Move the TODO.md entry for the negative cache cleanup to the top

The rebase onto next left it below the entries next gained since.

Model: opus-5-5

.dockerignore

@@ -13,21 +13,12 @@
 # `/myapp`, never `**/myapp`, which also matches `cmd/myapp/` and
 # deletes the package directory from the context.
 
-# .git is sent without its config. Without a VERSION build argument the
+# Unlike the standard file, which leaves out all of .git, pixa sends
-# stage that compiles runs `git describe --tags --always` on .git, which
+# .git without its config. Without a VERSION build argument the stage
-# does not need .git/config; that file can hold a credential, such as a
+# that compiles runs `git describe --tags --always` on .git, which does
+# not need .git/config; that file can hold a credential, such as a
 # password in a remote URL or the token the CI checkout step stores there.
-# Each submodule keeps a config with the same exposure in its git directory
+.git/config
-# under .git/modules/, nested again for a submodule's own submodules, or in
-# its own .git directory when it keeps one.
-# KNOWN GAP: a submodule whose name has a `config` segment (`config`,
-# `deploy/config`, `config/lib`) loses its whole git directory, because
-# `**/.git/modules/**/config` also matches that segment's directory
-# under .git/modules/. Go's version stamping then fails the build;
-# nothing leaks. Name such a submodule without that segment:
-# `git submodule add --name`.
-**/.git/config
-**/.git/modules/**/config
 
 # Agent scratch: one full checkout of the repo per in-flight agent.
 # Anchored because it occurs once where agents run at the repo root.
@@ -51,9 +42,7 @@
 **/[iI][dD]_[rR][sS][aA]
 **/[iI][dD]_[dD][sS][aA]
 **/[iI][dD]_[eE][cC][dD][sS][aA]
-**/[iI][dD]_[eE][cC][dD][sS][aA]_[sS][kK]
 **/[iI][dD]_[eE][dD]25519
-**/[iI][dD]_[eE][dD]25519_[sS][kK]
 
 # Dependencies: restored inside the image, never copied in.
 **/node_modules
@@ -71,8 +60,10 @@
 **/.vscode
 **/*.sublime-*
 
-# pixa's own entries. On the host, `make build` writes bin/pixad, and the
+# pixa's own entries. Nothing in the build reads .gitignore. On the
-# example config keeps its state directory in data/.
+# host, `make build` writes bin/pixad, and the example config keeps its
+# state directory in data/.
+.gitignore
 /bin
 /data
 

.editorconfig

@@ -13,6 +13,3 @@ indent_style = tab
 
 [*.go]
 indent_style = tab
-
-# This repository's own sections, such as one for another language it
-# uses, go below this comment, and a re-vendor keeps them.

.gitea/workflows/check.yml

@@ -1,20 +1,15 @@
 name: check
 on: [push]
-# Free the shared runner: a new push cancels only the same branch's older run.
-concurrency:
-    group: ${{ github.workflow }}-${{ github.ref }}
-    cancel-in-progress: true
 jobs:
     check:
         runs-on: ubuntu-latest
-        # Free the shared runner from a hung build.
-        timeout-minutes: 20
         steps:
             # actions/checkout v4.2.2, 2026-02-22
             - uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683
-              # script/cibuild needs no token, so none is left in .git/config.
+              # The default clone is shallow and has no tags, so the
+              # version the build takes from `git describe` would be a
+              # bare commit; this fetches the whole history with its tags.
               with:
-                  persist-credentials: false
-                  # All history and tags, so git describe finds the version tag.
                   fetch-depth: 0
             - run: script/cibuild
+            - run: script/docker-smoke

.gitignore

@@ -17,46 +17,15 @@ Thumbs.db
 # entry and must not be given a `**/` prefix on the way into one.
 .claude/
 
-# Node
+# Environment / secrets
-node_modules/
+.env
-
+.env.*
-# Secrets. Unanchored like every entry above, so each matches at every
+*.pem
-# depth. Matching is case-sensitive on Linux, so names use character
+*.key
-# ranges rather than a lowercase form that misses `Server.Key`.
-
-# Environment files. `*.env` covers bare `.env` and the `prod.env`
-# convention. Only the templates `example.env` and `sample.env` are
-# re-included below. A repository that commits any other template adds
-# its own negation at the end of this file, for example `!.env.example`.
-*.[eE][nN][vV]
-.[eE][nN][vV].*
-.[eE][nN][vV][rR][cC]
-!example.env
-!sample.env
-
-# Private keys and the bundles carrying them.
-*.[pP][eE][mM]
-*.[kK][eE][yY]
-*.[pP]12
-*.[pP][fF][xX]
-[iI][dD]_[rR][sS][aA]
-[iI][dD]_[dD][sS][aA]
-[iI][dD]_[eE][cC][dD][sS][aA]
-[iI][dD]_[eE][cC][dD][sS][aA]_[sS][kK]
-[iI][dD]_[eE][dD]25519
-[iI][dD]_[eE][dD]25519_[sS][kK]
-
-# This repository's own entries, such as its build outputs, go below
-# this comment, and a re-vendor keeps them. Anchor a binary built at the
-# root: `/myapp`, never `myapp`, which also ignores `cmd/myapp/`.
-
-# Go
-*.log
-*.out
-*.test
 
 # Dependencies
 vendor/
+node_modules/
 
 # Build output
 /bin/

.golangci.yml

@@ -17,7 +17,6 @@ linters:
   disable:
     # Genuinely incompatible with project patterns
     - exhaustruct      # Requires all struct fields
-    - exhaustruct_v5   # Requires all struct fields (successor to exhaustruct)
     - godot            # Requires comments to end with periods
     - wrapcheck        # Too verbose for internal packages
     - varnamelen       # Short names like db, id are idiomatic Go
@@ -25,8 +24,6 @@ linters:
     # silenced by disabling that name, not by enabling the successor.
     - wsl              # Deprecated, replaced by wsl_v5
     - gomodguard       # Deprecated, replaced by gomodguard_v2
-    # Misses findings at random in v2.14.0; back once a pinned release fixes it
-    - canonicalheader
   settings:
     lll:
       line-length: 88

.prettierignore

@@ -1,2 +1,7 @@
 node_modules/
 yarn.lock
+
+# A byte-for-byte copy of the one in sneak/prompts.
+REPO_POLICIES.md
+
+vendor/

CLAUDE.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 +1,7 @@
-# In every stage ARG CACHEBUST comes right after the steps that install
-# system packages and download Go's modules, or right after FROM in a
-# stage with neither, and every step that lints, tests or compiles
-# 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
+# golangci/golangci-lint:v2.12.2, 2026-10-04
-FROM golangci/golangci-lint@sha256:ad862ba6b3798cbe0fd9fd7408d498fd74fbd2623a92406b2fd3898faf0bf98f AS lint
+FROM golangci/golangci-lint@sha256:5cceeef04e53efe1470638d4b4b4f5ceefd574955ab3941b2d9a68a8c9ad5240 AS lint
 
 # The linter compiles every package, and govips needs the libvips
 # headers for that. REPO_POLICIES.md has the lint phase install them
@@ -22,87 +13,70 @@ 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 \
+RUN golangci-lint run --config .golangci.yml ./...
-    --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
+# Test phase. script/test builds it alone.
-# compiler, which the Debian Go image ships and the alpine one does not.
+# golang:1.25.4-alpine3.22, 2026-02-25; the runtime stage uses Alpine 3.22 too
-# golang:1.25.4-trixie, 2026-10-15
+FROM golang:1.25.4-alpine3.22@sha256:d3f0cf7723f3429e3f9ed846243970b20a2de7bae6a5b66fc5914e228d831bbb AS test
-FROM golang@sha256:a02d35efc036053fdf0da8c15919276bf777a80cbfda6a35c5e9f087e652adfc AS test
-
-# 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 (a C compiler,
+# 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
-# the step fails even if the second run passes. -count=1 because the
+# the step fails even if the second run passes. -parallel 4: by default
-# mounted cache also holds test results, which go test would otherwise
+# a package runs as many of its tests at once as the host has CPUs, and
-# replay. -parallel 4: by default a package runs as many of its tests at
+# on a busy host they then wait so long to be scheduled that a test
-# once as the host has CPUs, and on a busy host they then wait so long
+# that times a request can see it return a second late.
-# to be scheduled that a test that times a request can see it return a
+RUN go test -count=1 -timeout 90s -race -parallel 4 -cover ./... || \
-# second late.
-RUN --mount=type=cache,target=/root/.cache/go-build \
-    go test -count=1 -timeout 90s -race -parallel 4 -cover ./... || \
     { echo "--- Rerunning with -v for details ---"; \
       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
 
-# A tar-stream context keeps the sender's file owners, which git refuses.
+WORKDIR /src
-RUN git config --system --add safe.directory /src
+
+# Build dependencies and Go modules, as in the test phase
+COPY script/ ./script/
+COPY go.mod go.sum ./
+RUN script/bootstrap --cgo
 
 # Copy source code
 COPY . .
 
-# The VERSION build arg when one is given, otherwise
+# VERSION is declared here, not earlier: a new value reruns only the
-# `git describe --tags --always` on the .git in the build context: the
+# build, not script/bootstrap. Given none, the version is
-# tag on a tagged commit, tag-N-gHASH after one, the short commit when
+# `git describe --tags --always` of the .git in the build context (git
-# no tag is reachable. With .git present, a version that is still empty,
+# comes from script/bootstrap): the tag on a tagged commit, tag-N-gHASH
-# dev or unknown fails the build: git is missing or could not read the
+# after one, the short commit when no tag is reachable. A context that
-# checkout. A context without .git, as from a source tarball, stamps an
+# carries .git and still yields no version fails the build; one without
-# empty version. CGO stays enabled for govips; -trimpath keeps build
+# .git, as from a source tarball, stamps an empty version. CGO stays
-# paths out of the binary, and -s -w leave out the symbol table and
+# enabled for govips; -trimpath keeps build paths out of the binary, and
-# debug information.
+# -s -w leave out the symbol table and debug information.
 ARG VERSION
-RUN --mount=type=cache,target=/root/.cache/go-build \
+RUN version="${VERSION:-$(git describe --tags --always)}"; \
-    VERSION="${VERSION:-$(git describe --tags --always)}"; \
+    if [ -e .git ] && { [ -z "$version" ] || [ "$version" = dev ] || \
-    if [ -e .git ]; then \
+        [ "$version" = unknown ]; }; then \
-        case "$VERSION" in ""|dev|unknown) \
+        echo "the build context carries .git but yields no version" >&2; \
-            echo "version is '$VERSION' although .git is present" >&2; \
+        exit 1; \
-            exit 1 ;; \
-        esac; \
     fi; \
     CGO_ENABLED=1 GOTOOLCHAIN=auto go build -trimpath \
-        -ldflags="-s -w -X main.Version=${VERSION}" \
+        -ldflags "-s -w -X main.Version=${version}" \
         -o /pixad ./cmd/pixad
 
 # Runtime stage, and the last one: a plain `docker build .` builds this
@@ -121,7 +95,6 @@ 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

@@ -71,12 +71,12 @@ The state directory (`state_dir`, `/var/lib/pixa` in the container) holds the
 database and the disk cache:
 
 - It needs a persistent volume: without one, every restart starts with an empty
-  cache. Losing the directory also ends every login session (see Encrypted
+  cache. In the container, the startup script gives the directory to the user
-  URLs). In the container, the startup script gives the directory to the user
   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 +88,21 @@ 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
@@ -127,41 +123,9 @@ What the [upaas](https://git.eeqj.de/sneak/upaas) app for pixa needs:
       comma-separated; default none. Every image on a listed host is served to
       anyone without a signature, so list only hosts you control, where nobody
       else can put images.
-    - `PIXA_CACHE_MAX_BYTES`: disk cache limit in bytes; `0` disables it. Set
+    - `PIXA_CACHE_MAX_BYTES`: disk cache limit in bytes; `0` disables it;
-      it: the volume is a directory on the host's filesystem, shared with the
+      default 75% of (free space + what the cache holds)
-      host and every other app. The default is 75% of the sum of that
-      filesystem's free space and what the cache holds, and at least 500 MiB, so
-      the cache can grow to three quarters or more of the space they all have
-      left, and to all of it when that is 500 MiB or less.
     - the rest are in the table under Configuration below
-- **Memory:** pixa can use up to `max_concurrent_processing` times 4.2 GiB for
-  the images it processes at once, plus `upstream_connections` times
-  `upstream_max_response_size` for the source images it has fetched that wait
-  for processing. 4.2 GiB is the most resident memory was measured to grow while
-  pixa, with pixad's libvips settings, processed one 8192x8192 source, the
-  largest it accepts, saving it at full size to each output format in turn, one
-  at a time. The sources were a JPEG, a GIF, a WebP, an 8-bit and a 16-bit PNG,
-  an 8-bit and a 12-bit AVIF, and an 8-bit, a 16-bit and a 32-bit floating-point
-  JPEG XL; memory grew most for the 16-bit JPEG XL, of random pixels, saved as
-  WebP. At the defaults that is half the CPUs pixa sees times 4.2 GiB, plus 64
-  times 50 MiB: on a host where pixa sees 48 CPUs, 24 times 4.2 GiB plus 3.1
-  GiB, about 104 GiB. Set `PIXA_MAX_CONCURRENT_PROCESSING` and
-  `PIXA_UPSTREAM_CONNECTIONS` so that this fits the memory the container may
-  use.
-- **Temporary files:** while pixa processes a large source, libvips writes its
-  decoded pixels to a file in `/tmp`. The file disappears from `/tmp` once it is
-  written, so a listing of `/tmp` does not show it, but it keeps its space, on
-  disk or, where `/tmp` is a tmpfs, in memory, until the image is done. For a
-  GIF, WebP, AVIF or JPEG XL source the decoded pixels are held in memory as
-  well as written to that file, and the 4.2 GiB above includes that memory. For
-  an 8192x8192 source the file was measured on pixad at 192 MiB for an 8-bit RGB
-  JPEG, 512 MiB for a 16-bit RGBA PNG or JPEG XL, and 1 GiB for a JPEG XL of
-  32-bit floating-point RGBA, the largest measured: up to 1 GiB per image
-  processed at once, 24 GiB at the defaults on a host where pixa sees 48 CPUs.
-  This `/tmp` is in the container's own filesystem, not on the volume at
-  `/var/lib/pixa`, and `cache_max_bytes` does not count it. The 4.2 GiB above
-  does not include these files; where `/tmp` is a tmpfs, they are memory on top
-  of it.
 - **Health check:** the image's `HEALTHCHECK` requests
   `/.well-known/healthcheck.json`. upaas reads the container's health 60 seconds
   after a deploy and marks the deploy failed unless it is `healthy`. The probe
@@ -180,46 +144,26 @@ 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
-disk, and only then renamed into place, so a crash leaves no file under its own
-name with part of its data. When pixa starts, and every five minutes after, it
-removes each cached source or transformed image whose file is empty, or not the
-size the database records for it, with a warning naming the file; the next
-request for it fetches the source or converts the image again. Looking for those
-files reads the database once for every cached file, so pixa skips each
-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
 
@@ -240,66 +184,34 @@ path under `/v1/` answers 200, in maintenance mode too.
   session it answers 303 to `/`. Answers: 200 with the page showing the URL; 400
   with the page naming a field that is not valid; 500 when the URL cannot be
   made.
-- `POST /logout` — log out with the generator page's Logout button: end every
+- `GET /logout` — end the login session. Needs: nothing. Answers: 303 to `/`.
-  login session, in every browser (see Encrypted URLs), and remove the session
-  cookie. Needs: a login session and the generator page's form (below); without
-  a login session it only removes the cookie. Answers: 303 to `/`; 500 when the
-  logout cannot be saved in the database.
 - `GET` or `HEAD` `/v1/image/<host>/<path>/<size>.<format>`, or
   `/v1/image/<host>/<path>/<size>` with no format — an image, fetched, resized
   and converted (below). Needs: a signature, unless the host is allowlisted (see
-  Source Hosts). Answers:
+  Source Hosts). Answers: 200; 304 when `If-None-Match` matches the image's
-    - 200 with the image.
+  `ETag`; 400 for a URL or parameter that is not valid, or for the format `auto`
-    - 304 when `If-None-Match` matches the image's `ETag`.
+  an `Accept` header that is not valid; 406 for the format `auto` when `Accept`
-    - 400 for a URL or parameter that is not valid.
+  allows none of the formats it chooses from; 401 for a missing or wrong
-    - 400 when the format is `auto` and the `Accept` header is not valid.
+  signature, a missing `exp` or an `exp` in the past; 403 when the request's
-    - 406 when the format is `auto` and `Accept` allows none of the formats it
+  `Referer` names a host in `referer_blocklist`, checked before the signature,
-      chooses from.
+  the cache and the upstream fetch; 403 when the upstream host, or a host it
-    - 401 for a missing or wrong signature.
+  redirects to, is `localhost`, ends in `.localhost` or `.local`, or has an
-    - 401 for a missing `exp`.
+  address in a blocked network (see `blocked_networks`); 429 over
-    - 401 for an `exp` in the past.
+  `image_requests_per_minute` (below); 415 when the upstream answers with a
-    - 403 when the request's `Referer` names a host in `referer_blocklist`,
+  `Content-Type` that is not one of the source formats (below), or with an image
-      checked before the signature, the cache and the upstream fetch.
+  whose first bytes libvips reads as another format; 502 when the upstream
-    - 403 when the upstream host, or a host it redirects to, is `localhost` or
+  answered with an error status, and for 5 minutes after that for an image of
-      ends in `.localhost` or `.local`.
+  the same source URL that pixa can neither serve from its cache nor make from
-    - 403 when the upstream host, or a host it redirects to, has an address in a
+  the source image still in its cache; 503 when pixa is busy or in maintenance
-      blocked network (see `blocked_networks`).
+  mode; 500 for any other failure.
-    - 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).
-    - 415 when the upstream sends a body whose first bytes are not those of the
-      format its `Content-Type` names.
-    - 415 when the upstream sends an image whose first bytes libvips reads as
-      another format.
-    - 502 when the upstream answers with an error status.
-    - 502 for 5 minutes after that for the same source URL, when pixa has
-      neither the image nor its source image in its cache.
-    - 502 likewise for 5 minutes after a body whose first bytes are not those of
-      its `Content-Type`.
-    - 503 when pixa is busy.
-    - 503 when pixa is in maintenance mode.
-    - 504 when the upstream has not sent its response headers within
-      `upstream_fetch_timeout`.
-    - 500 when that time runs out while the image itself is still arriving.
-    - 500 for any other failure.
 - `GET` or `HEAD` `/v1/e/<token>/<name>` — an image through an encrypted URL
-  (see Encrypted URLs). Needs: nothing but the URL. Answers:
+  (see Encrypted URLs). Needs: nothing but the URL. Answers: 200; 304 when
-    - 200 with the image.
+  `If-None-Match` matches the image's `ETag`; 400 for a token that does not
-    - 304 when `If-None-Match` matches the image's `ETag`.
+  decrypt, or that asks for a size or fit that is not valid; 410 once it has
-    - 400 for a token that does not decrypt.
+  expired; 504 when the upstream has not sent its response headers within
-    - 400 for a token that asks for a size or fit that is not valid.
+  `upstream_fetch_timeout`, but 500 when that time runs out while the image
-    - 410 once the token has expired.
+  itself is still arriving; 400 for an `Accept` header that is not valid, and
-    - 400 when the token's format is `auto` and the `Accept` header is not
+  406, 403, 415, 429, 502, 503 and 500, as for `/v1/image/`.
-      valid.
-    - These answers, for the same causes as on `/v1/image/`:
-        - 406
-        - 403
-        - 415
-        - 429
-        - 502
-        - 503
-        - 504
-        - 500
 - `GET /robots.txt` — asks every crawler to stay away (`Disallow: /`). Needs:
   nothing. Answers: 200.
 - `GET /.well-known/healthcheck.json` — JSON with `status` (`ok`), `now`,
@@ -320,7 +232,7 @@ the request carries the same ID as `request_id`, and so do the lines it logs
 when it fetches, converts and serves an image; the fetch sends it to the
 upstream host as `X-Request-ID`.
 
-The `POST` routes accept only a form that pixa's own page served: the page puts
+Both `POST` routes accept only a form that pixa's own page served: the page puts
 a token in the form and sets a cookie to match, and a request without both is
 refused with 403, so another site cannot submit the form from a visitor's
 browser. The login and generator pages are meant to be opened over HTTPS: while
@@ -359,57 +271,17 @@ once, is refused with 400.
   both optional (values under Signature Specification). Both are part of what is
   cached, so each value of either is a separate cached image.
 
-A source URL's query follows its path after `%3F`, the encoded `?`:
-`/v1/image/<host>/<path>%3F<query>/<size>.<format>`. pixa decodes the
-percent-escapes in the image URL's path once, then reads the host up to the
-first `/`, the size and format after the last `/`, and between them the source
-path up to the first `?` and the source query after it. So the `?` before the
-query, any `?` in the query, and every `%` in the source path or query must be
-percent-encoded, as `%3F` and `%25`. Any other character may be written as
-itself or percent-encoded: `/`, `;`, `,`, `=` and `&` work either way. Neither
-the source path nor the source query may hold a `#`, and an image URL that
-writes one as `%23` is refused with 400. For example,
-`https://cdn.example.com/img?url=https://origin.example.com/my%20cat.jpg` at
-800x600 WebP is
-`/v1/image/cdn.example.com/img%3Furl=https://origin.example.com/my%2520cat.jpg/800x600.webp`,
-signed as shown under Signature Specification.
-
-The source path is the path with its percent-escapes decoded, and pixa fetches
-it percent-encoded again: every character other than letters, digits, `-`, `.`,
-`_`, `~`, `/`, `$`, `&`, `+`, `,`, `:`, `;`, `=` and `@` is sent as a
-percent-escape. So `my%20cat.jpg` in the image URL is the source path
-`/my cat.jpg`, fetched as `/my%20cat.jpg`; `my%2520cat.jpg` 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
-characters and characters outside ASCII) and a `%` that does not begin a
-percent-escape are percent-encoded. pixa signs and caches the query in that
-form, so `img%3Fname=my%20cat` and `img%3Fname=my%2520cat` in the image URL are
-the same 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
 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:
@@ -442,30 +314,9 @@ cache at once, they share one upstream fetch (or one read of the cached source)
 and one transcode: the first request does the work, and the others wait for its
 image or its error, holding no upstream connection or processing slot of their
 own. A waiting request stops waiting when its own client goes away. The work
-goes on for the others even if the first request's client goes away. The shared
+goes on for the others even if the first request's client goes away, until that
-fetch sends the first request's ID upstream, and the lines logged for the fetch
+request's `downstream_timeout` ends. The shared fetch sends the first request's
-and the transcode carry that ID.
+ID upstream, and the lines logged for the fetch and the transcode carry that ID.
-
-A transcode whose request's `downstream_timeout` has ended (for a shared one,
-the first request's) stops waiting for a processing slot, or, once it has one,
-gives it back without beginning to encode. A request waiting for a shared
-transcode that stops this way is answered 503 with the error
-`server busy, try again later`, though its own `downstream_timeout` may not have
-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.
-With one libvips thread, as pixad runs it, encoding 8192x8192 random pixels
-takes up to about 1 second as JPEG, 15 as PNG and 16 as GIF, the slowest of 8 or
-16 bits per sample, with or without an alpha channel. The WebP and JPEG XL
-encoders run below libvips' default effort, and AVIF at the lowest effort govips
-can set, so that no encode takes more than 40 seconds of the default
-`downstream_timeout` of 60: at any quality and 8 or 16 bits per sample,
-8192x8192 random pixels with an alpha channel take up to about 23 seconds as
-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
@@ -502,28 +353,14 @@ nor change what it asks for.
 
