the journal mode of %q: %v", dbURL, err)
-	}
-
-	if journalMode != "wal" {
-		t.Errorf("journal mode of %q = %q, want wal", dbURL, journalMode)
-	}
-
-	_, err = os.Stat(dbFile)
-	if err != nil {
-		t.Errorf("opening %q did not create %q: %v", dbURL, dbFile, err)
-	}
-}
-
 func TestExplicitValidValuesAreUsed(t *testing.T) {
 	t.Parallel()
 

internal/config/trusted_proxies_internal_test.go

@@ -83,41 +83,3 @@ func TestTrustedProxiesInvalidAbortsStartup(t *testing.T) {
 		},
 	})
 }
-
-// TestTrustedProxiesMappedEntryIsIPv4Range checks that an entry written in
-// the IPv4-mapped form (::ffff:a.b.c.d) is kept as the IPv4 range it covers,
-// since the client address is matched as the IPv4 address it holds. /96, the
-// shortest such entry, covers every IPv4 address.
-func TestTrustedProxiesMappedEntryIsIPv4Range(t *testing.T) {
-	t.Parallel()
-
-	c, err := configFromYAML(t, signingKeyLine+
-		`trusted_proxies: ["::ffff:10.0.0.0/104", "::ffff:0:0/96"]`+"\n")
-	if err != nil {
-		t.Fatalf("IPv4-mapped trusted_proxies entries should load: %v", err)
-	}
-
-	got := make([]string, len(c.TrustedProxies))
-	for i, p := range c.TrustedProxies {
-		got[i] = p.String()
-	}
-
-	if joined := strings.Join(got, ","); joined != "10.0.0.0/8,0.0.0.0/0" {
-		t.Errorf("TrustedProxies = %v, want 10.0.0.0/8 and 0.0.0.0/0", got)
-	}
-}
-
-// TestTrustedProxiesMappedEntryShorterThan96AbortsStartup checks that an
-// entry in the IPv4-mapped form shorter than /96, which covers more than the
-// IPv4 addresses, aborts startup with an error naming the key and the value.
-func TestTrustedProxiesMappedEntryShorterThan96AbortsStartup(t *testing.T) {
-	t.Parallel()
-
-	runAbortCases(t, []abortCase{
-		{
-			name:              "mapped-95",
-			yaml:              signingKeyLine + `trusted_proxies: ["::ffff:0:0/95"]` + "\n",
-			wantErrSubstrings: []string{keyTrustedProxies, "::ffff:0:0/95"},
-		},
-	})
-}

internal/database/concurrent_writes_internal_test.go

@@ -104,31 +104,40 @@ func writeConcurrently(t *testing.T, db *sql.DB) {
 
 	wg.Wait()
 
-	var sources int
+	var hits, sources int
 
-	err := db.QueryRowContext(ctx, `SELECT COUNT(*) FROM source_content`).
+	err := db.QueryRowContext(ctx, `
-		Scan(&sources)
+		SELECT hit_count, (SELECT COUNT(*) FROM source_content)
+		FROM cache_stats WHERE id = 1
+	`).Scan(&hits, &sources)
 	if err != nil {
 		t.Fatalf("failed to count the writes: %v", err)
 	}
 
-	if sources != totalRequests {
+	if hits != totalRequests || sources != totalRequests {
-		t.Errorf("%d source_content rows, want %d", sources, totalRequests)
+		t.Errorf("hit_count = %d and %d source_content rows, want %d of each",
+			hits, sources, totalRequests)
 	}
 }
 
 // writeLikeOneRequest makes the writes one request and the eviction pass
-// make: it stores a source, records a transformed image and deletes that
+// make: it counts a cache hit, stores a source, records a transformed image
-// record again.
+// and deletes that record again.
 func writeLikeOneRequest(ctx context.Context, db *sql.DB, key string) error {
-	_, err := db.ExecContext(ctx, `INSERT INTO source_content
+	_, err := db.ExecContext(ctx,
-		(source_key, size_bytes) VALUES (?, 1)`, key)
+		`UPDATE cache_stats SET hit_count = hit_count + 1 WHERE id = 1`)
+	if err != nil {
+		return fmt.Errorf("counting a cache hit: %w", err)
+	}
+
+	_, err = db.ExecContext(ctx, `INSERT INTO source_content
+		(content_hash, content_type, size_bytes) VALUES (?, 'image/png', 1)`, key)
 	if err != nil {
 		return fmt.Errorf("storing a source: %w", err)
 	}
 
 	_, err = db.ExecContext(ctx, `INSERT INTO variant_content
-		(cache_key, size_bytes) VALUES (?, 1)`, key)
+		(cache_key, size_bytes, content_type) VALUES (?, 1, 'image/png')`, key)
 	if err != nil {
 		return fmt.Errorf("recording a transformed image: %w", err)
 	}

internal/database/database.go

@@ -82,11 +82,7 @@ func ParseMigrationVersion(filename string) (int, error) {
 	return version, nil
 }
 
-// New opens the database and applies the migrations, so that the parts
+// New creates a new Database instance.
-// fx builds after it can read the database while they are built. Its
-// stop hook closes the database. fx runs stop hooks in the reverse of the
-// order it built their parts in, so the stop hooks of those parts run
-// before this one.
 func New(lc fx.Lifecycle, params Params) (*Database, error) {
 	s := &Database{
 		log:    params.Logger.Get(),
@@ -95,16 +91,20 @@ func New(lc fx.Lifecycle, params Params) (*Database, error) {
 
 	s.log.Info("Database instantiated")
 
-	err := s.connect(context.Background())
-	if err != nil {
-		return nil, err
-	}
-
 	lc.Append(fx.Hook{
+		OnStart: func(ctx context.Context) error {
+			s.log.Info("Database OnStart Hook")
+
+			return s.connect(ctx)
+		},
 		OnStop: func(_ context.Context) error {
 			s.log.Info("Database OnStop Hook")
 
-			return s.db.Close()
+			if s.db != nil {
+				return s.db.Close()
+			}
+
+			return nil
 		},
 	})
 

internal/database/database_internal_test.go

@@ -159,7 +159,10 @@ func TestApplyMigrations_CreatesSchemaAndTables(t *testing.T) {
 	}
 
 	// Verify that the application tables created by 001.sql exist.
-	tables := []string{"source_content", "negative_cache"}
+	tables := []string{
+		"source_content", "source_metadata", "output_content",
+		"request_cache", "negative_cache", "cache_stats",
+	}
 	for _, table := range tables {
 		var count int
 

internal/db/migrations/001_schema.sql

@@ -1,27 +1,52 @@
 -- Migration 001: Initial schema
 -- Creates all tables for the pixa caching image proxy
 
--- Source images, one row per source URL
+-- Source content blobs
--- Files stored at: cache/sources/<ab>/<cd>/<source_key>, where source_key
+-- Files stored at: cache/sources/<ab>/<cd>/<sha256>
--- is the SHA-256 of the source's host, path and query
 CREATE TABLE IF NOT EXISTS source_content (
-    source_key TEXT PRIMARY KEY,
+    content_hash TEXT PRIMARY KEY,
+    content_type TEXT NOT NULL,
     size_bytes INTEGER NOT NULL,
+    fetched_at DATETIME DEFAULT CURRENT_TIMESTAMP,
     last_accessed_at DATETIME NOT NULL DEFAULT CURRENT_TIMESTAMP
 );
 CREATE INDEX IF NOT EXISTS idx_source_content_last_accessed
     ON source_content(last_accessed_at);
 
+-- Source URL metadata - maps URLs to content hashes
+-- JSON stored at: cache/metadata/<hostname>/<path_hash>.json
+CREATE TABLE IF NOT EXISTS source_metadata (
+    id INTEGER PRIMARY KEY AUTOINCREMENT,
+    source_host TEXT NOT NULL,
+    source_path TEXT NOT NULL,
+    source_query TEXT NOT NULL DEFAULT '',
+    path_hash TEXT NOT NULL,
+    content_hash TEXT,
+    status_code INTEGER NOT NULL,
+    content_type TEXT,
+    response_headers TEXT,
+    fetched_at DATETIME DEFAULT CURRENT_TIMESTAMP,
+    expires_at DATETIME,
+    etag TEXT,
+    last_modified TEXT,
+    UNIQUE(source_host, source_path, source_query),
+    FOREIGN KEY (content_hash) REFERENCES source_content(content_hash)
+);
+CREATE INDEX IF NOT EXISTS idx_source_meta_host ON source_metadata(source_host);
+CREATE INDEX IF NOT EXISTS idx_source_meta_path_hash ON source_metadata(path_hash);
+CREATE INDEX IF NOT EXISTS idx_source_meta_expires ON source_metadata(expires_at);
+CREATE INDEX IF NOT EXISTS idx_source_meta_content_hash ON source_metadata(content_hash);
+
 -- Processed variant blobs
--- Files stored at: cache/variants/<ab>/<cd>/<cache_key>. Tracked here
+-- Files stored at: cache/variants/<ab>/<cd>/<cache_key> (plus a .meta
--- (like source content blobs above) so total cache usage is known
+-- sidecar with the content type). Tracked here (like source content
--- without a directory scan, and so LRU eviction has a timestamp to order
+-- blobs above) so total cache usage is known without a directory scan,
--- on. A cache hit does not read this table: it takes the content type
+-- and so LRU eviction has a timestamp to order on.
--- from the file's first bytes, and its last_accessed_at is written
--- later, in a batch.
 CREATE TABLE IF NOT EXISTS variant_content (
     cache_key TEXT PRIMARY KEY,
     size_bytes INTEGER NOT NULL,
+    content_type TEXT NOT NULL,
+    created_at DATETIME NOT NULL DEFAULT CURRENT_TIMESTAMP,
     last_accessed_at DATETIME NOT NULL DEFAULT CURRENT_TIMESTAMP
 );
 CREATE INDEX IF NOT EXISTS idx_variant_content_last_accessed
@@ -95,19 +120,63 @@ BEGIN
     WHERE id = 1;
 END;
 
--- Negative cache: source URLs whose fetch failed with an upstream error
+-- Output/transformed content blobs
--- status, or whose first bytes did not match their Content-Type. pixa does
+-- Not written: transformed images are stored in cache/variants and
--- not fetch such a URL again until its row expires.
+-- tracked in variant_content above.
+CREATE TABLE IF NOT EXISTS output_content (
+    content_hash TEXT PRIMARY KEY,
+    content_type TEXT NOT NULL,
+    size_bytes INTEGER NOT NULL,
+    fetched_at DATETIME DEFAULT CURRENT_TIMESTAMP
+);
+
+-- Request cache - maps full request params to output content
+CREATE TABLE IF NOT EXISTS request_cache (
+    id INTEGER PRIMARY KEY AUTOINCREMENT,
+    cache_key TEXT NOT NULL UNIQUE,
+    source_metadata_id INTEGER NOT NULL,
+    output_hash TEXT NOT NULL,
+    width INTEGER NOT NULL,
+    height INTEGER NOT NULL,
+    format TEXT NOT NULL,
+    quality INTEGER NOT NULL DEFAULT 85,
+    fit_mode TEXT NOT NULL DEFAULT 'cover',
+    fetched_at DATETIME DEFAULT CURRENT_TIMESTAMP,
+    access_count INTEGER NOT NULL DEFAULT 1,
+    FOREIGN KEY (source_metadata_id) REFERENCES source_metadata(id),
+    FOREIGN KEY (output_hash) REFERENCES output_content(content_hash)
+);
+CREATE INDEX IF NOT EXISTS idx_request_cache_key ON request_cache(cache_key);
+CREATE INDEX IF NOT EXISTS idx_request_cache_source ON request_cache(source_metadata_id);
+CREATE INDEX IF NOT EXISTS idx_request_cache_output ON request_cache(output_hash);
+CREATE INDEX IF NOT EXISTS idx_request_cache_fetched ON request_cache(fetched_at);
+
+-- Negative cache for failed fetches (404s, timeouts, etc.)
 CREATE TABLE IF NOT EXISTS negative_cache (
     id INTEGER PRIMARY KEY AUTOINCREMENT,
     source_host TEXT NOT NULL,
     source_path TEXT NOT NULL,
     source_query TEXT NOT NULL DEFAULT '',
+    status_code INTEGER NOT NULL,
+    error_message TEXT,
+    fetched_at DATETIME DEFAULT CURRENT_TIMESTAMP,
     expires_at DATETIME NOT NULL,
     UNIQUE(source_host, source_path, source_query)
 );
 CREATE INDEX IF NOT EXISTS idx_negative_cache_expires ON negative_cache(expires_at);
 
+-- Cache statistics for monitoring
+CREATE TABLE IF NOT EXISTS cache_stats (
+    id INTEGER PRIMARY KEY CHECK (id = 1),
+    hit_count INTEGER NOT NULL DEFAULT 0,
+    miss_count INTEGER NOT NULL DEFAULT 0,
+    upstream_fetch_count INTEGER NOT NULL DEFAULT 0,
+    upstream_fetch_bytes INTEGER NOT NULL DEFAULT 0,
+    transform_count INTEGER NOT NULL DEFAULT 0,
+    last_updated_at DATETIME DEFAULT CURRENT_TIMESTAMP
+);
+INSERT OR IGNORE INTO cache_stats (id) VALUES (1);
+
 -- A random value that a login session carries from its login. pixa makes it
 -- when the table has no row, and each logout replaces it; a login session
 -- carrying another value is refused, so logging out ends every login session.

internal/encurl/encurl.go

@@ -7,15 +7,15 @@ import (
 
 	"github.com/fxamacker/cbor/v2"
 
-	"sneak.berlin/go/pixa/internal/imagerequest"
+	"sneak.berlin/go/pixa/internal/imgcache"
 	"sneak.berlin/go/pixa/internal/seal"
 )
 
 // Default values for optional fields.
 const (
 	DefaultQuality = 85
-	DefaultFormat  = imagerequest.FormatJXL
+	DefaultFormat  = imgcache.FormatJXL
-	DefaultFitMode = imagerequest.FitCover
+	DefaultFitMode = imgcache.FitCover
 
 	// HKDF salt for URL encryption key derivation
 	urlKeySalt = "pixa-urlenc-v1"
@@ -28,19 +28,19 @@ var (
 	ErrDecryptFailed = errors.New("failed to decrypt URL")
 )
 
-// payload contains all image request parameters in a compact format.
+// Payload contains all image request parameters in a compact format.
 // Field names are short to minimize encoded size.
 // Fields with omitempty use sane defaults when absent.
-type payload struct {
+type Payload struct {
-	SourceHost  string              `cbor:"h"`            // required
+	SourceHost  string               `cbor:"h"`            // required
-	SourcePath  string              `cbor:"p"`            // required
+	SourcePath  string               `cbor:"p"`            // required
-	SourceQuery string              `cbor:"q,omitempty"`  // optional
+	SourceQuery string               `cbor:"q,omitempty"`  // optional
-	Width       int                 `cbor:"w,omitempty"`  // 0 = original
+	Width       int                  `cbor:"w,omitempty"`  // 0 = original
-	Height      int                 `cbor:"ht,omitempty"` // 0 = original
+	Height      int                  `cbor:"ht,omitempty"` // 0 = original
-	Format      imagerequest.Format `cbor:"f,omitempty"`  // default: jxl
+	Format      imgcache.ImageFormat `cbor:"f,omitempty"`  // default: jxl
-	Quality     int                 `cbor:"ql,omitempty"` // default: 85
+	Quality     int                  `cbor:"ql,omitempty"` // default: 85
-	FitMode     imagerequest.Fit    `cbor:"fm,omitempty"` // default: cover
+	FitMode     imgcache.FitMode     `cbor:"fm,omitempty"` // default: cover
-	ExpiresAt   int64               `cbor:"e,omitempty"`  // 0 = never expires
+	ExpiresAt   int64                `cbor:"e,omitempty"`  // 0 = never expires
 }
 
 // Generator creates and parses encrypted URL tokens.
@@ -59,27 +59,9 @@ func NewGenerator(signingKey string) (*Generator, error) {
 	return &Generator{key: key}, nil
 }
 
-// Generate creates an encrypted URL token from the request's source,
+// Generate creates an encrypted URL token from the payload.
-// transform and expiry, each as the request holds it; an empty format, a
+// The token is CBOR-encoded, encrypted with NaCl secretbox, and base64url-encoded.
-// quality of 0 or an empty fit mode is left out of the token, and a zero
+func (g *Generator) Generate(p *Payload) (string, error) {
-// Expires makes a token that never expires. The token is CBOR-encoded,
-// encrypted with NaCl secretbox, and base64url-encoded.
-func (g *Generator) Generate(req *imagerequest.Request) (string, error) {
-	p := &payload{
-		SourceHost:  req.Source.Host,
-		SourcePath:  req.Source.Path,
-		SourceQuery: req.Source.Query,
-		Width:       req.Transform.Size.Width,
-		Height:      req.Transform.Size.Height,
-		Format:      req.Transform.Format,
-		Quality:     req.Transform.Quality,
-		FitMode:     req.Transform.FitMode,
-	}
-
-	if !req.Expires.IsZero() {
-		p.ExpiresAt = req.Expires.Unix()
-	}
-
 	// CBOR encode the payload
 	data, err := cbor.Marshal(p)
 	if err != nil {
@@ -90,11 +72,9 @@ func (g *Generator) Generate(req *imagerequest.Request) (string, error) {
 	return seal.Encrypt(g.key, data)
 }
 
-// Parse decrypts and validates an encrypted URL token and returns the
+// Parse decrypts and validates an encrypted URL token.
-// request it holds, with default values for omitted optional fields. A token
-// that never expires gives the zero Expires.
 // Returns ErrExpired if the token has expired, or other errors for invalid tokens.
-func (g *Generator) Parse(token string) (*imagerequest.Request, error) {
+func (g *Generator) Parse(token string) (*Payload, error) {
 	// Decrypt
 	data, err := seal.Decrypt(g.key, token)
 	if err != nil {
@@ -107,7 +87,7 @@ func (g *Generator) Parse(token string) (*imagerequest.Request, error) {
 	}
 
 	// CBOR decode
-	var p payload
+	var p Payload
 
 	err = cbor.Unmarshal(data, &p)
 	if err != nil {
@@ -119,6 +99,13 @@ func (g *Generator) Parse(token string) (*imagerequest.Request, error) {
 		return nil, ErrExpired
 	}
 
+	return &p, nil
+}
+
+// ToImageRequest converts the payload to an ImageRequest.
+// Applies default values for omitted optional fields. An ExpiresAt of 0, a URL
+// that never expires, gives the zero Expires.
+func (p *Payload) ToImageRequest() *imgcache.ImageRequest {
 	format := p.Format
 	if format == "" {
 		format = DefaultFormat
@@ -139,18 +126,44 @@ func (g *Generator) Parse(token string) (*imagerequest.Request, error) {
 		expires = time.Unix(p.ExpiresAt, 0)
 	}
 
-	return &imagerequest.Request{
+	return &imgcache.ImageRequest{
-		Source: imagerequest.Source{
+		SourceHost:  p.SourceHost,
-			Host:  p.SourceHost,
+		SourcePath:  p.SourcePath,
-			Path:  p.SourcePath,
+		SourceQuery: p.SourceQuery,
-			Query: p.SourceQuery,
+		Size: imgcache.Size{
-		},
+			Width:  p.Width,
-		Transform: imagerequest.Transform{
+			Height: p.Height,
-			Size:    imagerequest.Size{Width: p.Width, Height: p.Height},
-			Format:  format,
-			Quality: quality,
-			FitMode: fitMode,
 		},
+		Format:  format,
+		Quality: quality,
+		FitMode: fitMode,
 		Expires: expires,
-	}, nil
+	}
+}
+
+// FromImageRequest creates a Payload from an ImageRequest with the given expiration.
+func FromImageRequest(req *imgcache.ImageRequest, expiresAt time.Time) *Payload {
+	p := &Payload{
+		SourceHost:  req.SourceHost,
+		SourcePath:  req.SourcePath,
+		SourceQuery: req.SourceQuery,
+		Width:       req.Size.Width,
+		Height:      req.Size.Height,
+		ExpiresAt:   expiresAt.Unix(),
+	}
+
+	// Only set non-default values to benefit from omitempty
+	if req.Format != "" && req.Format != DefaultFormat {
+		p.Format = req.Format
+	}
+
+	if req.Quality != 0 && req.Quality != DefaultQuality {
+		p.Quality = req.Quality
+	}
+
+	if req.FitMode != "" && req.FitMode != DefaultFitMode {
+		p.FitMode = req.FitMode
+	}
+
+	return p
 }

internal/encurl/encurl_test.go

@@ -6,7 +6,7 @@ import (
 	"time"
 
 	"sneak.berlin/go/pixa/internal/encurl"
-	"sneak.berlin/go/pixa/internal/imagerequest"
+	"sneak.berlin/go/pixa/internal/imgcache"
 )
 
 // Shared test fixture strings.
@@ -24,22 +24,19 @@ func TestGenerator_GenerateAndParse(t *testing.T) {
 		t.Fatalf("NewGenerator() error = %v", err)
 	}
 
-	req := &imagerequest.Request{
+	payload := &encurl.Payload{
-		Source: imagerequest.Source{
+		SourceHost:  testSourceHost,
-			Host:  testSourceHost,
+		SourcePath:  testSourcePath,
-			Path:  testSourcePath,
+		SourceQuery: testSourceQuery,
-			Query: testSourceQuery,
+		Width:       800,
-		},
+		Height:      600,
-		Transform: imagerequest.Transform{
+		Format:      imgcache.FormatWebP,
-			Size:    imagerequest.Size{Width: 800, Height: 600},
+		Quality:     90,
-			Format:  imagerequest.FormatWebP,
+		FitMode:     imgcache.FitContain,
-			Quality: 90,
+		ExpiresAt:   time.Now().Add(time.Hour).Unix(),
-			FitMode: imagerequest.FitContain,
-		},
-		Expires: time.Now().Add(time.Hour),
 	}
 
-	token, err := gen.Generate(req)
+	token, err := gen.Generate(payload)
 	if err != nil {
 		t.Fatalf("Generate() error = %v", err)
 	}
@@ -54,45 +51,40 @@ func TestGenerator_GenerateAndParse(t *testing.T) {
 	}
 
 	// Verify all fields
-	if parsed.Source.Host != req.Source.Host {
+	if parsed.SourceHost != payload.SourceHost {
-		t.Errorf("SourceHost = %q, want %q", parsed.Source.Host, req.Source.Host)
+		t.Errorf("SourceHost = %q, want %q", parsed.SourceHost, payload.SourceHost)
 	}
 
-	if parsed.Source.Path != req.Source.Path {
+	if parsed.SourcePath != payload.SourcePath {
-		t.Errorf("SourcePath = %q, want %q", parsed.Source.Path, req.Source.Path)
+		t.Errorf("SourcePath = %q, want %q", parsed.SourcePath, payload.SourcePath)
 	}
 
-	if parsed.Source.Query != req.Source.Query {
+	if parsed.SourceQuery != payload.SourceQuery {
-		t.Errorf("SourceQuery = %q, want %q", parsed.Source.Query, req.Source.Query)
+		t.Errorf("SourceQuery = %q, want %q", parsed.SourceQuery, payload.SourceQuery)
 	}
 
-	if parsed.Transform.Size.Width != req.Transform.Size.Width {
+	if parsed.Width != payload.Width {
-		t.Errorf("Width = %d, want %d",
+		t.Errorf("Width = %d, want %d", parsed.Width, payload.Width)
-			parsed.Transform.Size.Width, req.Transform.Size.Width)
 	}
 
-	if parsed.Transform.Size.Height != req.Transform.Size.Height {
+	if parsed.Height != payload.Height {
-		t.Errorf("Height = %d, want %d",
+		t.Errorf("Height = %d, want %d", parsed.Height, payload.Height)
-			parsed.Transform.Size.Height, req.Transform.Size.Height)
 	}
 
-	if parsed.Transform.Format != req.Transform.Format {
+	if parsed.Format != payload.Format {
-		t.Errorf("Format = %q, want %q",
+		t.Errorf("Format = %q, want %q", parsed.Format, payload.Format)
-			parsed.Transform.Format, req.Transform.Format)
 	}
 
-	if parsed.Transform.Quality != req.Transform.Quality {
+	if parsed.Quality != payload.Quality {
-		t.Errorf("Quality = %d, want %d",
+		t.Errorf("Quality = %d, want %d", parsed.Quality, payload.Quality)
-			parsed.Transform.Quality, req.Transform.Quality)
 	}
 
-	if parsed.Transform.FitMode != req.Transform.FitMode {
+	if parsed.FitMode != payload.FitMode {
-		t.Errorf("FitMode = %q, want %q",
+		t.Errorf("FitMode = %q, want %q", parsed.FitMode, payload.FitMode)
-			parsed.Transform.FitMode, req.Transform.FitMode)
 	}
 
-	if parsed.Expires.Unix() != req.Expires.Unix() {
+	if parsed.ExpiresAt != payload.ExpiresAt {
-		t.Errorf("ExpiresAt = %d, want %d", parsed.Expires.Unix(), req.Expires.Unix())
+		t.Errorf("ExpiresAt = %d, want %d", parsed.ExpiresAt, payload.ExpiresAt)
 	}
 }
 
@@ -101,15 +93,13 @@ func TestGenerator_Parse_Expired(t *testing.T) {
 
 	gen, _ := encurl.NewGenerator("test-signing-key-12345")
 
-	req := &imagerequest.Request{
+	payload := &encurl.Payload{
-		Source: imagerequest.Source{
+		SourceHost: testSourceHost,
-			Host: testSourceHost,
+		SourcePath: testSourcePath,
-			Path: testSourcePath,
+		ExpiresAt:  time.Now().Add(-time.Hour).Unix(), // Already expired
-		},
-		Expires: time.Now().Add(-time.Hour), // Already expired
 	}
 
-	token, err := gen.Generate(req)
+	token, err := gen.Generate(payload)
 	if err != nil {
 		t.Fatalf("Generate() error = %v", err)
 	}
@@ -140,15 +130,13 @@ func TestGenerator_Parse_TamperedToken(t *testing.T) {
 
 	gen, _ := encurl.NewGenerator("test-signing-key-12345")
 
-	req := &imagerequest.Request{
+	payload := &encurl.Payload{
-		Source: imagerequest.Source{
+		SourceHost: testSourceHost,
-			Host: testSourceHost,
+		SourcePath: testSourcePath,
-			Path: testSourcePath,
+		ExpiresAt:  time.Now().Add(time.Hour).Unix(),
-		},
-		Expires: time.Now().Add(time.Hour),
 	}
 
-	token, _ := gen.Generate(req)
+	token, _ := gen.Generate(payload)
 
 	// Tamper with the token
 	tampered := []byte(token)
@@ -168,15 +156,13 @@ func TestGenerator_Parse_WrongKey(t *testing.T) {
 	gen1, _ := encurl.NewGenerator("signing-key-1")
 	gen2, _ := encurl.NewGenerator("signing-key-2")
 
-	req := &imagerequest.Request{
+	payload := &encurl.Payload{
-		Source: imagerequest.Source{
+		SourceHost: testSourceHost,
-			Host: testSourceHost,
+		SourcePath: testSourcePath,
-			Path: testSourcePath,
+		ExpiresAt:  time.Now().Add(time.Hour).Unix(),
-		},
-		Expires: time.Now().Add(time.Hour),
 	}
 
-	token, _ := gen1.Generate(req)
+	token, _ := gen1.Generate(payload)
 
 	_, err := gen2.Parse(token)
 	if err == nil {
@@ -184,41 +170,140 @@ func TestGenerator_Parse_WrongKey(t *testing.T) {
 	}
 }
 
-func TestGenerator_Parse_Defaults(t *testing.T) {
+func TestPayload_ToImageRequest(t *testing.T) {
 	t.Parallel()
 
-	gen, _ := encurl.NewGenerator("test-signing-key-12345")
+	payload := &encurl.Payload{
-
+		SourceHost:  testSourceHost,
-	// Request with only required fields - should get defaults
+		SourcePath:  testSourcePath,
-	token, err := gen.Generate(&imagerequest.Request{
+		SourceQuery: testSourceQuery,
-		Source: imagerequest.Source{
+		Width:       800,
-			Host: testSourceHost,
+		Height:      600,
-			Path: testSourcePath,
+		Format:      imgcache.FormatWebP,
-		},
+		Quality:     90,
-		Expires: time.Now().Add(time.Hour),
+		FitMode:     imgcache.FitContain,
-	})
+		ExpiresAt:   time.Now().Add(time.Hour).Unix(),
-	if err != nil {
-		t.Fatalf("Generate() error = %v", err)
 	}
 
-	req, err := gen.Parse(token)
+	req := payload.ToImageRequest()
-	if err != nil {
+
-		t.Fatalf("Parse() error = %v", err)
+	if req.SourceHost != payload.SourceHost {
+		t.Errorf("SourceHost = %q, want %q", req.SourceHost, payload.SourceHost)
 	}
 
-	if req.Transform.Format != encurl.DefaultFormat {
+	if req.SourcePath != payload.SourcePath {
-		t.Errorf("Format = %q, want default %q",
+		t.Errorf("SourcePath = %q, want %q", req.SourcePath, payload.SourcePath)
-			req.Transform.Format, encurl.DefaultFormat)
 	}
 
-	if req.Transform.Quality != encurl.DefaultQuality {
+	if req.SourceQuery != payload.SourceQuery {
-		t.Errorf("Quality = %d, want default %d",
+		t.Errorf("SourceQuery = %q, want %q", req.SourceQuery, payload.SourceQuery)
-			req.Transform.Quality, encurl.DefaultQuality)
 	}
 
-	if req.Transform.FitMode != encurl.DefaultFitMode {
+	if req.Size.Width != payload.Width {
-		t.Errorf("FitMode = %q, want default %q",
+		t.Errorf("Width = %d, want %d", req.Size.Width, payload.Width)
-			req.Transform.FitMode, encurl.DefaultFitMode)
+	}
+
+	if req.Size.Height != payload.Height {
+		t.Errorf("Height = %d, want %d", req.Size.Height, payload.Height)
+	}
+
+	if req.Format != payload.Format {
+		t.Errorf("Format = %q, want %q", req.Format, payload.Format)
+	}
+
+	if req.Quality != payload.Quality {
+		t.Errorf("Quality = %d, want %d", req.Quality, payload.Quality)
+	}
+
+	if req.FitMode != payload.FitMode {
+		t.Errorf("FitMode = %q, want %q", req.FitMode, payload.FitMode)
+	}
+}
+
+func TestPayload_ToImageRequest_Defaults(t *testing.T) {
+	t.Parallel()
+
+	// Payload with only required fields - should get defaults
+	payload := &encurl.Payload{
+		SourceHost: testSourceHost,
+		SourcePath: testSourcePath,
+		ExpiresAt:  time.Now().Add(time.Hour).Unix(),
+	}
+
+	req := payload.ToImageRequest()
+
+	if req.Format != encurl.DefaultFormat {
+		t.Errorf("Format = %q, want default %q", req.Format, encurl.DefaultFormat)
+	}
+
+	if req.Quality != encurl.DefaultQuality {
+		t.Errorf("Quality = %d, want default %d", req.Quality, encurl.DefaultQuality)
+	}
+
+	if req.FitMode != encurl.DefaultFitMode {
+		t.Errorf("FitMode = %q, want default %q", req.FitMode, encurl.DefaultFitMode)
+	}
+}
+
+func TestFromImageRequest(t *testing.T) {
+	t.Parallel()
+
+	req := &imgcache.ImageRequest{
+		SourceHost:  testSourceHost,
+		SourcePath:  testSourcePath,
+		SourceQuery: testSourceQuery,
+		Size:        imgcache.Size{Width: 800, Height: 600},
+		Format:      imgcache.FormatWebP,
+		Quality:     90,
+		FitMode:     imgcache.FitContain,
+	}
+
+	expiresAt := time.Now().Add(time.Hour)
+	payload := encurl.FromImageRequest(req, expiresAt)
+
+	if payload.SourceHost != req.SourceHost {
+		t.Errorf("SourceHost = %q, want %q", payload.SourceHost, req.SourceHost)
+	}
+
+	if payload.SourcePath != req.SourcePath {
+		t.Errorf("SourcePath = %q, want %q", payload.SourcePath, req.SourcePath)
+	}
+
+	if payload.Width != req.Size.Width {
+		t.Errorf("Width = %d, want %d", payload.Width, req.Size.Width)
+	}
+
+	if payload.ExpiresAt != expiresAt.Unix() {
+		t.Errorf("ExpiresAt = %d, want %d", payload.ExpiresAt, expiresAt.Unix())
+	}
+}
+
+func TestFromImageRequest_OmitsDefaults(t *testing.T) {
+	t.Parallel()
+
+	// Request with default values - payload should omit them for
+	// smaller encoding
+	req := &imgcache.ImageRequest{
+		SourceHost: testSourceHost,
+		SourcePath: testSourcePath,
+		Format:     encurl.DefaultFormat,
+		Quality:    encurl.DefaultQuality,
+		FitMode:    encurl.DefaultFitMode,
+	}
+
+	payload := encurl.FromImageRequest(req, time.Now().Add(time.Hour))
+
+	// These should be zero/empty because they match defaults
+	if payload.Format != "" {
+		t.Errorf("Format should be empty for default, got %q", payload.Format)
+	}
+
+	if payload.Quality != 0 {
+		t.Errorf("Quality should be 0 for default, got %d", payload.Quality)
+	}
+
+	if payload.FitMode != "" {
+		t.Errorf("FitMode should be empty for default, got %q", payload.FitMode)
 	}
 }
 
@@ -227,15 +312,13 @@ func TestGenerator_TokenIsURLSafe(t *testing.T) {
 
 	gen, _ := encurl.NewGenerator("test-signing-key-12345")
 
-	req := &imagerequest.Request{
+	payload := &encurl.Payload{
-		Source: imagerequest.Source{
+		SourceHost: testSourceHost,
-			Host: testSourceHost,
+		SourcePath: testSourcePath,
-			Path: testSourcePath,
+		ExpiresAt:  time.Now().Add(time.Hour).Unix(),
-		},
-		Expires: time.Now().Add(time.Hour),
 	}
 
-	token, _ := gen.Generate(req)
+	token, _ := gen.Generate(payload)
 
 	// Check that token only contains URL-safe characters
 	for _, c := range token {

internal/handlers/auth.go

@@ -9,14 +9,12 @@ import (
 	"math"
 	"net/http"
 	"net/url"
-	"slices"
 	"strconv"
-	"strings"
 	"time"
 
 	"sneak.berlin/go/pixa/internal/clientip"
 	"sneak.berlin/go/pixa/internal/encurl"
-	"sneak.berlin/go/pixa/internal/imagerequest"
+	"sneak.berlin/go/pixa/internal/imgcache"
 	"sneak.berlin/go/pixa/internal/templates"
 )
 
@@ -127,7 +125,7 @@ func (s *Handlers) HandleGenerateURL() http.HandlerFunc {
 		sourceURL := r.FormValue("url")
 
 		// Validate source URL
-		parsed, err := parseSourceURL(sourceURL)
+		parsed, err := url.Parse(sourceURL)
 		if err != nil || parsed.Host == "" {
 			s.renderGeneratorWithForm(w, r, "Invalid source URL", r.Form,
 				http.StatusBadRequest)
@@ -135,17 +133,7 @@ func (s *Handlers) HandleGenerateURL() http.HandlerFunc {
 			return
 		}
 
-		// /v1/image/ refuses a ".." segment in the source path, and so does
+		payload, expiresAt, ttl, err := buildGeneratePayload(parsed, r.Form)
-		// the generator. The path is decoded, so %2e%2e counts too
-		if slices.Contains(strings.Split(parsed.Path, "/"), "..") {
-			s.renderGeneratorWithForm(w, r,
-				"Source URL path cannot hold a .. segment", r.Form,
-				http.StatusBadRequest)
-
-			return
-		}
-
-		req, expiresAt, ttl, err := buildGenerateRequest(parsed, r.Form)
 		if err != nil {
 			s.renderGeneratorWithForm(w, r, err.Error(), r.Form,
 				http.StatusBadRequest)
@@ -153,20 +141,24 @@ func (s *Handlers) HandleGenerateURL() http.HandlerFunc {
 			return
 		}
 
-		// The image URL must fetch the source URL as it was written
+		// The image URL must fetch the source URL as it was written. The
-		req.AllowHTTP = s.config.AllowHTTP
+		// token keeps the path decoded and pixa fetches it percent-encoded
-		fetchURL := req.SourceURL()
+		// again, so a path written another way, such as with %2F, would fetch
+		// another URL. The scheme is not kept: only path and query are compared
+		sourceRequest := payload.ToImageRequest()
+		sourceRequest.AllowHTTP = s.config.AllowHTTP
 
-		if !fetchedAsWritten(parsed, fetchURL) {
+		fetchURL, err := url.Parse(sourceRequest.SourceURL())
+		if err != nil || fetchURL.RequestURI() != parsed.RequestURI() {
 			s.renderGeneratorWithForm(w, r, "Source URL cannot be fetched as "+
-				"written: pixa would fetch "+fetchURL,
+				"written: pixa would fetch "+sourceRequest.SourceURL(),
 				r.Form, http.StatusBadRequest)
 
 			return
 		}
 
 		// Generate encrypted token
-		token, err := s.encGen.Generate(req)
+		token, err := s.encGen.Generate(payload)
 		if err != nil {
 			s.log.Error("failed to generate encrypted URL", "error", err)
 			s.renderGeneratorWithForm(w, r, "Failed to generate URL", r.Form,
@@ -197,57 +189,14 @@ func (s *Handlers) HandleGenerateURL() http.HandlerFunc {
 	}
 }
 
-// parseSourceURL parses the source URL entered on the generator page with its
+// buildGeneratePayload parses the numeric form fields and assembles the
-// host lower-cased and an empty path written as "/", as /v1/image/ reads a
+// encrypted URL payload. ttl=0 means never expires (ExpiresAt stays 0). A
-// source URL, so that each spelling of one source URL makes one cache key and
+// non-numeric or out-of-range width, height, quality or ttl, or an
-// one upstream request.
+// unrecognized fit mode, is a client error naming the offending field. The
-func parseSourceURL(sourceURL string) (*url.URL, error) {
+// format field is passed through unchecked.
-	parsed, err := url.Parse(sourceURL)
+func buildGeneratePayload(
-	if err != nil {
-		return nil, err
-	}
-
-	parsed.Host = strings.ToLower(parsed.Host)
-
-	if parsed.Path == "" {
-		parsed.Path = "/"
-	}
-
-	return parsed, nil
-}
-
-// fetchedAsWritten reports whether fetchURL, the URL pixa fetches for an
-// image URL made from the source URL source, is source as it was written,
-// apart from the scheme, which the token does not keep. It is not when source
-// holds a user name and password, which the token does not keep either, or a
-// "?" with no query after it. The token keeps the source path decoded and
-// pixa fetches it percent-encoded again, so a path written another way, such
-// as with %2F, is fetched as another path. url.URL keeps the path as written
-// in RawPath when it is not the decoded path percent-encoded again.
-// EscapedPath ignores RawPath when it also holds a character net/url encodes,
-// such as a space, so RawPath is compared itself.
-func fetchedAsWritten(source *url.URL, fetchURL string) bool {
-	writtenPath := source.RawPath
-	if writtenPath == "" {
-		writtenPath = source.EscapedPath()
-	}
-
-	fetched, err := url.Parse(fetchURL)
-
-	return err == nil && source.User == nil && !source.ForceQuery &&
-		fetched.EscapedPath() == writtenPath &&
-		fetched.RawQuery == source.RawQuery
-}
-
-// buildGenerateRequest parses the numeric form fields and assembles the
-// image request the encrypted URL's token is made from. ttl=0 means never
-// expires (Expires stays the zero time). A non-numeric or out-of-range
-// width, height, quality or ttl, or an unrecognized fit mode, is a client
-// error naming the offending field. The format field is passed through
-// unchecked.
-func buildGenerateRequest(
 	parsed *url.URL, form url.Values,
-) (*imagerequest.Request, time.Time, int, error) {
+) (*encurl.Payload, time.Time, int, error) {
 	width, err := parseFormDimension(form, "width")
 	if err != nil {
 		return nil, time.Time{}, 0, err
@@ -269,40 +218,42 @@ func buildGenerateRequest(
 		return nil, time.Time{}, 0, err
 	}
 
-	fitMode := imagerequest.Fit(form.Get("fit"))
+	fitMode := imgcache.FitMode(form.Get("fit"))
 
-	err = imagerequest.ValidateFitMode(fitMode)
+	err = imgcache.ValidateFitMode(fitMode)
 	if err != nil {
 		return nil, time.Time{}, 0,
-			fmt.Errorf("%w: %s", imagerequest.ErrInvalidFitMode, form.Get("fit"))
+			fmt.Errorf("%w: %s", imgcache.ErrInvalidFitMode, form.Get("fit"))
 	}
 
-	var expiresAt time.Time
+	var (
+		expiresAt     time.Time
+		expiresAtUnix int64
+	)
+
 	if ttl > 0 {
 		expiresAt = time.Now().Add(time.Duration(ttl) * time.Second)
+		expiresAtUnix = expiresAt.Unix()
 	}
 
-	req := &imagerequest.Request{
+	payload := &encurl.Payload{
-		Source: imagerequest.Source{
+		SourceHost:  parsed.Host,
-			Host:  parsed.Host,
+		SourcePath:  parsed.Path,
-			Path:  parsed.Path,
+		SourceQuery: parsed.RawQuery,
-			Query: parsed.RawQuery,
+		Width:       width,
-		},
+		Height:      height,
-		Transform: imagerequest.Transform{
+		Format:      imgcache.ImageFormat(form.Get("format")),
-			Size:    imagerequest.Size{Width: width, Height: height},
+		Quality:     quality,
-			Format:  imagerequest.Format(form.Get("format")),
+		FitMode:     fitMode,
-			Quality: quality,
+		ExpiresAt:   expiresAtUnix,
-			FitMode: fitMode,
-		},
-		Expires: expiresAt,
 	}
 
-	return req, expiresAt, ttl, nil
+	return payload, expiresAt, ttl, nil
 }
 
 // parseFormDimension reads an optional width or height form field. An empty
 // value means "original size" (0). A non-numeric value, or one
-// imagerequest.ValidateDimension rejects, is an error naming the field.
+// imgcache.ValidateDimension rejects, is an error naming the field.
 func parseFormDimension(form url.Values, field string) (int, error) {
 	raw := form.Get(field)
 	if raw == "" {
@@ -314,7 +265,7 @@ func parseFormDimension(form url.Values, field string) (int, error) {
 		return 0, fmt.Errorf("%w %s: not a number", errInvalidFormField, field)
 	}
 
-	err = imagerequest.ValidateDimension(field, value)
+	err = imgcache.ValidateDimension(field, value)
 	if err != nil {
 		return 0, err
 	}

internal/handlers/auth_generate_internal_test.go

@@ -11,7 +11,7 @@ import (
 	"time"
 
 	"sneak.berlin/go/pixa/internal/encurl"
-	"sneak.berlin/go/pixa/internal/imagerequest"
+	"sneak.berlin/go/pixa/internal/imgcache"
 )
 
 // Generator form field names, and a value that is not a number.
@@ -125,10 +125,10 @@ func TestGeneratePostRejectsBadField(t *testing.T) {
 	}
 }
 
-// TestBuildGenerateRequestDefaultAndLimits verifies that an empty quality
+// TestBuildGeneratePayloadDefaultAndLimits verifies that an empty quality
 // takes the default, and that the largest accepted width, height, quality and
 // ttl are accepted with an expiry still in the future.
-func TestBuildGenerateRequestDefaultAndLimits(t *testing.T) {
+func TestBuildGeneratePayloadDefaultAndLimits(t *testing.T) {
 	t.Parallel()
 
 	parsed, err := url.Parse(testSourceURL)
@@ -136,19 +136,19 @@ func TestBuildGenerateRequestDefaultAndLimits(t *testing.T) {
 		t.Fatalf("url.Parse() error = %v", err)
 	}
 
-	req, _, _, err := buildGenerateRequest(parsed, url.Values{})
+	payload, _, _, err := buildGeneratePayload(parsed, url.Values{})
 	if err != nil {
 		t.Fatalf("empty form: error = %v", err)
 	}
 
-	if req.Transform.Quality != encurl.DefaultQuality {
+	if payload.Quality != encurl.DefaultQuality {
 		t.Errorf("empty quality gave %d, want %d",
-			req.Transform.Quality, encurl.DefaultQuality)
+			payload.Quality, encurl.DefaultQuality)
 	}
 
-	_, expiresAt, _, err := buildGenerateRequest(parsed, url.Values{
+	_, expiresAt, _, err := buildGeneratePayload(parsed, url.Values{
-		widthField:   {strconv.Itoa(imagerequest.MaxDimension)},
+		widthField:   {strconv.Itoa(imgcache.MaxDimension)},
-		heightField:  {strconv.Itoa(imagerequest.MaxDimension)},
+		heightField:  {strconv.Itoa(imgcache.MaxDimension)},
 		qualityField: {strconv.Itoa(maxQuality)},
 		ttlField:     {strconv.Itoa(maxTTL)},
 	})

internal/handlers/auth_session_internal_test.go

@@ -10,7 +10,7 @@ import (
 	"testing"
 	"time"
 
-	"sneak.berlin/go/pixa/internal/imagerequest"
+	"sneak.berlin/go/pixa/internal/imgcache"
 	"sneak.berlin/go/pixa/internal/session"
 )
 
@@ -314,7 +314,7 @@ func TestGeneratePost_URLServesImage(t *testing.T) {
 		sourceURLField: {"https://" + signedHost + photoPath},
 		widthField:     {"50"},
 		heightField:    {"50"},
-		formatField:    {string(imagerequest.FormatJPEG)},
+		formatField:    {string(imgcache.FormatJPEG)},
 	})
 
 	if rec.Code != http.StatusOK {
@@ -347,7 +347,7 @@ func TestGeneratePost_URLWithTTLExpires(t *testing.T) {
 		sourceURLField: {"https://" + signedHost + photoPath},
 		widthField:     {"50"},
 		heightField:    {"50"},
-		formatField:    {string(imagerequest.FormatJPEG)},
+		formatField:    {string(imgcache.FormatJPEG)},
 		ttlField:       {"1"},
 	})
 

internal/handlers/avif_too_large_internal_test.go

@@ -1,49 +0,0 @@
-package handlers
-
-import (
-	"fmt"
-	"log/slog"
-	"net/http"
-	"net/http/httptest"
-	"strings"
-	"testing"
-
-	"sneak.berlin/go/pixa/internal/imageprocessor"
-	"sneak.berlin/go/pixa/internal/imagerequest"
-)
-
-// TestAVIFOutputTooLargeAnswers400 checks that respondImageError and
-// handleImageError, which answer the errors of the two image routes, answer
-// 400 naming the AVIF pixel limit when the image processor refuses an AVIF
-// output above it, wrapped as the service wraps it. The request's source only
-// goes into a log line, so it is left empty.
-func TestAVIFOutputTooLargeAnswers400(t *testing.T) {
-	t.Parallel()
-
-	h := &Handlers{log: slog.New(slog.DiscardHandler)}
-	err := fmt.Errorf("image processing failed: %w: 4097x4096",
-		imageprocessor.ErrAVIFOutputTooLarge)
-	wantBody := fmt.Sprintf("above %d pixels", imageprocessor.MaxAVIFOutputPixels)
-
-	plain := httptest.NewRecorder()
-	h.respondImageError(plain, &imagerequest.Request{}, err)
-
-	encrypted := httptest.NewRecorder()
-	h.handleImageError(encrypted, err)
-
-	for name, rec := range map[string]*httptest.ResponseRecorder{
-		"respondImageError": plain, "handleImageError": encrypted,
-	} {
-		t.Logf("%s: status = %d, body = %q", name, rec.Code, rec.Body.String())
-
-		if rec.Code != http.StatusBadRequest {
-			t.Errorf("%s: status = %d, want %d",
-				name, rec.Code, http.StatusBadRequest)
-		}
-
-		if !strings.Contains(rec.Body.String(), wantBody) {
-			t.Errorf("%s: body = %q, want it to say %q",
-				name, rec.Body.String(), wantBody)
-		}
-	}
-}

internal/handlers/cache_hit_internal_test.go

@@ -1,272 +0,0 @@
-package handlers
-
-import (
-	"bytes"
-	"context"
-	"database/sql"
-	"database/sql/driver"
-	"image"
-	"image/jpeg"
-	"log/slog"
-	"net/http"
-	"net/http/httptest"
-	"path/filepath"
-	"sync/atomic"
-	"testing"
-	"testing/fstest"
-	"time"
-
-	"github.com/go-chi/chi/v5"
-	"github.com/prometheus/client_golang/prometheus"
-
-	"sneak.berlin/go/pixa/internal/database"
-	"sneak.berlin/go/pixa/internal/encurl"
-	"sneak.berlin/go/pixa/internal/imageprocessor"
-	"sneak.berlin/go/pixa/internal/imagerequest"
-	"sneak.berlin/go/pixa/internal/imgcache"
-)
-
-// countingHost is the allowlisted host whose photoPath the server of
-// newCountingDatabaseServer serves.
-const countingHost = "counting.example.com"
-
-// countingConnector opens connections to the SQLite database file name with
-// sqliteDriver, each one counting in statements the statements run on it.
-type countingConnector struct {
-	sqliteDriver driver.Driver
-	name         string
-	statements   *atomic.Int64
-}
-
-func (c countingConnector) Connect(context.Context) (driver.Conn, error) {
-	conn, err := c.sqliteDriver.Open(c.name)
-	if err != nil {
-		return nil, err
-	}
-
-	return countingConn{Conn: conn, statements: c.statements}, nil
-}
-
-func (c countingConnector) Driver() driver.Driver {
-	return c.sqliteDriver
-}
-
-// countingConn counts the statements run on its connection. It has only the
-// methods of driver.Conn, so database/sql prepares every query and every
-// other statement with Prepare, which counts it.
-type countingConn struct {
-	driver.Conn
-
-	statements *atomic.Int64
-}
-
-func (c countingConn) Prepare(query string) (driver.Stmt, error) {
-	c.statements.Add(1)
-
-	return c.Conn.Prepare(query)
-}
-
-// newCountingDatabase returns a database with pixa's schema, in a file of
-// its own and with one connection, and the count of the statements run on
-// it once the schema is in place.
-func newCountingDatabase(tb testing.TB) (*sql.DB, *atomic.Int64) {
-	tb.Helper()
-
-	path := filepath.Join(tb.TempDir(), "state.sqlite3")
-
-	schemaDB, err := sql.Open("sqlite", path)
-	if err != nil {
-		tb.Fatalf("opening the database: %v", err)
-	}
-
-	defer func() { _ = schemaDB.Close() }()
-
-	err = database.ApplyMigrations(tb.Context(), schemaDB, nil)
-	if err != nil {
-		tb.Fatalf("applying the migrations: %v", err)
-	}
-
-	statements := new(atomic.Int64)
-
-	db := sql.OpenDB(countingConnector{
-		sqliteDriver: schemaDB.Driver(),
-		name:         path,
-		statements:   statements,
-	})
-	db.SetMaxOpenConns(1)
-
-	tb.Cleanup(func() { _ = db.Close() })
-
-	return db, statements
-}
-
-// newCountingDatabaseServer returns a router for both image routes whose
-// image cache uses newCountingDatabase, the count of the statements run on
-// that database, and a URL on each route for a different image of
-// photoPath on countingHost. Nothing writes the cache's access times in the
-// background, so every statement counted comes from a request.
-func newCountingDatabaseServer(
-	tb testing.TB,
-) (http.Handler, *atomic.Int64, []string) {
-	tb.Helper()
-
-	db, statements := newCountingDatabase(tb)
-
-	var photo bytes.Buffer
-
-	err := jpeg.Encode(&photo, image.NewRGBA(image.Rect(0, 0, 100, 100)), nil)
-	if err != nil {
-		tb.Fatalf("encoding the photo: %v", err)
-	}
-
-	cache, err := imgcache.NewCache(db, imgcache.CacheConfig{
-		StateDir:    tb.TempDir(),
-		NegativeTTL: 5 * time.Minute,
-		MaxBytes:    1 << 30,
-	}, prometheus.NewRegistry())
-	if err != nil {
-		tb.Fatalf("imgcache.NewCache() error = %v", err)
-	}
-
-	svc, err := imgcache.NewService(&imgcache.ServiceConfig{
-		Cache: cache,
-		Fetcher: newMockFetcher(fstest.MapFS{
-			countingHost + photoPath: &fstest.MapFile{Data: photo.Bytes()},
-		}),
-		Processor: imageprocessor.New(imageprocessor.Params{
-			MaxInputBytes:           50 << 20,
-			MaxConcurrentProcessing: 2,
-		}),
-		SigningKey:      testSigningKey,
-		Allowlist:       []string{countingHost},
-		MaxResponseSize: 50 << 20,
-		Logger:          slog.New(slog.DiscardHandler),
-	})
-	if err != nil {
-		tb.Fatalf("imgcache.NewService() error = %v", err)
-	}
-
-	encGen, err := encurl.NewGenerator(testSigningKey)
-	if err != nil {
-		tb.Fatalf("encurl.NewGenerator() error = %v", err)
-	}
-
-	token, err := encGen.Generate(&imagerequest.Request{
-		Source: imagerequest.Source{Host: countingHost, Path: photoPath},
-		Transform: imagerequest.Transform{
-			Size:    imagerequest.Size{Width: 40, Height: 40},
-			Format:  imagerequest.FormatJPEG,
-			Quality: 85,
-			FitMode: imagerequest.FitCover,
-		},
-	})
-	if err != nil {
-		tb.Fatalf("encGen.Generate() error = %v", err)
-	}
-
-	h := &Handlers{
-		log:    slog.New(slog.DiscardHandler),
-		imgSvc: svc,
-		encGen: encGen,
-	}
-
-	r := chi.NewRouter()
-	r.Get("/v1/image/*", h.HandleImage())
-	r.Get("/v1/e/{token}/*", h.HandleImageEnc())
-
-	return r, statements, []string{
-		"/v1/image/" + countingHost + photoPath + "/50x50.jpeg",
-		"/v1/e/" + token + "/img.jpg",
-	}
-}
-
-// serveImage sends srv a GET for target and returns the response, failing
-// the test unless it is a 200 with an image.
-func serveImage(
-	tb testing.TB, srv http.Handler, target string,
-) *httptest.ResponseRecorder {
-	tb.Helper()
-
-	rec := httptest.NewRecorder()
-	srv.ServeHTTP(rec,
-		httptest.NewRequestWithContext(tb.Context(), http.MethodGet, target, nil))
-
-	if rec.Code != http.StatusOK || rec.Body.Len() == 0 {
-		tb.Errorf("GET %s: %d with %d bytes, want 200 with an image",
-			target, rec.Code, rec.Body.Len())
-	}
-
-	return rec
-}
-
-// TestImageRoutes_CacheHitsMakeNoDatabaseCall serves an image on each image
-// route once, which makes and caches it, then serves it again from the cache.
-// Serving those cache hits must run no statement on the database.
-func TestImageRoutes_CacheHitsMakeNoDatabaseCall(t *testing.T) {
-	t.Parallel()
-
-	srv, statements, targets := newCountingDatabaseServer(t)
-
-	for _, target := range targets {
-		before := statements.Load()
-
-		serveImage(t, srv, target)
-
-		afterMiss := statements.Load()
-		t.Logf("GET %s, a miss: %d statements", target, afterMiss-before)
-
-		if afterMiss == before {
-			t.Fatalf("GET %s, a miss: no statement counted, want some", target)
-		}
-
-		for range 3 {
-			rec := serveImage(t, srv, target)
-
-			cacheStatus := rec.Header().Get("X-Pixa-Cache")
-			if cacheStatus != string(imgcache.CacheHit) {
-				t.Errorf("GET %s: X-Pixa-Cache = %q, want %s",
-					target, cacheStatus, imgcache.CacheHit)
-			}
-		}
-
-		if hitStatements := statements.Load() - afterMiss; hitStatements != 0 {
-			t.Errorf("GET %s: 3 cache hits ran %d statements, want 0",
-				target, hitStatements)
-		}
-	}
-}
-
-// BenchmarkHandleImage_CacheHits serves one cached image through the
-// /v1/image/ route from b.RunParallel's goroutines, and reports the cache
-// hits served per second. It fails if serving them ran any statement on the
-// database. script/bench runs it.
-func BenchmarkHandleImage_CacheHits(b *testing.B) {
-	srv, statements, targets := newCountingDatabaseServer(b)
-	target := targets[0]
-
-	serveImage(b, srv, target)
-
-	before := statements.Load()
-
-	b.ResetTimer()
-
-	b.RunParallel(func(pb *testing.PB) {
-		for pb.Next() {
-			rec := serveImage(b, srv, target)
-
-			cacheStatus := rec.Header().Get("X-Pixa-Cache")
-			if cacheStatus != string(imgcache.CacheHit) {
-				b.Errorf("GET %s: X-Pixa-Cache = %q, want %s",
-					target, cacheStatus, imgcache.CacheHit)
-
-				return
-			}
-		}
-	})
-
-	b.ReportMetric(float64(b.N)/b.Elapsed().Seconds(), "hits/s")
-
-	if hitStatements := statements.Load() - before; hitStatements != 0 {
-		b.Fatalf("%d cache hits ran %d statements, want 0", b.N, hitStatements)
-	}
-}

internal/handlers/cache_max_bytes_internal_test.go

@@ -0,0 +1,147 @@
+package handlers
+
+import (
+	"os"
+	"path/filepath"
+	"testing"
+
+	"go.uber.org/fx/fxtest"
+
+	"sneak.berlin/go/pixa/internal/config"
+	"sneak.berlin/go/pixa/internal/database"
+	"sneak.berlin/go/pixa/internal/globals"
+	"sneak.berlin/go/pixa/internal/logger"
+)
+
+// TestNewCacheConfigFromCacheMaxBytes checks the cache configuration
+// built from cache_max_bytes: omitted, the cache works out the default
+// limit; 0 turns the disk cache off; a positive value is the limit,
+// unchanged.
+func TestNewCacheConfigFromCacheMaxBytes(t *testing.T) {
+	t.Parallel()
+
+	const oneGiB = 1 << 30
+
+	cases := []struct {
+		name                   string
+		cacheMaxBytes          int64
+		cacheMaxBytesExplicit  bool
+		wantMaxBytes           int64
+		wantUseDefaultMaxBytes bool
+		wantDisableDiskCache   bool
+	}{
+		{
+			name:                   "cache_max_bytes omitted",
+			cacheMaxBytes:          0,
+			cacheMaxBytesExplicit:  false,
+			wantMaxBytes:           0,
+			wantUseDefaultMaxBytes: true,
+			wantDisableDiskCache:   false,
+		},
+		{
+			name:                   "cache_max_bytes: 0",
+			cacheMaxBytes:          0,
+			cacheMaxBytesExplicit:  true,
+			wantMaxBytes:           0,
+			wantUseDefaultMaxBytes: false,
+			wantDisableDiskCache:   true,
+		},
+		{
+			name:                   "cache_max_bytes: 1 GiB",
+			cacheMaxBytes:          oneGiB,
+			cacheMaxBytesExplicit:  true,
+			wantMaxBytes:           oneGiB,
+			wantUseDefaultMaxBytes: false,
+			wantDisableDiskCache:   false,
+		},
+	}
+
+	for _, tc := range cases {
+		t.Run(tc.name, func(t *testing.T) {
+			t.Parallel()
+
+			cfg := &config.Config{
+				CacheMaxBytes:         tc.cacheMaxBytes,
+				CacheMaxBytesExplicit: tc.cacheMaxBytesExplicit,
+			}
+
+			got := newCacheConfig(cfg, nil)
+			t.Logf("MaxBytes = %d, UseDefaultMaxBytes = %v, DisableDiskCache = %v",
+				got.MaxBytes, got.UseDefaultMaxBytes, got.DisableDiskCache)
+
+			if got.MaxBytes != tc.wantMaxBytes {
+				t.Errorf("MaxBytes = %d, want %d", got.MaxBytes, tc.wantMaxBytes)
+			}
+
+			if got.UseDefaultMaxBytes != tc.wantUseDefaultMaxBytes {
+				t.Errorf("UseDefaultMaxBytes = %v, want %v",
+					got.UseDefaultMaxBytes, tc.wantUseDefaultMaxBytes)
+			}
+
+			if got.DisableDiskCache != tc.wantDisableDiskCache {
+				t.Errorf("DisableDiskCache = %v, want %v",
+					got.DisableDiskCache, tc.wantDisableDiskCache)
+			}
+		})
+	}
+}
+
+// TestDiskCacheOffOnlyForExplicitZeroCacheMaxBytes starts the handlers
+// once with cache_max_bytes omitted and once with cache_max_bytes: 0,
+// and checks by whether the cache directories were created that the
+// disk cache is on in the first case and off in the second.
+func TestDiskCacheOffOnlyForExplicitZeroCacheMaxBytes(t *testing.T) {
+	t.Parallel()
+
+	cases := []struct {
+		name                  string
+		cacheMaxBytesExplicit bool
+		wantDiskCache         bool
+	}{
+		{name: "cache_max_bytes omitted", cacheMaxBytesExplicit: false, wantDiskCache: true},
+		{name: "cache_max_bytes: 0", cacheMaxBytesExplicit: true, wantDiskCache: false},
+	}
+
+	for _, tc := range cases {
+		t.Run(tc.name, func(t *testing.T) {
+			t.Parallel()
+
+			stateDir := t.TempDir()
+			cfg := &config.Config{
+				SigningKey:            testSigningKey,
+				StateDir:              stateDir,
+				DBURL:                 "file:" + filepath.Join(stateDir, "state.sqlite3"),
+				CacheMaxBytes:         0,
+				CacheMaxBytesExplicit: tc.cacheMaxBytesExplicit,
+			}
+
+			lc := fxtest.NewLifecycle(t)
+
+			log, err := logger.New(lc, logger.Params{Globals: &globals.Globals{}})
+			if err != nil {
+				t.Fatalf("logger.New() error = %v", err)
+			}
+
+			db, err := database.New(lc, database.Params{Logger: log, Config: cfg})
+			if err != nil {
+				t.Fatalf("database.New() error = %v", err)
+			}
+
+			_, err = New(lc, Params{Logger: log, Database: db, Config: cfg})
+			if err != nil {
+				t.Fatalf("New() error = %v", err)
+			}
+
+			lc.RequireStart()
+			t.Cleanup(lc.RequireStop)
+
+			_, err = os.Stat(filepath.Join(stateDir, "cache", "variants"))
+			gotDiskCache := err == nil
+
+			if gotDiskCache != tc.wantDiskCache {
+				t.Errorf("cache directories created = %v, want %v",
+					gotDiskCache, tc.wantDiskCache)
+			}
+		})
+	}
+}

internal/handlers/fetcher_internal_test.go

@@ -0,0 +1,61 @@
+package handlers
+
+import (
+	"net/http"
+	"net/netip"
+	"path/filepath"
+	"testing"
+	"time"
+
+	"github.com/go-chi/chi/v5"
+	"go.uber.org/fx"
+	"go.uber.org/fx/fxtest"
+
+	"sneak.berlin/go/pixa/internal/config"
+	"sneak.berlin/go/pixa/internal/database"
+	"sneak.berlin/go/pixa/internal/globals"
+	"sneak.berlin/go/pixa/internal/healthcheck"
+	"sneak.berlin/go/pixa/internal/logger"
+)
+
+// TestHandlersBuildTheirOwnFetcherWhenNoneIsProvided builds the handlers as
+// pixad does, in an fx app that provides no fetcher, and requests an image
+// from 192.0.2.10, which is on the allowlist and in blocked_networks. The URL
+// check accepts that address; only the dialer that refuses internal
+// addresses checks blocked_networks, so the answer is 403 only if the
+// fetcher the handlers build from the config connects with that dialer. Any
+// other dialer would try to connect until the upstream fetch timeout, which
+// is short so that the test then fails quickly.
+func TestHandlersBuildTheirOwnFetcherWhenNoneIsProvided(t *testing.T) {
+	t.Parallel()
+
+	const host = "192.0.2.10"
+
+	stateDir := t.TempDir()
+	cfg := &config.Config{
+		SigningKey:           testSigningKey,
+		StateDir:             stateDir,
+		DBURL:                "file:" + filepath.Join(stateDir, "state.sqlite3"),
+		AllowlistHosts:       []string{host},
+		BlockedNetworks:      []netip.Prefix{netip.MustParsePrefix("192.0.2.0/24")},
+		UpstreamFetchTimeout: 2 * time.Second,
+		// With no connection slots, the fetch would fail before dialing.
+		UpstreamConnections: config.DefaultUpstreamConnections,
+	}
+
+	var h *Handlers
+
+	app := fxtest.New(t,
+		fx.Supply(cfg),
+		fx.Provide(globals.New, logger.New, database.New, healthcheck.New, New),
+		fx.Populate(&h),
+	)
+	app.RequireStart()
+	t.Cleanup(app.RequireStop)
+
+	r := chi.NewRouter()
+	r.Get("/v1/image/*", h.HandleImage())
+
+	rec := sendGet(t, r, photoURL(host))
+	checkErrorBody(t, rec, http.StatusForbidden, "forbidden")
+}

internal/handlers/first_bytes_internal_test.go

@@ -1,192 +0,0 @@
-package handlers
-
-import (
-	"bytes"
-	"encoding/json"
-	"image/color"
-	"log/slog"
-	"net/http"
-	"slices"
-	"testing"
-	"testing/fstest"
-	"time"
-
-	"github.com/go-chi/chi/v5"
-	"github.com/prometheus/client_golang/prometheus"
-	"sneak.berlin/go/pixa/internal/encurl"
-	"sneak.berlin/go/pixa/internal/httpfetcher"
-	"sneak.berlin/go/pixa/internal/imageprocessor"
-	"sneak.berlin/go/pixa/internal/imagerequest"
-	"sneak.berlin/go/pixa/internal/imgcache"
-)
-
-// mismatchedSourcePath is the path of the source that
-// TestFirstBytesNotMatchingContentType serves on allowlistedHost. The mock
-// fetcher names a file's Content-Type from its extension, so the source is
-// sent as image/png.
-const mismatchedSourcePath = "/images/source.png"
-
-// newRoutesFetchingThrough returns both image routes, and the Handlers behind
-// them, whose image service fetches through fetcher and has allowlistedHost on
-// its allowlist. The handlers and the image service log to log.
-func newRoutesFetchingThrough(
-	t *testing.T, fetcher httpfetcher.Fetcher, log *slog.Logger,
-) (*Handlers, http.Handler) {
-	t.Helper()
-
-	cache, err := imgcache.NewCache(setupTestDB(t), imgcache.CacheConfig{
-		StateDir:    t.TempDir(),
-		NegativeTTL: 5 * time.Minute,
-		MaxBytes:    1 << 30,
-	}, prometheus.NewRegistry())
-	if err != nil {
-		t.Fatalf("imgcache.NewCache() error = %v", err)
-	}
-
-	svc, err := imgcache.NewService(&imgcache.ServiceConfig{
-		Cache:   cache,
-		Fetcher: fetcher,
-		Processor: imageprocessor.New(imageprocessor.Params{
-			MaxInputBytes:           50 << 20,
-			MaxConcurrentProcessing: 2,
-		}),
-		SigningKey:      testSigningKey,
-		Allowlist:       []string{allowlistedHost},
-		MaxResponseSize: 50 << 20,
-		Logger:          log,
-	})
-	if err != nil {
-		t.Fatalf("imgcache.NewService() error = %v", err)
-	}
-
-	encGen, err := encurl.NewGenerator(testSigningKey)
-	if err != nil {
-		t.Fatalf("encurl.NewGenerator() error = %v", err)
-	}
-
-	h := &Handlers{log: log, imgSvc: svc, encGen: encGen}
-
-	r := chi.NewRouter()
-	r.Get("/v1/image/*", h.HandleImage())
-	r.Get("/v1/e/{token}/*", h.HandleImageEnc())
-
-	return h, r
-}
-
-// mismatchedSourcePlainURL returns the /v1/image/ URL of mismatchedSourcePath
-// on allowlistedHost at 50x50 as a JPEG.
-func mismatchedSourcePlainURL(*testing.T, *Handlers) string {
-	return "/v1/image/" + allowlistedHost + mismatchedSourcePath + "/50x50.jpeg"
-}
-
-// mismatchedSourceEncURL returns an encrypted /v1/e/ URL, made with h's
-// generator, of mismatchedSourcePath on allowlistedHost at 50x50 as a JPEG.
-func mismatchedSourceEncURL(t *testing.T, h *Handlers) string {
-	t.Helper()
-
-	token, err := h.encGen.Generate(&imagerequest.Request{
-		Source: imagerequest.Source{
-			Host: allowlistedHost,
-			Path: mismatchedSourcePath,
-		},
-		Transform: imagerequest.Transform{
-			Size:   imagerequest.Size{Width: 50, Height: 50},
-			Format: imagerequest.FormatJPEG,
-		},
-	})
-	if err != nil {
-		t.Fatalf("Generate() error = %v", err)
-	}
-
-	return "/v1/e/" + token + "/img.jpg"
-}
-
-// loggedLevels reads the JSON log lines in logs and returns the messages
-// logged at each level.
-func loggedLevels(t *testing.T, logs *bytes.Buffer) map[string][]string {
-	t.Helper()
-
-	t.Logf("logged:\n%s", logs.String())
-
-	messages := make(map[string][]string)
-
-	dec := json.NewDecoder(logs)
-	for dec.More() {
-		var line struct {
-			Level string `json:"level"`
-			Msg   string `json:"msg"`
-		}
-
-		err := dec.Decode(&line)
-		if err != nil {
-			t.Fatalf("decoding log line: %v", err)
-		}
-
-		messages[line.Level] = append(messages[line.Level], line.Msg)
-	}
-
-	return messages
-}
-
-// TestFirstBytesNotMatchingContentType checks that both image routes answer
-// 415 for an upstream body whose first bytes are not those of the format its
-// Content-Type names, and log it as a refused source, not as an error of
-// pixa's. The next request for that source must answer 502 without fetching
-// it again, as after an upstream error status.
-func TestFirstBytesNotMatchingContentType(t *testing.T) {
-	t.Parallel()
-
-	bodies := map[string][]byte{
-		"JPEG sent as image/png":          generateTestJPEG(t, 10, 10, color.Black),
-		"text sent as image/png":          []byte("This is just text, not a PNG"),
-		"body too short to name a format": []byte("short"),
-	}
-
-	// The source's URL on each image route.
-	sourceURLs := map[string]func(*testing.T, *Handlers) string{
-		"plain URL":     mismatchedSourcePlainURL,
-		"encrypted URL": mismatchedSourceEncURL,
-	}
-
-	for bodyName, body := range bodies {
-		for urlName, sourceURL := range sourceURLs {
-			t.Run(urlName+", "+bodyName, func(t *testing.T) {
-				t.Parallel()
-
-				fetcher := &countingFetcher{
-					Fetcher: httpfetcher.NewMock(fstest.MapFS{
-						allowlistedHost + mismatchedSourcePath: &fstest.MapFile{
-							Data: body,
-						},
-					}),
-				}
-
-				var logs bytes.Buffer
-
-				h, routes := newRoutesFetchingThrough(t, fetcher,
-					slog.New(slog.NewJSONHandler(&logs, nil)))
-				target := sourceURL(t, h)
-
-				checkErrorBody(t, sendGet(t, routes, target),
-					http.StatusUnsupportedMediaType, "unsupported source format")
-
-				levels := loggedLevels(t, &logs)
-				if len(levels[slog.LevelError.String()]) != 0 {
-					t.Errorf("logged at error level: %q",
-						levels[slog.LevelError.String()])
-				}
-
-				if !slices.Contains(levels[slog.LevelWarn.String()], "source refused") {
-					t.Error(`no "source refused" line logged at warning level`)
-				}
-
-				checkErrorBody(t, sendGet(t, routes, target),
-					http.StatusBadGateway, "upstream error")
-
-				if n := fetcher.fetches.Load(); n != 1 {
-					t.Errorf("upstream fetched %d times, want 1", n)
-				}
-			})
-		}
-	}
-}

internal/handlers/format_auto.go

@@ -8,7 +8,7 @@ import (
 	"strconv"
 	"strings"
 