 1. Open `/` in a browser over HTTPS (or over plain HTTP while `debug` is on, see
    Routes) and log in with the signing key (`signing_key`). The login session
-   lasts 30 days, or until someone logs out with the generator page's Logout
+   lasts 30 days, or until `/logout`.
-   button. Every login is made with the one signing key, so logging out ends
-   every login session, in every browser, a copy of the session cookie included.
-   pixa keeps a random value in its database, which it makes when the database
-   has none and replaces at each logout. A login session carries the value
-   current at its login and is refused once the value has changed, also after a
-   restart (see Deployment). The check for a logout compares no time, so a login
-   after a logout works whatever the host's clock says; the 30 days are still
-   measured by the host's clock.
 2. On the generator page, give the source image's URL, the width and height, the
    format, quality and fit, and how long the URL lasts, then submit the form
    (`POST /generate`). The format is JPEG XL unless another is chosen; a form
    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.
-   more than 16,777,216 pixels or a source URL whose path holds a `..` segment.
-   So does a source URL that the image URL would fetch written another way, and
-   the page then shows the URL pixa would fetch: one with a user name and
-   password, which pixa does not send, or one whose path holds `%2F`, fetched as
-   `/`, 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
@@ -531,11 +368,9 @@ 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
@@ -587,20 +422,13 @@ Where:
 - `host` — source host as the URL writes it up to the first `/`, in lower case,
   keeping an IPv6 address's brackets and any `:` and port after it (e.g.
   `cdn.example.com`, `cdn.example.com:8443`, `[2001:db8::1]:8443`)
-- `path` — source path, with its percent-escapes decoded as under Routes (e.g.
+- `path` — source path (e.g. `/photos/cat.jpg`), with each `%` written as `%25`
-  `/photos/cat.jpg`, or `/photos/my cat.jpg` for `/photos/my%20cat.jpg`), with
+  and each `:` as `%3A`, so `/photos/a:b.jpg` is signed as `/photos/a%3Ab.jpg`
-  each `%` written as `%25` and each `:` as `%3A`, so `/photos/a:b.jpg` is
+- `query` — source query string, empty string if none, with `%` and `:` written
-  signed as `/photos/a%3Ab.jpg`
+  as in `path`; neither then holds a `:`, so path `/a:b` with no query and path
-- `query` — source query string as under Routes, empty string if none, with `%`
+  `/a` with query `b:` are signed differently
-  and `:` written as in `path`; neither then holds a `:`, so path `/a:b` with no
+- `width` — requested width in pixels, `0` for original
-  query and path `/a` with query `b:` are signed differently
+- `height` — requested height in pixels, `0` for original
-- `width` — requested width in pixels, or `0`: the width is then worked out from
-  the source's proportions and the requested height, rounded down but at least
-  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
@@ -613,10 +441,7 @@ 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
@@ -640,17 +465,6 @@ For the same image at quality 40 with fit `contain`, the input ends in
 and the URL is
 `/v1/image/cdn.example.com/photos/cat.jpg/800x600.webp?sig=5IwXUx6vf7yefhaUvFzgXZvG2o0Df4RJxPTK3pKq5VU=&exp=1704067200&q=40&fit=contain`.
 
-For a source URL with a query,
-`https://cdn.example.com/img?url=https://origin.example.com/my%20cat.jpg`, at
-800x600 WebP with the same key and expiration and the default quality and fit:
-
-1. Build input, with the query's `:` written as `%3A` and its `%` as `%25`:
-   `cdn.example.com:/img:url=https%3A//origin.example.com/my%2520cat.jpg:800:600:webp:1704067200:85:cover`
-2. The signature is `37aFa9GSVCZM1kRY9SzMOk2fOg_M7Wt5gKNR4xM-FYA=`
-3. URL, with the `?` before the query written as `%3F` and the query's `%` as
-   `%25` (see Routes):
-   `/v1/image/cdn.example.com/img%3Furl=https://origin.example.com/my%2520cat.jpg/800x600.webp?sig=37aFa9GSVCZM1kRY9SzMOk2fOg_M7Wt5gKNR4xM-FYA=&exp=1704067200`
-
 **Allowlist patterns:**
 
 - **Exact match**: `cdn.example.com` — matches only that host
@@ -666,11 +480,7 @@ pixa lower-cases the host of a `/v1/image/` URL before anything else uses it, so
 `CDN.Example.com` is matched, fetched, cached and counted against
 `upstream_connections_per_host` as `cdn.example.com`. Such a URL whose host has
 a port, as in `cdn.example.com:8443`, or a `:` with no port, needs a signature
-even when the host is allowlisted. The host must be a host name or an IPv4
+even when the host is allowlisted. A host holding `@` is refused with 400.
-address (letters, digits, hyphens, underscores and dots) or an IPv6 address in
-brackets, either one optionally followed by `:` and a port. Any other host, such
-as one holding `@`, or a `?`, `#`, `%`, `\` or space written percent-encoded, is
-refused with 400.
 
 ### Configuration
 
@@ -714,7 +524,7 @@ tell. With no file, pixa uses the environment and the defaults.
 | `PIXA_ALLOW_HTTP`                    | `allow_http`                    | Allow plain-HTTP upstreams, for testing only; default `false`                |
 | `PIXA_UPSTREAM_CONNECTIONS_PER_HOST` | `upstream_connections_per_host` | Concurrent connections per upstream host; default `20`                       |
 | `PIXA_UPSTREAM_CONNECTIONS`          | `upstream_connections`          | Concurrent connections to all upstream hosts together; default `64`          |
-| `PIXA_MAX_CONCURRENT_PROCESSING`     | `max_concurrent_processing`     | Images processed at once; default half the CPUs, at least 1                  |
+| `PIXA_MAX_CONCURRENT_PROCESSING`     | `max_concurrent_processing`     | Images processed at once; default the number of CPUs                         |
 | `PIXA_IMAGE_REQUESTS_PER_MINUTE`     | `image_requests_per_minute`     | Image requests per client per minute; `0` turns it off; default `600`        |
 | `PIXA_UPSTREAM_FETCH_TIMEOUT`        | `upstream_fetch_timeout`        | Time allowed for one fetch from an upstream host; default `30s`              |
 | `PIXA_UPSTREAM_MAX_RESPONSE_SIZE`    | `upstream_max_response_size`    | Largest upstream response accepted, in bytes; default 50 MiB                 |
@@ -752,12 +562,7 @@ 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
@@ -767,22 +572,16 @@ 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;
@@ -791,27 +590,14 @@ Key settings in more detail:
   duration; default `60s`. The upstream fetch counts toward it, and so do the
   waits for an upstream connection and for a processing slot (up to 10 seconds
   each), so keep it longer than `upstream_fetch_timeout` plus 20 seconds
-- `signing_key` — the secret that protects signed URLs, encrypted URLs and
+- `signing_key` — HMAC secret for URL signatures
-  logins. pixa uses it as it is for two things:
-    - the HMAC key of signed URLs (see Signature Specification)
-    - the password of the login page
-
-    pixa derives every other key it uses from it at startup, with HKDF-SHA256:
-    - a key that signs the session cookie
-    - a key that encrypts the session cookie
-    - a key that encrypts the token of an encrypted URL
-    - a key that signs the CSRF token cookie of the login and generator pages
-
 - `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
@@ -824,12 +610,10 @@ Key settings in more detail:
   does, and `downstream_timeout` has not ended first, the request is answered
   503 with the error `server busy, try again later`
 - `max_concurrent_processing` — the most images decoded and encoded at once;
-  default half the CPUs pixa can use (`GOMAXPROCS`, which follows a container's
+  default the number of CPUs pixa can use (`GOMAXPROCS`), which follows a
-  CPU limit), rounded down, and at least 1. A value that is not a whole number
+  container's CPU limit. A request that finds all of them in use waits up to 10
-  of at least 1 aborts startup. A request that finds all of them in use waits up
+  seconds for one to free up; if none does, and `downstream_timeout` has not
-  to 10 seconds for one to free up; if none does, and `downstream_timeout` has
+  ended first, it is answered 503 the same way
-  not ended first, it is answered 503 the same way. Each one can take a lot of
-  memory: see "Running under upaas"
 - `image_requests_per_minute` — how many requests one client may send to the
   image routes per minute (see the limit on them under Routes); default `600`.
   `0` turns the limit off, and a negative or non-integer value aborts startup.
@@ -848,34 +632,15 @@ 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
-    - the size of HTTP responses
-    - the HTTP requests in flight
-    - the Go runtime and process metrics
-    - `pixa_cache_hits_total`: image requests served from the cache
-    - `pixa_cache_misses_total`: image requests not served from the cache
-    - `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
@@ -894,9 +659,9 @@ provide:
   install-precommit)
 - `script/projectname` — output the project name ("pixa")
 - `script/test` — run the test suite: build the `test` phase of the
-  `Dockerfile`, writing no image
+  `Dockerfile`, tagged `pixa-test`
 - `script/lint` — run golangci-lint: build the `lint` phase of the `Dockerfile`,
-  writing no image; the linter never runs on the host
+  tagged `pixa-lint`; the linter never runs on the host
 - `script/fmt` — format the Go code with gofmt and the markdown with prettier
   (writes)
 - `script/fmt-check` — check the same formatting (read-only), on the host
@@ -907,9 +672,6 @@ 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
@@ -917,26 +679,15 @@ provide:
 - `script/install-precommit` — install the git pre-commit hook that runs
   `script/precommit`
 
-Every `docker build` in these scripts passes a new value of the `CACHEBUST`
+Every `docker build` in these scripts passes `--no-cache`, so the lint and test
-build argument, which every stage of the `Dockerfile` declares, so every `RUN`
+phases run on every build instead of coming from the build cache.
-step after that line, the lint and test steps included, runs on every build
+`script/check`, `script/cibuild`, `script/docker`, `script/lint`, `script/test`,
-instead of coming from the build cache. Above the line are the steps that
+`script/setup` and `script/install-precommit` are the standard copies from
-install system packages and download the Go modules; Docker keeps their layers
+`sneak/prompts`, kept identical to them. `script/fmt` and `script/fmt-check` are
-until the base image, the step itself, `go.mod` or `go.sum` changes. Go's build
+the standard copies with pixa's `gofmt` step kept before prettier. prettier
-cache is kept from build to build: the steps that compile mount it, so a package
+formats the markdown only: not the HTML templates, as it cannot parse a Go
-whose inputs are unchanged is not compiled again, and both `go test` runs pass
+template action inside a tag, and not `REPO_POLICIES.md` (see
-`-count=1` so that no stored test result is replayed. The lint step also mounts
+`.prettierignore`), a copy of the one in `sneak/prompts`.
-golangci-lint's cache, which reuses a package's findings only when its files,
-those of the packages it imports, `go.mod`, the linters and their settings in
-`.golangci.yml`, and the golangci-lint version are all unchanged. The `test`
-phase runs on the Debian Go image, with Debian's libvips and libheif; the image
-pixa ships is built and runs on Alpine. `script/check`, `script/cibuild`,
-`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
 
@@ -990,17 +741,6 @@ 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: 2026-09-08
 ---
 
 This document covers repository structure, tooling, and workflow standards. Code
@@ -54,39 +54,34 @@ style conventions are in separate documents:
   `cibuild`. `script/bootstrap` installs all dependencies idempotently and
   assumes nothing is present: base tools come from nix, apt, brew, or apk
   (detected in that order; apt runs noninteractive). For node it uses the
-  installed node only when its major version is the pinned one; otherwise (node
+  installed node if present; otherwise it installs a PINNED node version via
-  missing, or another major, such as the node 24 the CI runner image ships) it
+  nvm, first installing nvm itself if missing — from a hash-verified GitHub
-  installs the PINNED node version via nvm and installs yarn and the packages
+  release archive (never `curl | sh`), with bash installed as an explicit
-  under it. nvm itself is installed first if missing, from a hash-verified
+  prerequisite since nvm requires bash. yarn is then pinned via
-  GitHub release archive (never `curl | sh`), with bash installed as an explicit
+  `corepack prepare yarn@<version> --activate`. Never install "latest" or "lts";
-  prerequisite since nvm requires bash. Only the major version is compared
+  always exact versions. `script/cibuild` runs the CI build: it changes to the
-  because the `Dockerfile` stages start from a node image whose exact version is
+  repo root, runs `script/bootstrap`, runs `script/check`, and builds the image
-  not the pin, and nvm cannot install a prebuilt node on alpine. yarn is pinned
+  with the version; the Gitea workflow calls it. **`script/cibuild` runs
-  via `corepack prepare yarn@<version> --activate`. Never install "latest" or
-  "lts"; always exact versions. `script/cibuild` runs the CI build: it changes
-  to the repo root, runs `script/bootstrap`, runs `script/check`, and builds the
-  image with the version; the Gitea workflow calls it. **`script/cibuild` runs
   `script/bootstrap` first**, because the workflow checks out the repo and runs
   nothing else, while `script/fmt-check` runs the formatter on the host: on a
   pristine checkout with nothing installed the run dies there, after the
-  containerised gates have passed. **The bootstrap alone is not enough**: when
+  containerised gates have passed. **The bootstrap alone is not enough**:
-  `script/bootstrap` installs node and yarn under nvm it leaves neither on the
+  `script/bootstrap` installs node and yarn under nvm and leaves neither on the
-  `PATH` of the shell that called it, so a bare `yarn` either exits 127 or runs
+  `PATH` of the shell that called it, so a bare `yarn` still exits 127. The host
-  under another node. The host entrypoints that need yarn — `script/fmt` and
+  entrypoints that need yarn — `script/fmt` and `script/fmt-check` — therefore
-  `script/fmt-check` — therefore use the same test as `script/bootstrap`: when
+  source nvm for the pinned node version before invoking it, exactly as
-  the node on `PATH` has the pinned major version they run the `yarn` on `PATH`,
+  `script/bootstrap`'s own install step does. A runner carrying nothing but
-  and otherwise they load nvm through `$HOME/.nvm/nvm.sh` and run yarn under the
+  docker and git then gets through `script/check`. Four further scripts are our
-  pinned node. A runner carrying nothing but docker and git then gets through
+  own extensions to the standard: `script/check` runs `script/test`,
-  `script/check`. Four further scripts are our own extensions to the standard:
+  `script/lint` and `script/fmt-check`; `script/precommit` is what the git
-  `script/check` runs `script/test`, `script/lint` and `script/fmt-check`;
+  pre-commit hook runs, and it calls `script/check`; `script/install-precommit`
-  `script/precommit` is what the git pre-commit hook runs, and it calls
+  installs the git pre-commit hook (the `make hooks` target shims to it); and
-  `script/check`; `script/install-precommit` installs the git pre-commit hook
+  `script/projectname` (literally that filename) simply outputs the project's
-  (the `make hooks` target shims to it); and `script/projectname` (literally
+  name. Scripts that need the name call `script/projectname` — e.g.
-  that filename) simply outputs the project's name. Scripts that need the name
+  `script/docker` assembles its image tag from it — so those scripts stay
-  call `script/projectname` — e.g. `script/docker` assembles its image tag from
+  byte-identical across all repos. Repo-type-specific pre-commit extras (e.g.
-  it — so those scripts stay byte-identical across all repos. Repo-type-specific
+  `go mod tidy` verification in Go repos) belong in `script/precommit`, not in
-  pre-commit extras (e.g. `go mod tidy` verification in Go repos) belong in
+  the hook itself. Model scripts are at
-  `script/precommit`, not in the hook itself. Model scripts are at
   `https://git.eeqj.de/sneak/prompts/raw/branch/main/script/<name>`. The README
   must document the provided scripts in an **Entrypoints** section (see the
   README requirements below).
@@ -109,24 +104,18 @@ style conventions are in separate documents:
   `lint` phase and a `test` phase, with the final stage depending on both so the
   image cannot be built unless they pass. For non-server repos the final stage
   brings up a development environment; for server repos it is the runtime image.
-  The gate phases and the build stage start from their pinned base images and
+  Dockerfiles install development prerequisites by running `script/bootstrap`
-  install what those images lack either inline, as the canonical Go `Dockerfile`
+  rather than duplicating installs inline; COPY `script/` and the dependency
-  below does for `git`, or by running `script/bootstrap`, as the `prompts`
+  manifests (`package.json` + `yarn.lock`, `go.mod` + `go.sum`, etc.) before
-  repo's own `Dockerfile` does for its yarn packages. The development
+  running it.
-  environment stage installs development prerequisites by running
-  `script/bootstrap` rather than duplicating its installs inline. A stage that
-  runs `script/bootstrap` COPYs `script/` and the dependency manifests
-  (`package.json` + `yarn.lock`, `go.mod` + `go.sum`, etc.) before running it.
 
 - **Linting and testing run in Docker, as phases of the `Dockerfile`.** There is
   no separate lint file. `script/lint` and `script/test` each build one phase
   and nothing else:
 
     ```sh
-    docker build --build-arg CACHEBUST="$(date +%s)-$$" \
+    docker build --no-cache --target lint -t "$(script/projectname)-lint" .
-        --target lint --output type=cacheonly .
+    docker build --no-cache --target test -t "$(script/projectname)-test" .
-    docker build --build-arg CACHEBUST="$(date +%s)-$$" \
-        --target test --output type=cacheonly .
     ```
 
     **A stage that is not the last one in the file is built only when the final
@@ -136,15 +125,10 @@ style conventions are in separate documents:
     plain `docker build .` builds the last stage alone and exits 0 having linted
     and tested nothing.
 
-    **The gate builds write no image.** With `--output type=cacheonly` the phase
+    **Every `docker build` in `script/` is tagged**, here and in
-    runs and a failing step fails the build, but the result is not exported.
+    `script/cibuild` and `script/docker`. An untagged build leaves a dangling
-    Nothing uses those images, and writing one out is slow: a Go test phase's
+    image behind on every invocation, on every developer host and every CI
-    image holds the toolchain. A build given neither `--output` nor `-t` writes
+    runner; a tagged one replaces the previous image.
-    an untagged image and leaves it dangling, on every developer host and every
-    CI runner. `script/cibuild` and `script/docker` build the image that ships
-    and tag it, so each build replaces the previous image; each assigns the tag
-    on its own line before the build, so `set -e` stops it where
-    `script/projectname` fails.
 
     Inside a phase the tool is invoked directly — `golangci-lint`, `go test`,
     `eslint`, `prettier` — never through `make lint` or `script/test`, which are
@@ -159,122 +143,66 @@ 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 cache, its own `TMPDIR` and
-    out of reach. The lint phase does keep golangci-lint's cache between check
+    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
+- **Any build that runs checks is built with `--no-cache`.** Docker invalidates
-  invalidates a `COPY` layer only when the copied content changes, so on an
+  a `COPY` layer only when the copied content changes, so on an unchanged tree
-  unchanged tree the check `RUN` is served from cache, nothing executes, and the
+  the check `RUN` is served from cache, nothing executes, and the build still
-  build still exits 0. Every `docker build` in `script/` therefore passes
+  exits 0. Every `docker build` in `script/` therefore passes `--no-cache`:
-  `--build-arg CACHEBUST="$(date +%s)-$$"`, the time and the script's process
+  `script/lint`, `script/test`, `script/cibuild` and `script/docker` are the
-  id, so no two builds share a value, not even the three in one
+  four, and there is no fifth — `script/check` runs the two gate phases and
-  `script/cibuild`. `script/lint`, `script/test`, `script/cibuild` and
+  `script/fmt-check`, and builds no image of its own. A bare `docker build .` is
-  `script/docker` are the four, and there is no fifth — `script/check` runs the
+  not evidence that anything ran: a sub-second build reporting success is a
-  two gate phases and `script/fmt-check`, and builds no image of its own. In
+  cache hit, not a result. Never invalidate by pruning — `docker builder prune`
-  every stage of the `Dockerfile`, `ARG CACHEBUST` comes right after the steps
+  and friends destroy a build cache shared with every other build on the host.
-  that install system packages and download Go's modules, or right after `FROM`
-  in a stage with neither, and every step that lints, tests or compiles comes
-  after it. A step that installs anything else as well, such as a
-  `script/bootstrap` that also installs node packages, comes after it too. A new
-  value reruns every `RUN` step after that line; `COPY` steps are compared by
-  content and need nothing. Docker keeps the layers above the line until the
-  base image, their own lines or the files they copy change. A stage without the
-  `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
-  other build on the host. When a check is added or changed, prove it works by
-  planting a defect it must catch and watching the run fail on it, then revert
-  the defect. A green run alone shows neither that the check ran nor that it
-  covers what it should.
 
 - **The gate phases are separate stages, and the build stage depends on both.**
   The lint phase is based on the `golangci/golangci-lint` image (pinned by
   hash), so lint failures surface in seconds rather than after a full compile,
-  and the test phase is based on the Debian Go image. The canonical Go repo
+  and the test phase is based on the Go image. The canonical Go repo
   `Dockerfile`:
 
     ```dockerfile
-    # In every stage ARG CACHEBUST comes right after the steps that install
-    # system packages and download Go's modules, or right after FROM in a
-    # stage with neither, and every step that lints, tests or compiles
-    # 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
     WORKDIR /src
     COPY go.mod go.sum ./
     RUN go mod download
-    ARG CACHEBUST
     COPY . .
-    RUN --mount=type=cache,target=/root/.cache/go-build \
+    RUN golangci-lint run --config .golangci.yml ./...
-        --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
+    # Test phase
-    # image ships and the alpine one does not. -count=1 because the mounted
+    # golang:1.x-alpine, YYYY-MM-DD
-    # cache also holds test results, which go test would otherwise replay.
-    # golang:1.x, YYYY-MM-DD
     FROM golang@sha256:... AS test
     WORKDIR /src
     COPY go.mod go.sum ./
     RUN go mod download
-    ARG CACHEBUST
     COPY . .
-    RUN --mount=type=cache,target=/root/.cache/go-build \
+    RUN go test -timeout 90s -race -cover ./... || \
-        go test -count=1 -timeout 90s -race -cover ./... || \
         { echo "--- Rerunning with -v for details ---"; \
-          go test -count=1 -timeout 90s -race -v ./...; exit 1; }
+          go test -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
+    COPY --from=lint /src/go.sum /dev/null
+    COPY --from=test /src/go.sum /dev/null
     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
-    # A tar-stream context keeps the sender's file owners, which git refuses.
-    RUN git config --system --add safe.directory /src
     COPY . .
 
-    # The VERSION build arg when one is given, otherwise
+    ARG VERSION=dev
-    # `git describe --tags --always` on the .git in the build context. With
+    RUN CGO_ENABLED=0 go build -trimpath \
-    # .git present, a version that is still empty, dev or unknown fails the
-    # build: git is missing or could not read the checkout.
-    ARG VERSION
-    RUN --mount=type=cache,target=/root/.cache/go-build \
-        VERSION="${VERSION:-$(git describe --tags --always)}"; \
-        if [ -e .git ]; then \
-            case "$VERSION" in ""|dev|unknown) \
-                echo "version is '$VERSION' although .git is present" >&2; \
-                exit 1 ;; \
-            esac; \
-        fi; \
-        CGO_ENABLED=0 go build -trimpath \
         -ldflags="-s -w -X main.Version=${VERSION}" \
         -o /app ./cmd/app/
 
     # Runtime stage, and the last one
     FROM alpine@sha256:...
-    ARG CACHEBUST
     COPY --from=builder /app /usr/local/bin/app
     ENTRYPOINT ["app"]
     ```
@@ -289,106 +217,23 @@ 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:
-        - The layers above `ARG CACHEBUST`: the system packages and Go's
-          modules. Docker installs the packages again when the base image or the
-          install line changes, and downloads the modules again when `go.mod` or
-          `go.sum` changes. Go checks every module against `go.sum` as it
-          downloads it, and no later build can change a kept layer. The modules
-          are kept in a layer rather than a cache mount because a cache mount is
-          shared by every build on the host, and Go builds from whatever files
-          it holds without checking them again (only `go mod verify` does), so a
-          file changed there would go unnoticed.
-        - 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:
       `RUN mkdir -p web/dist && touch web/dist/index.html web/dist/style.css`.
-    - If the project requires CGO or system libraries for linting, install them
+    - If the project requires CGO or system libraries for linting (e.g.
-      in the lint phase. The `golangci/golangci-lint` image is Debian-based and
+      `vips-dev`), install them in the lint phase with `apk add`.
-      has no `apk`, so install with `apt-get` under the Debian package name
+    - `ARG VERSION=dev` is declared in the stage that compiles and supplied by
-      (`libvips-dev`, where alpine says `vips-dev`), and delete the package
+      `script/docker` and `script/cibuild`; no stage may call `git describe`.
-      lists in the same `RUN`, so the layer does not keep them. The test phase,
-      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
-      `config` at any depth (`**/.git/config`, `**/.git/modules/**/config`): the
-      repository's own, each submodule's under `.git/modules/`, and that of a
-      submodule keeping its own `.git` directory. `git describe` does not need
-      them, and each can hold a credential: a password in a remote URL, or the
-      token the CI checkout step stores there. A submodule whose name has a
-      `config` segment (`config`, `deploy/config`, `config/lib`) loses its whole
-      git directory to `**/.git/modules/**/config`, and Go's version stamping
-      then fails the build: give it a name without that segment
-      (`git submodule add --name`). The stage that compiles has `git` (the
-      Debian Go image has it; an alpine one needs `apk add --no-cache git`) and
-      takes the version from the `VERSION` build argument when one is given,
-      otherwise from `git describe --tags --always`. That gives the tag on a
-      tagged commit; on a later commit, the tag, the number of commits since it
-      and the short commit (`v1.2.3-4-gabc1234`); and the short commit when no
-      tag is reachable. The stage that compiles also marks its working directory
-      safe for git (`git config --system --add safe.directory /src`): a context
-      sent as a tar stream keeps the sender's file owners, and git refuses a
-      checkout owned by another user, so the version would come out empty.
-      `ARG VERSION` has no default, and the build fails if the context carries
-      `.git` and the version still comes out empty, `dev` or `unknown`. A plain
-      `docker build .` with no build arguments must succeed; a Dockerfile that
-      refuses an empty build argument drops that refusal and keeps the argument.
-      A checkout whose `.git` is a file (a linked worktree, or a repository
-      checked out as a submodule) is the exception: that file points to a git
-      directory outside the build context, so the build cannot read the version
-      and a plain `docker build .` fails; pass the version with
-      `--build-arg VERSION=...`, as `script/docker` and `script/cibuild` already
-      do.
 