-	"sneak.berlin/go/pixa/internal/imagerequest"
+	"sneak.berlin/go/pixa/internal/imgcache"
 )
 
 // Errors for an Accept header that an auto URL cannot be served for.
@@ -24,9 +24,9 @@ var (
 // header that is not valid and 406 for one that allows none of the formats,
 // and reports whether req can be served. Any other format is left as it is.
 func (s *Handlers) chooseAutoFormat(
-	w http.ResponseWriter, r *http.Request, req *imagerequest.Request,
+	w http.ResponseWriter, r *http.Request, req *imgcache.ImageRequest,
 ) bool {
-	if req.Transform.Format != imagerequest.FormatAuto {
+	if req.Format != imgcache.FormatAuto {
 		return true
 	}
 
@@ -45,7 +45,7 @@ func (s *Handlers) chooseAutoFormat(
 		return false
 	}
 
-	req.Transform.Format = format
+	req.Format = format
 
 	return true
 }
@@ -56,26 +56,26 @@ func (s *Handlers) chooseAutoFormat(
 // specific entry of image/jpeg, image/* and */* allows it, or when it names
 // nothing. A q of 0 refuses a format. JPEG XL, AVIF and WebP must be named, as
 // clients that cannot show them send image/* and */* too.
-func formatForAccept(accept string) (imagerequest.Format, error) {
+func formatForAccept(accept string) (imgcache.ImageFormat, error) {
 	qualities, err := parseAccept(accept)
 	if err != nil {
 		return "", err
 	}
 
 	if len(qualities) == 0 {
-		return imagerequest.FormatJPEG, nil
+		return imgcache.FormatJPEG, nil
 	}
 
 	if qualities["image/jxl"] > 0 {
-		return imagerequest.FormatJXL, nil
+		return imgcache.FormatJXL, nil
 	}
 
 	if qualities["image/avif"] > 0 {
-		return imagerequest.FormatAVIF, nil
+		return imgcache.FormatAVIF, nil
 	}
 
 	if qualities["image/webp"] > 0 {
-		return imagerequest.FormatWebP, nil
+		return imgcache.FormatWebP, nil
 	}
 
 	// For JPEG, the most specific entry the header has decides
@@ -89,7 +89,7 @@ func formatForAccept(accept string) (imagerequest.Format, error) {
 	}
 
 	if quality > 0 {
-		return imagerequest.FormatJPEG, nil
+		return imgcache.FormatJPEG, nil
 	}
 
 	return "", errNotAcceptable

internal/handlers/format_auto_internal_test.go

@@ -12,7 +12,8 @@ import (
 
 	"github.com/go-chi/chi/v5"
 
-	"sneak.berlin/go/pixa/internal/imagerequest"
+	"sneak.berlin/go/pixa/internal/encurl"
+	"sneak.berlin/go/pixa/internal/imgcache"
 )
 
 // The content types the tests below expect.
@@ -32,24 +33,24 @@ func TestFormatForAccept(t *testing.T) {
 	tests := []struct {
 		name    string
 		accept  string
-		want    imagerequest.Format
+		want    imgcache.ImageFormat
 		wantErr error
 	}{
 		{"AVIF-capable browser",
 			"image/avif,image/webp,image/apng,image/svg+xml,image/*,*/*;q=0.8",
-			imagerequest.FormatAVIF, nil},
+			imgcache.FormatAVIF, nil},
 		{"WebP-capable browser",
 			"image/webp,image/png,image/svg+xml,image/*;q=0.8,*/*;q=0.5",
-			imagerequest.FormatWebP, nil},
+			imgcache.FormatWebP, nil},
-		{"WebP only", webpType, imagerequest.FormatWebP, nil},
+		{"WebP only", webpType, imgcache.FormatWebP, nil},
-		{"neither", "image/png,image/*;q=0.8,*/*;q=0.5", imagerequest.FormatJPEG, nil},
+		{"neither", "image/png,image/*;q=0.8,*/*;q=0.5", imgcache.FormatJPEG, nil},
-		{"wildcard only", "*/*", imagerequest.FormatJPEG, nil},
+		{"wildcard only", "*/*", imgcache.FormatJPEG, nil},
-		{"image wildcard only", "image/*", imagerequest.FormatJPEG, nil},
+		{"image wildcard only", "image/*", imgcache.FormatJPEG, nil},
-		{"absent", "", imagerequest.FormatJPEG, nil},
+		{"absent", "", imgcache.FormatJPEG, nil},
-		{"q=0 on AVIF", "image/avif;q=0,image/webp,*/*", imagerequest.FormatWebP, nil},
+		{"q=0 on AVIF", "image/avif;q=0,image/webp,*/*", imgcache.FormatWebP, nil},
 		{"AVIF named twice, once with q=0", "image/avif,image/avif;q=0.0,*/*",
-			imagerequest.FormatJPEG, nil},
+			imgcache.FormatJPEG, nil},
-		{"upper case and spaces", " Image/AVIF ; Q=0.5 ", imagerequest.FormatAVIF, nil},
+		{"upper case and spaces", " Image/AVIF ; Q=0.5 ", imgcache.FormatAVIF, nil},
 		{"q=0 on JPEG", "image/jpeg;q=0,image/*", "", errNotAcceptable},
 		{"q=0 on everything", "*/*;q=0", "", errNotAcceptable},
 		{"PNG only", "image/png", "", errNotAcceptable},
@@ -75,33 +76,27 @@ func TestFormatForAccept(t *testing.T) {
 
 // autoPhotoURLs returns a signed /v1/image/ URL and an encrypted /v1/e/ URL,
 // both valid for a minute, for the JPEG at photoPath on signedHost at 50x50 in
-// the format auto. The first is signed with testSigningKey, the key of the
+// the format auto, made with h's image service and generator.
-// image service newSignedHostServer builds, and the second is made with h's
-// generator.
 func autoPhotoURLs(t *testing.T, h *Handlers) (string, string) {
 	t.Helper()
 
-	signedURL := generateSignedURL(testSigningKey, &imagerequest.Request{
+	signedURL, err := h.imgSvc.GenerateSignedURL("", &imgcache.ImageRequest{
-		Source: imagerequest.Source{
+		SourceHost: signedHost,
-			Host: signedHost,
+		SourcePath: photoPath,
-			Path: photoPath,
+		Size:       imgcache.Size{Width: 50, Height: 50},
-		},
+		Format:     imgcache.FormatAuto,
-		Transform: imagerequest.Transform{
-			Size:   imagerequest.Size{Width: 50, Height: 50},
-			Format: imagerequest.FormatAuto,
-		},
 	}, time.Minute)
+	if err != nil {
+		t.Fatalf("GenerateSignedURL() error = %v", err)
+	}
 
-	token, err := h.encGen.Generate(&imagerequest.Request{
+	token, err := h.encGen.Generate(&encurl.Payload{
-		Source: imagerequest.Source{
+		SourceHost: signedHost,
-			Host: signedHost,
+		SourcePath: photoPath,
-			Path: photoPath,
+		Width:      50,
-		},
+		Height:     50,
-		Transform: imagerequest.Transform{
+		Format:     imgcache.FormatAuto,
-			Size:   imagerequest.Size{Width: 50, Height: 50},
+		ExpiresAt:  time.Now().Add(time.Minute).Unix(),
-			Format: imagerequest.FormatAuto,
-		},
-		Expires: time.Now().Add(time.Minute),
 	})
 	if err != nil {
 		t.Fatalf("Generate() error = %v", err)
@@ -187,18 +182,17 @@ func TestFormatAuto_ChosenFromAccept(t *testing.T) {
 func TestFormatAuto_SignatureCoversAuto(t *testing.T) {
 	t.Parallel()
 
-	_, srv := newSignedHostServer(t, slog.New(slog.DiscardHandler))
+	h, srv := newSignedHostServer(t, slog.New(slog.DiscardHandler))
 
-	signedForAVIF := generateSignedURL(testSigningKey, &imagerequest.Request{
+	signedForAVIF, err := h.imgSvc.GenerateSignedURL("", &imgcache.ImageRequest{
-		Source: imagerequest.Source{
+		SourceHost: signedHost,
-			Host: signedHost,
+		SourcePath: photoPath,
-			Path: photoPath,
+		Size:       imgcache.Size{Width: 50, Height: 50},
-		},
+		Format:     imgcache.FormatAVIF,
-		Transform: imagerequest.Transform{
-			Size:   imagerequest.Size{Width: 50, Height: 50},
-			Format: imagerequest.FormatAVIF,
-		},
 	}, time.Minute)
+	if err != nil {
+		t.Fatalf("GenerateSignedURL() error = %v", err)
+	}
 
 	target := strings.Replace(signedForAVIF, "/50x50.avif?", "/50x50.auto?", 1)
 	if target == signedForAVIF {

internal/handlers/handlers.go

@@ -4,6 +4,7 @@ package handlers
 import (
 	"context"
 	"encoding/json"
+	"errors"
 	"log/slog"
 	"net/http"
 	"time"
@@ -11,8 +12,10 @@ import (
 	"go.uber.org/fx"
 	"sneak.berlin/go/pixa/internal/allowlist"
 	"sneak.berlin/go/pixa/internal/config"
+	"sneak.berlin/go/pixa/internal/database"
 	"sneak.berlin/go/pixa/internal/encurl"
 	"sneak.berlin/go/pixa/internal/healthcheck"
+	"sneak.berlin/go/pixa/internal/httpfetcher"
 	"sneak.berlin/go/pixa/internal/imgcache"
 	"sneak.berlin/go/pixa/internal/logger"
 	"sneak.berlin/go/pixa/internal/session"
@@ -24,19 +27,24 @@ type Params struct {
 
 	Logger      *logger.Logger
 	Healthcheck *healthcheck.Healthcheck
+	Database    *database.Database
 	Config      *config.Config
 
-	ImageService          *imgcache.Service
+	// Fetcher, when provided, fetches upstream images in place of the
-	SessionManager        *session.Manager
+	// fetcher the handlers build from the config. Only tests provide one;
-	EncryptedURLGenerator *encurl.Generator
+	// pixad does not.
+	Fetcher httpfetcher.Fetcher `optional:"true"`
 }
 
 // Handlers provides HTTP request handlers.
 type Handlers struct {
 	log         *slog.Logger
 	hc          *healthcheck.Healthcheck
+	db          *database.Database
 	config      *config.Config
+	fetcher     httpfetcher.Fetcher
 	imgSvc      *imgcache.Service
+	imgCache    *imgcache.Cache
 	sessMgr     *session.Manager
 	encGen      *encurl.Generator
 	csrfProtect func(http.Handler) http.Handler
@@ -47,22 +55,42 @@ type Handlers struct {
 }
 
 // New creates a new Handlers instance.
-func New(_ fx.Lifecycle, params Params) (*Handlers, error) {
+func New(lc fx.Lifecycle, params Params) (*Handlers, error) {
 	csrfProtect, err := newCSRFProtect(params.Config.SigningKey, params.Config.Debug)
 	if err != nil {
 		return nil, err
 	}
 
-	return &Handlers{
+	s := &Handlers{
 		log:              params.Logger.Get(),
 		hc:               params.Healthcheck,
+		db:               params.Database,
 		config:           params.Config,
-		imgSvc:           params.ImageService,
+		fetcher:          params.Fetcher,
-		sessMgr:          params.SessionManager,
-		encGen:           params.EncryptedURLGenerator,
 		csrfProtect:      csrfProtect,
 		refererBlocklist: allowlist.New(params.Config.RefererBlocklist),
-	}, nil
+	}
+
+	lc.Append(fx.Hook{
+		//nolint:contextcheck // the cache's goroutines outlive OnStart; OnStop stops them
+		OnStart: func(_ context.Context) error {
+			return s.initImageService()
+		},
+		// The pending counts are written here, before the database's stop
+		// hook closes it.
+		OnStop: func(ctx context.Context) error {
+			if s.imgCache == nil {
+				return nil
+			}
+
+			return errors.Join(
+				s.imgCache.StopEviction(ctx),
+				s.imgCache.StopPendingCountWrites(ctx),
+			)
+		},
+	})
+
+	return s, nil
 }
 
 // WaitForProcessing waits until no image is being processed, or until ctx
@@ -71,6 +99,94 @@ func (s *Handlers) WaitForProcessing(ctx context.Context) int {
 	return s.imgSvc.WaitForProcessing(ctx)
 }
 
+// newCacheConfig builds the image cache's configuration from cfg.
+// cache_max_bytes: 0 disables the disk cache entirely; any other value
+// is the eviction limit in bytes; when it is omitted, the cache works
+// out the default limit itself.
+func newCacheConfig(cfg *config.Config, log *slog.Logger) imgcache.CacheConfig {
+	return imgcache.CacheConfig{
+		StateDir:           cfg.StateDir,
+		NegativeTTL:        imgcache.DefaultNegativeTTL,
+		MaxBytes:           cfg.CacheMaxBytes,
+		UseDefaultMaxBytes: !cfg.CacheMaxBytesExplicit,
+		DisableDiskCache:   cfg.CacheMaxBytesExplicit && cfg.CacheMaxBytes == 0,
+		Logger:             log,
+	}
+}
+
+// initImageService initializes the image cache and service.
+func (s *Handlers) initImageService() error {
+	cache, err := imgcache.NewCache(s.db.DB(), newCacheConfig(s.config, s.log))
+	if err != nil {
+		return err
+	}
+
+	s.imgCache = cache
+
+	// Background eviction: startup reconciliation, then periodic and
+	// write-pressure passes, and the removal of expired negative cache
+	// rows, which is all it does when the disk cache is disabled.
+	cache.StartEviction(imgcache.DefaultEvictionInterval)
+
+	// Writes the counts requests could not write by their deadline
+	cache.StartPendingCountWrites()
+
+	// Create the fetcher config
+	fetcherCfg := httpfetcher.DefaultConfig()
+	fetcherCfg.AllowHTTP = s.config.AllowHTTP
+	fetcherCfg.Timeout = s.config.UpstreamFetchTimeout
+	fetcherCfg.MaxResponseSize = s.config.UpstreamMaxResponseSize
+
+	if s.config.UpstreamConnectionsPerHost > 0 {
+		fetcherCfg.MaxConnectionsPerHost = s.config.UpstreamConnectionsPerHost
+	}
+
+	fetcherCfg.MaxConnections = s.config.UpstreamConnections
+	fetcherCfg.BlockedNetworks = s.config.BlockedNetworks
+
+	// Create the service. With no fetcher provided, it builds its own from
+	// fetcherCfg.
+	svc, err := imgcache.NewService(&imgcache.ServiceConfig{
+		Cache:                   cache,
+		FetcherConfig:           fetcherCfg,
+		Fetcher:                 s.fetcher,
+		SigningKey:              s.config.SigningKey,
+		Allowlist:               s.config.AllowlistHosts,
+		MaxConcurrentProcessing: s.config.MaxConcurrentProcessing,
+		Logger:                  s.log,
+	})
+	if err != nil {
+		return err
+	}
+
+	s.imgSvc = svc
+	s.log.Info("image service initialized")
+
+	// Initialize session manager (signing key is validated at config load
+	// time). Session cookies are always Secure/HttpOnly/SameSite=Strict.
+	// The random value that each logout replaces is saved in the database,
+	// so it outlasts a restart.
+	sessMgr, err := session.NewManagerWithDatabase(
+		context.Background(), s.config.SigningKey, s.db.DB())
+	if err != nil {
+		return err
+	}
+
+	s.sessMgr = sessMgr
+
+	// Initialize encrypted URL generator
+	encGen, err := encurl.NewGenerator(s.config.SigningKey)
+	if err != nil {
+		return err
+	}
+
+	s.encGen = encGen
+
+	s.log.Info("session manager and URL generator initialized")
+
+	return nil
+}
+
 func (s *Handlers) respondJSON(w http.ResponseWriter, data any, status int) {
 	w.Header().Set("Content-Type", "application/json")
 	w.WriteHeader(status)

internal/handlers/handlers_internal_test.go

@@ -18,16 +18,15 @@ import (
 	"time"
 
 	"github.com/go-chi/chi/v5"
-	"github.com/prometheus/client_golang/prometheus"
 	"sneak.berlin/go/pixa/internal/database"
 	"sneak.berlin/go/pixa/internal/httpfetcher"
-	"sneak.berlin/go/pixa/internal/imageprocessor"
 	"sneak.berlin/go/pixa/internal/imgcache"
 )
 
 // testFixtures contains test data.
 type testFixtures struct {
 	handler  *Handlers
+	service  *imgcache.Service
 	goodHost string
 }
 
@@ -49,22 +48,16 @@ func setupTestHandler(t *testing.T) *testFixtures {
 	cache, err := imgcache.NewCache(db, imgcache.CacheConfig{
 		StateDir:    tmpDir,
 		NegativeTTL: 5 * time.Minute,
-		MaxBytes:    1 << 30,
+	})
-	}, prometheus.NewRegistry())
 	if err != nil {
 		t.Fatalf("failed to create cache: %v", err)
 	}
 
 	svc, err := imgcache.NewService(&imgcache.ServiceConfig{
-		Cache:   cache,
+		Cache:      cache,
-		Fetcher: newMockFetcher(mockFS),
+		Fetcher:    newMockFetcher(mockFS),
-		Processor: imageprocessor.New(imageprocessor.Params{
+		SigningKey: "test-signing-key-must-be-32-chars",
-			MaxInputBytes:           50 << 20,
+		Allowlist:  []string{goodHost},
-			MaxConcurrentProcessing: 2,
-		}),
-		SigningKey:      "test-signing-key-must-be-32-chars",
-		Allowlist:       []string{goodHost},
-		MaxResponseSize: 50 << 20,
 	})
 	if err != nil {
 		t.Fatalf("failed to create service: %v", err)
@@ -77,6 +70,7 @@ func setupTestHandler(t *testing.T) *testFixtures {
 
 	return &testFixtures{
 		handler:  h,
+		service:  svc,
 		goodHost: goodHost,
 	}
 }

internal/handlers/image.go

@@ -13,9 +13,7 @@ import (
 	"sneak.berlin/go/pixa/internal/encurl"
 	"sneak.berlin/go/pixa/internal/httpfetcher"
 	"sneak.berlin/go/pixa/internal/imageprocessor"
-	"sneak.berlin/go/pixa/internal/imagerequest"
 	"sneak.berlin/go/pixa/internal/imgcache"
-	"sneak.berlin/go/pixa/internal/magic"
 )
 
 // HandleImage handles the main image proxy route:
@@ -36,8 +34,8 @@ func (s *Handlers) HandleImage() http.HandlerFunc {
 		err := s.imgSvc.ValidateRequest(req)
 		if err != nil {
 			s.log.Warn("signature validation failed",
-				"host", req.Source.Host,
+				"host", req.SourceHost,
-				"path", req.Source.Path,
+				"path", req.SourcePath,
 				"error", err,
 			)
 			s.respondError(w, "unauthorized", http.StatusUnauthorized)
@@ -51,7 +49,7 @@ func (s *Handlers) HandleImage() http.HandlerFunc {
 		}
 
 		// Get cache key for logging
-		cacheKey := imagerequest.CacheKey(req)
+		cacheKey := imgcache.CacheKey(req)
 
 		// Get the image (from cache or fetch/process)
 		startTime := time.Now()
@@ -82,17 +80,17 @@ func (s *Handlers) HandleRobotsTxt() http.HandlerFunc {
 }
 
 // parseImageRequest parses the image URL's path and query parameters into
-// an image request. On invalid input it writes an error response and
+// an ImageRequest. On invalid input it writes an error response and
 // returns false.
 func (s *Handlers) parseImageRequest(
 	w http.ResponseWriter, r *http.Request,
-) (*imagerequest.Request, bool) {
+) (*imgcache.ImageRequest, bool) {
 	// The path is parsed decoded once, as r.URL.Path holds it, and not from
 	// chi's wildcard: chi routes on the path as the client wrote it whenever
 	// that is not Go's own encoding of it, so its wildcard would still hold
 	// the %3F before a source query when, say, a "/" in the query is written
 	// as %2F
-	req, err := imagerequest.ParseImageURL(r.URL.Path)
+	parsed, err := imgcache.ParseImageURL(r.URL.Path)
 	if err != nil {
 		s.log.Warn("failed to parse image URL",
 			"path", r.URL.Path,
@@ -103,6 +101,9 @@ func (s *Handlers) parseImageRequest(
 		return nil, false
 	}
 
+	// Convert to ImageRequest
+	req := parsed.ToImageRequest()
+
 	// Parse signature params from query string. r.URL.Query() would silently
 	// drop a pair it cannot decode, such as q=80%, so that q would be served
 	// at 85; a query string that cannot be decoded is refused instead. A
@@ -146,7 +147,7 @@ func (s *Handlers) parseImageRequest(
 		return nil, false
 	}
 
-	req.Transform.Quality, err = parseFormInt(query, "q",
+	req.Quality, err = parseFormInt(query, "q",
 		encurl.DefaultQuality, minQuality, maxQuality)
 	if err != nil {
 		s.respondError(w, fmt.Sprintf("%v, got %q", err, qStr),
@@ -158,23 +159,23 @@ func (s *Handlers) parseImageRequest(
 	// Only a fit missing from the URL is cover. A fit in the URL that is not a
 	// fit mode is refused by the fit-mode check below; that check would take an
 	// empty fit as missing, so an empty one is refused here.
-	req.Transform.FitMode = imagerequest.Fit(query.Get("fit"))
+	req.FitMode = imgcache.FitMode(query.Get("fit"))
-	if query.Has("fit") && req.Transform.FitMode == "" {
+	if query.Has("fit") && req.FitMode == "" {
 		s.respondError(w, `invalid fit: not a fit mode, got ""`, http.StatusBadRequest)
 
 		return nil, false
 	}
 
 	// Default fit mode if not set
-	if req.Transform.FitMode == "" {
+	if req.FitMode == "" {
-		req.Transform.FitMode = imagerequest.FitCover
+		req.FitMode = imgcache.FitCover
 	}
 
 	// Enforce dimension and fit-mode bounds, shared with the encrypted-URL
 	// route. Dimensions are already bounded by the path parser above; this
 	// also rejects an unrecognized fit mode with 400 instead of letting it
 	// reach the processor as a 500.
-	err = imagerequest.ValidateImageRequest(req)
+	err = imgcache.ValidateImageRequest(req)
 	if err != nil {
 		s.respondError(w, "invalid image request: "+err.Error(),
 			http.StatusBadRequest)
@@ -217,23 +218,11 @@ func (s *Handlers) HandleTooManyRequests() http.HandlerFunc {
 
 // respondImageError maps image retrieval errors to HTTP responses.
 func (s *Handlers) respondImageError(
-	w http.ResponseWriter, req *imagerequest.Request, err error,
+	w http.ResponseWriter, req *imgcache.ImageRequest, err error,
 ) {
-	// An upstream body whose first bytes are not those of the format its
-	// Content-Type names is the upstream's error, not pixa's: the image
-	// service has logged it as a refused source.
-	if errors.Is(err, magic.ErrMagicByteMismatch) ||
-		errors.Is(err, magic.ErrUnknownFormat) ||
-		errors.Is(err, magic.ErrNotEnoughData) {
-		s.respondError(w, "unsupported source format",
-			http.StatusUnsupportedMediaType)
-
-		return
-	}
-
 	s.log.Error("failed to get image",
-		"host", req.Source.Host,
+		"host", req.SourceHost,
-		"path", req.Source.Path,
+		"path", req.SourcePath,
 		"error", err,
 	)
 
@@ -275,14 +264,6 @@ func (s *Handlers) respondImageError(
 		return
 	}
 
-	if errors.Is(err, imageprocessor.ErrAVIFOutputTooLarge) {
-		s.respondError(w, fmt.Sprintf("size too large for AVIF: the output "+
-			"would be above %d pixels", imageprocessor.MaxAVIFOutputPixels),
-			http.StatusBadRequest)
-
-		return
-	}
-
 	s.respondError(w, "internal error", http.StatusInternalServerError)
 }
 
@@ -344,8 +325,8 @@ func notModified(w http.ResponseWriter, r *http.Request, etag string) bool {
 // handling conditional and HEAD requests.
 func (s *Handlers) writeImageResponse(
 	w http.ResponseWriter, r *http.Request,
-	req *imagerequest.Request, resp *imgcache.ImageResponse,
+	req *imgcache.ImageRequest, resp *imgcache.ImageResponse,
-	cacheKey imagerequest.VariantKey, startTime time.Time,
+	cacheKey imgcache.VariantKey, startTime time.Time,
 ) {
 	// Set response headers
 	w.Header().Set("Content-Type", resp.ContentType)
@@ -386,7 +367,7 @@ func (s *Handlers) writeImageResponse(
 		"cache_key", cacheKey,
 		"cache_status", resp.CacheStatus,
 		"duration_ms", duration.Milliseconds(),
-		"format", req.Transform.Format,
+		"format", req.Format,
 		"served_bytes", servedBytes,
 		"fetched_bytes", resp.FetchedBytes,
 	)

internal/handlers/image_cache_control_internal_test.go

@@ -12,11 +12,8 @@ import (
 	"time"
 
 	"github.com/go-chi/chi/v5"
-	"github.com/prometheus/client_golang/prometheus"
 
 	"sneak.berlin/go/pixa/internal/encurl"
-	"sneak.berlin/go/pixa/internal/imageprocessor"
-	"sneak.berlin/go/pixa/internal/imagerequest"
 	"sneak.berlin/go/pixa/internal/imgcache"
 )
 
@@ -35,8 +32,7 @@ func newSignedHostServer(
 	cache, err := imgcache.NewCache(setupTestDB(t), imgcache.CacheConfig{
 		StateDir:    t.TempDir(),
 		NegativeTTL: 5 * time.Minute,
-		MaxBytes:    1 << 30,
+	})
-	}, prometheus.NewRegistry())
 	if err != nil {
 		t.Fatalf("imgcache.NewCache() error = %v", err)
 	}
@@ -48,13 +44,8 @@ func newSignedHostServer(
 		Fetcher: newMockFetcher(fstest.MapFS{
 			signedHost + photoPath: &fstest.MapFile{Data: jpegData},
 		}),
-		Processor: imageprocessor.New(imageprocessor.Params{
+		SigningKey: testSigningKey,
-			MaxInputBytes:           50 << 20,
+		Logger:     log,
-			MaxConcurrentProcessing: 2,
-		}),
-		SigningKey:      testSigningKey,
-		MaxResponseSize: 50 << 20,
-		Logger:          log,
 	})
 	if err != nil {
 		t.Fatalf("imgcache.NewService() error = %v", err)
@@ -114,18 +105,17 @@ func getMaxAge(t *testing.T, srv http.Handler, target string) int {
 func TestHandleImage_SignedURL_MaxAgeEndsAtExp(t *testing.T) {
 	t.Parallel()
 
-	_, srv := newSignedHostServer(t, slog.New(slog.DiscardHandler))
+	h, srv := newSignedHostServer(t, slog.New(slog.DiscardHandler))
 
-	signedURL := generateSignedURL(testSigningKey, &imagerequest.Request{
+	signedURL, err := h.imgSvc.GenerateSignedURL("", &imgcache.ImageRequest{
-		Source: imagerequest.Source{
+		SourceHost: signedHost,
-			Host: signedHost,
+		SourcePath: photoPath,
-			Path: photoPath,
+		Size:       imgcache.Size{Width: 50, Height: 50},
-		},
+		Format:     imgcache.FormatJPEG,
-		Transform: imagerequest.Transform{
-			Size:   imagerequest.Size{Width: 50, Height: 50},
-			Format: imagerequest.FormatJPEG,
-		},
 	}, time.Minute)
+	if err != nil {
+		t.Fatalf("GenerateSignedURL() error = %v", err)
+	}
 
 	maxAge := getMaxAge(t, srv, signedURL)
 	if maxAge < 50 || maxAge > 60 {
@@ -178,13 +168,13 @@ func TestHandleImageEnc_MaxAge(t *testing.T) {
 
 	tests := []struct {
 		name        string
-		expires     time.Time
+		expiresAt   int64
 		wantAtLeast int
 		wantAtMost  int
 	}{
-		{"60 second TTL", time.Now().Add(time.Minute), 50, 60},
+		{"60 second TTL", time.Now().Add(time.Minute).Unix(), 50, 60},
-		{"two-year TTL", time.Now().Add(2 * 365 * 24 * time.Hour), 31536000, 31536000},
+		{"two-year TTL", time.Now().Add(2 * 365 * 24 * time.Hour).Unix(), 31536000, 31536000},
-		{"no TTL", time.Time{}, 31536000, 31536000},
+		{"no TTL", 0, 31536000, 31536000},
 	}
 
 	for _, tt := range tests {
@@ -193,16 +183,13 @@ func TestHandleImageEnc_MaxAge(t *testing.T) {
 
 			h, srv := newSignedHostServer(t, slog.New(slog.DiscardHandler))
 
-			token, err := h.encGen.Generate(&imagerequest.Request{
+			token, err := h.encGen.Generate(&encurl.Payload{
-				Source: imagerequest.Source{
+				SourceHost: signedHost,
-					Host: signedHost,
+				SourcePath: photoPath,
-					Path: photoPath,
+				Width:      50,
-				},
+				Height:     50,
-				Transform: imagerequest.Transform{
+				Format:     imgcache.FormatJPEG,
-					Size:   imagerequest.Size{Width: 50, Height: 50},
+				ExpiresAt:  tt.expiresAt,
-					Format: imagerequest.FormatJPEG,
-				},
-				Expires: tt.expires,
 			})
 			if err != nil {
 				t.Fatalf("Generate() error = %v", err)

internal/handlers/image_errors_internal_test.go

@@ -13,10 +13,7 @@ import (
 	"time"
 
 	"github.com/go-chi/chi/v5"
-	"github.com/prometheus/client_golang/prometheus"
 	"sneak.berlin/go/pixa/internal/httpfetcher"
-	"sneak.berlin/go/pixa/internal/imageprocessor"
-	"sneak.berlin/go/pixa/internal/imagerequest"
 	"sneak.berlin/go/pixa/internal/imgcache"
 	"sneak.berlin/go/pixa/internal/signature"
 )
@@ -33,22 +30,16 @@ func newImageRoute(t *testing.T, fetcher httpfetcher.Fetcher) http.Handler {
 	cache, err := imgcache.NewCache(setupTestDB(t), imgcache.CacheConfig{
 		StateDir:    t.TempDir(),
 		NegativeTTL: 5 * time.Minute,
-		MaxBytes:    1 << 30,
+	})
-	}, prometheus.NewRegistry())
 	if err != nil {
 		t.Fatalf("failed to create cache: %v", err)
 	}
 
 	svc, err := imgcache.NewService(&imgcache.ServiceConfig{
-		Cache:   cache,
+		Cache:      cache,
-		Fetcher: fetcher,
+		Fetcher:    fetcher,
-		Processor: imageprocessor.New(imageprocessor.Params{
+		SigningKey: testSigningKey,
-			MaxInputBytes:           50 << 20,
+		Allowlist:  []string{allowlistedHost},
-			MaxConcurrentProcessing: 2,
-		}),
-		SigningKey:      testSigningKey,
-		Allowlist:       []string{allowlistedHost},
-		MaxResponseSize: 50 << 20,
 	})
 	if err != nil {
 		t.Fatalf("failed to create service: %v", err)
@@ -93,18 +84,15 @@ func photoURLWithSig(host, sig string, expires time.Time) string {
 // photoSignature returns the signature of photoURL(host) at the default
 // quality and fit, made with key and expiring at expires.
 func photoSignature(key, host string, expires time.Time) string {
-	return signature.New(key).Sign(&imagerequest.Request{
+	return signature.New(key).Sign(&signature.Request{
-		Source: imagerequest.Source{
+		SourceHost: host,
-			Host: host,
+		SourcePath: photoPath,
-			Path: photoPath,
+		Width:      50,
-		},
+		Height:     50,
-		Transform: imagerequest.Transform{
+		Format:     string(imgcache.FormatJPEG),
-			Size:    imagerequest.Size{Width: 50, Height: 50},
+		Quality:    85,
-			Format:  imagerequest.FormatJPEG,
+		FitMode:    string(imgcache.FitCover),
-			Quality: 85,
+		Expires:    expires,
-			FitMode: imagerequest.FitCover,
-		},
-		Expires: expires,
 	})
 }
 
@@ -176,12 +164,7 @@ func TestHandleImage_ErrorAnswers(t *testing.T) {
 	photos := newPhotoFetcher(t,
 		signedHost, parentHost, siblingHost, subdomainHost, appendedHost)
 	// The real fetcher refuses localhost before any lookup or connection.
-	realFetcher := httpfetcher.New(&httpfetcher.Config{
+	realFetcher := httpfetcher.New(httpfetcher.DefaultConfig())
-		Timeout:               30 * time.Second,
-		MaxResponseSize:       50 << 20,
-		MaxConnectionsPerHost: 20,
-		MaxConnections:        64,
-	})
 
 	exp := time.Now().Add(time.Hour)
 	expired := time.Now().Add(-time.Hour)
@@ -370,18 +353,15 @@ func TestHandleImage_HashInSourcePathOrQuery_Returns400(t *testing.T) {
 	photos := newPhotoFetcher(t, allowlistedHost, signedHost)
 	exp := time.Now().Add(time.Hour)
 
-	sig := signature.New(testSigningKey).Sign(&imagerequest.Request{
+	sig := signature.New(testSigningKey).Sign(&signature.Request{
-		Source: imagerequest.Source{
+		SourceHost: signedHost,
-			Host: signedHost,
+		SourcePath: photoPath + "#x",
-			Path: photoPath + "#x",
+		Width:      50,
-		},
+		Height:     50,
-		Transform: imagerequest.Transform{
+		Format:     string(imgcache.FormatJPEG),
-			Size:    imagerequest.Size{Width: 50, Height: 50},
+		Quality:    85,
-			Format:  imagerequest.FormatJPEG,
+		FitMode:    string(imgcache.FitCover),
-			Quality: 85,
+		Expires:    exp,
-			FitMode: imagerequest.FitCover,
-		},
-		Expires: exp,
 	})
 
 	tests := []struct {

internal/handlers/image_signature_internal_test.go

@@ -5,12 +5,11 @@ import (
 	"fmt"
 	"net/http"
 	"net/http/httptest"
-	"net/url"
 	"testing"
 	"time"
 
 	"github.com/go-chi/chi/v5"
-	"sneak.berlin/go/pixa/internal/imagerequest"
+	"sneak.berlin/go/pixa/internal/imgcache"
 	"sneak.berlin/go/pixa/internal/signature"
 )
 
@@ -37,43 +36,6 @@ func getImage(t *testing.T, fix *testFixtures, target string) int {
 	return rec.Code
 }
 
-// generateSignedURL returns the /v1/image/ URL of req, signed with key and
-// expiring after ttl, and sets req's expiry. An unset quality or fit of req is
-// first set to 85 or cover, the values the route uses when a URL has no q or
-// fit. The URL carries q and fit next to sig and exp, so the route verifies it
-// for the quality and fit it was signed with.
-func generateSignedURL(
-	key string, req *imagerequest.Request, ttl time.Duration,
-) string {
-	if req.Transform.Quality == 0 {
-		req.Transform.Quality = 85
-	}
-
-	if req.Transform.FitMode == "" {
-		req.Transform.FitMode = imagerequest.FitCover
-	}
-
-	req.Expires = time.Now().Add(ttl)
-	sig := signature.New(key).Sign(req)
-
-	// A source query follows the source path after a "?". The image route
-	// reads the path decoded once, so the whole path is written in Go's own
-	// percent-encoding of a URL path, which writes "?" as %3F and "%" as %25,
-	// and leaves "/", ";", ",", "=" and "&" as they are.
-	sourcePathAndQuery := req.Source.Path
-	if req.Source.Query != "" {
-		sourcePathAndQuery += "?" + req.Source.Query
-	}
-
-	unescapedPath := fmt.Sprintf("/v1/image/%s%s/%dx%d.%s",
-		req.Source.Host, sourcePathAndQuery,
-		req.Transform.Size.Width, req.Transform.Size.Height, req.Transform.Format)
-
-	return fmt.Sprintf("%s?sig=%s&exp=%d&q=%d&fit=%s",
-		(&url.URL{Path: unescapedPath}).EscapedPath(), sig, req.Expires.Unix(),
-		req.Transform.Quality, req.Transform.FitMode)
-}
-
 // TestHandleImage_SignatureCoversQualityAndFit signs a URL for quality 85
 // and fit cover, the values the route uses when a URL has no q or fit, and
 // sends that signature with each q and fit below.
@@ -82,18 +44,15 @@ func TestHandleImage_SignatureCoversQualityAndFit(t *testing.T) {
 
 	expires := time.Now().Add(time.Hour)
 	signer := signature.New("test-signing-key-must-be-32-chars")
-	sig := signer.Sign(&imagerequest.Request{
+	sig := signer.Sign(&signature.Request{
-		Source: imagerequest.Source{
+		SourceHost: signedHost,
-			Host: signedHost,
+		SourcePath: "/images/photo.jpg",
-			Path: "/images/photo.jpg",
+		Width:      50,
-		},
+		Height:     50,
-		Transform: imagerequest.Transform{
+		Format:     string(imgcache.FormatJPEG),
-			Size:    imagerequest.Size{Width: 50, Height: 50},
+		Quality:    85,
-			Format:  imagerequest.FormatJPEG,
+		FitMode:    string(imgcache.FitCover),
-			Quality: 85,
+		Expires:    expires,
-			FitMode: imagerequest.FitCover,
-		},
-		Expires: expires,
 	})
 	signedURL := fmt.Sprintf("/v1/image/%s/images/photo.jpg/50x50.jpeg?sig=%s&exp=%d",
 		signedHost, sig, expires.Unix())
@@ -121,17 +80,17 @@ func TestHandleImage_SignatureCoversQualityAndFit(t *testing.T) {
 	}
 }
 
-// TestHandleImage_GeneratedSignedURLVerifies sends URLs built by
+// TestHandleImage_GeneratedSignedURLVerifies sends URLs built by the
-// generateSignedURL to the route.
+// service's signed-URL generator to the route.
 func TestHandleImage_GeneratedSignedURLVerifies(t *testing.T) {
 	t.Parallel()
 
 	tests := []struct {
 		name    string
 		quality int
-		fitMode imagerequest.Fit
+		fitMode imgcache.FitMode
 	}{
-		{"quality 40 and fit contain", 40, imagerequest.FitContain},
+		{"quality 40 and fit contain", 40, imgcache.FitContain},
 		{"quality and fit unset", 0, ""},
 	}
 
@@ -139,21 +98,21 @@ func TestHandleImage_GeneratedSignedURLVerifies(t *testing.T) {
 		t.Run(tt.name, func(t *testing.T) {
 			t.Parallel()
 
-			signedURL := generateSignedURL("test-signing-key-must-be-32-chars",
+			fix := setupTestHandler(t)
-				&imagerequest.Request{
-					Source: imagerequest.Source{
-						Host: signedHost,
-						Path: "/images/photo.jpg",
-					},
-					Transform: imagerequest.Transform{
-						Size:    imagerequest.Size{Width: 50, Height: 50},
-						Format:  imagerequest.FormatJPEG,
-						Quality: tt.quality,
-						FitMode: tt.fitMode,
-					},
-				}, time.Hour)
 
-			status := getImage(t, setupTestHandler(t), signedURL)
+			signedURL, err := fix.service.GenerateSignedURL("", &imgcache.ImageRequest{
+				SourceHost: signedHost,
+				SourcePath: "/images/photo.jpg",
+				Size:       imgcache.Size{Width: 50, Height: 50},
+				Format:     imgcache.FormatJPEG,
+				Quality:    tt.quality,
+				FitMode:    tt.fitMode,
+			}, time.Hour)
+			if err != nil {
+				t.Fatalf("GenerateSignedURL() error = %v", err)
+			}
+
+			status := getImage(t, fix, signedURL)
 			if status != http.StatusBadGateway {
 				t.Errorf("status = %d, want %d", status, http.StatusBadGateway)
 			}
@@ -212,10 +171,10 @@ func TestHandleImage_InvalidExp_Returns400(t *testing.T) {
 }
 
 // TestHandleImage_GeneratedSignedURLWithSourceQueryVerifies sends URLs built
-// by generateSignedURL for source URLs with a query to the route, through a
+// by the service's signed-URL generator for source URLs with a query to the
-// chi router: chi routes on the path as the client wrote it whenever that is
+// route, through a chi router: chi routes on the path as the client wrote it
-// not Go's own encoding of it. A 502 means the signature passed, so the route
+// whenever that is not Go's own encoding of it. A 502 means the signature
-// read the source path and query that were signed.
+// passed, so the route read the source path and query that were signed.
 func TestHandleImage_GeneratedSignedURLWithSourceQueryVerifies(t *testing.T) {
 	t.Parallel()
 
@@ -235,20 +194,20 @@ func TestHandleImage_GeneratedSignedURLWithSourceQueryVerifies(t *testing.T) {
 		t.Run(tt.name, func(t *testing.T) {
 			t.Parallel()
 
-			signedURL := generateSignedURL("test-signing-key-must-be-32-chars",
+			fix := setupTestHandler(t)
-				&imagerequest.Request{
-					Source: imagerequest.Source{
-						Host:  signedHost,
-						Path:  photoPath,
-						Query: tt.query,
-					},
-					Transform: imagerequest.Transform{
-						Size:   imagerequest.Size{Width: 50, Height: 50},
-						Format: imagerequest.FormatJPEG,
-					},
-				}, time.Hour)
 
-			status := getImage(t, setupTestHandler(t), signedURL)
+			signedURL, err := fix.service.GenerateSignedURL("", &imgcache.ImageRequest{
+				SourceHost:  signedHost,
+				SourcePath:  photoPath,
+				SourceQuery: tt.query,
+				Size:        imgcache.Size{Width: 50, Height: 50},
+				Format:      imgcache.FormatJPEG,
+			}, time.Hour)
+			if err != nil {
+				t.Fatalf("GenerateSignedURL() error = %v", err)
+			}
+
+			status := getImage(t, fix, signedURL)
 			if status != http.StatusBadGateway {
 				t.Errorf("status = %d, want %d", status, http.StatusBadGateway)
 			}
@@ -265,19 +224,16 @@ func TestHandleImage_SourceQueryEncodedAnyWay(t *testing.T) {
 
 	expires := time.Now().Add(time.Hour)
 	signer := signature.New("test-signing-key-must-be-32-chars")
-	sig := signer.Sign(&imagerequest.Request{
+	sig := signer.Sign(&signature.Request{
-		Source: imagerequest.Source{
+		SourceHost:  signedHost,
-			Host:  signedHost,
+		SourcePath:  photoPath,
-			Path:  photoPath,
+		SourceQuery: "url=https://origin.example.com/my%20cat.jpg",
-			Query: "url=https://origin.example.com/my%20cat.jpg",
+		Width:       50,
-		},
+		Height:      50,
-		Transform: imagerequest.Transform{
+		Format:      string(imgcache.FormatJPEG),
-			Size:    imagerequest.Size{Width: 50, Height: 50},
+		Quality:     85,
-			Format:  imagerequest.FormatJPEG,
+		FitMode:     string(imgcache.FitCover),
-			Quality: 85,
+		Expires:     expires,
-			FitMode: imagerequest.FitCover,
-		},
-		Expires: expires,
 	})
 
 	tests := []struct {
@@ -310,7 +266,7 @@ func TestHandleImage_SourceQueryEncodedAnyWay(t *testing.T) {
 // TestHandleImage_SourceURLHoldingPercent25Verifies signs a source path and a
 // source query that each hold %25, the percent-escape of a literal "%", and
 // sends each to the route written as the README says, with that "%" written as
-// %25, and as generateSignedURL writes it. A 502 means the signature passed.
+// %25, and as GenerateSignedURL writes it. A 502 means the signature passed.
 func TestHandleImage_SourceURLHoldingPercent25Verifies(t *testing.T) {
 	t.Parallel()
 
@@ -332,19 +288,16 @@ func TestHandleImage_SourceURLHoldingPercent25Verifies(t *testing.T) {
 
 			expires := time.Now().Add(time.Hour)
 			signer := signature.New("test-signing-key-must-be-32-chars")
-			sig := signer.Sign(&imagerequest.Request{
+			sig := signer.Sign(&signature.Request{
-				Source: imagerequest.Source{
+				SourceHost:  signedHost,
-					Host:  signedHost,
+				SourcePath:  tt.sourcePath,
-					Path:  tt.sourcePath,
+				SourceQuery: tt.sourceQuery,
-					Query: tt.sourceQuery,
+				Width:       50,
-				},
+				Height:      50,
-				Transform: imagerequest.Transform{
+				Format:      string(imgcache.FormatJPEG),
-					Size:    imagerequest.Size{Width: 50, Height: 50},
+				Quality:     85,
-					Format:  imagerequest.FormatJPEG,
+				FitMode:     string(imgcache.FitCover),
-					Quality: 85,
+				Expires:     expires,
-					FitMode: imagerequest.FitCover,
-				},
-				Expires: expires,
 			})
 
 			target := fmt.Sprintf("/v1/image/%s%s/50x50.jpeg?sig=%s&exp=%d",
@@ -356,23 +309,23 @@ func TestHandleImage_SourceURLHoldingPercent25Verifies(t *testing.T) {
 			}
 		})
 
-		t.Run(tt.name+" written by generateSignedURL", func(t *testing.T) {
+		t.Run(tt.name+" written by GenerateSignedURL", func(t *testing.T) {
 			t.Parallel()
 
-			signedURL := generateSignedURL("test-signing-key-must-be-32-chars",
+			fix := setupTestHandler(t)
-				&imagerequest.Request{
-					Source: imagerequest.Source{
-						Host:  signedHost,
-						Path:  tt.sourcePath,
-						Query: tt.sourceQuery,
-					},
-					Transform: imagerequest.Transform{
-						Size:   imagerequest.Size{Width: 50, Height: 50},
-						Format: imagerequest.FormatJPEG,
-					},
-				}, time.Hour)
 
-			status := getImage(t, setupTestHandler(t), signedURL)
+			signedURL, err := fix.service.GenerateSignedURL("", &imgcache.ImageRequest{
+				SourceHost:  signedHost,
+				SourcePath:  tt.sourcePath,
+				SourceQuery: tt.sourceQuery,
+				Size:        imgcache.Size{Width: 50, Height: 50},
+				Format:      imgcache.FormatJPEG,
+			}, time.Hour)
+			if err != nil {
+				t.Fatalf("GenerateSignedURL() error = %v", err)
+			}
+
+			status := getImage(t, fix, signedURL)
 			if status != http.StatusBadGateway {
 				t.Errorf("status = %d, want %d", status, http.StatusBadGateway)
 			}

internal/handlers/imageenc.go

@@ -14,9 +14,7 @@ import (
 	"sneak.berlin/go/pixa/internal/encurl"
 	"sneak.berlin/go/pixa/internal/httpfetcher"
 	"sneak.berlin/go/pixa/internal/imageprocessor"
-	"sneak.berlin/go/pixa/internal/imagerequest"
 	"sneak.berlin/go/pixa/internal/imgcache"
-	"sneak.berlin/go/pixa/internal/magic"
 )
 
 // HandleImageEnc handles requests to /v1/e/{token}/* for encrypted
@@ -38,11 +36,10 @@ func (s *Handlers) HandleImageEnc() http.HandlerFunc {
 
 		// Log the request
 		s.log.Debug("encrypted image request",
-			"host", req.Source.Host,
+			"host", req.SourceHost,
-			"path", req.Source.Path,
+			"path", req.SourcePath,
-			"dimensions", fmt.Sprintf("%dx%d",
+			"dimensions", fmt.Sprintf("%dx%d", req.Size.Width, req.Size.Height),
-				req.Transform.Size.Width, req.Transform.Size.Height),
+			"format", req.Format,
-			"format", req.Transform.Format,
 		)
 
 		// Fetch and process the image (no signature validation
@@ -90,10 +87,10 @@ func (s *Handlers) HandleImageEnc() http.HandlerFunc {
 		duration := time.Since(start)
 		s.log.Info("image served",
 			"request_id", middleware.GetReqID(ctx),
-			"cache_key", imagerequest.CacheKey(req),
+			"cache_key", imgcache.CacheKey(req),
-			"host", req.Source.Host,
+			"host", req.SourceHost,
-			"path", req.Source.Path,
+			"path", req.SourcePath,
-			"format", req.Transform.Format,
+			"format", req.Format,
 			"cache_status", resp.CacheStatus,
 			"served_bytes", written,
 			"duration_ms", duration.Milliseconds(),
@@ -102,12 +99,12 @@ func (s *Handlers) HandleImageEnc() http.HandlerFunc {
 }
 
 // parseImageEncRequest decrypts the token of an encrypted image URL into an
-// image request and checks it. On a token that is missing, does not decrypt,
+// ImageRequest and checks it. On a token that is missing, does not decrypt,
 // has expired or asks for something not valid, it writes an error response
 // and returns false.
 func (s *Handlers) parseImageEncRequest(
 	w http.ResponseWriter, r *http.Request,
-) (*imagerequest.Request, bool) {
+) (*imgcache.ImageRequest, bool) {
 	// Extract token from URL
 	token := chi.URLParam(r, "token")
 	if token == "" {
@@ -117,7 +114,7 @@ func (s *Handlers) parseImageEncRequest(
 	}
 
 	// Decrypt and validate the payload
-	req, err := s.encGen.Parse(token)
+	payload, err := s.encGen.Parse(token)
 	if err != nil {
 		if errors.Is(err, encurl.ErrExpired) {
 			s.log.Debug("encrypted URL expired", "error", err)
@@ -132,11 +129,14 @@ func (s *Handlers) parseImageEncRequest(
 		return nil, false
 	}
 
+	// Convert payload to ImageRequest
+	req := payload.ToImageRequest()
+
 	// Apply the same dimension and fit-mode bounds as the plain image
 	// route: a sealed payload is trusted for its origin, not for staying
 	// within limits, so an over-limit size or unknown fit mode is a 400
 	// here rather than an out-of-memory or a 500 from the processor.
-	err = imagerequest.ValidateImageRequest(req)
+	err = imgcache.ValidateImageRequest(req)
 	if err != nil {
 		s.log.Debug("encrypted URL failed validation", "error", err)
 		s.respondError(w, "invalid encrypted URL: "+err.Error(),
@@ -163,20 +163,13 @@ func (s *Handlers) handleImageError(w http.ResponseWriter, err error) {
 		s.respondError(w, "server busy, try again later",
 			http.StatusServiceUnavailable)
 	case errors.Is(err, httpfetcher.ErrInvalidContentType),
-		errors.Is(err, imageprocessor.ErrUnsupportedInputFormat),
+		errors.Is(err, imageprocessor.ErrUnsupportedInputFormat):
-		errors.Is(err, magic.ErrMagicByteMismatch),
-		errors.Is(err, magic.ErrUnknownFormat),
-		errors.Is(err, magic.ErrNotEnoughData):
 		s.respondError(w, "unsupported source format",
 			http.StatusUnsupportedMediaType)
 	case errors.Is(err, imageprocessor.ErrOutputTooLarge):
 		s.respondError(w, fmt.Sprintf("size too large for the source: the side "+
 			"computed from its proportions is above %d",
 			imageprocessor.MaxOutputDimension), http.StatusBadRequest)
-	case errors.Is(err, imageprocessor.ErrAVIFOutputTooLarge):
-		s.respondError(w, fmt.Sprintf("size too large for AVIF: the output "+
-			"would be above %d pixels", imageprocessor.MaxAVIFOutputPixels),
-			http.StatusBadRequest)
 	default:
 		s.log.Error("image request failed", "error", err)
 		s.respondError(w, "internal error", http.StatusInternalServerError)

internal/handlers/imageenc_internal_test.go

@@ -10,7 +10,7 @@ import (
 	"github.com/go-chi/chi/v5"
 
 	"sneak.berlin/go/pixa/internal/encurl"
-	"sneak.berlin/go/pixa/internal/imagerequest"
+	"sneak.berlin/go/pixa/internal/imgcache"
 )
 
 // newEncTestServer builds a router serving the encrypted-URL route with a
@@ -54,14 +54,11 @@ func TestHandleImageEnc_OverLimitDimension_Returns400(t *testing.T) {
 
 	encGen, srv := newEncTestServer(t)
 
-	token, err := encGen.Generate(&imagerequest.Request{
+	token, err := encGen.Generate(&encurl.Payload{
-		Source: imagerequest.Source{
+		SourceHost: "cdn.example.com",
-			Host: "cdn.example.com",
+		SourcePath: "/photo.jpg",
-			Path: "/photo.jpg",
+		Width:      100000,
-		},
+		Height:     100000,
-		Transform: imagerequest.Transform{
-			Size: imagerequest.Size{Width: 100000, Height: 100000},
-		},
 	})
 	if err != nil {
 		t.Fatalf("Generate() error = %v", err)
@@ -82,15 +79,12 @@ func TestHandleImageEnc_InvalidFitMode_Returns400(t *testing.T) {
 
 	encGen, srv := newEncTestServer(t)
 
-	token, err := encGen.Generate(&imagerequest.Request{
+	token, err := encGen.Generate(&encurl.Payload{
-		Source: imagerequest.Source{
+		SourceHost: "cdn.example.com",
-			Host: "cdn.example.com",
+		SourcePath: "/photo.jpg",
-			Path: "/photo.jpg",
+		Width:      800,
-		},
+		Height:     600,
-		Transform: imagerequest.Transform{
+		FitMode:    imgcache.FitMode("bogus"),
-			Size:    imagerequest.Size{Width: 800, Height: 600},
-			FitMode: imagerequest.Fit("bogus"),
-		},
 	})
 	if err != nil {
 		t.Fatalf("Generate() error = %v", err)

internal/handlers/imageenc_token_internal_test.go

@@ -9,7 +9,6 @@ import (
 	"time"
 
 	"sneak.berlin/go/pixa/internal/encurl"
-	"sneak.berlin/go/pixa/internal/imagerequest"
 )
 
 // requireServedPhoto requires that rec answers 200 with the JPEG at photoPath
@@ -60,14 +59,11 @@ func TestHandleImageEnc_RejectedToken(t *testing.T) {
 
 	h, srv := newSignedHostServer(t, slog.New(slog.DiscardHandler))
 
-	photo := imagerequest.Request{
+	photo := encurl.Payload{
-		Source: imagerequest.Source{
+		SourceHost: signedHost,
-			Host: signedHost,
+		SourcePath: photoPath,
-			Path: photoPath,
+		Width:      50,
-		},
+		Height:     50,
-		Transform: imagerequest.Transform{
-			Size: imagerequest.Size{Width: 50, Height: 50},
-		},
 	}
 
 	valid, err := h.encGen.Generate(&photo)
@@ -76,7 +72,7 @@ func TestHandleImageEnc_RejectedToken(t *testing.T) {
 	}
 
 	expiredPhoto := photo
-	expiredPhoto.Expires = time.Now().Add(-time.Minute)
+	expiredPhoto.ExpiresAt = time.Now().Add(-time.Minute).Unix()
 
 	expired, err := h.encGen.Generate(&expiredPhoto)
 	if err != nil {

internal/handlers/jpegxl_default_internal_test.go

@@ -14,7 +14,7 @@ import (
 	"github.com/davidbyttow/govips/v2/vips"
 
 	"sneak.berlin/go/pixa/internal/encurl"
-	"sneak.berlin/go/pixa/internal/imagerequest"
+	"sneak.berlin/go/pixa/internal/imgcache"
 	"sneak.berlin/go/pixa/internal/signature"
 )
 
@@ -58,18 +58,15 @@ func TestImageWithoutFormat_SignedAsJXL(t *testing.T) {
 	route := newImageRoute(t, newPhotoFetcher(t, signedHost))
 	expires := time.Now().Add(time.Hour)
 
-	sig := signature.New(testSigningKey).Sign(&imagerequest.Request{
+	sig := signature.New(testSigningKey).Sign(&signature.Request{
-		Source: imagerequest.Source{
+		SourceHost: signedHost,
-			Host: signedHost,
+		SourcePath: photoPath,
-			Path: photoPath,
+		Width:      50,
-		},
+		Height:     50,
-		Transform: imagerequest.Transform{
+		Format:     string(imgcache.FormatJXL),
-			Size:    imagerequest.Size{Width: 50, Height: 50},
+		Quality:    encurl.DefaultQuality,
-			Format:  imagerequest.FormatJXL,
+		FitMode:    string(imgcache.FitCover),
-			Quality: encurl.DefaultQuality,
+		Expires:    expires,
-			FitMode: imagerequest.FitCover,
-		},
-		Expires: expires,
 	})
 	query := fmt.Sprintf("?sig=%s&exp=%d", sig, expires.Unix())
 
@@ -86,14 +83,11 @@ func TestImageEncWithoutFormat_ServesJPEGXL(t *testing.T) {
 
 	h, srv := newSignedHostServer(t, slog.New(slog.DiscardHandler))
 
-	token, err := h.encGen.Generate(&imagerequest.Request{
+	token, err := h.encGen.Generate(&encurl.Payload{
-		Source: imagerequest.Source{
+		SourceHost: signedHost,
-			Host: signedHost,
+		SourcePath: photoPath,
-			Path: photoPath,
+		Width:      50,
-		},
+		Height:     50,
-		Transform: imagerequest.Transform{
-			Size: imagerequest.Size{Width: 50, Height: 50},
-		},
 	})
 	if err != nil {
 		t.Fatalf("Generate() error = %v", err)

internal/handlers/jpegxl_internal_test.go

@@ -7,7 +7,7 @@ import (
 
 	"github.com/davidbyttow/govips/v2/vips"
 
-	"sneak.berlin/go/pixa/internal/imagerequest"
+	"sneak.berlin/go/pixa/internal/imgcache"
 )
 
 // jxlType is the content type of JPEG XL.
@@ -22,14 +22,14 @@ func TestFormatForAccept_JPEGXL(t *testing.T) {
 	tests := []struct {
 		name   string
 		accept string
-		want   imagerequest.Format
+		want   imgcache.ImageFormat
 	}{
 		{"JPEG XL-capable browser",
-			"image/jxl,image/avif,image/webp,image/*,*/*;q=0.8", imagerequest.FormatJXL},
+			"image/jxl,image/avif,image/webp,image/*,*/*;q=0.8", imgcache.FormatJXL},
-		{"JPEG XL only", jxlType, imagerequest.FormatJXL},
+		{"JPEG XL only", jxlType, imgcache.FormatJXL},
 		{"JPEG XL with a lower q than AVIF", "image/avif,image/jxl;q=0.5",
-			imagerequest.FormatJXL},
+			imgcache.FormatJXL},
-		{"q=0 on JPEG XL", "image/jxl;q=0,image/avif,*/*", imagerequest.FormatAVIF},
+		{"q=0 on JPEG XL", "image/jxl;q=0,image/avif,*/*", imgcache.FormatAVIF},
 	}
 
 	for _, tt := range tests {

internal/handlers/referer_blocklist_internal_test.go

@@ -10,11 +10,9 @@ import (
 	"time"
 
 	"github.com/go-chi/chi/v5"
-	"github.com/prometheus/client_golang/prometheus"
 	"sneak.berlin/go/pixa/internal/allowlist"
 	"sneak.berlin/go/pixa/internal/encurl"
 	"sneak.berlin/go/pixa/internal/httpfetcher"
-	"sneak.berlin/go/pixa/internal/imageprocessor"
 	"sneak.berlin/go/pixa/internal/imgcache"
 )
 
@@ -52,22 +50,16 @@ func newRefererRoutes(t *testing.T) (http.Handler, *Handlers, *countingFetcher)
 	cache, err := imgcache.NewCache(setupTestDB(t), imgcache.CacheConfig{
 		StateDir:    t.TempDir(),
 		NegativeTTL: 5 * time.Minute,
-		MaxBytes:    1 << 30,
+	})
-	}, prometheus.NewRegistry())
 	if err != nil {
 		t.Fatalf("imgcache.NewCache() error = %v", err)
 	}
 
 	svc, err := imgcache.NewService(&imgcache.ServiceConfig{
-		Cache:   cache,
+		Cache:      cache,
-		Fetcher: fetcher,
+		Fetcher:    fetcher,
-		Processor: imageprocessor.New(imageprocessor.Params{
+		SigningKey: testSigningKey,
-			MaxInputBytes:           50 << 20,
+		Allowlist:  []string{allowlistedHost},
-			MaxConcurrentProcessing: 2,
-		}),
-		SigningKey:      testSigningKey,
-		Allowlist:       []string{allowlistedHost},
-		MaxResponseSize: 50 << 20,
 	})
 	if err != nil {
 		t.Fatalf("imgcache.NewService() error = %v", err)

internal/handlers/request_id_internal_test.go

@@ -13,26 +13,26 @@ import (
 
 	"github.com/go-chi/chi/v5/middleware"
 
-	"sneak.berlin/go/pixa/internal/imagerequest"
+	"sneak.berlin/go/pixa/internal/encurl"
+	"sneak.berlin/go/pixa/internal/imgcache"
 )
 
 // signedPhotoURL returns a signed /v1/image/ URL, valid for a minute, for the
-// JPEG at photoPath on signedHost at 50x50. It is signed with testSigningKey,
+// JPEG at photoPath on signedHost at 50x50, made with h's image service.
-// the key of the image service newSignedHostServer builds. It takes a Handlers
+func signedPhotoURL(t *testing.T, h *Handlers) string {
-// it does not use, so that it has the type of encPhotoURL.
-func signedPhotoURL(t *testing.T, _ *Handlers) string {
 	t.Helper()
 
-	return generateSignedURL(testSigningKey, &imagerequest.Request{
+	signedURL, err := h.imgSvc.GenerateSignedURL("", &imgcache.ImageRequest{
-		Source: imagerequest.Source{
+		SourceHost: signedHost,
-			Host: signedHost,
+		SourcePath: photoPath,
-			Path: photoPath,
+		Size:       imgcache.Size{Width: 50, Height: 50},
-		},
+		Format:     imgcache.FormatJPEG,
-		Transform: imagerequest.Transform{
-			Size:   imagerequest.Size{Width: 50, Height: 50},
-			Format: imagerequest.FormatJPEG,
-		},
 	}, time.Minute)
+	if err != nil {
+		t.Fatalf("GenerateSignedURL() error = %v", err)
+	}
+
+	return signedURL
 }
 
 // encPhotoURL returns an encrypted /v1/e/ URL, which never expires, for the
@@ -40,15 +40,12 @@ func signedPhotoURL(t *testing.T, _ *Handlers) string {
 func encPhotoURL(t *testing.T, h *Handlers) string {
 	t.Helper()
 
-	token, err := h.encGen.Generate(&imagerequest.Request{
+	token, err := h.encGen.Generate(&encurl.Payload{
-		Source: imagerequest.Source{
+		SourceHost: signedHost,
-			Host: signedHost,
+		SourcePath: photoPath,
-			Path: photoPath,
+		Width:      50,
-		},
+		Height:     50,
-		Transform: imagerequest.Transform{
+		Format:     imgcache.FormatJPEG,
-			Size:   imagerequest.Size{Width: 50, Height: 50},
-			Format: imagerequest.FormatJPEG,
-		},
 	})
 	if err != nil {
 		t.Fatalf("Generate() error = %v", err)

internal/handlers/server_busy_internal_test.go

@@ -11,7 +11,6 @@ import (
 
 	"sneak.berlin/go/pixa/internal/httpfetcher"
 	"sneak.berlin/go/pixa/internal/imageprocessor"
-	"sneak.berlin/go/pixa/internal/imagerequest"
 	"sneak.berlin/go/pixa/internal/imgcache"
 )
 
@@ -22,9 +21,7 @@ func TestServerBusyAnswers503(t *testing.T) {
 	t.Parallel()
 
 	h := &Handlers{log: slog.New(slog.DiscardHandler)}
-	req := &imagerequest.Request{
+	req := &imgcache.ImageRequest{SourceHost: "img.example.com", SourcePath: "/a.jpg"}
-		Source: imagerequest.Source{Host: "img.example.com", Path: "/a.jpg"},
-	}
 
 	for _, err := range []error{
 		fmt.Errorf("upstream fetch failed: %w", httpfetcher.ErrTooManyConnections),
@@ -67,7 +64,7 @@ func TestProcessingTimedOutAnswers503(t *testing.T) {
 		imgcache.ErrProcessingTimedOut, context.DeadlineExceeded)
 
 	plain := httptest.NewRecorder()
-	h.respondImageError(plain, &imagerequest.Request{}, err)
+	h.respondImageError(plain, &imgcache.ImageRequest{}, err)
 
 	encrypted := httptest.NewRecorder()
 	h.handleImageError(encrypted, err)

internal/handlers/unsupported_source_internal_test.go

@@ -10,7 +10,7 @@ import (
 
 	"sneak.berlin/go/pixa/internal/httpfetcher"
 	"sneak.berlin/go/pixa/internal/imageprocessor"
-	"sneak.berlin/go/pixa/internal/imagerequest"
+	"sneak.berlin/go/pixa/internal/imgcache"
 )
 
 // TestUnsupportedSourceFormatAnswers415 checks that both image routes answer
@@ -21,9 +21,7 @@ func TestUnsupportedSourceFormatAnswers415(t *testing.T) {
 	t.Parallel()
 
 	h := &Handlers{log: slog.New(slog.DiscardHandler)}
-	req := &imagerequest.Request{
+	req := &imgcache.ImageRequest{SourceHost: "img.example.com", SourcePath: "/a.svg"}
-		Source: imagerequest.Source{Host: "img.example.com", Path: "/a.svg"},
-	}
 
 	for _, err := range []error{
 		fmt.Errorf("upstream fetch failed: %w: image/svg+xml",

internal/httpfetcher/blocked_networks_internal_test.go

@@ -7,7 +7,6 @@ import (
 	"net/http"
 	"net/netip"
 	"testing"
-	"time"
 )
 
 // TestIsPrivateIPBlocksSpecialRanges covers the internal and special-use
@@ -71,15 +70,12 @@ func transportOf(t *testing.T, f *HTTPFetcher) *http.Transport {
 func TestDialerEnforcesBlockedNetworks(t *testing.T) {
 	t.Parallel()
 
-	transport := transportOf(t, New(&Config{
+	cfg := DefaultConfig()
-		Timeout:               30 * time.Second,
+	// TEST-NET-2 (198.51.100.0/24) is public to the built-in check, so
-		MaxResponseSize:       50 << 20,
+	// blocking it can only come from the operator-supplied list.
-		MaxConnectionsPerHost: 20,
+	cfg.BlockedNetworks = []netip.Prefix{netip.MustParsePrefix("198.51.100.0/24")}
-		MaxConnections:        64,
+
-		// TEST-NET-2 (198.51.100.0/24) is public to the built-in check, so
+	transport := transportOf(t, New(cfg))
-		// blocking it can only come from the operator-supplied list.
-		BlockedNetworks: []netip.Prefix{netip.MustParsePrefix("198.51.100.0/24")},
-	}))
 
 	blocked := []string{
 		"198.51.100.5:80", // operator-supplied range

internal/httpfetcher/dial_context_internal_test.go

@@ -4,7 +4,6 @@ import (
 	"errors"
 	"net"
 	"testing"
-	"time"
 )
 
 // TestNewUsesCheckedDialerWithoutDialContext checks that a fetcher built
@@ -14,12 +13,7 @@ func TestNewUsesCheckedDialerWithoutDialContext(t *testing.T) {
 	t.Parallel()
 
 	srv := startUpstream(t)
-	transport := transportOf(t, New(&Config{
+	transport := transportOf(t, New(DefaultConfig()))
-		Timeout:               30 * time.Second,
-		MaxResponseSize:       50 << 20,
-		MaxConnectionsPerHost: 20,
-		MaxConnections:        64,
-	}))
 
 	addr := srv.Listener.Addr().String()
 
@@ -38,14 +32,10 @@ func TestDialContextReplacesOnlyTheDialer(t *testing.T) {
 	srv := startUpstream(t)
 	dialer := &recordingDialer{target: srv.Listener.Addr().String()}
 
-	f := New(&Config{
+	cfg := DefaultConfig()
-		Timeout:               30 * time.Second,
+	cfg.AllowHTTP = true
-		MaxResponseSize:       50 << 20,
+	cfg.DialContext = dialer.dialContext
-		AllowHTTP:             true,
+	f := New(cfg)
-		MaxConnectionsPerHost: 20,
-		MaxConnections:        64,
-		DialContext:           dialer.dialContext,
-	})
 
 	if body := fetchBody(t, f, "/image"); body != imagePayload {
 		t.Errorf("body = %q, want %q", body, imagePayload)

internal/httpfetcher/fetch_internal_test.go

@@ -120,12 +120,7 @@ func newServerFetcher(
 	t.Helper()
 
 	if cfg == nil {
-		cfg = &Config{
+		cfg = DefaultConfig()
-			Timeout:               30 * time.Second,
-			MaxResponseSize:       50 << 20,
-			MaxConnectionsPerHost: 20,
-			MaxConnections:        64,
-		}
 	}
 
 	cfg.AllowHTTP = true
@@ -285,12 +280,8 @@ func TestFetchMaxResponseSizeEnforced(t *testing.T) {
 
 	srv := startUpstream(t)
 
-	cfg := &Config{
+	cfg := DefaultConfig()
-		Timeout:               30 * time.Second,
+	cfg.MaxResponseSize = 8
-		MaxResponseSize:       8,
-		MaxConnectionsPerHost: 20,
-		MaxConnections:        64,
-	}
 
 	f, _ := newServerFetcher(t, srv, cfg)
 
@@ -319,12 +310,8 @@ func fetchWithMaxResponseSize(
 	srv := httptest.NewServer(handler)
 	t.Cleanup(srv.Close)
 
-	cfg := &Config{
+	cfg := DefaultConfig()
-		Timeout:               30 * time.Second,
+	cfg.MaxResponseSize = maxResponseSize
-		MaxResponseSize:       maxResponseSize,
-		MaxConnectionsPerHost: 20,
-		MaxConnections:        64,
-	}
 
 	f, _ := newServerFetcher(t, srv, cfg)
 
@@ -449,12 +436,8 @@ func TestFetchSemaphoreReleasedOnError(t *testing.T) {
 
 	srv := startUpstream(t)
 
-	cfg := &Config{
+	cfg := DefaultConfig()
-		Timeout:               30 * time.Second,
+	cfg.MaxConnectionsPerHost = 1
-		MaxResponseSize:       50 << 20,
-		MaxConnectionsPerHost: 1,
-		MaxConnections:        64,
-	}
 
 	f, _ := newServerFetcher(t, srv, cfg)
 
@@ -483,12 +466,8 @@ func assertSlotReleasedByClose(
 
 	srv := startUpstream(t)
 
-	cfg := &Config{
+	cfg := DefaultConfig()
-		Timeout:               30 * time.Second,
+	cfg.MaxConnectionsPerHost = 1
-		MaxResponseSize:       50 << 20,
-		MaxConnectionsPerHost: 1,
-		MaxConnections:        64,
-	}
 
 	f, _ := newServerFetcher(t, srv, cfg)
 
@@ -545,7 +524,7 @@ func TestFetchSemaphoreReleasedOnPartialReadClose(t *testing.T) {
 	})
 }
 
-// The dial-time re-resolution in dialSSRFSafe is what closes the DNS
+// The dial-time re-resolution in ssrfSafeDialer is what closes the DNS
 // rebinding window: even if validateURL saw a public answer earlier, the
 // dialer independently re-checks the address it is about to connect to. A full
 // rebinding simulation (a resolver returning public, then private) would mean
@@ -565,9 +544,9 @@ func TestSSRFSafeDialerBlocksPrivateTarget(t *testing.T) {
 		t.Run(addr, func(t *testing.T) {
 			t.Parallel()
 
-			_, err := dialSSRFSafe(context.Background(), "tcp", addr, nil)
+			_, err := ssrfSafeDialer(context.Background(), "tcp", addr)
 			if !errors.Is(err, ErrSSRFBlocked) {
-				t.Errorf("dialSSRFSafe(%q) = %v, want ErrSSRFBlocked", addr, err)
+				t.Errorf("ssrfSafeDialer(%q) = %v, want ErrSSRFBlocked", addr, err)
 			}
 		})
 	}
@@ -581,7 +560,7 @@ func TestSSRFSafeDialerAllowsPublicTarget(t *testing.T) {
 	ctx, cancel := context.WithCancel(context.Background())
 	cancel()
 
-	_, err := dialSSRFSafe(ctx, "tcp", testPublicHost+":80", nil)
+	_, err := ssrfSafeDialer(ctx, "tcp", testPublicHost+":80")
 	if err == nil {
 		t.Fatal("expected a dial error for an unreachable public target")
 	}

internal/httpfetcher/httpfetcher.go

@@ -24,15 +24,16 @@ import (
 
 // Fetcher configuration constants.
 const (
-	DefaultTLSTimeout      = 10 * time.Second
+	DefaultFetchTimeout          = 30 * time.Second
-	DefaultMaxIdleConns    = 100
+	DefaultMaxResponseSize       = 50 << 20 // 50MB
-	DefaultIdleConnTimeout = 90 * time.Second
+	DefaultTLSTimeout            = 10 * time.Second
-	DefaultMaxRedirects    = 10
+	DefaultMaxIdleConns          = 100
+	DefaultIdleConnTimeout       = 90 * time.Second
+	DefaultMaxRedirects          = 10
+	DefaultMaxConnectionsPerHost = 20
+	DefaultMaxConnections        = 64
 )
 
-// userAgent is the User-Agent header sent to upstream servers.
-const userAgent = "pixa/1.0"
-
 // ConnectionWaitTimeout is how long Fetch waits for a free connection when
 // MaxConnections fetches are already in progress.
 const ConnectionWaitTimeout = 10 * time.Second
@@ -58,17 +59,15 @@ const (
 // builtinBlockedPrefixes are internal or special-use ranges that Go's
 // net.IP predicates (IsPrivate, IsLinkLocalUnicast, and the like) do not
 // already cover. They are always blocked, in addition to any
-// operator-supplied networks. IPv4-mapped and IPv4-compatible IPv6
+// operator-supplied networks. IPv4-mapped IPv6 addresses are unmapped
-// addresses are read as the IPv4 address they hold before matching, so
+// before matching, so these IPv4 ranges are caught in both forms.
-// these IPv4 ranges are caught in all three forms.
 //
 //nolint:gochecknoglobals // immutable built-in blocklist
 var builtinBlockedPrefixes = []netip.Prefix{
-	netip.MustParsePrefix("100.64.0.0/10"),  // RFC 6598 CGNAT / carrier-grade NAT
+	netip.MustParsePrefix("100.64.0.0/10"), // RFC 6598 CGNAT / carrier-grade NAT
-	netip.MustParsePrefix("192.0.0.0/24"),   // RFC 6890 IETF protocol assignments
+	netip.MustParsePrefix("192.0.0.0/24"),  // RFC 6890 IETF protocol assignments
-	netip.MustParsePrefix("198.18.0.0/15"),  // RFC 2544 benchmarking range
+	netip.MustParsePrefix("198.18.0.0/15"), // RFC 2544 benchmarking range
-	netip.MustParsePrefix("64:ff9b::/96"),   // RFC 6052 NAT64 (maps onto IPv4)
+	netip.MustParsePrefix("64:ff9b::/96"),  // RFC 6052 NAT64 (maps onto IPv4)
-	netip.MustParsePrefix("64:ff9b:1::/48"), // RFC 8215 local-use NAT64 (maps onto IPv4)
 }
 
 // Fetcher errors.
@@ -119,26 +118,16 @@ type FetchResult struct {
 	TLSCipherSuite string
 }
 
-// allowedContentTypes returns the content types an upstream response may
+// Config holds configuration for the upstream fetcher.
-// have, which Fetch also sends as its Accept header.
-func allowedContentTypes() []string {
-	return []string{
-		contentTypeJPEG,
-		contentTypePNG,
-		contentTypeGIF,
-		contentTypeWebP,
-		contentTypeAVIF,
-		contentTypeJXL,
-	}
-}
-
-// Config holds configuration for the upstream fetcher. Every field but
-// AllowHTTP, BlockedNetworks and DialContext must be set.
 type Config struct {
 	// Timeout for upstream requests.
 	Timeout time.Duration
 	// MaxResponseSize is the maximum allowed response body size.
 	MaxResponseSize int64
+	// UserAgent to send to upstream servers.
+	UserAgent string
+	// AllowedContentTypes is an allow list of MIME types to accept.
+	AllowedContentTypes []string
 	// AllowHTTP allows non-TLS connections (for testing only).
 	AllowHTTP bool
 	// MaxConnectionsPerHost limits concurrent connections to each upstream host.
@@ -156,6 +145,26 @@ type Config struct {
 	DialContext func(ctx context.Context, network, addr string) (net.Conn, error)
 }
 
+// DefaultConfig returns a Config with sensible defaults.
+func DefaultConfig() *Config {
+	return &Config{
+		Timeout:         DefaultFetchTimeout,
+		MaxResponseSize: DefaultMaxResponseSize,
+		UserAgent:       "pixa/1.0",
+		AllowedContentTypes: []string{
+			contentTypeJPEG,
+			contentTypePNG,
+			contentTypeGIF,
+			contentTypeWebP,
+			contentTypeAVIF,
+			contentTypeJXL,
+		},
+		AllowHTTP:             false,
+		MaxConnectionsPerHost: DefaultMaxConnectionsPerHost,
+		MaxConnections:        DefaultMaxConnections,
+	}
+}
+
 // HTTPFetcher implements Fetcher with SSRF protection and connection limits
 // per host and for all hosts together.
 type HTTPFetcher struct {
@@ -183,6 +192,10 @@ type hostSemaphore struct {
 
 // New creates a new HTTPFetcher with SSRF protection.
 func New(config *Config) *HTTPFetcher {
+	if config == nil {
+		config = DefaultConfig()
+	}
+
 	// Unless config.DialContext replaces it, the transport connects with
 	// the SSRF-safe dialer, which re-resolves and re-checks at connect time
 	// (closing the DNS-rebinding window) against both the built-in ranges
@@ -265,8 +278,8 @@ func (f *HTTPFetcher) Fetch(ctx context.Context, url string) (*FetchResult, erro
 		Header: make(http.Header),
 	}
 
-	req.Header.Set("User-Agent", userAgent)
+	req.Header.Set("User-Agent", f.config.UserAgent)
-	req.Header.Set("Accept", strings.Join(allowedContentTypes(), ", "))
+	req.Header.Set("Accept", strings.Join(f.config.AllowedContentTypes, ", "))
 
 	// The ID of the request this fetch serves, so the fetch can be found in
 	// the upstream host's logs
@@ -445,7 +458,7 @@ func (f *HTTPFetcher) isAllowedContentType(contentType string) bool {
 	// Extract the MIME type without parameters
 	mediaType := strings.TrimSpace(strings.Split(contentType, ";")[0])
 
-	for _, allowed := range allowedContentTypes() {
+	for _, allowed := range f.config.AllowedContentTypes {
 		if strings.EqualFold(mediaType, allowed) {
 			return true
 		}
@@ -460,18 +473,18 @@ func validateURL(ctx context.Context, rawURL string, allowHTTP bool) error {
 		return ErrUnsupportedScheme
 	}
 
-	parsedURL, err := neturl.Parse(rawURL)
+	// Parse to extract host
-	if err != nil {
+	host := extractHost(rawURL)
-		return fmt.Errorf("%w: %w", ErrInvalidHost, err)
-	}
-
-	// Hostname drops any port, and the brackets of an IPv6 address whether
-	// or not a port follows them
-	host := parsedURL.Hostname()
 	if host == "" {
 		return ErrInvalidHost
 	}
 
+	// Remove port if present
+	h, _, err := net.SplitHostPort(host)
+	if err == nil {
+		host = h
+	}
+
 	// Block obvious localhost patterns
 	if isLocalhost(host) {
 		return ErrSSRFBlocked
@@ -530,9 +543,6 @@ func isPrivateIP(ip net.IP) bool {
 		return true
 	}
 
-	// An IPv4-compatible IPv6 address is judged as the IPv4 address it holds
-	ip = ipv4CompatibleToIPv4(ip)
-
 	// Check for loopback
 	if ip.IsLoopback() {
 		return true
@@ -584,12 +594,7 @@ func isPrivateIP(ip net.IP) bool {
 }
 
 // isBlockedIP reports whether ip is refused, either by the built-in
-// internal-range check or by one of the operator-supplied prefixes. An
+// internal-range check or by one of the operator-supplied prefixes.
-// IPv4-compatible address (in ::/96) is refused when a prefix contains the
-// address as written or the IPv4 address it holds. An IPv4-mapped address (in
-// ::ffff:0:0/96) is matched only as the IPv4 address it holds: Go keeps a
-// plain IPv4 address in that form too, and an IPv6 prefix such as ::/0 must
-// not refuse every IPv4 address.
 func isBlockedIP(ip net.IP, blocked []netip.Prefix) bool {
 	if isPrivateIP(ip) {
 		return true
@@ -602,26 +607,16 @@ func isBlockedIP(ip net.IP, blocked []netip.Prefix) bool {
 
 	addr = addr.Unmap()
 
-	// ip read as IPv4 where it is or holds an IPv4 address, otherwise the
-	// zero netip.Addr, which no prefix contains. Matching asIPv4 as well as
-	// addr refuses more only for an IPv4-compatible address.
-	asIPv4, _ := netip.AddrFromSlice(ipv4CompatibleToIPv4(ip).To4())
-
 	return slices.ContainsFunc(blocked, func(prefix netip.Prefix) bool {
-		return prefix.Contains(addr) || prefix.Contains(asIPv4)
+		return prefix.Contains(addr)
 	})
 }
 
-// ipv4CompatibleToIPv4 returns the IPv4 address that an IPv4-compatible IPv6
+// ssrfSafeDialer validates IP addresses against the built-in blocked ranges
-// address (in ::/96, such as ::127.0.0.1) holds in its last four bytes, and
+// before connecting. New wraps dialSSRFSafe with the operator-supplied
-// any other address unchanged.
+// blocklist; this entry point enforces the built-in ranges alone.
-func ipv4CompatibleToIPv4(ip net.IP) net.IP {
+func ssrfSafeDialer(ctx context.Context, network, addr string) (net.Conn, error) {
-	addr, ok := netip.AddrFromSlice(ip)
+	return dialSSRFSafe(ctx, network, addr, nil)
-	if ok && netip.MustParsePrefix("::/96").Contains(addr) {
-		return ip[12:]
-	}
-
-	return ip
 }
 
 // dialSSRFSafe re-resolves addr and refuses to connect to any built-in

internal/httpfetcher/httpfetcher_internal_test.go

@@ -7,21 +7,60 @@ import (
 	"net"
 	"testing"
 	"testing/fstest"
-	"time"
 )
 
 // testHost is the hostname used by mock fetch tests.
 const testHost = "example.com"
 
+func TestDefaultConfig(t *testing.T) {
+	t.Parallel()
+
+	cfg := DefaultConfig()
+
+	if cfg.Timeout != DefaultFetchTimeout {
+		t.Errorf("Timeout = %v, want %v", cfg.Timeout, DefaultFetchTimeout)
+	}
+
+	if cfg.MaxResponseSize != DefaultMaxResponseSize {
+		t.Errorf("MaxResponseSize = %d, want %d", cfg.MaxResponseSize, DefaultMaxResponseSize)
+	}
+
+	if cfg.MaxConnectionsPerHost != DefaultMaxConnectionsPerHost {
+		t.Errorf("MaxConnectionsPerHost = %d, want %d",
+			cfg.MaxConnectionsPerHost, DefaultMaxConnectionsPerHost)
+	}
+
+	if cfg.AllowHTTP {
+		t.Error("AllowHTTP should default to false")
+	}
+
+	if len(cfg.AllowedContentTypes) == 0 {
+		t.Error("AllowedContentTypes should not be empty")
+	}
+}
+
+func TestNewWithNilConfigUsesDefaults(t *testing.T) {
+	t.Parallel()
+
+	f := New(nil)
+
+	if f == nil {
+		t.Fatal("New(nil) returned nil")
+	}
+
+	if f.config == nil {
+		t.Fatal("config should be populated from DefaultConfig")
+	}
+
+	if f.config.Timeout != DefaultFetchTimeout {
+		t.Errorf("Timeout = %v, want %v", f.config.Timeout, DefaultFetchTimeout)
+	}
+}
+
 func TestIsAllowedContentType(t *testing.T) {
 	t.Parallel()
 
-	f := New(&Config{
+	f := New(DefaultConfig())
-		Timeout:               30 * time.Second,
-		MaxResponseSize:       50 << 20,
-		MaxConnectionsPerHost: 20,
-		MaxConnections:        64,
-	})
 
 	tests := []struct {
 		contentType string
@@ -147,44 +186,6 @@ func TestIsPrivateIP(t *testing.T) {
 	}
 }
 
-// TestIsPrivateIPJudgesEmbeddedIPv4Address checks IPv6 addresses that hold an
-// IPv4 address in their last four bytes: the IPv4-compatible form (::/96) and
-// the NAT64 form (64:ff9b::/96). One holding a loopback, private or
-// link-local IPv4 address is refused as that address is, and one holding a
-// public IPv4 address in the IPv4-compatible form passes.
-func TestIsPrivateIPJudgesEmbeddedIPv4Address(t *testing.T) {
-	t.Parallel()
-
-	tests := []struct {
-		ip   string
-		want bool
-	}{
-		{"::127.0.0.1", true},       // loopback
-		{"::10.0.0.1", true},        // private
-		{"::169.254.169.254", true}, // link-local
-		{"64:ff9b::7f00:1", true},   // NAT64 form of 127.0.0.1
-		{"::8.8.8.8", false},        // public
-	}
-
-	for _, tc := range tests {
-		t.Run(tc.ip, func(t *testing.T) {
-			t.Parallel()
-
-			ip := net.ParseIP(tc.ip)
-			if ip == nil {
-				t.Fatalf("failed to parse IP %q", tc.ip)
-			}
-
-			got := isPrivateIP(ip)
-			t.Logf("isPrivateIP(%s) = %v", ip, got)
-
-			if got != tc.want {
-				t.Errorf("isPrivateIP(%q) = %v, want %v", tc.ip, got, tc.want)
-			}
-		})
-	}
-}
-
 func TestValidateURL_RejectsNonHTTPS(t *testing.T) {
 	t.Parallel()
 

internal/httpfetcher/jpegxl_internal_test.go

@@ -1,26 +1,16 @@
 package httpfetcher
 
-import (
+import "testing"
-	"testing"
-	"time"
-)
 
 // TestJPEGXLContentType verifies that the fetcher accepts an upstream answer
-// of type image/jxl, and that the mock fetcher serves a .jxl file as
+// of type image/jxl by default, and that the mock fetcher serves a .jxl file
-// image/jxl.
+// as image/jxl.
 func TestJPEGXLContentType(t *testing.T) {
 	t.Parallel()
 
 	const jxlType = "image/jxl"
 
-	f := New(&Config{
+	if !New(DefaultConfig()).isAllowedContentType(jxlType) {
-		Timeout:               30 * time.Second,
-		MaxResponseSize:       50 << 20,
-		MaxConnectionsPerHost: 20,
-		MaxConnections:        64,
-	})
-
-	if !f.isAllowedContentType(jxlType) {
 		t.Errorf("isAllowedContentType(%q) = false, want true", jxlType)
 	}
 

internal/httpfetcher/max_connections_internal_test.go

@@ -18,6 +18,14 @@ func imageURLOnPort(port int) string {
 		"/image"
 }
 
+func TestDefaultConfigMaxConnections(t *testing.T) {
+	t.Parallel()
+
+	if got := DefaultConfig().MaxConnections; got != DefaultMaxConnections {
+		t.Errorf("MaxConnections = %d, want %d", got, DefaultMaxConnections)
+	}
+}
+
 // TestFetchLimitsConnectionsToAllHostsTogether checks that MaxConnections
 // counts the fetches to every host together, apart from the per-host
 // limit: with MaxConnections at 2 and two responses open from two hosts, a
@@ -29,12 +37,8 @@ func TestFetchLimitsConnectionsToAllHostsTogether(t *testing.T) {
 
 	srv := startUpstream(t)
 
-	cfg := &Config{
+	cfg := DefaultConfig()
-		Timeout:               30 * time.Second,
+	cfg.MaxConnections = 2
-		MaxResponseSize:       50 << 20,
-		MaxConnectionsPerHost: 20,
-		MaxConnections:        2,
-	}
 
 	f, _ := newServerFetcher(t, srv, cfg)
 	f.connectionWaitTimeout = 100 * time.Millisecond
@@ -90,12 +94,8 @@ func TestFetchFreesHostSlotWhenContextEndsWaitingForConnection(t *testing.T) {
 
 	srv := startUpstream(t)
 
-	cfg := &Config{
+	cfg := DefaultConfig()
-		Timeout:               30 * time.Second,
+	cfg.MaxConnections = 1
-		MaxResponseSize:       50 << 20,
-		MaxConnectionsPerHost: 20,
-		MaxConnections:        1,
-	}
 
 	f, _ := newServerFetcher(t, srv, cfg)
 
@@ -163,12 +163,9 @@ func TestFetchRemovesHostSemaphoreWhenNoConnection(t *testing.T) {
 
 	srv := startUpstream(t)
 
-	cfg := &Config{
+	cfg := DefaultConfig()
-		Timeout:               30 * time.Second,
+	cfg.MaxConnections = 1
-		MaxResponseSize:       50 << 20,
+	cfg.MaxConnectionsPerHost = 1
-		MaxConnectionsPerHost: 1,
-		MaxConnections:        1,
-	}
 
 	f, _ := newServerFetcher(t, srv, cfg)
 	f.connectionWaitTimeout = 100 * time.Millisecond
@@ -239,12 +236,8 @@ func TestFetchReleasesConnectionOnError(t *testing.T) {
 
 			srv := startUpstream(t)
 
-			cfg := &Config{
+			cfg := DefaultConfig()
-				Timeout:               30 * time.Second,
+			cfg.MaxConnections = 1
-				MaxResponseSize:       50 << 20,
-				MaxConnectionsPerHost: 20,
-				MaxConnections:        1,
-			}
 
 			f, _ := newServerFetcher(t, srv, cfg)
 			f.connectionWaitTimeout = 100 * time.Millisecond

internal/imageprocessor/avif_too_large_internal_test.go

@@ -1,97 +0,0 @@
-package imageprocessor
-
-import (
-	"bytes"
-	"encoding/binary"
-	"errors"
-	"os"
-	"testing"
-
-	"sneak.berlin/go/pixa/internal/imagerequest"
-)
-
-// TestImageProcessor_RefusesAVIFAboveMaxPixels verifies that an AVIF output
-// of more than MaxAVIFOutputPixels is refused with ErrAVIFOutputTooLarge
-// before anything is decoded, whatever size and fit give it, the source's own
-// size included, and that an AVIF output of at most that many pixels, or one
-// in another format, is not. One input is a 64x32 PNG cut off in its pixel
-// data. The other is testdata/red.avif, a 4x4 AVIF, with the size in its
-// header changed to 4097x4096. libvips reads each input's size from its
-// header but fails when it decodes its pixel data, so a request that gets
-// that failure was not refused, and a refusal came before any decoding.
-func TestImageProcessor_RefusesAVIFAboveMaxPixels(t *testing.T) {
-	t.Parallel()
-
-	whole := createTestPNG(t, 64, 32)
-	cutOff := whole[:len(whole)/2]
-
-	largeAVIF, err := os.ReadFile("testdata/red.avif")
-	if err != nil {
-		t.Fatalf("failed to read test AVIF: %v", err)
-	}
-
-	// The ispe box gives the width and then the height, 4 bytes each, after
-	// the box's type and its 4 bytes of version and flags
-	ispe := bytes.Index(largeAVIF, []byte("ispe"))
-	binary.BigEndian.PutUint32(largeAVIF[ispe+8:], 4097)
-	binary.BigEndian.PutUint32(largeAVIF[ispe+12:], 4096)
-
-	tests := []struct {
-		name          string
-		input         []byte
-		format        imagerequest.Format
-		width, height int
-		fit           imagerequest.Fit
-		refused       bool
-	}{
-		{"AVIF at the limit", cutOff, imagerequest.FormatAVIF,
-			4096, 4096, imagerequest.FitCover, false},
-		{"AVIF above the limit", cutOff, imagerequest.FormatAVIF,
-			4096, 4097, imagerequest.FitCover, true},
-		{"WebP above the AVIF limit", cutOff, imagerequest.FormatWebP,
-			4096, 4097, imagerequest.FitCover, false},
-		// FitInside does not enlarge, so the output stays 64x32
-		{"AVIF inside a larger size", cutOff, imagerequest.FormatAVIF,
-			8192, 8192, imagerequest.FitInside, false},
-		// FitOutside scales 64x32 by 128 to cover 8192x1: 8192x4096
-		{"AVIF outside a smaller size", cutOff, imagerequest.FormatAVIF,
-			8192, 1, imagerequest.FitOutside, true},
-		// With no size, the output keeps the source's 4097x4096
-		{"AVIF of the source's size", largeAVIF, imagerequest.FormatAVIF,
-			0, 0, imagerequest.FitCover, true},
-		{"orig of an AVIF source", largeAVIF, imagerequest.FormatOriginal,
-			0, 0, imagerequest.FitCover, true},
-		{"JPEG of the source's size", largeAVIF, imagerequest.FormatJPEG,
-			0, 0, imagerequest.FitCover, false},
-	}
-
-	for _, tt := range tests {
-		t.Run(tt.name, func(t *testing.T) {
-			t.Parallel()
-
-			_, err := New(Params{
-				MaxInputBytes:           50 << 20,
-				MaxConcurrentProcessing: 1,
-			}).Process(t.Context(), bytes.NewReader(tt.input),
-				&imagerequest.Transform{
-					Size:    imagerequest.Size{Width: tt.width, Height: tt.height},
-					Format:  tt.format,
-					FitMode: tt.fit,
-				})
-			t.Logf("Process() error = %v", err)
-
-			if tt.refused {
-				if !errors.Is(err, ErrAVIFOutputTooLarge) {
-					t.Errorf("Process() error = %v, want %v", err, ErrAVIFOutputTooLarge)
-				}
-
-				return
-			}
-
-			if err == nil || errors.Is(err, ErrAVIFOutputTooLarge) {
-				t.Errorf("Process() error = %v, want the failure to decode "+
-					"the input", err)
-			}
-		})
-	}
-}

internal/imageprocessor/computed_side_internal_test.go

@@ -4,8 +4,6 @@ import (
 	"bytes"
 	"errors"
 	"testing"
-
-	"sneak.berlin/go/pixa/internal/imagerequest"
 )
 
 // TestImageProcessor_RefusesComputedSideAboveMaximum verifies that a size
@@ -19,17 +17,13 @@ func TestImageProcessor_RefusesComputedSideAboveMaximum(t *testing.T) {
 	tests := []struct {
 		name                    string
 		inputWidth, inputHeight int
-		size                    imagerequest.Size
+		size                    Size
 		wantErr                 error
 	}{
-		{"width at the maximum", 4096, 1,
+		{"width at the maximum", 4096, 1, Size{Height: 2}, nil},
-			imagerequest.Size{Height: 2}, nil},
+		{"width above the maximum", 4096, 1, Size{Height: 3}, ErrOutputTooLarge},
-		{"width above the maximum", 4096, 1,
+		{"height at the maximum", 1, 4096, Size{Width: 2}, nil},
-			imagerequest.Size{Height: 3}, ErrOutputTooLarge},
+		{"height above the maximum", 1, 4096, Size{Width: 3}, ErrOutputTooLarge},
-		{"height at the maximum", 1, 4096,
-			imagerequest.Size{Width: 2}, nil},
-		{"height above the maximum", 1, 4096,
-			imagerequest.Size{Width: 3}, ErrOutputTooLarge},
 	}
 
 	for _, tt := range tests {
@@ -38,16 +32,9 @@ func TestImageProcessor_RefusesComputedSideAboveMaximum(t *testing.T) {
 
 			input := createTestJPEG(t, tt.inputWidth, tt.inputHeight)
 
-			result, err := New(Params{
+			result, err := New(Params{}).Process(t.Context(),
-				MaxInputBytes:           50 << 20,
-				MaxConcurrentProcessing: 1,
-			}).Process(t.Context(),
 				bytes.NewReader(input),
-				&imagerequest.Transform{
+				&Request{Size: tt.size, Format: FormatJPEG, FitMode: FitCover})
-					Size:    tt.size,
-					Format:  imagerequest.FormatJPEG,
-					FitMode: imagerequest.FitCover,
-				})
 			if result != nil {
 				t.Logf("Process() made %dx%d", result.Width, result.Height)
 
@@ -63,79 +50,3 @@ func TestImageProcessor_RefusesComputedSideAboveMaximum(t *testing.T) {
 		})
 	}
 }
-
-// TestImageProcessor_ComputedSideIsAtLeastOne verifies that, for a size with
-// one side 0, the side computed from the input's proportions is 1 where it
-// would round down to 0, and that Process makes that size in every fit mode
-// but FitOutside, which scales the input to cover the size and so can make
-// it longer. Each case checks the size targetDimensions gives before it
-// calls Process: with that side at 0, an 8192x1 input at 1300x0 makes
-// libvips ask for about 39 GB with FitCover.
-func TestImageProcessor_ComputedSideIsAtLeastOne(t *testing.T) {
-	t.Parallel()
-
-	tests := []struct {
-		name                    string
-		inputWidth, inputHeight int
-		size                    imagerequest.Size
-		wantWidth, wantHeight   int
-	}{
-		{"8192x1 at 100x0", 8192, 1, imagerequest.Size{Width: 100}, 100, 1},
-		{"8192x1 at 1300x0", 8192, 1, imagerequest.Size{Width: 1300}, 1300, 1},
-		{"8192x2 at 100x0", 8192, 2, imagerequest.Size{Width: 100}, 100, 1},
-		{"1x8192 at 0x100", 1, 8192, imagerequest.Size{Height: 100}, 1, 100},
-		{"1x8192 at 0x1300", 1, 8192, imagerequest.Size{Height: 1300}, 1, 1300},
-		{"2x8192 at 0x100", 2, 8192, imagerequest.Size{Height: 100}, 1, 100},
-	}
-
-	fits := []imagerequest.Fit{
-		imagerequest.FitCover, imagerequest.FitContain, imagerequest.FitFill,
-		imagerequest.FitInside, imagerequest.FitOutside,
-	}
-
-	for _, tt := range tests {
-		for _, fit := range fits {
-			t.Run(tt.name+" "+string(fit), func(t *testing.T) {
-				t.Parallel()
-
-				width, height, err := targetDimensions(tt.size,
-					tt.inputWidth, tt.inputHeight)
-				if err != nil || width != tt.wantWidth || height != tt.wantHeight {
-					t.Fatalf("targetDimensions() = %dx%d, %v, want %dx%d",
-						width, height, err, tt.wantWidth, tt.wantHeight)
-				}
-
-				input := createTestJPEG(t, tt.inputWidth, tt.inputHeight)
-
-				result, err := New(Params{
-					MaxInputBytes:           50 << 20,
-					MaxConcurrentProcessing: 1,
-				}).Process(t.Context(),
-					bytes.NewReader(input),
-					&imagerequest.Transform{
-						Size:    tt.size,
-						Format:  imagerequest.FormatJPEG,
-						FitMode: fit,
-					})
-				if err != nil {
-					t.Fatalf("Process() error = %v", err)
-				}
-
-				defer func() { _ = result.Content.Close() }()
-
-				t.Logf("Process() made %dx%d", result.Width, result.Height)
-
-				ok := result.Width == tt.wantWidth && result.Height == tt.wantHeight
-				if fit == imagerequest.FitOutside {
-					ok = result.Width >= tt.wantWidth && result.Height >= tt.wantHeight
-				}
-
-				if !ok {
-					t.Errorf("Process() made %dx%d, want %dx%d (at least, for %s)",
-						result.Width, result.Height, tt.wantWidth, tt.wantHeight,
-						imagerequest.FitOutside)
-				}
-			})
-		}
-	}
-}

internal/imageprocessor/deadline_internal_test.go

@@ -84,9 +84,9 @@ func checkProcessStopsAtDeadline(
 ) {
 	t.Helper()
 
-	proc := New(Params{MaxInputBytes: 50 << 20, MaxConcurrentProcessing: 1})
+	proc := New(Params{MaxConcurrentProcessing: 1})
 
-	result, err := proc.Process(ctx, input, smallJPEGTransform())
+	result, err := proc.Process(ctx, input, smallJPEGRequest())
 	if result != nil {
 		t.Logf("Process() made a %dx%d image after its deadline passed",
 			result.Width, result.Height)

internal/imageprocessor/empty_format_internal_test.go

@@ -4,8 +4,6 @@ import (
 	"bytes"
 	"errors"
 	"testing"
-
-	"sneak.berlin/go/pixa/internal/imagerequest"
 )
 
 // TestImageProcessor_EmptyFormatRefused verifies that a request with no format
@@ -14,12 +12,8 @@ import (
 func TestImageProcessor_EmptyFormatRefused(t *testing.T) {
 	t.Parallel()
 
-	_, err := New(Params{
+	_, err := New(Params{}).Process(
-		MaxInputBytes:           50 << 20,
+		t.Context(), bytes.NewReader(createTestJPEG(t, 20, 20)), &Request{},
-		MaxConcurrentProcessing: 1,
-	}).Process(
-		t.Context(), bytes.NewReader(createTestJPEG(t, 20, 20)),
-		&imagerequest.Transform{},
 	)
 	if !errors.Is(err, ErrUnsupportedOutputFormat) {
 		t.Errorf("Process() error = %v, want %v", err, ErrUnsupportedOutputFormat)

internal/imageprocessor/encoder_settings_internal_test.go

@@ -8,20 +8,14 @@ import (
 	"testing"
 
 	"github.com/davidbyttow/govips/v2/vips"
-	"sneak.berlin/go/pixa/internal/imagerequest"
 )
 
 // processedSize runs input through Process and returns the output's size in
 // bytes.
-func processedSize(
+func processedSize(t *testing.T, input []byte, req *Request) int64 {
-	t *testing.T, input []byte, transform *imagerequest.Transform,
-) int64 {
 	t.Helper()
 
-	result, err := New(Params{
+	result, err := New(Params{}).Process(t.Context(), bytes.NewReader(input), req)
-		MaxInputBytes:           50 << 20,
-		MaxConcurrentProcessing: 1,
-	}).Process(t.Context(), bytes.NewReader(input), transform)
 	if err != nil {
 		t.Fatalf("Process() error = %v", err)
 	}
@@ -74,8 +68,7 @@ func TestImageProcessor_PNGIsCompressed(t *testing.T) {
 		}
 	}
 
-	size := processedSize(t, encodePNG(t, flat),
+	size := processedSize(t, encodePNG(t, flat), &Request{Format: FormatPNG})
-		&imagerequest.Transform{Format: imagerequest.FormatPNG})
 
 	const rawBytes = width * height * 3
 	if size > rawBytes/10 {
@@ -84,28 +77,27 @@ func TestImageProcessor_PNGIsCompressed(t *testing.T) {
 	}
 }
 
-// TestImageProcessor_WebPAtEffort2 verifies that WebP is saved at effort 2,
+// TestImageProcessor_WebPAtDefaultEffort verifies that WebP is saved at
-// not libvips' default of 4: the output is the size of the same image saved
+// libvips' default effort, 4: the output is the size of the same image saved
-// at effort 2.
+// at that effort.
-func TestImageProcessor_WebPAtEffort2(t *testing.T) {
+func TestImageProcessor_WebPAtDefaultEffort(t *testing.T) {
 	t.Parallel()
 
 	input := createTestJPEG(t, 200, 150)
 
-	size := processedSize(t, input,
+	size := processedSize(t, input, &Request{Format: FormatWebP, Quality: 85})
-		&imagerequest.Transform{Format: imagerequest.FormatWebP, Quality: 85})
 
 	want, _, err := decode(t, input).ExportWebp(&vips.WebpExportParams{
 		StripMetadata:   true,
 		Quality:         85,
-		ReductionEffort: 2,
+		ReductionEffort: 4,
 	})
 	if err != nil {
 		t.Fatalf("ExportWebp() error = %v", err)
 	}
 
 	if size != int64(len(want)) {
-		t.Errorf("WebP output is %d bytes, want %d, the size at effort 2",
+		t.Errorf("WebP output is %d bytes, want %d, the size at effort 4",
 			size, len(want))
 	}
 }
@@ -134,8 +126,7 @@ func TestImageProcessor_AVIFAtEffort1(t *testing.T) {
 
 	input := encodePNG(t, source)
 
-	size := processedSize(t, input,
+	size := processedSize(t, input, &Request{Format: FormatAVIF, Quality: 85})
-		&imagerequest.Transform{Format: imagerequest.FormatAVIF, Quality: 85})
 
 	want, _, err := decode(t, input).ExportAvif(&vips.AvifExportParams{
 		StripMetadata: true,
@@ -152,30 +143,3 @@ func TestImageProcessor_AVIFAtEffort1(t *testing.T) {
 			"and 8 bits", size, len(want))
 	}
 }
-
-// TestImageProcessor_JPEGXLAtEffort4 verifies that JPEG XL is saved at
-// effort 4, not libvips' default of 7: the output is the size of the same
-// image saved at effort 4, with the distance exportJXL gives quality 85.
-func TestImageProcessor_JPEGXLAtEffort4(t *testing.T) {
-	t.Parallel()
-
-	input := createTestJPEG(t, 200, 150)
-
-	size := processedSize(t, input,
-		&imagerequest.Transform{Format: imagerequest.FormatJXL, Quality: 85})
-
-	params := vips.NewJxlExportParams()
-	params.Quality = 85
-	params.Distance = jxlDistance(85)
-	params.Effort = 4
-
-	want, _, err := decode(t, input).ExportJxl(params)
-	if err != nil {
-		t.Fatalf("ExportJxl() error = %v", err)
-	}
-
-	if size != int64(len(want)) {
-		t.Errorf("JPEG XL output is %d bytes, want %d, the size at effort 4",
-			size, len(want))
-	}
-}

internal/imageprocessor/fit_cover_internal_test.go

@@ -7,8 +7,6 @@ import (
 	"image/png"
 	"math"
 	"testing"
-
-	"sneak.berlin/go/pixa/internal/imagerequest"
 )
 
 // TestImageProcessor_FitCoverServesThinSource verifies that FitCover serves
@@ -22,12 +20,12 @@ func TestImageProcessor_FitCoverServesThinSource(t *testing.T) {
 	tests := []struct {
 		name                    string
 		inputWidth, inputHeight int
-		size                    imagerequest.Size
+		size                    Size
 	}{
-		{"8192x1 at 8192x8192", 8192, 1, imagerequest.Size{Width: 8192, Height: 8192}},
+		{"8192x1 at 8192x8192", 8192, 1, Size{Width: 8192, Height: 8192}},
-		{"8192x1 at 1x8192", 8192, 1, imagerequest.Size{Width: 1, Height: 8192}},
+		{"8192x1 at 1x8192", 8192, 1, Size{Width: 1, Height: 8192}},
-		{"1x8192 at 8192x8192", 1, 8192, imagerequest.Size{Width: 8192, Height: 8192}},
+		{"1x8192 at 8192x8192", 1, 8192, Size{Width: 8192, Height: 8192}},
-		{"1x8192 at 8192x1", 1, 8192, imagerequest.Size{Width: 8192, Height: 1}},
+		{"1x8192 at 8192x1", 1, 8192, Size{Width: 8192, Height: 1}},
 	}
 
 	for _, tt := range tests {
@@ -36,16 +34,9 @@ func TestImageProcessor_FitCoverServesThinSource(t *testing.T) {
 
 			input := createTestJPEG(t, tt.inputWidth, tt.inputHeight)
 
-			result, err := New(Params{
+			result, err := New(Params{}).Process(t.Context(),
-				MaxInputBytes:           50 << 20,
-				MaxConcurrentProcessing: 1,
-			}).Process(t.Context(),
 				bytes.NewReader(input),
-				&imagerequest.Transform{
+				&Request{Size: tt.size, Format: FormatJPEG, FitMode: FitCover})
-					Size:    tt.size,
-					Format:  imagerequest.FormatJPEG,
-					FitMode: imagerequest.FitCover,
-				})
 			if err != nil {
 				t.Fatalf("Process() error = %v", err)
 			}
@@ -109,15 +100,12 @@ func TestImageProcessor_FitCoverCropsTheCentre(t *testing.T) {
 
 			input := createBandsPNG(t, tt.inputWidth, tt.inputHeight)
 
-			result, err := New(Params{
+			result, err := New(Params{}).Process(t.Context(),
-				MaxInputBytes:           50 << 20,
-				MaxConcurrentProcessing: 1,
-			}).Process(t.Context(),
 				bytes.NewReader(input),
-				&imagerequest.Transform{
+				&Request{
-					Size:    imagerequest.Size{Width: 50, Height: 50},
+					Size:    Size{Width: 50, Height: 50},
-					Format:  imagerequest.FormatPNG,
+					Format:  FormatPNG,
-					FitMode: imagerequest.FitCover,
+					FitMode: FitCover,
 				})
 			if err != nil {
 				t.Fatalf("Process() error = %v", err)
@@ -220,14 +208,14 @@ func TestImageProcessor_FitCoverKeepsProportions(t *testing.T) {
 	tests := []struct {
 		name             string
 		side, squareSide int
-		size             imagerequest.Size
+		size             Size
 	}{
-		{"16x16 at 100x60", 16, 8, imagerequest.Size{Width: 100, Height: 60}},
+		{"16x16 at 100x60", 16, 8, Size{Width: 100, Height: 60}},
-		{"16x16 at 60x100", 16, 8, imagerequest.Size{Width: 60, Height: 100}},
+		{"16x16 at 60x100", 16, 8, Size{Width: 60, Height: 100}},
-		{"10x10 at 100x35", 10, 2, imagerequest.Size{Width: 100, Height: 35}},
+		{"10x10 at 100x35", 10, 2, Size{Width: 100, Height: 35}},
-		{"10x10 at 35x100", 10, 2, imagerequest.Size{Width: 35, Height: 100}},
+		{"10x10 at 35x100", 10, 2, Size{Width: 35, Height: 100}},
-		{"64x64 at 300x100", 64, 16, imagerequest.Size{Width: 300, Height: 100}},
+		{"64x64 at 300x100", 64, 16, Size{Width: 300, Height: 100}},
-		{"64x64 at 100x300", 64, 16, imagerequest.Size{Width: 100, Height: 300}},
+		{"64x64 at 100x300", 64, 16, Size{Width: 100, Height: 300}},
 	}
 
 	for _, tt := range tests {
@@ -236,16 +224,9 @@ func TestImageProcessor_FitCoverKeepsProportions(t *testing.T) {
 
 			input := createSquarePNG(t, tt.side, tt.squareSide)
 
-			result, err := New(Params{
+			result, err := New(Params{}).Process(t.Context(),
-				MaxInputBytes:           50 << 20,
-				MaxConcurrentProcessing: 1,
-			}).Process(t.Context(),
 				bytes.NewReader(input),
-				&imagerequest.Transform{
+				&Request{Size: tt.size, Format: FormatPNG, FitMode: FitCover})
-					Size:    tt.size,
-					Format:  imagerequest.FormatPNG,
-					FitMode: imagerequest.FitCover,
-				})
 			if err != nil {
 				t.Fatalf("Process() error = %v", err)
 			}

internal/imageprocessor/fit_outside_internal_test.go

@@ -4,8 +4,6 @@ import (
 	"bytes"
 	"errors"
 	"testing"
-
-	"sneak.berlin/go/pixa/internal/imagerequest"
 )
 
 // TestImageProcessor_RefusesFitOutsideAboveMaximum verifies that FitOutside,
@@ -19,20 +17,15 @@ func TestImageProcessor_RefusesFitOutsideAboveMaximum(t *testing.T) {
 	tests := []struct {
 		name                    string
 		inputWidth, inputHeight int
-		size                    imagerequest.Size
+		size                    Size
 		// wantWidth and wantHeight are the output's, 0 for a refusal
 		wantWidth, wantHeight int
 	}{
-		{"width above the maximum", 3000, 600,
+		{"width above the maximum", 3000, 600, Size{Width: 1, Height: 8192}, 0, 0},
-			imagerequest.Size{Width: 1, Height: 8192}, 0, 0},
+		{"height above the maximum", 600, 3000, Size{Width: 8192, Height: 1}, 0, 0},
-		{"height above the maximum", 600, 3000,
+		{"width at the maximum", 1024, 256, Size{Width: 1, Height: 2048}, 8192, 2048},
-			imagerequest.Size{Width: 8192, Height: 1}, 0, 0},
+		{"height at the maximum", 256, 1024, Size{Width: 2048, Height: 1}, 2048, 8192},
-		{"width at the maximum", 1024, 256,
+		{"within the maximum", 3000, 600, Size{Width: 1, Height: 1200}, 6000, 1200},
-			imagerequest.Size{Width: 1, Height: 2048}, 8192, 2048},
-		{"height at the maximum", 256, 1024,
-			imagerequest.Size{Width: 2048, Height: 1}, 2048, 8192},
-		{"within the maximum", 3000, 600,
-			imagerequest.Size{Width: 1, Height: 1200}, 6000, 1200},
 	}
 
 	for _, tt := range tests {
@@ -41,16 +34,9 @@ func TestImageProcessor_RefusesFitOutsideAboveMaximum(t *testing.T) {
 
 			input := createTestJPEG(t, tt.inputWidth, tt.inputHeight)
 
-			result, err := New(Params{
+			result, err := New(Params{}).Process(t.Context(),
-				MaxInputBytes:           50 << 20,
-				MaxConcurrentProcessing: 1,
-			}).Process(t.Context(),
 				bytes.NewReader(input),
-				&imagerequest.Transform{
+				&Request{Size: tt.size, Format: FormatJPEG, FitMode: FitOutside})
-					Size:    tt.size,
-					Format:  imagerequest.FormatJPEG,
-					FitMode: imagerequest.FitOutside,
-				})
 			if result != nil {
 				t.Logf("Process() made %dx%d", result.Width, result.Height)
 			}
@@ -74,52 +60,3 @@ func TestImageProcessor_RefusesFitOutsideAboveMaximum(t *testing.T) {
 		})
 	}
 }
-
-// TestImageProcessor_FitOutsideSideIsAtLeastOne verifies that FitOutside
-// keeps each side at 1 or more when it works both sides out again from the
-// larger scale. A side of 49 scaled to 1 is 49 times 1/49, which in floating
-// point is just under 1 and so rounded down to 0, a width libvips refuses.
-func TestImageProcessor_FitOutsideSideIsAtLeastOne(t *testing.T) {
-	t.Parallel()
-
-	tests := []struct {
-		name                    string
-		inputWidth, inputHeight int
-		size                    imagerequest.Size
-		wantWidth, wantHeight   int
-	}{
-		{"49x8192 at 0x100", 49, 8192, imagerequest.Size{Height: 100}, 1, 167},
-		{"49x49 at 1x1", 49, 49, imagerequest.Size{Width: 1, Height: 1}, 1, 1},
-	}
-
-	for _, tt := range tests {
-		t.Run(tt.name, func(t *testing.T) {
-			t.Parallel()
-
-			input := createTestJPEG(t, tt.inputWidth, tt.inputHeight)
-
-			result, err := New(Params{
-				MaxInputBytes:           50 << 20,
-				MaxConcurrentProcessing: 1,
-			}).Process(t.Context(),
-				bytes.NewReader(input),
-				&imagerequest.Transform{
-					Size:    tt.size,
-					Format:  imagerequest.FormatJPEG,
-					FitMode: imagerequest.FitOutside,
-				})
-			if err != nil {
-				t.Fatalf("Process() error = %v", err)
-			}
-
-			defer func() { _ = result.Content.Close() }()
-
-			t.Logf("Process() made %dx%d", result.Width, result.Height)
-
-			if result.Width != tt.wantWidth || result.Height != tt.wantHeight {
-				t.Errorf("Process() made %dx%d, want %dx%d",
-					result.Width, result.Height, tt.wantWidth, tt.wantHeight)
-			}
-		})
-	}
-}

internal/imageprocessor/imageprocessor.go

@@ -11,7 +11,7 @@ import (
 	"time"
 
 	"github.com/davidbyttow/govips/v2/vips"
-	"sneak.berlin/go/pixa/internal/imagerequest"
+	"sneak.berlin/go/pixa/internal/config"
 )
 
 // vipsOnce ensures vips is initialized exactly once.
@@ -54,6 +54,49 @@ func CheckJPEGXLSupport() error {
 	return nil
 }
 
+// Format represents supported output image formats.
+type Format string
+
+// Supported image output formats.
+const (
+	FormatOriginal Format = "orig"
+	FormatJPEG     Format = "jpeg"
+	FormatPNG      Format = "png"
+	FormatWebP     Format = "webp"
+	FormatAVIF     Format = "avif"
+	FormatJXL      Format = "jxl"
+	FormatGIF      Format = "gif"
+)
+
+// FitMode represents how to fit an image into requested dimensions.
+type FitMode string
+
+// Supported image fit modes.
+const (
+	FitCover   FitMode = "cover"
+	FitContain FitMode = "contain"
+	FitFill    FitMode = "fill"
+	FitInside  FitMode = "inside"
+	FitOutside FitMode = "outside"
+)
+
+// ErrInvalidFitMode is returned when an invalid fit mode is provided.
+var ErrInvalidFitMode = errors.New("invalid fit mode")
+
+// Size represents requested image dimensions.
+type Size struct {
+	Width  int
+	Height int
+}
+
+// Request holds the parameters for image processing.
+type Request struct {
+	Size    Size
+	Format  Format
+	Quality int
+	FitMode FitMode
+}
+
 // Result contains the output of image processing.
 type Result struct {
 	// Content is the processed image data.
@@ -78,6 +121,10 @@ type Result struct {
 // Images larger than this are rejected to prevent DoS via decompression bombs.
 const MaxInputDimension = 8192
 
+// DefaultMaxInputBytes is the default maximum input size in bytes (50 MiB).
+// This matches the default upstream fetcher limit.
+const DefaultMaxInputBytes = 50 << 20
+
 // ErrInputTooLarge is returned when input image dimensions exceed MaxInputDimension.
 var ErrInputTooLarge = errors.New("input image dimensions exceed maximum")
 
@@ -86,8 +133,8 @@ var ErrInputTooLarge = errors.New("input image dimensions exceed maximum")
 var ErrInputDataTooLarge = errors.New("input data exceeds maximum allowed size")
 
 // MaxOutputDimension is the maximum width or height of an output image, and
-// so of a requested size (imagerequest.MaxDimension).
+// so of a requested size (imgcache.MaxDimension).
-const MaxOutputDimension = imagerequest.MaxDimension
+const MaxOutputDimension = 8192
 
 // ErrOutputTooLarge is returned, before resizing, when the output would have a
 // side above MaxOutputDimension: the side of a size with one side 0, computed
@@ -95,19 +142,6 @@ const MaxOutputDimension = imagerequest.MaxDimension
 // requested size.
 var ErrOutputTooLarge = errors.New("output image dimensions exceed maximum")
 
-// MaxAVIFOutputPixels is the most pixels an AVIF output may have, so that an
-// encode takes at most 40 seconds of the default downstream_timeout of 60
-// seconds; AVIF is already at the lowest effort govips can set (avifEffort).
-// With one thread, as pixad runs libvips, saving 4096x4096, 8192x2048 or
-// 2048x8192 random pixels with an alpha channel takes up to about 34
-// seconds, the slowest at any quality and at 8 or 16 bits per sample, and
-// 5120x4096 at 8 bits already takes about 36.
-const MaxAVIFOutputPixels = 4096 * 4096
-
-// ErrAVIFOutputTooLarge is returned, before anything is decoded, when an AVIF
-// output would have more than MaxAVIFOutputPixels pixels.
-var ErrAVIFOutputTooLarge = errors.New("AVIF output has too many pixels")
-
 // ErrUnsupportedOutputFormat is returned when the requested output format is
 // not supported.
 var ErrUnsupportedOutputFormat = errors.New("unsupported output format")
@@ -137,38 +171,50 @@ type ImageProcessor struct {
 	processingWaitTimeout time.Duration
 }
 
-// Params holds configuration for creating an ImageProcessor. Both fields
+// Params holds configuration for creating an ImageProcessor.
-// must be at least 1.
+// Zero values use sensible defaults (MaxInputBytes defaults to DefaultMaxInputBytes).
 type Params struct {
 	// MaxInputBytes is the maximum allowed input size in bytes.
+	// If <= 0, DefaultMaxInputBytes is used.
 	MaxInputBytes int64
 	// MaxConcurrentProcessing is the most images processed at once.
+	// If <= 0, config.DefaultMaxConcurrentProcessing() is used.
 	MaxConcurrentProcessing int
 }
 
 // New creates a new image processor with the given parameters.
+// A zero-value Params{} uses sensible defaults.
 func New(params Params) *ImageProcessor {
 	initVips()
 
+	maxInputBytes := params.MaxInputBytes
+	if maxInputBytes <= 0 {
+		maxInputBytes = DefaultMaxInputBytes
+	}
+
+	maxConcurrentProcessing := params.MaxConcurrentProcessing
+	if maxConcurrentProcessing <= 0 {
+		maxConcurrentProcessing = config.DefaultMaxConcurrentProcessing()
+	}
+
 	return &ImageProcessor{
-		maxInputBytes:         params.MaxInputBytes,
+		maxInputBytes:         maxInputBytes,
-		processingSemaphore:   make(chan struct{}, params.MaxConcurrentProcessing),
+		processingSemaphore:   make(chan struct{}, maxConcurrentProcessing),
 		processingWaitTimeout: ProcessingWaitTimeout,
 	}
 }
 
-// Process transforms an image according to transform. When
+// Process transforms an image according to the request. When
 // MaxConcurrentProcessing images are already being processed, it waits up
 // to ProcessingWaitTimeout for one to finish, then fails with
 // ErrTooManyImages. When ctx has ended once Process has a slot, or before it
 // encodes, it returns ctx's error and gives the slot back. govips gives pixa
 // no way to stop libvips once an encode has begun, so an encode keeps its
-// slot until it finishes. An AVIF output of more than MaxAVIFOutputPixels is
+// slot until it finishes.
-// refused with ErrAVIFOutputTooLarge before anything is decoded.
 func (p *ImageProcessor) Process(
 	ctx context.Context,
 	input io.Reader,
-	transform *imagerequest.Transform,
+	req *Request,
 ) (*Result, error) {
 	release, err := p.acquireSlot(ctx)
 	if err != nil {
@@ -177,9 +223,18 @@ func (p *ImageProcessor) Process(
 
 	defer release()
 
-	data, err := p.readInput(input)
+	// Read input with a size limit to prevent unbounded memory consumption.
+	// We read at most maxInputBytes+1 so we can detect if the input exceeds
+	// the limit without consuming additional memory.
+	limited := io.LimitReader(input, p.maxInputBytes+1)
+
+	data, err := io.ReadAll(limited)
 	if err != nil {
-		return nil, err
+		return nil, fmt.Errorf("failed to read input: %w", err)
+	}
+
+	if int64(len(data)) > p.maxInputBytes {
+		return nil, ErrInputDataTooLarge
 	}
 
 	// govips picks the libvips loader from the input's first bytes with
@@ -217,36 +272,27 @@ func (p *ImageProcessor) Process(
 	}
 
 	// Determine target dimensions; too large ones are refused before resizing
-	targetWidth, targetHeight, err := targetDimensions(transform.Size,
+	targetWidth, targetHeight, err := targetDimensions(req.Size, origWidth, origHeight)
-		origWidth, origHeight)
-	if err != nil {
-		return nil, err
-	}
-
-	// orig is the source's own format; encode refuses an empty format
-	outputFormat := transform.Format
-	if outputFormat == imagerequest.FormatOriginal {
-		outputFormat = sourceFormat
-	}
-
-	// Determine output dimensions; too large ones are refused before
-	// resizing, which with FitCover already decodes the input
-	outputWidth, outputHeight, err := outputDimensions(origWidth, origHeight,
-		targetWidth, targetHeight, transform.FitMode, outputFormat)
 	if err != nil {
 		return nil, err
 	}
 
 	// Resize if needed
 	if targetWidth != origWidth || targetHeight != origHeight {
-		err := p.resize(img, outputWidth, outputHeight, transform.FitMode)
+		err := p.resize(img, targetWidth, targetHeight, req.FitMode)
 		if err != nil {
 			return nil, fmt.Errorf("failed to resize: %w", err)
 		}
 	}
 
+	// orig is the source's own format; encode refuses an empty format
+	outputFormat := req.Format
+	if outputFormat == FormatOriginal {
+		outputFormat = sourceFormat
+	}
+
 	// Encode to target format
-	output, err := p.encode(ctx, img, outputFormat, transform.Quality)
+	output, err := p.encode(ctx, img, outputFormat, req.Quality)
 	if err != nil {
 		return nil, fmt.Errorf("failed to encode: %w", err)
 	}
@@ -265,13 +311,9 @@ func (p *ImageProcessor) Process(
 
 // targetDimensions calculates the output dimensions for a requested size,
 // scaling proportionally when only one dimension is given and keeping the
-// original dimensions when both are zero. A side scaled proportionally is
+// original dimensions when both are zero. A side scaled proportionally can
-// rounded down but kept at 1 or more, as for a thin image it would round
+// come out above MaxOutputDimension, which is ErrOutputTooLarge.
-// down to 0, a side of no pixels. It can come out above MaxOutputDimension,
+func targetDimensions(size Size, origWidth, origHeight int) (int, int, error) {
-// which is ErrOutputTooLarge.
-func targetDimensions(
-	size imagerequest.Size, origWidth, origHeight int,
-) (int, int, error) {
 	width, height := size.Width, size.Height
 
 	switch {
@@ -280,10 +322,10 @@ func targetDimensions(
 		return origWidth, origHeight, nil
 	case width == 0:
 		// Only height specified: calculate width proportionally
-		width = max(1, origWidth*height/origHeight)
+		width = origWidth * height / origHeight
 	case height == 0:
 		// Only width specified: calculate height proportionally
-		height = max(1, origHeight*width/origWidth)
+		height = origHeight * width / origWidth
 	}
 
 	if width > MaxOutputDimension || height > MaxOutputDimension {
@@ -304,22 +346,46 @@ const (
 	mimeJXL  = "image/jxl"
 )
 
+// SupportedInputFormats returns MIME types this processor can read.
+func (p *ImageProcessor) SupportedInputFormats() []string {
+	return []string{
+		mimeJPEG,
+		mimePNG,
+		mimeGIF,
+		mimeWebP,
+		mimeAVIF,
+		mimeJXL,
+	}
+}
+
+// SupportedOutputFormats returns formats this processor can write.
+func (p *ImageProcessor) SupportedOutputFormats() []Format {
+	return []Format{
+		FormatJPEG,
+		FormatPNG,
+		FormatGIF,
+		FormatWebP,
+		FormatAVIF,
+		FormatJXL,
+	}
+}
+
 // FormatToMIME converts a Format to its MIME type string.
-func FormatToMIME(format imagerequest.Format) string {
+func FormatToMIME(format Format) string {
 	switch format {
-	case imagerequest.FormatJPEG:
+	case FormatJPEG:
 		return mimeJPEG
-	case imagerequest.FormatPNG:
+	case FormatPNG:
 		return mimePNG
-	case imagerequest.FormatWebP:
+	case FormatWebP:
 		return mimeWebP
-	case imagerequest.FormatGIF:
+	case FormatGIF:
 		return mimeGIF
-	case imagerequest.FormatAVIF:
+	case FormatAVIF:
 		return mimeAVIF
-	case imagerequest.FormatJXL:
+	case FormatJXL:
 		return mimeJXL
-	case imagerequest.FormatOriginal, imagerequest.FormatAuto:
+	case FormatOriginal:
 		return "application/octet-stream"
 	default:
 		return "application/octet-stream"
@@ -377,23 +443,6 @@ func (p *ImageProcessor) acquireSlot(ctx context.Context) (func(), error) {
 	return release, nil
 }
 
-// readInput reads input with a size limit to prevent unbounded memory
-// consumption, refusing more than maxInputBytes with ErrInputDataTooLarge. It
-// reads at most maxInputBytes+1 so it can detect if the input exceeds the
-// limit without consuming additional memory.
-func (p *ImageProcessor) readInput(input io.Reader) ([]byte, error) {
-	data, err := io.ReadAll(io.LimitReader(input, p.maxInputBytes+1))
-	if err != nil {
-		return nil, fmt.Errorf("failed to read input: %w", err)
-	}
-
-	if int64(len(data)) > p.maxInputBytes {
-		return nil, ErrInputDataTooLarge
-	}
-
-	return data, nil
-}
-
 // detectFormat returns the format string for a govips image type.
 func (p *ImageProcessor) detectFormat(imageType vips.ImageType) string {
 	switch imageType {
@@ -406,9 +455,9 @@ func (p *ImageProcessor) detectFormat(imageType vips.ImageType) string {
 	case vips.ImageTypeWEBP:
 		return "webp"
 	case vips.ImageTypeAVIF, vips.ImageTypeHEIF:
-		return string(imagerequest.FormatAVIF)
+		return string(FormatAVIF)
 	case vips.ImageTypeJXL:
-		return string(imagerequest.FormatJXL)
+		return string(FormatJXL)
 	case vips.ImageTypeUnknown, vips.ImageTypeMagick, vips.ImageTypePDF,
 		vips.ImageTypeSVG, vips.ImageTypeTIFF, vips.ImageTypeBMP,
 		vips.ImageTypeJP2K:
@@ -418,94 +467,66 @@ func (p *ImageProcessor) detectFormat(imageType vips.ImageType) string {
 	}
 }
 
-// outputDimensions returns the dimensions resize gives an image of imgWidth x
+// resize resizes the image according to the fit mode. With FitOutside one
-// imgHeight for the target dimensions and fit mode, without resizing it, and
+// side can come out larger than requested; when it would be above
-// refuses an output too large for format. With FitOutside one side can come
+// MaxOutputDimension, resize returns ErrOutputTooLarge without resizing.
-// out larger than the target; when it would be above MaxOutputDimension,
-// outputDimensions returns ErrOutputTooLarge. An AVIF output of more than
-// MaxAVIFOutputPixels is ErrAVIFOutputTooLarge.
-func outputDimensions(
-	imgWidth, imgHeight, width, height int,
-	fit imagerequest.Fit, format imagerequest.Format,
-) (int, int, error) {
-	scaleW := float64(width) / float64(imgWidth)
-	scaleH := float64(height) / float64(imgHeight)
-	outputWidth, outputHeight := width, height
-
-	switch fit {
-	case imagerequest.FitCover, imagerequest.FitFill, "":
-		// Cover crops, and fill stretches, to exactly the target dimensions
-
-	case imagerequest.FitContain:
-		// Fit within the target dimensions, maintaining aspect ratio. Scaled
-		// by the smaller scale, the short side of a thin image can round
-		// down to 0, which libvips refuses as a width, so each side is at
-		// least 1.
-		scale := min(scaleW, scaleH)
-		outputWidth = max(1, int(float64(imgWidth)*scale))
-		outputHeight = max(1, int(float64(imgHeight)*scale))
-
-	case imagerequest.FitInside:
-		// Same as contain, but only shrink
-		scale := min(scaleW, scaleH, 1)
-		outputWidth = max(1, int(float64(imgWidth)*scale))
-		outputHeight = max(1, int(float64(imgHeight)*scale))
-
-	case imagerequest.FitOutside:
-		// The smallest dimension fits, the other may exceed the target. A
-		// side scaled to 1 can come out just under 1 in floating point, as
-		// 49 times 1/49 does, and round down to 0, which libvips refuses as
-		// a width, so each side is at least 1.
-		scale := max(scaleW, scaleH)
-		outputWidth = max(1, int(float64(imgWidth)*scale))
-		outputHeight = max(1, int(float64(imgHeight)*scale))
-
-	default:
-		return 0, 0, fmt.Errorf("%w: %s", imagerequest.ErrInvalidFitMode, fit)
-	}
-
-	// The side FitOutside scales past the target is held to the maximum too
-	if max(outputWidth, outputHeight) > MaxOutputDimension {
-		return 0, 0, fmt.Errorf("%w: %dx%d is above %d", ErrOutputTooLarge,
-			outputWidth, outputHeight, MaxOutputDimension)
-	}
-
-	if format == imagerequest.FormatAVIF &&
-		outputWidth*outputHeight > MaxAVIFOutputPixels {
-		return 0, 0, fmt.Errorf("%w: %dx%d is above %d pixels",
-			ErrAVIFOutputTooLarge, outputWidth, outputHeight, MaxAVIFOutputPixels)
-	}
-
-	return outputWidth, outputHeight, nil
-}
-
-// resize resizes the image to width x height, the dimensions
-// outputDimensions gives for the fit mode.
 func (p *ImageProcessor) resize(
-	img *vips.ImageRef, width, height int, fit imagerequest.Fit,
+	img *vips.ImageRef, width, height int, fit FitMode,
 ) error {
 	switch fit {
-	case imagerequest.FitCover, "":
+	case FitCover, "":
 		// Crop the centre and resize to fill exact dimensions (default)
 		return cropCentreAndResize(img, width, height)
 
-	case imagerequest.FitFill:
+	case FitContain:
+		// Resize to fit within dimensions, maintaining aspect ratio
+		imgW, imgH := img.Width(), img.Height()
+		scaleW := float64(width) / float64(imgW)
+		scaleH := float64(height) / float64(imgH)
+		scale := min(scaleW, scaleH)
+		newW := int(float64(imgW) * scale)
+		newH := int(float64(imgH) * scale)
+
+		return img.Thumbnail(newW, newH, vips.InterestingNone)
+
+	case FitFill:
 		// Resize to exact dimensions (may distort)
 		return img.ThumbnailWithSize(width, height, vips.InterestingNone, vips.SizeForce)
 
-	case imagerequest.FitInside:
+	case FitInside:
-		// outputDimensions keeps the dimensions of an image that already fits
+		// Same as contain, but only shrink
-		if img.Width() == width && img.Height() == height {
+		if img.Width() <= width && img.Height() <= height {
-			return nil
+			return nil // Already fits
 		}
 
-		return img.Thumbnail(width, height, vips.InterestingNone)
+		imgW, imgH := img.Width(), img.Height()
+		scaleW := float64(width) / float64(imgW)
+		scaleH := float64(height) / float64(imgH)
+		scale := min(scaleW, scaleH)
+		newW := int(float64(imgW) * scale)
+		newH := int(float64(imgH) * scale)
 
-	case imagerequest.FitContain, imagerequest.FitOutside:
+		return img.Thumbnail(newW, newH, vips.InterestingNone)
-		return img.Thumbnail(width, height, vips.InterestingNone)
+
+	case FitOutside:
+		// Resize so smallest dimension fits, may exceed target on other dimension
+		imgW, imgH := img.Width(), img.Height()
+		scaleW := float64(width) / float64(imgW)
+		scaleH := float64(height) / float64(imgH)
+		scale := max(scaleW, scaleH)
+		newW := int(float64(imgW) * scale)
+		newH := int(float64(imgH) * scale)
+
+		// The dimension that exceeds the target is held to the maximum too
+		if newW > MaxOutputDimension || newH > MaxOutputDimension {
+			return fmt.Errorf("%w: %dx%d is above %d", ErrOutputTooLarge,
+				newW, newH, MaxOutputDimension)
+		}
+
+		return img.Thumbnail(newW, newH, vips.InterestingNone)
 
 	default:
-		return fmt.Errorf("%w: %s", imagerequest.ErrInvalidFitMode, fit)
+		return fmt.Errorf("%w: %s", ErrInvalidFitMode, fit)
 	}
 }
 
@@ -547,8 +568,7 @@ const defaultQuality = 85
 // to stop libvips once an encode has begun, so when ctx has ended encode
 // returns ctx's error without beginning one.
 func (p *ImageProcessor) encode(
-	ctx context.Context, img *vips.ImageRef, format imagerequest.Format,
+	ctx context.Context, img *vips.ImageRef, format Format, quality int,
-	quality int,
 ) ([]byte, error) {
 	err := ctx.Err()
 	if err != nil {
@@ -571,25 +591,25 @@ func (p *ImageProcessor) encode(
 	}
 
 	switch format {
-	case imagerequest.FormatJPEG:
+	case FormatJPEG:
 		return exportJPEG(img, quality)
 
-	case imagerequest.FormatPNG:
+	case FormatPNG:
 		return exportPNG(img)
 
-	case imagerequest.FormatGIF:
+	case FormatGIF:
 		return exportGIF(img)
 
-	case imagerequest.FormatWebP:
+	case FormatWebP:
 		return exportWebP(img, quality)
 
-	case imagerequest.FormatAVIF:
+	case FormatAVIF:
 		return exportAVIF(img, quality)
 
-	case imagerequest.FormatJXL:
+	case FormatJXL:
 		return exportJXL(img, quality)
 
-	case imagerequest.FormatOriginal, imagerequest.FormatAuto:
+	case FormatOriginal:
 		return nil, fmt.Errorf("%w: %s", ErrUnsupportedOutputFormat, format)
 
 	default:
@@ -639,16 +659,11 @@ func exportGIF(img *vips.ImageRef) ([]byte, error) {
 	return output, err
 }
 
-// webpEffort is the WebP effort, from 0 (fastest) to 6. It is below libvips'
+// webpEffort is libvips' default WebP effort, from 0 (fastest) to 6.
-// default of 4 so that an encode takes at most 40 seconds of the default
+const webpEffort = 4
-// downstream_timeout of 60 seconds. With one thread, as pixad runs libvips,
-// saving an 8192x8192 image of random pixels with an alpha channel takes up
-// to about 23 seconds at 2, and up to about 16 without one, at any quality;
-// with an alpha channel, 3 takes about 50 seconds and 4 about 61.
-const webpEffort = 2
 
-// exportWebP encodes img as lossy WebP at quality and webpEffort, without
+// exportWebP encodes img as lossy WebP at quality and libvips' default
-// metadata.
+// effort, without metadata.
 func exportWebP(img *vips.ImageRef, quality int) ([]byte, error) {
 	output, _, err := img.ExportWebp(&vips.WebpExportParams{
 		StripMetadata:   true,
@@ -660,13 +675,12 @@ func exportWebP(img *vips.ImageRef, quality int) ([]byte, error) {
 }
 
 // avifEffort is the AVIF effort, from 0 (fastest) to 9; 1 is the lowest
-// govips can set. With one thread, as pixad runs libvips, 1 takes about 52
+// govips can set. With one thread, as pixad runs libvips, 1 takes about 51
-// seconds to save an 8192x8192 RGB image of random pixels at quality 85,
+// seconds to save an 8192x8192 RGB image of random pixels, and about 110
-// and about 96 with an alpha channel, against the default
+// with an alpha channel, the worst case, against the default
-// downstream_timeout of 60 seconds, so an AVIF output is held to
+// downstream_timeout of 60 seconds. On an image of milder noise, which 1
-// MaxAVIFOutputPixels. On an image of milder noise, which 1 saves in about
+// saves in about 12 seconds, 2 takes nearly a minute and libvips' default,
-// 12 seconds, 2 takes nearly a minute and libvips' default, 4, takes
+// 4, takes minutes.
-// minutes.
 const avifEffort = 1
 
 // avifBitdepth is the AVIF bit depth, 8 bits per sample for every image.
@@ -693,18 +707,10 @@ func exportAVIF(img *vips.ImageRef, quality int) ([]byte, error) {
 // JPEG that names none.
 const jxlResolution = 72 / 25.4
 
-// jxlEffort is the JPEG XL effort, from 1 (fastest) to 9. It is below
+// exportJXL encodes img as JPEG XL at quality, with libvips' default effort
-// libvips' default of 7 so that an encode takes at most 40 seconds of the
+// and without metadata. govips sends libvips a distance, the JPEG XL
-// default downstream_timeout of 60 seconds. With one thread, as pixad runs
+// encoder's own measure of quality, along with the quality, and libvips then
-// libvips, saving an 8192x8192 image of random pixels with an alpha channel
+// uses the distance alone, so the quality is also given as a distance.
-// takes up to about 27 seconds at 4, and up to about 13 without one, at any
-// quality; with an alpha channel, 5 takes about 43 seconds and 7 about 81.
-const jxlEffort = 4
-
-// exportJXL encodes img as JPEG XL at quality and jxlEffort, without
-// metadata. govips sends libvips a distance, the JPEG XL encoder's own
-// measure of quality, along with the quality, and libvips then uses the
-// distance alone, so the quality is also given as a distance.
 func exportJXL(img *vips.ImageRef, quality int) ([]byte, error) {
 	// libvips converts a CMYK image to sRGB before it saves WebP, AVIF or
 	// PNG, but cannot save one as JPEG XL. encode has already converted
@@ -743,7 +749,6 @@ func exportJXL(img *vips.ImageRef, quality int) ([]byte, error) {
 	params := vips.NewJxlExportParams()
 	params.Quality = quality
 	params.Distance = jxlDistance(quality)
-	params.Effort = jxlEffort
 
 	output, _, err := toSave.ExportJxl(params)
 	if err != nil {
@@ -771,22 +776,20 @@ func jxlDistance(quality int) float64 {
 
 // formatFromString converts a format string from detectFormat to Format. A
 // format detectFormat could not name is ErrUnsupportedInputFormat.
-func (p *ImageProcessor) formatFromString(
+func (p *ImageProcessor) formatFromString(format string) (Format, error) {
-	format string,
-) (imagerequest.Format, error) {
 	switch format {
 	case "jpeg":
-		return imagerequest.FormatJPEG, nil
+		return FormatJPEG, nil
 	case "png":
-		return imagerequest.FormatPNG, nil
+		return FormatPNG, nil
 	case "gif":
-		return imagerequest.FormatGIF, nil
+		return FormatGIF, nil
 	case "webp":
-		return imagerequest.FormatWebP, nil
+		return FormatWebP, nil
-	case string(imagerequest.FormatAVIF):
+	case string(FormatAVIF):
-		return imagerequest.FormatAVIF, nil
+		return FormatAVIF, nil
-	case string(imagerequest.FormatJXL):
+	case string(FormatJXL):
-		return imagerequest.FormatJXL, nil
+		return FormatJXL, nil
 	default:
 		return "", fmt.Errorf("%w: %s", ErrUnsupportedInputFormat, format)
 	}

internal/imageprocessor/imageprocessor_internal_test.go

@@ -15,7 +15,6 @@ import (
 	"testing"
 
 	"github.com/davidbyttow/govips/v2/vips"
-	"sneak.berlin/go/pixa/internal/imagerequest"
 )
 
 func TestMain(m *testing.M) {
@@ -88,7 +87,7 @@ func isAVIF(data []byte) bool {
 
 	brand := string(data[8:12])
 
-	return brand == string(imagerequest.FormatAVIF) || brand == "avis"
+	return brand == string(FormatAVIF) || brand == "avis"
 }
 
 // detectMIME is a minimal magic-byte detector for test assertions.
@@ -119,19 +118,19 @@ func detectMIME(data []byte) string {
 func TestImageProcessor_ResizeJPEG(t *testing.T) {
 	t.Parallel()
 
-	proc := New(Params{MaxInputBytes: 50 << 20, MaxConcurrentProcessing: 1})
+	proc := New(Params{})
 	ctx := context.Background()
 
 	input := createTestJPEG(t, 800, 600)
 
-	transform := &imagerequest.Transform{
+	req := &Request{
-		Size:    imagerequest.Size{Width: 400, Height: 300},
+		Size:    Size{Width: 400, Height: 300},
-		Format:  imagerequest.FormatJPEG,
+		Format:  FormatJPEG,
 		Quality: 85,
-		FitMode: imagerequest.FitCover,
+		FitMode: FitCover,
 	}
 
-	result, err := proc.Process(ctx, bytes.NewReader(input), transform)
+	result, err := proc.Process(ctx, bytes.NewReader(input), req)
 	if err != nil {
 		t.Fatalf("Process() error = %v", err)
 	}
@@ -165,18 +164,18 @@ func TestImageProcessor_ResizeJPEG(t *testing.T) {
 func TestImageProcessor_ConvertToPNG(t *testing.T) {
 	t.Parallel()
 