 - Every repo should have a Gitea Actions workflow (`.gitea/workflows/`) that
-  runs `script/cibuild` on push, and checks out the repo as its only other step,
+  runs `script/cibuild` on push, and checks out the repo as its only other step.
-  with `persist-credentials: false`: `script/cibuild` needs no token, and
+  That script bootstraps, runs the gate phases, and then builds the image, so a
-  without it the checkout leaves the job's token in `.git/config` for every
+  successful run means every check passed; a bare `docker build .` does not
-  later step. The checkout step also sets `fetch-depth: 0`, which fetches the
-  tags `git describe` needs: by default it clones shallow with no tags, and a
-  tagged repository's CI build would stamp a bare short commit id. The
-  workflow's `concurrency` block groups runs by workflow and branch
-  (`${{ github.workflow }}-${{ github.ref }}`) with `cancel-in-progress: true`,
-  so a new push cancels the older run on the same branch, queued or running, and
-  no other: runs for replaced commits do not hold up the shared runner.
-  `script/cibuild` bootstraps, runs the gate phases, and then builds the image,
-  so a successful run means every check passed; a bare `docker build .` does not
   carry the same guarantee, because its gate phases may come from the cache. The
-  image build gets a `CACHEBUST` value of its own and so runs the gate phases a
+  image build is uncached and so runs the gate phases a second time. That is the
-  second time. That is the price of the rule above, and it is worth paying: the
+  price of the rule above, and it is worth paying: the image that ships is built
-  image that ships is built from a run of its own gates rather than from a cache
+  from a run of its own gates rather than from a cache entry.
-  entry. The `check` job sets `timeout-minutes: 20`, so a hung build frees the
-  shared runner after 20 minutes. That allows for the three Docker builds
-  described above (the test phase, the lint phase, then the image), each held to
-  the 5-minute Docker build limit below, plus the bootstrap. A separate workflow
-  limited to `main` by a `branches` list under `on: push` cannot be checked by
-  review: to try a change to it, add the feature branch to that list and push,
-  then remove the branch from the list again before merging. Keep any job in it
-  that publishes behind `if: github.ref_name == 'main'`, so the run from the
-  feature branch publishes nothing.
 
 - Use platform-standard formatters: `black` for Python, `prettier` for
   JS/CSS/Markdown/HTML, `go fmt` for Go. Always use default configuration with
@@ -441,18 +286,17 @@ style conventions are in separate documents:
     ```
 
     `-count=1` is required on both invocations: it defeats Go's test _result_
-    cache, so neither run can report a stored pass in place of running the
+    cache, so the target cannot report a pass it did not earn, and the rerun
-    tests. It leaves the build cache alone, so it costs the runtime of the suite
+    reproduces a failure instead of replaying it. It leaves the build cache
-    and no recompilation.
+    alone, so it costs the runtime of the suite and no recompilation.
 
-    That cache is Go's own, separate from Docker's layer cache. Go stores a
+    Note that this is a second, independent cache, stacked below the Docker
-    passing result in its cache directory (`GOCACHE`), and when the same tests
+    layer cache that [issue #26](https://git.eeqj.de/sneak/prompts/issues/26)
-    run again on unchanged code it prints that result, marked `(cached)`,
+    addresses. `CHECK_EPOCH` guarantees the `RUN make test` _step_ re-executes;
-    without running them. The directory lasts from one run to the next on a
+    it does not guarantee `go test` inside that step does any work, because the
-    developer's machine, where this target runs, and in the `test` phase of the
+    `GOCACHE` baked into earlier image layers survives into the re-executed
-    `Dockerfile`, which mounts it to keep compiled packages between check
+    step. They are two separate defects requiring two separate fixes, and a fix
-    builds, so the phase's `go test` runs carry `-count=1` too. A new
+    for one must not be recorded as covering the other.
-    `CACHEBUST` value (above) is what makes that step run on an unchanged tree.
 
     Python example:
 
@@ -480,12 +324,9 @@ style conventions are in separate documents:
 
 - `.gitignore` should be comprehensive from the start: OS files (`.DS_Store`),
   editor files (`.swp`, `*~`), in-repo agent scratch directories (`.claude/`),
-  `node_modules/`, and the repo's own build outputs. Fetch the standard
+  language build artifacts, and `node_modules/`. Fetch the standard `.gitignore`
-  `.gitignore` from
+  from `https://git.eeqj.de/sneak/prompts/raw/branch/main/.gitignore` when
-  `https://git.eeqj.de/sneak/prompts/raw/branch/main/.gitignore` when setting up
+  setting up a new repo. These patterns are written to `.gitignore`'s own
-  a new repo. A repo's `.gitignore` is the standard file followed by the repo's
-  own entries, such as its binaries; a re-vendor replaces the standard part and
-  keeps those entries. These patterns are written to `.gitignore`'s own
   semantics, in which an unanchored pattern already matches at every depth; they
   are not a `.dockerignore` and must not be transplanted into one unmodified.
 
@@ -499,7 +340,7 @@ style conventions are in separate documents:
   — which is more dangerous than a short file with no secret patterns at all,
   because it reads as solved and stops anyone looking. Give every
   depth-independent pattern the `**/` prefix and leave only genuinely
-  root-anchored entries unprefixed: `.claude`, and the repo's own host-built
+  root-anchored entries unprefixed: `.git`, and the repo's own host-built
   binary, written `/myapp` and never `**/myapp`, which would also match
   `cmd/myapp/` and delete the package directory from the context. Matching is
   case-sensitive, and an ALL-CAPS twin per pattern still misses `Server.Key`, so
@@ -524,24 +365,21 @@ style conventions are in separate documents:
   directory, so a repo running agents in subdirectories still ships
   `services/api/.claude/` and must add its own anchored entry there.
 
-- **A plain `docker build .` of a clone stamps the version that
+- **Excluding `.git` means `git describe` cannot run inside any build stage, and
-  `git describe --tags --always` gives**, derived from the `.git` in the build
+  it fails quietly there.** In a build stage there is no repository, so
-  context as the canonical `Dockerfile` above shows. Without its failure check,
+  `git describe` writes nothing to stdout, `-X main.Version=` comes out empty,
-  a missing `git` or an unreadable checkout would leave `-X main.Version=` empty
+  the binary reports no version at all, and the build still exits 0. Compute the
-  and the build would still exit 0. `script/docker` and `script/cibuild` pass
+  version on the host and thread it in as a build arg. `script/docker` and
-  the version they compute on the host; it takes precedence. They do this
+  `script/cibuild` do this, byte-identically across repos:
-  byte-identically across repos:
 
     ```sh
-    # The version and the tag each get their own line: a failing command
+    # Own line: a failing command substitution inside an argument does not
-    # substitution inside an argument does not trip `set -e`, so the inline
+    # trip `set -e`, so the inline form degrades to an empty constant.
-    # form degrades to an empty constant.
     version="$(git describe --tags --always --dirty 2>/dev/null || true)"
     [ -n "$version" ] || version="unknown"
-    tag="$(script/projectname)"
+    docker build --no-cache \
-    docker build --build-arg CACHEBUST="$(date +%s)-$$" \
         --build-arg VERSION="$version" \
-        -t "$tag" .
+        -t "$(script/projectname)" .
     ```
 
     `--always` makes an untagged repo yield an abbreviated commit hash rather
@@ -549,12 +387,12 @@ style conventions are in separate documents:
     fallback is applied — a live check that fires on a build from an export with
     no `.git` and on a repository with no commits yet. Do not fold it into the
     substitution as `|| echo unknown`, which makes the guard unreachable. The
-    Dockerfile's side is `ARG VERSION` in the stage that compiles, declared
+    Dockerfile's side is `ARG VERSION=dev` in the stage that compiles, declared
     there because `ARG` is stage-scoped; passing `VERSION` to a repo whose
     Dockerfile declares no such `ARG` is ignored and costs nothing, which is why
     the scripts stay byte-identical. One consequence for CI: the standard
-    checkout action clones shallow and fetches no tags, so the canonical
+    checkout action clones shallow and fetches no tags, so a repo that embeds a
-    `.gitea/workflows/check.yml` sets `fetch-depth: 0` on its checkout step.
+    tag-derived version must set `fetch-depth: 0` on its checkout step.
 
 - **Verify `.dockerignore` by enumerating the image, not by reading the
   patterns.** Plant files at the root _and_ at least two directories deep, build
@@ -588,18 +426,12 @@ style conventions are in separate documents:
   `test-support` depguard rule, where a repo names its own test-support packages
   by full import path. A repo adds entries there and changes nothing else, and a
   re-vendor carries its entries forward. The canonical golangci-lint version is
-  v2.14.0 (released 2026-09-24), pinned as the digest of the lint phase's base
+  v2.12.2 (released 2026-05-06), pinned as the digest of the lint phase's base
   image
-  (`golangci/golangci-lint@sha256:ad862ba6b3798cbe0fd9fd7408d498fd74fbd2623a92406b2fd3898faf0bf98f`,
+  (`golangci/golangci-lint@sha256:5cceeef04e53efe1470638d4b4b4f5ceefd574955ab3941b2d9a68a8c9ad5240`,
-  which reports `2.14.0 built with go1.27.0 from 114493f9`). A module's `go`
+  which reports `2.12.2 built with go1.26.2 from c0d3ddc9`). That digest is the
-  directive must not name a newer Go minor version than the one golangci-lint
+  only pin, since no repo installs golangci-lint on the host: bumping the
-  was built with, or golangci-lint refuses to lint it: this release lints
+  version means changing it and nothing else.
-  `go 1.27.1` but not `go 1.28`. That digest is the only pin, since no repo
-  installs golangci-lint on the host. A repo sets the lint phase digest to the
-  one named here and re-vendors `.golangci.yml` in the same commit, whichever of
-  the two prompted the change: the canonical copy can name linters that an older
-  golangci-lint rejects, and a newer golangci-lint can add linters that
-  `default: all` switches on until the canonical copy disables them.
 
 - **`script/bootstrap` installs a pinned tool by comparing versions, never by
   testing presence.** An `if ! command -v <tool>; then install; fi` guard tests
@@ -621,18 +453,8 @@ style conventions are in separate documents:
       function defined and never invoked has the same exit status and the same
       empty output as one that worked.
 
-    Node is the exception to the whole-token comparison: the canonical
-    `script/bootstrap` compares only its major version, because the node 22
-    alpine image the `Dockerfile` stages start from is not the exact pin, and
-    nvm cannot install a prebuilt node on alpine.
-
     Keep it POSIX sh: no arrays, no `[[`, no `grep -P`.
 
-    A Go tool a repo needs on the host is installed with `go install` pinned to
-    a commit hash (`go install <package>@<commit hash>`). It is never tracked as
-    a `go.mod` tool dependency or through a `tools.go` file, either of which
-    pulls the tool's own dependencies into the repo's `go.mod` and `go.sum`.
-
 - When pinning images or packages by hash, add a comment above the reference
   with the version and date (YYYY-MM-DD).
 
@@ -742,17 +564,13 @@ style conventions are in separate documents:
       Never edit existing migrations after release.
 
 - All repos should have an `.editorconfig` enforcing the project's indentation
-  settings: the standard file from
+  settings.
-  `https://git.eeqj.de/sneak/prompts/raw/branch/main/.editorconfig`, which sets
-  tabs for `Makefile` and Go files, followed by the repo's own sections, such as
-  one for another language it uses. A re-vendor replaces the standard part and
-  keeps those sections.
 
 - Avoid putting files in the repo root unless necessary. Root should contain
-  only project-level config files (`README.md`, `AGENTS.md`, `Makefile`,
+  only project-level config files (`README.md`, `Makefile`, `Dockerfile`,
-  `Dockerfile`, `LICENSE`, `.gitignore`, `.editorconfig`, `REPO_POLICIES.md`,
+  `LICENSE`, `.gitignore`, `.editorconfig`, `REPO_POLICIES.md`, and
-  and language-specific config). Everything else goes in a subdirectory.
+  language-specific config). Everything else goes in a subdirectory. Canonical
-  Canonical subdirectory names:
+  subdirectory names:
     - `bin/` — executable scripts and tools
     - `cmd/` — Go command entrypoints; thin only: one `main.go` per binary whose
       body is a single call into `internal/` or `pkg/`, no project logic in
@@ -783,7 +601,3 @@ style conventions are in separate documents:
     - Go: `go.mod`, `go.sum`, `.golangci.yml`
     - JS: `package.json`, `yarn.lock`, `.prettierrc`, `.prettierignore`
     - Python: `pyproject.toml`
-
-- Guidance for coding agents lives in one `AGENTS.md` at the repository root. It
-  is never committed under a file or directory named after one agent tool, such
-  as `CLAUDE.md` or `.claude/`, and never split into separate memory files.

TODO.md

@@ -18,7 +18,7 @@
 
 pre-1.0. No git tags exist. The `1.0.0` milestone is in progress; work lands on
 `next`, and `main` receives only the milestone PR that the owner merges. `next`
-is at the canonical `golangci-lint` v2.14.0 config and is green. Recent work
+is at the canonical `golangci-lint` v2.12.2 config and is green. Recent work
 extracted the internal/magic, internal/allowlist, internal/httpfetcher, and
 internal/signature packages. The gosec findings from the 2026-07-06 survey are
 resolved. The disk cache is now size-bounded with LRU eviction
@@ -30,420 +30,6 @@ P2: security: per-origin rate limiting
 
 # Completed Steps
 
-- 2026-10-26 both image routes serve an image with one function, `serveImage`,
-  and answer its errors with one, `respondImageError` (closes #316).
-  `HandleImage` parses the path and verifies the signature, and `HandleImageEnc`
-  decrypts the token. Each then calls `serveImage`.
-    - `handleImageError`, the encrypted route's own mapping, is gone.
-    - `/v1/image/` answers 504 when the upstream has not sent its response
-      headers within `upstream_fetch_timeout`, as `/v1/e/` did. It answered 500.
-    - `respondImageError` logs the image service's errors as "failed to get
-      image". Each answer gets the same level on `/v1/image/` and on `/v1/e/`:
-        - 500: error, as pixa's own failure
-        - 400: warn
-        - 403: warn
-        - 415: warn
-        - 502: warn
-        - 503: warn
-        - 504: warn
-    - Before, `/v1/image/` logged all of these answers at error level. `/v1/e/`
-      logged only its 500, as "image request failed", without the host and the
-      path.
-    - `respondImageError` does not log the 415 for a body refused for its first
-      bytes, on either route. The image service logs it as "source refused", at
-      warn level.
-    - The "image served" line carries the host, the path and `fetched_bytes` on
-      both routes. The debug line "encrypted image request" is gone.
-    - The debug line "failed to decrypt URL" is now "invalid encrypted URL". A
-      token that decrypts to a payload that does not decode also gets it.
-    - A failed write is logged once, as "failed to write response" at warn
-      level, since most often the client has gone away. It carries the
-      `request_id`, the host, the path, `served_bytes` and the error, and is not
-      also logged as "image served".
-- 2026-10-26 every key derived from the signing key is derived in one place
-  (closes #315): `seal.DeriveKeys` returns them as one `seal.Keys`, with their
-  salts declared beside it. `internal/providers` calls it once at startup. Each
-  key is derived as before, with `seal.DeriveKey` and the same salt.
-    - The session manager, the encrypted URL generator and the CSRF protection
-      each take their own key instead of the signing key.
-    - `session.NewManager`, `encurl.NewGenerator`, `newCSRFProtect` and
-      `handlers.New` return no error, as nothing in them can fail now.
-    - The signing key itself stays the HMAC key of signed URLs and the login
-      password.
-    - `README.md` says under `signing_key` what it protects.
-- 2026-10-26 the image request holds only what names the cached object (closes
-  #314): its source and its transform, which the variant key covers. The signed
-  URL format, the signing algorithm and every route's answers are unchanged.
-    - The `/v1/image/` handler checks `allowlist_hosts` and verifies the
-      signature itself, with `Signer.Verify(req, sig, expires)`.
-    - Each image handler keeps its URL's expiry as a value of its own, for
-      `Cache-Control`. `encurl`'s `Generate` takes the expiry and its `Parse`
-      returns it.
-    - The fetcher takes the source and builds its URL with `Source.URL`, over
-      http only when the fetcher's own `AllowHTTP` is set. `validateURL` takes
-      that URL, so no URL string is built and parsed again.
-    - `chooseAutoFormat` returns the format it chooses, and the handler puts it
-      into the request it parsed.
-    - The image service serves images through `Get`, and has `WaitForProcessing`
-      for shutdown.
-    - Removed:
-        - `Signature`, `Expires`, `AllowHTTP` and `SourceURL` of the image
-          request
-        - `Service.ValidateRequest`, and the service's signer, allowlist and
-          `AllowHTTP`
-        - `extractHost` of the fetcher and `urlToFSPath` of the mock fetcher
-- 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
-  centre, so an 8192x64 source at 8192x8192 made it allocate about 24 GiB, and
-  an 8192x1 source answered 500. The image processor now first cuts the centre
-  of the source, widened to whole source pixels, and thumbnail scales and cuts
-  only that, by the same amount on both sides as before. What it copies into
-  memory is then larger than the output by less than one scaled source pixel on
-  each side. With the runtime image's libvips and JPEG output at 8192x8192,
-  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.
-- 2026-10-15 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
-  upstream image, without a signature for an allowlisted host, and cached it
-  under keys of its own. `README.md` says neither may hold a `#`.
-- 2026-10-15 the host of a `/v1/image/` URL must be a host name or an IPv4
-  address (letters, digits, hyphens, underscores and dots) or an IPv6 address in
-  brackets, either one optionally followed by `:` and a port, and any other host
-  is refused with 400 (closes #275): only `@` was refused, so a `?` written as
-  `%3F` gave the host `cdn.example.com?x=1`, which Go's URL parser reads as
-  `cdn.example.com` with a query. Such a URL passed the allowlist, and each text
-  after the `?` fetched the host's root path and cached the answer under keys of
-  its own. A `#`, `%`, `\` or space written percent-encoded is refused the same
-  way, and so is an IPv6 address without brackets, which needed a signature
-  before. Underscores are kept because `allowlist_hosts` accepts host names
-  holding them.
-- 2026-10-15 the README says how a source URL with a query is written into an
-  image URL, and the image route accepts it (closes #255): the query follows the
-  source path after `%3F`. pixa now reads the image URL's path decoded once, so
-  the `?` before the query, any `?` in it and every `%` in the source path or
-  query must be percent-encoded, and any other character may be. The route used
-  to parse chi's wildcard, which holds the path as the client wrote it whenever
-  that is not Go's own encoding of it; a `/`, `;` or `,` in the query written as
-  `%2F`, `%3B` or `%2C`, as `GenerateSignedURL` wrote them, kept the `%3F` from
-  being read as `?`, and the request failed with 401. `GenerateSignedURL` now
-  writes Go's own encoding of the path. The README has an example with a query
-  and its signature. The path traversal check no longer reads the source query,
-  and keeps a `%` that does not start a percent-escape as it is instead of
-  refusing the URL, so a source path or query holding `%25` is accepted, while a
-  double-encoded `..` next to such a `%` is still refused.
-- 2026-10-15 `max_concurrent_processing` defaults to half the CPUs pixa sees,
-  rounded down, and at least 1 (closes #242): it defaulted to one image per CPU,
-  and a container with no CPU limit sees every CPU of the host, so on a 48-CPU
-  host pixa processed 48 images at once, each of which can take about 4.2 GiB.
-  `config.DefaultMaxConcurrentProcessing` gives the default to the config and to
-  `imageprocessor.New`; `PIXA_MAX_CONCURRENT_PROCESSING` still overrides it.
-  "Running under upaas" in `README.md` gives the worst-case memory, measured,
-  and tells the operator to set `PIXA_MAX_CONCURRENT_PROCESSING` and
-  `PIXA_UPSTREAM_CONNECTIONS` to fit the container's memory. It also gives the
-  file libvips writes to `/tmp` for each large source, up to 1 GiB, measured,
-  which is outside `/var/lib/pixa` and `cache_max_bytes` and is memory where
-  `/tmp` is a tmpfs.
-- 2026-10-15 the canonical files are re-vendored from `sneak/prompts` commit
-  `e3f79c4` (closes #221): `.dockerignore`, `.editorconfig`,
-  `.gitea/workflows/check.yml`, `.gitignore`, `.golangci.yml`,
-  `.prettierignore`, `.prettierrc`, `REPO_POLICIES.md` and the standard scripts
-  are its copies. pixa's own entries follow the standard part: `/bin`, `/data`
-  and the local config files in `.dockerignore`; Go's `*.log`, `*.out` and
-  `*.test`, `vendor/`, the binaries, `/data/`, `*.sqlite3` and the local config
-  files in `.gitignore`. The workflow keeps its `script/docker-smoke` step while
-  https://git.eeqj.de/sneak/pixa/issues/203 is open. The scripts pass a new
-  `CACHEBUST` build argument in place of `--no-cache`, and every `Dockerfile`
-  stage declares it first, so every `RUN` step still runs on every build while
-  Go's build cache, mounted on the steps that compile, is kept; both `go test`
-  runs keep `-count=1`. The lint and test builds write no image. The lint phase
-  runs golangci-lint v2.14.0, the test phase runs on the Debian Go image, and
-  the build stage marks `/src` safe for git. `script/bootstrap`, `script/fmt`
-  and `script/fmt-check` use the node on the `PATH` only when it has the pinned
-  major version. Of golangci-lint v2.14.0's two findings, an unused `nolint`
-  directive is removed, and gosec's new path check is marked as not applying to
-  the fixed config file locations. The agent guidance moves unchanged from
-  `CLAUDE.md` to a root `AGENTS.md`, where `REPO_POLICIES.md` keeps it.
-- 2026-10-15 the request metrics record any method that is not a standard one as
-  `other` (closes #274): their `method` label was each request's method as sent,
-  and Go's HTTP server accepts any method name, so a client sending made-up
-  methods added series to the Prometheus registry that were never removed. The
-  label is now the request's method only for `GET`, `HEAD`, `POST`, `PUT`,
-  `PATCH`, `DELETE`, `OPTIONS`, `CONNECT` and `TRACE`. The metrics library reads
-  the method from the request it is handed, so the metrics middleware hands it a
-  copy of the request carrying the label; the handlers still see the method the
-  client sent.
-- 2026-10-15 logging out ends every login session (closes #256): a login session
-  was a cookie with nothing kept on the server, so `/logout` removed it from one
-  browser and a copy of it kept working for its 30 days. Every login is made
-  with the one signing key, so logging out now ends them all: the session
-  manager keeps a random value, made with `crypto/rand` when the new `logout`
-  table has none and replaced by each logout, saves it there so that it outlasts
-  a restart, puts the value at login in each session, and refuses a session
-  carrying another value. The check for a logout compares no time, so a login
-  after a logout works whatever the host's clock does; a session's 30 days are
-  still checked against the clock. Losing the state directory ends every login
-  session, and no logout can make an ended one work again. Logging out is now
-  `POST /logout` from a form on the generator page, behind the CSRF check the
-  other forms have, so a link or image elsewhere on the same site cannot end the
-  sessions. A logout without a valid login session ends none and only removes
-  the cookie, as anyone can take a CSRF token from the login page. A logout that
-  cannot be saved answers 500. `session.NewManager`, which the tests use, keeps
-  the value in memory only; pixad uses `session.NewManagerWithDatabase`.
-- 2026-10-15 a cached file left empty or partial is no longer served, or fetched
-  again on every request (closes #252). Source and transformed image files, and
-  each transformed image's `.meta` file, are synced to disk before they are
-  renamed into place, and their directory after; the `.meta` file is written
-  before the image, and a failed directory sync removes the renamed file. The
-  reconciliation pass, at startup and every five minutes, removes a cached
-  source or transformed image whose file is empty, or not the size the database
-  records for it, with its rows and a warning naming the file, so the next
-  request fetches the source or converts the image again; requests compare no
-  sizes. Storing a source over a file of another size replaces that file. A
-  source that fails to decode is not removed for that alone: a damaged upstream
-  image would then be fetched on every request.
-- 2026-10-15 a transcode stops once its request's `downstream_timeout` has
-  ended, unless it has begun encoding (closes #243): the image processor looked
-  at its context only while it waited for a processing slot, so an image was
-  decoded and encoded, holding the slot, however long after its request's
-  deadline that took. `Process` now returns the context's error, and gives the
-  slot back, when the context has ended by the time it has the slot or before it
-  encodes. A request that waited for a shared transcode stopped at the first
-  request's deadline is answered 503 `server busy, try again later`, not 500,
-  though its own `downstream_timeout` may not have ended. govips gives pixa no
-  way to stop libvips once an encode has begun, so that encode keeps its slot
-  until it finishes; the limit of 8192 on each side of the source and of the
-  output bounds how long that takes. With one libvips thread, 8192x8192 random
-  pixels take up to about 1 second to encode as JPEG, 15 as PNG, 16 as GIF, 63
-  as WebP, 110 as AVIF and 96 as JPEG XL, the last three with an alpha channel,
-  plus up to about 11 seconds to decode the source; `README.md` gives these
-  times and no longer says the work stops when `downstream_timeout` ends. The
-  settings of the WebP, AVIF and JPEG XL encoders, which can hold a slot past
-  the default `downstream_timeout` of 60 seconds, are unchanged.
-- 2026-10-15 "Running under upaas" in `README.md` tells the operator to set
-  `PIXA_CACHE_MAX_BYTES` (closes #251): it listed the variable as optional, but
-  under upaas the volume is a directory on the host's filesystem. The default,
-  75% of the sum of that filesystem's free space and what the cache holds, and
-  at least 500 MiB, let one pixa take three quarters or more of the space the
-  host and every other app had left, and all of it when that was 500 MiB or
-  less. The section now says so. The default is unchanged.
-- 2026-10-15 the request metrics are labelled by route, not by path (closes
-  #254): their `handler` label was each request's path, so every new path, a 404
-  or an encrypted URL, added series to the Prometheus registry that were never
-  removed, and `/metrics` listed every encrypted URL's token. The label is now
-  the pattern of the chi route the request matches, such as `/v1/image/*`, or
-  `unmatched` for a request that matches none: one the router answers 404 or
-  405, or a CORS preflight. The metrics library takes the label before the
-  request is routed, so the metrics middleware asks the router which route
-  matches.
 - 2026-10-15 expired negative cache rows are removed on a schedule (closes
   #244): the row of a failed fetch, which makes pixa answer 502 for that source
   URL for 5 minutes, was deleted only when the same URL was requested again
@@ -947,11 +533,11 @@ P2: security: per-origin rate limiting
   cancellation but keeps its deadline, and the others wait for its image or
   error holding no upstream connection or processing slot, and stop waiting when
   their own context ends; the request doing the processing waits for it even
-  then, until it ends, which can be after its deadline; a request whose context
+  then, up to its deadline; a request whose context has already ended starts
-  has already ended starts nothing; each request counts one miss, and the
+  nothing; each request counts one miss, and the processing counts its fetch and
-  processing counts its fetch and transcode once; a panic while processing is
+  transcode once; a panic while processing is reported to Sentry when
-  reported to Sentry when `sentry_dsn` is set and becomes an error for every
+  `sentry_dsn` is set and becomes an error for every waiting request instead of
-  waiting request instead of stopping pixad; documented in `README.md`.
+  stopping pixad; documented in `README.md`.
 - 2026-09-29 only the image routes send CORS headers (closes #98): the CORS
   middleware, with the `access_control_allow_origin` origin, moved from the
   router root onto a `/v1` subrouter holding `/v1/image/` and `/v1/e/`, where it