-	proc := New(Params{MaxInputBytes: 50 << 20, MaxConcurrentProcessing: 1})
+	proc := New(Params{})
 	ctx := context.Background()
 
 	input := createTestJPEG(t, 200, 150)
 
-	transform := &imagerequest.Transform{
+	req := &Request{
-		Size:    imagerequest.Size{Width: 200, Height: 150},
+		Size:    Size{Width: 200, Height: 150},
-		Format:  imagerequest.FormatPNG,
+		Format:  FormatPNG,
-		FitMode: imagerequest.FitCover,
+		FitMode: FitCover,
 	}
 
-	result, err := proc.Process(ctx, bytes.NewReader(input), transform)
+	result, err := proc.Process(ctx, bytes.NewReader(input), req)
 	if err != nil {
 		t.Fatalf("Process() error = %v", err)
 	}
@@ -197,23 +196,23 @@ func TestImageProcessor_ConvertToPNG(t *testing.T) {
 // processAndCheckSize processes a test JPEG of the given input dimensions
 // with the requested size and asserts the resulting dimensions.
 func processAndCheckSize(
-	t *testing.T, inputW, inputH int, size imagerequest.Size, wantW, wantH int,
+	t *testing.T, inputW, inputH int, size Size, wantW, wantH int,
 ) {
 	t.Helper()
 
-	proc := New(Params{MaxInputBytes: 50 << 20, MaxConcurrentProcessing: 1})
+	proc := New(Params{})
 	ctx := context.Background()
 
 	input := createTestJPEG(t, inputW, inputH)
 
-	transform := &imagerequest.Transform{
+	req := &Request{
 		Size:    size,
-		Format:  imagerequest.FormatJPEG,
+		Format:  FormatJPEG,
 		Quality: 85,
-		FitMode: imagerequest.FitCover,
+		FitMode: FitCover,
 	}
 
-	result, err := proc.Process(ctx, bytes.NewReader(input), transform)
+	result, err := proc.Process(ctx, bytes.NewReader(input), req)
 	if err != nil {
 		t.Fatalf("Process() error = %v", err)
 	}
@@ -233,27 +232,27 @@ func TestImageProcessor_OriginalSize(t *testing.T) {
 	t.Parallel()
 
 	// Width and height 0: keep original size
-	processAndCheckSize(t, 640, 480, imagerequest.Size{Width: 0, Height: 0}, 640, 480)
+	processAndCheckSize(t, 640, 480, Size{Width: 0, Height: 0}, 640, 480)
 }
 
 func TestImageProcessor_FitContain(t *testing.T) {
 	t.Parallel()
 
-	proc := New(Params{MaxInputBytes: 50 << 20, MaxConcurrentProcessing: 1})
+	proc := New(Params{})
 	ctx := context.Background()
 
 	// 800x400 image (2:1 aspect) into 400x400 box with contain
 	// Should result in 400x200 (maintaining aspect ratio)
 	input := createTestJPEG(t, 800, 400)
 
-	transform := &imagerequest.Transform{
+	req := &Request{
-		Size:    imagerequest.Size{Width: 400, Height: 400},
+		Size:    Size{Width: 400, Height: 400},
-		Format:  imagerequest.FormatJPEG,
+		Format:  FormatJPEG,
 		Quality: 85,
-		FitMode: imagerequest.FitContain,
+		FitMode: FitContain,
 	}
 
-	result, err := proc.Process(ctx, bytes.NewReader(input), transform)
+	result, err := proc.Process(ctx, bytes.NewReader(input), req)
 	if err != nil {
 		t.Fatalf("Process() error = %v", err)
 	}
@@ -271,7 +270,7 @@ func TestImageProcessor_ProportionalScale_WidthOnly(t *testing.T) {
 
 	// 800x600 image, request width=400 height=0
 	// Should scale proportionally to 400x300
-	processAndCheckSize(t, 800, 600, imagerequest.Size{Width: 400, Height: 0}, 400, 300)
+	processAndCheckSize(t, 800, 600, Size{Width: 400, Height: 0}, 400, 300)
 }
 
 func TestImageProcessor_ProportionalScale_HeightOnly(t *testing.T) {
@@ -279,24 +278,24 @@ func TestImageProcessor_ProportionalScale_HeightOnly(t *testing.T) {
 
 	// 800x600 image, request width=0 height=300
 	// Should scale proportionally to 400x300
-	processAndCheckSize(t, 800, 600, imagerequest.Size{Width: 0, Height: 300}, 400, 300)
+	processAndCheckSize(t, 800, 600, Size{Width: 0, Height: 300}, 400, 300)
 }
 
 func TestImageProcessor_ProcessPNG(t *testing.T) {
 	t.Parallel()
 
-	proc := New(Params{MaxInputBytes: 50 << 20, MaxConcurrentProcessing: 1})
+	proc := New(Params{})
 	ctx := context.Background()
 
 	input := createTestPNG(t, 400, 300)
 
-	transform := &imagerequest.Transform{
+	req := &Request{
-		Size:    imagerequest.Size{Width: 200, Height: 150},
+		Size:    Size{Width: 200, Height: 150},
-		Format:  imagerequest.FormatPNG,
+		Format:  FormatPNG,
-		FitMode: imagerequest.FitCover,
+		FitMode: FitCover,
 	}
 
-	result, err := proc.Process(ctx, bytes.NewReader(input), transform)
+	result, err := proc.Process(ctx, bytes.NewReader(input), req)
 	if err != nil {
 		t.Fatalf("Process() error = %v", err)
 	}
@@ -312,6 +311,22 @@ func TestImageProcessor_ProcessPNG(t *testing.T) {
 	}
 }
 
+func TestImageProcessor_SupportedFormats(t *testing.T) {
+	t.Parallel()
+
+	proc := New(Params{})
+
+	inputFormats := proc.SupportedInputFormats()
+	if len(inputFormats) == 0 {
+		t.Error("SupportedInputFormats() returned empty slice")
+	}
+
+	outputFormats := proc.SupportedOutputFormats()
+	if len(outputFormats) == 0 {
+		t.Error("SupportedOutputFormats() returned empty slice")
+	}
+}
+
 func TestImageProcessor_RejectsOversizedInput(t *testing.T) {
 	t.Parallel()
 
@@ -330,18 +345,18 @@ func TestImageProcessor_RejectsOversizedInput(t *testing.T) {
 		t.Run(tt.name, func(t *testing.T) {
 			t.Parallel()
 
-			proc := New(Params{MaxInputBytes: 50 << 20, MaxConcurrentProcessing: 1})
+			proc := New(Params{})
 			ctx := context.Background()
 			input := createTestJPEG(t, tt.width, tt.height)
 
-			transform := &imagerequest.Transform{
+			req := &Request{
-				Size:    imagerequest.Size{Width: 100, Height: 100},
+				Size:    Size{Width: 100, Height: 100},
-				Format:  imagerequest.FormatJPEG,
+				Format:  FormatJPEG,
 				Quality: 85,
-				FitMode: imagerequest.FitCover,
+				FitMode: FitCover,
 			}
 
-			_, err := proc.Process(ctx, bytes.NewReader(input), transform)
+			_, err := proc.Process(ctx, bytes.NewReader(input), req)
 			if err == nil {
 				t.Error("Process() should reject oversized input images")
 			}
@@ -356,20 +371,20 @@ func TestImageProcessor_RejectsOversizedInput(t *testing.T) {
 func TestImageProcessor_AcceptsMaxDimensionInput(t *testing.T) {
 	t.Parallel()
 
-	proc := New(Params{MaxInputBytes: 50 << 20, MaxConcurrentProcessing: 1})
+	proc := New(Params{})
 	ctx := context.Background()
 
 	// Create an image at exactly MaxInputDimension - should be accepted
 	input := createTestJPEG(t, MaxInputDimension, 100)
 
-	transform := &imagerequest.Transform{
+	req := &Request{
-		Size:    imagerequest.Size{Width: 100, Height: 100},
+		Size:    Size{Width: 100, Height: 100},
-		Format:  imagerequest.FormatJPEG,
+		Format:  FormatJPEG,
 		Quality: 85,
-		FitMode: imagerequest.FitCover,
+		FitMode: FitCover,
 	}
 
-	result, err := proc.Process(ctx, bytes.NewReader(input), transform)
+	result, err := proc.Process(ctx, bytes.NewReader(input), req)
 	if err != nil {
 		t.Fatalf(
 			"Process() should accept images at MaxInputDimension, got error: %v",
@@ -382,24 +397,22 @@ func TestImageProcessor_AcceptsMaxDimensionInput(t *testing.T) {
 
 // encodeAndCheck processes a 200x150 test JPEG into a 100x75 output of the
 // given format and asserts the output MIME type and dimensions.
-func encodeAndCheck(
+func encodeAndCheck(t *testing.T, format Format, quality int, wantMIME string) {
-	t *testing.T, format imagerequest.Format, quality int, wantMIME string,
-) {
 	t.Helper()
 
-	proc := New(Params{MaxInputBytes: 50 << 20, MaxConcurrentProcessing: 1})
+	proc := New(Params{})
 	ctx := context.Background()
 
 	input := createTestJPEG(t, 200, 150)
 
-	transform := &imagerequest.Transform{
+	req := &Request{
-		Size:    imagerequest.Size{Width: 100, Height: 75},
+		Size:    Size{Width: 100, Height: 75},
 		Format:  format,
 		Quality: quality,
-		FitMode: imagerequest.FitCover,
+		FitMode: FitCover,
 	}
 
-	result, err := proc.Process(ctx, bytes.NewReader(input), transform)
+	result, err := proc.Process(ctx, bytes.NewReader(input), req)
 	if err != nil {
 		t.Fatalf("Process() error = %v, want nil", err)
 	}
@@ -430,13 +443,13 @@ func encodeAndCheck(
 func TestImageProcessor_EncodeWebP(t *testing.T) {
 	t.Parallel()
 
-	encodeAndCheck(t, imagerequest.FormatWebP, 80, mimeWebP)
+	encodeAndCheck(t, FormatWebP, 80, mimeWebP)
 }
 
 func TestImageProcessor_DecodeAVIF(t *testing.T) {
 	t.Parallel()
 
-	proc := New(Params{MaxInputBytes: 50 << 20, MaxConcurrentProcessing: 1})
+	proc := New(Params{})
 	ctx := context.Background()
 
 	// Load test AVIF file
@@ -446,14 +459,14 @@ func TestImageProcessor_DecodeAVIF(t *testing.T) {
 	}
 
 	// Request resize and convert to JPEG
-	transform := &imagerequest.Transform{
+	req := &Request{
-		Size:    imagerequest.Size{Width: 2, Height: 2},
+		Size:    Size{Width: 2, Height: 2},
-		Format:  imagerequest.FormatJPEG,
+		Format:  FormatJPEG,
 		Quality: 85,
-		FitMode: imagerequest.FitCover,
+		FitMode: FitCover,
 	}
 
-	result, err := proc.Process(ctx, bytes.NewReader(input), transform)
+	result, err := proc.Process(ctx, bytes.NewReader(input), req)
 	if err != nil {
 		t.Fatalf("Process() error = %v, want nil (AVIF decoding should work)", err)
 	}
@@ -478,7 +491,7 @@ func TestImageProcessor_RejectsOversizedInputData(t *testing.T) {
 	// Create a processor with a very small byte limit
 	const limit = 1024
 
-	proc := New(Params{MaxInputBytes: limit, MaxConcurrentProcessing: 1})
+	proc := New(Params{MaxInputBytes: limit})
 	ctx := context.Background()
 
 	// Create a valid JPEG that exceeds the byte limit
@@ -487,14 +500,14 @@ func TestImageProcessor_RejectsOversizedInputData(t *testing.T) {
 		t.Fatalf("test JPEG must exceed %d bytes, got %d", limit, len(input))
 	}
 
-	transform := &imagerequest.Transform{
+	req := &Request{
-		Size:    imagerequest.Size{Width: 100, Height: 75},
+		Size:    Size{Width: 100, Height: 75},
-		Format:  imagerequest.FormatJPEG,
+		Format:  FormatJPEG,
 		Quality: 85,
-		FitMode: imagerequest.FitCover,
+		FitMode: FitCover,
 	}
 
-	_, err := proc.Process(ctx, bytes.NewReader(input), transform)
+	_, err := proc.Process(ctx, bytes.NewReader(input), req)
 	if err == nil {
 		t.Fatal("Process() should reject input exceeding maxInputBytes")
 	}
@@ -511,17 +524,17 @@ func TestImageProcessor_AcceptsInputWithinLimit(t *testing.T) {
 	input := createTestJPEG(t, 10, 10)
 	limit := int64(len(input)) * 10 // 10× headroom
 
-	proc := New(Params{MaxInputBytes: limit, MaxConcurrentProcessing: 1})
+	proc := New(Params{MaxInputBytes: limit})
 	ctx := context.Background()
 
-	transform := &imagerequest.Transform{
+	req := &Request{
-		Size:    imagerequest.Size{Width: 10, Height: 10},
+		Size:    Size{Width: 10, Height: 10},
-		Format:  imagerequest.FormatJPEG,
+		Format:  FormatJPEG,
 		Quality: 85,
-		FitMode: imagerequest.FitCover,
+		FitMode: FitCover,
 	}
 
-	result, err := proc.Process(ctx, bytes.NewReader(input), transform)
+	result, err := proc.Process(ctx, bytes.NewReader(input), req)
 	if err != nil {
 		t.Fatalf("Process() error = %v, want nil", err)
 	}
@@ -529,24 +542,35 @@ func TestImageProcessor_AcceptsInputWithinLimit(t *testing.T) {
 	defer func() { _ = result.Content.Close() }()
 }
 
+func TestImageProcessor_DefaultMaxInputBytes(t *testing.T) {
+	t.Parallel()
+
+	// Passing 0 should use the default
+	proc := New(Params{})
+	if proc.maxInputBytes != DefaultMaxInputBytes {
+		t.Errorf("maxInputBytes = %d, want %d", proc.maxInputBytes, DefaultMaxInputBytes)
+	}
+
+	// Passing negative should also use the default
+	proc = New(Params{MaxInputBytes: -1})
+	if proc.maxInputBytes != DefaultMaxInputBytes {
+		t.Errorf("maxInputBytes = %d, want %d", proc.maxInputBytes, DefaultMaxInputBytes)
+	}
+}
+
 func TestImageProcessor_EncodeAVIF(t *testing.T) {
 	t.Parallel()
 
-	encodeAndCheck(t, imagerequest.FormatAVIF, 85, mimeAVIF)
+	encodeAndCheck(t, FormatAVIF, 85, mimeAVIF)
 }
 
 // processAndDecode runs input through Process and decodes the output with
 // vips, so a test can inspect the image a client would receive.
-func processAndDecode(
+func processAndDecode(t *testing.T, input []byte, req *Request) *vips.ImageRef {
-	t *testing.T, input []byte, transform *imagerequest.Transform,
-) *vips.ImageRef {
 	t.Helper()
 
-	result, err := New(Params{
+	result, err := New(Params{}).Process(
-		MaxInputBytes:           50 << 20,
+		context.Background(), bytes.NewReader(input), req,
-		MaxConcurrentProcessing: 1,
-	}).Process(
-		context.Background(), bytes.NewReader(input), transform,
 	)
 	if err != nil {
 		t.Fatalf("Process() error = %v", err)
@@ -590,17 +614,15 @@ func TestImageProcessor_StripsEXIF(t *testing.T) {
 		t.Fatal("testdata/gps-exif.jpg has no GPS latitude")
 	}
 
-	formats := []imagerequest.Format{
+	formats := []Format{
-		imagerequest.FormatJPEG, imagerequest.FormatPNG, imagerequest.FormatWebP,
+		FormatJPEG, FormatPNG, FormatWebP, FormatAVIF, FormatGIF, FormatOriginal,
-		imagerequest.FormatAVIF, imagerequest.FormatGIF, imagerequest.FormatOriginal,
 	}
 
 	for _, format := range formats {
 		t.Run(string(format), func(t *testing.T) {
 			t.Parallel()
 
-			output := processAndDecode(t, input,
+			output := processAndDecode(t, input, &Request{Format: format})
-				&imagerequest.Transform{Format: format})
 
 			if output.HasExif() {
 				t.Errorf("output has EXIF: %v", output.GetExif())
@@ -622,21 +644,21 @@ func TestImageProcessor_AppliesEXIFOrientation(t *testing.T) {
 
 	tests := []struct {
 		name  string
-		size  imagerequest.Size
+		size  Size
 		wantW int
 		wantH int
 	}{
-		{name: "original size", size: imagerequest.Size{}, wantW: 8, wantH: 16},
+		{name: "original size", size: Size{}, wantW: 8, wantH: 16},
-		{name: "width only", size: imagerequest.Size{Width: 4}, wantW: 4, wantH: 8},
+		{name: "width only", size: Size{Width: 4}, wantW: 4, wantH: 8},
 	}
 
 	for _, tt := range tests {
 		t.Run(tt.name, func(t *testing.T) {
 			t.Parallel()
 
-			output := processAndDecode(t, input, &imagerequest.Transform{
+			output := processAndDecode(t, input, &Request{
 				Size:   tt.size,
-				Format: imagerequest.FormatPNG,
+				Format: FormatPNG,
 			})
 
 			if output.Width() != tt.wantW || output.Height() != tt.wantH {
@@ -672,8 +694,7 @@ func TestImageProcessor_ConvertsWideGamutToSRGB(t *testing.T) {
 		t.Fatalf("failed to read test JPEG: %v", err)
 	}
 
-	output := processAndDecode(t, input,
+	output := processAndDecode(t, input, &Request{Format: FormatPNG})
-		&imagerequest.Transform{Format: imagerequest.FormatPNG})
 
 	if output.HasICCProfile() {
 		t.Error("output has an ICC profile")

internal/imageprocessor/jpegxl_output_internal_test.go

@@ -8,7 +8,6 @@ import (
 	"testing"
 
 	"github.com/davidbyttow/govips/v2/vips"
-	"sneak.berlin/go/pixa/internal/imagerequest"
 )
 
 // TestImageProcessor_EncodeJPEGXL converts a JPEG to a smaller JPEG XL and
@@ -16,16 +15,10 @@ import (
 func TestImageProcessor_EncodeJPEGXL(t *testing.T) {
 	t.Parallel()
 
-	transform := &imagerequest.Transform{
+	req := &Request{Size: Size{Width: 100, Height: 75}, Format: FormatJXL}
-		Size:   imagerequest.Size{Width: 100, Height: 75},
-		Format: imagerequest.FormatJXL,
-	}
 
-	result, err := New(Params{
+	result, err := New(Params{}).Process(
-		MaxInputBytes:           50 << 20,
+		t.Context(), bytes.NewReader(createTestJPEG(t, 200, 150)), req,
-		MaxConcurrentProcessing: 1,
-	}).Process(
-		t.Context(), bytes.NewReader(createTestJPEG(t, 200, 150)), transform,
 	)
 	if err != nil {
 		t.Fatalf("Process() error = %v", err)
@@ -67,12 +60,8 @@ func TestImageProcessor_JPEGXLQuality(t *testing.T) {
 	outputBytes := make(map[int]int64)
 
 	for _, quality := range []int{30, 90} {
-		result, err := New(Params{
+		result, err := New(Params{}).Process(t.Context(),
-			MaxInputBytes:           50 << 20,
+			bytes.NewReader(input), &Request{Format: FormatJXL, Quality: quality})
-			MaxConcurrentProcessing: 1,
-		}).Process(t.Context(),
-			bytes.NewReader(input),
-			&imagerequest.Transform{Format: imagerequest.FormatJXL, Quality: quality})
 		if err != nil {
 			t.Fatalf("Process() at quality %d error = %v", quality, err)
 		}
@@ -100,8 +89,7 @@ func TestImageProcessor_JPEGXLDropsSourceEXIF(t *testing.T) {
 		t.Fatalf("failed to read test JPEG: %v", err)
 	}
 
-	exif := processAndDecode(t, input,
+	exif := processAndDecode(t, input, &Request{Format: FormatJXL}).GetExif()
-		&imagerequest.Transform{Format: imagerequest.FormatJXL}).GetExif()
 
 	for _, field := range []string{
 		"exif-ifd0-Make", "exif-ifd0-Model", "exif-ifd2-BodySerialNumber",
@@ -127,8 +115,7 @@ func TestImageProcessor_JPEGXLDropsSourceResolution(t *testing.T) {
 		t.Fatalf("failed to read test JPEG: %v", err)
 	}
 
-	output := processAndDecode(t, input,
+	output := processAndDecode(t, input, &Request{Format: FormatJXL})
-		&imagerequest.Transform{Format: imagerequest.FormatJXL})
 
 	// libvips gives the resolution in pixels per millimetre.
 	xDPI := math.Round(output.ResX() * 25.4)
@@ -153,8 +140,7 @@ func TestImageProcessor_JPEGXLAppliesEXIFOrientation(t *testing.T) {
 		t.Fatalf("failed to read test JPEG: %v", err)
 	}
 
-	output := processAndDecode(t, input,
+	output := processAndDecode(t, input, &Request{Format: FormatJXL})
-		&imagerequest.Transform{Format: imagerequest.FormatJXL})
 
 	if output.Width() != 8 || output.Height() != 16 {
 		t.Fatalf("output is %dx%d, want 8x16", output.Width(), output.Height())
@@ -190,8 +176,7 @@ func TestImageProcessor_JPEGXLConvertsWideGamutToSRGB(t *testing.T) {
 		t.Fatalf("failed to read test JPEG: %v", err)
 	}
 
-	output := processAndDecode(t, input,
+	output := processAndDecode(t, input, &Request{Format: FormatJXL})
-		&imagerequest.Transform{Format: imagerequest.FormatJXL})
 
 	pixel, err := output.GetPoint(4, 4)
 	if err != nil {
@@ -218,8 +203,7 @@ func TestImageProcessor_JPEGXLFromCMYK(t *testing.T) {
 		t.Fatalf("failed to read test JPEG: %v", err)
 	}
 
-	output := processAndDecode(t, input,
+	output := processAndDecode(t, input, &Request{Format: FormatJXL})
-		&imagerequest.Transform{Format: imagerequest.FormatJXL})
 
 	if output.Bands() != 3 {
 		t.Fatalf("output has %d bands, want 3", output.Bands())

internal/imageprocessor/max_concurrent_processing_internal_test.go

@@ -5,13 +5,12 @@ import (
 	"context"
 	"errors"
 	"io"
+	"runtime"
 	"strings"
 	"sync"
 	"testing"
 	"testing/iotest"
 	"time"
-
-	"sneak.berlin/go/pixa/internal/imagerequest"
 )
 
 // errTestReadFailed is the error the unreadable test input returns.
@@ -77,13 +76,13 @@ func (r *gatedReader) Read(p []byte) (int, error) {
 	return n, err
 }
 
-// smallJPEGTransform asks for a 5x5 JPEG.
+// smallJPEGRequest asks for a 5x5 JPEG.
-func smallJPEGTransform() *imagerequest.Transform {
+func smallJPEGRequest() *Request {
-	return &imagerequest.Transform{
+	return &Request{
-		Size:    imagerequest.Size{Width: 5, Height: 5},
+		Size:    Size{Width: 5, Height: 5},
-		Format:  imagerequest.FormatJPEG,
+		Format:  FormatJPEG,
 		Quality: 85,
-		FitMode: imagerequest.FitCover,
+		FitMode: FitCover,
 	}
 }
 
@@ -93,7 +92,7 @@ func processInBackground(
 	proc *ImageProcessor, reader *gatedReader, results chan<- error,
 ) {
 	go func() {
-		result, err := proc.Process(context.Background(), reader, smallJPEGTransform())
+		result, err := proc.Process(context.Background(), reader, smallJPEGRequest())
 		if err == nil {
 			_ = result.Content.Close()
 		}
@@ -116,15 +115,47 @@ func waitForEntries(t *testing.T, entered <-chan struct{}, count int) {
 	}
 }
 
-func TestNewMakesMaxConcurrentProcessingSlots(t *testing.T) {
+func TestNewDefaultsMaxConcurrentProcessingToHalfTheCPUs(t *testing.T) {
 	t.Parallel()
 
-	proc := New(Params{MaxInputBytes: 50 << 20, MaxConcurrentProcessing: 3})
+	for _, limit := range []int{0, -1} {
+		proc := New(Params{MaxConcurrentProcessing: limit})
+		if got := cap(proc.processingSemaphore); got != max(runtime.GOMAXPROCS(0)/2, 1) {
+			t.Errorf("MaxConcurrentProcessing %d: %d slots, want %d, half the CPUs",
+				limit, got, max(runtime.GOMAXPROCS(0)/2, 1))
+		}
+	}
+
+	proc := New(Params{MaxConcurrentProcessing: 3})
 	if got := cap(proc.processingSemaphore); got != 3 {
 		t.Errorf("MaxConcurrentProcessing 3: %d slots, want 3", got)
 	}
 }
 
+// TestNewDefaultIsHalfTheCPUsAndAtLeastOne checks that New, given no
+// MaxConcurrentProcessing, makes one slot for every two CPUs Go uses,
+// rounded down, and one slot when Go uses one CPU.
+//
+//nolint:paralleltest // it sets GOMAXPROCS, which other tests read
+func TestNewDefaultIsHalfTheCPUsAndAtLeastOne(t *testing.T) {
+	cpusBefore := runtime.GOMAXPROCS(0)
+
+	t.Cleanup(func() { runtime.GOMAXPROCS(cpusBefore) })
+
+	for _, tc := range []struct{ cpus, want int }{
+		{1, 1}, {2, 1}, {3, 1}, {8, 4},
+	} {
+		runtime.GOMAXPROCS(tc.cpus)
+
+		got := cap(New(Params{}).processingSemaphore)
+		t.Logf("GOMAXPROCS %d: %d slots", tc.cpus, got)
+
+		if got != tc.want {
+			t.Errorf("GOMAXPROCS %d: %d slots, want %d", tc.cpus, got, tc.want)
+		}
+	}
+}
+
 // TestProcessNeverExceedsMaxConcurrentProcessing starts more Process calls
 // than MaxConcurrentProcessing allows and holds the first ones inside
 // Process until the test lets them go. No more than the limit may be
@@ -138,7 +169,7 @@ func TestProcessNeverExceedsMaxConcurrentProcessing(t *testing.T) {
 		calls = 6
 	)
 
-	proc := New(Params{MaxInputBytes: 50 << 20, MaxConcurrentProcessing: limit})
+	proc := New(Params{MaxConcurrentProcessing: limit})
 	input := createTestJPEG(t, 50, 50)
 
 	counter := &readingCounter{}
@@ -185,7 +216,7 @@ func TestProcessNeverExceedsMaxConcurrentProcessing(t *testing.T) {
 func TestProcessWaitsThenFailsWhenNoSlotFrees(t *testing.T) {
 	t.Parallel()
 
-	proc := New(Params{MaxInputBytes: 50 << 20, MaxConcurrentProcessing: 1})
+	proc := New(Params{MaxConcurrentProcessing: 1})
 	proc.processingWaitTimeout = 100 * time.Millisecond
 
 	input := createTestJPEG(t, 10, 10)
@@ -206,7 +237,7 @@ func TestProcessWaitsThenFailsWhenNoSlotFrees(t *testing.T) {
 	start := time.Now()
 
 	_, err := proc.Process(context.Background(), bytes.NewReader(input),
-		smallJPEGTransform())
+		smallJPEGRequest())
 	if !errors.Is(err, ErrTooManyImages) {
 		t.Fatalf("Process() error = %v, want ErrTooManyImages", err)
 	}
@@ -232,38 +263,38 @@ func TestProcessReleasesSlotOnError(t *testing.T) {
 
 	valid := createTestJPEG(t, 10, 10)
 
-	unsupported := smallJPEGTransform()
+	unsupported := smallJPEGRequest()
 	unsupported.Format = "bmp"
 
 	cases := []struct {
-		name      string
+		name  string
-		input     io.Reader
+		input io.Reader
-		transform *imagerequest.Transform
+		req   *Request
 		// want is the error Process must return; nil means any error.
 		want error
 	}{
 		{
-			name:      "input cannot be read",
+			name:  "input cannot be read",
-			input:     iotest.ErrReader(errTestReadFailed),
+			input: iotest.ErrReader(errTestReadFailed),
-			transform: smallJPEGTransform(),
+			req:   smallJPEGRequest(),
-			want:      errTestReadFailed,
+			want:  errTestReadFailed,
 		},
 		{
-			name:      "input over the byte limit",
+			name:  "input over the byte limit",
-			input:     bytes.NewReader(createTestJPEG(t, 800, 600)),
+			input: bytes.NewReader(createTestJPEG(t, 800, 600)),
-			transform: smallJPEGTransform(),
+			req:   smallJPEGRequest(),
-			want:      ErrInputDataTooLarge,
+			want:  ErrInputDataTooLarge,
 		},
 		{
-			name:      "input not an image",
+			name:  "input not an image",
-			input:     strings.NewReader("not an image"),
+			input: strings.NewReader("not an image"),
-			transform: smallJPEGTransform(),
+			req:   smallJPEGRequest(),
 		},
 		{
-			name:      "output format not supported",
+			name:  "output format not supported",
-			input:     bytes.NewReader(valid),
+			input: bytes.NewReader(valid),
-			transform: unsupported,
+			req:   unsupported,
-			want:      ErrUnsupportedOutputFormat,
+			want:  ErrUnsupportedOutputFormat,
 		},
 	}
 
@@ -274,7 +305,7 @@ func TestProcessReleasesSlotOnError(t *testing.T) {
 			proc := New(Params{MaxInputBytes: 4096, MaxConcurrentProcessing: 1})
 			proc.processingWaitTimeout = 100 * time.Millisecond
 
-			_, err := proc.Process(context.Background(), tc.input, tc.transform)
+			_, err := proc.Process(context.Background(), tc.input, tc.req)
 			if err == nil || (tc.want != nil && !errors.Is(err, tc.want)) {
 				t.Fatalf("Process() error = %v, want %v", err, tc.want)
 			}
@@ -284,7 +315,7 @@ func TestProcessReleasesSlotOnError(t *testing.T) {
 			}
 
 			result, err := proc.Process(context.Background(), bytes.NewReader(valid),
-				smallJPEGTransform())
+				smallJPEGRequest())
 			if err != nil {
 				t.Fatalf("Process() after the error = %v, want nil", err)
 			}
@@ -301,7 +332,7 @@ func TestProcessReleasesSlotOnError(t *testing.T) {
 func TestWaitForProcessing(t *testing.T) {
 	t.Parallel()
 
-	proc := New(Params{MaxInputBytes: 50 << 20, MaxConcurrentProcessing: 2})
+	proc := New(Params{MaxConcurrentProcessing: 2})
 
 	gate := make(chan struct{})
 	entered := make(chan struct{}, 1)

internal/imageprocessor/orig_format_internal_test.go

@@ -6,7 +6,6 @@ import (
 	"testing"
 
 	"github.com/davidbyttow/govips/v2/vips"
-	"sneak.berlin/go/pixa/internal/imagerequest"
 )
 
 // TestImageProcessor_OrigOfUnnamedFormatRefused verifies that orig of a TIFF
@@ -27,12 +26,8 @@ func TestImageProcessor_OrigOfUnnamedFormatRefused(t *testing.T) {
 		t.Fatalf("failed to save test TIFF: %v", err)
 	}
 
-	result, err := New(Params{
+	result, err := New(Params{}).Process(
-		MaxInputBytes:           50 << 20,
+		t.Context(), bytes.NewReader(tiff), &Request{Format: FormatOriginal},
-		MaxConcurrentProcessing: 1,
-	}).Process(
-		t.Context(), bytes.NewReader(tiff),
-		&imagerequest.Transform{Format: imagerequest.FormatOriginal},
 	)
 	if result != nil {
 		t.Logf("Process() returned %s", result.ContentType)

internal/imageprocessor/source_formats_internal_test.go

@@ -4,8 +4,6 @@ import (
 	"bytes"
 	"io"
 	"testing"
-
-	"sneak.berlin/go/pixa/internal/imagerequest"
 )
 
 // TestImageProcessor_LoadsEachSourceFormat verifies that an image in each of
@@ -14,15 +12,13 @@ import (
 func TestImageProcessor_LoadsEachSourceFormat(t *testing.T) {
 	t.Parallel()
 
-	proc := New(Params{MaxInputBytes: 50 << 20, MaxConcurrentProcessing: 1})
+	proc := New(Params{})
 
-	for _, format := range []imagerequest.Format{
+	for _, format := range []Format{
-		imagerequest.FormatJPEG, imagerequest.FormatPNG, imagerequest.FormatGIF,
+		FormatJPEG, FormatPNG, FormatGIF, FormatWebP, FormatAVIF, FormatJXL,
-		imagerequest.FormatWebP, imagerequest.FormatAVIF, imagerequest.FormatJXL,
 	} {
 		saved, err := proc.Process(t.Context(),
-			bytes.NewReader(createTestPNG(t, 20, 20)),
+			bytes.NewReader(createTestPNG(t, 20, 20)), &Request{Format: format})
-			&imagerequest.Transform{Format: format})
 		if err != nil {
 			t.Fatalf("saving the test image as %s: %v", format, err)
 		}
@@ -33,7 +29,7 @@ func TestImageProcessor_LoadsEachSourceFormat(t *testing.T) {
 		}
 
 		result, err := proc.Process(t.Context(), bytes.NewReader(source),
-			&imagerequest.Transform{Format: imagerequest.FormatOriginal})
+			&Request{Format: FormatOriginal})
 		if err != nil {
 			t.Errorf("orig of the %s image: %v", format, err)
 

internal/imagerequest/imagerequest.go

@@ -1,147 +0,0 @@
-// Package imagerequest holds the image request type, its parts, its checks,
-// the parsing of the /v1/image/ path, the variant key and the source key. It
-// imports no other package of this repo, so every package that handles an
-// image request can import it.
-package imagerequest
-
-import (
-	"errors"
-	"net/url"
-	"time"
-)
-
-// ErrInvalidFitMode is returned when an invalid fit mode is provided.
-var ErrInvalidFitMode = errors.New("invalid fit mode")
-
-// Format represents supported output image formats.
-type Format string
-
-// Supported image output formats.
-const (
-	FormatOriginal Format = "orig"
-	FormatJPEG     Format = "jpeg"
-	FormatPNG      Format = "png"
-	FormatWebP     Format = "webp"
-	FormatAVIF     Format = "avif"
-	FormatJXL      Format = "jxl"
-	FormatGIF      Format = "gif"
-
-	// FormatAuto stands for JPEG XL, AVIF, WebP or JPEG, chosen for each
-	// request from its Accept header once the URL's signature or token has
-	// been checked; it is never processed or cached as itself.
-	FormatAuto Format = "auto"
-)
-
-// Size represents requested image dimensions
-type Size struct {
-	Width  int
-	Height int
-}
-
-// OriginalSize returns true if this represents "keep original size"
-func (s Size) OriginalSize() bool {
-	return s.Width == 0 && s.Height == 0
-}
-
-// Fit represents how to fit image into requested dimensions.
-type Fit string
-
-// Supported image fit modes.
-const (
-	FitCover   Fit = "cover"
-	FitContain Fit = "contain"
-	FitFill    Fit = "fill"
-	FitInside  Fit = "inside"
-	FitOutside Fit = "outside"
-)
-
-// ValidateFitMode checks if the given fit mode is valid.
-// Returns ErrInvalidFitMode for unrecognized fit modes.
-func ValidateFitMode(fit Fit) error {
-	switch fit {
-	case FitCover, FitContain, FitFill, FitInside, FitOutside, "":
-		return nil
-	default:
-		return ErrInvalidFitMode
-	}
-}
-
-// ValidateImageRequest checks a request's width and height with
-// ValidateDimension and its fit mode with ValidateFitMode. Both the plain
-// /v1/image/ route and the encrypted /v1/e/ route validate through this
-// function so a request from either source enforces identical bounds.
-func ValidateImageRequest(req *Request) error {
-	err := ValidateDimension("width", req.Transform.Size.Width)
-	if err != nil {
-		return err
-	}
-
-	err = ValidateDimension("height", req.Transform.Size.Height)
-	if err != nil {
-		return err
-	}
-
-	return ValidateFitMode(req.Transform.FitMode)
-}
-
-// Request represents a request for a processed image: the source to fetch
-// and the transform to apply to it.
-type Request struct {
-	// Source is what to fetch
-	Source Source
-	// Transform is what to do to it
-	Transform Transform
-	// Signature is the HMAC signature for non-allowlisted hosts
-	Signature string
-	// Expires is when the URL expires: the exp of a signed URL, or the expiry
-	// of an encrypted URL; the zero time if it has none
-	Expires time.Time
-	// AllowHTTP indicates whether HTTP (non-TLS) is allowed for this request
-	AllowHTTP bool
-}
-
-// Source is the image a request fetches from the origin.
-type Source struct {
-	// Host is the origin host (e.g., "cdn.example.com")
-	Host string
-	// Path is the path on the origin with its percent-escapes decoded, as
-	// url.URL's Path holds it (e.g., "/photos/my cat.jpg")
-	Path string
-	// Query is the optional query string for the origin URL as the URL
-	// writes it, percent-escapes included, as url.URL's RawQuery holds it
-	Query string
-}
-
-// Transform is what a request does to its source; the image processor
-// takes it alone.
-type Transform struct {
-	// Size is the requested output dimensions
-	Size Size
-	// Format is the requested output format
-	Format Format
-	// Quality is the output quality (1-100) for lossy formats
-	Quality int
-	// FitMode is how to fit the image into requested dimensions
-	FitMode Fit
-}
-
-// SourceURL returns the full upstream URL to fetch: the source path
-// percent-encoded again, as net/url writes a path, so each source path is one
-// upstream path, and the source query as it is, with the characters
-// escapeQuery encodes percent-encoded. Uses http:// scheme when AllowHTTP is
-// true, otherwise https://.
-func (r *Request) SourceURL() string {
-	scheme := "https"
-	if r.AllowHTTP {
-		scheme = "http"
-	}
-
-	sourceURL := url.URL{
-		Scheme:   scheme,
-		Host:     r.Source.Host,
-		Path:     r.Source.Path,
-		RawQuery: escapeQuery(r.Source.Query),
-	}
-
-	return sourceURL.String()
-}

internal/imagerequest/sourcekey.go

@@ -1,26 +0,0 @@
-package imagerequest
-
-import (
-	"crypto/sha256"
-	"encoding/hex"
-	"fmt"
-)
-
-// SourceKey is a SHA256 hash identifying a cached source image (hex-encoded).
-type SourceKey string
-
-// Key returns the key the source is cached under, made as CacheKey makes a
-// variant key.
-// Format: sha256(host:path:query)
-// The path and query go through escapePercentAndColon, so that a ":" in
-// either cannot be taken for the one between them.
-func (s Source) Key() SourceKey {
-	data := fmt.Sprintf("%s:%s:%s",
-		s.Host,
-		escapePercentAndColon(s.Path),
-		escapePercentAndColon(s.Query),
-	)
-	h := sha256.Sum256([]byte(data))
-
-	return SourceKey(hex.EncodeToString(h[:]))
-}

internal/imagerequest/sourcekey_internal_test.go

@@ -1,40 +0,0 @@
-package imagerequest
-
-import "testing"
-
-// TestSourceKey_DiffersForEachSource checks that each source gets a key of
-// 64 hex characters, the same each time, and that no two of these sources
-// share one, also when they differ only by a ":" or "%" in the path or query.
-func TestSourceKey_DiffersForEachSource(t *testing.T) {
-	t.Parallel()
-
-	sources := []Source{
-		{Host: testHostCDN, Path: testPathCat},
-		{Host: testHostCDN, Path: testPathCat, Query: "v=2"},
-		{Host: "other.example.com", Path: testPathCat},
-		{Host: testHostCDN, Path: "/c:d"},
-		{Host: testHostCDN, Path: "/c", Query: "d:"},
-		{Host: testHostCDN, Path: "/c%3Ad"},
-	}
-
-	seen := make(map[SourceKey]Source)
-
-	for _, source := range sources {
-		key := source.Key()
-		t.Logf("Key() of %+v = %s", source, key)
-
-		if len(key) != 64 {
-			t.Errorf("Key() of %+v length = %d, want 64", source, len(key))
-		}
-
-		if again := source.Key(); again != key {
-			t.Errorf("Key() of %+v not deterministic: %s vs %s", source, key, again)
-		}
-
-		if earlier, found := seen[key]; found {
-			t.Errorf("Key() gave %+v and %+v the same key", earlier, source)
-		}
-
-		seen[key] = source
-	}
-}

internal/imagerequest/variantkey.go

@@ -1,39 +0,0 @@
-package imagerequest
-
-import (
-	"crypto/sha256"
-	"encoding/hex"
-	"fmt"
-	"strings"
-)
-
-// VariantKey is a SHA256 hash identifying a specific image variant (hex-encoded).
-type VariantKey string
-
-// CacheKey generates a unique key for a request variant.
-// Format: sha256(host:path:query:width:height:format:quality:fit_mode)
-// The path and query go through escapePercentAndColon, so that a ":" in
-// either cannot be taken for the one between them.
-func CacheKey(req *Request) VariantKey {
-	data := fmt.Sprintf("%s:%s:%s:%d:%d:%s:%d:%s",
-		req.Source.Host,
-		escapePercentAndColon(req.Source.Path),
-		escapePercentAndColon(req.Source.Query),
-		req.Transform.Size.Width,
-		req.Transform.Size.Height,
-		req.Transform.Format,
-		req.Transform.Quality,
-		req.Transform.FitMode,
-	)
-	h := sha256.Sum256([]byte(data))
-
-	return VariantKey(hex.EncodeToString(h[:]))
-}
-
-// escapePercentAndColon returns s with each "%" written as "%25" and each
-// ":" as "%3A", so that the result holds no ":".
-func escapePercentAndColon(s string) string {
-	s = strings.ReplaceAll(s, "%", "%25")
-
-	return strings.ReplaceAll(s, ":", "%3A")
-}

internal/imagerequest/variantkey_internal_test.go

@@ -1,142 +0,0 @@
-package imagerequest
-
-import "testing"
-
-func TestCacheKey(t *testing.T) {
-	t.Parallel()
-
-	req1 := &Request{
-		Source: Source{Host: testHostCDN, Path: testPathCat, Query: ""},
-		Transform: Transform{
-			Size: Size{Width: 800, Height: 600}, Format: FormatWebP,
-			Quality: 85, FitMode: FitCover,
-		},
-	}
-
-	req2 := &Request{
-		Source: Source{Host: testHostCDN, Path: testPathCat, Query: ""},
-		Transform: Transform{
-			Size: Size{Width: 800, Height: 600}, Format: FormatWebP,
-			Quality: 85, FitMode: FitCover,
-		},
-	}
-
-	// Same request should produce same key
-	key1 := CacheKey(req1)
-	key2 := CacheKey(req2)
-
-	if key1 != key2 {
-		t.Errorf("CacheKey() not deterministic: %s vs %s", key1, key2)
-	}
-
-	// Key should be 64 hex chars
-	if len(string(key1)) != 64 {
-		t.Errorf("CacheKey() length = %d, want 64", len(string(key1)))
-	}
-
-	// Different size should produce different key
-	req3 := &Request{
-		Source: Source{Host: testHostCDN, Path: testPathCat, Query: ""},
-		Transform: Transform{
-			Size: Size{Width: 400, Height: 300}, Format: FormatWebP, // Different size
-			Quality: 85, FitMode: FitCover,
-		},
-	}
-
-	key3 := CacheKey(req3)
-	if key1 == key3 {
-		t.Error("CacheKey() produced same key for different sizes")
-	}
-
-	// Different format should produce different key
-	req4 := &Request{
-		Source: Source{Host: testHostCDN, Path: testPathCat, Query: ""},
-		Transform: Transform{
-			Size: Size{Width: 800, Height: 600}, Format: FormatPNG, // Different format
-			Quality: 85, FitMode: FitCover,
-		},
-	}
-
-	key4 := CacheKey(req4)
-	if key1 == key4 {
-		t.Error("CacheKey() produced same key for different formats")
-	}
-
-	// Different quality should produce different key
-	req5 := &Request{
-		Source: Source{Host: testHostCDN, Path: testPathCat, Query: ""},
-		Transform: Transform{
-			Size: Size{Width: 800, Height: 600}, Format: FormatWebP,
-			Quality: 50, FitMode: FitCover, // Different quality
-		},
-	}
-
-	key5 := CacheKey(req5)
-	if key1 == key5 {
-		t.Error("CacheKey() produced same key for different quality")
-	}
-}
-
-// TestCacheKey_ColonOrPercentInPathOrQuery checks that two different source
-// URLs whose path or query holds ":" or "%" get different keys.
-func TestCacheKey_ColonOrPercentInPathOrQuery(t *testing.T) {
-	t.Parallel()
-
-	cases := []struct {
-		name          string
-		path1, query1 string
-		path2, query2 string
-	}{
-		{
-			name:  "colon moved from path to query",
-			path1: "/a:b", query1: "",
-			path2: "/a", query2: "b:",
-		},
-		{
-			name:  "colon in path and its percent-encoding",
-			path1: "/a:b", query1: "",
-			path2: "/a%3Ab", query2: "",
-		},
-	}
-
-	for _, tt := range cases {
-		t.Run(tt.name, func(t *testing.T) {
-			t.Parallel()
-
-			key1 := CacheKey(&Request{
-				Source: Source{
-					Host:  testHostCDN,
-					Path:  tt.path1,
-					Query: tt.query1,
-				},
-				Transform: Transform{
-					Size:    Size{Width: 800, Height: 600},
-					Format:  FormatWebP,
-					Quality: 85,
-					FitMode: FitCover,
-				},
-			})
-			key2 := CacheKey(&Request{
-				Source: Source{
-					Host:  testHostCDN,
-					Path:  tt.path2,
-					Query: tt.query2,
-				},
-				Transform: Transform{
-					Size:    Size{Width: 800, Height: 600},
-					Format:  FormatWebP,
-					Quality: 85,
-					FitMode: FitCover,
-				},
-			})
-
-			t.Logf("CacheKey() of path %q query %q = %s", tt.path1, tt.query1, key1)
-			t.Logf("CacheKey() of path %q query %q = %s", tt.path2, tt.query2, key2)
-
-			if key1 == key2 {
-				t.Errorf("CacheKey() gave path %q query %q and path %q query %q "+
-					"the same key", tt.path1, tt.query1, tt.path2, tt.query2)
-			}
-		})
-	}
-}

internal/imgcache/cache.go

@@ -2,23 +2,35 @@ package imgcache
 
 import (
 	"context"
+	"crypto/sha256"
 	"database/sql"
+	"encoding/hex"
+	"encoding/json"
 	"errors"
 	"fmt"
 	"io"
 	"log/slog"
 	"path/filepath"
+	"sync"
+	"sync/atomic"
 	"time"
 
-	"github.com/prometheus/client_golang/prometheus"
+	lru "github.com/hashicorp/golang-lru/v2"
-	"sneak.berlin/go/pixa/internal/imagerequest"
+	"sneak.berlin/go/pixa/internal/httpfetcher"
 )
 
-// maxPendingAccessTimes is how many access times of variants served from
+// Cache errors.
-// the cache, and how many of cached sources a miss used, may each wait to be
+var (
-// written, at about 80 bytes each. An access time handed over while that
+	ErrCacheMiss     = errors.New("cache miss")
-// many of its kind wait is dropped.
+	ErrNegativeCache = errors.New("negative cache hit")
-const maxPendingAccessTimes = 10000
+)
+
+// HTTP status code for successful fetch.
+const httpStatusOK = 200
+
+// metaCacheSize is how many variants' content types metaCache holds. A
+// variant not among them is served as before, reading its .meta file.
+const metaCacheSize = 10000
 
 // cleanExpiredBatchSize is the most expired negative cache rows one
 // statement of CleanExpired deletes. Each batch is a statement of its
@@ -32,12 +44,23 @@ type CacheConfig struct {
 	NegativeTTL time.Duration
 
 	// MaxBytes is the disk cache size limit in bytes that eviction
-	// enforces. Zero turns the disk cache off entirely: no cache
+	// enforces. Zero means no limit is enforced (no eviction).
-	// directories are created, lookups always miss, stores are no-ops,
-	// and the eviction goroutine only removes the expired negative cache
-	// rows.
 	MaxBytes int64
 
+	// UseDefaultMaxBytes makes NewCache replace MaxBytes with the
+	// default limit: 75% of the sum of the space free on the filesystem
+	// holding the cache and the bytes the cache already holds, at least
+	// DefaultCacheMaxBytesFloor. The config layer sets this when the
+	// operator omits cache_max_bytes.
+	UseDefaultMaxBytes bool
+
+	// DisableDiskCache turns the disk cache off entirely: no cache
+	// directories are created, lookups always miss, stores are
+	// no-ops, and the eviction goroutine only removes the expired
+	// negative cache rows. The config layer sets this when the
+	// operator configures cache_max_bytes: 0.
+	DisableDiskCache bool
+
 	// Logger receives accounting and eviction log output. A nil
 	// Logger means slog.Default().
 	Logger *slog.Logger
@@ -45,11 +68,16 @@ type CacheConfig struct {
 
 // Cache implements the caching layer for the image proxy.
 type Cache struct {
-	db         *sql.DB
+	db          *sql.DB
-	srcContent *ContentStorage // source images by source key
+	srcContent  *ContentStorage  // source images by content hash
-	variants   *VariantStorage // processed variants by cache key
+	variants    *VariantStorage  // processed variants by cache key
-	config     CacheConfig
+	srcMetadata *MetadataStorage // source metadata by host/path
-	log        *slog.Logger
+	config      CacheConfig
+	log         *slog.Logger
+
+	// disabled means the disk cache is turned off entirely: lookups
+	// always miss, stores are no-ops, and no eviction runs.
+	disabled bool
 
 	// Eviction machinery. The channels are created in NewCache so
 	// stores can signal write pressure without racing StartEviction.
@@ -59,30 +87,47 @@ type Cache struct {
 	evictionDone     chan struct{}
 	evictionCancel   context.CancelFunc
 
-	// pendingVariantAccessTimes holds the variants served from the cache,
+	// The pending counts: hits, misses, upstream fetches and transforms
-	// and pendingSourceAccessTimes the cached sources a miss used, whose
+	// whose write to the database missed its request's deadline, kept
-	// access time is still to be written by the goroutine that
+	// here until they are written by the goroutine that
-	// StartPendingAccessTimeWrites starts, so that no request waits for the
+	// StartPendingCountWrites starts. As for eviction, the channels are
-	// database to record it. As for eviction, the channels are created in
+	// created in NewCache: pendingCountsAdded wakes that goroutine, and
-	// NewCache, so that requests can hand over access times before that
+	// pendingCountsDone is closed when it returns. pendingCountsCancel,
-	// goroutine starts; pendingAccessTimesDone is closed when it returns.
+	// set by StartPendingCountWrites, cancels its context, which tells it
-	// pendingAccessTimesCancel, set by StartPendingAccessTimeWrites,
+	// to finish.
-	// cancels its context, which tells it to finish.
+	pendingHits               atomic.Int64
-	pendingVariantAccessTimes chan imagerequest.VariantKey
+	pendingMisses             atomic.Int64
-	pendingSourceAccessTimes  chan imagerequest.SourceKey
+	pendingUpstreamFetches    atomic.Int64
-	pendingAccessTimesDone    chan struct{}
+	pendingUpstreamFetchBytes atomic.Int64
-	pendingAccessTimesCancel  context.CancelFunc
+	pendingTransforms         atomic.Int64
+	pendingCountsAdded        chan struct{}
+	pendingCountsDone         chan struct{}
+	pendingCountsCancel       context.CancelFunc
 
-	// The counts of what the cache does, made and registered by
+	// Held through each write of the pending counts, and by
-	// registerCounters (see counters.go)
+	// readHitAndMissCounts to read them
-	cacheHits          prometheus.Counter
+	pendingCountsWriteMutex sync.Mutex
-	cacheMisses        prometheus.Counter
+
-	upstreamFetches    prometheus.Counter
+	// metaCache holds the content types of the variants most recently
-	upstreamFetchBytes prometheus.Counter
+	// stored or served, so a hit does not read the variant's .meta file.
-	transforms         prometheus.Counter
+	// It never stands in for the variant file, which is always opened.
+	metaCache *lru.Cache[VariantKey, string]
+
+	// contentLocks serializes StoreSource and evictSourceBlob per
+	// content hash, closing the race window between an eviction's row
+	// deletion and its file unlink against a concurrent store of
+	// identical content.
+	contentLocks *contentLock
+
+	// evictSourceBlobTestHook, when set, is invoked by evictSourceBlob
+	// after its row-deletion transaction commits and before the
+	// content file is unlinked. It exists solely so tests can
+	// deterministically pause inside that window to exercise
+	// concurrent stores against it; production code leaves it nil.
+	evictSourceBlobTestHook func(ContentHash)
 
 	// reconciliationPageSize is the most rows one read of a content table
-	// returns in the reconciliation pass. NewCache sets it to
+	// returns in the reconciliation pass and in Stats. newCache sets it to
 	// defaultReconciliationPageSize; tests set it smaller.
 	reconciliationPageSize int
 
@@ -93,37 +138,43 @@ type Cache struct {
 	reconciliationReadTestHook func(rows int)
 }
 
-// NewCache creates a new cache instance and registers its counters on
+// NewCache creates a new cache instance.
-// metricsRegistry. pixad passes Prometheus' default registry, the one
+func NewCache(db *sql.DB, config CacheConfig) (*Cache, error) {
-// /metrics serves. It makes no database call.
+	return newCache(db, config, defaultFreeSpaceProbe)
-func NewCache(
+}
-	db *sql.DB, config CacheConfig, metricsRegistry prometheus.Registerer,
+
+// newCache is NewCache with the free-space probe passed in, so tests
+// can fake the free space the default limit is worked out from.
+func newCache(
+	db *sql.DB, config CacheConfig, probe FreeSpaceProbeFunc,
 ) (*Cache, error) {
 	log := config.Logger
 	if log == nil {
 		log = slog.Default()
 	}
 
+	metaCache, err := lru.New[VariantKey, string](metaCacheSize)
+	if err != nil {
+		return nil, fmt.Errorf("failed to create variant content type cache: %w", err)
+	}
+
 	c := &Cache{
 		db:               db,
 		config:           config,
 		log:              log,
+		disabled:         config.DisableDiskCache,
 		evictionPressure: make(chan struct{}, 1),
 		evictionDone:     make(chan struct{}),
+		metaCache:        metaCache,
+		contentLocks:     newContentLock(),
 
-		pendingVariantAccessTimes: make(chan imagerequest.VariantKey, maxPendingAccessTimes),
+		pendingCountsAdded: make(chan struct{}, 1),
-		pendingSourceAccessTimes:  make(chan imagerequest.SourceKey, maxPendingAccessTimes),
+		pendingCountsDone:  make(chan struct{}),
-		pendingAccessTimesDone:    make(chan struct{}),
 
 		reconciliationPageSize: defaultReconciliationPageSize,
 	}
 
-	err := c.registerCounters(metricsRegistry)
+	if c.disabled {
-	if err != nil {
-		return nil, err
-	}
-
-	if config.MaxBytes == 0 {
 		return c, nil
 	}
 
@@ -135,80 +186,180 @@ func NewCache(
 	}
 
 	variants, err := NewVariantStorage(
-		filepath.Join(config.StateDir, "cache", "variants"),
+		filepath.Join(config.StateDir, "cache", "variants"), log,
 	)
 	if err != nil {
 		return nil, fmt.Errorf("failed to create variant storage: %w", err)
 	}
 
+	srcMetadata, err := NewMetadataStorage(
+		filepath.Join(config.StateDir, "cache", "metadata"),
+	)
+	if err != nil {
+		return nil, fmt.Errorf("failed to create source metadata storage: %w", err)
+	}
+
 	c.srcContent = srcContent
 	c.variants = variants
+	c.srcMetadata = srcMetadata
+
+	if config.UseDefaultMaxBytes {
+		limit, err := c.computeDefaultMaxBytes(context.Background(), probe)
+		if err != nil {
+			return nil, err
+		}
+
+		c.config.MaxBytes = limit
+
+		log.Info("computed default cache size limit from free space and cache contents",
+			"cache_max_bytes", limit,
+			"cache_dir", filepath.Join(config.StateDir, "cache"),
+		)
+	}
 
 	return c, nil
 }
 
-// GetVariant opens a cached variant and returns a reader, its size and its
+// LookupResult contains the result of a cache lookup.
-// content type, read from the variant file's first bytes. It opens that one
+type LookupResult struct {
-// file and makes no database call. A variant not in the cache, or any
+	Hit         bool
-// variant of a disabled cache, is ErrNotFound; a variant file whose first
+	CacheKey    VariantKey
-// bytes are not those of an output format is another error.
+	ContentType string
-func (c *Cache) GetVariant(
+	SizeBytes   int64
-	cacheKey imagerequest.VariantKey,
+	CacheStatus CacheStatus
-) (io.ReadCloser, int64, string, error) {
+}
-	if c.config.MaxBytes == 0 {
+
+// Lookup checks if a processed variant exists on disk. Hits touch the
+// variant's LRU timestamp; a disabled cache always misses.
+func (c *Cache) Lookup(ctx context.Context, req *ImageRequest) (*LookupResult, error) {
+	cacheKey := CacheKey(req)
+
+	// Check variant storage directly - no DB needed for cache hits
+	if !c.disabled && c.variants.Exists(cacheKey) {
+		c.touchVariant(ctx, cacheKey)
+
+		return &LookupResult{
+			Hit:         true,
+			CacheKey:    cacheKey,
+			CacheStatus: CacheHit,
+		}, nil
+	}
+
+	return &LookupResult{
+		Hit:         false,
+		CacheKey:    cacheKey,
+		CacheStatus: CacheMiss,
+	}, nil
+}
+
+// GetVariant returns a reader, size, and content type for a cached
+// variant. The content type comes from metaCache, or else from the
+// variant's .meta file and is then kept in metaCache. A variant with
+// no .meta file is served as application/octet-stream, which is not
+// kept.
+func (c *Cache) GetVariant(cacheKey VariantKey) (io.ReadCloser, int64, string, error) {
+	if c.disabled {
 		return nil, 0, "", ErrNotFound
 	}
 
-	return c.variants.LoadWithContentType(cacheKey)
+	contentType, known := c.metaCache.Get(cacheKey)
+	if !known {
+		return c.loadVariantWithMeta(cacheKey)
+	}
+
+	reader, size, err := c.variants.LoadWithSize(cacheKey)
+	if err != nil {
+		// The file is gone, e.g. deleted outside pixa
+		c.metaCache.Remove(cacheKey)
+
+		return nil, 0, "", err
+	}
+
+	return reader, size, contentType, nil
 }
 
-// StoreSource stores fetched source content: it writes the file named by
+// StoreSource stores fetched source content and metadata. On a
-// the source's key, then the source's row. When the row cannot be written
+// disabled cache it is a no-op returning an empty hash.
-// the file is removed and the store fails, as a file with no row is never
-// served or evicted; if that removal fails too, the next reconciliation
-// pass removes the file. On a disabled cache it is a no-op returning an
-// empty key.
 func (c *Cache) StoreSource(
 	ctx context.Context,
-	req *imagerequest.Request,
+	req *ImageRequest,
 	content io.Reader,
-) (imagerequest.SourceKey, error) {
+	result *httpfetcher.FetchResult,
-	if c.config.MaxBytes == 0 {
+) (ContentHash, error) {
+	if c.disabled {
 		return "", nil
 	}
 
+	// Hash the content ourselves (rather than via srcContent.Store,
+	// which would hash internally) so the content hash is known before
+	// any file or database work happens: that lets the entire store be
+	// serialized, per hash, against a concurrent eviction of the same
+	// content below.
 	data, err := io.ReadAll(content)
 	if err != nil {
 		return "", fmt.Errorf("failed to read source content: %w", err)
 	}
 
-	key := req.Source.Key()
+	sum := sha256.Sum256(data)
+	contentHash := ContentHash(hex.EncodeToString(sum[:]))
 
-	size, err := c.srcContent.Store(key, data)
+	// Hold the content hash's lock for the whole store operation. A
+	// concurrent eviction of this exact hash (the real SHA-256 dedup
+	// case: a different source path whose bytes hash identically)
+	// deletes the accounting rows and unlinks the file inside the same
+	// lock, so the two can never interleave: either this store
+	// completes first (and a subsequent eviction removes it together
+	// with its rows and file, correctly), or eviction completes first
+	// (and this store finds the file already gone and recreates it
+	// fresh) — never a fresh row left pointing at a file eviction is
+	// mid-unlink on.
+	unlock := c.contentLocks.Lock(string(contentHash))
+	defer unlock()
+
+	size, err := c.srcContent.StoreHashed(contentHash, data)
 	if err != nil {
 		return "", fmt.Errorf("failed to store source content: %w", err)
 	}
 
-	_, err = c.db.ExecContext(ctx, `
+	// Store in database
-		INSERT INTO source_content (source_key, size_bytes)
+	pathHash := HashPath(req.SourcePath + "?" + req.SourceQuery)
-		VALUES (?, ?)
-		ON CONFLICT(source_key) DO UPDATE SET
-			size_bytes = excluded.size_bytes,
-			last_accessed_at = CURRENT_TIMESTAMP
-	`, string(key), size)
-	if err != nil {
-		deleteErr := c.srcContent.Delete(key)
-		if deleteErr != nil {
-			c.log.Warn("failed to remove source file whose row was not written",
-				"source_key", key, "error", deleteErr)
-		}
 
+	headersJSON, err := json.Marshal(result.Headers)
+	if err != nil {
+		return "", fmt.Errorf("failed to marshal response headers: %w", err)
+	}
+
+	_, err = c.db.ExecContext(ctx, `
+		INSERT INTO source_content (content_hash, content_type, size_bytes)
+		VALUES (?, ?, ?)
+		ON CONFLICT(content_hash) DO NOTHING
+	`, contentHash, result.ContentType, size)
+	if err != nil {
 		return "", fmt.Errorf("failed to insert source content: %w", err)
 	}
 
+	_, err = c.db.ExecContext(ctx, `
+		INSERT INTO source_metadata
+			(source_host, source_path, source_query, path_hash,
+			 content_hash, status_code, content_type, response_headers)
+		VALUES (?, ?, ?, ?, ?, ?, ?, ?)
+		ON CONFLICT(source_host, source_path, source_query) DO UPDATE SET
+			content_hash = excluded.content_hash,
+			status_code = excluded.status_code,
+			content_type = excluded.content_type,
+			response_headers = excluded.response_headers,
+			fetched_at = CURRENT_TIMESTAMP
+	`, req.SourceHost, req.SourcePath, req.SourceQuery, pathHash,
+		contentHash, httpStatusOK, result.ContentType, string(headersJSON))
+	if err != nil {
+		return "", fmt.Errorf("failed to insert source metadata: %w", err)
+	}
+
+	c.writeMetadataSidecar(req, pathHash, contentHash, result)
+
 	c.notifyWritePressure()
 
-	return key, nil
+	return contentHash, nil
 }
 
 // StoreVariant stores a processed variant by its cache key and records
@@ -216,24 +367,27 @@ func (c *Cache) StoreSource(
 // accounting insert is best-effort (the startup reconciliation pass
 // adopts any variant file that misses its accounting row).
 func (c *Cache) StoreVariant(
-	ctx context.Context, cacheKey imagerequest.VariantKey, content io.Reader,
+	ctx context.Context, cacheKey VariantKey, content io.Reader, contentType string,
 ) error {
-	if c.config.MaxBytes == 0 {
+	if c.disabled {
 		return nil
 	}
 
-	size, err := c.variants.Store(cacheKey, content)
+	size, err := c.variants.Store(cacheKey, content, contentType)
 	if err != nil {
 		return err
 	}
 
+	c.metaCache.Add(cacheKey, contentType)
+
 	_, err = c.db.ExecContext(ctx, `
-		INSERT INTO variant_content (cache_key, size_bytes)
+		INSERT INTO variant_content (cache_key, size_bytes, content_type)
-		VALUES (?, ?)
+		VALUES (?, ?, ?)
 		ON CONFLICT(cache_key) DO UPDATE SET
 			size_bytes = excluded.size_bytes,
+			content_type = excluded.content_type,
 			last_accessed_at = CURRENT_TIMESTAMP
-	`, string(cacheKey), size)
+	`, string(cacheKey), size, contentType)
 	if err != nil {
 		c.log.Warn("failed to record variant in size accounting",
 			"cache_key", cacheKey, "error", err)
@@ -245,53 +399,60 @@ func (c *Cache) StoreVariant(
 }
 
 // LookupSource checks if we have cached source content for a request.
-// Returns the source key if found, or an empty key if not; a row whose
+// Returns the content hash and content type if found, or empty values
-// file is missing is not found. A source found has its access time
+// if not. Hits touch the blob's LRU timestamp; a disabled cache always
-// handed to the background writer without waiting (see
+// reports no cached source.
-// touchSourceContent); a disabled cache always reports no cached source.
 func (c *Cache) LookupSource(
-	ctx context.Context, req *imagerequest.Request,
+	ctx context.Context, req *ImageRequest,
-) (imagerequest.SourceKey, error) {
+) (ContentHash, string, error) {
-	if c.config.MaxBytes == 0 {
+	if c.disabled {
-		return "", nil
+		return "", "", nil
 	}
 
-	key := req.Source.Key()
+	var hashStr, contentType string
-
-	var rowExists bool
 
 	err := c.db.QueryRowContext(ctx, `
-		SELECT EXISTS(SELECT 1 FROM source_content WHERE source_key = ?)
+		SELECT content_hash, content_type FROM source_metadata
-	`, string(key)).Scan(&rowExists)
+		WHERE source_host = ? AND source_path = ? AND source_query = ?
-	if err != nil {
+	`, req.SourceHost, req.SourcePath, req.SourceQuery).Scan(&hashStr, &contentType)
-		return "", fmt.Errorf("failed to lookup source: %w", err)
+
+	if errors.Is(err, sql.ErrNoRows) {
+		return "", "", nil
 	}
 
-	if !rowExists {
+	if err != nil {
-		return "", nil
+		return "", "", fmt.Errorf("failed to lookup source: %w", err)
 	}
 
+	contentHash := ContentHash(hashStr)
+
 	// Verify the content file exists
-	if !c.srcContent.Exists(key) {
+	if !c.srcContent.Exists(contentHash) {
-		return "", nil
+		return "", "", nil
 	}
 
-	c.touchSourceContent(key)
+	c.touchSourceContent(ctx, contentHash)
 
-	return key, nil
+	return contentHash, contentType, nil
 }
 
 // StoreNegative stores a negative cache entry for a failed fetch.
-func (c *Cache) StoreNegative(ctx context.Context, req *imagerequest.Request) error {
+func (c *Cache) StoreNegative(
+	ctx context.Context, req *ImageRequest, statusCode int, errMsg string,
+) error {
 	expiresAt := time.Now().UTC().Add(c.config.NegativeTTL)
 
 	_, err := c.db.ExecContext(ctx, `
 		INSERT INTO negative_cache
-			(source_host, source_path, source_query, expires_at)
+			(source_host, source_path, source_query, status_code,
-		VALUES (?, ?, ?, ?)
+			 error_message, expires_at)
+		VALUES (?, ?, ?, ?, ?, ?)
 		ON CONFLICT(source_host, source_path, source_query) DO UPDATE SET
+			status_code = excluded.status_code,
+			error_message = excluded.error_message,
+			fetched_at = CURRENT_TIMESTAMP,
 			expires_at = excluded.expires_at
-	`, req.Source.Host, req.Source.Path, req.Source.Query, expiresAt)
+	`, req.SourceHost, req.SourcePath, req.SourceQuery, statusCode, errMsg, expiresAt)
 	if err != nil {
 		return fmt.Errorf("failed to insert negative cache: %w", err)
 	}
@@ -299,16 +460,33 @@ func (c *Cache) StoreNegative(ctx context.Context, req *imagerequest.Request) er
 	return nil
 }
 
-// GetSourceContent returns a reader for cached source content by its key,
+// GetSourceMetadataID returns the source metadata ID for a request.
+func (c *Cache) GetSourceMetadataID(
+	ctx context.Context, req *ImageRequest,
+) (int64, error) {
+	var id int64
+
+	err := c.db.QueryRowContext(ctx, `
+		SELECT id FROM source_metadata
+		WHERE source_host = ? AND source_path = ? AND source_query = ?
+	`, req.SourceHost, req.SourcePath, req.SourceQuery).Scan(&id)
+	if err != nil {
+		return 0, fmt.Errorf("failed to get source metadata ID: %w", err)
+	}
+
+	return id, nil
+}
+
+// GetSourceContent returns a reader for cached source content by its hash,
 // and the content's size in bytes.
 func (c *Cache) GetSourceContent(
-	key imagerequest.SourceKey,
+	contentHash ContentHash,
 ) (io.ReadCloser, int64, error) {
-	if c.config.MaxBytes == 0 {
+	if c.disabled {
 		return nil, 0, ErrNotFound
 	}
 
-	return c.srcContent.LoadWithSize(key)
+	return c.srcContent.LoadWithSize(contentHash)
 }
 
 // CleanExpired removes the negative cache rows past their expiry, one
@@ -334,72 +512,241 @@ func (c *Cache) CleanExpired(ctx context.Context) error {
 	}
 }
 
-// IncrementStats counts a cache hit or miss, and an upstream fetch that read
+// Stats returns cache statistics.
-// fetchBytes bytes, as IncrementUpstreamFetch does. Like the other Increment
+func (c *Cache) Stats(ctx context.Context) (*CacheStats, error) {
-// methods, it only adds to the cache's Prometheus counters in memory (see
+	var stats CacheStats
-// counters.go), so it never waits for the database or fails.
+
-func (c *Cache) IncrementStats(hit bool, fetchBytes int64) {
+	err := c.readHitAndMissCounts(ctx, &stats)
-	if hit {
+	if err != nil && !errors.Is(err, sql.ErrNoRows) {
-		c.cacheHits.Inc()
+		return nil, fmt.Errorf("failed to get cache stats: %w", err)
-	} else {
-		c.cacheMisses.Inc()
 	}
 
-	c.IncrementUpstreamFetch(fetchBytes)
+	// Count and size the cached source images and processed variants from
+	// their tables. A disabled cache holds none, whatever rows an earlier
+	// run left.
+	if !c.disabled {
+		err = c.db.QueryRowContext(ctx, `
+			SELECT (SELECT COUNT(*) FROM source_content)
+			     + (SELECT COUNT(*) FROM variant_content)
+		`).Scan(&stats.TotalItems)
+		if err != nil {
+			c.log.Warn("failed to count cache items for stats", "error", err)
+		}
+
+		stats.TotalSizeBytes, err = c.sumContentSizeBytes(ctx)
+		if err != nil {
+			c.log.Warn("failed to sum cache size for stats", "error", err)
+		}
+	}
+
+	// Compute hit rate as a ratio
+	if stats.HitCount+stats.MissCount > 0 {
+		stats.HitRate = float64(stats.HitCount) / float64(stats.HitCount+stats.MissCount)
+	}
+
+	return &stats, nil
+}
+
+// IncrementStats counts a cache hit or miss, and an upstream fetch that read
+// fetchBytes bytes, as IncrementUpstreamFetch does. Like the other Increment
+// methods, it writes to the database with ctx's deadline but not its
+// cancellation, so an ended request is still counted but does not wait for
+// the database past its deadline; a count not written by then becomes a
+// pending count (see StartPendingCountWrites).
+func (c *Cache) IncrementStats(ctx context.Context, hit bool, fetchBytes int64) {
+	countCtx, cancel := withoutCancelKeepingDeadline(ctx)
+	defer cancel()
+
+	var err error
+
+	pendingCount := &c.pendingMisses
+
+	if hit {
+		pendingCount = &c.pendingHits
+
+		_, err = c.db.ExecContext(countCtx, `
+			UPDATE cache_stats
+			SET hit_count = hit_count + 1,
+			    last_updated_at = CURRENT_TIMESTAMP
+			WHERE id = 1
+		`)
+	} else {
+		_, err = c.db.ExecContext(countCtx, `
+			UPDATE cache_stats
+			SET miss_count = miss_count + 1,
+			    last_updated_at = CURRENT_TIMESTAMP
+			WHERE id = 1
+		`)
+	}
+
+	switch {
+	case errors.Is(err, context.DeadlineExceeded):
+		c.addPendingCount(pendingCount, 1)
+	case err != nil:
+		c.log.Warn("failed to count cache hit or miss", "hit", hit, "error", err)
+	}
+
+	c.IncrementUpstreamFetch(ctx, fetchBytes)
 }
 