configs/config.example.yml

@@ -108,11 +108,10 @@ upstream_connections_per_host: 20
 # downstream_timeout has ended first.
 upstream_connections: 64
 
-# Maximum number of images decoded and encoded at once (default: half the
+# Maximum number of images decoded and encoded at once (default: the
-# number of CPUs pixa can use, at least 1; the number of CPUs follows a
+# number of CPUs pixa can use, which follows a container's CPU limit). A
-# container's CPU limit). A request that finds none free waits up to 10
+# request that finds none free waits up to 10 seconds for one, and if none
-# seconds for one, and if none frees up it is answered 503, unless
+# frees up it is answered 503, unless downstream_timeout has ended first.
-# downstream_timeout has ended first.
 # max_concurrent_processing: 4
 
 # How many requests to the image routes (/v1/image/ and /v1/e/) one client

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/concurrency_limits_internal_test.go

@@ -1,7 +1,6 @@
 package config
 
 import (
-	"fmt"
 	"runtime"
 	"testing"
 )
@@ -13,8 +12,8 @@ const (
 )
 
 // TestOmittedConcurrencyLimitsUseDefaults checks that an omitted
-// max_concurrent_processing is half the CPUs Go uses, and at least 1, and
+// max_concurrent_processing is the number of CPUs Go uses and an omitted
-// an omitted upstream_connections is 64.
+// upstream_connections is 64.
 func TestOmittedConcurrencyLimitsUseDefaults(t *testing.T) {
 	t.Parallel()
 
@@ -23,9 +22,9 @@ func TestOmittedConcurrencyLimitsUseDefaults(t *testing.T) {
 		t.Fatalf("minimal config should be valid, got error: %v", err)
 	}
 
-	if c.MaxConcurrentProcessing != max(runtime.GOMAXPROCS(0)/2, 1) {
+	if c.MaxConcurrentProcessing != runtime.GOMAXPROCS(0) {
-		t.Errorf("MaxConcurrentProcessing = %d, want %d, half the CPUs",
+		t.Errorf("MaxConcurrentProcessing = %d, want %d, one per CPU",
-			c.MaxConcurrentProcessing, max(runtime.GOMAXPROCS(0)/2, 1))
+			c.MaxConcurrentProcessing, runtime.GOMAXPROCS(0))
 	}
 
 	if c.UpstreamConnections != 64 {
@@ -33,36 +32,6 @@ func TestOmittedConcurrencyLimitsUseDefaults(t *testing.T) {
 	}
 }
 
-// TestOmittedMaxConcurrentProcessingIsHalfTheCPUsAndAtLeastOne checks
-// that an omitted max_concurrent_processing is half the CPUs Go uses,
-// rounded down, and 1 when Go uses one CPU.
-//
-//nolint:paralleltest // it sets GOMAXPROCS, which other tests read
-func TestOmittedMaxConcurrentProcessingIsHalfTheCPUsAndAtLeastOne(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)
-
-		c, err := configFromYAML(t, signingKeyLine)
-		if err != nil {
-			t.Fatalf("minimal config should be valid, got error: %v", err)
-		}
-
-		t.Logf("GOMAXPROCS %d: MaxConcurrentProcessing %d",
-			tc.cpus, c.MaxConcurrentProcessing)
-
-		if c.MaxConcurrentProcessing != tc.want {
-			t.Errorf("GOMAXPROCS %d: MaxConcurrentProcessing = %d, want %d",
-				tc.cpus, c.MaxConcurrentProcessing, tc.want)
-		}
-	}
-}
-
 // TestExplicitConcurrencyLimitsAreUsed checks that valid values for the
 // two limits are used as given.
 func TestExplicitConcurrencyLimitsAreUsed(t *testing.T) {
@@ -191,19 +160,3 @@ func TestConcurrencyLimitsFromEnvironment(t *testing.T) {
 		})
 	}
 }
-
-// TestInvalidMaxConcurrentProcessingFromEnvironmentAbortsStartup checks
-// that a PIXA_MAX_CONCURRENT_PROCESSING that is not a whole number of at
-// least 1, an empty one included, aborts startup naming the variable and
-// the key instead of taking the default.
-func TestInvalidMaxConcurrentProcessingFromEnvironmentAbortsStartup(t *testing.T) {
-	for _, value := range []string{"", " ", "0.5", "half", "-1", "4 images"} {
-		t.Run(fmt.Sprintf("value %q", value), func(t *testing.T) {
-			t.Setenv(testMaxConcurrentProcessingVar, value)
-
-			_, err := configFromYAML(t, signingKeyLine)
-			wantStartupError(t, err,
-				testMaxConcurrentProcessingVar, keyMaxConcurrentProcessing)
-		})
-	}
-}

internal/config/config.go

@@ -37,45 +37,6 @@ const (
 	DefaultImageRequestsPerMinute     = 600
 )
 
-// DefaultMaxConcurrentProcessing returns the most images processed at once
-// when max_concurrent_processing is omitted: half the CPUs Go uses
-// (runtime.GOMAXPROCS(0), which follows a container's CPU limit), rounded
-// down, and at least 1.
-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 +83,6 @@ 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 +181,18 @@ 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 +230,8 @@ 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,
@@ -333,8 +297,10 @@ func newFromSmartConfig(sc *smartconfig.Config) (*Config, error) {
 			keyUpstreamConnectionsPerHost, DefaultUpstreamConnectionsPerHost),
 		UpstreamConnections: loader.intVal(
 			keyUpstreamConnections, DefaultUpstreamConnections),
+		// Decoding and encoding are CPU-bound, so the default is one image
+		// per CPU Go uses, which follows a container's CPU limit.
 		MaxConcurrentProcessing: loader.intVal(
-			keyMaxConcurrentProcessing, DefaultMaxConcurrentProcessing()),
+			keyMaxConcurrentProcessing, runtime.GOMAXPROCS(0)),
 		UpstreamFetchTimeout: loader.durationVal(
 			keyUpstreamFetchTimeout, DefaultUpstreamFetchTimeout),
 		UpstreamMaxResponseSize: loader.int64Val(
@@ -352,8 +318,8 @@ 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 +332,8 @@ 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 +348,6 @@ 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
@@ -880,7 +823,6 @@ func loadConfigFile(log *slog.Logger, appName string) (*smartconfig.Config, erro
 		// one whose path runs through a file, such as under a HOME of
 		// /dev/null. One that cannot be read or does not parse is a
 		// fatal startup error.
-		//nolint:gosec // G703: a fixed config location; HOME is the operator's
 		_, statErr := os.Stat(cleanPath)
 		if errors.Is(statErr, fs.ErrNotExist) || errors.Is(statErr, syscall.ENOTDIR) {
 			continue
@@ -1276,13 +1218,6 @@ 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 +1233,6 @@ 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 +1242,6 @@ 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")
 
+			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
@@ -95,23 +120,59 @@ 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);
 
--- A random value that a login session carries from its login. pixa makes it
+-- Cache statistics for monitoring
--- when the table has no row, and each logout replaces it; a login session
+CREATE TABLE IF NOT EXISTS cache_stats (
--- carrying another value is refused, so logging out ends every login session.
-CREATE TABLE IF NOT EXISTS logout (
     id INTEGER PRIMARY KEY CHECK (id = 1),
-    logout_value TEXT NOT NULL
+    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);

internal/encurl/encurl.go

@@ -7,15 +7,18 @@ 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"
 )
 
 // Errors returned by encurl operations.
@@ -25,18 +28,18 @@ 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
 	SourcePath  string               `cbor:"p"`            // required
 	SourceQuery string               `cbor:"q,omitempty"`  // optional
 	Width       int                  `cbor:"w,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
-	FitMode     imagerequest.Fit    `cbor:"fm,omitempty"` // default: cover
+	FitMode     imgcache.FitMode     `cbor:"fm,omitempty"` // default: cover
 	ExpiresAt   int64                `cbor:"e,omitempty"`  // 0 = never expires
 }
 
@@ -45,35 +48,20 @@ type Generator struct {
 	key [seal.KeySize]byte
 }
 
-// NewGenerator creates an encrypted URL generator that encrypts its tokens
+// NewGenerator creates an encrypted URL generator with a key derived
-// with key.
+// from the signing key.
-func NewGenerator(key [seal.KeySize]byte) *Generator {
+func NewGenerator(signingKey string) (*Generator, error) {
-	return &Generator{key: key}
+	key, err := seal.DeriveKey([]byte(signingKey), urlKeySalt)
+	if err != nil {
+		return nil, err
+	}
+
+	return &Generator{key: key}, nil
 }
 
-// Generate creates an encrypted URL token from the request's source and
+// Generate creates an encrypted URL token from the payload.
-// transform, each as the request holds it, and from expires; an empty format,
+// The token is CBOR-encoded, encrypted with NaCl secretbox, and base64url-encoded.
-// a 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, expires time.Time,
-) (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 !expires.IsZero() {
-		p.ExpiresAt = expires.Unix()
-	}
-
 	// CBOR encode the payload
 	data, err := cbor.Marshal(p)
 	if err != nil {
@@ -84,35 +72,40 @@ func (g *Generator) Generate(
 	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, and its
-// expiry. A token that never expires gives the zero time.
 // Returns ErrExpired if the token has expired, or other errors for invalid tokens.
-func (g *Generator) Parse(token string) (*imagerequest.Request, time.Time, error) {
+func (g *Generator) Parse(token string) (*Payload, error) {
 	// Decrypt
 	data, err := seal.Decrypt(g.key, token)
 	if err != nil {
 		if errors.Is(err, seal.ErrDecryptionFailed) ||
 			errors.Is(err, seal.ErrInvalidPayload) {
-			return nil, time.Time{}, ErrDecryptFailed
+			return nil, ErrDecryptFailed
 		}
 
-		return nil, time.Time{}, err
+		return nil, err
 	}
 
 	// CBOR decode
-	var p payload
+	var p Payload
 
 	err = cbor.Unmarshal(data, &p)
 	if err != nil {
-		return nil, time.Time{}, ErrInvalidFormat
+		return nil, ErrInvalidFormat
 	}
 
 	// Check expiration (0 = never expires)
 	if p.ExpiresAt != 0 && time.Now().Unix() > p.ExpiresAt {
-		return nil, time.Time{}, ErrExpired
+		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
@@ -133,17 +126,44 @@ func (g *Generator) Parse(token string) (*imagerequest.Request, time.Time, 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,
+			Height: p.Height,
 		},
-		Transform: imagerequest.Transform{
-			Size:    imagerequest.Size{Width: p.Width, Height: p.Height},
 		Format:  format,
 		Quality: quality,
 		FitMode: fitMode,
-		},
+		Expires: 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

@@ -6,8 +6,7 @@ import (
 	"time"
 
 	"sneak.berlin/go/pixa/internal/encurl"
-	"sneak.berlin/go/pixa/internal/imagerequest"
+	"sneak.berlin/go/pixa/internal/imgcache"
-	"sneak.berlin/go/pixa/internal/seal"
 )
 
 // Shared test fixture strings.
@@ -20,29 +19,24 @@ const (
 func TestGenerator_GenerateAndParse(t *testing.T) {
 	t.Parallel()
 
-	keys, err := seal.DeriveKeys("test-signing-key-12345")
+	gen, err := encurl.NewGenerator("test-signing-key-12345")
 	if err != nil {
-		t.Fatalf("seal.DeriveKeys() error = %v", err)
+		t.Fatalf("NewGenerator() error = %v", err)
 	}
 
-	gen := encurl.NewGenerator(keys.EncryptedURLKey)
+	payload := &encurl.Payload{
-
+		SourceHost:  testSourceHost,
-	req := &imagerequest.Request{
+		SourcePath:  testSourcePath,
-		Source: imagerequest.Source{
+		SourceQuery: testSourceQuery,
-			Host:  testSourceHost,
+		Width:       800,
-			Path:  testSourcePath,
+		Height:      600,
-			Query: testSourceQuery,
+		Format:      imgcache.FormatWebP,
-		},
-		Transform: imagerequest.Transform{
-			Size:    imagerequest.Size{Width: 800, Height: 600},
-			Format:  imagerequest.FormatWebP,
 		Quality:     90,
-			FitMode: imagerequest.FitContain,
+		FitMode:     imgcache.FitContain,
-		},
+		ExpiresAt:   time.Now().Add(time.Hour).Unix(),
 	}
-	expires := time.Now().Add(time.Hour)
 
-	token, err := gen.Generate(req, expires)
+	token, err := gen.Generate(payload)
 	if err != nil {
 		t.Fatalf("Generate() error = %v", err)
 	}
@@ -51,73 +45,66 @@ func TestGenerator_GenerateAndParse(t *testing.T) {
 		t.Fatal("Generate() returned empty token")
 	}
 
-	parsed, parsedExpires, err := gen.Parse(token)
+	parsed, err := gen.Parse(token)
 	if err != nil {
 		t.Fatalf("Parse() error = %v", err)
 	}
 
 	// 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 parsedExpires.Unix() != expires.Unix() {
+	if parsed.ExpiresAt != payload.ExpiresAt {
-		t.Errorf("ExpiresAt = %d, want %d", parsedExpires.Unix(), expires.Unix())
+		t.Errorf("ExpiresAt = %d, want %d", parsed.ExpiresAt, payload.ExpiresAt)
 	}
 }
 
 func TestGenerator_Parse_Expired(t *testing.T) {
 	t.Parallel()
 
-	keys, _ := seal.DeriveKeys("test-signing-key-12345")
+	gen, _ := encurl.NewGenerator("test-signing-key-12345")
-	gen := encurl.NewGenerator(keys.EncryptedURLKey)
 
-	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
-		},
 	}
 
-	token, err := gen.Generate(req, time.Now().Add(-time.Hour)) // Already expired
+	token, err := gen.Generate(payload)
 	if err != nil {
 		t.Fatalf("Generate() error = %v", err)
 	}
 
-	_, _, err = gen.Parse(token)
+	_, err = gen.Parse(token)
 	if err == nil {
 		t.Error("Parse() should fail for expired token")
 	}
@@ -130,10 +117,9 @@ func TestGenerator_Parse_Expired(t *testing.T) {
 func TestGenerator_Parse_InvalidToken(t *testing.T) {
 	t.Parallel()
 
-	keys, _ := seal.DeriveKeys("test-signing-key-12345")
+	gen, _ := encurl.NewGenerator("test-signing-key-12345")
-	gen := encurl.NewGenerator(keys.EncryptedURLKey)
 
-	_, _, err := gen.Parse("not-a-valid-token")
+	_, err := gen.Parse("not-a-valid-token")
 	if err == nil {
 		t.Error("Parse() should fail for invalid token")
 	}
@@ -142,17 +128,15 @@ func TestGenerator_Parse_InvalidToken(t *testing.T) {
 func TestGenerator_Parse_TamperedToken(t *testing.T) {
 	t.Parallel()
 
-	keys, _ := seal.DeriveKeys("test-signing-key-12345")
+	gen, _ := encurl.NewGenerator("test-signing-key-12345")
-	gen := encurl.NewGenerator(keys.EncryptedURLKey)
 
-	req := &imagerequest.Request{
+	payload := &encurl.Payload{
-		Source: imagerequest.Source{
+		SourceHost: testSourceHost,
-			Host: testSourceHost,
+		SourcePath: testSourcePath,
-			Path: testSourcePath,
+		ExpiresAt:  time.Now().Add(time.Hour).Unix(),
-		},
 	}
 
-	token, _ := gen.Generate(req, time.Now().Add(time.Hour))
+	token, _ := gen.Generate(payload)
 
 	// Tamper with the token
 	tampered := []byte(token)
@@ -160,7 +144,7 @@ func TestGenerator_Parse_TamperedToken(t *testing.T) {
 		tampered[10] ^= 0x01
 	}
 
-	_, _, err := gen.Parse(string(tampered))
+	_, err := gen.Parse(string(tampered))
 	if err == nil {
 		t.Error("Parse() should fail for tampered token")
 	}
@@ -169,78 +153,172 @@ func TestGenerator_Parse_TamperedToken(t *testing.T) {
 func TestGenerator_Parse_WrongKey(t *testing.T) {
 	t.Parallel()
 
-	keys1, _ := seal.DeriveKeys("signing-key-1")
+	gen1, _ := encurl.NewGenerator("signing-key-1")
-	keys2, _ := seal.DeriveKeys("signing-key-2")
+	gen2, _ := encurl.NewGenerator("signing-key-2")
-	gen1 := encurl.NewGenerator(keys1.EncryptedURLKey)
-	gen2 := encurl.NewGenerator(keys2.EncryptedURLKey)
 
-	req := &imagerequest.Request{
+	payload := &encurl.Payload{
-		Source: imagerequest.Source{
+		SourceHost: testSourceHost,
-			Host: testSourceHost,
+		SourcePath: testSourcePath,
-			Path: testSourcePath,
+		ExpiresAt:  time.Now().Add(time.Hour).Unix(),
-		},
 	}
 
-	token, _ := gen1.Generate(req, time.Now().Add(time.Hour))
+	token, _ := gen1.Generate(payload)
 
-	_, _, err := gen2.Parse(token)
+	_, err := gen2.Parse(token)
 	if err == nil {
 		t.Error("Parse() should fail with different signing key")
 	}
 }
 
-func TestGenerator_Parse_Defaults(t *testing.T) {
+func TestPayload_ToImageRequest(t *testing.T) {
 	t.Parallel()
 
-	keys, _ := seal.DeriveKeys("test-signing-key-12345")
+	payload := &encurl.Payload{
-	gen := encurl.NewGenerator(keys.EncryptedURLKey)
+		SourceHost:  testSourceHost,
-
+		SourcePath:  testSourcePath,
-	// Request with only required fields - should get defaults
+		SourceQuery: testSourceQuery,
-	token, err := gen.Generate(&imagerequest.Request{
+		Width:       800,
-		Source: imagerequest.Source{
+		Height:      600,
-			Host: testSourceHost,
+		Format:      imgcache.FormatWebP,
-			Path: testSourcePath,
+		Quality:     90,
-		},
+		FitMode:     imgcache.FitContain,
-	}, time.Now().Add(time.Hour))
+		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)
 	}
 }
 
 func TestGenerator_TokenIsURLSafe(t *testing.T) {
 	t.Parallel()
 
-	keys, _ := seal.DeriveKeys("test-signing-key-12345")
+	gen, _ := encurl.NewGenerator("test-signing-key-12345")
-	gen := encurl.NewGenerator(keys.EncryptedURLKey)
 
-	req := &imagerequest.Request{
+	payload := &encurl.Payload{
-		Source: imagerequest.Source{
+		SourceHost: testSourceHost,
-			Host: testSourceHost,
+		SourcePath: testSourcePath,
-			Path: testSourcePath,
+		ExpiresAt:  time.Now().Add(time.Hour).Unix(),
-		},
 	}
 
-	token, _ := gen.Generate(req, time.Now().Add(time.Hour))
+	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"
 )
 
@@ -91,18 +89,10 @@ func (s *Handlers) handleLoginPost(w http.ResponseWriter, r *http.Request) {
 	http.Redirect(w, r, "/", http.StatusSeeOther)
 }
 
-// HandleLogout logs out, which ends every login session (see
+// HandleLogout clears the session and redirects to login.
-// session.Manager.Logout), and redirects to login.
 func (s *Handlers) HandleLogout() http.HandlerFunc {
 	return func(w http.ResponseWriter, r *http.Request) {
-		err := s.sessMgr.Logout(w, r)
+		s.sessMgr.ClearSession(w)
-		if err != nil {
-			s.log.Error("failed to log out", "error", err)
-			http.Error(w, "Failed to log out", http.StatusInternalServerError)
-
-			return
-		}
-
 		http.Redirect(w, r, "/", http.StatusSeeOther)
 	}
 }
@@ -127,7 +117,7 @@ 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 +125,7 @@ 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 +133,8 @@ func (s *Handlers) HandleGenerateURL() http.HandlerFunc {
 			return
 		}
 
-		// The image URL must fetch the source URL as it was written. The
-		// fetcher fetches over http only when allow_http is set.
-		fetchURL := req.Source.URL(s.config.AllowHTTP)
-
-		if !fetchedAsWritten(parsed, fetchURL) {
-			s.renderGeneratorWithForm(w, r, "Source URL cannot be fetched as "+
-				"written: pixa would fetch "+fetchURL.String(),
-				r.Form, http.StatusBadRequest)
-
-			return
-		}
-
 		// Generate encrypted token
-		token, err := s.encGen.Generate(req, expiresAt)
+		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,
@@ -197,55 +165,14 @@ 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, fetchURL *url.URL) bool {
-	writtenPath := source.RawPath
-	if writtenPath == "" {
-		writtenPath = source.EscapedPath()
-	}
-
-	return source.User == nil && !source.ForceQuery &&
-		fetchURL.EscapedPath() == writtenPath &&
-		fetchURL.RawQuery == source.RawQuery
-}
-
-// buildGenerateRequest parses the numeric form fields and assembles the
-// image request the encrypted URL's token is made from, and its expiry.
-// ttl=0 means never expires (the expiry is 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
@@ -267,39 +194,42 @@ 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},
-			Format:  imagerequest.Format(form.Get("format")),
 		Quality:     quality,
 		FitMode:     fitMode,
-		},
+		ExpiresAt:   expiresAtUnix,
 	}
 
-	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 == "" {
@@ -311,7 +241,7 @@ 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_csrf_internal_test.go

@@ -14,7 +14,6 @@ import (
 
 	"sneak.berlin/go/pixa/internal/config"
 	"sneak.berlin/go/pixa/internal/encurl"
-	"sneak.berlin/go/pixa/internal/seal"
 	"sneak.berlin/go/pixa/internal/session"
 )
 
@@ -45,17 +44,27 @@ func newCSRFTestRouter(t *testing.T) (*Handlers, http.Handler) {
 
 	cfg := &config.Config{SigningKey: testSigningKey, Debug: true}
 
-	keys, err := seal.DeriveKeys(testSigningKey)
+	sessMgr, err := session.NewManager(testSigningKey)
 	if err != nil {
-		t.Fatalf("seal.DeriveKeys() error = %v", err)
+		t.Fatalf("session.NewManager() error = %v", err)
+	}
+
+	encGen, err := encurl.NewGenerator(testSigningKey)
+	if err != nil {
+		t.Fatalf("encurl.NewGenerator() error = %v", err)
+	}
+
+	protect, err := newCSRFProtect(testSigningKey, cfg.Debug)
+	if err != nil {
+		t.Fatalf("newCSRFProtect() error = %v", err)
 	}
 
 	h := &Handlers{
 		log:         slog.New(slog.DiscardHandler),
 		config:      cfg,
-		sessMgr:     session.NewManager(keys.SessionHashKey, keys.SessionBlockKey),
+		sessMgr:     sessMgr,
-		encGen:      encurl.NewGenerator(keys.EncryptedURLKey),
+		encGen:      encGen,
-		csrfProtect: newCSRFProtect(keys.CSRFKey, cfg.Debug),
+		csrfProtect: protect,
 	}
 
 	r := chi.NewRouter()

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_login_log_internal_test.go

@@ -10,7 +10,6 @@ import (
 	"testing"
 
 	"sneak.berlin/go/pixa/internal/config"
-	"sneak.berlin/go/pixa/internal/seal"
 	"sneak.berlin/go/pixa/internal/session"
 )
 
@@ -23,15 +22,15 @@ func TestLoginLogLeavesOutSubmittedKey(t *testing.T) {
 
 	var buf bytes.Buffer
 
-	keys, err := seal.DeriveKeys(testSigningKey)
+	sessMgr, err := session.NewManager(testSigningKey)
 	if err != nil {
-		t.Fatalf("seal.DeriveKeys() error = %v", err)
+		t.Fatalf("session.NewManager() error = %v", err)
 	}
 
 	h := &Handlers{
 		log:     slog.New(slog.NewJSONHandler(&buf, nil)),
 		config:  &config.Config{SigningKey: testSigningKey},
-		sessMgr: session.NewManager(keys.SessionHashKey, keys.SessionBlockKey),
+		sessMgr: sessMgr,
 	}
 
 	submittedKeys := []string{wrongKey, testSigningKey}

internal/handlers/auth_session_internal_test.go

@@ -10,8 +10,7 @@ import (
 	"testing"
 	"time"
 
-	"sneak.berlin/go/pixa/internal/imagerequest"
+	"sneak.berlin/go/pixa/internal/imgcache"
-	"sneak.berlin/go/pixa/internal/seal"
 	"sneak.berlin/go/pixa/internal/session"
 )
 
@@ -186,103 +185,6 @@ func TestHandleLogout_ClearsSessionCookie(t *testing.T) {
 	}
 }
 
-// TestHandleLogout_EndsCopiedSession verifies that after POST /logout a copy
-// of the session cookie taken before it shows the login page, not the
-// generator page.
-func TestHandleLogout_EndsCopiedSession(t *testing.T) {
-	t.Parallel()
-
-	h, srv := newCSRFTestRouter(t)
-
-	copied := newSessionCookie(t, h)
-
-	req := httptest.NewRequestWithContext(
-		t.Context(), http.MethodPost, "/logout", nil)
-	req.AddCookie(copied)
-
-	rec := httptest.NewRecorder()
-	h.HandleLogout().ServeHTTP(rec, req)
-
-	if rec.Code != http.StatusSeeOther {
-		t.Fatalf("POST /logout status = %d, want %d",
-			rec.Code, http.StatusSeeOther)
-	}
-
-	req = httptest.NewRequestWithContext(t.Context(), http.MethodGet, "/", nil)
-	req.AddCookie(copied)
-
-	rec = httptest.NewRecorder()
-	srv.ServeHTTP(rec, req)
-
-	body := rec.Body.String()
-	t.Logf("GET / with the copied cookie: status %d, login page %v",
-		rec.Code, strings.Contains(body, loginForm))
-
-	if !strings.Contains(body, loginForm) || strings.Contains(body, generatorForm) {
-		t.Error("a cookie copied before /logout still opens the generator page")
-	}
-}
-
-// TestHandleLogout_SaveFails_Answers500 verifies that when the logout cannot
-// be saved in the database, POST /logout answers 500, leaves the session
-// cookie in place and ends no session.
-func TestHandleLogout_SaveFails_Answers500(t *testing.T) {
-	t.Parallel()
-
-	h, srv := newCSRFTestRouter(t)
-
-	db := setupTestDB(t)
-
-	keys, err := seal.DeriveKeys(testSigningKey)
-	if err != nil {
-		t.Fatalf("seal.DeriveKeys() error = %v", err)
-	}
-
-	sessMgr, err := session.NewManagerWithDatabase(
-		t.Context(), keys.SessionHashKey, keys.SessionBlockKey, db)
-	if err != nil {
-		t.Fatalf("session.NewManagerWithDatabase() error = %v", err)
-	}
-
-	h.sessMgr = sessMgr
-	cookie := newSessionCookie(t, h)
-
-	// Saving the logout fails on a closed database.
-	err = db.Close()
-	if err != nil {
-		t.Fatalf("closing the database: %v", err)
-	}
-
-	req := httptest.NewRequestWithContext(
-		t.Context(), http.MethodPost, "/logout", nil)
-	req.AddCookie(cookie)
-
-	rec := httptest.NewRecorder()
-	h.HandleLogout().ServeHTTP(rec, req)
-
-	t.Logf("POST /logout: status %d, Set-Cookie %q",
-		rec.Code, rec.Header().Get("Set-Cookie"))
-
-	if rec.Code != http.StatusInternalServerError {
-		t.Errorf("POST /logout status = %d, want %d",
-			rec.Code, http.StatusInternalServerError)
-	}
-
-	if c := findSessionCookie(rec); c != nil {
-		t.Errorf("a logout that failed set the session cookie: %s", c)
-	}
-
-	req = httptest.NewRequestWithContext(t.Context(), http.MethodGet, "/", nil)
-	req.AddCookie(cookie)
-
-	rec = httptest.NewRecorder()
-	srv.ServeHTTP(rec, req)
-
-	if !strings.Contains(rec.Body.String(), generatorForm) {
-		t.Error("a logout that failed ended the session")
-	}
-}
-
 // TestGeneratePost_NoSession_RedirectsToLogin verifies that POST /generate
 // with a valid CSRF token but no login session answers 303 to / and makes no
 // URL.
@@ -320,7 +222,7 @@ 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 {
@@ -353,7 +255,7 @@ 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

@@ -1,39 +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, which
-// answers the errors of both image routes, answers 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)
-
-	rec := httptest.NewRecorder()
-	h.respondImageError(rec, &imagerequest.Request{}, err)
-	t.Logf("status = %d, body = %q", rec.Code, rec.Body.String())
-
-	if rec.Code != http.StatusBadRequest {
-		t.Errorf("status = %d, want %d", rec.Code, http.StatusBadRequest)
-	}
-
-	if !strings.Contains(rec.Body.String(), wantBody) {
-		t.Errorf("body = %q, want it to say %q", rec.Body.String(), wantBody)
-	}
-}

internal/handlers/bodylimit_internal_test.go

@@ -11,7 +11,6 @@ import (
 
 	"sneak.berlin/go/pixa/internal/config"
 	"sneak.berlin/go/pixa/internal/encurl"
-	"sneak.berlin/go/pixa/internal/seal"
 	"sneak.berlin/go/pixa/internal/session"
 )
 
@@ -33,17 +32,27 @@ func newBodyLimitTestRouter(
 
 	cfg := &config.Config{SigningKey: testSigningKey, Debug: true}
 
-	keys, err := seal.DeriveKeys(testSigningKey)
+	sessMgr, err := session.NewManager(testSigningKey)
 	if err != nil {
-		t.Fatalf("seal.DeriveKeys() error = %v", err)
+		t.Fatalf("session.NewManager() error = %v", err)
+	}
+
+	encGen, err := encurl.NewGenerator(testSigningKey)
+	if err != nil {
+		t.Fatalf("encurl.NewGenerator() error = %v", err)
+	}
+
+	protect, err := newCSRFProtect(testSigningKey, cfg.Debug)
+	if err != nil {
+		t.Fatalf("newCSRFProtect() error = %v", err)
 	}
 
 	h := &Handlers{
 		log:         slog.New(slog.DiscardHandler),
 		config:      cfg,
-		sessMgr:     session.NewManager(keys.SessionHashKey, keys.SessionBlockKey),
+		sessMgr:     sessMgr,
-		encGen:      encurl.NewGenerator(keys.EncryptedURLKey),
+		encGen:      encGen,
-		csrfProtect: newCSRFProtect(keys.CSRFKey, cfg.Debug),
+		csrfProtect: protect,
 	}
 
 	r := chi.NewRouter()

internal/handlers/cache_hit_internal_test.go

@@ -1,277 +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/allowlist"
-	"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"
-	"sneak.berlin/go/pixa/internal/seal"
-	"sneak.berlin/go/pixa/internal/signature"
-)
-
-// 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,
-		}),
-		MaxResponseSize: 50 << 20,
-		Logger:          slog.New(slog.DiscardHandler),
-	})
-	if err != nil {
-		tb.Fatalf("imgcache.NewService() error = %v", err)
-	}
-
-	keys, err := seal.DeriveKeys(testSigningKey)
-	if err != nil {
-		tb.Fatalf("seal.DeriveKeys() error = %v", err)
-	}
-
-	encGen := encurl.NewGenerator(keys.EncryptedURLKey)
-
-	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,
-		},
-	}, time.Time{})
-	if err != nil {
-		tb.Fatalf("encGen.Generate() error = %v", err)
-	}
-
-	h := &Handlers{
-		log:       slog.New(slog.DiscardHandler),
-		imgSvc:    svc,
-		encGen:    encGen,
-		signer:    signature.New(testSigningKey),
-		allowlist: allowlist.New([]string{countingHost}),
-	}
-
-	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/csrf.go

@@ -9,10 +9,15 @@ import (
 	"sneak.berlin/go/pixa/internal/seal"
 )
 
+// csrfKeySalt provides domain separation for the CSRF authentication key,
+// derived from the signing key so tokens survive restarts without extra
+// configuration and never reuse the session or encrypted-URL key material.
+const csrfKeySalt = "pixa-csrf-v1"
+
 // newCSRFProtect builds the CSRF-protection middleware for the
 // state-mutating HTML form routes. The token lives in its own cookie,
 // independent of the session cookie, so it also protects the login POST
-// where no session exists yet (login CSRF). key signs that cookie.
+// where no session exists yet (login CSRF).
 //
 // When plaintext is true (local HTTP development), requests are marked
 // plaintext so the library neither demands an https Referer nor sets a
@@ -20,8 +25,13 @@ import (
 // service runs behind a TLS-terminating proxy, so plaintext is false and
 // the library enforces its https Referer origin check.
 func newCSRFProtect(
-	key [seal.KeySize]byte, plaintext bool,
+	signingKey string, plaintext bool,
-) func(http.Handler) http.Handler {
+) (func(http.Handler) http.Handler, error) {
+	key, err := seal.DeriveKey([]byte(signingKey), csrfKeySalt)
+	if err != nil {
+		return nil, err
+	}
+
 	protect := csrf.Protect(
 		key[:],
 		csrf.Path("/"),
@@ -30,7 +40,7 @@ func newCSRFProtect(
 	)
 
 	if !plaintext {
-		return protect
+		return protect, nil
 	}
 
 	return func(next http.Handler) http.Handler {
@@ -39,7 +49,7 @@ func newCSRFProtect(
 		return http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
 			protected.ServeHTTP(w, csrf.PlaintextHTTPRequest(r))
 		})
-	}
+	}, nil
 }
 
 // CSRF returns the CSRF-protection middleware for the login and generator

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

@@ -1,202 +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/allowlist"
-	"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/seal"
-	"sneak.berlin/go/pixa/internal/signature"
-)
-
-// 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 which have
-// allowlistedHost on their 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,
-		}),
-		MaxResponseSize: 50 << 20,
-		Logger:          log,
-	})
-	if err != nil {
-		t.Fatalf("imgcache.NewService() error = %v", err)
-	}
-
-	keys, err := seal.DeriveKeys(testSigningKey)
-	if err != nil {
-		t.Fatalf("seal.DeriveKeys() error = %v", err)
-	}
-
-	encGen := encurl.NewGenerator(keys.EncryptedURLKey)
-
-	h := &Handlers{
-		log:       log,
-		imgSvc:    svc,
-		encGen:    encGen,
-		signer:    signature.New(testSigningKey),
-		allowlist: allowlist.New([]string{allowlistedHost}),
-	}
-
-	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,
-		},
-	}, time.Time{})
-	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.
@@ -18,17 +18,16 @@ var (
 		"image/jxl, image/avif, image/webp or image/jpeg")
 )
 
-// chooseAutoFormat returns the format to serve for the requested format: for
+// chooseAutoFormat replaces the format auto in req with the format
-// the format auto, the format formatForAccept chooses from r's Accept header,
+// formatForAccept chooses from r's Accept header, and adds Vary: Accept to the
-// and any other format as it is. For auto it adds Vary: Accept to the
 // response, which then depends on that header. It answers 400 for an Accept
 // header that is not valid and 406 for one that allows none of the formats,
-// and reports whether the image can be served.
+// 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, requested imagerequest.Format,
+	w http.ResponseWriter, r *http.Request, req *imgcache.ImageRequest,
-) (imagerequest.Format, bool) {
+) bool {
-	if requested != imagerequest.FormatAuto {
+	if req.Format != imgcache.FormatAuto {
-		return requested, true
+		return true
 	}
 
 	w.Header().Add("Vary", "Accept")
@@ -37,16 +36,18 @@ func (s *Handlers) chooseAutoFormat(
 	if errors.Is(err, errNotAcceptable) {
 		s.respondError(w, err.Error(), http.StatusNotAcceptable)
 
-		return "", false
+		return false
 	}
 
 	if err != nil {
 		s.respondError(w, err.Error(), http.StatusBadRequest)
 
-		return "", false
+		return false
 	}
 
-	return format, true
+	req.Format = format
+
+	return true
 }
 
 // formatForAccept returns the format an auto URL is served in for the Accept
@@ -55,26 +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
@@ -88,7 +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 +76,28 @@ 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 the
+// the format auto, made with h's image service and generator.
-// handlers that newSignedHostServer builds check signatures with. 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,
+	})
-		},
-	}, time.Now().Add(time.Minute))
 	if err != nil {
 		t.Fatalf("Generate() error = %v", err)
 	}
@@ -186,18 +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"
@@ -11,13 +12,13 @@ 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/seal"
 	"sneak.berlin/go/pixa/internal/session"
-	"sneak.berlin/go/pixa/internal/signature"
 )
 
 // Params defines dependencies for Handlers.
@@ -26,48 +27,70 @@ type Params struct {
 
 	Logger      *logger.Logger
 	Healthcheck *healthcheck.Healthcheck
+	Database    *database.Database
 	Config      *config.Config
-	Keys        seal.Keys
 
-	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
 
-	// signer checks the signature of a /v1/image/ URL with signing_key.
-	signer *signature.Signer
-	// allowlist matches the hosts of allowlist_hosts, which a /v1/image/
-	// URL may name without a signature.
-	allowlist *allowlist.HostAllowList
 	// refererBlocklist matches the hosts of referer_blocklist; its IsAllowed
 	// reports whether a URL's host is on that list.
 	refererBlocklist *allowlist.HostAllowList
 }
 
 // New creates a new Handlers instance.
-func New(_ fx.Lifecycle, params Params) *Handlers {
+func New(lc fx.Lifecycle, params Params) (*Handlers, error) {
-	return &Handlers{
+	csrfProtect, err := newCSRFProtect(params.Config.SigningKey, params.Config.Debug)
+	if err != nil {
+		return nil, err
+	}
+
+	s := &Handlers{
 		log:              params.Logger.Get(),
 		hc:               params.Healthcheck,
+		db:               params.Database,
 		config:           params.Config,
-		imgSvc:           params.ImageService,
+		fetcher:          params.Fetcher,
-		sessMgr:          params.SessionManager,
+		csrfProtect:      csrfProtect,
-		encGen:           params.EncryptedURLGenerator,
-		csrfProtect:      newCSRFProtect(params.Keys.CSRFKey, params.Config.Debug),
-		signer:           signature.New(params.Config.SigningKey),
-		allowlist:        allowlist.New(params.Config.AllowlistHosts),
 		refererBlocklist: allowlist.New(params.Config.RefererBlocklist),
 	}
+
+	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
@@ -76,6 +99,91 @@ 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.
+	sessMgr, err := session.NewManager(s.config.SigningKey)
+	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

@@ -18,19 +18,15 @@ 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/database"
 	"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"
 )
 
 // testFixtures contains test data.
 type testFixtures struct {
 	handler  *Handlers
+	service  *imgcache.Service
 	goodHost string
 }
 
@@ -52,8 +48,7 @@ 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)
 	}
@@ -61,11 +56,8 @@ func setupTestHandler(t *testing.T) *testFixtures {
 	svc, err := imgcache.NewService(&imgcache.ServiceConfig{
 		Cache:      cache,
 		Fetcher:    newMockFetcher(mockFS),
-		Processor: imageprocessor.New(imageprocessor.Params{
+		SigningKey: "test-signing-key-must-be-32-chars",
-			MaxInputBytes:           50 << 20,
+		Allowlist:  []string{goodHost},
-			MaxConcurrentProcessing: 2,
-		}),
-		MaxResponseSize: 50 << 20,
 	})
 	if err != nil {
 		t.Fatalf("failed to create service: %v", err)
@@ -74,12 +66,11 @@ func setupTestHandler(t *testing.T) *testFixtures {
 	h := &Handlers{
 		imgSvc: svc,
 		log:    slog.Default(),
-		signer:    signature.New("test-signing-key-must-be-32-chars"),
-		allowlist: allowlist.New([]string{goodHost}),
 	}
 
 	return &testFixtures{
 		handler:  h,
+		service:  svc,
 		goodHost: goodHost,
 	}
 }
@@ -130,9 +121,10 @@ func newMockFetcher(fs fs.FS) *mockFetcher {
 }
 
 func (f *mockFetcher) Fetch(
-	_ context.Context, source imagerequest.Source,
+	_ context.Context, url string,
 ) (*httpfetcher.FetchResult, error) {
-	path := source.Host + source.Path
+	// Remove https:// prefix
+	path := url[8:] // Remove "https://"
 
 	data, err := fs.ReadFile(f.fs, path)
 	if err != nil {

internal/handlers/image.go

@@ -7,16 +7,14 @@ import (
 	"net/http"
 	"net/url"
 	"strconv"
-	"strings"
 	"time"
 
+	"github.com/go-chi/chi/v5"
 	"github.com/go-chi/chi/v5/middleware"
 	"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:
@@ -28,17 +26,17 @@ func (s *Handlers) HandleImage() http.HandlerFunc {
 			return
 		}
 
-		req, sig, expires, ok := s.parseImageRequest(w, r)
+		req, ok := s.parseImageRequest(w, r)
 		if !ok {
 			return
 		}
 
 		// Validate signature if required
-		err := s.validateSignature(req, sig, expires)
+		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)
@@ -46,7 +44,27 @@ func (s *Handlers) HandleImage() http.HandlerFunc {
 			return
 		}
 
-		s.serveImage(w, r, req, expires)
+		// The signature covers the format auto, not the format chosen
+		if !s.chooseAutoFormat(w, r, req) {
+			return
+		}
+
+		// Get cache key for logging
+		cacheKey := imgcache.CacheKey(req)
+
+		// Get the image (from cache or fetch/process)
+		startTime := time.Now()
+
+		resp, err := s.imgSvc.Get(r.Context(), req)
+		if err != nil {
+			s.respondImageError(w, req, err)
+
+			return
+		}
+
+		defer func() { _ = resp.Content.Close() }()
+
+		s.writeImageResponse(w, r, req, resp, cacheKey, startTime)
 	}
 }
 
@@ -62,28 +80,30 @@ func (s *Handlers) HandleRobotsTxt() http.HandlerFunc {
 	}
 }
 
-// parseImageRequest parses the image URL's path and query parameters into
+// parseImageRequest parses the wildcard path and query parameters into
-// an image request, and returns it with the URL's signature and expiry. On
+// an ImageRequest. On invalid input it writes an error response and
-// invalid input it writes an error response and returns false.
+// returns false.
 func (s *Handlers) parseImageRequest(
 	w http.ResponseWriter, r *http.Request,
-) (*imagerequest.Request, string, time.Time, bool) {
+) (*imgcache.ImageRequest, bool) {
-	// The path is parsed decoded once, as r.URL.Path holds it, and not from
+	// Get the wildcard path from chi
-	// chi's wildcard: chi routes on the path as the client wrote it whenever
+	pathParam := chi.URLParam(r, "*")
-	// 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
+	// Parse the URL path
-	// as %2F
+	parsed, err := imgcache.ParseImagePath(pathParam)
-	req, err := imagerequest.ParseImageURL(r.URL.Path)
 	if err != nil {
 		s.log.Warn("failed to parse image URL",
-			"path", r.URL.Path,
+			"path", pathParam,
 			"error", err,
 		)
 		s.respondError(w, "invalid image URL: "+err.Error(), http.StatusBadRequest)
 