 // IncrementUpstreamFetch counts one upstream fetch that read fetchBytes bytes.
 // A fetch that read no bytes is not counted.
-func (c *Cache) IncrementUpstreamFetch(fetchBytes int64) {
+func (c *Cache) IncrementUpstreamFetch(ctx context.Context, fetchBytes int64) {
 	if fetchBytes <= 0 {
 		return
 	}
 
-	c.upstreamFetches.Inc()
+	countCtx, cancel := withoutCancelKeepingDeadline(ctx)
-	c.upstreamFetchBytes.Add(float64(fetchBytes))
+	defer cancel()
+
+	_, err := c.db.ExecContext(countCtx, `
+		UPDATE cache_stats
+		SET upstream_fetch_count = upstream_fetch_count + 1,
+		    upstream_fetch_bytes = upstream_fetch_bytes + ?,
+		    last_updated_at = CURRENT_TIMESTAMP
+		WHERE id = 1
+	`, fetchBytes)
+
+	switch {
+	case errors.Is(err, context.DeadlineExceeded):
+		c.addPendingCount(&c.pendingUpstreamFetches, 1)
+		c.addPendingCount(&c.pendingUpstreamFetchBytes, fetchBytes)
+	case err != nil:
+		c.log.Warn("failed to count upstream fetch",
+			"fetch_bytes", fetchBytes, "error", err)
+	}
 }
 
 // IncrementTransformCount counts one image transcoded by the image processor.
-func (c *Cache) IncrementTransformCount() {
+func (c *Cache) IncrementTransformCount(ctx context.Context) {
-	c.transforms.Inc()
+	countCtx, cancel := withoutCancelKeepingDeadline(ctx)
-}
+	defer cancel()
 
-// touchVariant hands the access time of a variant served from the cache to
+	_, err := c.db.ExecContext(countCtx, `
-// the goroutine StartPendingAccessTimeWrites starts, which writes it in its
+		UPDATE cache_stats
-// next batch. It never waits: while maxPendingAccessTimes access times of
+		SET transform_count = transform_count + 1,
-// variants wait to be written, this one is dropped, and the variant only
+		    last_updated_at = CURRENT_TIMESTAMP
-// looks colder to eviction.
+		WHERE id = 1
-func (c *Cache) touchVariant(cacheKey imagerequest.VariantKey) {
+	`)
-	select {
+
-	case c.pendingVariantAccessTimes <- cacheKey:
+	switch {
-	default:
+	case errors.Is(err, context.DeadlineExceeded):
+		c.addPendingCount(&c.pendingTransforms, 1)
+	case err != nil:
+		c.log.Warn("failed to count transform", "error", err)
 	}
 }
 
-// touchSourceContent hands the access time of a cached source a miss used to
+// readHitAndMissCounts sets the hit and miss counts of stats to those of the
-// the goroutine StartPendingAccessTimeWrites starts, which writes it in its
+// cache_stats row plus the pending hits and misses (see
-// next batch. It never waits: while maxPendingAccessTimes access times of
+// StartPendingCountWrites). It holds pendingCountsWriteMutex, so that no
-// sources wait to be written, this one is dropped, and the source only looks
+// write of the pending counts falls between the two reads.
-// colder to eviction.
+func (c *Cache) readHitAndMissCounts(ctx context.Context, stats *CacheStats) error {
-func (c *Cache) touchSourceContent(key imagerequest.SourceKey) {
+	c.pendingCountsWriteMutex.Lock()
-	select {
+	defer c.pendingCountsWriteMutex.Unlock()
-	case c.pendingSourceAccessTimes <- key:
+
-	default:
+	err := c.db.QueryRowContext(ctx, `
+		SELECT hit_count, miss_count
+		FROM cache_stats WHERE id = 1
+	`).Scan(&stats.HitCount, &stats.MissCount)
+
+	stats.HitCount += c.pendingHits.Load()
+	stats.MissCount += c.pendingMisses.Load()
+
+	return err
+}
+
+// loadVariantWithMeta is GetVariant for a variant metaCache does not
+// hold: it reads the content type from the variant's .meta file and
+// keeps it in metaCache, unless a StoreVariant has put one there
+// meanwhile, as the store's is newer. A read that finds no .meta file,
+// as one can when the store's .meta write failed or an eviction removed
+// the file after the read opened the variant, serves
+// application/octet-stream and keeps nothing, so metaCache only ever
+// holds a type read from a .meta file or passed to StoreVariant.
+func (c *Cache) loadVariantWithMeta(
+	cacheKey VariantKey,
+) (io.ReadCloser, int64, string, error) {
+	reader, size, contentType, err := c.variants.LoadWithMeta(cacheKey)
+	if err != nil {
+		return nil, 0, "", err
+	}
+
+	if contentType == "" {
+		return reader, size, fallbackContentType, nil
+	}
+
+	c.metaCache.ContainsOrAdd(cacheKey, contentType)
+
+	return reader, size, contentType, nil
+}
+
+// writeMetadataSidecar writes the JSON metadata sidecar of a stored source.
+// A failure is logged and is otherwise non-fatal; the metadata is in the
+// database.
+func (c *Cache) writeMetadataSidecar(
+	req *ImageRequest,
+	pathHash PathHash,
+	contentHash ContentHash,
+	result *httpfetcher.FetchResult,
+) {
+	meta := &SourceMetadata{
+		Host:            req.SourceHost,
+		Path:            req.SourcePath,
+		Query:           req.SourceQuery,
+		ContentHash:     string(contentHash),
+		StatusCode:      result.StatusCode,
+		ContentType:     result.ContentType,
+		ContentLength:   result.ContentLength,
+		ResponseHeaders: result.Headers,
+		FetchedAt:       time.Now().UTC().Unix(),
+		FetchDurationMs: result.FetchDurationMs,
+		RemoteAddr:      result.RemoteAddr,
+	}
+
+	err := c.srcMetadata.Store(req.SourceHost, pathHash, meta)
+	if err != nil {
+		c.log.Warn("failed to write metadata sidecar",
+			"host", req.SourceHost, "path_hash", pathHash, "error", err)
 	}
 }
 
-// checkNegativeCache checks if a request is in the negative cache. It only
+// touchVariant updates the LRU timestamp of a variant, best-effort:
-// reads: a row past its expiry is not a hit, and the eviction goroutine
+// a failed touch only makes the entry look colder to eviction.
-// deletes it with the other expired rows (see CleanExpired).
+func (c *Cache) touchVariant(ctx context.Context, cacheKey VariantKey) {
+	_, err := c.db.ExecContext(ctx, `
+		UPDATE variant_content SET last_accessed_at = CURRENT_TIMESTAMP
+		WHERE cache_key = ?
+	`, string(cacheKey))
+	if err != nil {
+		c.log.Debug("failed to touch variant LRU timestamp",
+			"cache_key", cacheKey, "error", err)
+	}
+}
+
+// touchSourceContent updates the LRU timestamp of a source content
+// blob, best-effort: a failed touch only makes the blob look colder.
+func (c *Cache) touchSourceContent(ctx context.Context, contentHash ContentHash) {
+	_, err := c.db.ExecContext(ctx, `
+		UPDATE source_content SET last_accessed_at = CURRENT_TIMESTAMP
+		WHERE content_hash = ?
+	`, string(contentHash))
+	if err != nil {
+		c.log.Debug("failed to touch source content LRU timestamp",
+			"content_hash", contentHash, "error", err)
+	}
+}
+
+// checkNegativeCache checks if a request is in the negative cache.
 func (c *Cache) checkNegativeCache(
-	ctx context.Context, req *imagerequest.Request,
+	ctx context.Context, req *ImageRequest,
 ) (bool, error) {
 	var expiresAt time.Time
 
 	err := c.db.QueryRowContext(ctx, `
 		SELECT expires_at FROM negative_cache
 		WHERE source_host = ? AND source_path = ? AND source_query = ?
-	`, req.Source.Host, req.Source.Path, req.Source.Query).Scan(&expiresAt)
+	`, req.SourceHost, req.SourcePath, req.SourceQuery).Scan(&expiresAt)
 
 	if errors.Is(err, sql.ErrNoRows) {
 		return false, nil
@@ -409,9 +756,22 @@ func (c *Cache) checkNegativeCache(
 		return false, fmt.Errorf("failed to check negative cache: %w", err)
 	}
 
-	expired := time.Now().After(expiresAt)
+	// Check if expired
+	if time.Now().After(expiresAt) {
+		// Clean up expired entry
+		_, err = c.db.ExecContext(ctx, `
+			DELETE FROM negative_cache
+			WHERE source_host = ? AND source_path = ? AND source_query = ?
+		`, req.SourceHost, req.SourcePath, req.SourceQuery)
+		if err != nil {
+			c.log.Warn("failed to delete expired negative cache entry",
+				"host", req.SourceHost, "path", req.SourcePath, "error", err)
+		}
 
-	return !expired, nil
+		return false, nil
+	}
+
+	return true, nil
 }
 
 // cleanExpiredBatch deletes up to cleanExpiredBatchSize negative cache

internal/imgcache/cache_hit_internal_test.go

@@ -1,303 +0,0 @@
-package imgcache
-
-import (
-	"bytes"
-	"errors"
-	"fmt"
-	"image/color"
-	"io"
-	"os"
-	"testing"
-	"time"
-
-	"sneak.berlin/go/pixa/internal/imageprocessor"
-	"sneak.berlin/go/pixa/internal/imagerequest"
-	"sneak.berlin/go/pixa/internal/magic"
-)
-
-// TestGetVariant_ContentTypeFromFirstBytes stores an image in each output
-// format as a variant and checks that GetVariant serves it whole with the
-// content type of its format, read from the file.
-func TestGetVariant_ContentTypeFromFirstBytes(t *testing.T) {
-	t.Parallel()
-
-	cache, _ := newEvictionTestCache(t, 1<<30)
-	processor := imageprocessor.New(imageprocessor.Params{
-		MaxInputBytes:           50 << 20,
-		MaxConcurrentProcessing: 1,
-	})
-	source := generateTestJPEG(t, 40, 30, color.RGBA{200, 40, 40, 255})
-
-	for _, format := range []imagerequest.Format{
-		imagerequest.FormatJPEG, imagerequest.FormatPNG, imagerequest.FormatGIF,
-		imagerequest.FormatWebP, imagerequest.FormatAVIF, imagerequest.FormatJXL,
-	} {
-		result, err := processor.Process(t.Context(), bytes.NewReader(source),
-			&imagerequest.Transform{
-				Size:    imagerequest.Size{Width: 20, Height: 15},
-				Format:  format,
-				Quality: 85,
-				FitMode: imagerequest.FitCover,
-			})
-		if err != nil {
-			t.Fatalf("making a %s image: %v", format, err)
-		}
-
-		image, err := io.ReadAll(result.Content)
-		if err != nil {
-			t.Fatalf("reading the %s image: %v", format, err)
-		}
-
-		key := imagerequest.VariantKey("aabbccdd10" + string(format))
-
-		err = cache.StoreVariant(t.Context(), key, bytes.NewReader(image))
-		if err != nil {
-			t.Fatalf("StoreVariant(%s) error = %v", format, err)
-		}
-
-		reader, size, contentType, err := cache.GetVariant(key)
-		if err != nil {
-			t.Fatalf("GetVariant(%s) error = %v", format, err)
-		}
-
-		served, err := io.ReadAll(reader)
-		_ = reader.Close()
-
-		if err != nil {
-			t.Fatalf("reading the %s variant: %v", format, err)
-		}
-
-		t.Logf("%s: %d bytes served as %s", format, size, contentType)
-
-		if want := imageprocessor.FormatToMIME(format); contentType != want {
-			t.Errorf("%s variant content type = %q, want %q", format, contentType, want)
-		}
-
-		if size != int64(len(image)) || !bytes.Equal(served, image) {
-			t.Errorf("%s variant served %d bytes, size %d, want the %d bytes stored",
-				format, len(served), size, len(image))
-		}
-	}
-}
-
-// TestGetVariant_RefusesFileOfNoOutputFormat checks that GetVariant refuses
-// a variant file whose first bytes are not those of an output format, with
-// an error other than ErrNotFound, and that a variant with no file, or any
-// variant of a disabled cache, is ErrNotFound.
-func TestGetVariant_RefusesFileOfNoOutputFormat(t *testing.T) {
-	t.Parallel()
-
-	cache, _ := newEvictionTestCache(t, 1<<30)
-	jpegImage := generateTestJPEG(t, 10, 10, color.RGBA{0, 0, 255, 255})
-
-	tests := []struct {
-		name    string
-		content []byte
-		wantErr error
-	}{
-		{"text", []byte("this is text, not an image"), magic.ErrUnknownFormat},
-		{"SVG", []byte(`<svg xmlns="http://www.w3.org/2000/svg"></svg>`),
-			errNotAnOutputFormat},
-		{"JPEG cut to 10 bytes", jpegImage[:10], io.EOF},
-		{"empty", nil, io.EOF},
-	}
-
-	for i, tt := range tests {
-		key := imagerequest.VariantKey(fmt.Sprintf("aabbccdd20%02d", i))
-
-		_, err := cache.variants.Store(key, bytes.NewReader(tt.content))
-		if err != nil {
-			t.Fatalf("%s: storing the variant file: %v", tt.name, err)
-		}
-
-		reader, _, contentType, err := cache.GetVariant(key)
-		t.Logf("%s: GetVariant() error = %v", tt.name, err)
-
-		if reader != nil || contentType != "" || !errors.Is(err, tt.wantErr) {
-			t.Errorf("%s: GetVariant() = reader %v, content type %q, error %v; "+
-				"want no reader and %v", tt.name, reader, contentType, err, tt.wantErr)
-		}
-	}
-
-	reader, _, _, err := cache.GetVariant(testVariantKeyFour)
-	if reader != nil || !errors.Is(err, ErrNotFound) {
-		t.Errorf("GetVariant() of a variant with no file = reader %v, error %v; "+
-			"want no reader and %v", reader, err, ErrNotFound)
-	}
-
-	disabled, _ := newEvictionTestCache(t, 0)
-
-	reader, _, _, err = disabled.GetVariant(testVariantKeyOne)
-	if reader != nil || !errors.Is(err, ErrNotFound) {
-		t.Errorf("GetVariant() on a disabled cache = reader %v, error %v; "+
-			"want no reader and %v", reader, err, ErrNotFound)
-	}
-}
-
-// TestService_Get_MakesAgainVariantOfNoOutputFormat replaces a cached
-// variant's file with text, and checks that the next request is a miss
-// answered with the variant made again, and the one after a hit.
-func TestService_Get_MakesAgainVariantOfNoOutputFormat(t *testing.T) {
-	t.Parallel()
-
-	svc, fixtures := SetupTestService(t)
-	req := photoVariant(fixtures, 85, imagerequest.FitCover)
-
-	want, _ := getImage(t, svc, req)
-
-	path := svc.cache.variants.keyToPath(imagerequest.CacheKey(req))
-
-	err := os.WriteFile(path, []byte("this is text, not an image"), StorageFilePerm)
-	if err != nil {
-		t.Fatalf("replacing the variant file: %v", err)
-	}
-
-	got, status := getImage(t, svc, req)
-	t.Logf("after the replacement: %d bytes, %s", len(got), status)
-
-	if status != CacheMiss || !bytes.Equal(got, want) {
-		t.Errorf("after the replacement: Get() = %d bytes, %s; want the %d bytes "+
-			"made again, %s", len(got), status, len(want), CacheMiss)
-	}
-
-	got, status = getImage(t, svc, req)
-
-	if status != CacheHit || !bytes.Equal(got, want) {
-		t.Errorf("next request: Get() = %d bytes, %s; want the %d bytes, %s",
-			len(got), status, len(want), CacheHit)
-	}
-}
-
-// TestService_Get_HitWaitsForNoDatabaseWrite holds the database's one
-// connection while a cached variant is requested. The hit must be answered
-// while the connection is still held, and its access time must reach the
-// database once it is free.
-func TestService_Get_HitWaitsForNoDatabaseWrite(t *testing.T) {
-	t.Parallel()
-
-	svc, fixtures := SetupTestService(t)
-	req := photoVariant(fixtures, 85, imagerequest.FitCover)
-	key := imagerequest.CacheKey(req)
-
-	getImage(t, svc, req)
-
-	// Each connection to an in-memory SQLite database opens a new, empty one,
-	// so the goroutine that writes the access times must share the
-	// connection that holds the schema.
-	svc.cache.db.SetMaxOpenConns(1)
-	svc.cache.StartPendingAccessTimeWrites()
-
-	defer func() { _ = svc.cache.StopPendingAccessTimeWrites(t.Context()) }()
-
-	anHourAgo := time.Now().Add(-time.Hour)
-	setVariantLastAccessed(t, svc.cache, key, anHourAgo)
-
-	releaseDatabase := holdDatabase(t, svc.cache)
-	defer releaseDatabase()
-
-	results := startGet(t.Context(), svc, req)
-
-	select {
-	case got := <-results:
-		if got.err != nil {
-			t.Fatalf("Get() of the cached variant error = %v", got.err)
-		}
-	case <-time.After(pendingAccessTimesWait):
-		t.Fatal("the cache hit waited for the database")
-	}
-
-	releaseDatabase()
-
-	deadline := time.Now().Add(pendingAccessTimesWait)
-
-	for countRows(t, svc.cache, `
-		SELECT COUNT(*) FROM variant_content
-		WHERE cache_key = ? AND last_accessed_at > ?
-	`, string(key), anHourAgo.UTC().Format(sqliteTimestampFormat)) == 0 {
-		if time.Now().After(deadline) {
-			t.Fatal("the hit's access time was not written")
-		}
-
-		time.Sleep(10 * time.Millisecond)
-	}
-}
-
-// TestTouchVariantAndTouchSourceContent_DropAccessTimesPastTheLimit hands one
-// more access time of a variant, and one more of a source, than may wait to
-// be written. touchVariant and touchSourceContent must return each time
-// without waiting, and the last of each must be dropped.
-func TestTouchVariantAndTouchSourceContent_DropAccessTimesPastTheLimit(t *testing.T) {
-	t.Parallel()
-
-	cache, _ := newEvictionTestCache(t, 1<<30)
-
-	done := make(chan struct{})
-
-	go func() {
-		defer close(done)
-
-		for range maxPendingAccessTimes + 1 {
-			cache.touchVariant(testVariantKeyOne)
-			cache.touchSourceContent("aabbccdd3001")
-		}
-	}()
-
-	select {
-	case <-done:
-	case <-time.After(pendingAccessTimesWait):
-		t.Fatal("touchVariant or touchSourceContent waited once the access " +
-			"times reached the limit")
-	}
-
-	if waiting := len(cache.pendingVariantAccessTimes); waiting != maxPendingAccessTimes {
-		t.Errorf("%d access times of variants wait to be written, want %d",
-			waiting, maxPendingAccessTimes)
-	}
-
-	if waiting := len(cache.pendingSourceAccessTimes); waiting != maxPendingAccessTimes {
-		t.Errorf("%d access times of sources wait to be written, want %d",
-			waiting, maxPendingAccessTimes)
-	}
-}
-
-// TestStopPendingAccessTimeWrites_WritesPendingAccessTimes hands the access
-// time of one of two variants, three times, then stops the goroutine that
-// writes them, which never started. The stop must write that access time and
-// leave the other variant's.
-func TestStopPendingAccessTimeWrites_WritesPendingAccessTimes(t *testing.T) {
-	t.Parallel()
-
-	cache, _ := newEvictionTestCache(t, 1<<30)
-	anHourAgo := time.Now().Add(-time.Hour)
-
-	for _, key := range []imagerequest.VariantKey{testVariantKeyOne, testVariantKeyTwo} {
-		storeEvictionTestVariant(t, cache, key, []byte("variant bytes"))
-		setVariantLastAccessed(t, cache, key, anHourAgo)
-	}
-
-	for range 3 {
-		cache.touchVariant(testVariantKeyOne)
-	}
-
-	err := cache.StopPendingAccessTimeWrites(t.Context())
-	if err != nil {
-		t.Fatalf("StopPendingAccessTimeWrites() error = %v", err)
-	}
-
-	for key, wantTouched := range map[imagerequest.VariantKey]int{
-		testVariantKeyOne: 1, testVariantKeyTwo: 0,
-	} {
-		touched := countRows(t, cache, `
-			SELECT COUNT(*) FROM variant_content
-			WHERE cache_key = ? AND last_accessed_at > ?
-		`, string(key), anHourAgo.UTC().Format(sqliteTimestampFormat))
-		if touched != wantTouched {
-			t.Errorf("variant %s: %d rows with a new access time, want %d",
-				key, touched, wantTouched)
-		}
-	}
-
-	if waiting := len(cache.pendingVariantAccessTimes); waiting != 0 {
-		t.Errorf("%d access times still wait to be written, want 0", waiting)
-	}
-}

internal/imgcache/cache_internal_test.go

@@ -1,14 +1,15 @@
 package imgcache
 
 import (
+	"bytes"
 	"context"
 	"database/sql"
 	"os"
 	"testing"
 	"time"
 
-	"github.com/prometheus/client_golang/prometheus"
 	_ "modernc.org/sqlite"
+	"sneak.berlin/go/pixa/internal/httpfetcher"
 )
 
 func setupTestDB(t *testing.T) *sql.DB {
@@ -22,18 +23,67 @@ func setupTestDB(t *testing.T) *sql.DB {
 	// Create schema
 	schema := `
 		CREATE TABLE source_content (
-			source_key TEXT PRIMARY KEY,
+			content_hash TEXT PRIMARY KEY,
+			content_type TEXT NOT NULL,
 			size_bytes INTEGER NOT NULL,
-			last_accessed_at DATETIME NOT NULL DEFAULT CURRENT_TIMESTAMP
+			fetched_at DATETIME DEFAULT CURRENT_TIMESTAMP
+		);
+		CREATE TABLE source_metadata (
+			id INTEGER PRIMARY KEY AUTOINCREMENT,
+			source_host TEXT NOT NULL,
+			source_path TEXT NOT NULL,
+			source_query TEXT NOT NULL DEFAULT '',
+			path_hash TEXT NOT NULL,
+			content_hash TEXT,
+			status_code INTEGER NOT NULL,
+			content_type TEXT,
+			response_headers TEXT,
+			fetched_at DATETIME DEFAULT CURRENT_TIMESTAMP,
+			expires_at DATETIME,
+			etag TEXT,
+			last_modified TEXT,
+			UNIQUE(source_host, source_path, source_query)
+		);
+		CREATE TABLE output_content (
+			content_hash TEXT PRIMARY KEY,
+			content_type TEXT NOT NULL,
+			size_bytes INTEGER NOT NULL,
+			fetched_at DATETIME DEFAULT CURRENT_TIMESTAMP
+		);
+		CREATE TABLE request_cache (
+			id INTEGER PRIMARY KEY AUTOINCREMENT,
+			cache_key TEXT NOT NULL UNIQUE,
+			source_metadata_id INTEGER NOT NULL,
+			output_hash TEXT NOT NULL,
+			width INTEGER NOT NULL,
+			height INTEGER NOT NULL,
+			format TEXT NOT NULL,
+			quality INTEGER NOT NULL DEFAULT 85,
+			fit_mode TEXT NOT NULL DEFAULT 'cover',
+			fetched_at DATETIME DEFAULT CURRENT_TIMESTAMP,
+			access_count INTEGER NOT NULL DEFAULT 1
 		);
 		CREATE TABLE negative_cache (
 			id INTEGER PRIMARY KEY AUTOINCREMENT,
 			source_host TEXT NOT NULL,
 			source_path TEXT NOT NULL,
 			source_query TEXT NOT NULL DEFAULT '',
+			status_code INTEGER NOT NULL,
+			error_message TEXT,
+			fetched_at DATETIME DEFAULT CURRENT_TIMESTAMP,
 			expires_at DATETIME NOT NULL,
 			UNIQUE(source_host, source_path, source_query)
 		);
+		CREATE TABLE cache_stats (
+			id INTEGER PRIMARY KEY CHECK (id = 1),
+			hit_count INTEGER NOT NULL DEFAULT 0,
+			miss_count INTEGER NOT NULL DEFAULT 0,
+			upstream_fetch_count INTEGER NOT NULL DEFAULT 0,
+			upstream_fetch_bytes INTEGER NOT NULL DEFAULT 0,
+			transform_count INTEGER NOT NULL DEFAULT 0,
+			last_updated_at DATETIME DEFAULT CURRENT_TIMESTAMP
+		);
+		INSERT INTO cache_stats (id) VALUES (1);
 	`
 
 	_, err = db.ExecContext(t.Context(), schema)
@@ -44,6 +94,361 @@ func setupTestDB(t *testing.T) *sql.DB {
 	return db
 }
 
+func setupTestCache(t *testing.T) *Cache {
+	t.Helper()
+
+	tmpDir := t.TempDir()
+	db := setupTestDB(t)
+
+	cache, err := NewCache(db, CacheConfig{
+		StateDir:    tmpDir,
+		NegativeTTL: 5 * time.Minute,
+	})
+	if err != nil {
+		t.Fatalf("failed to create cache: %v", err)
+	}
+
+	return cache
+}
+
+func TestCache_LookupMiss(t *testing.T) {
+	t.Parallel()
+
+	cache := setupTestCache(t)
+	ctx := context.Background()
+
+	req := &ImageRequest{
+		SourceHost: testHostCDN,
+		SourcePath: testPathCat,
+		Size:       Size{Width: 800, Height: 600},
+		Format:     FormatWebP,
+		Quality:    85,
+		FitMode:    FitCover,
+	}
+
+	result, err := cache.Lookup(ctx, req)
+	if err != nil {
+		t.Fatalf("Lookup() error = %v", err)
+	}
+
+	if result.Hit {
+		t.Error("Lookup() hit = true, want false for cache miss")
+	}
+
+	if result.CacheStatus != CacheMiss {
+		t.Errorf("Lookup() status = %v, want %v", result.CacheStatus, CacheMiss)
+	}
+}
+
+func TestCache_StoreAndLookup(t *testing.T) {
+	t.Parallel()
+
+	cache := setupTestCache(t)
+	ctx := context.Background()
+
+	req := &ImageRequest{
+		SourceHost: testHostCDN,
+		SourcePath: testPathCat,
+		Size:       Size{Width: 800, Height: 600},
+		Format:     FormatWebP,
+		Quality:    85,
+		FitMode:    FitCover,
+	}
+
+	// Store source content
+	sourceContent := []byte("fake jpeg data")
+	fetchResult := &httpfetcher.FetchResult{
+		ContentType: testContentTypeJPEG,
+		Headers:     map[string][]string{testHeaderContentType: {testContentTypeJPEG}},
+	}
+
+	contentHash, err := cache.StoreSource(
+		ctx, req, bytes.NewReader(sourceContent), fetchResult)
+	if err != nil {
+		t.Fatalf("StoreSource() error = %v", err)
+	}
+
+	if contentHash == "" {
+		t.Error("StoreSource() returned empty hash")
+	}
+
+	// Store variant
+	cacheKey := CacheKey(req)
+	outputContent := []byte("fake webp data")
+
+	err = cache.StoreVariant(
+		t.Context(), cacheKey, bytes.NewReader(outputContent), "image/webp")
+	if err != nil {
+		t.Fatalf("StoreVariant() error = %v", err)
+	}
+
+	// Now lookup should hit
+	result, err := cache.Lookup(ctx, req)
+	if err != nil {
+		t.Fatalf("Lookup() error = %v", err)
+	}
+
+	if !result.Hit {
+		t.Error("Lookup() hit = false, want true after store")
+	}
+
+	if result.CacheStatus != CacheHit {
+		t.Errorf("Lookup() status = %v, want %v", result.CacheStatus, CacheHit)
+	}
+
+	if result.CacheKey == "" {
+		t.Error("Lookup() returned empty cache key")
+	}
+}
+
+func TestCache_NegativeCache(t *testing.T) {
+	t.Parallel()
+
+	cache := setupTestCache(t)
+	ctx := context.Background()
+
+	req := &ImageRequest{
+		SourceHost: testHostCDN,
+		SourcePath: "/photos/notfound.jpg",
+		Size:       Size{Width: 800, Height: 600},
+		Format:     FormatWebP,
+	}
+
+	// Store negative cache entry
+	err := cache.StoreNegative(ctx, req, 404, "not found")
+	if err != nil {
+		t.Fatalf("StoreNegative() error = %v", err)
+	}
+
+	// Lookup should return miss (negative cache is checked at service level)
+	result, err := cache.Lookup(ctx, req)
+	if err != nil {
+		t.Fatalf("Lookup() error = %v", err)
+	}
+
+	if result.Hit {
+		t.Error("Lookup() hit = true, want false for negative cache entry")
+	}
+}
+
+func TestCache_NegativeCacheExpiry(t *testing.T) {
+	t.Parallel()
+
+	tmpDir := t.TempDir()
+	db := setupTestDB(t)
+
+	// Very short negative TTL for testing
+	cache, err := NewCache(db, CacheConfig{
+		StateDir:    tmpDir,
+		NegativeTTL: 1 * time.Millisecond,
+	})
+	if err != nil {
+		t.Fatalf("failed to create cache: %v", err)
+	}
+
+	ctx := context.Background()
+
+	req := &ImageRequest{
+		SourceHost: testHostCDN,
+		SourcePath: "/photos/expired.jpg",
+		Size:       Size{Width: 800, Height: 600},
+		Format:     FormatWebP,
+	}
+
+	// Store negative cache entry
+	err = cache.StoreNegative(ctx, req, 404, "not found")
+	if err != nil {
+		t.Fatalf("StoreNegative() error = %v", err)
+	}
+
+	// Wait for expiry
+	time.Sleep(10 * time.Millisecond)
+
+	// Lookup should return miss after expiry
+	result, err := cache.Lookup(ctx, req)
+	if err != nil {
+		t.Fatalf("Lookup() error = %v, want nil after expiry", err)
+	}
+
+	if result.Hit {
+		t.Error("Lookup() hit = true, want false after negative cache expiry")
+	}
+}
+
+func TestCache_VariantLookup(t *testing.T) {
+	t.Parallel()
+
+	cache := setupTestCache(t)
+	ctx := context.Background()
+
+	req := &ImageRequest{
+		SourceHost: testHostCDN,
+		SourcePath: "/photos/variant.jpg",
+		Size:       Size{Width: 800, Height: 600},
+		Format:     FormatWebP,
+		Quality:    85,
+		FitMode:    FitCover,
+	}
+
+	// Store variant
+	cacheKey := CacheKey(req)
+	outputContent := []byte("output data")
+
+	err := cache.StoreVariant(
+		t.Context(), cacheKey, bytes.NewReader(outputContent), "image/webp")
+	if err != nil {
+		t.Fatalf("StoreVariant() error = %v", err)
+	}
+
+	// First lookup
+	result1, err := cache.Lookup(ctx, req)
+	if err != nil {
+		t.Fatalf("Lookup() first error = %v", err)
+	}
+
+	if !result1.Hit {
+		t.Error("Lookup() first hit = false")
+	}
+
+	// Second lookup should also hit (from disk)
+	result2, err := cache.Lookup(ctx, req)
+	if err != nil {
+		t.Fatalf("Lookup() second error = %v", err)
+	}
+
+	if !result2.Hit {
+		t.Error("Lookup() second hit = false")
+	}
+
+	if result1.CacheKey != result2.CacheKey {
+		t.Error("Lookup() returned different cache keys")
+	}
+}
+
+func TestCache_GetVariant_ReturnsContentType(t *testing.T) {
+	t.Parallel()
+
+	cache := setupTestCache(t)
+	ctx := context.Background()
+
+	req := &ImageRequest{
+		SourceHost: testHostCDN,
+		SourcePath: "/photos/variantct.jpg",
+		Size:       Size{Width: 800, Height: 600},
+		Format:     FormatWebP,
+		Quality:    85,
+		FitMode:    FitCover,
+	}
+
+	// Store variant
+	cacheKey := CacheKey(req)
+	outputContent := []byte("output webp data")
+
+	err := cache.StoreVariant(
+		t.Context(), cacheKey, bytes.NewReader(outputContent), "image/webp")
+	if err != nil {
+		t.Fatalf("StoreVariant() error = %v", err)
+	}
+
+	// Lookup
+	result, err := cache.Lookup(ctx, req)
+	if err != nil {
+		t.Fatalf("Lookup() error = %v", err)
+	}
+
+	if !result.Hit {
+		t.Fatal("Lookup() hit = false, want true")
+	}
+
+	// GetVariant should return content type
+	reader, size, contentType, err := cache.GetVariant(result.CacheKey)
+	if err != nil {
+		t.Fatalf("GetVariant() error = %v", err)
+	}
+
+	defer func() { _ = reader.Close() }()
+
+	if contentType != "image/webp" {
+		t.Errorf("GetVariant() ContentType = %q, want %q", contentType, "image/webp")
+	}
+
+	if size != int64(len(outputContent)) {
+		t.Errorf("GetVariant() size = %d, want %d", size, len(outputContent))
+	}
+}
+
+func TestCache_GetVariant(t *testing.T) {
+	t.Parallel()
+
+	cache := setupTestCache(t)
+	ctx := context.Background()
+
+	req := &ImageRequest{
+		SourceHost: testHostCDN,
+		SourcePath: "/photos/output.jpg",
+		Size:       Size{Width: 800, Height: 600},
+		Format:     FormatWebP,
+		Quality:    85,
+		FitMode:    FitCover,
+	}
+
+	// Store variant
+	cacheKey := CacheKey(req)
+	outputContent := []byte("the actual output content")
+
+	err := cache.StoreVariant(
+		t.Context(), cacheKey, bytes.NewReader(outputContent), "image/webp")
+	if err != nil {
+		t.Fatalf("StoreVariant() error = %v", err)
+	}
+
+	// Lookup to get cache key
+	result, err := cache.Lookup(ctx, req)
+	if err != nil {
+		t.Fatalf("Lookup() error = %v", err)
+	}
+
+	// Get variant content
+	reader, _, _, err := cache.GetVariant(result.CacheKey)
+	if err != nil {
+		t.Fatalf("GetVariant() error = %v", err)
+	}
+
+	defer func() { _ = reader.Close() }()
+
+	buf := make([]byte, 100)
+	n, _ := reader.Read(buf)
+
+	if !bytes.Equal(buf[:n], outputContent) {
+		t.Errorf("GetVariant() content = %q, want %q", buf[:n], outputContent)
+	}
+}
+
+func TestCache_Stats(t *testing.T) {
+	t.Parallel()
+
+	cache := setupTestCache(t)
+	ctx := context.Background()
+
+	// Increment some stats
+	cache.IncrementStats(ctx, true, 0)
+	cache.IncrementStats(ctx, true, 0)
+	cache.IncrementStats(ctx, false, 1024)
+
+	stats, err := cache.Stats(ctx)
+	if err != nil {
+		t.Fatalf("Stats() error = %v", err)
+	}
+
+	if stats.HitCount != 2 {
+		t.Errorf("Stats() HitCount = %d, want 2", stats.HitCount)
+	}
+
+	if stats.MissCount != 1 {
+		t.Errorf("Stats() MissCount = %d, want 1", stats.MissCount)
+	}
+}
+
 func TestCache_CleanExpired(t *testing.T) {
 	t.Parallel()
 
@@ -53,16 +458,15 @@ func TestCache_CleanExpired(t *testing.T) {
 	cache, _ := NewCache(db, CacheConfig{
 		StateDir:    tmpDir,
 		NegativeTTL: 1 * time.Millisecond,
-		MaxBytes:    1 << 30,
+	})
-	}, prometheus.NewRegistry())
 
 	ctx := context.Background()
 
 	// Insert expired negative cache entry directly
 	_, err := db.ExecContext(ctx, `
 		INSERT INTO negative_cache
-			(source_host, source_path, source_query, expires_at)
+			(source_host, source_path, source_query, status_code, expires_at)
-		VALUES ('example.com', '/old.jpg', '', datetime('now', '-1 hour'))
+		VALUES ('example.com', '/old.jpg', '', 404, datetime('now', '-1 hour'))
 	`)
 	if err != nil {
 		t.Fatalf("failed to insert test data: %v", err)
@@ -105,8 +509,7 @@ func TestCache_StorageDirectoriesCreated(t *testing.T) {
 
 	_, err := NewCache(db, CacheConfig{
 		StateDir: tmpDir,
-		MaxBytes: 1 << 30,
+	})
-	}, prometheus.NewRegistry())
 	if err != nil {
 		t.Fatalf("NewCache() error = %v", err)
 	}
@@ -115,6 +518,7 @@ func TestCache_StorageDirectoriesCreated(t *testing.T) {
 	dirs := []string{
 		"cache/sources",
 		"cache/variants",
+		"cache/metadata",
 	}
 
 	for _, dir := range dirs {

internal/imgcache/cache_usage_internal_test.go

@@ -5,8 +5,6 @@ import (
 	"strconv"
 	"strings"
 	"testing"
-
-	"sneak.berlin/go/pixa/internal/imagerequest"
 )
 
 // TestEvictionReadsTheUsageTotal adds, stores again, resizes and evicts
@@ -31,10 +29,10 @@ func TestEvictionReadsTheUsageTotal(t *testing.T) {
 	storeEvictionTestVariant(t, cache, testVariantKeyTwo,
 		bytes.Repeat([]byte{0x75}, 200))
 
-	// Storing a source URL again changes its size, so the total must
+	// pixa never changes a source's size, but a statement that does must
-	// follow a statement that changes it.
+	// change the total too.
 	_, err := cache.db.ExecContext(ctx,
-		`UPDATE source_content SET size_bytes = 900 WHERE source_key = ?`,
+		`UPDATE source_content SET size_bytes = 900 WHERE content_hash = ?`,
 		string(kept))
 	if err != nil {
 		t.Fatalf("failed to change the source's size: %v", err)
@@ -155,9 +153,8 @@ func TestUsageTotalNotCorrectedFromAnOlderSum(t *testing.T) {
 // pass. No read the pass makes of a content table, to check its rows or
 // to sum them, may cover more than two rows, so a request's query waits
 // for one page at most. Between them the reads must still cover every
-// variant row twice, once to check it and once to sum it, and every
+// row of both tables twice, once to check it and once to sum it, and the
-// source row once, as source rows are read only to sum them, and the sum
+// sum must put a wrong total right.
-// must put a wrong total right.
 func TestReconciliationReadsAPageAtATime(t *testing.T) {
 	t.Parallel()
 
@@ -174,8 +171,7 @@ func TestReconciliationReadsAPageAtATime(t *testing.T) {
 
 		storeEvictionTestSource(t, cache, "pages.example.com",
 			"/"+strconv.Itoa(i)+".jpg", bytes.Repeat(content, 100))
-		storeEvictionTestVariant(t, cache,
+		storeEvictionTestVariant(t, cache, VariantKey("aabbccdd000"+strconv.Itoa(i)),
-			imagerequest.VariantKey("aabbccdd000"+strconv.Itoa(i)),
 			bytes.Repeat(content, 10))
 	}
 
@@ -208,10 +204,9 @@ func TestReconciliationReadsAPageAtATime(t *testing.T) {
 		coveredRows += rows
 	}
 
-	// Five variant rows, each read once to check it and once to sum it,
+	// Ten rows, each read once to check it and once to sum it.
-	// and five source rows, read only to sum them.
+	if coveredRows != 20 {
-	if coveredRows != 15 {
+		t.Errorf("the reads covered %d rows in all, want 20", coveredRows)
-		t.Errorf("the reads covered %d rows in all, want 15", coveredRows)
 	}
 
 	usage, err := cache.UsageBytes(ctx)

internal/imgcache/cachesize.go

@@ -0,0 +1,85 @@
+package imgcache
+
+import (
+	"context"
+	"errors"
+	"fmt"
+	"math"
+	"path/filepath"
+	"syscall"
+)
+
+// DefaultCacheMaxBytesFloor is the minimum computed default for the
+// cache_max_bytes setting: 500 MiB. The floor applies only to the
+// computed default (when the key is omitted from the configuration),
+// never to explicitly configured values.
+const DefaultCacheMaxBytesFloor int64 = 524288000
+
+// freeSpaceFractionNumerator and freeSpaceFractionDenominator express
+// the 75% share used for the computed default limit as integer
+// arithmetic (dividing before multiplying avoids overflow).
+const (
+	freeSpaceFractionNumerator   uint64 = 3
+	freeSpaceFractionDenominator uint64 = 4
+)
+
+var errNegativeBlockSize = errors.New("statfs reported negative block size")
+
+// FreeSpaceProbeFunc reports the number of free bytes available on the
+// filesystem containing path. It is a function type so tests can
+// inject a fake probe instead of depending on the host disk.
+type FreeSpaceProbeFunc func(path string) (uint64, error)
+
+// defaultFreeSpaceProbe reports free filesystem bytes via statfs on
+// the given path, as available to unprivileged processes.
+func defaultFreeSpaceProbe(path string) (uint64, error) {
+	var stat syscall.Statfs_t
+
+	err := syscall.Statfs(path, &stat)
+	if err != nil {
+		return 0, err
+	}
+
+	if stat.Bsize < 0 {
+		return 0, fmt.Errorf("%w %d for %q", errNegativeBlockSize, stat.Bsize, path)
+	}
+
+	blockSize := uint64(stat.Bsize)
+
+	return stat.Bavail * blockSize, nil
+}
+
+// computeDefaultMaxBytes returns the default cache size limit: 75% of
+// the sum of the free bytes probe reports for <state_dir>/cache/ and
+// the bytes the cache already holds, with a floor of
+// DefaultCacheMaxBytesFloor. Counting what the cache holds keeps the
+// limit from shrinking as the cache fills.
+func (c *Cache) computeDefaultMaxBytes(
+	ctx context.Context, probe FreeSpaceProbeFunc,
+) (int64, error) {
+	cacheDir := filepath.Join(c.config.StateDir, "cache")
+
+	freeBytes, err := probe(cacheDir)
+	if err != nil {
+		return 0, fmt.Errorf(
+			"default cache_max_bytes: cannot determine free space for %q: %w",
+			cacheDir, err)
+	}
+
+	usedBytes, err := c.UsageBytes(ctx)
+	if err != nil {
+		return 0, err
+	}
+
+	// Both terms are at most math.MaxInt64, so the sum cannot overflow.
+	//nolint:gosec // G115: UsageBytes returns the total cache usage, never negative
+	spaceBytes := min(freeBytes, math.MaxInt64) + uint64(usedBytes)
+
+	computed := spaceBytes / freeSpaceFractionDenominator * freeSpaceFractionNumerator
+	computed = min(computed, math.MaxInt64)
+
+	limit := int64(computed)
+	limit = max(limit, DefaultCacheMaxBytesFloor)
+
+	return limit, nil
+}

internal/imgcache/cachesize_internal_test.go

@@ -0,0 +1,188 @@
+package imgcache
+
+import (
+	"errors"
+	"os"
+	"path/filepath"
+	"strings"
+	"testing"
+)
+
+// Static errors returned by the stub free-space probes below.
+var (
+	errTestStatfsFailed     = errors.New("statfs failed")
+	errTestProbeNotExpected = errors.New("probe must not be called")
+)
+
+// TestComputeDefaultMaxBytesCountsWhatTheCacheHolds verifies that the
+// default limit is 75% of the free space plus what the cache already
+// holds, so a cache filled to its limit keeps that limit across a
+// restart instead of shrinking to 75% of the space left free.
+func TestComputeDefaultMaxBytesCountsWhatTheCacheHolds(t *testing.T) {
+	t.Parallel()
+
+	cache, _ := newEvictionTestCache(t, 1<<30)
+
+	// Empty cache, 4 GiB free -> 3 GiB default.
+	got, err := cache.computeDefaultMaxBytes(t.Context(),
+		func(string) (uint64, error) { return 4294967296, nil })
+	if err != nil {
+		t.Fatalf("computeDefaultMaxBytes returned error: %v", err)
+	}
+
+	t.Logf("default for an empty cache with 4 GiB free: %d", got)
+
+	if got != 3221225472 {
+		t.Errorf("default for an empty cache = %d, want 3221225472 (75%% of 4 GiB)",
+			got)
+	}
+
+	// The cache now holds those 3 GiB, which leaves 1 GiB free.
+	_, err = cache.db.ExecContext(t.Context(),
+		`INSERT INTO variant_content (cache_key, size_bytes, content_type)
+		 VALUES (?, ?, ?)`,
+		string(testVariantKeyOne), 3221225472, testContentTypeWebP,
+	)
+	if err != nil {
+		t.Fatalf("failed to insert variant accounting row: %v", err)
+	}
+
+	got, err = cache.computeDefaultMaxBytes(t.Context(),
+		func(string) (uint64, error) { return 1073741824, nil })
+	if err != nil {
+		t.Fatalf("computeDefaultMaxBytes returned error: %v", err)
+	}
+
+	t.Logf("default for a cache holding 3 GiB with 1 GiB free: %d", got)
+
+	if got != 3221225472 {
+		t.Errorf("default for a cache holding 3 GiB with 1 GiB free = %d, "+
+			"want 3221225472 (75%% of 1 GiB + 3 GiB)", got)
+	}
+}
+
+// TestComputeDefaultMaxBytesAppliesFloor verifies that when 75% of the
+// free space plus what the cache holds is below 500 MiB, the default
+// is floored at DefaultCacheMaxBytesFloor.
+func TestComputeDefaultMaxBytesAppliesFloor(t *testing.T) {
+	t.Parallel()
+
+	cases := []struct {
+		name      string
+		freeBytes uint64
+	}{
+		{name: "100 MiB free", freeBytes: 104857600},
+		{name: "zero free", freeBytes: 0},
+		{name: "just below floor threshold", freeBytes: 699050665},
+	}
+
+	for _, tc := range cases {
+		t.Run(tc.name, func(t *testing.T) {
+			t.Parallel()
+
+			cache, _ := newEvictionTestCache(t, 1<<30)
+
+			got, err := cache.computeDefaultMaxBytes(t.Context(),
+				func(string) (uint64, error) { return tc.freeBytes, nil })
+			if err != nil {
+				t.Fatalf("computeDefaultMaxBytes returned error: %v", err)
+			}
+
+			if got != DefaultCacheMaxBytesFloor {
+				t.Errorf("computeDefaultMaxBytes = %d, want floor %d",
+					got, DefaultCacheMaxBytesFloor)
+			}
+		})
+	}
+}
+
+// TestComputeDefaultMaxBytesPropagatesProbeError verifies that a
+// failing free-space probe produces an error naming cache_max_bytes,
+// instead of a silently wrong default.
+func TestComputeDefaultMaxBytesPropagatesProbeError(t *testing.T) {
+	t.Parallel()
+
+	cache, _ := newEvictionTestCache(t, 1<<30)
+
+	_, err := cache.computeDefaultMaxBytes(t.Context(),
+		func(string) (uint64, error) { return 0, errTestStatfsFailed })
+	if err == nil {
+		t.Fatal("probe failure must produce an error, got nil")
+	}
+
+	t.Logf("got expected error: %v", err)
+
+	if !strings.Contains(err.Error(), "cache_max_bytes") {
+		t.Errorf("error %q does not name cache_max_bytes", err.Error())
+	}
+}
+
+// TestNewCacheComputesDefaultMaxBytesWhenAsked verifies that with
+// UseDefaultMaxBytes set, the cache's limit becomes the computed
+// default, and that the probe is pointed at <state_dir>/cache/, which
+// must be created first so statfs measures the right filesystem.
+func TestNewCacheComputesDefaultMaxBytesWhenAsked(t *testing.T) {
+	t.Parallel()
+
+	stateDir := t.TempDir()
+	wantCacheDir := filepath.Join(stateDir, "cache")
+
+	var probedPath string
+
+	// 4 GiB free -> 3 GiB default.
+	probe := func(path string) (uint64, error) {
+		probedPath = path
+
+		info, err := os.Stat(path)
+		if err != nil || !info.IsDir() {
+			t.Errorf("cache directory %q was not created before probing: info=%v err=%v",
+				path, info, err)
+		}
+
+		return 4294967296, nil
+	}
+
+	cache, err := newCache(evictionTestDB(t), CacheConfig{
+		StateDir:           stateDir,
+		UseDefaultMaxBytes: true,
+	}, probe)
+	if err != nil {
+		t.Fatalf("newCache returned error: %v", err)
+	}
+
+	if cache.config.MaxBytes != 3221225472 {
+		t.Errorf("MaxBytes = %d, want computed default 3221225472",
+			cache.config.MaxBytes)
+	}
+
+	if probedPath != wantCacheDir {
+		t.Errorf("free space probed at %q, want cache directory %q",
+			probedPath, wantCacheDir)
+	}
+}
+
+// TestNewCacheKeepsExplicitMaxBytes verifies that without
+// UseDefaultMaxBytes the cache keeps MaxBytes exactly as given and
+// never consults the free-space probe.
+func TestNewCacheKeepsExplicitMaxBytes(t *testing.T) {
+	t.Parallel()
+
+	probe := func(string) (uint64, error) {
+		t.Error("free-space probe must not be consulted for explicit values")
+
+		return 0, errTestProbeNotExpected
+	}
+
+	cache, err := newCache(evictionTestDB(t), CacheConfig{
+		StateDir: t.TempDir(),
+		MaxBytes: 1024,
+	}, probe)
+	if err != nil {
+		t.Fatalf("newCache returned error: %v", err)
+	}
+
+	if cache.config.MaxBytes != 1024 {
+		t.Errorf("MaxBytes = %d, want explicit 1024 (no floor, no recompute)",
+			cache.config.MaxBytes)
+	}
+}

internal/imgcache/concurrent_misses_internal_test.go

@@ -16,7 +16,6 @@ import (
 	"github.com/getsentry/sentry-go"
 	"sneak.berlin/go/pixa/internal/httpfetcher"
 	"sneak.berlin/go/pixa/internal/imageprocessor"
-	"sneak.berlin/go/pixa/internal/imagerequest"
 	"sneak.berlin/go/pixa/internal/magic"
 )
 
@@ -81,20 +80,14 @@ func setupHeldFetchService(t *testing.T) (*Service, *TestFixtures, *heldFetcher)
 // photoVariant asks for the test photo, 100x100, at 50x25 as a JPEG of the
 // given quality and fit mode. Each call returns a new request, as Get writes
 // to the request it is given.
-func photoVariant(
+func photoVariant(fixtures *TestFixtures, quality int, fit FitMode) *ImageRequest {
-	fixtures *TestFixtures, quality int, fit imagerequest.Fit,
+	return &ImageRequest{
-) *imagerequest.Request {
+		SourceHost: fixtures.GoodHost,
-	return &imagerequest.Request{
+		SourcePath: testPathPhoto,
-		Source: imagerequest.Source{
+		Size:       Size{Width: 50, Height: 25},
-			Host: fixtures.GoodHost,
+		Format:     FormatJPEG,
-			Path: testPathPhoto,
+		Quality:    quality,
-		},
+		FitMode:    fit,
-		Transform: imagerequest.Transform{
-			Size:    imagerequest.Size{Width: 50, Height: 25},
-			Format:  imagerequest.FormatJPEG,
-			Quality: quality,
-			FitMode: fit,
-		},
 	}
 }
 
@@ -107,7 +100,7 @@ type getResult struct {
 // startGet calls Get in a goroutine of its own and delivers what it returned
 // on the channel.
 func startGet(
-	ctx context.Context, svc *Service, req *imagerequest.Request,
+	ctx context.Context, svc *Service, req *ImageRequest,
 ) <-chan getResult {
 	results := make(chan getResult, 1)
 
@@ -153,7 +146,7 @@ func TestService_Get_ConcurrentMissesShareOneFetch(t *testing.T) {
 	pending := make([]<-chan getResult, 0, requests)
 	for range requests {
 		pending = append(pending,
-			startGet(t.Context(), svc, photoVariant(fixtures, 85, imagerequest.FitCover)))
+			startGet(t.Context(), svc, photoVariant(fixtures, 85, FitCover)))
 	}
 
 	<-fetcher.started
@@ -191,9 +184,9 @@ func TestService_Get_ConcurrentMissesShareOneFetch(t *testing.T) {
 		t.Fatal(err)
 	}
 
-	want := counterValues{0, requests, 1, int64(len(photo)), 1}
+	want := cacheStatsCounters{0, requests, 1, int64(len(photo)), 1}
 
-	if got := readCounters(svc.cache); got != want {
+	if got := readCacheStatsCounters(t, svc.cache); got != want {
 		t.Errorf("counters = %+v, want %+v", got, want)
 	}
 }
@@ -206,11 +199,9 @@ func TestService_Get_ConcurrentVariantsStayApart(t *testing.T) {
 
 	svc, fixtures, fetcher := setupHeldFetchService(t)
 
-	cover := startGet(t.Context(), svc, photoVariant(fixtures, 85, imagerequest.FitCover))
+	cover := startGet(t.Context(), svc, photoVariant(fixtures, 85, FitCover))
-	lowQuality := startGet(t.Context(), svc,
+	lowQuality := startGet(t.Context(), svc, photoVariant(fixtures, 40, FitCover))
-		photoVariant(fixtures, 40, imagerequest.FitCover))
+	contain := startGet(t.Context(), svc, photoVariant(fixtures, 85, FitContain))
-	contain := startGet(t.Context(), svc,
-		photoVariant(fixtures, 85, imagerequest.FitContain))
 
 	for range 3 {
 		select {
@@ -262,12 +253,12 @@ func TestService_Get_WaiterStopsWhenItsContextEnds(t *testing.T) {
 
 	svc, fixtures, fetcher := setupHeldFetchService(t)
 
-	first := startGet(t.Context(), svc, photoVariant(fixtures, 85, imagerequest.FitCover))
+	first := startGet(t.Context(), svc, photoVariant(fixtures, 85, FitCover))
 
 	<-fetcher.started
 
 	waiterCtx, cancelWaiter := context.WithCancel(t.Context())
-	waiter := startGet(waiterCtx, svc, photoVariant(fixtures, 85, imagerequest.FitCover))
+	waiter := startGet(waiterCtx, svc, photoVariant(fixtures, 85, FitCover))
 
 	time.Sleep(arrivalWait)
 	cancelWaiter()
@@ -309,11 +300,11 @@ func TestService_Get_FirstRequestLeavingKeepsTheWork(t *testing.T) {
 	svc, fixtures, fetcher := setupHeldFetchService(t)
 
 	firstCtx, cancelFirst := context.WithCancel(t.Context())
-	first := startGet(firstCtx, svc, photoVariant(fixtures, 85, imagerequest.FitCover))
+	first := startGet(firstCtx, svc, photoVariant(fixtures, 85, FitCover))
 
 	<-fetcher.started
 
-	second := startGet(t.Context(), svc, photoVariant(fixtures, 85, imagerequest.FitCover))
+	second := startGet(t.Context(), svc, photoVariant(fixtures, 85, FitCover))
 
 	time.Sleep(arrivalWait)
 	cancelFirst()
@@ -340,7 +331,8 @@ func TestService_Get_FirstRequestLeavingKeepsTheWork(t *testing.T) {
 // TestService_Get_ConcurrentMissesShareAFailure has several requests for an
 // image that cannot be served arrive while its fetch is held: the one fetch
 // answers all of them with its error. The request after them is answered from
-// the negative cache, where the failure is kept.
+// the negative cache when the failure is kept there, and fetches again when it
+// is not.
 func TestService_Get_ConcurrentMissesShareAFailure(t *testing.T) {
 	t.Parallel()
 
@@ -354,8 +346,8 @@ func TestService_Get_ConcurrentMissesShareAFailure(t *testing.T) {
 		{"upstream answers 404, kept in the negative cache",
 			"/images/missing.jpg", httpfetcher.ErrUpstreamError,
 			ErrNegativeCached, 1},
-		{"source fails the magic byte check, kept in the negative cache",
+		{"source fails the magic byte check, not kept",
-			"/images/text.png", magic.ErrUnknownFormat, ErrNegativeCached, 1},
+			"/images/text.png", magic.ErrUnknownFormat, magic.ErrUnknownFormat, 2},
 	}
 
 	for _, tc := range tests {
@@ -364,9 +356,9 @@ func TestService_Get_ConcurrentMissesShareAFailure(t *testing.T) {
 
 			svc, fixtures, fetcher := setupHeldFetchService(t)
 
-			request := func() *imagerequest.Request {
+			request := func() *ImageRequest {
-				req := photoVariant(fixtures, 85, imagerequest.FitCover)
+				req := photoVariant(fixtures, 85, FitCover)
-				req.Source.Path = tc.path
+				req.SourcePath = tc.path
 
 				return req
 			}
@@ -408,7 +400,7 @@ func TestService_Get_EndedRequestFetchesNothing(t *testing.T) {
 	ctx, cancel := context.WithCancel(t.Context())
 	cancel()
 
-	_, err := svc.Get(ctx, photoVariant(fixtures, 85, imagerequest.FitCover))
+	_, err := svc.Get(ctx, photoVariant(fixtures, 85, FitCover))
 	if !errors.Is(err, context.Canceled) {
 		t.Errorf("Get() error = %v, want %v", err, context.Canceled)
 	}
@@ -432,7 +424,7 @@ func TestService_Get_ReturnsByItsDeadline(t *testing.T) {
 	ctx, cancel := context.WithTimeout(t.Context(), timeout)
 	defer cancel()
 
-	results := startGet(ctx, svc, photoVariant(fixtures, 85, imagerequest.FitCover))
+	results := startGet(ctx, svc, photoVariant(fixtures, 85, FitCover))
 
 	select {
 	case got := <-results:
@@ -455,7 +447,7 @@ func TestService_Get_WaiterGetsProcessingTimedOut(t *testing.T) {
 
 	svc, fixtures, fetcher := setupHeldFetchService(t)
 	svc.processor = imageprocessor.New(
-		imageprocessor.Params{MaxInputBytes: 50 << 20, MaxConcurrentProcessing: 1},
+		imageprocessor.Params{MaxConcurrentProcessing: 1},
 	)
 
 	holdProcessingSlot(t, svc.processor)
@@ -465,11 +457,11 @@ func TestService_Get_WaiterGetsProcessingTimedOut(t *testing.T) {
 	firstCtx, cancelFirst := context.WithTimeout(t.Context(), firstTimeout)
 	defer cancelFirst()
 
-	first := startGet(firstCtx, svc, photoVariant(fixtures, 85, imagerequest.FitCover))
+	first := startGet(firstCtx, svc, photoVariant(fixtures, 85, FitCover))
 
 	<-fetcher.started
 
-	waiter := startGet(t.Context(), svc, photoVariant(fixtures, 85, imagerequest.FitCover))
+	waiter := startGet(t.Context(), svc, photoVariant(fixtures, 85, FitCover))
 
 	time.Sleep(arrivalWait)
 	fetcher.releaseFetches()
@@ -512,7 +504,7 @@ func TestService_Get_PanicBecomesAnError(t *testing.T) {
 			}
 		}()
 
-		_, err = svc.Get(t.Context(), photoVariant(fixtures, 85, imagerequest.FitCover))
+		_, err = svc.Get(t.Context(), photoVariant(fixtures, 85, FitCover))
 	}()
 
 	if err == nil || !strings.Contains(err.Error(), "upstream fetcher panicked") {
@@ -549,7 +541,7 @@ func TestService_Get_PanicIsReportedToSentry(t *testing.T) {
 			}
 		}()
 
-		_, _ = svc.Get(ctx, photoVariant(fixtures, 85, imagerequest.FitCover))
+		_, _ = svc.Get(ctx, photoVariant(fixtures, 85, FitCover))
 	}()
 
 	events := transport.Events()

internal/imgcache/contentlock.go

@@ -0,0 +1,64 @@
+package imgcache
+
+import "sync"
+
+// contentLock provides per-key mutual exclusion for content-hash keyed
+// operations. StoreSource and evictSourceBlob each hold a content
+// hash's lock for the full duration of their file-plus-accounting-row
+// work, so a store and an eviction racing on identical content bytes
+// (the real SHA-256 content-addressed dedup case, not a contrived one)
+// can never interleave: the unlink of an evicted blob's file can never
+// race the creation of a fresh database row for a concurrently
+// re-stored copy of the same content. Entries are removed once no
+// goroutine holds or is waiting for them, so a long-running process
+// does not accumulate memory proportional to the number of distinct
+// content hashes it has ever seen.
+type contentLock struct {
+	mu      sync.Mutex
+	entries map[string]*contentLockEntry
+}
+
+// contentLockEntry is one key's exclusion lock plus a count of
+// goroutines currently holding or waiting to acquire it, used to know
+// when it is safe to remove the entry from the map.
+type contentLockEntry struct {
+	mu    sync.Mutex
+	count int
+}
+
+// newContentLock creates an empty contentLock.
+func newContentLock() *contentLock {
+	return &contentLock{entries: make(map[string]*contentLockEntry)}
+}
+
+// Lock acquires exclusive access for key, blocking until it is
+// available, and returns a function that releases it. The caller must
+// invoke the returned function exactly once to release the lock.
+func (c *contentLock) Lock(key string) func() {
+	c.mu.Lock()
+
+	entry, ok := c.entries[key]
+	if !ok {
+		entry = &contentLockEntry{}
+		c.entries[key] = entry
+	}
+
+	entry.count++
+
+	c.mu.Unlock()
+
+	entry.mu.Lock()
+
+	return func() {
+		entry.mu.Unlock()
+
+		c.mu.Lock()
+
+		entry.count--
+		if entry.count == 0 {
+			delete(c.entries, key)
+		}
+
+		c.mu.Unlock()
+	}
+}

internal/imgcache/contentlock_internal_test.go

@@ -0,0 +1,142 @@
+package imgcache
+
+import (
+	"sync"
+	"sync/atomic"
+	"testing"
+	"time"
+)
+
+// TestContentLockExcludesSameKey verifies that two goroutines locking
+// the same key never run their critical sections concurrently.
+func TestContentLockExcludesSameKey(t *testing.T) {
+	t.Parallel()
+
+	lock := newContentLock()
+
+	var (
+		active  atomic.Int32
+		maxSeen int32
+		wg      sync.WaitGroup
+	)
+
+	const goroutines = 20
+
+	wg.Add(goroutines)
+
+	for range goroutines {
+		go func() {
+			defer wg.Done()
+
+			unlock := lock.Lock("same-key")
+			defer unlock()
+
+			n := active.Add(1)
+
+			for {
+				seen := atomic.LoadInt32(&maxSeen)
+				if n <= seen || atomic.CompareAndSwapInt32(&maxSeen, seen, n) {
+					break
+				}
+			}
+
+			time.Sleep(time.Millisecond)
+
+			active.Add(-1)
+		}()
+	}
+
+	wg.Wait()
+
+	if maxSeen != 1 {
+		t.Errorf("max concurrent holders of the same key = %d, want 1", maxSeen)
+	}
+}
+
+// TestContentLockAllowsDifferentKeys verifies that locking distinct
+// keys does not serialize unrelated work: all goroutines must be able
+// to enter their critical sections at once, proven by every one of
+// them reaching the rendezvous point before any is allowed to
+// proceed.
+func TestContentLockAllowsDifferentKeys(t *testing.T) {
+	t.Parallel()
+
+	lock := newContentLock()
+
+	const goroutines = 20
+
+	var (
+		wg      sync.WaitGroup
+		inside  atomic.Int32
+		reached = make(chan struct{}, goroutines)
+	)
+
+	wg.Add(goroutines)
+
+	release := make(chan struct{})
+
+	for i := range goroutines {
+		key := string(rune('a' + i))
+
+		go func() {
+			defer wg.Done()
+
+			unlock := lock.Lock(key)
+			defer unlock()
+
+			inside.Add(1)
+
+			reached <- struct{}{}
+
+			<-release
+		}()
+	}
+
+	// Every goroutine must reach the rendezvous point (i.e. acquire its
+	// own key's lock) without needing any other to release first. If
+	// keys were incorrectly serialized onto one underlying lock, only
+	// one would get here and this would time out.
+	for i := range goroutines {
+		select {
+		case <-reached:
+		case <-time.After(2 * time.Second):
+			t.Fatalf("only %d/%d goroutines locking distinct keys made progress; "+
+				"keys may be incorrectly serialized", i, goroutines)
+		}
+	}
+
+	if n := inside.Load(); n != goroutines {
+		t.Errorf("goroutines inside their critical section = %d, want %d",
+			n, goroutines)
+	}
+
+	close(release)
+	wg.Wait()
+}
+
+// TestContentLockRemovesEntryAfterUnlock verifies that the internal
+// entries map does not grow without bound: once no goroutine holds or
+// awaits a key, its entry is removed.
+func TestContentLockRemovesEntryAfterUnlock(t *testing.T) {
+	t.Parallel()
+
+	lock := newContentLock()
+
+	unlock := lock.Lock("k")
+
+	lock.mu.Lock()
+	if _, ok := lock.entries["k"]; !ok {
+		lock.mu.Unlock()
+		t.Fatal("entry missing while lock is held")
+	}
+	lock.mu.Unlock()
+
+	unlock()
+
+	lock.mu.Lock()
+	defer lock.mu.Unlock()
+
+	if _, ok := lock.entries["k"]; ok {
+		t.Error("entry for key still present after the last holder unlocked")
+	}
+}

internal/imgcache/counters.go

@@ -1,45 +0,0 @@
-package imgcache
-
-import (
-	"fmt"
-
-	"github.com/prometheus/client_golang/prometheus"
-)
-
-// registerCounters makes the cache's counters and registers them on
-// metricsRegistry. The counters are kept in memory, so adding to one waits
-// for nothing and makes no database call. It fails when metricsRegistry
-// already holds counters of the same names.
-func (c *Cache) registerCounters(metricsRegistry prometheus.Registerer) error {
-	c.cacheHits = prometheus.NewCounter(prometheus.CounterOpts{
-		Name: "pixa_cache_hits_total",
-		Help: "Image requests served from the cache.",
-	})
-	c.cacheMisses = prometheus.NewCounter(prometheus.CounterOpts{
-		Name: "pixa_cache_misses_total",
-		Help: "Image requests not served from the cache.",
-	})
-	c.upstreamFetches = prometheus.NewCounter(prometheus.CounterOpts{
-		Name: "pixa_upstream_fetches_total",
-		Help: "Fetches of a source image from upstream that read any bytes.",
-	})
-	c.upstreamFetchBytes = prometheus.NewCounter(prometheus.CounterOpts{
-		Name: "pixa_upstream_fetch_bytes_total",
-		Help: "Bytes read from upstream by fetches of source images.",
-	})
-	c.transforms = prometheus.NewCounter(prometheus.CounterOpts{
-		Name: "pixa_transforms_total",
-		Help: "Images the image processor transformed.",
-	})
-
-	for _, counter := range []prometheus.Counter{
-		c.cacheHits, c.cacheMisses, c.upstreamFetches, c.upstreamFetchBytes, c.transforms,
-	} {
-		err := metricsRegistry.Register(counter)
-		if err != nil {
-			return fmt.Errorf("failed to register the cache's counters: %w", err)
-		}
-	}
-
-	return nil
-}

internal/imgcache/counters_internal_test.go

@@ -1,87 +0,0 @@
-package imgcache
-
-import (
-	"errors"
-	"testing"
-
-	"github.com/prometheus/client_golang/prometheus"
-	"github.com/prometheus/client_golang/prometheus/testutil"
-)
-
-// counterValues holds the values of a cache's counters.
-type counterValues struct {
-	hitCount           int64
-	missCount          int64
-	upstreamFetchCount int64
-	upstreamFetchBytes int64
-	transformCount     int64
-}
-
-// readCounters reads cache's counters.
-func readCounters(cache *Cache) counterValues {
-	return counterValues{
-		hitCount:           int64(testutil.ToFloat64(cache.cacheHits)),
-		missCount:          int64(testutil.ToFloat64(cache.cacheMisses)),
-		upstreamFetchCount: int64(testutil.ToFloat64(cache.upstreamFetches)),
-		upstreamFetchBytes: int64(testutil.ToFloat64(cache.upstreamFetchBytes)),
-		transformCount:     int64(testutil.ToFloat64(cache.transforms)),
-	}
-}
-
-// TestNewCache_RegistersItsCountersOnItsRegistry checks that NewCache
-// registers the cache's counters on the registry it is given, under the
-// names README.md gives them.
-func TestNewCache_RegistersItsCountersOnItsRegistry(t *testing.T) {
-	t.Parallel()
-
-	registry := prometheus.NewRegistry()
-
-	_, err := NewCache(evictionTestDB(t),
-		CacheConfig{StateDir: t.TempDir(), MaxBytes: 1 << 30}, registry)
-	if err != nil {
-		t.Fatalf("NewCache() error = %v", err)
-	}
-
-	names := []string{
-		"pixa_cache_hits_total",
-		"pixa_cache_misses_total",
-		"pixa_upstream_fetches_total",
-		"pixa_upstream_fetch_bytes_total",
-		"pixa_transforms_total",
-	}
-
-	count, err := testutil.GatherAndCount(registry, names...)
-	if err != nil {
-		t.Fatalf("testutil.GatherAndCount() error = %v", err)
-	}
-
-	if count != len(names) {
-		t.Errorf("%d of the counters %v are on the registry, want %d",
-			count, names, len(names))
-	}
-}
-
-// TestNewCache_FailsWhenItsCountersCannotBeRegistered makes a second cache
-// on the registry of a first. Its counters have the same names, so the
-// registry refuses them, and NewCache must return that error.
-func TestNewCache_FailsWhenItsCountersCannotBeRegistered(t *testing.T) {
-	t.Parallel()
-
-	registry := prometheus.NewRegistry()
-
-	_, err := NewCache(evictionTestDB(t),
-		CacheConfig{StateDir: t.TempDir(), MaxBytes: 1 << 30}, registry)
-	if err != nil {
-		t.Fatalf("NewCache() of the first cache error = %v", err)
-	}
-
-	_, err = NewCache(evictionTestDB(t),
-		CacheConfig{StateDir: t.TempDir(), MaxBytes: 1 << 30}, registry)
-	t.Logf("NewCache() of the second cache error = %v", err)
-
-	var alreadyRegistered prometheus.AlreadyRegisteredError
-	if !errors.As(err, &alreadyRegistered) {
-		t.Errorf("NewCache() of the second cache error = %v, want %T",
-			err, alreadyRegistered)
-	}
-}

internal/imgcache/eviction.go

@@ -3,6 +3,7 @@ package imgcache
 import (
 	"context"
 	"database/sql"
+	"encoding/json"
 	"errors"
 	"fmt"
 	"io/fs"
@@ -10,8 +11,6 @@ import (
 	"path/filepath"
 	"strings"
 	"time"
-
-	"sneak.berlin/go/pixa/internal/imagerequest"
 )
 
 // DefaultEvictionInterval is how often the background evictor checks
@@ -19,14 +18,6 @@ import (
 // write-pressure wakeups triggered by stores.
 const DefaultEvictionInterval = 5 * time.Minute
 
-// reconciliationWaitFactor is how many times as long as a
-// reconciliation pass took the eviction loop waits at least, after that
-// pass ends, before it starts the next one. A pass reads a row and stats a
-// file for every cached file, so its time grows with the cache; waiting
-// ten times as long keeps reconciliation to at most a tenth of the time,
-// however large the cache is.
-const reconciliationWaitFactor = 10
-
 // evictionBatchSize is how many LRU candidates of each class (variants
 // and source blobs) one eviction pass fetches from the database.
 const evictionBatchSize = 100
@@ -51,26 +42,27 @@ const sqliteTimestampLayout = "2006-01-02 15:04:05"
 // writes (".tmp-*" patterns in the storage layer).
 const tempFilePrefix = ".tmp-"
 