-		return nil, "", time.Time{}, false
+		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
@@ -94,7 +114,7 @@ func (s *Handlers) parseImageRequest(
 		s.respondError(w, fmt.Sprintf("invalid query string %q: %v",
 			r.URL.RawQuery, err), http.StatusBadRequest)
 
-		return nil, "", time.Time{}, false
+		return nil, false
 	}
 
 	for name, values := range query {
@@ -102,15 +122,17 @@ func (s *Handlers) parseImageRequest(
 			s.respondError(w, fmt.Sprintf("invalid %s: given more than once",
 				name), http.StatusBadRequest)
 
-			return nil, "", time.Time{}, false
+			return nil, false
 		}
 	}
 
-	expires, err := parseExpires(query)
+	req.Signature = query.Get("sig")
+
+	req.Expires, err = parseExpires(query)
 	if err != nil {
 		s.respondError(w, err.Error(), http.StatusBadRequest)
 
-		return nil, "", time.Time{}, false
+		return nil, false
 	}
 
 	// Parse optional quality and fit params. Only a q missing from the URL is
@@ -122,76 +144,51 @@ func (s *Handlers) parseImageRequest(
 		s.respondError(w, `invalid q: not a number, got ""`,
 			http.StatusBadRequest)
 
-		return nil, "", time.Time{}, false
+		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),
 			http.StatusBadRequest)
 
-		return nil, "", time.Time{}, false
+		return nil, false
 	}
 
 	// 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, "", time.Time{}, false
+		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)
 
-		return nil, "", time.Time{}, false
+		return nil, false
 	}
 
-	return req, query.Get("sig"), expires, true
+	return req, true
-}
-
-// validateSignature returns nil when the source host of req is on
-// allowlist_hosts and names no port. Otherwise it verifies sig, the URL's
-// signature of req, and expires, the URL's expiry.
-func (s *Handlers) validateSignature(
-	req *imagerequest.Request, sig string, expires time.Time,
-) error {
-	// An allowlist entry names no port, so a host followed by ":", with or
-	// without a port, needs a signature. Go's URL type reads the port as the
-	// fetcher does: in an IPv6 address written without brackets, such as
-	// 2001:db8::1:8443, it is what follows the last ":". This is checked here
-	// and not in allowlist.IsAllowed, which also matches referer_blocklist,
-	// where a Referer must be blocked whatever its port. Port and IsAllowed
-	// read only the host of a URL.
-	sourceURL := &url.URL{Host: req.Source.Host}
-	hostHasPort := sourceURL.Port() != "" ||
-		strings.HasSuffix(sourceURL.Host, ":")
-
-	if !hostHasPort && s.allowlist.IsAllowed(sourceURL) {
-		return nil
-	}
-
-	// Signature required for non-allowed hosts
-	return s.signer.Verify(req, sig, expires)
 }
 
 // parseExpires reads the exp query parameter, a Unix time in seconds. An exp
-// missing from the URL gives the zero time, which the signature check refuses
+// missing from the URL gives the zero time, which the signature check takes
-// as a missing exp. An exp in the URL that is not a whole number, an empty
+// as no expiration. An exp in the URL that is not a whole number, an empty
 // one included, is an error naming exp and the value.
 func parseExpires(query url.Values) (time.Time, error) {
 	if !query.Has("exp") {
@@ -219,73 +216,54 @@ func (s *Handlers) HandleTooManyRequests() http.HandlerFunc {
 	}
 }
 
-// respondImageError answers err, the image service's error for req, on both
+// respondImageError maps image retrieval errors to HTTP responses.
-// image routes. It logs a 500 at error level, as pixa's own failure. It logs
-// the other answers at warn level, since the client, the upstream or a full
-// limit caused them. The 415 for a source refused for its first bytes is not
-// logged here, because the image service logs it.
 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
+	s.log.Error("failed to get image",
-	// Content-Type names is the upstream's error, not pixa's: the image
+		"host", req.SourceHost,
-	// service has logged it as a refused source.
+		"path", req.SourcePath,
-	if errors.Is(err, magic.ErrMagicByteMismatch) ||
+		"error", err,
-		errors.Is(err, magic.ErrUnknownFormat) ||
+	)
-		errors.Is(err, magic.ErrNotEnoughData) {
+
+	// Check for specific error types
+	if errors.Is(err, httpfetcher.ErrSSRFBlocked) {
+		s.respondError(w, "forbidden", http.StatusForbidden)
+
+		return
+	}
+
+	if errors.Is(err, httpfetcher.ErrUpstreamError) {
+		s.respondError(w, "upstream error", http.StatusBadGateway)
+
+		return
+	}
+
+	if errors.Is(err, httpfetcher.ErrTooManyConnections) ||
+		errors.Is(err, imageprocessor.ErrTooManyImages) {
+		s.respondError(w, "server busy, try again later",
+			http.StatusServiceUnavailable)
+
+		return
+	}
+
+	if errors.Is(err, httpfetcher.ErrInvalidContentType) ||
+		errors.Is(err, imageprocessor.ErrUnsupportedInputFormat) {
 		s.respondError(w, "unsupported source format",
 			http.StatusUnsupportedMediaType)
 
 		return
 	}
 
-	var (
+	if errors.Is(err, imageprocessor.ErrOutputTooLarge) {
-		status  int
+		s.respondError(w, fmt.Sprintf("size too large for the source: the side "+
-		message string
-	)
-
-	switch {
-	case errors.Is(err, httpfetcher.ErrSSRFBlocked):
-		status, message = http.StatusForbidden, "forbidden"
-	case errors.Is(err, httpfetcher.ErrUpstreamError):
-		status, message = http.StatusBadGateway, "upstream error"
-	case errors.Is(err, httpfetcher.ErrUpstreamTimeout):
-		status, message = http.StatusGatewayTimeout, "upstream timeout"
-	case errors.Is(err, httpfetcher.ErrTooManyConnections),
-		errors.Is(err, imageprocessor.ErrTooManyImages),
-		errors.Is(err, imgcache.ErrProcessingTimedOut):
-		status = http.StatusServiceUnavailable
-		message = "server busy, try again later"
-	case errors.Is(err, httpfetcher.ErrInvalidContentType),
-		errors.Is(err, imageprocessor.ErrUnsupportedInputFormat):
-		status = http.StatusUnsupportedMediaType
-		message = "unsupported source format"
-	case errors.Is(err, imageprocessor.ErrOutputTooLarge):
-		status = http.StatusBadRequest
-		message = fmt.Sprintf("size too large for the source: the side "+
 			"computed from its proportions is above %d",
-			imageprocessor.MaxOutputDimension)
+			imageprocessor.MaxOutputDimension), http.StatusBadRequest)
-	case errors.Is(err, imageprocessor.ErrAVIFOutputTooLarge):
-		status = http.StatusBadRequest
-		message = fmt.Sprintf("size too large for AVIF: the output "+
-			"would be above %d pixels", imageprocessor.MaxAVIFOutputPixels)
-	default:
-		s.log.Error("failed to get image",
-			"host", req.Source.Host,
-			"path", req.Source.Path,
-			"error", err,
-		)
-		s.respondError(w, "internal error", http.StatusInternalServerError)
 
 		return
 	}
 
-	s.log.Warn("failed to get image",
+	s.respondError(w, "internal error", http.StatusInternalServerError)
-		"host", req.Source.Host,
-		"path", req.Source.Path,
-		"error", err,
-	)
-	s.respondError(w, message, status)
 }
 
 // cacheControl returns the Cache-Control header for an image served through a
@@ -342,34 +320,13 @@ func notModified(w http.ResponseWriter, r *http.Request, etag string) bool {
 	return true
 }
 
-// serveImage serves the image that req asks for. Both image routes call it
+// writeImageResponse writes headers and streams the image content,
-// once they have the request and its URL's expiry, which ends the
+// handling conditional and HEAD requests.
-// Cache-Control max-age. It chooses the format for the format auto, answers
+func (s *Handlers) writeImageResponse(
-// If-None-Match with 304 and HEAD with the headers only, and answers an error
-// of the image service with respondImageError.
-func (s *Handlers) serveImage(
 	w http.ResponseWriter, r *http.Request,
-	req *imagerequest.Request, expires time.Time,
+	req *imgcache.ImageRequest, resp *imgcache.ImageResponse,
+	cacheKey imgcache.VariantKey, startTime time.Time,
 ) {
-	// The signature or the token covers the format auto, not the format chosen
-	format, ok := s.chooseAutoFormat(w, r, req.Transform.Format)
-	if !ok {
-		return
-	}
-
-	req.Transform.Format = format
-
-	startTime := time.Now()
-
-	resp, err := s.imgSvc.Get(r.Context(), req)
-	if err != nil {
-		s.respondImageError(w, req, err)
-
-		return
-	}
-
-	defer func() { _ = resp.Content.Close() }()
-
 	// Set response headers
 	w.Header().Set("Content-Type", resp.ContentType)
 
@@ -378,7 +335,7 @@ func (s *Handlers) serveImage(
 	}
 
 	// Cache control headers
-	w.Header().Set("Cache-Control", cacheControl(expires))
+	w.Header().Set("Cache-Control", cacheControl(req.Expires))
 	w.Header().Set("X-Pixa-Cache", string(resp.CacheStatus))
 
 	if notModified(w, r, resp.ETag) {
@@ -395,31 +352,21 @@ func (s *Handlers) serveImage(
 	// Stream the response
 	w.WriteHeader(http.StatusOK)
 
-	// A failed write is most often a client that has gone away, not pixa's
-	// failure, so it is logged at warn level
 	servedBytes, err := io.Copy(w, resp.Content)
 	if err != nil {
-		s.log.Warn("failed to write response",
+		s.log.Error("failed to write response",
-			"request_id", middleware.GetReqID(r.Context()),
-			"host", req.Source.Host,
-			"path", req.Source.Path,
-			"served_bytes", servedBytes,
 			"error", err,
 		)
-
-		return
 	}
 
 	// Log cache status and timing after serving
 	duration := time.Since(startTime)
 	s.log.Info("image served",
 		"request_id", middleware.GetReqID(r.Context()),
-		"cache_key", imagerequest.CacheKey(req),
+		"cache_key", cacheKey,
-		"host", req.Source.Host,
-		"path", req.Source.Path,
 		"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

@@ -12,15 +12,9 @@ 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/imageprocessor"
-	"sneak.berlin/go/pixa/internal/imagerequest"
 	"sneak.berlin/go/pixa/internal/imgcache"
-	"sneak.berlin/go/pixa/internal/seal"
-	"sneak.berlin/go/pixa/internal/signature"
 )
 
 // photoPath is the path of the JPEG that newSignedHostServer serves.
@@ -38,8 +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)
 	}
@@ -51,30 +44,22 @@ func newSignedHostServer(
 		Fetcher: newMockFetcher(fstest.MapFS{
 			signedHost + photoPath: &fstest.MapFile{Data: jpegData},
 		}),
-		Processor: imageprocessor.New(imageprocessor.Params{
+		SigningKey: testSigningKey,
-			MaxInputBytes:           50 << 20,
-			MaxConcurrentProcessing: 2,
-		}),
-		MaxResponseSize: 50 << 20,
 		Logger:     log,
 	})
 	if err != nil {
 		t.Fatalf("imgcache.NewService() error = %v", err)
 	}
 
-	keys, err := seal.DeriveKeys(testSigningKey)
+	encGen, err := encurl.NewGenerator(testSigningKey)
 	if err != nil {
-		t.Fatalf("seal.DeriveKeys() error = %v", err)
+		t.Fatalf("encurl.NewGenerator() error = %v", err)
 	}
 
-	encGen := encurl.NewGenerator(keys.EncryptedURLKey)
-
 	h := &Handlers{
 		log:    log,
 		imgSvc: svc,
 		encGen: encGen,
-		signer:    signature.New(testSigningKey),
-		allowlist: allowlist.New(nil),
 	}
 
 	r := chi.NewRouter()
@@ -120,18 +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 {
@@ -184,13 +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 {
@@ -199,16 +183,14 @@ 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,
+			})
-				},
-			}, tt.expires)
 			if err != nil {
 				t.Fatalf("Generate() error = %v", err)
 			}

internal/handlers/image_errors_internal_test.go

@@ -1,28 +1,19 @@
 package handlers
 
 import (
-	"bytes"
-	"context"
 	"encoding/json"
 	"fmt"
 	"image/color"
-	"io"
 	"log/slog"
 	"net/http"
 	"net/http/httptest"
-	"slices"
 	"strings"
 	"testing"
 	"testing/fstest"
 	"time"
 
 	"github.com/go-chi/chi/v5"
-	"github.com/go-chi/chi/v5/middleware"
-	"github.com/prometheus/client_golang/prometheus"
-	"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/imgcache"
 	"sneak.berlin/go/pixa/internal/signature"
 )
@@ -32,15 +23,14 @@ import (
 const allowlistedHost = "allowed.example.com"
 
 // newImageRoute returns the image route of a Handlers whose service fetches
-// with fetcher, and which checks signatures with testSigningKey.
+// with fetcher and checks signatures with testSigningKey.
 func newImageRoute(t *testing.T, fetcher httpfetcher.Fetcher) 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("failed to create cache: %v", err)
 	}
@@ -48,22 +38,14 @@ func newImageRoute(t *testing.T, fetcher httpfetcher.Fetcher) http.Handler {
 	svc, err := imgcache.NewService(&imgcache.ServiceConfig{
 		Cache:      cache,
 		Fetcher:    fetcher,
-		Processor: imageprocessor.New(imageprocessor.Params{
+		SigningKey: testSigningKey,
-			MaxInputBytes:           50 << 20,
+		Allowlist:  []string{allowlistedHost},
-			MaxConcurrentProcessing: 2,
-		}),
-		MaxResponseSize: 50 << 20,
 	})
 	if err != nil {
 		t.Fatalf("failed to create service: %v", err)
 	}
 
-	h := &Handlers{
+	h := &Handlers{imgSvc: svc, log: slog.New(slog.DiscardHandler)}
-		imgSvc:    svc,
-		log:       slog.New(slog.DiscardHandler),
-		signer:    signature.New(testSigningKey),
-		allowlist: allowlist.New([]string{allowlistedHost}),
-	}
 
 	r := chi.NewRouter()
 	r.Get("/v1/image/*", h.HandleImage())
@@ -72,7 +54,7 @@ func newImageRoute(t *testing.T, fetcher httpfetcher.Fetcher) http.Handler {
 }
 
 // newPhotoFetcher returns a mock fetcher that serves a JPEG at photoPath on
-// each of hosts, and answers any other source with an upstream error.
+// each of hosts, and answers any other URL with an upstream error.
 func newPhotoFetcher(t *testing.T, hosts ...string) *httpfetcher.MockFetcher {
 	t.Helper()
 
@@ -99,27 +81,19 @@ func photoURLWithSig(host, sig string, expires time.Time) string {
 	return fmt.Sprintf("%s?sig=%s&exp=%d", photoURL(host), sig, expires.Unix())
 }
 
-// photoRequest returns the image request of photoURL(host) at the default
-// quality and fit.
-func photoRequest(host string) *imagerequest.Request {
-	return &imagerequest.Request{
-		Source: imagerequest.Source{
-			Host: host,
-			Path: photoPath,
-		},
-		Transform: imagerequest.Transform{
-			Size:    imagerequest.Size{Width: 50, Height: 50},
-			Format:  imagerequest.FormatJPEG,
-			Quality: 85,
-			FitMode: imagerequest.FitCover,
-		},
-	}
-}
-
 // 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(photoRequest(host), expires)
+	return signature.New(key).Sign(&signature.Request{
+		SourceHost: host,
+		SourcePath: photoPath,
+		Width:      50,
+		Height:     50,
+		Format:     string(imgcache.FormatJPEG),
+		Quality:    85,
+		FitMode:    string(imgcache.FitCover),
+		Expires:    expires,
+	})
 }
 
 // sendGet sends a GET for target to route and returns the response.
@@ -190,12 +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)
@@ -295,292 +264,3 @@ func TestHandleImage_AllowlistOrSignature(t *testing.T) {
 		})
 	}
 }
-
-// TestHandleImage_InvalidHost_Returns400 sends image URLs whose host no URL
-// host can be, and checks that each is refused with 400 naming the host as
-// decoded: allowlistedHost with a character after it that a URL host cannot
-// hold, percent-encoded, an IPv6 address without brackets, and brackets
-// around something that is not an IPv6 address. Later steps put the host
-// unparsed into the allowlist check, the cache key and the upstream URL, so
-// such a host is refused first.
-func TestHandleImage_InvalidHost_Returns400(t *testing.T) {
-	t.Parallel()
-
-	photos := newPhotoFetcher(t, allowlistedHost)
-
-	tests := []struct {
-		name        string
-		writtenHost string
-		decodedHost string
-	}{
-		{"? written as %3F", allowlistedHost + "%3Fx=1", allowlistedHost + "?x=1"},
-		{"# written as %23", allowlistedHost + "%23x", allowlistedHost + "#x"},
-		{"% written as %25", allowlistedHost + "%253F", allowlistedHost + "%3F"},
-		{`\ written as %5C`, allowlistedHost + "%5Cx", allowlistedHost + `\x`},
-		{"space written as %20", allowlistedHost + "%20", allowlistedHost + " "},
-		{"IPv6 address without brackets", "2001:db8::1", "2001:db8::1"},
-		{"IPv4 address in brackets", "[203.0.113.5]", "[203.0.113.5]"},
-		{"no address in brackets", "[abc]", "[abc]"},
-	}
-
-	for _, tt := range tests {
-		t.Run(tt.name, func(t *testing.T) {
-			t.Parallel()
-
-			rec := sendGet(t, newImageRoute(t, photos), photoURL(tt.writtenHost))
-			checkErrorBody(t, rec, http.StatusBadRequest,
-				fmt.Sprintf("invalid image URL: invalid source host: %q",
-					tt.decodedHost))
-		})
-	}
-}
-
-// TestHandleImage_HostForms_Served checks that the image route serves, with
-// a valid signature, the image at photoPath on a host name, an IPv4 address,
-// an IPv6 address in brackets, and a host followed by ":" with or without a
-// port.
-func TestHandleImage_HostForms_Served(t *testing.T) {
-	t.Parallel()
-
-	hosts := []string{
-		allowlistedHost,
-		"img_1.example.com",
-		"203.0.113.5",
-		"[2001:db8::1]",
-		allowlistedHost + ":8443",
-		"[2001:db8::1]:8443",
-		allowlistedHost + ":",
-	}
-
-	photos := newPhotoFetcher(t, hosts...)
-	exp := time.Now().Add(time.Hour)
-
-	for _, host := range hosts {
-		t.Run(host, func(t *testing.T) {
-			t.Parallel()
-
-			sig := photoSignature(testSigningKey, host, exp)
-
-			rec := sendGet(t, newImageRoute(t, photos),
-				photoURLWithSig(host, sig, exp))
-			if rec.Code != http.StatusOK {
-				t.Errorf("status = %d, want %d: %s",
-					rec.Code, http.StatusOK, rec.Body)
-			}
-		})
-	}
-}
-
-// TestHandleImage_HashInSourcePathOrQuery_Returns400 sends image URLs whose
-// source path or source query holds a "#", written as %23, and checks that
-// each is refused with 400, the one signed for that source path included.
-// A "#" starts a URL's fragment, so neither the source path nor the source
-// query may hold one.
-func TestHandleImage_HashInSourcePathOrQuery_Returns400(t *testing.T) {
-	t.Parallel()
-
-	photos := newPhotoFetcher(t, allowlistedHost, signedHost)
-	exp := time.Now().Add(time.Hour)
-
-	sig := signature.New(testSigningKey).Sign(&imagerequest.Request{
-		Source: imagerequest.Source{
-			Host: signedHost,
-			Path: photoPath + "#x",
-		},
-		Transform: imagerequest.Transform{
-			Size:    imagerequest.Size{Width: 50, Height: 50},
-			Format:  imagerequest.FormatJPEG,
-			Quality: 85,
-			FitMode: imagerequest.FitCover,
-		},
-	}, exp)
-
-	tests := []struct {
-		name   string
-		target string
-	}{
-		{"# in the source path",
-			"/v1/image/" + allowlistedHost + photoPath + "%23x/50x50.jpeg"},
-		{"# in the source query",
-			"/v1/image/" + allowlistedHost + photoPath + "%3Fv=1%23x/50x50.jpeg"},
-		{"# in the source path, signed",
-			fmt.Sprintf("/v1/image/%s%s%%23x/50x50.jpeg?sig=%s&exp=%d",
-				signedHost, photoPath, sig, exp.Unix())},
-	}
-
-	for _, tt := range tests {
-		t.Run(tt.name, func(t *testing.T) {
-			t.Parallel()
-
-			rec := sendGet(t, newImageRoute(t, photos), tt.target)
-			checkErrorBody(t, rec, http.StatusBadRequest,
-				`invalid image URL: invalid image path: `+
-					`the source path or query holds a "#"`)
-		})
-	}
-}
-
-// failingFetcher answers every fetch with its error.
-type failingFetcher struct {
-	err error
-}
-
-// Fetch returns f's error.
-func (f failingFetcher) Fetch(
-	context.Context, imagerequest.Source,
-) (*httpfetcher.FetchResult, error) {
-	return nil, f.err
-}
-
-// photoURLsByRoute returns, for each image route, the function that makes the
-// URL of the JPEG at photoPath on signedHost on that route.
-func photoURLsByRoute() map[string]func(*testing.T, *Handlers) string {
-	return map[string]func(*testing.T, *Handlers) string{
-		"/v1/image/": signedPhotoURL,
-		"/v1/e/":     encPhotoURL,
-	}
-}
-
-// TestImageRoutes_SameErrorAnswers checks that both image routes answer each
-// upstream fetch error below with the same status. They log it as "failed to
-// get image" at the same level: error for the 500 and warn for the others.
-// Each request gets routes of its own, so no request finds another's failed
-// fetch in the negative cache.
-func TestImageRoutes_SameErrorAnswers(t *testing.T) {
-	t.Parallel()
-
-	tests := []struct {
-		name       string
-		err        error
-		wantStatus int
-		wantLevel  slog.Level
-	}{
-		{"blocked upstream address", httpfetcher.ErrSSRFBlocked,
-			http.StatusForbidden, slog.LevelWarn},
-		{"upstream error status",
-			fmt.Errorf("%w: status 404", httpfetcher.ErrUpstreamError),
-			http.StatusBadGateway, slog.LevelWarn},
-		{"no response headers within the fetch timeout",
-			httpfetcher.ErrUpstreamTimeout, http.StatusGatewayTimeout,
-			slog.LevelWarn},
-		{"no free upstream connection", httpfetcher.ErrTooManyConnections,
-			http.StatusServiceUnavailable, slog.LevelWarn},
-		{"Content-Type not a source format",
-			fmt.Errorf("%w: image/svg+xml", httpfetcher.ErrInvalidContentType),
-			http.StatusUnsupportedMediaType, slog.LevelWarn},
-		{"any other failure", io.ErrUnexpectedEOF,
-			http.StatusInternalServerError, slog.LevelError},
-	}
-
-	for _, tt := range tests {
-		for route, imageURL := range photoURLsByRoute() {
-			t.Run(route+" "+tt.name, func(t *testing.T) {
-				t.Parallel()
-
-				var logs bytes.Buffer
-
-				h, routes := newRoutesFetchingThrough(t,
-					failingFetcher{err: tt.err},
-					slog.New(slog.NewJSONHandler(&logs, nil)))
-
-				rec := sendGet(t, routes, imageURL(t, h))
-				if rec.Code != tt.wantStatus {
-					t.Errorf("status = %d, want %d: %s",
-						rec.Code, tt.wantStatus, rec.Body)
-				}
-
-				levels := loggedLevels(t, &logs)
-				if !slices.Contains(levels[tt.wantLevel.String()],
-					"failed to get image") {
-					t.Errorf(`no "failed to get image" line logged at level %s`,
-						tt.wantLevel)
-				}
-
-				if tt.wantLevel != slog.LevelError &&
-					len(levels[slog.LevelError.String()]) != 0 {
-					t.Errorf("logged at error level: %q",
-						levels[slog.LevelError.String()])
-				}
-			})
-		}
-	}
-}
-
-// failingResponseWriter is a response writer whose Write always fails, as when
-// the client has gone away.
-type failingResponseWriter struct {
-	*httptest.ResponseRecorder
-}
-
-// Write writes nothing and returns io.ErrClosedPipe.
-func (failingResponseWriter) Write([]byte) (int, error) {
-	return 0, io.ErrClosedPipe
-}
-
-// TestImageRoutes_FailedWriteLoggedOnce checks that both image routes log a
-// failed write of the image once, at warn level, with the request's ID, the
-// source host and path, the bytes served and the error. Neither may also log
-// the image as served.
-func TestImageRoutes_FailedWriteLoggedOnce(t *testing.T) {
-	t.Parallel()
-
-	const requestID = "test-request-id"
-
-	for route, imageURL := range photoURLsByRoute() {
-		t.Run(route, func(t *testing.T) {
-			t.Parallel()
-
-			var logs bytes.Buffer
-
-			h, srv := newSignedHostServer(t,
-				slog.New(slog.NewJSONHandler(&logs, nil)))
-
-			ctx := context.WithValue(t.Context(),
-				middleware.RequestIDKey, requestID)
-			srv.ServeHTTP(failingResponseWriter{httptest.NewRecorder()},
-				httptest.NewRequestWithContext(
-					ctx, http.MethodGet, imageURL(t, h), nil))
-
-			t.Logf("logged:\n%s", logs.String())
-
-			var failedWrites []map[string]any
-
-			dec := json.NewDecoder(&logs)
-			for dec.More() {
-				var line map[string]any
-
-				err := dec.Decode(&line)
-				if err != nil {
-					t.Fatalf("decoding log line: %v", err)
-				}
-
-				switch line["msg"] {
-				case "image served":
-					t.Error(`"image served" logged after a failed write`)
-				case "failed to write response":
-					failedWrites = append(failedWrites, line)
-				}
-			}
-
-			if len(failedWrites) != 1 {
-				t.Fatalf(`"failed to write response" logged %d times, want 1`,
-					len(failedWrites))
-			}
-
-			want := map[string]any{
-				"level":        slog.LevelWarn.String(),
-				"request_id":   requestID,
-				"host":         signedHost,
-				"path":         photoPath,
-				"served_bytes": float64(0),
-				"error":        io.ErrClosedPipe.Error(),
-			}
-
-			for key, wantValue := range want {
-				if got := failedWrites[0][key]; got != wantValue {
-					t.Errorf("%s = %v, want %v", key, got, wantValue)
-				}
-			}
-		})
-	}
-}