+// variantMetaSuffix is the sidecar suffix VariantStorage writes next
+// to each variant file.
+const variantMetaSuffix = ".meta"
+
+// fallbackContentType is the content type given to a variant file that
+// has no readable .meta sidecar, when it is served or reconciled.
+const fallbackContentType = "application/octet-stream"
+
 // UsageBytes returns the total number of bytes of cache content
-// tracked in the database, as the package function UsageBytes does, or 0
+// tracked in the database (source content blobs plus processed
-// when the disk cache is off.
+// variants). It reads the total the database keeps up to date as rows
+// are added and removed, so it neither scans the cache directories nor
+// sums the tables.
 func (c *Cache) UsageBytes(ctx context.Context) (int64, error) {
-	if c.config.MaxBytes == 0 {
+	if c.disabled {
 		return 0, nil
 	}
 
-	return UsageBytes(ctx, c.db)
-}
-
-// UsageBytes returns the total number of bytes of cache content tracked
-// in db (source content blobs plus processed variants). It reads the
-// total the database keeps up to date as rows are added and removed, so
-// it neither scans the cache directories nor sums the tables. pixad reads
-// it before it builds the cache, to work out the default cache_max_bytes.
-func UsageBytes(ctx context.Context, db *sql.DB) (int64, error) {
 	var total int64
 
-	err := db.QueryRowContext(ctx,
+	err := c.db.QueryRowContext(ctx,
 		`SELECT total_size_bytes FROM cache_usage WHERE id = 1`,
 	).Scan(&total)
 	if err != nil {
@@ -82,20 +74,20 @@ func UsageBytes(ctx context.Context, db *sql.DB) (int64, error) {
 
 // evictionCandidate is one LRU eviction victim candidate: either a
 // processed variant (isVariant true, identified by cacheKey) or a
-// source content blob (identified by sourceKey).
+// source content blob (identified by contentHash).
 type evictionCandidate struct {
 	isVariant      bool
-	cacheKey       imagerequest.VariantKey
+	cacheKey       VariantKey
-	sourceKey      imagerequest.SourceKey
+	contentHash    ContentHash
 	sizeBytes      int64
 	lastAccessedAt string
 }
 
 // EvictToLimit evicts least-recently-used cache entries until total
 // tracked usage is at or below the configured MaxBytes limit. It is a
-// no-op when the cache is disabled.
+// no-op when the cache is disabled or no limit is configured.
 func (c *Cache) EvictToLimit(ctx context.Context) error {
-	if c.config.MaxBytes == 0 {
+	if c.disabled || c.config.MaxBytes <= 0 {
 		return nil
 	}
 
@@ -158,7 +150,7 @@ func (c *Cache) evictBatch(ctx context.Context, excessBytes int64) (int64, error
 
 			c.log.Warn("failed to evict cache entry",
 				"cache_key", candidate.cacheKey,
-				"source_key", candidate.sourceKey,
+				"content_hash", candidate.contentHash,
 				"error", err,
 			)
 
@@ -177,7 +169,7 @@ func (c *Cache) evictCandidate(ctx context.Context, candidate evictionCandidate)
 		return c.evictVariant(ctx, candidate.cacheKey)
 	}
 
-	return c.evictSourceBlob(ctx, candidate.sourceKey)
+	return c.evictSourceBlob(ctx, candidate.contentHash)
 }
 
 // evictionCandidates returns up to evictionBatchSize variants and
@@ -240,7 +232,7 @@ func (c *Cache) variantCandidates(ctx context.Context) ([]evictionCandidate, err
 			return nil, fmt.Errorf("failed to scan variant candidate: %w", err)
 		}
 
-		candidate.cacheKey = imagerequest.VariantKey(key)
+		candidate.cacheKey = VariantKey(key)
 		candidates = append(candidates, candidate)
 	}
 
@@ -257,9 +249,9 @@ func (c *Cache) variantCandidates(ctx context.Context) ([]evictionCandidate, err
 // SQLite reads the rows in order from that column's index instead of
 // sorting the whole table.
 const sourceCandidatesQuery = `
-	SELECT source_key, size_bytes, last_accessed_at
+	SELECT content_hash, size_bytes, last_accessed_at
 	FROM source_content
-	ORDER BY last_accessed_at ASC, source_key ASC
+	ORDER BY last_accessed_at ASC, content_hash ASC
 	LIMIT ?`
 
 // sourceCandidates returns the least recently used source blobs.
@@ -276,14 +268,14 @@ func (c *Cache) sourceCandidates(ctx context.Context) ([]evictionCandidate, erro
 	for rows.Next() {
 		var candidate evictionCandidate
 
-		var key string
+		var hash string
 
-		err := rows.Scan(&key, &candidate.sizeBytes, &candidate.lastAccessedAt)
+		err := rows.Scan(&hash, &candidate.sizeBytes, &candidate.lastAccessedAt)
 		if err != nil {
 			return nil, fmt.Errorf("failed to scan source candidate: %w", err)
 		}
 
-		candidate.sourceKey = imagerequest.SourceKey(key)
+		candidate.contentHash = ContentHash(hash)
 		candidates = append(candidates, candidate)
 	}
 
@@ -296,16 +288,19 @@ func (c *Cache) sourceCandidates(ctx context.Context) ([]evictionCandidate, erro
 }
 
 // evictVariant removes one variant: accounting row first, then the
-// file, so the database never references a deleted file.
+// content and .meta files, so the database never references a deleted
-func (c *Cache) evictVariant(
+// file. The metaCache entry goes before the files; a GetVariant that
-	ctx context.Context, cacheKey imagerequest.VariantKey,
+// read them just before may put it back, and the next GetVariant then
-) error {
+// fails to open the file and removes it again.
+func (c *Cache) evictVariant(ctx context.Context, cacheKey VariantKey) error {
 	_, err := c.db.ExecContext(ctx,
 		`DELETE FROM variant_content WHERE cache_key = ?`, string(cacheKey))
 	if err != nil {
 		return fmt.Errorf("failed to delete variant accounting row: %w", err)
 	}
 
+	c.metaCache.Remove(cacheKey)
+
 	err = c.variants.Delete(cacheKey)
 	if err != nil {
 		return err
@@ -314,18 +309,117 @@ func (c *Cache) evictVariant(
 	return nil
 }
 
-// evictSourceBlob removes one source: its row first, then its file, as
+// sourceReference identifies one source_metadata row's JSON sidecar.
-// evictVariant does for a variant. It holds no lock: a store of the same
+type sourceReference struct {
-// source in between can leave the source's row with no file, which
+	host     string
-// LookupSource treats as a miss.
+	pathHash PathHash
-func (c *Cache) evictSourceBlob(ctx context.Context, key imagerequest.SourceKey) error {
+}
-	_, err := c.db.ExecContext(ctx,
+
-		`DELETE FROM source_content WHERE source_key = ?`, string(key))
+// evictSourceBlob removes one source content blob. All source_metadata
+// rows referencing the blob are deleted together with its
+// source_content row in a single transaction BEFORE the file is
+// unlinked: a blob referenced by multiple source paths is only ever
+// removed together with all of its references, and database rows never
+// point at deleted files. The JSON metadata sidecars for the removed
+// rows are deleted afterwards.
+//
+// The whole operation holds the content hash's lock (the same one
+// StoreSource holds for its full store), so a concurrent store of
+// identical content bytes can never observe the file gone but a row
+// still present, or insert a fresh row between this transaction's
+// commit and the file unlink below: it either runs entirely before
+// this eviction starts, or is blocked until this eviction (row
+// deletion and unlink together) has fully completed.
+func (c *Cache) evictSourceBlob(ctx context.Context, contentHash ContentHash) error {
+	unlock := c.contentLocks.Lock(string(contentHash))
+	defer unlock()
+
+	references, err := c.sourceReferences(ctx, contentHash)
+	if err != nil {
+		return err
+	}
+
+	tx, err := c.db.BeginTx(ctx, nil)
+	if err != nil {
+		return fmt.Errorf("failed to begin eviction transaction: %w", err)
+	}
+
+	defer func() { _ = tx.Rollback() }()
+
+	_, err = tx.ExecContext(ctx,
+		`DELETE FROM source_metadata WHERE content_hash = ?`, string(contentHash))
+	if err != nil {
+		return fmt.Errorf("failed to delete source metadata rows: %w", err)
+	}
+
+	_, err = tx.ExecContext(ctx,
+		`DELETE FROM source_content WHERE content_hash = ?`, string(contentHash))
 	if err != nil {
 		return fmt.Errorf("failed to delete source content row: %w", err)
 	}
 
-	return c.srcContent.Delete(key)
+	err = tx.Commit()
+	if err != nil {
+		return fmt.Errorf("failed to commit eviction transaction: %w", err)
+	}
+
+	if c.evictSourceBlobTestHook != nil {
+		c.evictSourceBlobTestHook(contentHash)
+	}
+
+	// Only after the rows are gone may the files be removed.
+	for _, reference := range references {
+		err := c.srcMetadata.Delete(reference.host, reference.pathHash)
+		if err != nil {
+			c.log.Warn("failed to delete metadata sidecar",
+				"host", reference.host, "path_hash", reference.pathHash, "error", err)
+		}
+	}
+
+	err = c.srcContent.Delete(contentHash)
+	if err != nil {
+		return err
+	}
+
+	return nil
+}
+
+// sourceReferences lists the metadata sidecar locations of every
+// source_metadata row referencing the given blob.
+func (c *Cache) sourceReferences(
+	ctx context.Context, contentHash ContentHash,
+) ([]sourceReference, error) {
+	rows, err := c.db.QueryContext(ctx, `
+		SELECT source_host, path_hash FROM source_metadata WHERE content_hash = ?
+	`, string(contentHash))
+	if err != nil {
+		return nil, fmt.Errorf("failed to query source references: %w", err)
+	}
+
+	defer func() { _ = rows.Close() }()
+
+	var references []sourceReference
+
+	for rows.Next() {
+		var reference sourceReference
+
+		var pathHash string
+
+		err := rows.Scan(&reference.host, &pathHash)
+		if err != nil {
+			return nil, fmt.Errorf("failed to scan source reference: %w", err)
+		}
+
+		reference.pathHash = PathHash(pathHash)
+		references = append(references, reference)
+	}
+
+	err = rows.Err()
+	if err != nil {
+		return nil, fmt.Errorf("source reference iteration failed: %w", err)
+	}
+
+	return references, nil
 }
 
 // notifyWritePressure wakes the background evictor after a store, so
@@ -333,7 +427,7 @@ func (c *Cache) evictSourceBlob(ctx context.Context, key imagerequest.SourceKey)
 // storing request. The notification channel has capacity one and drops
 // when a wakeup is already pending.
 func (c *Cache) notifyWritePressure() {
-	if c.config.MaxBytes == 0 {
+	if c.disabled || c.config.MaxBytes <= 0 {
 		return
 	}
 
@@ -344,12 +438,10 @@ func (c *Cache) notifyWritePressure() {
 }
 
 // StartEviction launches the background eviction goroutine, which
+// reconciles the database accounting with the cache directories and
 // removes the expired negative cache rows at startup and again on every
-// periodic tick thereafter, reconciles the database accounting with the
+// periodic tick thereafter, and evicts to the configured limit on the
-// cache directories at startup and again on the first periodic tick
+// given periodic interval and on write-pressure notifications. On a
-// that comes at least ten times as long after a reconciliation pass
-// ended as that pass took, and evicts to the configured limit on the given
-// periodic interval and on write-pressure notifications. On a
 // disabled cache it only removes the expired negative cache rows, as
 // the negative cache is used either way. It is a no-op when already
 // started. The goroutine outlives the caller, so it runs with its own
@@ -390,7 +482,7 @@ func (c *Cache) StopEviction(ctx context.Context) error {
 func (c *Cache) evictionLoop(ctx context.Context, interval time.Duration) {
 	defer close(c.evictionDone)
 
-	nextReconciliation := c.runReconciliationPass(ctx)
+	c.runReconciliationPass(ctx)
 	c.runCleanExpired(ctx)
 	c.runEvictionPass(ctx)
 
@@ -402,20 +494,16 @@ func (c *Cache) evictionLoop(ctx context.Context, interval time.Duration) {
 		case <-ctx.Done():
 			return
 		case <-ticker.C:
-			// Reconciliation walks the cache directories and reads a
+			// Reconciliation walks the cache directories, so it only
-			// row for every file, so it runs only on the periodic
+			// runs on the periodic ticker rather than on every
-			// ticker rather than on every write-pressure wakeup, and
+			// write-pressure wakeup, keeping it off the per-store hot
-			// only on the first tick at or after nextReconciliation,
+			// path. Reusing the eviction interval itself (rather than a
-			// which is ten times as long after the last pass ended as
+			// separate, longer one) is a deliberate choice: it is the
-			// that pass took. Passes then never run back to back,
+			// simplest option that still bounds how long a store's
-			// however long one takes. A file whose best-effort
+			// best-effort accounting insert can stay silently
-			// accounting insert failed in a store stays unaccounted for
+			// unaccounted for to one interval, on a process that is
-			// until the next pass, up to about one eviction interval
+			// already running this loop regardless.
-			// plus ten times the last pass's time.
+			c.runReconciliationPass(ctx)
-			if !time.Now().Before(nextReconciliation) {
-				nextReconciliation = c.runReconciliationPass(ctx)
-			}
-
 			c.runCleanExpired(ctx)
 		case <-c.evictionPressure:
 		}
@@ -439,25 +527,17 @@ func (c *Cache) runEvictionPass(ctx context.Context) {
 }
 
 // runReconciliationPass runs one reconciliation pass, logging failures
-// instead of propagating them (the loop must keep running), and returns
+// instead of propagating them (the loop must keep running). It does
-// the earliest time the next pass may start: reconciliationWaitFactor
+// nothing once ctx is cancelled.
-// times as long after this pass ended as it took. It does nothing once
+func (c *Cache) runReconciliationPass(ctx context.Context) {
-// ctx is cancelled.
-func (c *Cache) runReconciliationPass(ctx context.Context) time.Time {
 	if ctx.Err() != nil {
-		return time.Now()
+		return
 	}
 
-	started := time.Now()
-
 	err := c.reconcileAccounting(ctx)
 	if err != nil {
 		c.log.Warn("cache accounting reconciliation failed", "error", err)
 	}
-
-	ended := time.Now()
-
-	return ended.Add(reconciliationWaitFactor * ended.Sub(started))
 }
 
 // runCleanExpired runs CleanExpired, logging a failure instead of
@@ -476,23 +556,21 @@ func (c *Cache) runCleanExpired(ctx context.Context) {
 
 // reconcileAccounting synchronizes the database size accounting with
 // the actual contents of the cache directories. It runs at startup and
-// then on the first periodic eviction tick that comes at least ten times
+// again on every periodic eviction tick thereafter, off the request
-// as long after the last pass ended as that pass took, off the request
 // hot path: it adopts variant files that predate the accounting table
 // (or whose accounting insert failed, e.g. StoreVariant's best-effort
-// insert under transient DB contention), drops variant accounting rows
+// insert under transient DB contention), drops accounting rows whose
-// whose files are missing, removes source blob files the database does
+// files are missing, removes source blob files the database does not
-// not know, removes source and variant files that are empty or not the
+// know (and rows whose files are gone), removes source and variant files
-// size their rows record, sweeps stale temp files left behind by crashed
+// that are empty or not the size their rows record, sweeps stale temp
-// writes, and last checks the total cache usage against the tables. It
+// files left behind by crashed writes, and last checks the total cache
-// reads the tables a page at a time.
+// usage against the tables. It reads the tables a page at a time.
 // Running it periodically, not just once, bounds how long such drift can
-// accumulate unaccounted for on a long-running process to about one
+// accumulate unaccounted for on a long-running process to one eviction
-// eviction interval plus ten times the last pass's time.
+// interval. Once ctx is cancelled, it stops at the next file or row and
-// Once ctx is cancelled, it stops at the next file or row and returns
+// returns ctx's error.
-// ctx's error.
 func (c *Cache) reconcileAccounting(ctx context.Context) error {
-	if c.config.MaxBytes == 0 {
+	if c.disabled {
 		return nil
 	}
 
@@ -511,19 +589,20 @@ func (c *Cache) reconcileAccounting(ctx context.Context) error {
 		return err
 	}
 
+	err = c.reconcileSourceRows(ctx)
+	if err != nil {
+		return err
+	}
+
 	return c.reconcileUsageTotal(ctx)
 }
 
-// reconcileFiles walks baseDir, one of the cache's storage directories,
+// reconcileVariantFiles walks the variant storage directory, checking
-// sweeping stale temp files and passing each other file, with its name, to
+// each variant file against its accounting row (reconcileVariantFile)
-// reconcileFile. Once ctx is cancelled it stops at the next file and
+// and sweeping stale temp files.
-// returns ctx's error.
+func (c *Cache) reconcileVariantFiles(ctx context.Context) error {
-func (c *Cache) reconcileFiles(
-	ctx context.Context, baseDir string,
-	reconcileFile func(path string, entry fs.DirEntry, name string) error,
-) error {
 	return filepath.WalkDir(
-		baseDir,
+		c.variants.baseDir,
 		func(path string, entry fs.DirEntry, err error) error {
 			if ctx.Err() != nil {
 				return ctx.Err()
@@ -541,28 +620,22 @@ func (c *Cache) reconcileFiles(
 				return nil
 			}
 
-			return reconcileFile(path, entry, name)
+			if strings.HasSuffix(name, variantMetaSuffix) {
+				return nil
+			}
+
+			return c.reconcileVariantFile(ctx, path, entry, VariantKey(name))
 		},
 	)
 }
 
-// reconcileVariantFiles walks the variant storage directory, checking
-// each variant file against its accounting row (reconcileVariantFile)
-// and sweeping stale temp files.
-func (c *Cache) reconcileVariantFiles(ctx context.Context) error {
-	return c.reconcileFiles(ctx, c.variants.baseDir,
-		func(path string, entry fs.DirEntry, name string) error {
-			return c.reconcileVariantFile(ctx, path, entry, imagerequest.VariantKey(name))
-		})
-}
-
 // reconcileVariantFile checks one variant file against its accounting
 // row. A file without a row is adopted into the accounting, unless it is
 // empty. A file that is empty, or not the size its row records, as a
 // crash or a restored snapshot can leave it, is removed with its row and
 // a warning naming it, so the variant is converted again.
 func (c *Cache) reconcileVariantFile(
-	ctx context.Context, path string, entry fs.DirEntry, cacheKey imagerequest.VariantKey,
+	ctx context.Context, path string, entry fs.DirEntry, cacheKey VariantKey,
 ) error {
 	info, err := entry.Info()
 	if err != nil {
@@ -577,7 +650,7 @@ func (c *Cache) reconcileVariantFile(
 
 	switch {
 	case errors.Is(err, sql.ErrNoRows) && info.Size() > 0:
-		return c.adoptVariantFile(ctx, info, cacheKey)
+		return c.adoptVariantFile(ctx, path, info, cacheKey)
 	case err != nil && !errors.Is(err, sql.ErrNoRows):
 		return fmt.Errorf("failed to check variant accounting row: %w", err)
 	case info.Size() > 0 && info.Size() == recordedSize:
@@ -594,14 +667,16 @@ func (c *Cache) reconcileVariantFile(
 // adoptVariantFile inserts an accounting row for a variant file that
 // has none, using the file's size and modification time.
 func (c *Cache) adoptVariantFile(
-	ctx context.Context, info fs.FileInfo, cacheKey imagerequest.VariantKey,
+	ctx context.Context, path string, info fs.FileInfo, cacheKey VariantKey,
 ) error {
 	modTime := info.ModTime().UTC().Format(sqliteTimestampLayout)
+	contentType := c.variantContentTypeFromSidecar(path)
 
 	_, err := c.db.ExecContext(ctx, `
-		INSERT INTO variant_content (cache_key, size_bytes, last_accessed_at)
+		INSERT INTO variant_content
-		VALUES (?, ?, ?)
+			(cache_key, size_bytes, content_type, created_at, last_accessed_at)
-	`, string(cacheKey), info.Size(), modTime)
+		VALUES (?, ?, ?, ?, ?)
+	`, string(cacheKey), info.Size(), contentType, modTime, modTime)
 	if err != nil {
 		return fmt.Errorf("failed to adopt variant file into accounting: %w", err)
 	}
@@ -612,10 +687,27 @@ func (c *Cache) adoptVariantFile(
 	return nil
 }
 
+// variantContentTypeFromSidecar reads the content type from a variant
+// .meta sidecar, falling back to application/octet-stream.
+func (c *Cache) variantContentTypeFromSidecar(variantPath string) string {
+	//nolint:gosec // path from cache walk
+	metaData, err := os.ReadFile(variantPath + variantMetaSuffix)
+	if err != nil {
+		return fallbackContentType
+	}
+
+	var meta VariantMeta
+	if json.Unmarshal(metaData, &meta) != nil || meta.ContentType == "" {
+		return fallbackContentType
+	}
+
+	return meta.ContentType
+}
+
 // reconcileVariantRows drops accounting rows whose variant files are
 // missing, so the database never references deleted content.
 func (c *Cache) reconcileVariantRows(ctx context.Context) error {
-	var after imagerequest.VariantKey
+	var after VariantKey
 
 	for {
 		keys, err := c.variantKeysAfter(ctx, after)
@@ -656,9 +748,9 @@ func (c *Cache) reconcileVariantRows(ctx context.Context) error {
 // variantKeysAfter returns, in order, up to c.reconciliationPageSize
 // tracked variant cache keys that sort after the given one.
 func (c *Cache) variantKeysAfter(
-	ctx context.Context, after imagerequest.VariantKey,
+	ctx context.Context, after VariantKey,
-) ([]imagerequest.VariantKey, error) {
+) ([]VariantKey, error) {
-	return queryStringColumn[imagerequest.VariantKey](ctx, c.db, `
+	return queryStringColumn[VariantKey](ctx, c.db, `
 		SELECT cache_key FROM variant_content
 		WHERE cache_key > ? ORDER BY cache_key LIMIT ?
 	`, "variant keys", "variant key", string(after), c.reconciliationPageSize)
@@ -703,20 +795,38 @@ func queryStringColumn[T ~string](
 // each blob file against its source_content row (reconcileSourceFile)
 // and sweeping stale temp files.
 func (c *Cache) reconcileSourceFiles(ctx context.Context) error {
-	return c.reconcileFiles(ctx, c.srcContent.baseDir,
+	return filepath.WalkDir(
-		func(path string, entry fs.DirEntry, name string) error {
+		c.srcContent.baseDir,
-			return c.reconcileSourceFile(ctx, path, entry, imagerequest.SourceKey(name))
+		func(path string, entry fs.DirEntry, err error) error {
-		})
+			if ctx.Err() != nil {
+				return ctx.Err()
+			}
+
+			if err != nil || entry.IsDir() {
+				return err
+			}
+
+			name := entry.Name()
+
+			if strings.HasPrefix(name, tempFilePrefix) {
+				c.sweepStaleTempFile(path, entry)
+
+				return nil
+			}
+
+			return c.reconcileSourceFile(ctx, path, entry, ContentHash(name))
+		},
+	)
 }
 
 // reconcileSourceFile checks one source blob file against its
-// source_content row. A file without a row is removed, as no lookup
+// source_content row. A file without a row is removed: it is
-// serves it and no eviction removes it. A file that is empty, or not the
+// unreachable, as source lookups always go through source_metadata. A
-// size its row records, as a crash or a restored snapshot can leave it,
+// file that is empty, or not the size its row records, as a crash or a
-// is removed with its row and a warning naming it, so the source is
+// restored snapshot can leave it, is removed with its rows and a warning
-// fetched again.
+// naming it, so the source is fetched again.
 func (c *Cache) reconcileSourceFile(
-	ctx context.Context, path string, entry fs.DirEntry, key imagerequest.SourceKey,
+	ctx context.Context, path string, entry fs.DirEntry, contentHash ContentHash,
 ) error {
 	info, err := entry.Info()
 	if err != nil {
@@ -726,13 +836,13 @@ func (c *Cache) reconcileSourceFile(
 	var recordedSize int64
 
 	err = c.db.QueryRowContext(ctx,
-		`SELECT size_bytes FROM source_content WHERE source_key = ?`,
+		`SELECT size_bytes FROM source_content WHERE content_hash = ?`,
-		string(key),
+		string(contentHash),
 	).Scan(&recordedSize)
 
 	switch {
 	case errors.Is(err, sql.ErrNoRows):
-		return c.removeUntrackedSourceFile(path, key)
+		return c.removeUntrackedSourceFile(ctx, path, contentHash)
 	case err != nil:
 		return fmt.Errorf("failed to check source content row: %w", err)
 	case info.Size() > 0 && info.Size() == recordedSize:
@@ -743,34 +853,96 @@ func (c *Cache) reconcileSourceFile(
 	c.log.Warn("removing damaged cached source file", "path", path,
 		"file_bytes", info.Size(), "recorded_bytes", recordedSize)
 
-	return c.evictSourceBlob(ctx, key)
+	return c.evictSourceBlob(ctx, contentHash)
 }
 
 // removeUntrackedSourceFile deletes a source blob file that has no
-// source_content row.
+// source_content row. Any source_metadata rows referencing the hash
+// are removed first so no row ever points at a deleted file.
 func (c *Cache) removeUntrackedSourceFile(
-	path string, key imagerequest.SourceKey,
+	ctx context.Context, path string, contentHash ContentHash,
 ) error {
-	err := os.Remove(path)
+	_, err := c.db.ExecContext(ctx,
+		`DELETE FROM source_metadata WHERE content_hash = ?`, string(contentHash))
+	if err != nil {
+		return fmt.Errorf("failed to delete metadata rows for untracked blob: %w", err)
+	}
+
+	err = os.Remove(path)
 	if err != nil && !os.IsNotExist(err) {
 		return fmt.Errorf("failed to remove untracked source file: %w", err)
 	}
 
-	c.log.Info("removed untracked source content file", "source_key", key)
+	c.log.Info("removed untracked source content file", "content_hash", contentHash)
 
 	return nil
 }
 
+// reconcileSourceRows removes source_content rows (and their metadata
+// references and sidecars) whose blob files are missing on disk.
+func (c *Cache) reconcileSourceRows(ctx context.Context) error {
+	var after ContentHash
+
+	for {
+		hashes, err := c.sourceContentHashesAfter(ctx, after)
+		if err != nil {
+			return err
+		}
+
+		if c.reconciliationReadTestHook != nil {
+			c.reconciliationReadTestHook(len(hashes))
+		}
+
+		if len(hashes) == 0 {
+			return nil
+		}
+
+		for _, hash := range hashes {
+			if ctx.Err() != nil {
+				return ctx.Err()
+			}
+
+			if c.srcContent.Exists(hash) {
+				continue
+			}
+
+			// The blob file is already gone; evictSourceBlob removes the
+			// rows and sidecars and tolerates the missing file.
+			err := c.evictSourceBlob(ctx, hash)
+			if err != nil {
+				return err
+			}
+
+			c.log.Info("dropped rows for missing source content file", "content_hash", hash)
+		}
+
+		after = hashes[len(hashes)-1]
+	}
+}
+
+// sourceContentHashesAfter returns, in order, up to
+// c.reconciliationPageSize tracked source content hashes that sort after
+// the given one.
+func (c *Cache) sourceContentHashesAfter(
+	ctx context.Context, after ContentHash,
+) ([]ContentHash, error) {
+	return queryStringColumn[ContentHash](ctx, c.db, `
+		SELECT content_hash FROM source_content
+		WHERE content_hash > ? ORDER BY content_hash LIMIT ?
+	`, "source content hashes", "content hash", string(after),
+		c.reconciliationPageSize)
+}
+
 // Each of these queries sums size_bytes over the next page of rows of
 // one content table, the rows that sort after a key, and returns the
 // page's last key, the sum and the number of rows in the page. Past the
 // last row the page has no rows and the key is NULL.
 const (
 	sourceSizePageQuery = `
-		SELECT MAX(source_key), COALESCE(SUM(size_bytes), 0), COUNT(*)
+		SELECT MAX(content_hash), COALESCE(SUM(size_bytes), 0), COUNT(*)
 		FROM (
-			SELECT source_key, size_bytes FROM source_content
+			SELECT content_hash, size_bytes FROM source_content
-			WHERE source_key > ? ORDER BY source_key LIMIT ?
+			WHERE content_hash > ? ORDER BY content_hash LIMIT ?
 		)`
 	variantSizePageQuery = `
 		SELECT MAX(cache_key), COALESCE(SUM(size_bytes), 0), COUNT(*)

internal/imgcache/eviction_internal_test.go

@@ -10,14 +10,12 @@ import (
 	"os"
 	"path/filepath"
 	"strings"
-	"sync"
 	"testing"
 	"time"
 
-	"github.com/prometheus/client_golang/prometheus"
+	_ "modernc.org/sqlite"
-	"modernc.org/sqlite"
 	"sneak.berlin/go/pixa/internal/database"
-	"sneak.berlin/go/pixa/internal/imagerequest"
+	"sneak.berlin/go/pixa/internal/httpfetcher"
 )
 
 // sqliteTimestampFormat matches the format SQLite's CURRENT_TIMESTAMP
@@ -29,10 +27,10 @@ const sqliteTimestampFormat = "2006-01-02 15:04:05"
 // keys reused across the eviction tests, in the order the tests store
 // them.
 const (
-	testVariantKeyOne   imagerequest.VariantKey = "aabbccdd0001"
+	testVariantKeyOne   VariantKey = "aabbccdd0001"
-	testVariantKeyTwo   imagerequest.VariantKey = "aabbccdd0002"
+	testVariantKeyTwo   VariantKey = "aabbccdd0002"
-	testVariantKeyThree imagerequest.VariantKey = "aabbccdd0003"
+	testVariantKeyThree VariantKey = "aabbccdd0003"
-	testVariantKeyFour  imagerequest.VariantKey = "aabbccdd0004"
+	testVariantKeyFour  VariantKey = "aabbccdd0004"
 )
 
 // evictionTestDB creates an in-memory SQLite database with the real
@@ -66,12 +64,16 @@ func newEvictionTestCache(t *testing.T, maxBytes int64) (*Cache, string) {
 	tmpDir := t.TempDir()
 	db := evictionTestDB(t)
 
-	// maxBytes zero turns the disk cache off, as cache_max_bytes: 0 does.
+	// maxBytes zero mirrors the production mapping of
+	// cache_max_bytes: 0 (handlers sets DisableDiskCache); at the
+	// CacheConfig layer itself a zero MaxBytes means "no limit" for
+	// backwards compatibility with existing fixtures.
 	cache, err := NewCache(db, CacheConfig{
-		StateDir:    tmpDir,
+		StateDir:         tmpDir,
-		NegativeTTL: 5 * time.Minute,
+		NegativeTTL:      5 * time.Minute,
-		MaxBytes:    maxBytes,
+		MaxBytes:         maxBytes,
-	}, prometheus.NewRegistry())
+		DisableDiskCache: maxBytes == 0,
+	})
 	if err != nil {
 		t.Fatalf("failed to create cache: %v", err)
 	}
@@ -80,42 +82,47 @@ func newEvictionTestCache(t *testing.T, maxBytes int64) (*Cache, string) {
 }
 
 // storeEvictionTestSource stores content as a fetched source for
-// host/path and returns the resulting source key.
+// host/path and returns the resulting content hash.
 func storeEvictionTestSource(
 	t *testing.T, cache *Cache, host, path string, content []byte,
-) imagerequest.SourceKey {
+) ContentHash {
 	t.Helper()
 
-	req := &imagerequest.Request{
+	req := &ImageRequest{
-		Source: imagerequest.Source{
+		SourceHost: host,
-			Host: host,
+		SourcePath: path,
-			Path: path,
+		Format:     FormatJPEG,
-		},
+		Quality:    85,
-		Transform: imagerequest.Transform{
+		FitMode:    FitCover,
-			Format:  imagerequest.FormatJPEG,
+	}
-			Quality: 85,
+
-			FitMode: imagerequest.FitCover,
+	result := &httpfetcher.FetchResult{
+		StatusCode:    200,
+		ContentType:   testContentTypeJPEG,
+		ContentLength: int64(len(content)),
+		Headers: map[string][]string{
+			testHeaderContentType: {testContentTypeJPEG},
 		},
 	}
 
-	key, err := cache.StoreSource(
+	hash, err := cache.StoreSource(
-		context.Background(), req, bytes.NewReader(content),
+		context.Background(), req, bytes.NewReader(content), result,
 	)
 	if err != nil {
 		t.Fatalf("StoreSource(%s%s) failed: %v", host, path, err)
 	}
 
-	return key
+	return hash
 }
 
 // storeEvictionTestVariant stores content as a processed variant under
 // the given cache key.
 func storeEvictionTestVariant(
-	t *testing.T, cache *Cache, key imagerequest.VariantKey, content []byte,
+	t *testing.T, cache *Cache, key VariantKey, content []byte,
 ) {
 	t.Helper()
 
-	err := cache.StoreVariant(t.Context(), key, bytes.NewReader(content))
+	err := cache.StoreVariant(t.Context(), key, bytes.NewReader(content), "image/webp")
 	if err != nil {
 		t.Fatalf("StoreVariant(%s) failed: %v", key, err)
 	}
@@ -124,7 +131,7 @@ func storeEvictionTestVariant(
 // setVariantLastAccessed backdates the last access time of a tracked
 // variant, to make LRU ordering deterministic in tests.
 func setVariantLastAccessed(
-	t *testing.T, cache *Cache, key imagerequest.VariantKey, when time.Time,
+	t *testing.T, cache *Cache, key VariantKey, when time.Time,
 ) {
 	t.Helper()
 
@@ -150,13 +157,13 @@ func setVariantLastAccessed(
 // setSourceLastAccessed backdates the last access time of a tracked
 // source content blob.
 func setSourceLastAccessed(
-	t *testing.T, cache *Cache, key imagerequest.SourceKey, when time.Time,
+	t *testing.T, cache *Cache, hash ContentHash, when time.Time,
 ) {
 	t.Helper()
 
 	res, err := cache.db.ExecContext(t.Context(),
-		`UPDATE source_content SET last_accessed_at = ? WHERE source_key = ?`,
+		`UPDATE source_content SET last_accessed_at = ? WHERE content_hash = ?`,
-		when.UTC().Format(sqliteTimestampFormat), string(key),
+		when.UTC().Format(sqliteTimestampFormat), string(hash),
 	)
 	if err != nil {
 		t.Fatalf("failed to set source last_accessed_at: %v", err)
@@ -168,7 +175,7 @@ func setSourceLastAccessed(
 	}
 
 	if affected != 1 {
-		t.Fatalf("source %s has no accounting row (affected=%d)", key, affected)
+		t.Fatalf("source %s has no accounting row (affected=%d)", hash, affected)
 	}
 }
 
@@ -193,31 +200,32 @@ func assertNoDanglingReferences(t *testing.T, cache *Cache) {
 	t.Helper()
 
 	rows, err := cache.db.QueryContext(t.Context(),
-		`SELECT source_key FROM source_content`,
+		`SELECT content_hash FROM source_metadata
+		 WHERE content_hash IS NOT NULL AND content_hash != ''`,
 	)
 	if err != nil {
-		t.Fatalf("failed to query source_content: %v", err)
+		t.Fatalf("failed to query source_metadata: %v", err)
 	}
 
 	defer func() { _ = rows.Close() }()
 
 	for rows.Next() {
-		var key string
+		var hash string
 
-		err := rows.Scan(&key)
+		err := rows.Scan(&hash)
 		if err != nil {
-			t.Fatalf("failed to scan source_key: %v", err)
+			t.Fatalf("failed to scan content_hash: %v", err)
 		}
 
-		if !cache.srcContent.Exists(imagerequest.SourceKey(key)) {
+		if !cache.srcContent.Exists(ContentHash(hash)) {
-			t.Errorf("source_content references content %s but the file is missing",
+			t.Errorf("source_metadata references content %s but the file is missing",
-				key)
+				hash)
 		}
 	}
 
 	err = rows.Err()
 	if err != nil {
-		t.Fatalf("source_content iteration failed: %v", err)
+		t.Fatalf("source_metadata iteration failed: %v", err)
 	}
 
 	variantRows, err := cache.db.QueryContext(t.Context(),
@@ -236,7 +244,7 @@ func assertNoDanglingReferences(t *testing.T, cache *Cache) {
 			t.Fatalf("failed to scan cache_key: %v", err)
 		}
 
-		if !cache.variants.Exists(imagerequest.VariantKey(key)) {
+		if !cache.variants.Exists(VariantKey(key)) {
 			t.Errorf("variant_content references key %s but the file is missing", key)
 		}
 	}
@@ -300,6 +308,33 @@ func TestUsageBytesAccountsSourceAndVariantBytes(t *testing.T) {
 	}
 }
 
+func TestUsageBytesCountsMultiReferencedBlobOnce(t *testing.T) {
+	t.Parallel()
+
+	cache, _ := newEvictionTestCache(t, 1<<30)
+
+	content := bytes.Repeat([]byte{0xCC}, 1200)
+
+	hashOne := storeEvictionTestSource(t, cache,
+		"src.example.com", "/one.jpg", content)
+	hashTwo := storeEvictionTestSource(t, cache,
+		"src.example.com", "/two.jpg", content)
+
+	if hashOne != hashTwo {
+		t.Fatalf("identical content produced different hashes: %s vs %s",
+			hashOne, hashTwo)
+	}
+
+	usage, err := cache.UsageBytes(context.Background())
+	if err != nil {
+		t.Fatalf("UsageBytes failed: %v", err)
+	}
+
+	if usage != 1200 {
+		t.Errorf("UsageBytes = %d, want 1200 (deduplicated blob counted once)", usage)
+	}
+}
+
 func TestEvictToLimitEvictsLeastRecentlyUsedFirst(t *testing.T) {
 	t.Parallel()
 
@@ -308,7 +343,7 @@ func TestEvictToLimitEvictsLeastRecentlyUsedFirst(t *testing.T) {
 	cache, _ := newEvictionTestCache(t, limit)
 
 	now := time.Now()
-	keys := []imagerequest.VariantKey{
+	keys := []VariantKey{
 		testVariantKeyOne, testVariantKeyTwo,
 		testVariantKeyThree, testVariantKeyFour,
 	}
@@ -353,15 +388,102 @@ func TestEvictToLimitEvictsLeastRecentlyUsedFirst(t *testing.T) {
 	assertNoDanglingReferences(t, cache)
 }
 
+func TestEvictionRemovesMultiReferencedBlobTogetherWithAllReferences(t *testing.T) {
+	t.Parallel()
+
+	const limit = 1000
+
+	cache, _ := newEvictionTestCache(t, limit)
+
+	now := time.Now()
+
+	// One 800-byte blob referenced by two source paths.
+	sharedContent := bytes.Repeat([]byte{0xDD}, 800)
+	sharedHash := storeEvictionTestSource(t, cache,
+		"src.example.com", "/a.jpg", sharedContent)
+
+	h := storeEvictionTestSource(t, cache,
+		"src.example.com", "/b.jpg", sharedContent)
+	if h != sharedHash {
+		t.Fatalf("identical content produced different hashes: %s vs %s",
+			h, sharedHash)
+	}
+
+	// A newer 600-byte blob referenced by one source path.
+	recentHash := storeEvictionTestSource(t, cache, "src.example.com", "/c.jpg",
+		bytes.Repeat([]byte{0xEE}, 600))
+
+	setSourceLastAccessed(t, cache, sharedHash, now.Add(-2*time.Hour))
+	setSourceLastAccessed(t, cache, recentHash, now.Add(-time.Minute))
+
+	err := cache.EvictToLimit(context.Background())
+	if err != nil {
+		t.Fatalf("EvictToLimit failed: %v", err)
+	}
+
+	usage, err := cache.UsageBytes(context.Background())
+	if err != nil {
+		t.Fatalf("UsageBytes failed: %v", err)
+	}
+
+	if usage > limit {
+		t.Errorf("usage after eviction = %d, want <= %d", usage, limit)
+	}
+
+	// The multi-referenced blob must be gone from disk, from
+	// source_content, and from BOTH source_metadata rows: references
+	// are removed together with the blob, never left dangling.
+	if cache.srcContent.Exists(sharedHash) {
+		t.Errorf("evicted blob %s still exists on disk", sharedHash)
+	}
+
+	if n := countRows(t, cache,
+		`SELECT COUNT(*) FROM source_content WHERE content_hash = ?`, string(sharedHash),
+	); n != 0 {
+		t.Errorf("evicted blob %s still has %d source_content rows", sharedHash, n)
+	}
+
+	if n := countRows(t, cache,
+		`SELECT COUNT(*) FROM source_metadata WHERE content_hash = ?`, string(sharedHash),
+	); n != 0 {
+		t.Errorf("evicted blob %s still has %d source_metadata references", sharedHash, n)
+	}
+
+	// The JSON metadata sidecars for both referencing paths must be
+	// removed along with the rows.
+	for _, path := range []string{"/a.jpg", "/b.jpg"} {
+		pathHash := HashPath(path + "?")
+		if cache.srcMetadata.Exists("src.example.com", pathHash) {
+			t.Errorf("metadata sidecar for %s must be removed with its row", path)
+		}
+	}
+
+	// The more recently used blob survives fully intact.
+	if !cache.srcContent.Exists(recentHash) {
+		t.Errorf("recently used blob %s must survive eviction", recentHash)
+	}
+
+	if n := countRows(t, cache,
+		`SELECT COUNT(*) FROM source_metadata WHERE content_hash = ?`, string(recentHash),
+	); n != 1 {
+		t.Errorf("recently used blob %s has %d source_metadata rows, want 1",
+			recentHash, n)
+	}
+
+	assertNoDanglingReferences(t, cache)
+}
+
 func TestEvictionKeepsEverythingWhenUnderLimit(t *testing.T) {
 	t.Parallel()
 
 	cache, _ := newEvictionTestCache(t, 1<<30)
 
 	content := bytes.Repeat([]byte{0xDF}, 800)
-	keys := []imagerequest.SourceKey{
+	hash := storeEvictionTestSource(t, cache, "src.example.com", "/a.jpg", content)
-		storeEvictionTestSource(t, cache, "src.example.com", "/a.jpg", content),
+
-		storeEvictionTestSource(t, cache, "src.example.com", "/b.jpg", content),
+	h := storeEvictionTestSource(t, cache, "src.example.com", "/b.jpg", content)
+	if h != hash {
+		t.Fatalf("identical content produced different hashes: %s vs %s", h, hash)
 	}
 
 	storeEvictionTestVariant(t, cache, testVariantKeyOne,
@@ -372,16 +494,14 @@ func TestEvictionKeepsEverythingWhenUnderLimit(t *testing.T) {
 		t.Fatalf("EvictToLimit failed: %v", err)
 	}
 
-	for _, key := range keys {
+	if !cache.srcContent.Exists(hash) {
-		if !cache.srcContent.Exists(key) {
+		t.Errorf("blob %s must not be evicted while usage is under the limit", hash)
-			t.Errorf("source %s must not be evicted while usage is under the limit", key)
+	}
-		}
 
-		if n := countRows(t, cache,
+	if n := countRows(t, cache,
-			`SELECT COUNT(*) FROM source_content WHERE source_key = ?`, string(key),
+		`SELECT COUNT(*) FROM source_metadata WHERE content_hash = ?`, string(hash),
-		); n != 1 {
+	); n != 2 {
-			t.Errorf("source %s has %d source_content rows, want 1", key, n)
+		t.Errorf("blob %s has %d source_metadata rows, want 2", hash, n)
-		}
 	}
 
 	if !cache.variants.Exists(testVariantKeyOne) {
@@ -396,16 +516,12 @@ func TestZeroMaxBytesDisablesDiskCache(t *testing.T) {
 
 	cache, tmpDir := newEvictionTestCache(t, 0)
 
-	req := &imagerequest.Request{
+	req := &ImageRequest{
-		Source: imagerequest.Source{
+		SourceHost: "src.example.com",
-			Host: "src.example.com",
+		SourcePath: "/a.jpg",
-			Path: "/a.jpg",
+		Format:     FormatJPEG,
-		},
+		Quality:    85,
-		Transform: imagerequest.Transform{
+		FitMode:    FitCover,
-			Format:  imagerequest.FormatJPEG,
-			Quality: 85,
-			FitMode: imagerequest.FitCover,
-		},
 	}
 
 	assertDisabledCacheWritesAreNoOps(t, cache, req)
@@ -417,45 +533,62 @@ func TestZeroMaxBytesDisablesDiskCache(t *testing.T) {
 // assertDisabledCacheWritesAreNoOps verifies that stores against a
 // disabled cache report success without recording anything.
 func assertDisabledCacheWritesAreNoOps(
-	t *testing.T, cache *Cache, req *imagerequest.Request,
+	t *testing.T, cache *Cache, req *ImageRequest,
 ) {
 	t.Helper()
 
 	ctx := t.Context()
 
 	err := cache.StoreVariant(
-		ctx, imagerequest.CacheKey(req), bytes.NewReader([]byte("data")),
+		ctx, CacheKey(req), bytes.NewReader([]byte("data")), "image/webp",
 	)
 	if err != nil {
 		t.Fatalf("StoreVariant on disabled cache must be a no-op, got error: %v", err)
 	}
 
-	key, err := cache.StoreSource(ctx, req, bytes.NewReader([]byte("data")))
+	result := &httpfetcher.FetchResult{
+		StatusCode:    200,
+		ContentType:   testContentTypeJPEG,
+		ContentLength: 4,
+		Headers:       map[string][]string{},
+	}
+
+	hash, err := cache.StoreSource(ctx, req, bytes.NewReader([]byte("data")), result)
 	if err != nil {
 		t.Fatalf("StoreSource on disabled cache must be a no-op, got error: %v", err)
 	}
 
-	if key != "" {
+	if hash != "" {
-		t.Errorf("StoreSource on disabled cache returned key %q, want empty", key)
+		t.Errorf("StoreSource on disabled cache returned hash %q, want empty", hash)
 	}
 }
 
 // assertDisabledCacheReadsAlwaysMiss verifies that lookups against a
 // disabled cache never report a hit.
 func assertDisabledCacheReadsAlwaysMiss(
-	t *testing.T, cache *Cache, req *imagerequest.Request,
+	t *testing.T, cache *Cache, req *ImageRequest,
 ) {
 	t.Helper()
 
 	ctx := t.Context()
 
-	key, err := cache.LookupSource(ctx, req)
+	lookup, err := cache.Lookup(ctx, req)
+	if err != nil {
+		t.Fatalf("Lookup on disabled cache failed: %v", err)
+	}
+
+	if lookup.Hit {
+		t.Error("Lookup on disabled cache must always miss")
+	}
+
+	srcHash, srcType, err := cache.LookupSource(ctx, req)
 	if err != nil {
 		t.Fatalf("LookupSource on disabled cache failed: %v", err)
 	}
 
-	if key != "" {
+	if srcHash != "" || srcType != "" {
-		t.Errorf("LookupSource on disabled cache = %q, want empty", key)
+		t.Errorf("LookupSource on disabled cache = (%q, %q), want empty",
+			srcHash, srcType)
 	}
 }
 
@@ -476,6 +609,10 @@ func assertDisabledCacheTracksNothing(t *testing.T, cache *Cache) {
 	if n := countRows(t, cache, `SELECT COUNT(*) FROM source_content`); n != 0 {
 		t.Errorf("disabled cache wrote %d source_content rows, want 0", n)
 	}
+
+	if n := countRows(t, cache, `SELECT COUNT(*) FROM source_metadata`); n != 0 {
+		t.Errorf("disabled cache wrote %d source_metadata rows, want 0", n)
+	}
 }
 
 // assertDisabledCacheWroteNothingToDisk verifies that a disabled cache
@@ -524,7 +661,7 @@ func TestEvictionRunsUnderWritePressure(t *testing.T) {
 	cache.StartEviction(time.Hour)
 	defer func() { _ = cache.StopEviction(t.Context()) }()
 
-	keys := []imagerequest.VariantKey{
+	keys := []VariantKey{
 		testVariantKeyOne, testVariantKeyTwo, testVariantKeyThree,
 	}
 	fills := []byte{0x11, 0x12, 0x13}
@@ -578,7 +715,7 @@ func TestEvictionRunsOnPeriodicSchedule(t *testing.T) {
 		time.Sleep(10 * time.Millisecond)
 	}
 
-	keys := []imagerequest.VariantKey{
+	keys := []VariantKey{
 		testVariantKeyOne, testVariantKeyTwo, testVariantKeyThree,
 	}
 	fills := []byte{0x21, 0x22, 0x23}
@@ -586,7 +723,7 @@ func TestEvictionRunsOnPeriodicSchedule(t *testing.T) {
 	for i, key := range keys {
 		content := bytes.Repeat([]byte{fills[i]}, 1000)
 
-		_, err = cache.variants.Store(key, bytes.NewReader(content))
+		_, err = cache.variants.Store(key, bytes.NewReader(content), "image/webp")
 		if err != nil {
 			t.Fatalf("failed to store variant file: %v", err)
 		}
@@ -638,7 +775,7 @@ func TestStartEvictionReconcilesAccountingWithDisk(t *testing.T) {
 	untracked := bytes.Repeat([]byte{0x31}, 1000)
 
 	_, err := cache.variants.Store(
-		testVariantKeyOne, bytes.NewReader(untracked),
+		testVariantKeyOne, bytes.NewReader(untracked), "image/webp",
 	)
 	if err != nil {
 		t.Fatalf("failed to store untracked variant file: %v", err)
@@ -646,8 +783,9 @@ func TestStartEvictionReconcilesAccountingWithDisk(t *testing.T) {
 
 	// An accounting row whose file is missing must be dropped.
 	_, err = cache.db.ExecContext(t.Context(),
-		`INSERT INTO variant_content (cache_key, size_bytes) VALUES (?, ?)`,
+		`INSERT INTO variant_content (cache_key, size_bytes, content_type)
-		"deadbeef0001", 700,
+		 VALUES (?, ?, ?)`,
+		"deadbeef0001", 700, "image/webp",
 	)
 	if err != nil {
 		t.Fatalf("failed to insert stale variant accounting row: %v", err)
@@ -739,7 +877,7 @@ func TestPeriodicReconciliationAdoptsFileThatAppearsAfterStartup(t *testing.T) {
 	untracked := bytes.Repeat([]byte{0x41}, 900)
 
 	_, err = cache.variants.Store(
-		"aabbccdd0099", bytes.NewReader(untracked),
+		"aabbccdd0099", bytes.NewReader(untracked), "image/webp",
 	)
 	if err != nil {
 		t.Fatalf("failed to store untracked variant file: %v", err)
@@ -780,89 +918,6 @@ func TestPeriodicReconciliationAdoptsFileThatAppearsAfterStartup(t *testing.T) {
 	}
 }
 
-// TestReconciliationPassesAreSpacedByTenTimesTheirTime makes the hook
-// called after every read of the reconciliation pass sleep 10 ms, runs
-// the eviction loop on a 10 ms interval, and records when each of those
-// calls starts and ends. A pass starts before its first call and ends
-// after its last, so the time from the first call's start to the last
-// call's end is at most the pass's time. The next pass's first call must
-// start at least ten times that long after the last call ended.
-func TestReconciliationPassesAreSpacedByTenTimesTheirTime(t *testing.T) {
-	t.Parallel()
-
-	cache, _ := newEvictionTestCache(t, 1<<30)
-
-	// A pass made here, before the loop starts, counts the reads one
-	// pass makes on this empty cache, so the reads recorded below can be
-	// split into passes.
-	readsPerPass := 0
-	cache.reconciliationReadTestHook = func(int) { readsPerPass++ }
-
-	err := cache.reconcileAccounting(t.Context())
-	if err != nil {
-		t.Fatalf("reconcileAccounting failed: %v", err)
-	}
-
-	t.Logf("one reconciliation pass makes %d reads", readsPerPass)
-
-	if readsPerPass == 0 {
-		t.Fatal("a reconciliation pass made no read")
-	}
-
-	// The pass at startup and two after it.
-	const passes = 3
-
-	type read struct{ start, end time.Time }
-
-	// The channel holds every read the test looks at, so none of those
-	// is dropped; reads after them are, and never block the loop.
-	reads := make(chan read, passes*readsPerPass)
-
-	cache.reconciliationReadTestHook = func(int) {
-		start := time.Now()
-
-		time.Sleep(10 * time.Millisecond)
-
-		select {
-		case reads <- read{start: start, end: time.Now()}:
-		default:
-		}
-	}
-
-	cache.StartEviction(10 * time.Millisecond)
-	defer func() { _ = cache.StopEviction(t.Context()) }()
-
-	recorded := make([]read, 0, passes*readsPerPass)
-	timeout := time.After(15 * time.Second)
-
-	for len(recorded) < passes*readsPerPass {
-		select {
-		case r := <-reads:
-			recorded = append(recorded, r)
-		case <-timeout:
-			t.Fatalf("saw %d reconciliation reads in 15 s, want %d (%d passes)",
-				len(recorded), passes*readsPerPass, passes)
-		}
-	}
-
-	for pass := range passes - 1 {
-		first := recorded[pass*readsPerPass]
-		last := recorded[(pass+1)*readsPerPass-1]
-		next := recorded[(pass+1)*readsPerPass]
-
-		passTime := last.end.Sub(first.start)
-		wait := next.start.Sub(last.end)
-
-		t.Logf("pass %d took at least %v, and the next pass started %v after it",
-			pass+1, passTime, wait)
-
-		if wait < 10*passTime {
-			t.Errorf("pass %d took at least %v, and the next pass started %v "+
-				"after it, want at least %v", pass+1, passTime, wait, 10*passTime)
-		}
-	}
-}
-
 // TestStopEvictionInterruptsPassInProgress holds the test database's
 // only connection, so the startup reconciliation pass waits for it, and
 // checks that StopEviction stops that pass instead of waiting for the
@@ -917,15 +972,9 @@ func TestStopEvictionInterruptsPassInProgress(t *testing.T) {
 }
 
 // TestEvictToLimitStopsAtNextCandidateOnceCancelled cancels the context
-// once the oldest of three sources is evicted, while the next one waits
+// while the oldest of three source blobs is being evicted, and checks that
-// for the database, and checks that EvictToLimit then returns
+// EvictToLimit then returns context.Canceled without evicting the other
-// context.Canceled, with that source gone and the other two kept, and
+// two or logging a warning for either of them.
-// logs no warning. The test database has one connection. When the
-// deletion of the oldest source's row commits, a commit hook holds the
-// deletion until the test waits for the connection, so the test takes it
-// as soon as the deletion is done. The eviction of the next source then
-// waits for the connection, and the test cancels the context while it
-// waits.
 func TestEvictToLimitStopsAtNextCandidateOnceCancelled(t *testing.T) {
 	t.Parallel()
 
@@ -935,7 +984,7 @@ func TestEvictToLimitStopsAtNextCandidateOnceCancelled(t *testing.T) {
 
 	cache.log = slog.New(slog.NewJSONHandler(&logBuf, nil))
 
-	keys := []imagerequest.SourceKey{
+	hashes := []ContentHash{
 		storeEvictionTestSource(t, cache, "cancel.example.com", "/a.jpg",
 			bytes.Repeat([]byte{0x61}, 1000)),
 		storeEvictionTestSource(t, cache, "cancel.example.com", "/b.jpg",
@@ -946,155 +995,69 @@ func TestEvictToLimitStopsAtNextCandidateOnceCancelled(t *testing.T) {
 
 	base := time.Now().Add(-time.Hour)
 
-	for i, key := range keys {
+	for i, hash := range hashes {
-		setSourceLastAccessed(t, cache, key, base.Add(time.Duration(i)*time.Minute))
+		setSourceLastAccessed(t, cache, hash, base.Add(time.Duration(i)*time.Minute))
 	}
 
-	waitsBefore := cache.db.Stats().WaitCount
-	oldestRowDeleted := make(chan struct{})
-
-	var oldestRowDeletedOnce sync.Once
-
-	setCommitHook(t, cache, func() int32 {
-		oldestRowDeletedOnce.Do(func() {
-			close(oldestRowDeleted)
-
-			deadline := time.Now().Add(5 * time.Second)
-
-			for cache.db.Stats().WaitCount == waitsBefore && time.Now().Before(deadline) {
-				time.Sleep(time.Millisecond)
-			}
-		})
-
-		return 0
-	})
-
 	ctx, cancel := context.WithCancel(t.Context())
 	defer cancel()
 
-	evicted := make(chan error, 1)
+	cache.evictSourceBlobTestHook = func(ContentHash) { cancel() }
 
-	go func() { evicted <- cache.EvictToLimit(ctx) }()
+	err := cache.EvictToLimit(ctx)
-
-	select {
-	case <-oldestRowDeleted:
-	case err := <-evicted:
-		t.Fatalf("EvictToLimit() returned %v without deleting a row", err)
-	case <-time.After(5 * time.Second):
-		t.Fatal("EvictToLimit never deleted a row")
-	}
-
-	releaseDatabase := holdDatabase(t, cache)
-	defer releaseDatabase()
-
-	waitForConnectionWaits(t, cache.db, waitsBefore+2)
-	cancel()
-
-	err := <-evicted
 	t.Logf("EvictToLimit() error = %v", err)
 	t.Logf("log output: %s", logBuf.String())
 
-	// The checks below read the database, so the connection goes back.
-	releaseDatabase()
-
-	setCommitHook(t, cache, nil)
-
 	if !errors.Is(err, context.Canceled) {
 		t.Errorf("EvictToLimit() error = %v, want context.Canceled", err)
 	}
 
-	assertOnlyOldestSourceEvicted(t, cache, keys)
+	if cache.srcContent.Exists(hashes[0]) {
+		t.Errorf("source blob %s, evicted when the context was cancelled, "+
+			"is still on disk", hashes[0])
+	}
+
+	for _, hash := range hashes[1:] {
+		if !cache.srcContent.Exists(hash) {
+			t.Errorf("source blob %s was evicted after the context was cancelled", hash)
+		}
+	}
 
 	if strings.Contains(logBuf.String(), `"level":"WARN"`) {
 		t.Errorf("EvictToLimit logged a warning after the context was cancelled")
 	}
-}
-
-// setCommitHook makes the SQLite driver call hook each time a write on
-// the test database's one connection commits, or stops it when hook is
-// nil.
-func setCommitHook(t *testing.T, cache *Cache, hook sqlite.CommitHookFn) {
-	t.Helper()
-
-	conn, err := cache.db.Conn(t.Context())
-	if err != nil {
-		t.Fatalf("failed to take the database connection: %v", err)
-	}
-
-	defer func() { _ = conn.Close() }()
-
-	err = conn.Raw(func(driverConn any) error {
-		hooks, ok := driverConn.(sqlite.HookRegisterer)
-		if !ok {
-			t.Fatalf("the database connection is a %T, which takes no hooks",
-				driverConn)
-		}
-
-		hooks.RegisterCommitHook(hook)
-
-		return nil
-	})
-	if err != nil {
-		t.Fatalf("failed to set the commit hook: %v", err)
-	}
-}
-
-// assertOnlyOldestSourceEvicted checks that the first of keys has neither
-// its file nor its row, and that every other one has both.
-func assertOnlyOldestSourceEvicted(
-	t *testing.T, cache *Cache, keys []imagerequest.SourceKey,
-) {
-	t.Helper()
-
-	if cache.srcContent.Exists(keys[0]) {
-		t.Errorf("source %s, evicted when the context was cancelled, "+
-			"is still on disk", keys[0])
-	}
-
-	for _, key := range keys[1:] {
-		if !cache.srcContent.Exists(key) {
-			t.Errorf("source %s was evicted after the context was cancelled", key)
-		}
-
-		if n := countRows(t, cache,
-			`SELECT COUNT(*) FROM source_content WHERE source_key = ?`, string(key),
-		); n != 1 {
-			t.Errorf("source %s, kept, has %d source_content rows, want 1", key, n)
-		}
-	}
 
 	assertNoDanglingReferences(t, cache)
 }
 
-// TestStopEvictionReturnsWhenItsContextEnds pauses the startup
+// TestStopEvictionReturnsWhenItsContextEnds pauses an eviction pass where
-// reconciliation pass in the hook called after each of its reads, where
+// cancellation cannot reach it, after a source blob's rows are deleted and
-// cancellation cannot reach it, and checks that StopEviction returns an
+// before its file is removed, and checks that StopEviction returns its
-// error wrapping its context's error when that context ends, instead of
+// context's error when that context ends instead of waiting for the pass.
-// waiting for the pass. Once the pass goes on, the goroutine exits, and a
+// Once the pass goes on, the goroutine exits and no row points at a
-// second StopEviction returns nil.
+// missing file.
 func TestStopEvictionReturnsWhenItsContextEnds(t *testing.T) {
 	t.Parallel()
 
-	cache, _ := newEvictionTestCache(t, 1<<30)
+	cache, _ := newEvictionTestCache(t, 1)
 
 	paused := make(chan struct{})
 	resume := make(chan struct{})
 
-	var pauseOnce sync.Once
+	cache.evictSourceBlobTestHook = func(ContentHash) {
-
+		close(paused)
-	cache.reconciliationReadTestHook = func(int) {
+		<-resume
-		pauseOnce.Do(func() {
-			close(paused)
-			<-resume
-		})
 	}
 
+	hash := storeEvictionTestSource(t, cache, "stop.example.com", "/a.jpg",
+		bytes.Repeat([]byte{0x61}, 1000))
+
 	cache.StartEviction(time.Hour)
 
 	select {
 	case <-paused:
 	case <-time.After(5 * time.Second):
-		t.Fatal("the reconciliation pass never made a read")
+		t.Fatal("the eviction pass never reached the source blob")
 	}
 
 	ctx, cancel := context.WithTimeout(t.Context(), 50*time.Millisecond)
@@ -1113,6 +1076,12 @@ func TestStopEvictionReturnsWhenItsContextEnds(t *testing.T) {
 	if err != nil {
 		t.Fatalf("second StopEviction() error = %v, want nil", err)
 	}
+
+	assertNoDanglingReferences(t, cache)
+
+	if cache.srcContent.Exists(hash) {
+		t.Errorf("source blob %s is still on disk after its rows were deleted", hash)
+	}
 }
 
 // TestReconciliationWalksStopOnceCancelled checks that both directory
@@ -1184,3 +1153,125 @@ func TestReconciliationPassLogsNoWarningOnceCancelled(t *testing.T) {
 		t.Errorf("runReconciliationPass logged a warning with a cancelled context")
 	}
 }
+
+// TestEvictSourceBlobExcludesConcurrentStoreOfIdenticalContent exercises
+// the exact TOCTOU window between evictSourceBlob's row-deletion
+// transaction commit and its content file unlink: a concurrent
+// StoreSource for a different source path whose content hashes to the
+// same value (real SHA-256 dedup, not a contrived case) must not be
+// able to insert a fresh row referencing the file while eviction is
+// mid-unlink, and must not lose its own store once eviction has fully
+// released the content hash.
+func TestEvictSourceBlobExcludesConcurrentStoreOfIdenticalContent(t *testing.T) {
+	t.Parallel()
+
+	cache, _ := newEvictionTestCache(t, 1<<30)
+	ctx := context.Background()
+
+	content := bytes.Repeat([]byte{0x55}, 400)
+
+	hash := storeEvictionTestSource(t, cache,
+		"race.example.com", "/first.jpg", content)
+
+	proceed := make(chan struct{})
+	storeAttempted := make(chan struct{})
+
+	cache.evictSourceBlobTestHook = func(gotHash ContentHash) {
+		if gotHash != hash {
+			t.Errorf("test hook invoked for hash %s, want %s", gotHash, hash)
+		}
+
+		close(storeAttempted)
+		<-proceed
+	}
+
+	evictDone := make(chan error, 1)
+
+	go func() {
+		evictDone <- cache.evictSourceBlob(ctx, hash)
+	}()
+
+	// Wait until eviction has committed its delete transaction and is
+	// paused (inside the test hook) immediately before unlinking the
+	// content file: exactly the window the review flagged.
+	<-storeAttempted
+
+	storeDone := storeIdenticalContentConcurrently(ctx, cache, content)
+
+	// The concurrent store must not be able to complete while eviction
+	// still holds the content hash (i.e. before the file is unlinked):
+	// if it could, it would insert a row referencing a file about to be
+	// removed out from under it.
+	select {
+	case err := <-storeDone:
+		t.Fatalf("StoreSource for identical content completed (err=%v) while eviction "+
+			"still held the content hash open between commit and unlink; the store and "+
+			"the evict of identical content are not mutually exclusive", err)
+	case <-time.After(200 * time.Millisecond):
+		// Expected: the store is blocked behind eviction's exclusion.
+	}
+
+	close(proceed)
+
+	err := <-evictDone
+	if err != nil {
+		t.Fatalf("evictSourceBlob failed: %v", err)
+	}
+
+	err = <-storeDone
+	if err != nil {
+		t.Fatalf("StoreSource failed: %v", err)
+	}
+
+	assertNoDanglingReferences(t, cache)
+
+	dupHash, _, err := cache.LookupSource(ctx, &ImageRequest{
+		SourceHost: "race.example.com",
+		SourcePath: "/dup.jpg",
+	})
+	if err != nil {
+		t.Fatalf("LookupSource failed: %v", err)
+	}
+
+	if dupHash == "" {
+		t.Fatal("re-stored blob was lost: the store legitimately ran after eviction " +
+			"released the content hash and must have recreated the file and row")
+	}
+
+	if !cache.srcContent.Exists(dupHash) {
+		t.Errorf("source_content/source_metadata references %s but its file is missing",
+			dupHash)
+	}
+}
+
+// storeIdenticalContentConcurrently starts a StoreSource for a second
+// source path whose body hashes to the same content hash, returning the
+// channel its error is delivered on.
+func storeIdenticalContentConcurrently(
+	ctx context.Context, cache *Cache, content []byte,
+) chan error {
+	storeDone := make(chan error, 1)
+
+	go func() {
+		req := &ImageRequest{
+			SourceHost: "race.example.com",
+			SourcePath: "/dup.jpg",
+			Format:     FormatJPEG,
+			Quality:    85,
+			FitMode:    FitCover,
+		}
+		result := &httpfetcher.FetchResult{
+			StatusCode:    200,
+			ContentType:   testContentTypeJPEG,
+			ContentLength: int64(len(content)),
+			Headers: map[string][]string{
+				testHeaderContentType: {testContentTypeJPEG},
+			},
+		}
+
+		_, err := cache.StoreSource(ctx, req, bytes.NewReader(content), result)
+		storeDone <- err
+	}()
+
+	return storeDone
+}

internal/imgcache/imgcache.go

@@ -1,7 +1,135 @@
-// Package imgcache provides types for the image caching proxy.
+// Package imgcache provides interfaces and types for the image caching proxy.
 package imgcache
 
-import "io"
+import (
+	"context"
+	"errors"
+	"io"
+	"net/url"
+	"time"
+)
+
+// ErrInvalidFitMode is returned when an invalid fit mode is provided.
+var ErrInvalidFitMode = errors.New("invalid fit mode")
+
+// ImageFormat represents supported output image formats.
+type ImageFormat string
+
+// Supported image output formats.
+const (
+	FormatOriginal ImageFormat = "orig"
+	FormatJPEG     ImageFormat = "jpeg"
+	FormatPNG      ImageFormat = "png"
+	FormatWebP     ImageFormat = "webp"
+	FormatAVIF     ImageFormat = "avif"
+	FormatJXL      ImageFormat = "jxl"
+	FormatGIF      ImageFormat = "gif"
+
+	// FormatAuto stands for JPEG XL, AVIF, WebP or JPEG, chosen for each
+	// request from its Accept header once the URL's signature or token has
+	// been checked; it is never processed or cached as itself.
+	FormatAuto ImageFormat = "auto"
+)
+
+// Size represents requested image dimensions
+type Size struct {
+	Width  int
+	Height int
+}
+
+// OriginalSize returns true if this represents "keep original size"
+func (s Size) OriginalSize() bool {
+	return s.Width == 0 && s.Height == 0
+}
+
+// FitMode represents how to fit image into requested dimensions.
+type FitMode string
+
+// Supported image fit modes.
+const (
+	FitCover   FitMode = "cover"
+	FitContain FitMode = "contain"
+	FitFill    FitMode = "fill"
+	FitInside  FitMode = "inside"
+	FitOutside FitMode = "outside"
+)
+
+// ValidateFitMode checks if the given fit mode is valid.
+// Returns ErrInvalidFitMode for unrecognized fit modes.
+func ValidateFitMode(fit FitMode) error {
+	switch fit {
+	case FitCover, FitContain, FitFill, FitInside, FitOutside, "":
+		return nil
+	default:
+		return ErrInvalidFitMode
+	}
+}
+
+// ValidateImageRequest checks a request's width and height with
+// ValidateDimension and its fit mode with ValidateFitMode. Both the plain
+// /v1/image/ route and the encrypted /v1/e/ route validate through this
+// function so a request from either source enforces identical bounds.
+func ValidateImageRequest(req *ImageRequest) error {
+	err := ValidateDimension("width", req.Size.Width)
+	if err != nil {
+		return err
+	}
+
+	err = ValidateDimension("height", req.Size.Height)
+	if err != nil {
+		return err
+	}
+
+	return ValidateFitMode(req.FitMode)
+}
+
+// ImageRequest represents a request for a processed image
+type ImageRequest struct {
+	// SourceHost is the origin host (e.g., "cdn.example.com")
+	SourceHost string
+	// SourcePath is the path on the origin with its percent-escapes decoded,
+	// as url.URL's Path holds it (e.g., "/photos/my cat.jpg")
+	SourcePath string
+	// SourceQuery is the optional query string for the origin URL as the URL
+	// writes it, percent-escapes included, as url.URL's RawQuery holds it
+	SourceQuery string
+	// Size is the requested output dimensions
+	Size Size
+	// Format is the requested output format
+	Format ImageFormat
+	// Quality is the output quality (1-100) for lossy formats
+	Quality int
+	// FitMode is how to fit the image into requested dimensions
+	FitMode FitMode
+	// Signature is the HMAC signature for non-allowlisted hosts
+	Signature string
+	// Expires is when the URL expires: the exp of a signed URL, or the expiry
+	// of an encrypted URL; the zero time if it has none
+	Expires time.Time
+	// AllowHTTP indicates whether HTTP (non-TLS) is allowed for this request
+	AllowHTTP bool
+}
+
+// SourceURL returns the full upstream URL to fetch: the source path
+// percent-encoded again, as net/url writes a path, so each source path is one
+// upstream path, and the source query as it is, with the characters
+// escapeQuery encodes percent-encoded. Uses http:// scheme when AllowHTTP is
+// true, otherwise https://.
+func (r *ImageRequest) SourceURL() string {
+	scheme := "https"
+	if r.AllowHTTP {
+		scheme = "http"
+	}
+
+	sourceURL := url.URL{
+		Scheme:   scheme,
+		Host:     r.SourceHost,
+		Path:     r.SourcePath,
+		RawQuery: escapeQuery(r.SourceQuery),
+	}
+
+	return sourceURL.String()
+}
 
 // ImageResponse represents a processed image ready to serve
 type ImageResponse struct {
@@ -13,7 +141,9 @@ type ImageResponse struct {
 	ContentType string
 	// ETag is the entity tag for caching
 	ETag string
-	// CacheStatus indicates HIT or MISS
+	// LastModified is when the content was last modified
+	LastModified time.Time
+	// CacheStatus indicates HIT, MISS, or STALE
 	CacheStatus CacheStatus
 	// FetchedBytes is the number of bytes fetched from upstream (0 if cache hit)
 	FetchedBytes int64
@@ -24,6 +154,35 @@ type CacheStatus string
 
 // Cache status values for response headers.
 const (
-	CacheHit  CacheStatus = "HIT"
+	CacheHit   CacheStatus = "HIT"
-	CacheMiss CacheStatus = "MISS"
+	CacheMiss  CacheStatus = "MISS"
+	CacheStale CacheStatus = "STALE"
 )
+
+// ImageCache is the main interface for the image caching proxy
+type ImageCache interface {
+	// Get retrieves a processed image, fetching and processing if necessary
+	Get(ctx context.Context, req *ImageRequest) (*ImageResponse, error)
+
+	// Warm pre-fetches and caches an image without returning it
+	Warm(ctx context.Context, req *ImageRequest) error
+
+	// Stats returns cache statistics
+	Stats(ctx context.Context) (*CacheStats, error)
+}
+
+// CacheStats contains cache statistics
+type CacheStats struct {
+	// TotalItems is the number of cached source images plus processed
+	// variants
+	TotalItems int64
+	// TotalSizeBytes is the total size of cached source images and
+	// processed variants
+	TotalSizeBytes int64
+	// HitCount is the number of cache hits
+	HitCount int64
+	// MissCount is the number of cache misses
+	MissCount int64
+	// HitRate is HitCount / (HitCount + MissCount)
+	HitRate float64
+}

internal/imgcache/max_concurrent_processing_internal_test.go

@@ -9,23 +9,18 @@ import (
 	"time"
 