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"
 )
 
@@ -37,47 +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. It signs a copy of req, so req itself is not changed.
-// An unset quality or fit in the copy is 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 {
-	signed := *req
-
-	if signed.Transform.Quality == 0 {
-		signed.Transform.Quality = 85
-	}
-
-	if signed.Transform.FitMode == "" {
-		signed.Transform.FitMode = imagerequest.FitCover
-	}
-
-	expires := time.Now().Add(ttl)
-	sig := signature.New(key).Sign(&signed, expires)
-
-	// 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 := signed.Source.Path
-	if signed.Source.Query != "" {
-		sourcePathAndQuery += "?" + signed.Source.Query
-	}
-
-	unescapedPath := fmt.Sprintf("/v1/image/%s%s/%dx%d.%s",
-		signed.Source.Host, sourcePathAndQuery,
-		signed.Transform.Size.Width, signed.Transform.Size.Height,
-		signed.Transform.Format)
-
-	return fmt.Sprintf("%s?sig=%s&exp=%d&q=%d&fit=%s",
-		(&url.URL{Path: unescapedPath}).EscapedPath(), sig, expires.Unix(),
-		signed.Transform.Quality, signed.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.
@@ -86,18 +44,16 @@ 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},
-			Format:  imagerequest.FormatJPEG,
 		Quality:    85,
-			FitMode: imagerequest.FitCover,
+		FitMode:    string(imgcache.FitCover),
-		},
+		Expires:    expires,
-	}, expires)
+	})
 	signedURL := fmt.Sprintf("/v1/image/%s/images/photo.jpg/50x50.jpeg?sig=%s&exp=%d",
 		signedHost, sig, expires.Unix())
 
@@ -124,17 +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, ""},
 	}
 
@@ -142,21 +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{
+			signedURL, err := fix.service.GenerateSignedURL("", &imgcache.ImageRequest{
-						Host: signedHost,
+				SourceHost: signedHost,
-						Path: "/images/photo.jpg",
+				SourcePath: "/images/photo.jpg",
-					},
+				Size:       imgcache.Size{Width: 50, Height: 50},
-					Transform: imagerequest.Transform{
+				Format:     imgcache.FormatJPEG,
-						Size:    imagerequest.Size{Width: 50, Height: 50},
-						Format:  imagerequest.FormatJPEG,
 				Quality:    tt.quality,
 				FitMode:    tt.fitMode,
-					},
 			}, time.Hour)
+			if err != nil {
+				t.Fatalf("GenerateSignedURL() error = %v", err)
+			}
 
-			status := getImage(t, setupTestHandler(t), signedURL)
+			status := getImage(t, fix, signedURL)
 			if status != http.StatusBadGateway {
 				t.Errorf("status = %d, want %d", status, http.StatusBadGateway)
 			}
@@ -213,170 +169,3 @@ 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
-// chi router: chi routes on the path as the client wrote it whenever that is
-// not Go's own encoding of it. A 502 means the signature passed, so the route
-// read the source path and query that were signed.
-func TestHandleImage_GeneratedSignedURLWithSourceQueryVerifies(t *testing.T) {
-	t.Parallel()
-
-	tests := []struct {
-		name  string
-		query string
-	}{
-		{"slash and colon", "url=https://origin.example.com/cat.jpg"},
-		{"semicolon", "a=1;b=2"},
-		{"comma", "crop=0,0,50,50"},
-		{"equals and ampersand", "a=1&b=2"},
-		{"percent-escape", "name=my%20cat"},
-		{"question mark", "next=/a?b=1"},
-	}
-
-	for _, tt := range tests {
-		t.Run(tt.name, func(t *testing.T) {
-			t.Parallel()
-
-			signedURL := generateSignedURL("test-signing-key-must-be-32-chars",
-				&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)
-			if status != http.StatusBadGateway {
-				t.Errorf("status = %d, want %d", status, http.StatusBadGateway)
-			}
-		})
-	}
-}
-
-// TestHandleImage_SourceQueryEncodedAnyWay signs one source URL with a query
-// and writes it into the image URL in ways the README allows: the "?" before
-// the query and each "%" in it percent-encoded, and every other character as
-// itself or percent-encoded. A 502 means the signature passed.
-func TestHandleImage_SourceQueryEncodedAnyWay(t *testing.T) {
-	t.Parallel()
-
-	expires := time.Now().Add(time.Hour)
-	signer := signature.New("test-signing-key-must-be-32-chars")
-	sig := signer.Sign(&imagerequest.Request{
-		Source: imagerequest.Source{
-			Host:  signedHost,
-			Path:  photoPath,
-			Query: "url=https://origin.example.com/my%20cat.jpg",
-		},
-		Transform: imagerequest.Transform{
-			Size:    imagerequest.Size{Width: 50, Height: 50},
-			Format:  imagerequest.FormatJPEG,
-			Quality: 85,
-			FitMode: imagerequest.FitCover,
-		},
-	}, expires)
-
-	tests := []struct {
-		name         string
-		writtenQuery string
-	}{
-		{"only ? and % encoded",
-			"%3Furl=https://origin.example.com/my%2520cat.jpg"},
-		{"every reserved character encoded",
-			"%3Furl%3Dhttps%3A%2F%2Forigin.example.com%2Fmy%2520cat.jpg"},
-		{"lower-case hex digits",
-			"%3furl=https://origin.example.com/my%2520cat.jpg"},
-	}
-
-	for _, tt := range tests {
-		t.Run(tt.name, func(t *testing.T) {
-			t.Parallel()
-
-			target := fmt.Sprintf("/v1/image/%s%s%s/50x50.jpeg?sig=%s&exp=%d",
-				signedHost, photoPath, tt.writtenQuery, sig, expires.Unix())
-
-			status := getImage(t, setupTestHandler(t), target)
-			if status != http.StatusBadGateway {
-				t.Errorf("status = %d, want %d", status, http.StatusBadGateway)
-			}
-		})
-	}
-}
-
-// 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.
-func TestHandleImage_SourceURLHoldingPercent25Verifies(t *testing.T) {
-	t.Parallel()
-
-	tests := []struct {
-		name        string
-		sourcePath  string
-		sourceQuery string
-		// writtenPathAndQuery is the source path and query as the README says
-		// to write them into the image URL
-		writtenPathAndQuery string
-	}{
-		{"path", "/sale/50%25off.jpg", "", "/sale/50%2525off.jpg"},
-		{"query", photoPath, "discount=50%25", photoPath + "%3Fdiscount=50%2525"},
-	}
-
-	for _, tt := range tests {
-		t.Run(tt.name+" written by the README rule", func(t *testing.T) {
-			t.Parallel()
-
-			expires := time.Now().Add(time.Hour)
-			signer := signature.New("test-signing-key-must-be-32-chars")
-			sig := signer.Sign(&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,
-					Quality: 85,
-					FitMode: imagerequest.FitCover,
-				},
-			}, expires)
-
-			target := fmt.Sprintf("/v1/image/%s%s/50x50.jpeg?sig=%s&exp=%d",
-				signedHost, tt.writtenPathAndQuery, sig, expires.Unix())
-
-			status := getImage(t, setupTestHandler(t), target)
-			if status != http.StatusBadGateway {
-				t.Errorf("status = %d, want %d", status, http.StatusBadGateway)
-			}
-		})
-
-		t.Run(tt.name+" written by generateSignedURL", func(t *testing.T) {
-			t.Parallel()
-
-			signedURL := generateSignedURL("test-signing-key-must-be-32-chars",
-				&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)
-			if status != http.StatusBadGateway {
-				t.Errorf("status = %d, want %d", status, http.StatusBadGateway)
-			}
-		})
-	}
-}

internal/handlers/imageenc.go

@@ -2,13 +2,19 @@ package handlers
 
 import (
 	"errors"
+	"fmt"
+	"io"
 	"net/http"
+	"strconv"
 	"time"
 
 	"github.com/go-chi/chi/v5"
+	"github.com/go-chi/chi/v5/middleware"
 
 	"sneak.berlin/go/pixa/internal/encurl"
-	"sneak.berlin/go/pixa/internal/imagerequest"
+	"sneak.berlin/go/pixa/internal/httpfetcher"
+	"sneak.berlin/go/pixa/internal/imageprocessor"
+	"sneak.berlin/go/pixa/internal/imgcache"
 )
 
 // HandleImageEnc handles requests to /v1/e/{token}/* for encrypted
@@ -20,59 +26,151 @@ func (s *Handlers) HandleImageEnc() http.HandlerFunc {
 			return
 		}
 
-		req, expires, ok := s.parseImageEncRequest(w, r)
+		ctx := r.Context()
-		if !ok {
+		start := time.Now()
+
+		req, ok := s.parseImageEncRequest(w, r)
+		if !ok || !s.chooseAutoFormat(w, r, req) {
 			return
 		}
 
-		s.serveImage(w, r, req, expires)
+		// Log the request
+		s.log.Debug("encrypted image request",
+			"host", req.SourceHost,
+			"path", req.SourcePath,
+			"dimensions", fmt.Sprintf("%dx%d", req.Size.Width, req.Size.Height),
+			"format", req.Format,
+		)
+
+		// Fetch and process the image (no signature validation
+		// needed - encrypted URL is trusted)
+		resp, err := s.imgSvc.Get(ctx, req)
+		if err != nil {
+			s.handleImageError(w, err)
+
+			return
+		}
+
+		defer func() { _ = resp.Content.Close() }()
+
+		// Set response headers
+		w.Header().Set("Content-Type", resp.ContentType)
+
+		if resp.ContentLength > 0 {
+			w.Header().Set("Content-Length", strconv.FormatInt(resp.ContentLength, 10))
+		}
+
+		// Cache headers: max-age ends at the URL's expiry
+		w.Header().Set("Cache-Control", cacheControl(req.Expires))
+		w.Header().Set("X-Pixa-Cache", string(resp.CacheStatus))
+
+		if notModified(w, r, resp.ETag) {
+			return
+		}
+
+		// A HEAD request gets the headers only
+		if r.Method == http.MethodHead {
+			w.WriteHeader(http.StatusOK)
+
+			return
+		}
+
+		// Stream the response
+		written, err := io.Copy(w, resp.Content)
+		if err != nil {
+			s.log.Error("failed to write response", "error", err)
+
+			return
+		}
+
+		// Log completion
+		duration := time.Since(start)
+		s.log.Info("image served",
+			"request_id", middleware.GetReqID(ctx),
+			"cache_key", imgcache.CacheKey(req),
+			"host", req.SourceHost,
+			"path", req.SourcePath,
+			"format", req.Format,
+			"cache_status", resp.CacheStatus,
+			"served_bytes", written,
+			"duration_ms", duration.Milliseconds(),
+		)
 	}
 }
 
 // parseImageEncRequest decrypts the token of an encrypted image URL into an
-// image request and checks it, and returns it with the token's expiry. On a
+// ImageRequest and checks it. On a token that is missing, does not decrypt,
-// token that is missing, does not decrypt, has expired or asks for something
+// has expired or asks for something not valid, it writes an error response
-// not valid, it writes an error response and returns false.
+// and returns false.
 func (s *Handlers) parseImageEncRequest(
 	w http.ResponseWriter, r *http.Request,
-) (*imagerequest.Request, time.Time, bool) {
+) (*imgcache.ImageRequest, bool) {
 	// Extract token from URL
 	token := chi.URLParam(r, "token")
 	if token == "" {
 		s.respondError(w, "missing token", http.StatusBadRequest)
 
-		return nil, time.Time{}, false
+		return nil, false
 	}
 
 	// Decrypt and validate the payload
-	req, expires, 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)
 			s.respondError(w, "URL has expired", http.StatusGone)
 
-			return nil, time.Time{}, false
+			return nil, false
 		}
 
-		s.log.Debug("invalid encrypted URL", "error", err)
+		s.log.Debug("failed to decrypt URL", "error", err)
 		s.respondError(w, "invalid encrypted URL", http.StatusBadRequest)
 
-		return nil, time.Time{}, false
+		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. This refuses an over-limit size before the source is
+	// within limits, so an over-limit size or unknown fit mode is a 400
-	// fetched. An unknown fit mode is a 400 here rather than a 500 from the
+	// here rather than an out-of-memory or a 500 from the processor.
-	// processor.
+	err = imgcache.ValidateImageRequest(req)
-	err = imagerequest.ValidateImageRequest(req)
 	if err != nil {
 		s.log.Debug("encrypted URL failed validation", "error", err)
 		s.respondError(w, "invalid encrypted URL: "+err.Error(),
 			http.StatusBadRequest)
 
-		return nil, time.Time{}, false
+		return nil, false
 	}
 
-	return req, expires, true
+	return req, true
+}
+
+// handleImageError converts image service errors to HTTP responses.
+func (s *Handlers) handleImageError(w http.ResponseWriter, err error) {
+	switch {
+	case errors.Is(err, httpfetcher.ErrSSRFBlocked):
+		s.respondError(w, "forbidden", http.StatusForbidden)
+	case errors.Is(err, httpfetcher.ErrUpstreamError):
+		s.respondError(w, "upstream error", http.StatusBadGateway)
+	case errors.Is(err, httpfetcher.ErrUpstreamTimeout):
+		s.respondError(w, "upstream timeout", http.StatusGatewayTimeout)
+	case errors.Is(err, httpfetcher.ErrTooManyConnections),
+		errors.Is(err, imageprocessor.ErrTooManyImages):
+		s.respondError(w, "server busy, try again later",
+			http.StatusServiceUnavailable)
+	case errors.Is(err, httpfetcher.ErrInvalidContentType),
+		errors.Is(err, imageprocessor.ErrUnsupportedInputFormat):
+		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)
+	default:
+		s.log.Error("image request failed", "error", err)
+		s.respondError(w, "internal error", http.StatusInternalServerError)
+	}
 }

internal/handlers/imageenc_internal_test.go

@@ -6,13 +6,11 @@ import (
 	"net/http"
 	"net/http/httptest"
 	"testing"
-	"time"
 
 	"github.com/go-chi/chi/v5"
 
 	"sneak.berlin/go/pixa/internal/encurl"
-	"sneak.berlin/go/pixa/internal/imagerequest"
+	"sneak.berlin/go/pixa/internal/imgcache"
-	"sneak.berlin/go/pixa/internal/seal"
 )
 
 // newEncTestServer builds a router serving the encrypted-URL route with a
@@ -22,13 +20,11 @@ import (
 func newEncTestServer(t *testing.T) (*encurl.Generator, http.Handler) {
 	t.Helper()
 
-	keys, err := seal.DeriveKeys(testSigningKey)
+	encGen, err := encurl.NewGenerator(testSigningKey)
 	if err != nil {
-		t.Fatalf("seal.DeriveKeys() error = %v", err)
+		t.Fatalf("encurl.NewGenerator() error = %v", err)
 	}
 
-	encGen := encurl.NewGenerator(keys.EncryptedURLKey)
-
 	h := &Handlers{
 		log:    slog.New(slog.DiscardHandler),
 		encGen: encGen,
@@ -58,15 +54,12 @@ 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},
-		},
-	}, time.Time{})
 	if err != nil {
 		t.Fatalf("Generate() error = %v", err)
 	}
@@ -86,16 +79,13 @@ 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"),
-		},
-	}, time.Time{})
 	if err != nil {
 		t.Fatalf("Generate() error = %v", err)
 	}

internal/handlers/imageenc_token_internal_test.go

@@ -9,8 +9,6 @@ import (
 	"time"
 
 	"sneak.berlin/go/pixa/internal/encurl"
-	"sneak.berlin/go/pixa/internal/imagerequest"
-	"sneak.berlin/go/pixa/internal/seal"
 )
 
 // requireServedPhoto requires that rec answers 200 with the JPEG at photoPath
@@ -61,34 +59,32 @@ 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, time.Time{})
+	valid, err := h.encGen.Generate(&photo)
 	if err != nil {
 		t.Fatalf("Generate() error = %v", err)
 	}
 
-	expired, err := h.encGen.Generate(&photo, time.Now().Add(-time.Minute))
+	expiredPhoto := photo
+	expiredPhoto.ExpiresAt = time.Now().Add(-time.Minute).Unix()
+
+	expired, err := h.encGen.Generate(&expiredPhoto)
 	if err != nil {
 		t.Fatalf("Generate() error = %v", err)
 	}
 
-	keys, err := seal.DeriveKeys("another-signing-key-fedcba9876543210")
+	otherGen, err := encurl.NewGenerator("another-signing-key-fedcba9876543210")
 	if err != nil {
-		t.Fatalf("seal.DeriveKeys() error = %v", err)
+		t.Fatalf("encurl.NewGenerator() error = %v", err)
 	}
 
-	otherGen := encurl.NewGenerator(keys.EncryptedURLKey)
+	otherKey, err := otherGen.Generate(&photo)
-
-	otherKey, err := otherGen.Generate(&photo, time.Time{})
 	if err != nil {
 		t.Fatalf("Generate() error = %v", err)
 	}

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 +58,16 @@ 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},
-			Format:  imagerequest.FormatJXL,
 		Quality:    encurl.DefaultQuality,
-			FitMode: imagerequest.FitCover,
+		FitMode:    string(imgcache.FitCover),
-		},
+		Expires:    expires,
-	}, expires)
+	})
 	query := fmt.Sprintf("?sig=%s&exp=%d", sig, expires.Unix())
 
 	for _, size := range []string{"50x50.jxl", "50x50"} {
@@ -85,15 +83,12 @@ 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},
-		},
-	}, time.Time{})
 	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

@@ -10,15 +10,10 @@ 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/imagerequest"
 	"sneak.berlin/go/pixa/internal/imgcache"
-	"sneak.berlin/go/pixa/internal/seal"
-	"sneak.berlin/go/pixa/internal/signature"
 )
 
 // blockedReferer is a page on leech.example, which newRefererRoutes puts on
@@ -34,11 +29,11 @@ type countingFetcher struct {
 
 // Fetch counts the fetch and passes it on.
 func (f *countingFetcher) Fetch(
-	ctx context.Context, source imagerequest.Source,
+	ctx context.Context, url string,
 ) (*httpfetcher.FetchResult, error) {
 	f.fetches.Add(1)
 
-	return f.Fetcher.Fetch(ctx, source)
+	return f.Fetcher.Fetch(ctx, url)
 }
 
 // newRefererRoutes returns both image routes of a Handlers whose
@@ -55,8 +50,7 @@ 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)
 	}
@@ -64,29 +58,22 @@ func newRefererRoutes(t *testing.T) (http.Handler, *Handlers, *countingFetcher)
 	svc, err := imgcache.NewService(&imgcache.ServiceConfig{
 		Cache:      cache,
 		Fetcher:    fetcher,
-		Processor: imageprocessor.New(imageprocessor.Params{
+		SigningKey: testSigningKey,
-			MaxInputBytes:           50 << 20,
+		Allowlist:  []string{allowlistedHost},
-			MaxConcurrentProcessing: 2,
-		}),
-		MaxResponseSize: 50 << 20,
 	})
 	if err != nil {
 		t.Fatalf("imgcache.NewService() error = %v", err)
 	}
 
-	keys, err := seal.DeriveKeys(testSigningKey)
+	encGen, err := encurl.NewGenerator(testSigningKey)
 	if err != nil {
-		t.Fatalf("seal.DeriveKeys() error = %v", err)
+		t.Fatalf("encurl.NewGenerator() error = %v", err)
 	}
 
-	encGen := encurl.NewGenerator(keys.EncryptedURLKey)
-
 	h := &Handlers{
 		log:    slog.New(slog.DiscardHandler),
 		imgSvc: svc,
 		encGen: encGen,
-		signer:    signature.New(testSigningKey),
-		allowlist: allowlist.New([]string{allowlistedHost}),
 		refererBlocklist: allowlist.New(
 			[]string{"leech.example", ".hotlinker.example"}),
 	}

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 the handlers that newSignedHostServer builds check signatures with.
+func signedPhotoURL(t *testing.T, h *Handlers) string {
-// It takes a Handlers 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
@@ -40,16 +40,13 @@ 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,
-		},
-	}, time.Time{})
 	if err != nil {
 		t.Fatalf("Generate() error = %v", err)
 	}

internal/handlers/server_busy_internal_test.go

@@ -1,7 +1,6 @@
 package handlers
 
 import (
-	"context"
 	"fmt"
 	"log/slog"
 	"net/http"
@@ -11,64 +10,40 @@ 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"
 )
 
-// TestServerBusyAnswers503 checks that respondImageError, which answers the
+// TestServerBusyAnswers503 checks that both image routes answer 503 with
-// errors of both image routes, answers 503 with a clear error when the image
+// a clear error when the image service gives up waiting for a free upstream
-// service gives up waiting for a free upstream connection or processing slot,
+// connection or processing slot, wrapped as the service wraps them.
-// wrapped as the service wraps them.
 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),
 		fmt.Errorf("image processing failed: %w", imageprocessor.ErrTooManyImages),
 	} {
-		rec := httptest.NewRecorder()
+		plain := httptest.NewRecorder()
-		h.respondImageError(rec, req, err)
+		h.respondImageError(plain, req, err)
 