 	"sneak.berlin/go/pixa/internal/imageprocessor"
-	"sneak.berlin/go/pixa/internal/imagerequest"
 )
 
 // widthOnlyRequest asks for the test photo at width, its height scaled to
 // keep the photo's aspect ratio.
-func widthOnlyRequest(fixtures *TestFixtures, width int) *imagerequest.Request {
+func widthOnlyRequest(fixtures *TestFixtures, width int) *ImageRequest {
-	return &imagerequest.Request{
+	return &ImageRequest{
-		Source: imagerequest.Source{
+		SourceHost: fixtures.GoodHost,
-			Host: fixtures.GoodHost,
+		SourcePath: testPathPhoto,
-			Path: testPathPhoto,
+		Size:       Size{Width: width},
-		},
+		Format:     FormatJPEG,
-		Transform: imagerequest.Transform{
+		Quality:    85,
-			Size:    imagerequest.Size{Width: width},
+		FitMode:    FitCover,
-			Format:  imagerequest.FormatJPEG,
-			Quality: 85,
-			FitMode: imagerequest.FitCover,
-		},
 	}
 }
 
@@ -41,7 +36,7 @@ func holdProcessingSlot(
 	input, feed := io.Pipe()
 
 	go func() {
-		_, _ = proc.Process(t.Context(), input, &imagerequest.Transform{})
+		_, _ = proc.Process(t.Context(), input, &imageprocessor.Request{})
 	}()
 
 	_, err := feed.Write([]byte{0})
@@ -66,7 +61,7 @@ func TestService_Get_WaitsForSlotBeforeReadingCachedSource(t *testing.T) {
 
 	svc, fixtures := SetupTestService(t)
 	svc.processor = imageprocessor.New(
-		imageprocessor.Params{MaxInputBytes: 50 << 20, MaxConcurrentProcessing: 1},
+		imageprocessor.Params{MaxConcurrentProcessing: 1},
 	)
 
 	// A first request caches the photo as a source.
@@ -77,11 +72,11 @@ func TestService_Get_WaitsForSlotBeforeReadingCachedSource(t *testing.T) {
 
 	_ = resp.Content.Close()
 
-	sourceKey, err := svc.cache.LookupSource(t.Context(),
+	contentHash, _, err := svc.cache.LookupSource(t.Context(),
 		widthOnlyRequest(fixtures, 50))
-	if err != nil || sourceKey == "" {
+	if err != nil || contentHash == "" {
 		t.Fatalf("LookupSource() = %q, %v; want the cached source",
-			sourceKey, err)
+			contentHash, err)
 	}
 
 	release := holdProcessingSlot(t, svc.processor)
@@ -103,7 +98,7 @@ func TestService_Get_WaitsForSlotBeforeReadingCachedSource(t *testing.T) {
 	// before waiting, it would have read it by now.
 	time.Sleep(100 * time.Millisecond)
 
-	err = os.WriteFile(svc.cache.srcContent.keyToPath(sourceKey),
+	err = os.WriteFile(svc.cache.srcContent.hashToPath(contentHash),
 		generateTestJPEG(t, 100, 50, color.RGBA{0, 0, 255, 255}), 0o600)
 	if err != nil {
 		t.Fatalf("failed to rewrite the cached source: %v", err)

internal/imgcache/metacache_internal_test.go

@@ -0,0 +1,349 @@
+package imgcache
+
+import (
+	"bytes"
+	"encoding/json"
+	"errors"
+	"fmt"
+	"io"
+	"os"
+	"sync"
+	"testing"
+	"time"
+)
+
+// webpRequest returns a request for a 100x100 WebP variant of path.
+func webpRequest(path string) *ImageRequest {
+	return &ImageRequest{
+		SourceHost: testHostCDN,
+		SourcePath: path,
+		Size:       Size{Width: 100, Height: 100},
+		Format:     FormatWebP,
+		Quality:    85,
+		FitMode:    FitCover,
+	}
+}
+
+// assertVariantServed checks that GetVariant serves key with the given
+// content and the image/webp content type storeEvictionTestVariant stores.
+func assertVariantServed(t *testing.T, cache *Cache, key VariantKey, content []byte) {
+	t.Helper()
+
+	reader, size, contentType, err := cache.GetVariant(key)
+	if err != nil {
+		t.Fatalf("GetVariant(%s) error = %v", key, err)
+	}
+
+	defer func() { _ = reader.Close() }()
+
+	got, err := io.ReadAll(reader)
+	if err != nil {
+		t.Fatalf("reading variant %s: %v", key, err)
+	}
+
+	if !bytes.Equal(got, content) {
+		t.Errorf("GetVariant(%s) content = %q, want %q", key, got, content)
+	}
+
+	if size != int64(len(content)) {
+		t.Errorf("GetVariant(%s) size = %d, want %d", key, size, len(content))
+	}
+
+	if contentType != testContentTypeWebP {
+		t.Errorf("GetVariant(%s) content type = %q, want %q",
+			key, contentType, testContentTypeWebP)
+	}
+}
+
+// assertVariantNotFound checks that GetVariant refuses key with
+// ErrNotFound.
+func assertVariantNotFound(t *testing.T, cache *Cache, key VariantKey) {
+	t.Helper()
+
+	reader, _, _, err := cache.GetVariant(key)
+	if err == nil {
+		_ = reader.Close()
+	}
+
+	if !errors.Is(err, ErrNotFound) {
+		t.Errorf("GetVariant(%s) error = %v, want ErrNotFound", key, err)
+	}
+}
+
+// assertLookupMisses checks that Lookup reports request as a miss.
+func assertLookupMisses(t *testing.T, cache *Cache, request *ImageRequest) {
+	t.Helper()
+
+	lookup, err := cache.Lookup(t.Context(), request)
+	if err != nil {
+		t.Fatalf("Lookup(%s) error = %v", request.SourcePath, err)
+	}
+
+	if lookup.Hit {
+		t.Errorf("Lookup(%s) is a hit, want a miss", request.SourcePath)
+	}
+}
+
+// renameFile renames the file at from to to.
+func renameFile(t *testing.T, from, to string) {
+	t.Helper()
+
+	err := os.Rename(from, to)
+	if err != nil {
+		t.Fatalf("renaming %s: %v", from, err)
+	}
+}
+
+// TestSecondHitDoesNotReadMetaFile checks that once a variant has been
+// stored or read, a hit takes its content type from memory: with the
+// .meta file deleted, GetVariant must still return the stored content
+// type rather than the application/octet-stream it uses without one.
+func TestSecondHitDoesNotReadMetaFile(t *testing.T) {
+	t.Parallel()
+
+	cache, _ := newEvictionTestCache(t, 1<<20)
+	content := []byte("webp variant bytes")
+
+	storeEvictionTestVariant(t, cache, testVariantKeyOne, content)
+
+	// A second Cache on the same state directory starts with nothing in
+	// memory, as pixad does after a restart, so its first read uses the
+	// .meta file.
+	restarted, err := NewCache(cache.db, cache.config)
+	if err != nil {
+		t.Fatalf("NewCache() error = %v", err)
+	}
+
+	assertVariantServed(t, restarted, testVariantKeyOne, content)
+
+	err = os.Remove(cache.variants.keyToPath(testVariantKeyOne) + ".meta")
+	if err != nil {
+		t.Fatalf("removing .meta file: %v", err)
+	}
+
+	assertVariantServed(t, cache, testVariantKeyOne, content)
+	assertVariantServed(t, restarted, testVariantKeyOne, content)
+}
+
+// TestReadDuringStoreKeepsStoredContentType checks that a GetVariant
+// which began before StoreVariant finished cannot replace the content
+// type the store kept in memory. Such a read can find the variant file
+// but not yet its .meta file, and so gets application/octet-stream. The
+// test deletes the .meta file after the store, then runs the part of
+// GetVariant that comes after its check of memory.
+func TestReadDuringStoreKeepsStoredContentType(t *testing.T) {
+	t.Parallel()
+
+	cache, _ := newEvictionTestCache(t, 1<<20)
+	content := []byte("webp variant bytes")
+
+	storeEvictionTestVariant(t, cache, testVariantKeyOne, content)
+
+	err := os.Remove(cache.variants.keyToPath(testVariantKeyOne) + ".meta")
+	if err != nil {
+		t.Fatalf("removing .meta file: %v", err)
+	}
+
+	reader, _, contentType, err := cache.loadVariantWithMeta(testVariantKeyOne)
+	if err != nil {
+		t.Fatalf("loadVariantWithMeta(%s) error = %v", testVariantKeyOne, err)
+	}
+
+	_ = reader.Close()
+
+	t.Logf("the read without a .meta file got content type %q", contentType)
+
+	assertVariantServed(t, cache, testVariantKeyOne, content)
+}
+
+// TestReadOfOlderMetaFileKeepsStoredContentType checks that a read
+// which got its content type from a .meta file that StoreVariant had
+// not yet rewritten cannot replace the type the store kept in memory.
+// The test writes such a .meta file, with a different content type,
+// after the store, then runs the part of GetVariant that comes after
+// its check of memory.
+func TestReadOfOlderMetaFileKeepsStoredContentType(t *testing.T) {
+	t.Parallel()
+
+	cache, _ := newEvictionTestCache(t, 1<<20)
+	content := []byte("webp variant bytes")
+
+	storeEvictionTestVariant(t, cache, testVariantKeyOne, content)
+
+	olderMeta, err := json.Marshal(VariantMeta{
+		ContentType: testContentTypeJPEG,
+		Size:        int64(len(content)),
+	})
+	if err != nil {
+		t.Fatalf("encoding .meta file: %v", err)
+	}
+
+	metaPath := cache.variants.keyToPath(testVariantKeyOne) + ".meta"
+
+	err = os.WriteFile(metaPath, olderMeta, StorageFilePerm)
+	if err != nil {
+		t.Fatalf("writing .meta file: %v", err)
+	}
+
+	reader, _, contentType, err := cache.loadVariantWithMeta(testVariantKeyOne)
+	if err != nil {
+		t.Fatalf("loadVariantWithMeta(%s) error = %v", testVariantKeyOne, err)
+	}
+
+	_ = reader.Close()
+
+	if contentType != testContentTypeJPEG {
+		t.Fatalf("loadVariantWithMeta(%s) content type = %q, want %q from the .meta file",
+			testVariantKeyOne, contentType, testContentTypeJPEG)
+	}
+
+	kept, _ := cache.metaCache.Get(testVariantKeyOne)
+	if kept != testContentTypeWebP {
+		t.Errorf("content type in memory = %q, want the stored %q",
+			kept, testContentTypeWebP)
+	}
+}
+
+// TestFailedReadDuringStoreKeepsStoredContentType checks that a read
+// which found no .meta file cannot leave application/octet-stream in
+// memory, even when another read has removed the content type
+// StoreVariant kept there. In this order: the store; a read that finds
+// the variant in memory but cannot open its file, and so removes it
+// from memory; a read that opened the variant file before the store
+// wrote its .meta file. Later hits must get the stored content type.
+func TestFailedReadDuringStoreKeepsStoredContentType(t *testing.T) {
+	t.Parallel()
+
+	cache, _ := newEvictionTestCache(t, 1<<20)
+	content := []byte("webp variant bytes")
+	variantPath := cache.variants.keyToPath(testVariantKeyOne)
+	metaPath := variantPath + ".meta"
+
+	storeEvictionTestVariant(t, cache, testVariantKeyOne, content)
+
+	renameFile(t, variantPath, variantPath+".hidden")
+	assertVariantNotFound(t, cache, testVariantKeyOne)
+	renameFile(t, variantPath+".hidden", variantPath)
+
+	renameFile(t, metaPath, metaPath+".hidden")
+
+	reader, _, contentType, err := cache.GetVariant(testVariantKeyOne)
+	if err != nil {
+		t.Fatalf("GetVariant(%s) error = %v", testVariantKeyOne, err)
+	}
+
+	_ = reader.Close()
+
+	t.Logf("the read without a .meta file got content type %q", contentType)
+
+	renameFile(t, metaPath+".hidden", metaPath)
+
+	assertVariantServed(t, cache, testVariantKeyOne, content)
+}
+
+// TestEvictedVariantIsNotServed checks that a variant the evictor
+// removed is a miss and cannot be read, although it had been stored
+// and served before.
+func TestEvictedVariantIsNotServed(t *testing.T) {
+	t.Parallel()
+
+	cache, _ := newEvictionTestCache(t, 1500)
+
+	oldRequest := webpRequest("/old.jpg")
+	newRequest := webpRequest("/new.jpg")
+	oldKey := CacheKey(oldRequest)
+	newKey := CacheKey(newRequest)
+	oldContent := bytes.Repeat([]byte{0x01}, 1000)
+	newContent := bytes.Repeat([]byte{0x02}, 1000)
+
+	storeEvictionTestVariant(t, cache, oldKey, oldContent)
+	storeEvictionTestVariant(t, cache, newKey, newContent)
+	assertVariantServed(t, cache, oldKey, oldContent)
+	setVariantLastAccessed(t, cache, oldKey, time.Now().Add(-time.Hour))
+
+	err := cache.EvictToLimit(t.Context())
+	if err != nil {
+		t.Fatalf("EvictToLimit() error = %v", err)
+	}
+
+	assertLookupMisses(t, cache, oldRequest)
+	assertVariantNotFound(t, cache, oldKey)
+	assertVariantServed(t, cache, newKey, newContent)
+}
+
+// TestVariantDeletedFromDiskIsNotServed checks that a variant whose
+// file was deleted by something other than the evictor cannot be read,
+// and is a miss afterwards.
+func TestVariantDeletedFromDiskIsNotServed(t *testing.T) {
+	t.Parallel()
+
+	cache, _ := newEvictionTestCache(t, 1<<20)
+
+	request := webpRequest("/deleted.jpg")
+	key := CacheKey(request)
+	content := []byte("webp variant bytes")
+
+	storeEvictionTestVariant(t, cache, key, content)
+	assertVariantServed(t, cache, key, content)
+
+	err := os.Remove(cache.variants.keyToPath(key))
+	if err != nil {
+		t.Fatalf("removing variant file: %v", err)
+	}
+
+	assertVariantNotFound(t, cache, key)
+	assertLookupMisses(t, cache, request)
+}
+
+// TestConcurrentVariantStoreReadAndEvict stores, reads and evicts
+// variants from several goroutines at once, for the race detector.
+func TestConcurrentVariantStoreReadAndEvict(t *testing.T) {
+	t.Parallel()
+
+	cache, _ := newEvictionTestCache(t, 1<<20)
+	ctx := t.Context()
+
+	var wg sync.WaitGroup
+
+	for goroutine := range 8 {
+		wg.Go(func() {
+			key := VariantKey(fmt.Sprintf("aabbccdd01%02d", goroutine))
+			content := []byte(key)
+
+			for range 20 {
+				err := cache.StoreVariant(
+					ctx, key, bytes.NewReader(content), testContentTypeWebP)
+				if err != nil {
+					t.Errorf("StoreVariant(%s) error = %v", key, err)
+
+					return
+				}
+
+				reader, _, contentType, err := cache.GetVariant(key)
+				if err != nil {
+					t.Errorf("GetVariant(%s) error = %v", key, err)
+
+					return
+				}
+
+				_ = reader.Close()
+
+				if contentType != testContentTypeWebP {
+					t.Errorf("GetVariant(%s) content type = %q, want %q",
+						key, contentType, testContentTypeWebP)
+				}
+
+				err = cache.evictVariant(ctx, key)
+				if err != nil {
+					t.Errorf("evictVariant(%s) error = %v", key, err)
+
+					return
+				}
+
+				assertVariantNotFound(t, cache, key)
+			}
+		})
+	}
+
+	wg.Wait()
+}

internal/imgcache/negative_cache_internal_test.go

@@ -6,9 +6,6 @@ import (
 	"strconv"
 	"testing"
 	"time"
-
-	"github.com/prometheus/client_golang/prometheus"
-	"sneak.berlin/go/pixa/internal/imagerequest"
 )
 
 func TestNegativeCache_StoreAndCheck(t *testing.T) {
@@ -20,18 +17,15 @@ func TestNegativeCache_StoreAndCheck(t *testing.T) {
 	cache, err := NewCache(db, CacheConfig{
 		StateDir:    dir,
 		NegativeTTL: 5 * time.Minute,
-		MaxBytes:    1 << 30,
+	})
-	}, prometheus.NewRegistry())
 	if err != nil {
 		t.Fatal(err)
 	}
 
 	ctx := context.Background()
-	req := &imagerequest.Request{
+	req := &ImageRequest{
-		Source: imagerequest.Source{
+		SourceHost: testHostExample,
-			Host: testHostExample,
+		SourcePath: "/missing.jpg",
-			Path: "/missing.jpg",
-		},
 	}
 
 	// Initially should not be in negative cache
@@ -45,7 +39,7 @@ func TestNegativeCache_StoreAndCheck(t *testing.T) {
 	}
 
 	// Store a negative entry
-	err = cache.StoreNegative(ctx, req)
+	err = cache.StoreNegative(ctx, req, 404, "not found")
 	if err != nil {
 		t.Fatal(err)
 	}
@@ -70,22 +64,19 @@ func TestNegativeCache_Expired(t *testing.T) {
 	cache, err := NewCache(db, CacheConfig{
 		StateDir:    dir,
 		NegativeTTL: 1 * time.Millisecond, // very short TTL
-		MaxBytes:    1 << 30,
+	})
-	}, prometheus.NewRegistry())
 	if err != nil {
 		t.Fatal(err)
 	}
 
 	ctx := context.Background()
-	req := &imagerequest.Request{
+	req := &ImageRequest{
-		Source: imagerequest.Source{
+		SourceHost: testHostExample,
-			Host: testHostExample,
+		SourcePath: "/expired.jpg",
-			Path: "/expired.jpg",
-		},
 	}
 
 	// Store a negative entry with very short TTL
-	err = cache.StoreNegative(ctx, req)
+	err = cache.StoreNegative(ctx, req, 500, "server error")
 	if err != nil {
 		t.Fatal(err)
 	}
@@ -115,20 +106,20 @@ func TestService_Get_ServesCachedVariantOfNegativeCachedURL(t *testing.T) {
 
 	svc, fixtures := SetupTestService(t)
 
-	resp, err := svc.Get(t.Context(), photoVariant(fixtures, 85, imagerequest.FitCover))
+	resp, err := svc.Get(t.Context(), photoVariant(fixtures, 85, FitCover))
 	if err != nil {
 		t.Fatalf("Get() first request error = %v", err)
 	}
 
 	_ = resp.Content.Close()
 
-	err = svc.cache.StoreNegative(t.Context(),
+	err = svc.cache.StoreNegative(t.Context(), photoVariant(fixtures, 85, FitCover),
-		photoVariant(fixtures, 85, imagerequest.FitCover))
+		httpStatusBadGateway, "upstream answered 503")
 	if err != nil {
 		t.Fatalf("StoreNegative() error = %v", err)
 	}
 
-	resp, err = svc.Get(t.Context(), photoVariant(fixtures, 85, imagerequest.FitCover))
+	resp, err = svc.Get(t.Context(), photoVariant(fixtures, 85, FitCover))
 	if err != nil {
 		t.Fatalf("Get() of the cached variant error = %v", err)
 	}
@@ -140,7 +131,7 @@ func TestService_Get_ServesCachedVariantOfNegativeCachedURL(t *testing.T) {
 			resp.CacheStatus, CacheHit)
 	}
 
-	resp, err = svc.Get(t.Context(), photoVariant(fixtures, 40, imagerequest.FitCover))
+	resp, err = svc.Get(t.Context(), photoVariant(fixtures, 40, FitCover))
 	t.Logf("Get() of a variant made from the cached source: error = %v", err)
 
 	if err != nil {
@@ -149,18 +140,18 @@ func TestService_Get_ServesCachedVariantOfNegativeCachedURL(t *testing.T) {
 
 	_ = resp.Content.Close()
 
-	sourceKey, err := svc.cache.LookupSource(t.Context(),
+	contentHash, _, err := svc.cache.LookupSource(t.Context(),
-		photoVariant(fixtures, 85, imagerequest.FitCover))
+		photoVariant(fixtures, 85, FitCover))
-	if err != nil || sourceKey == "" {
+	if err != nil || contentHash == "" {
-		t.Fatalf("LookupSource() = %q, %v, want the cached source", sourceKey, err)
+		t.Fatalf("LookupSource() = %q, %v, want the cached source", contentHash, err)
 	}
 
-	err = svc.cache.evictSourceBlob(t.Context(), sourceKey)
+	err = svc.cache.evictSourceBlob(t.Context(), contentHash)
 	if err != nil {
 		t.Fatalf("evictSourceBlob() error = %v", err)
 	}
 
-	_, err = svc.Get(t.Context(), photoVariant(fixtures, 60, imagerequest.FitCover))
+	_, err = svc.Get(t.Context(), photoVariant(fixtures, 60, FitCover))
 	t.Logf("Get() of a variant whose source was evicted: error = %v", err)
 
 	if !errors.Is(err, ErrNegativeCached) {
@@ -179,11 +170,11 @@ func TestEvictionLoopRemovesExpiredNegativeCacheRows(t *testing.T) {
 	t.Parallel()
 
 	tests := []struct {
-		name     string
+		name             string
-		maxBytes int64
+		disableDiskCache bool
 	}{
-		{name: "disk cache enabled", maxBytes: 1 << 30},
+		{name: "disk cache enabled", disableDiskCache: false},
-		{name: "disk cache disabled", maxBytes: 0},
+		{name: "disk cache disabled", disableDiskCache: true},
 	}
 
 	for _, tt := range tests {
@@ -191,19 +182,19 @@ func TestEvictionLoopRemovesExpiredNegativeCacheRows(t *testing.T) {
 			t.Parallel()
 
 			cache, err := NewCache(evictionTestDB(t), CacheConfig{
-				StateDir:    t.TempDir(),
+				StateDir:         t.TempDir(),
-				NegativeTTL: time.Second,
+				NegativeTTL:      time.Second,
-				MaxBytes:    tt.maxBytes,
+				DisableDiskCache: tt.disableDiskCache,
-			}, prometheus.NewRegistry())
+			})
 			if err != nil {
 				t.Fatalf("failed to create cache: %v", err)
 			}
 
-			expired := &imagerequest.Request{
+			expired := &ImageRequest{
-				Source: imagerequest.Source{Host: testHostExample, Path: "/gone.jpg"},
+				SourceHost: testHostExample, SourcePath: "/gone.jpg",
 			}
 
-			err = cache.StoreNegative(t.Context(), expired)
+			err = cache.StoreNegative(t.Context(), expired, 404, "not found")
 			if err != nil {
 				t.Fatalf("StoreNegative failed: %v", err)
 			}
@@ -212,8 +203,8 @@ func TestEvictionLoopRemovesExpiredNegativeCacheRows(t *testing.T) {
 
 			_, err = cache.db.ExecContext(t.Context(), `
 				INSERT INTO negative_cache
-					(source_host, source_path, expires_at)
+					(source_host, source_path, status_code, expires_at)
-				VALUES (?, ?, datetime('now', '+1 hour'))
+				VALUES (?, ?, 404, datetime('now', '+1 hour'))
 			`, testHostExample, notExpiredPath)
 			if err != nil {
 				t.Fatalf("failed to insert a row that has not expired: %v", err)
@@ -224,7 +215,7 @@ func TestEvictionLoopRemovesExpiredNegativeCacheRows(t *testing.T) {
 			cache.StartEviction(100 * time.Millisecond)
 			defer func() { _ = cache.StopEviction(t.Context()) }()
 
-			for negativeCacheRowCount(t, cache, expired.Source.Path) > 0 {
+			for negativeCacheRowCount(t, cache, expired.SourcePath) > 0 {
 				if time.Since(started) > 10*time.Second {
 					t.Fatal("the expired row is still in negative_cache")
 				}
@@ -268,9 +259,7 @@ func negativeCacheRowCount(tb testing.TB, cache *Cache, sourcePath string) int {
 func TestCleanExpiredDeletesInBatches(t *testing.T) {
 	t.Parallel()
 
-	cache, err := NewCache(evictionTestDB(t),
+	cache, err := NewCache(evictionTestDB(t), CacheConfig{StateDir: t.TempDir()})
-		CacheConfig{StateDir: t.TempDir(), MaxBytes: 1 << 30},
-		prometheus.NewRegistry())
 	if err != nil {
 		t.Fatalf("failed to create cache: %v", err)
 	}
@@ -283,8 +272,8 @@ func TestCleanExpiredDeletesInBatches(t *testing.T) {
 
 	_, err = cache.db.ExecContext(ctx, `
 		INSERT INTO negative_cache
-			(source_host, source_path, expires_at)
+			(source_host, source_path, status_code, expires_at)
-		VALUES (?, ?, datetime('now', '+1 hour'))
+		VALUES (?, ?, 404, datetime('now', '+1 hour'))
 	`, testHostExample, notExpiredPath)
 	if err != nil {
 		t.Fatalf("failed to insert a row that has not expired: %v", err)
@@ -324,9 +313,7 @@ func TestCleanExpiredDeletesInBatches(t *testing.T) {
 func TestCleanExpiredRemovesMoreThanOneBatch(t *testing.T) {
 	t.Parallel()
 
-	cache, err := NewCache(evictionTestDB(t),
+	cache, err := NewCache(evictionTestDB(t), CacheConfig{StateDir: t.TempDir()})
-		CacheConfig{StateDir: t.TempDir(), MaxBytes: 1 << 30},
-		prometheus.NewRegistry())
 	if err != nil {
 		t.Fatalf("failed to create cache: %v", err)
 	}
@@ -356,9 +343,7 @@ func TestCleanExpiredRemovesMoreThanOneBatch(t *testing.T) {
 func TestCleanExpiredStopsOnceContextEnds(t *testing.T) {
 	t.Parallel()
 
-	cache, err := NewCache(evictionTestDB(t),
+	cache, err := NewCache(evictionTestDB(t), CacheConfig{StateDir: t.TempDir()})
-		CacheConfig{StateDir: t.TempDir(), MaxBytes: 1 << 30},
-		prometheus.NewRegistry())
 	if err != nil {
 		t.Fatalf("failed to create cache: %v", err)
 	}
@@ -386,8 +371,8 @@ func insertExpiredNegativeCacheRows(t *testing.T, cache *Cache, count int) {
 	for i := range count {
 		_, err := cache.db.ExecContext(t.Context(), `
 			INSERT INTO negative_cache
-				(source_host, source_path, expires_at)
+				(source_host, source_path, status_code, expires_at)
-			VALUES (?, ?, datetime('now', '-1 hour'))
+			VALUES (?, ?, 404, datetime('now', '-1 hour'))
 		`, testHostExample, "/expired/"+strconv.Itoa(i)+".jpg")
 		if err != nil {
 			t.Fatalf("failed to insert an expired row: %v", err)

internal/imgcache/partial_cache_files_internal_test.go

@@ -2,33 +2,31 @@ package imgcache
 
 import (
 	"bytes"
+	"crypto/sha256"
+	"encoding/hex"
 	"io"
 	"log/slog"
 	"os"
 	"path/filepath"
 	"strings"
 	"testing"
-
-	"sneak.berlin/go/pixa/internal/imagerequest"
 )
 
 // getImage calls Get for req and returns the image it answered with and
 // its cache status.
-func getImage(
+func getImage(t *testing.T, svc *Service, req *ImageRequest) ([]byte, CacheStatus) {
-	t *testing.T, svc *Service, req *imagerequest.Request,
-) ([]byte, CacheStatus) {
 	t.Helper()
 
 	resp, err := svc.Get(t.Context(), req)
 	if err != nil {
-		t.Fatalf("Get() of quality %d error = %v", req.Transform.Quality, err)
+		t.Fatalf("Get() of quality %d error = %v", req.Quality, err)
 	}
 
 	defer func() { _ = resp.Content.Close() }()
 
 	body, err := io.ReadAll(resp.Content)
 	if err != nil {
-		t.Fatalf("reading the image of quality %d: %v", req.Transform.Quality, err)
+		t.Fatalf("reading the image of quality %d: %v", req.Quality, err)
 	}
 
 	return body, resp.CacheStatus
@@ -60,17 +58,15 @@ func truncateFile(t *testing.T, path string, size int64) {
 }
 
 // cachedSourcePath returns the path of the cached source file req uses.
-func cachedSourcePath(
+func cachedSourcePath(t *testing.T, svc *Service, req *ImageRequest) string {
-	t *testing.T, svc *Service, req *imagerequest.Request,
-) string {
 	t.Helper()
 
-	sourceKey, err := svc.cache.LookupSource(t.Context(), req)
+	contentHash, _, err := svc.cache.LookupSource(t.Context(), req)
-	if err != nil || sourceKey == "" {
+	if err != nil || contentHash == "" {
-		t.Fatalf("LookupSource() = %q, %v; want the cached source", sourceKey, err)
+		t.Fatalf("LookupSource() = %q, %v; want the cached source", contentHash, err)
 	}
 
-	return svc.cache.srcContent.keyToPath(sourceKey)
+	return svc.cache.srcContent.hashToPath(contentHash)
 }
 
 // reconcileAsAtStartup runs the cache's reconciliation pass, as pixa does
@@ -117,18 +113,18 @@ func TestService_Get_FetchesAgainForEmptyCachedSource(t *testing.T) {
 
 	svc, fixtures := SetupTestService(t)
 
-	getImage(t, svc, photoVariant(fixtures, 85, imagerequest.FitCover))
+	getImage(t, svc, photoVariant(fixtures, 85, FitCover))
 
-	path := cachedSourcePath(t, svc, photoVariant(fixtures, 85, imagerequest.FitCover))
+	path := cachedSourcePath(t, svc, photoVariant(fixtures, 85, FitCover))
 	wholeSize := fileSize(t, path)
 
 	truncateFile(t, path, 0)
 	assertWarningNames(t, reconcileAsAtStartup(t, svc.cache), path)
 
-	getImage(t, svc, photoVariant(fixtures, 40, imagerequest.FitCover))
+	getImage(t, svc, photoVariant(fixtures, 40, FitCover))
-	getImage(t, svc, photoVariant(fixtures, 30, imagerequest.FitCover))
+	getImage(t, svc, photoVariant(fixtures, 30, FitCover))
 
-	fetches := readCounters(svc.cache).upstreamFetchCount
+	fetches := readCacheStatsCounters(t, svc.cache).upstreamFetchCount
 	t.Logf("upstream fetches = %d", fetches)
 
 	if fetches != 2 {
@@ -153,18 +149,18 @@ func TestService_Get_FetchesAgainForPartialCachedSource(t *testing.T) {
 
 	svc, fixtures := SetupTestService(t)
 
-	getImage(t, svc, photoVariant(fixtures, 85, imagerequest.FitCover))
+	getImage(t, svc, photoVariant(fixtures, 85, FitCover))
 
-	path := cachedSourcePath(t, svc, photoVariant(fixtures, 85, imagerequest.FitCover))
+	path := cachedSourcePath(t, svc, photoVariant(fixtures, 85, FitCover))
 	wholeSize := fileSize(t, path)
 
 	truncateFile(t, path, wholeSize/2)
 	assertWarningNames(t, reconcileAsAtStartup(t, svc.cache), path)
 
-	getImage(t, svc, photoVariant(fixtures, 40, imagerequest.FitCover))
+	getImage(t, svc, photoVariant(fixtures, 40, FitCover))
-	getImage(t, svc, photoVariant(fixtures, 30, imagerequest.FitCover))
+	getImage(t, svc, photoVariant(fixtures, 30, FitCover))
 
-	fetches := readCounters(svc.cache).upstreamFetchCount
+	fetches := readCacheStatsCounters(t, svc.cache).upstreamFetchCount
 	t.Logf("upstream fetches = %d", fetches)
 
 	if fetches != 2 {
@@ -186,11 +182,11 @@ func assertConvertedAgain(t *testing.T, size int64) {
 	t.Helper()
 
 	svc, fixtures := SetupTestService(t)
-	req := photoVariant(fixtures, 85, imagerequest.FitCover)
+	req := photoVariant(fixtures, 85, FitCover)
 
 	want, _ := getImage(t, svc, req)
 
-	path := svc.cache.variants.keyToPath(imagerequest.CacheKey(req))
+	path := svc.cache.variants.keyToPath(CacheKey(req))
 
 	truncateFile(t, path, size)
 	assertWarningNames(t, reconcileAsAtStartup(t, svc.cache), path)
@@ -239,7 +235,8 @@ func TestReconciliationRemovesEmptyVariantFileWithoutRow(t *testing.T) {
 
 	cache, _ := newEvictionTestCache(t, 1<<30)
 
-	_, err := cache.variants.Store(testVariantKeyOne, bytes.NewReader(nil))
+	_, err := cache.variants.Store(testVariantKeyOne, bytes.NewReader(nil),
+		testContentTypeWebP)
 	if err != nil {
 		t.Fatalf("failed to store an empty variant file: %v", err)
 	}
@@ -260,10 +257,63 @@ func TestReconciliationRemovesEmptyVariantFileWithoutRow(t *testing.T) {
 	}
 }
 
-// TestContentStorage_StoreReplacesFileOfAnotherSize checks that a
+// TestVariantStorage_StoreReplacesMetaFile stores a variant over one
-// store over a file of another size at the source's path, such as a
+// already stored and checks that Store puts a new .meta file in place of
+// the old one, as it does the image, rather than writing into the old
+// file, which a crash could leave empty. The old .meta file is given a
+// second name before the store, so that it can be told apart from the new
+// one after it.
+func TestVariantStorage_StoreReplacesMetaFile(t *testing.T) {
+	t.Parallel()
+
+	storage, key := storeTestVariant(t)
+	metaPath := storage.keyToPath(key) + variantMetaSuffix
+	oldMetaPath := metaPath + ".old"
+
+	err := os.Link(metaPath, oldMetaPath)
+	if err != nil {
+		t.Fatalf("giving the .meta file a second name: %v", err)
+	}
+
+	_, err = storage.Store(key, bytes.NewReader([]byte("new variant data")),
+		testContentTypeJPEG)
+	if err != nil {
+		t.Fatalf("Store() error = %v", err)
+	}
+
+	oldMeta, err := os.Stat(oldMetaPath)
+	if err != nil {
+		t.Fatalf("stat of the old .meta file: %v", err)
+	}
+
+	newMeta, err := os.Stat(metaPath)
+	if err != nil {
+		t.Fatalf("stat of the new .meta file: %v", err)
+	}
+
+	if os.SameFile(oldMeta, newMeta) {
+		t.Error("Store() wrote into the old .meta file instead of putting " +
+			"a new one in its place")
+	}
+
+	reader, _, contentType, err := storage.LoadWithMeta(key)
+	if err != nil {
+		t.Fatalf("LoadWithMeta() error = %v", err)
+	}
+
+	_ = reader.Close()
+
+	t.Logf("content type after the store: %s", contentType)
+
+	if contentType != testContentTypeJPEG {
+		t.Errorf("content type = %q, want %q", contentType, testContentTypeJPEG)
+	}
+}
+
+// TestContentStorage_StoreHashedReplacesFileOfAnotherSize checks that a
+// store over a file of another size at the content's path, such as a
 // partial file a crash left, replaces it with the content.
-func TestContentStorage_StoreReplacesFileOfAnotherSize(t *testing.T) {
+func TestContentStorage_StoreHashedReplacesFileOfAnotherSize(t *testing.T) {
 	t.Parallel()
 
 	storage, err := NewContentStorage(t.TempDir())
@@ -272,12 +322,13 @@ func TestContentStorage_StoreReplacesFileOfAnotherSize(t *testing.T) {
 	}
 
 	content := []byte("the whole source image")
-	key := imagerequest.Source{Host: testHostCDN, Path: testPathCat}.Key()
+	sum := sha256.Sum256(content)
-	path := storage.keyToPath(key)
+	hash := ContentHash(hex.EncodeToString(sum[:]))
+	path := storage.hashToPath(hash)
 
 	err = os.MkdirAll(filepath.Dir(path), StorageDirPerm)
 	if err != nil {
-		t.Fatalf("creating the source's directory: %v", err)
+		t.Fatalf("creating the content's directory: %v", err)
 	}
 
 	err = os.WriteFile(path, content[:5], StorageFilePerm)
@@ -285,14 +336,14 @@ func TestContentStorage_StoreReplacesFileOfAnotherSize(t *testing.T) {
 		t.Fatalf("writing a partial file: %v", err)
 	}
 
-	_, err = storage.Store(key, content)
+	_, err = storage.StoreHashed(hash, content)
 	if err != nil {
-		t.Fatalf("Store() error = %v", err)
+		t.Fatalf("StoreHashed() error = %v", err)
 	}
 
-	stored, _, err := storage.LoadWithSize(key)
+	stored, err := storage.Load(hash)
 	if err != nil {
-		t.Fatalf("LoadWithSize() error = %v", err)
+		t.Fatalf("Load() error = %v", err)
 	}
 
 	defer func() { _ = stored.Close() }()

internal/imgcache/pendingaccesstimes.go

@@ -1,160 +0,0 @@
-package imgcache
-
-import (
-	"context"
-	"fmt"
-	"time"
-
-	"sneak.berlin/go/pixa/internal/imagerequest"
-)
-
-// pendingWriteInterval is how often the goroutine
-// StartPendingAccessTimeWrites starts writes the pending access times.
-// SQLite's CURRENT_TIMESTAMP, which an access time is written as, counts
-// whole seconds.
-const pendingWriteInterval = time.Second
-
-// StartPendingAccessTimeWrites starts the goroutine that writes, every
-// pendingWriteInterval, the pending access times in one transaction.
-// Requests only hand these to it, so none waits for the database to record
-// them, and only this goroutine's write ever waits for it. It is a no-op
-// when already started. The goroutine outlives the caller, so it runs with
-// its own context, which StopPendingAccessTimeWrites cancels to tell it to
-// finish.
-func (c *Cache) StartPendingAccessTimeWrites() {
-	if c.pendingAccessTimesCancel != nil {
-		return
-	}
-
-	ctx, cancel := context.WithCancel(context.Background())
-	c.pendingAccessTimesCancel = cancel
-
-	go func() {
-		c.pendingAccessTimeWriteLoop(ctx)
-	}()
-}
-
-// StopPendingAccessTimeWrites tells the goroutine
-// StartPendingAccessTimeWrites started, if it did, to finish, and waits for
-// its write under way to end and for it to return. It then writes the
-// pending access times left, once, so that they are written before the
-// database closes. It waits for all of this at most until ctx ends. When
-// access times are not written, it logs that and returns an error.
-func (c *Cache) StopPendingAccessTimeWrites(ctx context.Context) error {
-	var err error
-
-	if c.pendingAccessTimesCancel != nil {
-		c.pendingAccessTimesCancel()
-
-		select {
-		case <-c.pendingAccessTimesDone:
-		case <-ctx.Done():
-			// The write given up on here may not reach the database:
-			// database/sql closes without waiting for a query, and a write
-			// still waiting for the connection fails when the database
-			// closes. Nothing is written here.
-			err = fmt.Errorf("access times still being written: %w", ctx.Err())
-		}
-	}
-
-	if err == nil {
-		err = c.writePendingAccessTimes(ctx)
-	}
-
-	if err != nil {
-		c.log.Error("access times not written at shutdown", "error", err)
-	}
-
-	return err
-}
-
-// pendingAccessTimeWriteLoop is the body of the goroutine
-// StartPendingAccessTimeWrites starts. Once ctx is cancelled it starts no
-// write and returns, but does not cut off a write under way then. Access
-// times whose write fails are dropped.
-func (c *Cache) pendingAccessTimeWriteLoop(ctx context.Context) {
-	defer close(c.pendingAccessTimesDone)
-
-	ticker := time.NewTicker(pendingWriteInterval)
-	defer ticker.Stop()
-
-	for {
-		select {
-		case <-ctx.Done():
-			return
-		case <-ticker.C:
-		}
-
-		// select picks at random when ctx is cancelled and a tick waits
-		// too.
-		if ctx.Err() != nil {
-			return
-		}
-
-		err := c.writePendingAccessTimes(context.WithoutCancel(ctx))
-		if err != nil {
-			c.log.Warn("failed to write access times", "error", err)
-		}
-	}
-}
-
-// writePendingAccessTimes takes out the variants waiting in
-// pendingVariantAccessTimes and the sources waiting in
-// pendingSourceAccessTimes, and sets their last_accessed_at to now in one
-// transaction, once for each however often it was used. Nothing else takes
-// from those channels while it runs: only the goroutine
-// StartPendingAccessTimeWrites starts calls it, or
-// StopPendingAccessTimeWrites once that goroutine has returned.
-func (c *Cache) writePendingAccessTimes(ctx context.Context) error {
-	variants := make(map[imagerequest.VariantKey]struct{})
-
-	for range len(c.pendingVariantAccessTimes) {
-		variants[<-c.pendingVariantAccessTimes] = struct{}{}
-	}
-
-	sources := make(map[imagerequest.SourceKey]struct{})
-
-	for range len(c.pendingSourceAccessTimes) {
-		sources[<-c.pendingSourceAccessTimes] = struct{}{}
-	}
-
-	accessTimes := len(variants) + len(sources)
-	if accessTimes == 0 {
-		return nil
-	}
-
-	tx, err := c.db.BeginTx(ctx, nil)
-	if err != nil {
-		return fmt.Errorf("failed to write %d access times: %w", accessTimes, err)
-	}
-
-	// Does nothing once the transaction is committed
-	defer func() { _ = tx.Rollback() }()
-
-	for cacheKey := range variants {
-		_, err = tx.ExecContext(ctx, `
-			UPDATE variant_content SET last_accessed_at = CURRENT_TIMESTAMP
-			WHERE cache_key = ?
-		`, string(cacheKey))
-		if err != nil {
-			return fmt.Errorf("failed to write %d access times: %w", accessTimes, err)
-		}
-	}
-
-	for sourceKey := range sources {
-		_, err = tx.ExecContext(ctx, `
-			UPDATE source_content SET last_accessed_at = CURRENT_TIMESTAMP
-			WHERE source_key = ?
-		`, string(sourceKey))
-		if err != nil {
-			return fmt.Errorf("failed to write %d access times: %w", accessTimes, err)
-		}
-	}
-
-	err = tx.Commit()
-	if err != nil {
-		return fmt.Errorf("failed to write %d access times: %w", accessTimes, err)
-	}
-
-	return nil
-}

internal/imgcache/pendingaccesstimes_internal_test.go

@@ -1,319 +0,0 @@
-package imgcache
-
-import (
-	"bytes"
-	"context"
-	"database/sql"
-	"errors"
-	"log/slog"
-	"strings"
-	"testing"
-	"time"
-
-	"sneak.berlin/go/pixa/internal/imagerequest"
-)
-
-// pendingAccessTimesWait is how long a test waits for the database's
-// connection, for an access time to reach the database, for a write to start
-// waiting for the connection, for a request to return past its deadline, or
-// for StopPendingAccessTimeWrites to return.
-const pendingAccessTimesWait = 5 * time.Second
-
-// otherWritesWait is how long a test gives other writes, once one write waits
-// for the database's connection, to start waiting for it too.
-const otherWritesWait = 100 * time.Millisecond
-
-// holdDatabase takes the one connection of cache's database, so that every
-// other query waits for it, and returns the func that frees it.
-func holdDatabase(t *testing.T, cache *Cache) func() {
-	t.Helper()
-
-	ctx, cancel := context.WithTimeout(t.Context(), pendingAccessTimesWait)
-	defer cancel()
-
-	conn, err := cache.db.Conn(ctx)
-	if err != nil {
-		t.Fatalf("failed to take the database connection: %v", err)
-	}
-
-	return func() { _ = conn.Close() }
-}
-
-// waitForConnectionWaits waits until db.Stats().WaitCount, the number of
-// times a caller has waited for a connection, reaches waits.
-func waitForConnectionWaits(t *testing.T, db *sql.DB, waits int64) {
-	t.Helper()
-
-	deadline := time.Now().Add(pendingAccessTimesWait)
-
-	for db.Stats().WaitCount < waits {
-		if time.Now().After(deadline) {
-			t.Fatalf("callers waited for the database connection %d times, want %d",
-				db.Stats().WaitCount, waits)
-		}
-
-		time.Sleep(10 * time.Millisecond)
-	}
-}
-
-// TestService_Get_ReturnsByItsDeadlineWhileTheDatabaseIsBusy holds the
-// database's one connection while a request whose fetch is held reaches its
-// deadline. The request must return with the deadline's error while the
-// connection is still held, as it waits for no database write past its
-// deadline.
-func TestService_Get_ReturnsByItsDeadlineWhileTheDatabaseIsBusy(t *testing.T) {
-	t.Parallel()
-
-	svc, fixtures, fetcher := setupHeldFetchService(t)
-
-	svc.cache.StartPendingAccessTimeWrites()
-	defer func() { _ = svc.cache.StopPendingAccessTimeWrites(t.Context()) }()
-
-	// Room for the request to reach its fetch on a busy host
-	const timeout = 2 * time.Second
-
-	ctx, cancel := context.WithTimeout(t.Context(), timeout)
-	defer cancel()
-
-	deadline, _ := ctx.Deadline()
-
-	results := startGet(ctx, svc, photoVariant(fixtures, 85, imagerequest.FitCover))
-
-	// The request has made its database reads by the time it fetches.
-	select {
-	case <-fetcher.started:
-	case <-time.After(timeout):
-		t.Fatal("request did not reach its fetch by its deadline")
-	}
-
-	releaseDatabase := holdDatabase(t, svc.cache)
-	defer releaseDatabase()
-
-	select {
-	case got := <-results:
-		t.Logf("Get() returned %v after its deadline, error = %v",
-			time.Since(deadline), got.err)
-
-		if !errors.Is(got.err, context.DeadlineExceeded) {
-			t.Errorf("Get() error = %v, want %v", got.err, context.DeadlineExceeded)
-		}
-	case <-time.After(time.Until(deadline) + pendingAccessTimesWait):
-		t.Fatal("request did not return while the database was busy")
-	}
-}
-
-// TestStopPendingAccessTimeWrites_LetsTheWriteUnderWayFinish holds the
-// database's one connection while the goroutine that writes the pending
-// access times waits for it, hands over another access time, then stops that
-// goroutine. The stop must leave the write under way to finish rather than
-// cut it off, and once the connection is free it must write the access time
-// that write left.
-func TestStopPendingAccessTimeWrites_LetsTheWriteUnderWayFinish(t *testing.T) {
-	t.Parallel()
-
-	cache, _ := newEvictionTestCache(t, 1<<30)
-	anHourAgo := time.Now().Add(-time.Hour)
-
-	for _, key := range []imagerequest.VariantKey{testVariantKeyOne, testVariantKeyTwo} {
-		storeEvictionTestVariant(t, cache, key, []byte("variant bytes"))
-		setVariantLastAccessed(t, cache, key, anHourAgo)
-	}
-
-	cache.StartPendingAccessTimeWrites()
-	defer func() { _ = cache.StopPendingAccessTimeWrites(t.Context()) }()
-
-	releaseDatabase := holdDatabase(t, cache)
-	defer releaseDatabase()
-
-	waitsBefore := cache.db.Stats().WaitCount
-
-	cache.touchVariant(testVariantKeyOne)
-
-	// The goroutine's write waits for the connection.
-	waitForConnectionWaits(t, cache.db, waitsBefore+1)
-
-	// Handed over after that write took the pending access times
-	cache.touchVariant(testVariantKeyTwo)
-
-	// The goroutine is told to finish here as well as by the stop, so that it
-	// is told before its write under way ends, however late the stop runs.
-	// The access time above then reaches the database only through the
-	// stop's own write.
-	cache.pendingAccessTimesCancel()
-
-	stopped := make(chan error, 1)
-
-	go func() {
-		stopped <- cache.StopPendingAccessTimeWrites(t.Context())
-	}()
-
-	// Had the stop cut off the write under way, its own write would wait for
-	// the connection too.
-	time.Sleep(otherWritesWait)
-
-	waits := cache.db.Stats().WaitCount - waitsBefore
-	t.Logf("%d writes waited for the database", waits)
-
-	if waits > 1 {
-		t.Errorf("%d writes waited for the database, want 1: "+
-			"the stop cut off the write under way", waits)
-	}
-
-	releaseDatabase()
-
-	select {
-	case err := <-stopped:
-		if err != nil {
-			t.Fatalf("StopPendingAccessTimeWrites() error = %v", err)
-		}
-	case <-time.After(pendingAccessTimesWait):
-		t.Fatal("StopPendingAccessTimeWrites() did not return once the database was free")
-	}
-
-	for _, key := range []imagerequest.VariantKey{testVariantKeyOne, testVariantKeyTwo} {
-		if countRows(t, cache, `
-			SELECT COUNT(*) FROM variant_content
-			WHERE cache_key = ? AND last_accessed_at > ?
-		`, string(key), anHourAgo.UTC().Format(sqliteTimestampFormat)) != 1 {
-			t.Errorf("the access time of variant %s was not written", key)
-		}
-	}
-}
-
-// TestStopPendingAccessTimeWrites_ReturnsWhenItsContextEnds holds the
-// database's one connection while the goroutine that writes the pending
-// access times waits for it, then stops that goroutine with a context that
-// ends first. The stop must return the context's error, and the write under
-// way must still reach the database once the connection is free.
-func TestStopPendingAccessTimeWrites_ReturnsWhenItsContextEnds(t *testing.T) {
-	t.Parallel()
-
-	cache, _ := newEvictionTestCache(t, 1<<30)
-	storeEvictionTestVariant(t, cache, testVariantKeyOne, []byte("variant bytes"))
-
-	anHourAgo := time.Now().Add(-time.Hour)
-	setVariantLastAccessed(t, cache, testVariantKeyOne, anHourAgo)
-
-	cache.StartPendingAccessTimeWrites()
-	defer func() { _ = cache.StopPendingAccessTimeWrites(t.Context()) }()
-
-	releaseDatabase := holdDatabase(t, cache)
-	defer releaseDatabase()
-
-	waitsBefore := cache.db.Stats().WaitCount
-
-	cache.touchVariant(testVariantKeyOne)
-
-	// The goroutine's write waits for the connection.
-	waitForConnectionWaits(t, cache.db, waitsBefore+1)
-
-	stopCtx, cancelStop := context.WithCancel(t.Context())
-	cancelStop()
-
-	stopped := make(chan error, 1)
-
-	go func() {
-		stopped <- cache.StopPendingAccessTimeWrites(stopCtx)
-	}()
-
-	select {
-	case err := <-stopped:
-		if !errors.Is(err, context.Canceled) {
-			t.Errorf("StopPendingAccessTimeWrites() error = %v, want %v",
-				err, context.Canceled)
-		}
-	case <-time.After(pendingAccessTimesWait):
-		t.Fatal("StopPendingAccessTimeWrites() did not return once its context ended")
-	}
-
-	releaseDatabase()
-
-	deadline := time.Now().Add(pendingAccessTimesWait)
-
-	for countRows(t, cache, `
-		SELECT COUNT(*) FROM variant_content
-		WHERE cache_key = ? AND last_accessed_at > ?
-	`, string(testVariantKeyOne), anHourAgo.UTC().Format(sqliteTimestampFormat)) == 0 {
-		if time.Now().After(deadline) {
-			t.Fatal("the access time being written was not written")
-		}
-
-		time.Sleep(10 * time.Millisecond)
-	}
-}
-
-// TestLookupSource_HandsAccessTimeToTheBackgroundWriter finds a cached source
-// whose access time is an hour old. LookupSource must not write the access
-// time itself but hand it over to be written, and StopPendingAccessTimeWrites
-// must then write it.
-func TestLookupSource_HandsAccessTimeToTheBackgroundWriter(t *testing.T) {
-	t.Parallel()
-
-	cache, _ := newEvictionTestCache(t, 1<<30)
-	key := storeEvictionTestSource(t, cache, "example.com", "/photo.jpg",
-		[]byte("source bytes"))
-	anHourAgo := time.Now().Add(-time.Hour)
-	setSourceLastAccessed(t, cache, key, anHourAgo)
-
-	touchedQuery := `
-		SELECT COUNT(*) FROM source_content
-		WHERE source_key = ? AND last_accessed_at > ?
-	`
-	anHourAgoInDatabase := anHourAgo.UTC().Format(sqliteTimestampFormat)
-
-	found, err := cache.LookupSource(t.Context(), &imagerequest.Request{
-		Source: imagerequest.Source{Host: "example.com", Path: "/photo.jpg"},
-	})
-	if err != nil || found != key {
-		t.Fatalf("LookupSource() = %q, %v; want %q", found, err, key)
-	}
-
-	if countRows(t, cache, touchedQuery, string(key), anHourAgoInDatabase) != 0 {
-		t.Error("LookupSource wrote the source's access time itself")
-	}
-
-	if waiting := len(cache.pendingSourceAccessTimes); waiting != 1 {
-		t.Errorf("%d access times of sources wait to be written, want 1", waiting)
-	}
-
-	err = cache.StopPendingAccessTimeWrites(t.Context())
-	if err != nil {
-		t.Fatalf("StopPendingAccessTimeWrites() error = %v", err)
-	}
-
-	if countRows(t, cache, touchedQuery, string(key), anHourAgoInDatabase) != 1 {
-		t.Error("the source's access time was not written")
-	}
-}
-
-// TestStopPendingAccessTimeWrites_LogsWhatWasNotWritten makes the write of
-// the access times fail at shutdown, by dropping the table they are written
-// to. The stop must return an error and log that access times were not
-// written.
-func TestStopPendingAccessTimeWrites_LogsWhatWasNotWritten(t *testing.T) {
-	t.Parallel()
-
-	cache, _ := newEvictionTestCache(t, 1<<30)
-
-	var logs bytes.Buffer
-
-	cache.log = slog.New(slog.NewJSONHandler(&logs, nil))
-
-	cache.touchVariant(testVariantKeyOne)
-
-	_, err := cache.db.ExecContext(t.Context(), `DROP TABLE variant_content`)
-	if err != nil {
-		t.Fatalf("dropping variant_content: %v", err)
-	}
-
-	err = cache.StopPendingAccessTimeWrites(t.Context())
-	t.Logf("StopPendingAccessTimeWrites() error = %v; logged:\n%s", err, logs.String())
-
-	if err == nil {
-		t.Error("StopPendingAccessTimeWrites() error = nil, want the access times' error")
-	}
-
-	if !strings.Contains(logs.String(), "access times not written at shutdown") {
-		t.Error("the access times not written were not logged")
-	}
-}

internal/imgcache/pendingcounts.go

@@ -0,0 +1,149 @@
+package imgcache
+
+import (
+	"context"
+	"fmt"
+	"sync/atomic"
+)
+
+// StartPendingCountWrites starts the goroutine that writes the pending
+// counts to the database whenever there are some, one UPDATE at a time:
+// however many requests pass their deadline before their counts are
+// written, at most this one write waits for the database. It is a no-op
+// when already started. The goroutine outlives the caller, so it runs with
+// its own context, which StopPendingCountWrites cancels to tell it to
+// finish.
+func (c *Cache) StartPendingCountWrites() {
+	if c.pendingCountsCancel != nil {
+		return
+	}
+
+	ctx, cancel := context.WithCancel(context.Background())
+	c.pendingCountsCancel = cancel
+
+	go func() {
+		c.pendingCountWriteLoop(ctx)
+	}()
+}
+
+// StopPendingCountWrites tells the goroutine StartPendingCountWrites
+// started, if it did, to finish, and waits for its write under way to end
+// and for it to return. It then writes the pending counts left, so that
+// they are written before the database closes. It waits for all of this at
+// most until ctx ends, then logs the counts not written and returns an
+// error.
+func (c *Cache) StopPendingCountWrites(ctx context.Context) error {
+	var err error
+
+	if c.pendingCountsCancel != nil {
+		c.pendingCountsCancel()
+
+		select {
+		case <-c.pendingCountsDone:
+		case <-ctx.Done():
+			// The write given up on here may not reach the database:
+			// database/sql closes without waiting for a query, and a
+			// write still waiting for the connection fails when the
+			// database closes.
+			err = fmt.Errorf("pending counts still being written: %w", ctx.Err())
+		}
+	}
+
+	if err == nil {
+		err = c.writePendingCounts(ctx)
+	}
+
+	if err != nil {
+		c.log.Error("counts not written at shutdown",
+			"hits", c.pendingHits.Load(),
+			"misses", c.pendingMisses.Load(),
+			"upstream_fetches", c.pendingUpstreamFetches.Load(),
+			"upstream_fetch_bytes", c.pendingUpstreamFetchBytes.Load(),
+			"transforms", c.pendingTransforms.Load(),
+			"error", err,
+		)
+
+		return err
+	}
+
+	return nil
+}
+
+// pendingCountWriteLoop is the body of the goroutine
+// StartPendingCountWrites starts. Once ctx is cancelled it starts no write
+// and returns, but does not cut off a write under way then. A write that
+// fails leaves the counts pending, for the next write.
+func (c *Cache) pendingCountWriteLoop(ctx context.Context) {
+	defer close(c.pendingCountsDone)
+
+	for {
+		select {
+		case <-ctx.Done():
+			return
+		case <-c.pendingCountsAdded:
+		}
+
+		// select picks at random when ctx is cancelled and a wakeup
+		// waits too.
+		if ctx.Err() != nil {
+			return
+		}
+
+		err := c.writePendingCounts(context.WithoutCancel(ctx))
+		if err != nil {
+			c.log.Warn("failed to write pending counts", "error", err)
+		}
+	}
+}
+
+// addPendingCount adds n to pendingCount, one of the pending counts, and
+// wakes the goroutine that writes them. pendingCountsAdded has capacity one,
+// so a wakeup already waiting is enough.
+func (c *Cache) addPendingCount(pendingCount *atomic.Int64, n int64) {
+	pendingCount.Add(n)
+
+	select {
+	case c.pendingCountsAdded <- struct{}{}:
+	default:
+	}
+}
+
+// writePendingCounts adds the pending counts to the cache_stats row in one
+// UPDATE, then takes what it wrote out of them, leaving any added
+// meanwhile. When the UPDATE fails, they all stay pending.
+func (c *Cache) writePendingCounts(ctx context.Context) error {
+	c.pendingCountsWriteMutex.Lock()
+	defer c.pendingCountsWriteMutex.Unlock()
+
+	hits := c.pendingHits.Load()
+	misses := c.pendingMisses.Load()
+	upstreamFetches := c.pendingUpstreamFetches.Load()
+	upstreamFetchBytes := c.pendingUpstreamFetchBytes.Load()
+	transforms := c.pendingTransforms.Load()
+
+	if hits+misses+upstreamFetches+upstreamFetchBytes+transforms == 0 {
+		return nil
+	}
+
+	_, err := c.db.ExecContext(ctx, `
+		UPDATE cache_stats
+		SET hit_count = hit_count + ?,
+		    miss_count = miss_count + ?,
+		    upstream_fetch_count = upstream_fetch_count + ?,
+		    upstream_fetch_bytes = upstream_fetch_bytes + ?,
+		    transform_count = transform_count + ?,
+		    last_updated_at = CURRENT_TIMESTAMP
+		WHERE id = 1
+	`, hits, misses, upstreamFetches, upstreamFetchBytes, transforms)
+	if err != nil {
+		return fmt.Errorf("failed to write pending counts: %w", err)
+	}
+
+	c.pendingHits.Add(-hits)
+	c.pendingMisses.Add(-misses)
+	c.pendingUpstreamFetches.Add(-upstreamFetches)
+	c.pendingUpstreamFetchBytes.Add(-upstreamFetchBytes)
+	c.pendingTransforms.Add(-transforms)
+
+	return nil
+}

internal/imgcache/pendingcounts_internal_test.go

@@ -0,0 +1,327 @@
+package imgcache
+
+import (
+	"context"
+	"database/sql"
+	"errors"
+	"testing"
+	"time"
+)
+
+// pendingCountsWait is how long a test waits for the database's connection,
+// for a count to reach the database, for a write to start waiting for the
+// connection, for a request to return past its deadline, or for
+// StopPendingCountWrites to return.
+const pendingCountsWait = 5 * time.Second
+
+// otherWritesWait is how long a test gives other writes, once one write waits
+// for the database's connection, to start waiting for it too.
+const otherWritesWait = 100 * time.Millisecond
+
+// holdDatabase takes the one connection of cache's database, so that every
+// other query waits for it, and returns the func that frees it.
+func holdDatabase(t *testing.T, cache *Cache) func() {
+	t.Helper()
+
+	ctx, cancel := context.WithTimeout(t.Context(), pendingCountsWait)
+	defer cancel()
+
+	conn, err := cache.db.Conn(ctx)
+	if err != nil {
+		t.Fatalf("failed to take the database connection: %v", err)
+	}
+
+	return func() { _ = conn.Close() }
+}
+
+// waitForConnectionWaits waits until db.Stats().WaitCount, the number of
+// times a caller has waited for a connection, reaches waits.
+func waitForConnectionWaits(t *testing.T, db *sql.DB, waits int64) {
+	t.Helper()
+
+	deadline := time.Now().Add(pendingCountsWait)
+
+	for db.Stats().WaitCount < waits {
+		if time.Now().After(deadline) {
+			t.Fatalf("callers waited for the database connection %d times, want %d",
+				db.Stats().WaitCount, waits)
+		}
+
+		time.Sleep(10 * time.Millisecond)
+	}
+}
+
+// waitForCounters waits until the cache_stats row holds want.
+func waitForCounters(t *testing.T, cache *Cache, want cacheStatsCounters) {
+	t.Helper()
+
+	deadline := time.Now().Add(pendingCountsWait)
+
+	for {
+		got := readCacheStatsCounters(t, cache)
+		if got == want {
+			return
+		}
+
+		if time.Now().After(deadline) {
+			t.Fatalf("counters = %+v, want %+v", got, want)
+		}
+
+		time.Sleep(10 * time.Millisecond)
+	}
+}
+
+// TestService_Get_ReturnsByItsDeadlineWhileTheDatabaseIsBusy holds the
+// database's one connection while a request whose fetch is held reaches its
+// deadline. The request must return with the deadline's error while the
+// connection is still held, as it waits for no database write past its
+// deadline, and its miss must reach the database once the connection is free.
+func TestService_Get_ReturnsByItsDeadlineWhileTheDatabaseIsBusy(t *testing.T) {
+	t.Parallel()
+
+	svc, fixtures, fetcher := setupHeldFetchService(t)
+
+	svc.cache.StartPendingCountWrites()
+	defer func() { _ = svc.cache.StopPendingCountWrites(t.Context()) }()
+
+	// Room for the request to reach its fetch on a busy host
+	const timeout = 2 * time.Second
+
+	ctx, cancel := context.WithTimeout(t.Context(), timeout)
+	defer cancel()
+
+	deadline, _ := ctx.Deadline()
+
+	results := startGet(ctx, svc, photoVariant(fixtures, 85, FitCover))
+
+	// The request has made its database reads by the time it fetches.
+	select {
+	case <-fetcher.started:
+	case <-time.After(timeout):
+		t.Fatal("request did not reach its fetch by its deadline")
+	}
+
+	releaseDatabase := holdDatabase(t, svc.cache)
+	defer releaseDatabase()
+
+	select {
+	case got := <-results:
+		t.Logf("Get() returned %v after its deadline, error = %v",
+			time.Since(deadline), got.err)
+
+		if !errors.Is(got.err, context.DeadlineExceeded) {
+			t.Errorf("Get() error = %v, want %v", got.err, context.DeadlineExceeded)
+		}
+	case <-time.After(time.Until(deadline) + pendingCountsWait):
+		t.Fatal("request did not return while the database was busy")
+	}
+
+	releaseDatabase()
+
+	waitForCounters(t, svc.cache, cacheStatsCounters{missCount: 1})
+}
+
+// TestIncrementStats_ManyCountsPastTheirDeadlineLeaveOneWriteWaiting holds the
+// database's one connection while many misses are counted past their
+// deadline. At most one write may then wait for the connection, and every
+// miss must reach the database once it is free.
+func TestIncrementStats_ManyCountsPastTheirDeadlineLeaveOneWriteWaiting(t *testing.T) {
+	t.Parallel()
+
+	cache, _ := newEvictionTestCache(t, 1<<30)
+
+	cache.StartPendingCountWrites()
+	defer func() { _ = cache.StopPendingCountWrites(t.Context()) }()
+
+	releaseDatabase := holdDatabase(t, cache)
+	defer releaseDatabase()
+
+	waitsBefore := cache.db.Stats().WaitCount
+
+	// Writes given a context past its deadline fail at once.
+	ended, cancel := context.WithDeadline(t.Context(), time.Now())
+	defer cancel()
+
+	const misses = 20
+
+	for range misses {
+		cache.IncrementStats(ended, false, 0)
+	}
+
+	// Once one write waits for the connection, any others start waiting too.
+	waitForConnectionWaits(t, cache.db, waitsBefore+1)
+	time.Sleep(otherWritesWait)
+
+	waits := cache.db.Stats().WaitCount - waitsBefore
+	t.Logf("%d writes waited for the database", waits)
+
+	if waits > 1 {
+		t.Errorf("%d writes waited for the database, want at most 1", waits)
+	}
+
+	releaseDatabase()
+
+	waitForCounters(t, cache, cacheStatsCounters{missCount: misses})
+}
+
+// TestStats_IncludesPendingCounts counts hits and misses whose writes miss
+// their deadline, and checks that Stats adds them to the database's counts
+// before they are written.
+func TestStats_IncludesPendingCounts(t *testing.T) {
+	t.Parallel()
+
+	cache, _ := newEvictionTestCache(t, 1<<30)
+
+	_, err := cache.db.ExecContext(t.Context(),
+		`UPDATE cache_stats SET hit_count = 75, miss_count = 25 WHERE id = 1`)
+	if err != nil {
+		t.Fatal(err)
+	}
+
+	// Writes given a context past its deadline fail at once.
+	ended, cancel := context.WithDeadline(t.Context(), time.Now())
+	defer cancel()
+
+	cache.IncrementStats(ended, true, 0)
+	cache.IncrementStats(ended, true, 0)
+	cache.IncrementStats(ended, false, 0)
+
+	stats, err := cache.Stats(t.Context())
+	if err != nil {
+		t.Fatalf("Stats() error = %v", err)
+	}
+
+	if stats.HitCount != 77 || stats.MissCount != 26 {
+		t.Errorf("HitCount = %d, MissCount = %d, want 77 and 26",
+			stats.HitCount, stats.MissCount)
+	}
+
+	want := cacheStatsCounters{hitCount: 75, missCount: 25}
+	if got := readCacheStatsCounters(t, cache); got != want {
+		t.Errorf("counters in the database = %+v, want %+v", got, want)
+	}
+}
+
+// TestStopPendingCountWrites_WritesPendingCounts holds the database's one
+// connection while the goroutine that writes the pending counts waits for it,
+// counts more, then stops that goroutine. The stop must leave the write under
+// way to finish rather than cut it off, and once the connection is free it
+// must write the counts that write left.
+func TestStopPendingCountWrites_WritesPendingCounts(t *testing.T) {
+	t.Parallel()
+
+	cache, _ := newEvictionTestCache(t, 1<<30)
+
+	cache.StartPendingCountWrites()
+	defer func() { _ = cache.StopPendingCountWrites(t.Context()) }()
+
+	releaseDatabase := holdDatabase(t, cache)
+	defer releaseDatabase()
+
+	waitsBefore := cache.db.Stats().WaitCount
+
+	// Writes given a context past its deadline fail at once.
+	ended, cancel := context.WithDeadline(t.Context(), time.Now())
+	defer cancel()
+
+	cache.IncrementStats(ended, true, 0)
+
+	// The goroutine's write waits for the connection.
+	waitForConnectionWaits(t, cache.db, waitsBefore+1)
+
+	// Counted after that write read the pending counts
+	cache.IncrementStats(ended, false, 0)
+	cache.IncrementUpstreamFetch(ended, 1024)
+	cache.IncrementTransformCount(ended)
+
+	// The goroutine is told to finish here as well as by the stop, so that it
+	// is told before its write under way ends, however late the stop runs.
+	// The counts above then reach the database only through the stop's own
+	// write.
+	cache.pendingCountsCancel()
+
+	stopped := make(chan error, 1)
+
+	go func() {
+		stopped <- cache.StopPendingCountWrites(t.Context())
+	}()
+
+	// Had the stop cut off the write under way, its own write would wait for
+	// the connection too.
+	time.Sleep(otherWritesWait)
+
+	waits := cache.db.Stats().WaitCount - waitsBefore
+	t.Logf("%d writes waited for the database", waits)
+
+	if waits > 1 {
+		t.Errorf("%d writes waited for the database, want 1: "+
+			"the stop cut off the write under way", waits)
+	}
+
+	releaseDatabase()
+
+	select {
+	case err := <-stopped:
+		if err != nil {
+			t.Fatalf("StopPendingCountWrites() error = %v", err)
+		}
+	case <-time.After(pendingCountsWait):
+		t.Fatal("StopPendingCountWrites() did not return once the database was free")
+	}
+
+	want := cacheStatsCounters{1, 1, 1, 1024, 1}
+	if got := readCacheStatsCounters(t, cache); got != want {
+		t.Errorf("counters = %+v, want %+v", got, want)
+	}
+}
+
+// TestStopPendingCountWrites_ReturnsWhenItsContextEnds holds the database's
+// one connection while the goroutine that writes the pending counts waits for
+// it, then stops that goroutine with a context that ends first. The stop must
+// return the context's error, and the write under way must still reach the
+// database once the connection is free.
+func TestStopPendingCountWrites_ReturnsWhenItsContextEnds(t *testing.T) {
+	t.Parallel()
+
+	cache, _ := newEvictionTestCache(t, 1<<30)
+
+	cache.StartPendingCountWrites()
+	defer func() { _ = cache.StopPendingCountWrites(t.Context()) }()
+
+	releaseDatabase := holdDatabase(t, cache)
+	defer releaseDatabase()
+
+	waitsBefore := cache.db.Stats().WaitCount
+
+	// Writes given a context past its deadline fail at once.
+	ended, cancel := context.WithDeadline(t.Context(), time.Now())
+	defer cancel()
+
+	cache.IncrementStats(ended, true, 0)
+
+	// The goroutine's write waits for the connection.
+	waitForConnectionWaits(t, cache.db, waitsBefore+1)
+
+	stopCtx, cancelStop := context.WithCancel(t.Context())
+	cancelStop()
+
+	stopped := make(chan error, 1)
+
+	go func() {
+		stopped <- cache.StopPendingCountWrites(stopCtx)
+	}()
+
+	select {
+	case err := <-stopped:
+		if !errors.Is(err, context.Canceled) {
+			t.Errorf("StopPendingCountWrites() error = %v, want %v",
+				err, context.Canceled)
+		}
+	case <-time.After(pendingCountsWait):
+		t.Fatal("StopPendingCountWrites() did not return once its context ended")
+	}
+
+	releaseDatabase()
+
+	waitForCounters(t, cache, cacheStatsCounters{hitCount: 1})
+}

internal/imgcache/service.go

@@ -19,12 +19,12 @@ import (
 	"sneak.berlin/go/pixa/internal/allowlist"
 	"sneak.berlin/go/pixa/internal/httpfetcher"
 	"sneak.berlin/go/pixa/internal/imageprocessor"
-	"sneak.berlin/go/pixa/internal/imagerequest"
 	"sneak.berlin/go/pixa/internal/magic"
 	"sneak.berlin/go/pixa/internal/signature"
 )
 
-// Service orchestrates the cache, fetcher, and processor.
+// Service implements the ImageCache interface, orchestrating cache,
+// fetcher, and processor.
 type Service struct {
 	cache           *Cache
 	fetcher         httpfetcher.Fetcher
@@ -43,20 +43,18 @@ type Service struct {
 type ServiceConfig struct {
 	// Cache is the cache instance
 	Cache *Cache
-	// Fetcher fetches source images from upstream hosts
+	// FetcherConfig configures the upstream fetcher built when Fetcher is
+	// not set. Its AllowHTTP and MaxResponseSize are used either way.
+	FetcherConfig *httpfetcher.Config
+	// Fetcher is an optional custom fetcher (for testing)
 	Fetcher httpfetcher.Fetcher
-	// Processor converts and resizes the images
-	Processor *imageprocessor.ImageProcessor
 	// SigningKey is the HMAC signing key (empty disables signing)
 	SigningKey string
 	// Allowlist is the list of hosts that don't require signatures
 	Allowlist []string
-	// AllowHTTP makes the service fetch sources over http instead of
+	// MaxConcurrentProcessing is the most images processed at once; zero
-	// https (testing only), so the fetcher must allow http too
+	// uses the image processor's default, half the CPUs
-	AllowHTTP bool
+	MaxConcurrentProcessing int
-	// MaxResponseSize is the largest source accepted, in bytes; a cached
-	// source larger than this is fetched again
-	MaxResponseSize int64
 	// Logger for logging
 	Logger *slog.Logger
 }
@@ -77,11 +75,32 @@ func NewService(cfg *ServiceConfig) (*Service, error) {
 		return nil, errSigningKeyRequired
 	}
 
+	// Resolve fetcher config for defaults
+	fetcherCfg := cfg.FetcherConfig
+	if fetcherCfg == nil {
+		fetcherCfg = httpfetcher.DefaultConfig()
+	}
+
+	// Use custom fetcher if provided, otherwise create HTTP fetcher
+	var fetcher httpfetcher.Fetcher
+	if cfg.Fetcher != nil {
+		fetcher = cfg.Fetcher
+	} else {
+		fetcher = httpfetcher.New(fetcherCfg)
+	}
+
+	signer := signature.New(cfg.SigningKey)
+
 	log := cfg.Logger
 	if log == nil {
 		log = slog.Default()
 	}
 
+	allowHTTP := false
+	if cfg.FetcherConfig != nil {
+		allowHTTP = cfg.FetcherConfig.AllowHTTP
+	}
+
 	// JPEG XL is the default output format, so pixad does not start
 	// without it.
 	err := imageprocessor.CheckJPEGXLSupport()
@@ -89,15 +108,21 @@ func NewService(cfg *ServiceConfig) (*Service, error) {
 		return nil, err
 	}
 
+	maxResponseSize := fetcherCfg.MaxResponseSize
+	processor := imageprocessor.New(imageprocessor.Params{
+		MaxInputBytes:           maxResponseSize,
+		MaxConcurrentProcessing: cfg.MaxConcurrentProcessing,
+	})
+
 	return &Service{
 		cache:           cfg.Cache,
-		fetcher:         cfg.Fetcher,
+		fetcher:         fetcher,
-		processor:       cfg.Processor,
+		processor:       processor,
-		signer:          signature.New(cfg.SigningKey),
+		signer:          signer,
 		allowlist:       allowlist.New(cfg.Allowlist),
 		log:             log,
-		allowHTTP:       cfg.AllowHTTP,
+		allowHTTP:       allowHTTP,
-		maxResponseSize: cfg.MaxResponseSize,
+		maxResponseSize: maxResponseSize,
 	}, nil
 }
 
@@ -114,37 +139,34 @@ var ErrProcessingTimedOut = errors.New(
 // While its source URL is in the negative cache, a cached variant is still
 // served and a variant not in the cache is still made from a cached source;
 // only a request that needs the source fetched is refused.
-//
+func (s *Service) Get(ctx context.Context, req *ImageRequest) (*ImageResponse, error) {
-// A cache hit opens the variant file and makes no database call: its access
-// time is handed to the goroutine that StartPendingAccessTimeWrites starts,
-// without waiting for it, and its hit is counted in memory. A variant file
-// that cannot be served, such as one whose first bytes are not those of an
-// output format, is a miss, and the variant is made again.
-func (s *Service) Get(
-	ctx context.Context, req *imagerequest.Request,
-) (*ImageResponse, error) {
 	// Propagate AllowHTTP setting to the request
 	req.AllowHTTP = s.allowHTTP
 
-	cacheKey := imagerequest.CacheKey(req)
+	// Check variant cache first (disk only, no DB)
-
+	result, err := s.cache.Lookup(ctx, req)
-	reader, size, contentType, err := s.cache.GetVariant(cacheKey)
+	if err != nil {
-	if err == nil {
+		s.log.Warn("cache lookup failed", "error", err)
-		s.cache.touchVariant(cacheKey)
-		s.cache.IncrementStats(true, 0)
-
-		return &ImageResponse{
-			Content:       reader,
-			ContentLength: size,
-			ContentType:   contentType,
-			CacheStatus:   CacheHit,
-			ETag:          formatETag(cacheKey),
-		}, nil
 	}
 
-	if !errors.Is(err, ErrNotFound) {
+	// Cache hit - serve directly from disk
-		s.log.Warn("cached variant not served, making it again",
+	if result != nil && result.Hit {
-			"cache_key", cacheKey, "error", err)
+		reader, size, contentType, err := s.cache.GetVariant(result.CacheKey)
+		if err != nil {
+			s.log.Error("failed to get cached variant", "key", result.CacheKey, "error", err)
+			// Fall through to re-process
+		} else {
+			// Counted also when the request context has ended meanwhile
+			s.cache.IncrementStats(ctx, true, 0)
+
+			return &ImageResponse{
+				Content:       reader,
+				ContentLength: size,
+				ContentType:   contentType,
+				CacheStatus:   CacheHit,
+				ETag:          formatETag(result.CacheKey),
+			}, nil
+		}
 	}
 
 	// Cache miss - get the variant, processed once for all the requests that
@@ -152,7 +174,7 @@ func (s *Service) Get(
 	// failed or the request context has ended meanwhile
 	response, err := s.processOrWait(ctx, req)
 
-	s.cache.IncrementStats(false, 0)
+	s.cache.IncrementStats(ctx, false, 0)
 
 	if err != nil {
 		return nil, err
@@ -163,6 +185,18 @@ func (s *Service) Get(
 	return response, nil
 }
 
+// Warm pre-fetches and caches an image without returning it.
+func (s *Service) Warm(ctx context.Context, req *ImageRequest) error {
+	_, err := s.Get(ctx, req)
+
+	return err
+}
+
+// Stats returns cache statistics.
+func (s *Service) Stats(ctx context.Context) (*CacheStats, error) {
+	return s.cache.Stats(ctx)
+}
+
 // WaitForProcessing waits until no image is being processed, or until ctx
 // ends, and returns how many images were still being processed then.
 func (s *Service) WaitForProcessing(ctx context.Context) int {
@@ -170,7 +204,7 @@ func (s *Service) WaitForProcessing(ctx context.Context) int {
 }
 
 // ValidateRequest validates the request signature if required.
-func (s *Service) ValidateRequest(req *imagerequest.Request) error {
+func (s *Service) ValidateRequest(req *ImageRequest) error {
 	// Check if host is allowed (no signature required)
 	sourceURL := req.SourceURL()
 
@@ -193,7 +227,35 @@ func (s *Service) ValidateRequest(req *imagerequest.Request) error {
 	}
 
 	// Signature required for non-allowed hosts
-	return s.signer.Verify(req)
+	return s.signer.Verify(signatureRequest(req))
+}
+
+// GenerateSignedURL generates a signed URL for the given request. The URL
+// carries q and fit next to sig and exp, so the image route verifies it for
+// the quality and fit it was signed with. An unset quality or fit is first
+// set to 85 or cover, the values the route uses when a URL has no q or fit.
+func (s *Service) GenerateSignedURL(
+	baseURL string,
+	req *ImageRequest,
+	ttl time.Duration,
+) (string, error) {
+	if req.Quality == 0 {
+		req.Quality = 85
+	}
+
+	if req.FitMode == "" {
+		req.FitMode = FitCover
+	}
+
+	sigReq := signatureRequest(req)
+	path, sig, exp := s.signer.GenerateSignedURL(sigReq, ttl)
+
+	// Propagate the generated signature and expiration back onto the request.
+	req.Expires = sigReq.Expires
+	req.Signature = sigReq.Signature
+
+	return fmt.Sprintf("%s%s?sig=%s&exp=%d&q=%d&fit=%s",
+		baseURL, path, sig, exp, req.Quality, req.FitMode), nil
 }
 
 // errPanicked is returned when processing a variant panicked.
@@ -206,14 +268,14 @@ var errPanicked = errors.New("panic while processing image")
 // the first request's cancellation, so the others are still served if that
 // client goes away, but keeps its deadline.
 func (s *Service) processOrWait(
-	ctx context.Context, req *imagerequest.Request,
+	ctx context.Context, req *ImageRequest,
 ) (*ImageResponse, error) {
 	// A request that has already ended starts no processing
 	if ctx.Err() != nil {
 		return nil, ctx.Err()
 	}
 
-	cacheKey := imagerequest.CacheKey(req)
+	cacheKey := CacheKey(req)
 
 	// Closed when this request's own function runs, which singleflight does
 	// only when no other request is processing the variant
@@ -231,7 +293,7 @@ func (s *Service) processOrWait(
 				recovered := recover()
 				if recovered != nil {
 					s.log.Error("panic while processing image",
-						"host", req.Source.Host, "path", req.Source.Path,
+						"host", req.SourceHost, "path", req.SourcePath,
 						"panic", recovered, "stack", string(debug.Stack()))
 
 					if hub := sentry.GetHubFromContext(ctx); hub != nil {
@@ -298,9 +360,9 @@ func withoutCancelKeepingDeadline(
 // returns it with its size; nil if the cached data is unavailable, empty or
 // exceeds maxResponseSize.
 func (s *Service) loadCachedSource(
-	sourceKey imagerequest.SourceKey,
+	contentHash ContentHash,
 ) (io.ReadCloser, int64) {
-	reader, size, err := s.cache.GetSourceContent(sourceKey)
+	reader, size, err := s.cache.GetSourceContent(contentHash)
 	if err != nil {
 		s.log.Warn("failed to load cached source, fetching", "error", err)
 
@@ -311,7 +373,7 @@ func (s *Service) loadCachedSource(
 		_ = reader.Close()
 
 		s.log.Warn("cached source exceeds max response size, discarding",
-			"source_key", sourceKey,
+			"hash", contentHash,
 			"max_bytes", s.maxResponseSize,
 		)
 
@@ -331,11 +393,11 @@ func (s *Service) loadCachedSource(
 // if available.
 func (s *Service) processFromSourceOrFetch(
 	ctx context.Context,
-	req *imagerequest.Request,
+	req *ImageRequest,
-	cacheKey imagerequest.VariantKey,
+	cacheKey VariantKey,
 ) (*processedVariant, error) {
 	// Check if we have cached source content
-	sourceKey, err := s.cache.LookupSource(ctx, req)
+	contentHash, _, err := s.cache.LookupSource(ctx, req)
 	if err != nil {
 		s.log.Warn("source lookup failed", "error", err)
 	}
@@ -345,9 +407,9 @@ func (s *Service) processFromSourceOrFetch(
 		sourceSize int64
 	)
 
-	if sourceKey != "" {
+	if contentHash != "" {
-		s.log.Debug("using cached source", "source_key", sourceKey)
+		s.log.Debug("using cached source", "hash", contentHash)
-		source, sourceSize = s.loadCachedSource(sourceKey)
+		source, sourceSize = s.loadCachedSource(contentHash)
 	}
 
 	// Fetch from upstream if we don't have source data or it's empty
@@ -369,8 +431,8 @@ func (s *Service) processFromSourceOrFetch(
 // source URL is in the negative cache.
 func (s *Service) fetchAndProcess(
 	ctx context.Context,
-	req *imagerequest.Request,
+	req *ImageRequest,
-	cacheKey imagerequest.VariantKey,
+	cacheKey VariantKey,
 ) (*processedVariant, error) {
 	// Check negative cache - skip fetching for recently-failed URLs
 	negHit, err := s.cache.checkNegativeCache(ctx, req)
@@ -380,8 +442,8 @@ func (s *Service) fetchAndProcess(
 
 	if negHit {
 		s.log.Debug("negative cache hit",
-			"host", req.Source.Host,
+			"host", req.SourceHost,
-			"path", req.Source.Path,
+			"path", req.SourcePath,
 		)
 
 		return nil, fmt.Errorf("%w: %w", httpfetcher.ErrUpstreamError, ErrNegativeCached)
@@ -396,7 +458,13 @@ func (s *Service) fetchAndProcess(
 	if err != nil {
 		// Store negative cache for certain errors
 		if isNegativeCacheable(err) {
-			s.storeNegative(ctx, req)
+			statusCode := extractStatusCode(err)
+
+			storeErr := s.cache.StoreNegative(ctx, req, statusCode, err.Error())
+			if storeErr != nil {
+				s.log.Warn("failed to store negative cache entry",
+					"host", req.SourceHost, "path", req.SourcePath, "error", storeErr)
+			}
 		}
 
 		return nil, fmt.Errorf("upstream fetch failed: %w", err)
@@ -413,7 +481,7 @@ func (s *Service) fetchAndProcess(
 	fetchBytes := int64(len(sourceData))
 
 	// Counted also when the request context has ended meanwhile
-	s.cache.IncrementUpstreamFetch(fetchBytes)
+	s.cache.IncrementUpstreamFetch(ctx, fetchBytes)
 
 	if err != nil {
 		return nil, fmt.Errorf("failed to read upstream response: %w", err)
@@ -431,8 +499,8 @@ func (s *Service) fetchAndProcess(
 	// Log upstream fetch details
 	s.log.Info("upstream fetched",
 		"request_id", middleware.GetReqID(ctx),
-		"host", req.Source.Host,
+		"host", req.SourceHost,
-		"path", req.Source.Path,
+		"path", req.SourcePath,
 		"bytes", fetchBytes,
 		"fetch_ms", fetchResult.FetchDurationMs,
 		"rate", downloadRate,
@@ -442,21 +510,14 @@ func (s *Service) fetchAndProcess(
 		"cipher", fetchResult.TLSCipherSuite,
 	)
 
-	// Validate magic bytes match content type. A body that does not is the
+	// Validate magic bytes match content type
-	// upstream's error, so it gets a negative cache entry, as an upstream
-	// error status does.
 	err = magic.ValidateMagicBytes(sourceData, fetchResult.ContentType)
 	if err != nil {
-		s.log.Warn("source refused", "request_id", middleware.GetReqID(ctx),
-			"host", req.Source.Host, "path", req.Source.Path,
-			"content_type", fetchResult.ContentType, "error", err)
-		s.storeNegative(ctx, req)
-
 		return nil, fmt.Errorf("content validation failed: %w", err)
 	}
 
 	// Store source content
-	_, err = s.cache.StoreSource(ctx, req, bytes.NewReader(sourceData))
+	_, err = s.cache.StoreSource(ctx, req, bytes.NewReader(sourceData), fetchResult)
 	if err != nil {
 		s.log.Warn("failed to store source content", "error", err)
 		// Continue even if caching fails
@@ -467,17 +528,6 @@ func (s *Service) fetchAndProcess(
 	)
 }
 
-// storeNegative stores a negative cache entry for req's source, whose fetch
-// failed, so the source is not fetched again until the entry expires. A
-// failure to store the entry is only logged.
-func (s *Service) storeNegative(ctx context.Context, req *imagerequest.Request) {
-	err := s.cache.StoreNegative(ctx, req)
-	if err != nil {
-		s.log.Warn("failed to store negative cache entry",
-			"host", req.Source.Host, "path", req.Source.Path, "error", err)
-	}
-}
-
 // processedVariant is a variant as processAndStore made it. Each request that
 // shared its processing serves it through a reader of its own.
 type processedVariant struct {
@@ -490,17 +540,24 @@ type processedVariant struct {
 // result.
 func (s *Service) processAndStore(
 	ctx context.Context,
-	req *imagerequest.Request,
+	req *ImageRequest,
-	cacheKey imagerequest.VariantKey,
+	cacheKey VariantKey,
 	source io.Reader,
 	fetchBytes int64,
 ) (*processedVariant, error) {
 	// Process the image
 	processStart := time.Now()
 
+	processReq := &imageprocessor.Request{
+		Size:    imageprocessor.Size{Width: req.Size.Width, Height: req.Size.Height},
+		Format:  imageprocessor.Format(req.Format),
+		Quality: req.Quality,
+		FitMode: imageprocessor.FitMode(req.FitMode),
+	}
+
 	// ctx has the deadline of the request doing the processing, which can
 	// end while a request waiting for its image has time left
-	processResult, err := s.processor.Process(ctx, source, &req.Transform)
+	processResult, err := s.processor.Process(ctx, source, processReq)
 	if errors.Is(err, context.DeadlineExceeded) {
 		return nil, fmt.Errorf("%w: %w", ErrProcessingTimedOut, err)
 	}
@@ -512,7 +569,7 @@ func (s *Service) processAndStore(
 	processDuration := time.Since(processStart)
 
 	// Counted also when the request context has ended meanwhile
-	s.cache.IncrementTransformCount()
+	s.cache.IncrementTransformCount(ctx)
 
 	// Read processed content
 	processedData, err := io.ReadAll(processResult.Content)
@@ -533,10 +590,10 @@ func (s *Service) processAndStore(
 
 	s.log.Info("image converted",
 		"request_id", middleware.GetReqID(ctx),
-		"host", req.Source.Host,
+		"host", req.SourceHost,
-		"path", req.Source.Path,
+		"path", req.SourcePath,
 		"src_format", processResult.InputFormat,
-		"dst_format", req.Transform.Format,
+		"dst_format", req.Format,
 		"src_bytes", fetchBytes,
 		"dst_bytes", outputSize,
 		"src_dimensions", fmt.Sprintf("%dx%d",
@@ -545,12 +602,14 @@ func (s *Service) processAndStore(
 			processResult.Width, processResult.Height),
 		"size_ratio", fmt.Sprintf("%.1f%%", sizePercent),
 		"convert_ms", processDuration.Milliseconds(),
-		"quality", req.Transform.Quality,
+		"quality", req.Quality,
-		"fit", req.Transform.FitMode,
+		"fit", req.FitMode,
 	)
 
 	// Store variant to cache
-	err = s.cache.StoreVariant(ctx, cacheKey, bytes.NewReader(processedData))
+	err = s.cache.StoreVariant(
+		ctx, cacheKey, bytes.NewReader(processedData), processResult.ContentType,
+	)
 	if err != nil {
 		s.log.Warn("failed to store variant", "error", err)
 		// Continue even if caching fails
@@ -563,16 +622,50 @@ func (s *Service) processAndStore(
 	}, nil
 }
 
+// signatureRequest projects an ImageRequest onto the standalone
+// signature.Request type used by the signature package. This keeps the
+// import edge one-way: imgcache depends on signature, never the reverse.
+func signatureRequest(req *ImageRequest) *signature.Request {
+	return &signature.Request{
+		SourceHost:  req.SourceHost,
+		SourcePath:  req.SourcePath,
+		SourceQuery: req.SourceQuery,
+		Width:       req.Size.Width,
+		Height:      req.Size.Height,
+		Format:      string(req.Format),
+		Quality:     req.Quality,
+		FitMode:     string(req.FitMode),
+		Signature:   req.Signature,
+		Expires:     req.Expires,
+	}
+}
+
+// HTTP status codes for error responses.
+const (
+	httpStatusBadGateway    = 502
+	httpStatusInternalError = 500
+)
+
 // isNegativeCacheable returns true if the error should be cached.
 func isNegativeCacheable(err error) bool {
 	return errors.Is(err, httpfetcher.ErrUpstreamError)
 }
 
+// extractStatusCode extracts HTTP status code from error message.
+func extractStatusCode(err error) int {
+	// Default to 502 Bad Gateway for upstream errors
+	if errors.Is(err, httpfetcher.ErrUpstreamError) {
+		return httpStatusBadGateway
+	}
+
+	return httpStatusInternalError
+}
+
 // etagHashLength is the number of hash characters to use for ETags.
 const etagHashLength = 16
 
 // formatETag formats a VariantKey as a quoted ETag value.
-func formatETag(key imagerequest.VariantKey) string {
+func formatETag(key VariantKey) string {
 	hash := string(key)
 	// Use first 16 characters of hash for a shorter but still unique ETag
 	if len(hash) > etagHashLength {

internal/imgcache/service_internal_test.go

@@ -2,12 +2,12 @@ package imgcache
 
 import (
 	"context"
+	"encoding/json"
 	"io"
 	"os"
 	"testing"
 	"time"
 
-	"sneak.berlin/go/pixa/internal/imagerequest"
 	"sneak.berlin/go/pixa/internal/magic"
 	"sneak.berlin/go/pixa/internal/signature"
 )
@@ -25,17 +25,13 @@ func TestService_Get_AllowlistedHost(t *testing.T) {
 	svc, fixtures := SetupTestService(t)
 	ctx := context.Background()
 
-	req := &imagerequest.Request{
+	req := &ImageRequest{
-		Source: imagerequest.Source{
+		SourceHost: fixtures.GoodHost,
-			Host: fixtures.GoodHost,
+		SourcePath: testPathPhoto,
-			Path: testPathPhoto,
+		Size:       Size{Width: 50, Height: 50},
-		},
+		Format:     FormatJPEG,
-		Transform: imagerequest.Transform{
+		Quality:    85,
-			Size:    imagerequest.Size{Width: 50, Height: 50},
+		FitMode:    FitCover,
-			Format:  imagerequest.FormatJPEG,
-			Quality: 85,
-			FitMode: imagerequest.FitCover,
-		},
 	}
 
 	resp, err := svc.Get(ctx, req)
@@ -65,17 +61,13 @@ func TestService_Get_NonAllowlistedHost_NoSignature(t *testing.T) {
 
 	svc, fixtures := SetupTestService(t, WithSigningKey("test-key"))
 
-	req := &imagerequest.Request{
+	req := &ImageRequest{
-		Source: imagerequest.Source{
+		SourceHost: fixtures.OtherHost,
-			Host: fixtures.OtherHost,
+		SourcePath: testPathUpload,
-			Path: testPathUpload,
+		Size:       Size{Width: 50, Height: 50},
-		},
+		Format:     FormatJPEG,
-		Transform: imagerequest.Transform{
+		Quality:    85,
-			Size:    imagerequest.Size{Width: 50, Height: 50},
+		FitMode:    FitCover,
-			Format:  imagerequest.FormatJPEG,
-			Quality: 85,
-			FitMode: imagerequest.FitCover,
-		},
 	}
 
 	// Should fail validation - not allowlisted and no signature
@@ -92,23 +84,19 @@ func TestService_Get_NonAllowlistedHost_ValidSignature(t *testing.T) {
 	svc, fixtures := SetupTestService(t, WithSigningKey(signingKey))
 	ctx := context.Background()
 
-	req := &imagerequest.Request{
+	req := &ImageRequest{
-		Source: imagerequest.Source{
+		SourceHost: fixtures.OtherHost,
-			Host: fixtures.OtherHost,
+		SourcePath: testPathUpload,
-			Path: testPathUpload,
+		Size:       Size{Width: 50, Height: 50},
-		},
+		Format:     FormatJPEG,
-		Transform: imagerequest.Transform{
+		Quality:    85,
-			Size:    imagerequest.Size{Width: 50, Height: 50},
+		FitMode:    FitCover,
-			Format:  imagerequest.FormatJPEG,
-			Quality: 85,
-			FitMode: imagerequest.FitCover,
-		},
 	}
 
 	// Generate a valid signature
 	signer := signature.New(signingKey)
 	req.Expires = time.Now().Add(time.Hour)
-	req.Signature = signer.Sign(req)
+	req.Signature = signer.Sign(signatureRequest(req))
 
 	// Should pass validation
 	err := svc.ValidateRequest(req)
@@ -140,23 +128,19 @@ func TestService_Get_NonAllowlistedHost_ExpiredSignature(t *testing.T) {
 	signingKey := testSigningKey
 	svc, fixtures := SetupTestService(t, WithSigningKey(signingKey))
 
-	req := &imagerequest.Request{
+	req := &ImageRequest{
-		Source: imagerequest.Source{
+		SourceHost: fixtures.OtherHost,
-			Host: fixtures.OtherHost,
+		SourcePath: testPathUpload,
-			Path: testPathUpload,
+		Size:       Size{Width: 50, Height: 50},
-		},
+		Format:     FormatJPEG,
-		Transform: imagerequest.Transform{
+		Quality:    85,
-			Size:    imagerequest.Size{Width: 50, Height: 50},
+		FitMode:    FitCover,
-			Format:  imagerequest.FormatJPEG,
-			Quality: 85,
-			FitMode: imagerequest.FitCover,
-		},
 	}
 
 	// Generate an expired signature
 	signer := signature.New(signingKey)
 	req.Expires = time.Now().Add(-time.Hour) // Already expired
-	req.Signature = signer.Sign(req)
+	req.Signature = signer.Sign(signatureRequest(req))
 
 	// Should fail validation
 	err := svc.ValidateRequest(req)
@@ -171,17 +155,13 @@ func TestService_Get_NonAllowlistedHost_InvalidSignature(t *testing.T) {
 	signingKey := testSigningKey
 	svc, fixtures := SetupTestService(t, WithSigningKey(signingKey))
 
-	req := &imagerequest.Request{
+	req := &ImageRequest{
-		Source: imagerequest.Source{
+		SourceHost: fixtures.OtherHost,
-			Host: fixtures.OtherHost,
+		SourcePath: testPathUpload,
-			Path: testPathUpload,
+		Size:       Size{Width: 50, Height: 50},
-		},
+		Format:     FormatJPEG,
-		Transform: imagerequest.Transform{
+		Quality:    85,
-			Size:    imagerequest.Size{Width: 50, Height: 50},
+		FitMode:    FitCover,
-			Format:  imagerequest.FormatJPEG,
-			Quality: 85,
-			FitMode: imagerequest.FitCover,
-		},
 	}
 
 	// Set an invalid signature
@@ -211,20 +191,16 @@ func TestService_ValidateRequest_SignatureExactHostMatch(t *testing.T) {
 	signer := signature.New(signingKey)
 
 	// Sign a request for "cdn.example.com"
-	signedReq := &imagerequest.Request{
+	signedReq := &ImageRequest{
-		Source: imagerequest.Source{
+		SourceHost: testHostCDN,
-			Host: testHostCDN,
+		SourcePath: testPathCat,
-			Path: testPathCat,
+		Size:       Size{Width: 50, Height: 50},
-		},
+		Format:     FormatJPEG,
-		Transform: imagerequest.Transform{
+		Quality:    85,
-			Size:    imagerequest.Size{Width: 50, Height: 50},
+		FitMode:    FitCover,
-			Format:  imagerequest.FormatJPEG,
+		Expires:    time.Now().Add(time.Hour),
-			Quality: 85,
-			FitMode: imagerequest.FitCover,
-		},
-		Expires: time.Now().Add(time.Hour),
 	}
-	signedReq.Signature = signer.Sign(signedReq)
+	signedReq.Signature = signer.Sign(signatureRequest(signedReq))
 
 	// The original request should pass validation
 	t.Run("exact host passes", func(t *testing.T) {
@@ -252,22 +228,23 @@ func TestService_ValidateRequest_SignatureExactHostMatch(t *testing.T) {
 		t.Run(tt.name+" rejected", func(t *testing.T) {
 			t.Parallel()
 
-			req := &imagerequest.Request{
+			req := &ImageRequest{
-				Source: imagerequest.Source{
+				SourceHost:  tt.host,
-					Host:  tt.host,
+				SourcePath:  signedReq.SourcePath,
-					Path:  signedReq.Source.Path,
+				SourceQuery: signedReq.SourceQuery,
-					Query: signedReq.Source.Query,
+				Size:        signedReq.Size,
-				},
+				Format:      signedReq.Format,
-				Transform: signedReq.Transform,
+				Quality:     signedReq.Quality,
-				Expires:   signedReq.Expires,
+				FitMode:     signedReq.FitMode,
-				Signature: signedReq.Signature,
+				Expires:     signedReq.Expires,
+				Signature:   signedReq.Signature,
 			}
 
 			err := svc.ValidateRequest(req)
 			if err == nil {
 				t.Errorf(
 					"ValidateRequest() should reject signature for host %q (signed for %q)",
-					tt.host, signedReq.Source.Host)
+					tt.host, signedReq.SourceHost)
 			}
 		})
 	}
@@ -303,17 +280,13 @@ func TestService_ValidateRequest_HostWithPortNeedsSignature(t *testing.T) {
 		t.Run(tt.host, func(t *testing.T) {
 			t.Parallel()
 
-			req := &imagerequest.Request{
+			req := &ImageRequest{
-				Source: imagerequest.Source{
+				SourceHost: tt.host,
-					Host: tt.host,
+				SourcePath: testPathCat,
-					Path: testPathCat,
+				Size:       Size{Width: 50, Height: 50},
-				},
+				Format:     FormatJPEG,
-				Transform: imagerequest.Transform{
+				Quality:    85,
-					Size:    imagerequest.Size{Width: 50, Height: 50},
+				FitMode:    FitCover,
-					Format:  imagerequest.FormatJPEG,
-					Quality: 85,
-					FitMode: imagerequest.FitCover,
-				},
 			}
 
 			err := svc.ValidateRequest(req)
@@ -347,17 +320,13 @@ func TestService_ValidateRequest_UnbracketedIPv6PortNeedsSignature(
 		t.Run(host, func(t *testing.T) {
 			t.Parallel()
 
-			req := &imagerequest.Request{
+			req := &ImageRequest{
-				Source: imagerequest.Source{
+				SourceHost: host,
-					Host: host,
+				SourcePath: testPathCat,
-					Path: testPathCat,
+				Size:       Size{Width: 50, Height: 50},
-				},
+				Format:     FormatJPEG,
-				Transform: imagerequest.Transform{
+				Quality:    85,
-					Size:    imagerequest.Size{Width: 50, Height: 50},
+				FitMode:    FitCover,
-					Format:  imagerequest.FormatJPEG,
-					Quality: 85,
-					FitMode: imagerequest.FitCover,
-				},
 			}
 
 			err := svc.ValidateRequest(req)
@@ -378,9 +347,14 @@ func TestService_Get_InvalidFile(t *testing.T) {
 	svc, fixtures := SetupTestService(t)
 	ctx := context.Background()
 
-	req := photoVariant(fixtures, 85, imagerequest.FitCover)
+	req := &ImageRequest{
-	req.Source.Path = "/images/fake.jpg"
+		SourceHost: fixtures.GoodHost,
-	req.Transform.Size = imagerequest.Size{Width: 50, Height: 50}
+		SourcePath: "/images/fake.jpg",
+		Size:       Size{Width: 50, Height: 50},
+		Format:     FormatJPEG,
+		Quality:    85,
+		FitMode:    FitCover,
+	}
 
 	// Should fail because magic bytes don't match
 	_, err := svc.Get(ctx, req)
@@ -395,9 +369,14 @@ func TestService_Get_NotFound(t *testing.T) {
 	svc, fixtures := SetupTestService(t)
 	ctx := context.Background()
 
-	req := photoVariant(fixtures, 85, imagerequest.FitCover)
+	req := &ImageRequest{
-	req.Source.Path = "/images/nonexistent.jpg"
+		SourceHost: fixtures.GoodHost,
-	req.Transform.Size = imagerequest.Size{Width: 50, Height: 50}
+		SourcePath: "/images/nonexistent.jpg",
+		Size:       Size{Width: 50, Height: 50},
+		Format:     FormatJPEG,
+		Quality:    85,
+		FitMode:    FitCover,
+	}
 
 	_, err := svc.Get(ctx, req)
 	if err == nil {
@@ -414,25 +393,25 @@ func TestService_Get_FormatConversion(t *testing.T) {
 	tests := []struct {
 		name       string
 		sourcePath string
-		outFormat  imagerequest.Format
+		outFormat  ImageFormat
 		wantMIME   string
 	}{
 		{
 			name:       "JPEG to PNG",
 			sourcePath: testPathPhoto,
-			outFormat:  imagerequest.FormatPNG,
+			outFormat:  FormatPNG,
 			wantMIME:   "image/png",
 		},
 		{
 			name:       "PNG to JPEG",
 			sourcePath: "/images/logo.png",
-			outFormat:  imagerequest.FormatJPEG,
+			outFormat:  FormatJPEG,
 			wantMIME:   testContentTypeJPEG,
 		},
 		{
 			name:       "GIF to PNG",
 			sourcePath: "/images/animation.gif",
-			outFormat:  imagerequest.FormatPNG,
+			outFormat:  FormatPNG,
 			wantMIME:   "image/png",
 		},
 	}
@@ -441,12 +420,13 @@ func TestService_Get_FormatConversion(t *testing.T) {
 		t.Run(tt.name, func(t *testing.T) {
 			t.Parallel()
 
-			req := &imagerequest.Request{
+			req := &ImageRequest{
-				Source: imagerequest.Source{Host: fixtures.GoodHost, Path: tt.sourcePath},
+				SourceHost: fixtures.GoodHost,
-				Transform: imagerequest.Transform{
+				SourcePath: tt.sourcePath,
-					Size:   imagerequest.Size{Width: 50, Height: 50},
+				Size:       Size{Width: 50, Height: 50},
-					Format: tt.outFormat, Quality: 85, FitMode: imagerequest.FitCover,
+				Format:     tt.outFormat,
-				},
+				Quality:    85,
+				FitMode:    FitCover,
 			}
 
 			resp, err := svc.Get(ctx, req)
@@ -494,17 +474,13 @@ func TestService_Get_Caching(t *testing.T) {
 	svc, fixtures := SetupTestService(t)
 	ctx := context.Background()
 
-	req := &imagerequest.Request{
+	req := &ImageRequest{
-		Source: imagerequest.Source{
+		SourceHost: fixtures.GoodHost,
-			Host: fixtures.GoodHost,
+		SourcePath: testPathPhoto,
-			Path: testPathPhoto,
+		Size:       Size{Width: 50, Height: 50},
-		},
+		Format:     FormatJPEG,
-		Transform: imagerequest.Transform{
+		Quality:    85,
-			Size:    imagerequest.Size{Width: 50, Height: 50},
+		FitMode:    FitCover,
-			Format:  imagerequest.FormatJPEG,
-			Quality: 85,
-			FitMode: imagerequest.FitCover,
-		},
 	}
 
 	// First request - should be a cache miss
@@ -549,20 +525,26 @@ func TestService_Get_Caching(t *testing.T) {
 
 // TestService_Get_ServesSourceAndVariantCachedTwoDaysAgo caches a source and
 // a variant of it and sets back two days every time pixa stored for them.
-// For the source: last_accessed_at in source_content, and the access and
+// For the source: fetched_at in source_metadata, fetched_at and
-// modification times of its file. For the variant: last_accessed_at in
+// last_accessed_at in source_content, the fetched_at in its metadata file,
-// variant_content, and the access and modification times of its file. It
+// and the access and modification times of its file and of its metadata
-// then checks that the variant is still served from the cache and that a new
+// file. For the variant: created_at and last_accessed_at in variant_content,
-// variant is made from the cached source without fetching it again.
+// the created_at in its .meta file, and the access and modification times of
+// its file and of its .meta file. It then checks that the variant is still
+// served from the cache and that a new variant is made from the cached source
+// without fetching it again.
 //
 // Left at the present: the files' status change and birth times, which a
 // program cannot set, and the times of the directories holding the files,
-// which other entries share.
+// which other entries share. The source's stored response headers are empty,
+// as the mock fetcher sends none. expires_at, etag and last_modified in
+// source_metadata and in the metadata file are never written, nor are the
+// request_cache and output_content tables.
 func TestService_Get_ServesSourceAndVariantCachedTwoDaysAgo(t *testing.T) {
 	t.Parallel()
 
 	svc, fixtures := SetupTestService(t)
-	variant := photoVariant(fixtures, 85, imagerequest.FitCover)
+	variant := photoVariant(fixtures, 85, FitCover)
 
 	resp, err := svc.Get(t.Context(), variant)
 	if err != nil {
@@ -588,14 +570,14 @@ func TestService_Get_ServesSourceAndVariantCachedTwoDaysAgo(t *testing.T) {
 	}
 
 	// Another quality is a new variant, made from the cached source
-	resp, err = svc.Get(t.Context(), photoVariant(fixtures, 40, imagerequest.FitCover))
+	resp, err = svc.Get(t.Context(), photoVariant(fixtures, 40, FitCover))
 	if err != nil {
 		t.Fatalf("Get() of a new variant error = %v", err)
 	}
 
 	_ = resp.Content.Close()
 
-	fetches := readCounters(svc.cache).upstreamFetchCount
+	fetches := readCacheStatsCounters(t, svc.cache).upstreamFetchCount
 	if fetches != 1 {
 		t.Errorf("upstream fetches = %d, want 1", fetches)
 	}
@@ -604,18 +586,43 @@ func TestService_Get_ServesSourceAndVariantCachedTwoDaysAgo(t *testing.T) {
 // backdateSource sets every time pixa stored for req's cached source to when,
 // as listed on TestService_Get_ServesSourceAndVariantCachedTwoDaysAgo.
 func backdateSource(
-	t *testing.T, cache *Cache, req *imagerequest.Request, when time.Time,
+	t *testing.T, cache *Cache, req *ImageRequest, when time.Time,
 ) {
 	t.Helper()
 
-	key := req.Source.Key()
+	pathHash := HashPath(req.SourcePath + "?" + req.SourceQuery)
-	setSourceLastAccessed(t, cache, key, when)
 
-	path := cache.srcContent.keyToPath(key)
+	meta, err := cache.srcMetadata.Load(req.SourceHost, pathHash)
-
-	err := os.Chtimes(path, when, when)
 	if err != nil {
-		t.Fatalf("setting back the times of %s: %v", path, err)
+		t.Fatalf("reading the source's metadata file: %v", err)
+	}
+
+	meta.FetchedAt = when.Unix()
+
+	err = cache.srcMetadata.Store(req.SourceHost, pathHash, meta)
+	if err != nil {
+		t.Fatalf("writing the source's metadata file: %v", err)
+	}
+
+	dbTime := when.UTC().Format(sqliteTimestampFormat)
+
+	updateOneRow(t, cache, `
+		UPDATE source_metadata SET fetched_at = ?
+		WHERE source_host = ? AND source_path = ? AND source_query = ?
+	`, dbTime, req.SourceHost, req.SourcePath, req.SourceQuery)
+	updateOneRow(t, cache,
+		`UPDATE source_content SET fetched_at = ? WHERE content_hash = ?`,
+		dbTime, meta.ContentHash)
+	setSourceLastAccessed(t, cache, ContentHash(meta.ContentHash), when)
+
+	for _, path := range []string{
+		cache.srcContent.hashToPath(ContentHash(meta.ContentHash)),
+		cache.srcMetadata.metaPath(req.SourceHost, pathHash),
+	} {
+		err = os.Chtimes(path, when, when)
+		if err != nil {
+			t.Fatalf("setting back the times of %s: %v", path, err)
+		}
 	}
 }
 
@@ -623,18 +630,62 @@ func backdateSource(
 // for to when, as listed on
 // TestService_Get_ServesSourceAndVariantCachedTwoDaysAgo.
 func backdateVariant(
-	t *testing.T, cache *Cache, req *imagerequest.Request, when time.Time,
+	t *testing.T, cache *Cache, req *ImageRequest, when time.Time,
 ) {
 	t.Helper()
 
-	key := imagerequest.CacheKey(req)
+	key := CacheKey(req)
+
+	content, size, contentType, err := cache.variants.LoadWithMeta(key)
+	if err != nil || contentType == "" {
+		t.Fatalf("reading the variant's .meta file: content type %q, error %v",
+			contentType, err)
+	}
+
+	_ = content.Close()
+
+	meta, err := json.Marshal(VariantMeta{
+		ContentType: contentType,
+		Size:        size,
+		CreatedAt:   when.Unix(),
+	})
+	if err != nil {
+		t.Fatalf("encoding the variant's .meta file: %v", err)
+	}
+
 	path := cache.variants.keyToPath(key)
 
+	err = os.WriteFile(path+variantMetaSuffix, meta, StorageFilePerm)
+	if err != nil {
+		t.Fatalf("writing the variant's .meta file: %v", err)
+	}
+
+	updateOneRow(t, cache,
+		`UPDATE variant_content SET created_at = ? WHERE cache_key = ?`,
+		when.UTC().Format(sqliteTimestampFormat), string(key))
 	setVariantLastAccessed(t, cache, key, when)
 
-	err := os.Chtimes(path, when, when)
+	for _, file := range []string{path, path + variantMetaSuffix} {
+		err = os.Chtimes(file, when, when)
+		if err != nil {
+			t.Fatalf("setting back the times of %s: %v", file, err)
+		}
+	}
+}
+
+// updateOneRow runs the UPDATE statement query and fails the test unless it
+// changed exactly one row.
+func updateOneRow(t *testing.T, cache *Cache, query string, args ...any) {
+	t.Helper()
+
+	result, err := cache.db.ExecContext(t.Context(), query, args...)
 	if err != nil {
-		t.Fatalf("setting back the times of %s: %v", path, err)
+		t.Fatalf("%s: %v", query, err)
+	}
+
+	rows, err := result.RowsAffected()
+	if err != nil || rows != 1 {
+		t.Fatalf("%s: rows = %d, error = %v, want 1 row", query, rows, err)
 	}
 }
 
@@ -645,7 +696,7 @@ func TestService_Get_DifferentSizes(t *testing.T) {
 	ctx := context.Background()
 
 	// Request same image at different sizes
-	sizes := []imagerequest.Size{
+	sizes := []Size{
 		{Width: 25, Height: 25},
 		{Width: 50, Height: 50},
 		{Width: 75, Height: 75},
@@ -654,17 +705,13 @@ func TestService_Get_DifferentSizes(t *testing.T) {
 	responses := make([][]byte, 0, len(sizes))
 
 	for _, size := range sizes {
-		req := &imagerequest.Request{
+		req := &ImageRequest{
-			Source: imagerequest.Source{
+			SourceHost: fixtures.GoodHost,
-				Host: fixtures.GoodHost,
+			SourcePath: testPathPhoto,
-				Path: testPathPhoto,
+			Size:       size,
-			},
+			Format:     FormatJPEG,
-			Transform: imagerequest.Transform{
+			Quality:    85,
-				Size:    size,
+			FitMode:    FitCover,
-				Format:  imagerequest.FormatJPEG,
-				Quality: 85,
-				FitMode: imagerequest.FitCover,
-			},
 		}
 
 		resp, err := svc.Get(ctx, req)
@@ -698,17 +745,13 @@ func TestService_ValidateRequest_NoSigningKey(t *testing.T) {
 	// Service with no signing key - all non-allowlisted requests should fail
 	svc, fixtures := SetupTestService(t, WithNoAllowlist())
 
-	req := &imagerequest.Request{
+	req := &ImageRequest{
-		Source: imagerequest.Source{
+		SourceHost: fixtures.OtherHost,
-			Host: fixtures.OtherHost,
+		SourcePath: testPathUpload,
-			Path: testPathUpload,
+		Size:       Size{Width: 50, Height: 50},
-		},
+		Format:     FormatJPEG,
-		Transform: imagerequest.Transform{
+		Quality:    85,
-			Size:    imagerequest.Size{Width: 50, Height: 50},
+		FitMode:    FitCover,
-			Format:  imagerequest.FormatJPEG,
-			Quality: 85,
-			FitMode: imagerequest.FitCover,
-		},
 	}
 
 	err := svc.ValidateRequest(req)
@@ -727,17 +770,13 @@ func TestService_Get_ContextCancellation(t *testing.T) {
 	ctx, cancel := context.WithCancel(context.Background())
 	cancel() // Cancel immediately
 
-	req := &imagerequest.Request{
+	req := &ImageRequest{
-		Source: imagerequest.Source{
+		SourceHost: fixtures.GoodHost,
-			Host: fixtures.GoodHost,
+		SourcePath: testPathPhoto,
-			Path: testPathPhoto,
+		Size:       Size{Width: 50, Height: 50},
-		},
+		Format:     FormatJPEG,
-		Transform: imagerequest.Transform{
+		Quality:    85,
-			Size:    imagerequest.Size{Width: 50, Height: 50},
+		FitMode:    FitCover,
-			Format:  imagerequest.FormatJPEG,
-			Quality: 85,
-			FitMode: imagerequest.FitCover,
-		},
 	}
 
 	_, err := svc.Get(ctx, req)
@@ -752,17 +791,13 @@ func TestService_Get_ReturnsETag(t *testing.T) {
 	svc, fixtures := SetupTestService(t)
 	ctx := context.Background()
 
-	req := &imagerequest.Request{
+	req := &ImageRequest{
-		Source: imagerequest.Source{
+		SourceHost: fixtures.GoodHost,
-			Host: fixtures.GoodHost,
+		SourcePath: testPathPhoto,
-			Path: testPathPhoto,
+		Size:       Size{Width: 50, Height: 50},
-		},
+		Format:     FormatJPEG,
-		Transform: imagerequest.Transform{
+		Quality:    85,
-			Size:    imagerequest.Size{Width: 50, Height: 50},
+		FitMode:    FitCover,
-			Format:  imagerequest.FormatJPEG,
-			Quality: 85,
-			FitMode: imagerequest.FitCover,
-		},
 	}
 
 	resp, err := svc.Get(ctx, req)
@@ -789,17 +824,13 @@ func TestService_Get_ETagConsistency(t *testing.T) {
 	svc, fixtures := SetupTestService(t)
 	ctx := context.Background()
 
-	req := &imagerequest.Request{
+	req := &ImageRequest{
-		Source: imagerequest.Source{
+		SourceHost: fixtures.GoodHost,
-			Host: fixtures.GoodHost,
+		SourcePath: testPathPhoto,
-			Path: testPathPhoto,
+		Size:       Size{Width: 50, Height: 50},
-		},
+		Format:     FormatJPEG,
-		Transform: imagerequest.Transform{
+		Quality:    85,
-			Size:    imagerequest.Size{Width: 50, Height: 50},
+		FitMode:    FitCover,
-			Format:  imagerequest.FormatJPEG,
-			Quality: 85,
-			FitMode: imagerequest.FitCover,
-		},
 	}
 
 	// First request
@@ -835,30 +866,22 @@ func TestService_Get_DifferentETagsForDifferentContent(t *testing.T) {
 	ctx := context.Background()
 
 	// Request same image at different sizes - should get different ETags
-	req1 := &imagerequest.Request{
+	req1 := &ImageRequest{
-		Source: imagerequest.Source{
+		SourceHost: fixtures.GoodHost,
-			Host: fixtures.GoodHost,
+		SourcePath: testPathPhoto,
-			Path: testPathPhoto,
+		Size:       Size{Width: 25, Height: 25},
-		},
+		Format:     FormatJPEG,
-		Transform: imagerequest.Transform{
+		Quality:    85,
-			Size:    imagerequest.Size{Width: 25, Height: 25},
+		FitMode:    FitCover,
-			Format:  imagerequest.FormatJPEG,
-			Quality: 85,
-			FitMode: imagerequest.FitCover,
-		},
 	}
 
-	req2 := &imagerequest.Request{
+	req2 := &ImageRequest{
-		Source: imagerequest.Source{
+		SourceHost: fixtures.GoodHost,
-			Host: fixtures.GoodHost,
+		SourcePath: testPathPhoto,
-			Path: testPathPhoto,
+		Size:       Size{Width: 50, Height: 50},
-		},
+		Format:     FormatJPEG,
-		Transform: imagerequest.Transform{
+		Quality:    85,
-			Size:    imagerequest.Size{Width: 50, Height: 50},
+		FitMode:    FitCover,
-			Format:  imagerequest.FormatJPEG,
-			Quality: 85,
-			FitMode: imagerequest.FitCover,
-		},
 	}
 
 	resp1, err := svc.Get(ctx, req1)

internal/imgcache/source_content_internal_test.go

@@ -1,141 +0,0 @@
-package imgcache
-
-import (
-	"bytes"
-	"io"
-	"os"
-	"path/filepath"
-	"testing"
-
-	"sneak.berlin/go/pixa/internal/imagerequest"
-)
-
-// TestStoreSource_StoresIdenticalBytesOfTwoURLsTwice stores the same bytes
-// for two source URLs and checks that each URL has a source_content row of
-// its own and a file of its own, named by its source key under
-// cache/sources/<ab>/<cd>/.
-func TestStoreSource_StoresIdenticalBytesOfTwoURLsTwice(t *testing.T) {
-	t.Parallel()
-
-	cache, stateDir := newEvictionTestCache(t, 1<<30)
-	content := bytes.Repeat([]byte{0x5A}, 400)
-
-	keys := map[string]imagerequest.SourceKey{
-		"/a.jpg": storeEvictionTestSource(t, cache, testHostCDN, "/a.jpg", content),
-		"/b.jpg": storeEvictionTestSource(t, cache, testHostCDN, "/b.jpg", content),
-	}
-	t.Logf("source keys: %v", keys)
-
-	if keys["/a.jpg"] == keys["/b.jpg"] {
-		t.Fatalf("both source URLs got the key %s", keys["/a.jpg"])
-	}
-
-	for sourcePath, key := range keys {
-		rows := countRows(t, cache,
-			`SELECT COUNT(*) FROM source_content WHERE source_key = ?`, string(key))
-		if rows != 1 {
-			t.Errorf("%s has %d source_content rows, want 1", sourcePath, rows)
-		}
-
-		name := string(key)
-		file := filepath.Join(stateDir, "cache", "sources", name[0:2], name[2:4], name)
-
-		stored, err := os.ReadFile(file) //nolint:gosec // path in the test's state dir
-		if err != nil || !bytes.Equal(stored, content) {
-			t.Errorf("file of %s at %s holds %d bytes (error %v), want the %d stored",
-				sourcePath, file, len(stored), err, len(content))
-		}
-	}
-
-	usage, err := cache.UsageBytes(t.Context())
-	if err != nil {
-		t.Fatalf("UsageBytes() error = %v", err)
-	}
-
-	if usage != 800 {
-		t.Errorf("UsageBytes() = %d, want 800, the 400 bytes once for each URL", usage)
-	}
-}
-
-// TestEvictSourceBlob_LeavesSourceWithIdenticalBytesServed stores the same
-// bytes for two source URLs and evicts the first. Its row and file must be
-// gone, and the second must still be found and read from the cache.
-func TestEvictSourceBlob_LeavesSourceWithIdenticalBytesServed(t *testing.T) {
-	t.Parallel()
-
-	cache, _ := newEvictionTestCache(t, 1<<30)
-	content := bytes.Repeat([]byte{0x5B}, 400)
-
-	evicted := storeEvictionTestSource(t, cache, testHostCDN, "/evicted.jpg", content)
-	storeEvictionTestSource(t, cache, testHostCDN, "/kept.jpg", content)
-
-	err := cache.evictSourceBlob(t.Context(), evicted)
-	if err != nil {
-		t.Fatalf("evictSourceBlob() error = %v", err)
-	}
-
-	if cache.srcContent.Exists(evicted) {
-		t.Error("the evicted source's file is still on disk")
-	}
-
-	if n := countRows(t, cache,
-		`SELECT COUNT(*) FROM source_content WHERE source_key = ?`, string(evicted),
-	); n != 0 {
-		t.Errorf("the evicted source still has %d source_content rows", n)
-	}
-
-	kept, err := cache.LookupSource(t.Context(), &imagerequest.Request{
-		Source: imagerequest.Source{Host: testHostCDN, Path: "/kept.jpg"},
-	})
-	t.Logf("LookupSource() of the kept source = %q, error %v", kept, err)
-
-	if err != nil || kept == "" {
-		t.Fatalf("LookupSource() of the kept source = %q, %v; want it cached", kept, err)
-	}
-
-	reader, _, err := cache.GetSourceContent(kept)
-	if err != nil {
-		t.Fatalf("GetSourceContent() of the kept source error = %v", err)
-	}
-
-	defer func() { _ = reader.Close() }()
-
-	served, err := io.ReadAll(reader)
-	if err != nil {
-		t.Fatalf("reading the kept source: %v", err)
-	}
-
-	if !bytes.Equal(served, content) {
-		t.Errorf("the kept source reads as %d bytes, want the %d stored",
-			len(served), len(content))
-	}
-}
-
-// TestStoreSource_FailedRowWriteLeavesNoFile drops source_content, so that
-// StoreSource cannot write the source's row, and checks that the store fails
-// and leaves no file under the source's key.
-func TestStoreSource_FailedRowWriteLeavesNoFile(t *testing.T) {
-	t.Parallel()
-
-	cache, _ := newEvictionTestCache(t, 1<<30)
-
-	_, err := cache.db.ExecContext(t.Context(), `DROP TABLE source_content`)
-	if err != nil {
-		t.Fatalf("failed to drop source_content: %v", err)
-	}
-
-	req := &imagerequest.Request{
-		Source: imagerequest.Source{Host: testHostCDN, Path: testPathCat},
-	}
-	key, err := cache.StoreSource(t.Context(), req,
-		bytes.NewReader([]byte("source bytes")))
-	t.Logf("StoreSource() = %q, error = %v", key, err)
-
-	if err == nil {
-		t.Error("StoreSource() error = nil, want the failed row write")
-	}
-
-	if cache.srcContent.Exists(req.Source.Key()) {
-		t.Error("the source's file is on disk although its row was not written")
-	}
-}

internal/imgcache/sourceurl_internal_test.go

@@ -1,16 +1,14 @@
-package imagerequest
+package imgcache
 
 import "testing"
 
-func TestRequest_SourceURL_DefaultHTTPS(t *testing.T) {
+func TestImageRequest_SourceURL_DefaultHTTPS(t *testing.T) {
 	t.Parallel()
 
-	req := &Request{
+	req := &ImageRequest{
-		Source: Source{
+		SourceHost:  testHostCDN,
-			Host:  testHostCDN,
+		SourcePath:  testPathCat,
-			Path:  testPathCat,
+		SourceQuery: "v=2",
-			Query: "v=2",
-		},
 	}
 
 	got := req.SourceURL()
@@ -21,15 +19,13 @@ func TestRequest_SourceURL_DefaultHTTPS(t *testing.T) {
 	}
 }
 
-func TestRequest_SourceURL_AllowHTTP(t *testing.T) {
+func TestImageRequest_SourceURL_AllowHTTP(t *testing.T) {
 	t.Parallel()
 
-	req := &Request{
+	req := &ImageRequest{
-		Source: Source{
+		SourceHost: "localhost:8080",
-			Host: "localhost:8080",
+		SourcePath: testPathCat,
-			Path: testPathCat,
+		AllowHTTP:  true,
-		},
-		AllowHTTP: true,
 	}
 
 	got := req.SourceURL()
@@ -40,15 +36,13 @@ func TestRequest_SourceURL_AllowHTTP(t *testing.T) {
 	}
 }
 
-func TestRequest_SourceURL_AllowHTTPFalse(t *testing.T) {
+func TestImageRequest_SourceURL_AllowHTTPFalse(t *testing.T) {
 	t.Parallel()
 
-	req := &Request{
+	req := &ImageRequest{
-		Source: Source{
+		SourceHost: testHostCDN,
-			Host: testHostCDN,
+		SourcePath: "/img.jpg",
-			Path: "/img.jpg",
+		AllowHTTP:  false,
-		},
-		AllowHTTP: false,
 	}
 
 	got := req.SourceURL()

internal/imgcache/stats_internal_test.go

@@ -3,18 +3,281 @@ package imgcache
 import (
 	"bytes"
 	"context"
+	"database/sql"
 	"image/color"
 	"io"
 	"io/fs"
+	"log/slog"
+	"math"
+	"strings"
 	"testing"
+	"time"
 
+	"sneak.berlin/go/pixa/internal/database"
 	"sneak.berlin/go/pixa/internal/httpfetcher"
-	"sneak.berlin/go/pixa/internal/imagerequest"
 )
 
+func setupStatsTestDB(t *testing.T) *sql.DB {
+	t.Helper()
+
+	db, err := sql.Open("sqlite", ":memory:")
+	if err != nil {
+		t.Fatal(err)
+	}
+
+	err = database.ApplyMigrations(context.Background(), db, nil)
+	if err != nil {
+		t.Fatal(err)
+	}
+
+	t.Cleanup(func() { _ = db.Close() })
+
+	return db
+}
+
+func TestStats_HitRateIsRatio(t *testing.T) {
+	t.Parallel()
+
+	db := setupStatsTestDB(t)
+	dir := t.TempDir()
+
+	cache, err := NewCache(db, CacheConfig{
+		StateDir:    dir,
+		NegativeTTL: 5 * time.Minute,
+	})
+	if err != nil {
+		t.Fatal(err)
+	}
+
+	ctx := context.Background()
+
+	// Set some hit/miss counts and a transform_count
+	_, err = db.ExecContext(ctx, `
+		UPDATE cache_stats
+		SET hit_count = 75, miss_count = 25, transform_count = 9999
+		WHERE id = 1
+	`)
+	if err != nil {
+		t.Fatal(err)
+	}
+
+	stats, err := cache.Stats(ctx)
+	if err != nil {
+		t.Fatal(err)
+	}
+
+	if stats.HitCount != 75 {
+		t.Errorf("HitCount = %d, want 75", stats.HitCount)
+	}
+
+	if stats.MissCount != 25 {
+		t.Errorf("MissCount = %d, want 25", stats.MissCount)
+	}
+
+	// HitRate should be 0.75, NOT 9999 (transform_count)
+	expectedRate := 0.75
+	if math.Abs(stats.HitRate-expectedRate) > 0.001 {
+		t.Errorf("HitRate = %f, want %f (was it scanning transform_count?)",
+			stats.HitRate, expectedRate)
+	}
+}
+
+func TestStats_ZeroCounts(t *testing.T) {
+	t.Parallel()
+
+	db := setupStatsTestDB(t)
+	dir := t.TempDir()
+
+	cache, err := NewCache(db, CacheConfig{
+		StateDir:    dir,
+		NegativeTTL: 5 * time.Minute,
+	})
+	if err != nil {
+		t.Fatal(err)
+	}
+
+	stats, err := cache.Stats(context.Background())
+	if err != nil {
+		t.Fatal(err)
+	}
+
+	// With zero hits and misses, HitRate should be 0, not some garbage value
+	if stats.HitRate != 0.0 {
+		t.Errorf("HitRate = %f, want 0.0 for zero counts", stats.HitRate)
+	}
+}
+
+// TestStats_LogsFailedCountQueries verifies that a failed item count query
+// and a failed size query are each logged at warn and Stats still succeeds.
+func TestStats_LogsFailedCountQueries(t *testing.T) {
+	t.Parallel()
+
+	db := setupStatsTestDB(t)
+
+	var logBuf bytes.Buffer
+
+	cache, err := NewCache(db, CacheConfig{
+		StateDir:    t.TempDir(),
+		NegativeTTL: 5 * time.Minute,
+		Logger:      slog.New(slog.NewJSONHandler(&logBuf, nil)),
+	})
+	if err != nil {
+		t.Fatal(err)
+	}
+
+	_, err = db.ExecContext(t.Context(),
+		`DROP TABLE source_content; DROP TABLE variant_content`)
+	if err != nil {
+		t.Fatal(err)
+	}
+
+	_, err = cache.Stats(t.Context())
+	if err != nil {
+		t.Fatalf("Stats() error = %v, want nil", err)
+	}
+
+	for _, msg := range []string{
+		"failed to count cache items for stats",
+		"failed to sum cache size for stats",
+	} {
+		want := `"level":"WARN","msg":"` + msg + `"`
+		if !strings.Contains(logBuf.String(), want) {
+			t.Errorf("log missing %s; got %q", want, logBuf.String())
+		}
+	}
+}
+
+// TestIncrementStats_LogsFailedUpdates verifies that a failed hit or miss
+// count update and a failed upstream fetch count update are each logged at
+// warn.
+func TestIncrementStats_LogsFailedUpdates(t *testing.T) {
+	t.Parallel()
+
+	db := setupStatsTestDB(t)
+
+	var logBuf bytes.Buffer
+
+	cache, err := NewCache(db, CacheConfig{
+		StateDir:    t.TempDir(),
+		NegativeTTL: 5 * time.Minute,
+		Logger:      slog.New(slog.NewJSONHandler(&logBuf, nil)),
+	})
+	if err != nil {
+		t.Fatal(err)
+	}
+
+	_, err = db.ExecContext(t.Context(), `DROP TABLE cache_stats`)
+	if err != nil {
+		t.Fatal(err)
+	}
+
+	cache.IncrementStats(t.Context(), false, 1024)
+
+	for _, msg := range []string{
+		"failed to count cache hit or miss",
+		"failed to count upstream fetch",
+	} {
+		want := `"level":"WARN","msg":"` + msg + `"`
+		if !strings.Contains(logBuf.String(), want) {
+			t.Errorf("log missing %s; got %q", want, logBuf.String())
+		}
+	}
+}
+
+// TestStats_TotalsCountSourcesAndVariants verifies that TotalItems and
+// TotalSizeBytes cover the stored source images and processed variants.
+func TestStats_TotalsCountSourcesAndVariants(t *testing.T) {
+	t.Parallel()
+
+	cache, _ := newEvictionTestCache(t, 1<<30)
+
+	storeEvictionTestSource(t, cache, testHostCDN, testPathCat,
+		bytes.Repeat([]byte{0xAA}, 1000))
+	storeEvictionTestVariant(t, cache, testVariantKeyOne,
+		bytes.Repeat([]byte{0xAB}, 500))
+	storeEvictionTestVariant(t, cache, testVariantKeyTwo,
+		bytes.Repeat([]byte{0xAC}, 250))
+
+	stats, err := cache.Stats(t.Context())
+	if err != nil {
+		t.Fatalf("Stats() error = %v", err)
+	}
+
+	if stats.TotalItems != 3 {
+		t.Errorf("TotalItems = %d, want 3 (1 source, 2 variants)", stats.TotalItems)
+	}
+
+	if stats.TotalSizeBytes != 1750 {
+		t.Errorf("TotalSizeBytes = %d, want 1750 (1000+500+250)",
+			stats.TotalSizeBytes)
+	}
+}
+
+// TestStats_DisabledCacheReportsNoItems verifies that a disabled disk cache
+// reports no items and no size, even when its database still holds the
+// rows of an earlier run with the disk cache enabled.
+func TestStats_DisabledCacheReportsNoItems(t *testing.T) {
+	t.Parallel()
+
+	enabled, _ := newEvictionTestCache(t, 1<<30)
+
+	storeEvictionTestSource(t, enabled, testHostCDN, testPathCat,
+		bytes.Repeat([]byte{0xAA}, 1000))
+	storeEvictionTestVariant(t, enabled, testVariantKeyOne,
+		bytes.Repeat([]byte{0xAB}, 500))
+
+	disabled, err := NewCache(enabled.db, CacheConfig{
+		StateDir:         t.TempDir(),
+		NegativeTTL:      5 * time.Minute,
+		DisableDiskCache: true,
+	})
+	if err != nil {
+		t.Fatal(err)
+	}
+
+	stats, err := disabled.Stats(t.Context())
+	if err != nil {
+		t.Fatalf("Stats() error = %v", err)
+	}
+
+	if stats.TotalItems != 0 || stats.TotalSizeBytes != 0 {
+		t.Errorf("TotalItems = %d, TotalSizeBytes = %d, want 0 and 0",
+			stats.TotalItems, stats.TotalSizeBytes)
+	}
+}
+
+// cacheStatsCounters holds the counters of the cache_stats row, in column
+// order.
+type cacheStatsCounters struct {
+	hitCount           int64
+	missCount          int64
+	upstreamFetchCount int64
+	upstreamFetchBytes int64
+	transformCount     int64
+}
+
+// readCacheStatsCounters reads the counters of the cache_stats row.
+func readCacheStatsCounters(t *testing.T, cache *Cache) cacheStatsCounters {
+	t.Helper()
+
+	var got cacheStatsCounters
+
+	err := cache.db.QueryRowContext(t.Context(), `
+		SELECT hit_count, miss_count, upstream_fetch_count,
+		       upstream_fetch_bytes, transform_count
+		FROM cache_stats WHERE id = 1
+	`).Scan(&got.hitCount, &got.missCount, &got.upstreamFetchCount,
+		&got.upstreamFetchBytes, &got.transformCount)
+	if err != nil {
+		t.Fatalf("failed to read cache_stats: %v", err)
+	}
+
+	return got
+}
+
 // TestService_Get_CountsStats walks Get through a miss that fetches the
 // source, a hit, a miss that reuses the cached source, and two misses whose
-// source cannot be used, checking every counter of the cache after each.
+// source cannot be used, checking every cache_stats counter after each.
 func TestService_Get_CountsStats(t *testing.T) {
 	t.Parallel()
 
@@ -41,32 +304,28 @@ func TestService_Get_CountsStats(t *testing.T) {
 		path    string
 		size    int
 		wantErr bool
-		want    counterValues
+		want    cacheStatsCounters
 	}{
 		{"miss that fetches the source", testPathPhoto, 50, false,
-			counterValues{0, 1, 1, photoBytes, 1}},
+			cacheStatsCounters{0, 1, 1, photoBytes, 1}},
 		{"hit", testPathPhoto, 50, false,
-			counterValues{1, 1, 1, photoBytes, 1}},
+			cacheStatsCounters{1, 1, 1, photoBytes, 1}},
 		{"miss that reuses the cached source", testPathPhoto, 25, false,
-			counterValues{1, 2, 1, photoBytes, 2}},
+			cacheStatsCounters{1, 2, 1, photoBytes, 2}},
 		{"miss whose source fails the magic byte check", "/images/fake.jpg", 50, true,
-			counterValues{1, 3, 2, photoBytes + fakeBytes, 2}},
+			cacheStatsCounters{1, 3, 2, photoBytes + fakeBytes, 2}},
 		{"miss whose source is not found", "/images/nonexistent.jpg", 50, true,
-			counterValues{1, 4, 2, photoBytes + fakeBytes, 2}},
+			cacheStatsCounters{1, 4, 2, photoBytes + fakeBytes, 2}},
 	}
 
 	for _, step := range steps {
-		resp, err := svc.Get(t.Context(), &imagerequest.Request{
+		resp, err := svc.Get(t.Context(), &ImageRequest{
-			Source: imagerequest.Source{
+			SourceHost: fixtures.GoodHost,
-				Host: fixtures.GoodHost,
+			SourcePath: step.path,
-				Path: step.path,
+			Size:       Size{Width: step.size, Height: step.size},
-			},
+			Format:     FormatJPEG,
-			Transform: imagerequest.Transform{
+			Quality:    85,
-				Size:    imagerequest.Size{Width: step.size, Height: step.size},
+			FitMode:    FitCover,
-				Format:  imagerequest.FormatJPEG,
-				Quality: 85,
-				FitMode: imagerequest.FitCover,
-			},
 		})
 		if (err != nil) != step.wantErr {
 			t.Fatalf("%s: Get() error = %v, want error %t", step.name, err, step.wantErr)
@@ -76,7 +335,7 @@ func TestService_Get_CountsStats(t *testing.T) {
 			_ = resp.Content.Close()
 		}
 
-		got := readCounters(svc.cache)
+		got := readCacheStatsCounters(t, svc.cache)
 		if got != step.want {
 			t.Fatalf("after the %s: counters = %+v, want %+v", step.name, got, step.want)
 		}
@@ -114,7 +373,7 @@ func (u *fakeUpstream) Read(p []byte) (int, error) {
 	return 0, u.err
 }
 
-// TestService_Get_CountsInterruptedMisses checks every counter of the cache
+// TestService_Get_CountsInterruptedMisses checks every cache_stats counter
 // after a miss whose request context ends during or after the upstream
 // fetch, and after a miss whose upstream body is over the size limit.
 func TestService_Get_CountsInterruptedMisses(t *testing.T) {
@@ -130,15 +389,15 @@ func TestService_Get_CountsInterruptedMisses(t *testing.T) {
 		cancel  bool  // whether the body then ends the request context
 		readErr error // what the body then returns
 		wantErr bool
-		want    counterValues
+		want    cacheStatsCounters
 	}{
 		{"request context ends during the fetch", half, true, context.Canceled, true,
-			counterValues{0, 1, 1, int64(half), 0}},
+			cacheStatsCounters{0, 1, 1, int64(half), 0}},
 		{"request context ends after the fetch", len(photo), true, io.EOF, false,
-			counterValues{0, 1, 1, int64(len(photo)), 1}},
+			cacheStatsCounters{0, 1, 1, int64(len(photo)), 1}},
 		{"upstream body over the size limit", half, false,
 			httpfetcher.ErrResponseTooLarge, true,
-			counterValues{0, 1, 1, int64(half), 0}},
+			cacheStatsCounters{0, 1, 1, int64(half), 0}},
 	}
 
 	for _, tc := range tests {
@@ -160,17 +419,13 @@ func TestService_Get_CountsInterruptedMisses(t *testing.T) {
 
 			svc.fetcher = upstream
 
-			resp, err := svc.Get(ctx, &imagerequest.Request{
+			resp, err := svc.Get(ctx, &ImageRequest{
-				Source: imagerequest.Source{
+				SourceHost: fixtures.GoodHost,
-					Host: fixtures.GoodHost,
+				SourcePath: testPathPhoto,
-					Path: testPathPhoto,
+				Size:       Size{Width: 50, Height: 50},
-				},
+				Format:     FormatJPEG,
-				Transform: imagerequest.Transform{
+				Quality:    85,
-					Size:    imagerequest.Size{Width: 50, Height: 50},
+				FitMode:    FitCover,
-					Format:  imagerequest.FormatJPEG,
-					Quality: 85,
-					FitMode: imagerequest.FitCover,
-				},
 			})
 			t.Logf("Get() error = %v", err)
 
@@ -182,7 +437,7 @@ func TestService_Get_CountsInterruptedMisses(t *testing.T) {
 				_ = resp.Content.Close()
 			}
 
-			got := readCounters(svc.cache)
+			got := readCacheStatsCounters(t, svc.cache)
 			if got != tc.want {
 				t.Errorf("counters = %+v, want %+v", got, tc.want)
 			}
@@ -190,25 +445,21 @@ func TestService_Get_CountsInterruptedMisses(t *testing.T) {
 	}
 }
 
-// TestService_Get_CountsHitAfterRequestEnds checks every counter of the
+// TestService_Get_CountsHitAfterRequestEnds checks every cache_stats counter
-// cache after a hit served with a request context that has already ended:
+// after a hit served with a request context that has already ended: only
-// only the hit count moves.
+// the hit count moves.
 func TestService_Get_CountsHitAfterRequestEnds(t *testing.T) {
 	t.Parallel()
 
 	svc, fixtures := SetupTestService(t)
 
-	req := &imagerequest.Request{
+	req := &ImageRequest{
-		Source: imagerequest.Source{
+		SourceHost: fixtures.GoodHost,
-			Host: fixtures.GoodHost,
+		SourcePath: testPathPhoto,
-			Path: testPathPhoto,
+		Size:       Size{Width: 50, Height: 50},
-		},
+		Format:     FormatJPEG,
-		Transform: imagerequest.Transform{
+		Quality:    85,
-			Size:    imagerequest.Size{Width: 50, Height: 50},
+		FitMode:    FitCover,
-			Format:  imagerequest.FormatJPEG,
-			Quality: 85,
-			FitMode: imagerequest.FitCover,
-		},
 	}
 
 	// A first request caches the variant.
@@ -219,7 +470,7 @@ func TestService_Get_CountsHitAfterRequestEnds(t *testing.T) {
 
 	_ = resp.Content.Close()
 
-	want := readCounters(svc.cache)
+	want := readCacheStatsCounters(t, svc.cache)
 	want.hitCount++
 
 	ctx, cancel := context.WithCancel(t.Context())
@@ -236,7 +487,7 @@ func TestService_Get_CountsHitAfterRequestEnds(t *testing.T) {
 		t.Fatalf("CacheStatus = %v, want %v", resp.CacheStatus, CacheHit)
 	}
 
-	got := readCounters(svc.cache)
+	got := readCacheStatsCounters(t, svc.cache)
 	if got != want {
 		t.Errorf("counters = %+v, want %+v", got, want)
 	}