+		encrypted := httptest.NewRecorder()
+		h.handleImageError(encrypted, err)
+
+		for route, rec := range map[string]*httptest.ResponseRecorder{
+			"/v1/image/": plain, "/v1/e/": encrypted,
+		} {
 			if rec.Code != http.StatusServiceUnavailable {
-			t.Errorf("for %v: status = %d, want %d",
+				t.Errorf("%s for %v: status = %d, want %d",
-				err, rec.Code, http.StatusServiceUnavailable)
+					route, err, rec.Code, http.StatusServiceUnavailable)
 			}
 
 			if !strings.Contains(rec.Body.String(), "server busy, try again later") {
-			t.Errorf("for %v: body = %q, want the server busy error",
+				t.Errorf("%s for %v: body = %q, want the server busy error",
-				err, rec.Body.String())
+					route, err, rec.Body.String())
+			}
 		}
 	}
 }
-
-// TestProcessingTimedOutAnswers503 checks that respondImageError, which
-// answers the errors of both image routes, answers 503 with the server busy
-// error when the image service reports that processing stopped at the
-// deadline of the request doing it, wrapped as the service wraps it. A request
-// that waited for that processing gets this error while its own deadline may
-// have time left. The request's source only goes into a log line, so it is
-// left empty.
-func TestProcessingTimedOutAnswers503(t *testing.T) {
-	t.Parallel()
-
-	h := &Handlers{log: slog.New(slog.DiscardHandler)}
-	err := fmt.Errorf("%w: failed to encode: %w",
-		imgcache.ErrProcessingTimedOut, context.DeadlineExceeded)
-
-	rec := httptest.NewRecorder()
-	h.respondImageError(rec, &imagerequest.Request{}, err)
-	t.Logf("status = %d, body = %q", rec.Code, rec.Body.String())
-
-	if rec.Code != http.StatusServiceUnavailable {
-		t.Errorf("status = %d, want %d", rec.Code, http.StatusServiceUnavailable)
-	}
-
-	if !strings.Contains(rec.Body.String(), "server busy, try again later") {
-		t.Errorf("body = %q, want the server busy error", rec.Body.String())
-	}
-}

internal/handlers/unsupported_source_internal_test.go

@@ -10,21 +10,18 @@ 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 respondImageError, which
+// TestUnsupportedSourceFormatAnswers415 checks that both image routes answer
-// answers the errors of both image routes, answers 415 with a clear error when
+// 415 with a clear error when the upstream answers with a content type pixa
-// the upstream answers with a content type pixa does not accept, such as SVG,
+// does not accept, such as SVG, and when orig is asked of a source in a
-// and when orig is asked of a source in a format the processor cannot name,
+// format the processor cannot name, wrapped as the service wraps them.
-// wrapped as the service wraps them.
 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",
@@ -32,18 +29,26 @@ func TestUnsupportedSourceFormatAnswers415(t *testing.T) {
 		fmt.Errorf("image processing failed: %w: unknown",
 			imageprocessor.ErrUnsupportedInputFormat),
 	} {
-		rec := httptest.NewRecorder()
+		plain := httptest.NewRecorder()
-		h.respondImageError(rec, req, err)
+		h.respondImageError(plain, req, err)
-		t.Logf("for %v: %d %s", err, rec.Code, rec.Body.String())
+
+		encrypted := httptest.NewRecorder()
+		h.handleImageError(encrypted, err)
+
+		for route, rec := range map[string]*httptest.ResponseRecorder{
+			"HandleImage": plain, "HandleImageEnc": encrypted,
+		} {
+			t.Logf("%s for %v: %d %s", route, err, rec.Code, rec.Body.String())
 
 			if rec.Code != http.StatusUnsupportedMediaType {
-			t.Errorf("for %v: status = %d, want %d",
+				t.Errorf("%s for %v: status = %d, want %d",
-				err, rec.Code, http.StatusUnsupportedMediaType)
+					route, err, rec.Code, http.StatusUnsupportedMediaType)
 			}
 
 			if !strings.Contains(rec.Body.String(), "unsupported source format") {
-			t.Errorf("for %v: body = %q, want the unsupported source format error",
+				t.Errorf("%s for %v: body = %q, want the unsupported source format error",
-				err, rec.Body.String())
+					route, err, rec.Body.String())
+			}
 		}
 	}
 }

internal/handlers/validate_signature_internal_test.go

@@ -1,211 +0,0 @@
-package handlers
-
-import (
-	"testing"
-	"time"
-
-	"sneak.berlin/go/pixa/internal/allowlist"
-	"sneak.berlin/go/pixa/internal/signature"
-)
-
-// Addresses the port tests below put on the allowlist.
-const (
-	allowlistedIPv4 = "203.0.113.5"
-	allowlistedIPv6 = "2001:db8::1"
-)
-
-// newSignatureChecker returns Handlers that check signatures with
-// testSigningKey and have allowlistHosts on their allowlist, as New builds
-// them from signing_key and allowlist_hosts.
-func newSignatureChecker(allowlistHosts ...string) *Handlers {
-	return &Handlers{
-		signer:    signature.New(testSigningKey),
-		allowlist: allowlist.New(allowlistHosts),
-	}
-}
-
-func TestValidateSignature_NonAllowlistedHost_NoSignature(t *testing.T) {
-	t.Parallel()
-
-	h := newSignatureChecker(allowlistedHost)
-
-	// Should fail validation - not allowlisted and no signature
-	err := h.validateSignature(photoRequest(signedHost), "", time.Time{})
-	if err == nil {
-		t.Error("validateSignature() expected error for non-allowlisted " +
-			"host without signature")
-	}
-}
-
-func TestValidateSignature_NonAllowlistedHost_ValidSignature(t *testing.T) {
-	t.Parallel()
-
-	h := newSignatureChecker(allowlistedHost)
-	req := photoRequest(signedHost)
-
-	// Generate a valid signature
-	expires := time.Now().Add(time.Hour)
-	sig := signature.New(testSigningKey).Sign(req, expires)
-
-	// Should pass validation
-	err := h.validateSignature(req, sig, expires)
-	if err != nil {
-		t.Errorf("validateSignature() error = %v", err)
-	}
-}
-
-func TestValidateSignature_NonAllowlistedHost_ExpiredSignature(t *testing.T) {
-	t.Parallel()
-
-	h := newSignatureChecker(allowlistedHost)
-	req := photoRequest(signedHost)
-
-	// Generate an expired signature
-	expires := time.Now().Add(-time.Hour)
-	sig := signature.New(testSigningKey).Sign(req, expires)
-
-	// Should fail validation
-	err := h.validateSignature(req, sig, expires)
-	if err == nil {
-		t.Error("validateSignature() expected error for expired signature")
-	}
-}
-
-func TestValidateSignature_NonAllowlistedHost_InvalidSignature(t *testing.T) {
-	t.Parallel()
-
-	h := newSignatureChecker(allowlistedHost)
-
-	// Should fail validation
-	err := h.validateSignature(photoRequest(signedHost), "invalid-signature",
-		time.Now().Add(time.Hour))
-	if err == nil {
-		t.Error("validateSignature() expected error for invalid signature")
-	}
-}
-
-// TestValidateSignature_NoAllowlist checks that with no host on the
-// allowlist, a request without a signature fails validation.
-func TestValidateSignature_NoAllowlist(t *testing.T) {
-	t.Parallel()
-
-	h := newSignatureChecker()
-
-	err := h.validateSignature(photoRequest(signedHost), "", time.Time{})
-	if err == nil {
-		t.Error("validateSignature() expected error when no host is allowlisted")
-	}
-}
-
-// TestValidateSignature_SignatureExactHostMatch verifies that
-// validateSignature enforces exact host matching for signatures. A
-// signature for one host must not verify for a different host, even
-// if they share a domain suffix.
-func TestValidateSignature_SignatureExactHostMatch(t *testing.T) {
-	t.Parallel()
-
-	h := newSignatureChecker()
-
-	// Sign a request for signedHost
-	signedReq := photoRequest(signedHost)
-	expires := time.Now().Add(time.Hour)
-	sig := signature.New(testSigningKey).Sign(signedReq, expires)
-
-	// The original request should pass validation
-	t.Run("exact host passes", func(t *testing.T) {
-		t.Parallel()
-
-		err := h.validateSignature(signedReq, sig, expires)
-		if err != nil {
-			t.Errorf("validateSignature() exact host failed: %v", err)
-		}
-	})
-
-	// Try to reuse the signature with different hosts
-	tests := []struct {
-		name string
-		host string
-	}{
-		{"parent domain", "example.com"},
-		{"sibling subdomain", "images.example.com"},
-		{"deeper subdomain", "a." + signedHost},
-		{"evil suffix domain", signedHost + ".evil.com"},
-		{"prefixed host", "evil" + signedHost},
-	}
-
-	for _, tt := range tests {
-		t.Run(tt.name+" rejected", func(t *testing.T) {
-			t.Parallel()
-
-			err := h.validateSignature(photoRequest(tt.host), sig, expires)
-			if err == nil {
-				t.Errorf("validateSignature() should reject signature for "+
-					"host %q (signed for %q)", tt.host, signedHost)
-			}
-		})
-	}
-}
-
-// TestValidateSignature_HostWithPortNeedsSignature verifies that a host
-// followed by a port, or by a colon with no port, matches no allowlist entry,
-// so that a request for it without a signature is refused, while the same
-// host with no port is allowlisted.
-func TestValidateSignature_HostWithPortNeedsSignature(t *testing.T) {
-	t.Parallel()
-
-	h := newSignatureChecker(allowlistedHost, allowlistedIPv4, allowlistedIPv6)
-
-	tests := []struct {
-		host        string
-		allowlisted bool
-	}{
-		{allowlistedHost, true},
-		{allowlistedHost + ":8443", false},
-		{allowlistedHost + ":443", false},
-		{allowlistedHost + ":", false},
-		{allowlistedIPv4, true},
-		{allowlistedIPv4 + ":8080", false},
-		{"[" + allowlistedIPv6 + "]", true},
-		{"[" + allowlistedIPv6 + "]:8443", false},
-	}
-
-	for _, tt := range tests {
-		t.Run(tt.host, func(t *testing.T) {
-			t.Parallel()
-
-			err := h.validateSignature(photoRequest(tt.host), "", time.Time{})
-			t.Logf("validateSignature() for host %q with no signature: %v",
-				tt.host, err)
-
-			if allowlisted := err == nil; allowlisted != tt.allowlisted {
-				t.Errorf("host %q served without a signature = %v, want %v",
-					tt.host, allowlisted, tt.allowlisted)
-			}
-		})
-	}
-}
-
-// TestValidateSignature_UnbracketedIPv6PortNeedsSignature verifies that an
-// allowlisted IPv6 address written without brackets and followed by a port,
-// or by a colon with no port, needs a signature. Go's URL type reads
-// 2001:db8::1:8443 as the host 2001:db8::1 with the port 8443.
-func TestValidateSignature_UnbracketedIPv6PortNeedsSignature(t *testing.T) {
-	t.Parallel()
-
-	h := newSignatureChecker(allowlistedIPv6)
-
-	for _, host := range []string{allowlistedIPv6 + ":8443", allowlistedIPv6 + ":"} {
-		t.Run(host, func(t *testing.T) {
-			t.Parallel()
-
-			err := h.validateSignature(photoRequest(host), "", time.Time{})
-			t.Logf("validateSignature() for host %q with no signature: %v",
-				host, err)
-
-			if err == nil {
-				t.Errorf("host %q served without a signature, want refused",
-					host)
-			}
-		})
-	}
-}

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,
-		MaxResponseSize:       50 << 20,
-		MaxConnectionsPerHost: 20,
-		MaxConnections:        64,
 	// TEST-NET-2 (198.51.100.0/24) is public to the built-in check, so
 	// blocking it can only come from the operator-supplied list.
-		BlockedNetworks: []netip.Prefix{netip.MustParsePrefix("198.51.100.0/24")},
+	cfg.BlockedNetworks = []netip.Prefix{netip.MustParsePrefix("198.51.100.0/24")}
-	}))
+
+	transport := transportOf(t, New(cfg))
 
 	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()
 
@@ -38,25 +32,21 @@ 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)
 	}
 
-	_, err := f.Fetch(testContext(t), imageSourceOn("127.0.0.1"))
+	_, err := f.Fetch(testContext(t), "http://127.0.0.1/image")
 	if !errors.Is(err, ErrSSRFBlocked) {
 		t.Errorf("Fetch(loopback URL) error = %v, want ErrSSRFBlocked", err)
 	}
 
-	_, err = f.Fetch(testContext(t), upstreamSource("/redirect/private"))
+	_, err = f.Fetch(testContext(t), upstreamURL("/redirect/private"))
 	if !errors.Is(err, ErrSSRFBlocked) {
 		t.Errorf("Fetch(/redirect/private) error = %v, want ErrSSRFBlocked", err)
 	}

internal/httpfetcher/fetch_internal_test.go

@@ -14,8 +14,6 @@ import (
 	"sync"
 	"testing"
 	"time"
-
-	"sneak.berlin/go/pixa/internal/imagerequest"
 )
 
 // testPublicHost is a TEST-NET-1 (RFC 5737) literal. isPrivateIP treats it as
@@ -31,9 +29,9 @@ const imagePayload = "fake-jpeg-bytes"
 // would mean SSRF protection let a forbidden target reach the transport.
 var errUnexpectedDial = errors.New("unexpected dial target")
 
-// upstreamSource returns the source at path on the fake public host.
+// upstreamURL builds a fetch URL on the fake public host for the given path.
-func upstreamSource(path string) imagerequest.Source {
+func upstreamURL(path string) string {
-	return imagerequest.Source{Host: testPublicHost, Path: path}
+	return "http://" + testPublicHost + path
 }
 
 // recordingDialer records every address the transport asks it to dial and
@@ -122,12 +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
@@ -160,7 +153,7 @@ func testContext(t *testing.T) context.Context {
 func fetchImage(t *testing.T, f *HTTPFetcher, path string) *FetchResult {
 	t.Helper()
 
-	res, err := f.Fetch(testContext(t), upstreamSource(path))
+	res, err := f.Fetch(testContext(t), upstreamURL(path))
 	if err != nil {
 		t.Fatalf("Fetch(%s) error = %v", path, err)
 	}
@@ -172,7 +165,7 @@ func fetchImage(t *testing.T, f *HTTPFetcher, path string) *FetchResult {
 func fetchExpectError(t *testing.T, f *HTTPFetcher, path string) error {
 	t.Helper()
 
-	res, err := f.Fetch(testContext(t), upstreamSource(path))
+	res, err := f.Fetch(testContext(t), upstreamURL(path))
 	if err == nil {
 		_ = res.Content.Close()
 
@@ -224,7 +217,7 @@ func TestFetchRedirectToPrivateIPBlocked(t *testing.T) {
 	srv := startUpstream(t)
 	f, dialer := newServerFetcher(t, srv, nil)
 
-	_, err := f.Fetch(testContext(t), upstreamSource("/redirect/private"))
+	_, err := f.Fetch(testContext(t), upstreamURL("/redirect/private"))
 	if !errors.Is(err, ErrSSRFBlocked) {
 		t.Fatalf("Fetch() error = %v, want ErrSSRFBlocked", err)
 	}
@@ -287,12 +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)
 
@@ -321,12 +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)
 
@@ -451,12 +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)
 
@@ -485,12 +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)
 
@@ -547,7 +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
@@ -567,9 +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)
 			}
 		})
 	}
@@ -583,7 +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")
 	}
@@ -592,53 +569,3 @@ func TestSSRFSafeDialerAllowsPublicTarget(t *testing.T) {
 		t.Errorf("public target was SSRF-blocked: %v", err)
 	}
 }
-
-// TestFetchSchemeFollowsAllowHTTP checks that the fetcher fetches a source
-// over https, on port 443, unless AllowHTTP is set, and then over http, on
-// port 80. The test server speaks plain HTTP, so only the fetch over http
-// succeeds.
-func TestFetchSchemeFollowsAllowHTTP(t *testing.T) {
-	t.Parallel()
-
-	tests := []struct {
-		allowHTTP bool
-		wantAddr  string
-	}{
-		{false, net.JoinHostPort(testPublicHost, "443")},
-		{true, net.JoinHostPort(testPublicHost, "80")},
-	}
-
-	for _, tt := range tests {
-		t.Run(fmt.Sprintf("AllowHTTP %v", tt.allowHTTP), func(t *testing.T) {
-			t.Parallel()
-
-			srv := startUpstream(t)
-			dialer := &recordingDialer{target: srv.Listener.Addr().String()}
-
-			f := New(&Config{
-				Timeout:               30 * time.Second,
-				MaxResponseSize:       50 << 20,
-				AllowHTTP:             tt.allowHTTP,
-				MaxConnectionsPerHost: 20,
-				MaxConnections:        64,
-				DialContext:           dialer.dialContext,
-			})
-
-			res, err := f.Fetch(testContext(t), upstreamSource("/image"))
-			if err == nil {
-				_ = res.Content.Close()
-			}
-
-			dialed := dialer.dialedAddrs()
-			t.Logf("Fetch(): error %v, dialed %v", err, dialed)
-
-			if served := err == nil; served != tt.allowHTTP {
-				t.Errorf("served = %v, want %v", served, tt.allowHTTP)
-			}
-
-			if len(dialed) != 1 || dialed[0] != tt.wantAddr {
-				t.Errorf("dialed %v, want only %s", dialed, tt.wantAddr)
-			}
-		})
-	}
-}

internal/httpfetcher/httpfetcher.go

@@ -20,20 +20,20 @@ import (
 	"time"
 
 	"github.com/go-chi/chi/v5/middleware"
-	"sneak.berlin/go/pixa/internal/imagerequest"
 )
 
 // Fetcher configuration constants.
 const (
+	DefaultFetchTimeout          = 30 * time.Second
+	DefaultMaxResponseSize       = 50 << 20 // 50MB
 	DefaultTLSTimeout            = 10 * time.Second
 	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
@@ -59,9 +59,8 @@ 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{
@@ -69,7 +68,6 @@ var builtinBlockedPrefixes = []netip.Prefix{
 	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("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.
@@ -92,8 +90,8 @@ var (
 
 // Fetcher retrieves content from upstream origins.
 type Fetcher interface {
-	// Fetch retrieves the content of the source image.
+	// Fetch retrieves content from the given URL.
-	Fetch(ctx context.Context, source imagerequest.Source) (*FetchResult, error)
+	Fetch(ctx context.Context, url string) (*FetchResult, error)
 }
 
 // FetchResult contains the result of fetching from upstream.
@@ -120,28 +118,17 @@ 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
-	// AllowHTTP makes the fetcher fetch sources over http instead of https,
+	// UserAgent to send to upstream servers.
-	// and follow redirects to http (for testing only).
+	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.
 	MaxConnectionsPerHost int
@@ -158,6 +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 {
@@ -185,6 +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
@@ -213,7 +224,7 @@ func New(config *Config) *HTTPFetcher {
 			}
 
 			// Validate the redirect target
-			err := validateURL(req.Context(), req.URL, config.AllowHTTP)
+			err := validateURL(req.Context(), req.URL.String(), config.AllowHTTP)
 			if err != nil {
 				return fmt.Errorf("redirect blocked: %w", err)
 			}
@@ -231,22 +242,18 @@ func New(config *Config) *HTTPFetcher {
 	}
 }
 
-// Fetch retrieves the source image with SSRF protection, over https, or over
+// Fetch retrieves content from the given URL with SSRF protection. When
-// http when AllowHTTP is set. When MaxConnections fetches are already in
+// MaxConnections fetches are already in progress, it waits up to
-// progress, it waits up to ConnectionWaitTimeout for one to finish, then
+// ConnectionWaitTimeout for one to finish, then fails with
-// fails with ErrTooManyConnections.
+// ErrTooManyConnections.
-func (f *HTTPFetcher) Fetch(
+func (f *HTTPFetcher) Fetch(ctx context.Context, url string) (*FetchResult, error) {
-	ctx context.Context, source imagerequest.Source,
-) (*FetchResult, error) {
-	sourceURL := source.URL(f.config.AllowHTTP)
-
 	// Validate URL before making request
-	err := validateURL(ctx, sourceURL, f.config.AllowHTTP)
+	err := validateURL(ctx, url, f.config.AllowHTTP)
 	if err != nil {
 		return nil, err
 	}
 
-	release, err := f.acquireConnection(ctx, source.Host)
+	release, err := f.acquireConnection(ctx, extractHost(url))
 	if err != nil {
 		return nil, err
 	}
@@ -260,14 +267,19 @@ func (f *HTTPFetcher) Fetch(
 		}
 	}()
 
+	parsedURL, err := neturl.Parse(url)
+	if err != nil {
+		return nil, fmt.Errorf("failed to parse URL: %w", err)
+	}
+
 	req := &http.Request{
 		Method: http.MethodGet,
-		URL:    sourceURL,
+		URL:    parsedURL,
 		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
@@ -446,7 +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
 		}
@@ -456,18 +468,23 @@ func (f *HTTPFetcher) isAllowedContentType(contentType string) bool {
 }
 
 // validateURL checks if a URL is safe to fetch (not internal/private).
-func validateURL(ctx context.Context, fetchURL *neturl.URL, allowHTTP bool) error {
+func validateURL(ctx context.Context, rawURL string, allowHTTP bool) error {
-	if !allowHTTP && fetchURL.Scheme != "https" {
+	if !allowHTTP && !strings.HasPrefix(rawURL, "https://") {
 		return ErrUnsupportedScheme
 	}
 
-	// Hostname drops any port, and the brackets of an IPv6 address whether
+	// Parse to extract host
-	// or not a port follows them
+	host := extractHost(rawURL)
-	host := fetchURL.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
@@ -489,6 +506,25 @@ func validateURL(ctx context.Context, fetchURL *neturl.URL, allowHTTP bool) erro
 	return nil
 }
 
+// extractHost extracts the host from a URL string.
+func extractHost(rawURL string) string {
+	// Simple extraction without full URL parsing
+	url := rawURL
+	if idx := strings.Index(url, "://"); idx != -1 {
+		url = url[idx+3:]
+	}
+
+	if idx := strings.Index(url, "/"); idx != -1 {
+		url = url[:idx]
+	}
+
+	if idx := strings.Index(url, "?"); idx != -1 {
+		url = url[:idx]
+	}
+
+	return url
+}
+
 // isLocalhost checks if the host is localhost.
 func isLocalhost(host string) bool {
 	host = strings.ToLower(host)
@@ -507,9 +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
@@ -561,12 +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
@@ -579,26 +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

@@ -5,26 +5,62 @@ import (
 	"errors"
 	"io"
 	"net"
-	"net/url"
 	"testing"
 	"testing/fstest"
-	"time"
-
-	"sneak.berlin/go/pixa/internal/imagerequest"
 )
 
 // 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
@@ -52,6 +88,33 @@ func TestIsAllowedContentType(t *testing.T) {
 	}
 }
 
+func TestExtractHost(t *testing.T) {
+	t.Parallel()
+
+	tests := []struct {
+		url  string
+		want string
+	}{
+		{"https://example.com/path", testHost},
+		{"http://example.com:8080/path", "example.com:8080"},
+		{"https://example.com", testHost},
+		{"https://example.com?q=1", testHost},
+		{"example.com/path", testHost},
+		{"", ""},
+	}
+
+	for _, tc := range tests {
+		t.Run(tc.url, func(t *testing.T) {
+			t.Parallel()
+
+			got := extractHost(tc.url)
+			if got != tc.want {
+				t.Errorf("extractHost(%q) = %q, want %q", tc.url, got, tc.want)
+			}
+		})
+	}
+}
+
 func TestIsLocalhost(t *testing.T) {
 	t.Parallel()
 
@@ -123,48 +186,10 @@ 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()
 
-	err := validateURL(t.Context(), &url.URL{Scheme: "http", Host: testHost}, false)
+	err := validateURL(t.Context(), "http://example.com/path", false)
 	if !errors.Is(err, ErrUnsupportedScheme) {
 		t.Errorf("validateURL http = %v, want ErrUnsupportedScheme", err)
 	}
@@ -174,8 +199,7 @@ func TestValidateURL_AllowsHTTPWhenConfigured(t *testing.T) {
 	t.Parallel()
 
 	// Use a host that won't resolve (explicit .invalid TLD) so we don't hit DNS.
-	err := validateURL(t.Context(),
+	err := validateURL(t.Context(), "http://nonexistent.invalid/path", true)
-		&url.URL{Scheme: "http", Host: "nonexistent.invalid"}, true)
 	// We expect a host resolution error, not ErrUnsupportedScheme.
 	if errors.Is(err, ErrUnsupportedScheme) {
 		t.Error("validateURL with AllowHTTP should not return ErrUnsupportedScheme")
@@ -185,7 +209,7 @@ func TestValidateURL_AllowsHTTPWhenConfigured(t *testing.T) {
 func TestValidateURL_RejectsLocalhost(t *testing.T) {
 	t.Parallel()
 
-	err := validateURL(t.Context(), &url.URL{Scheme: "https", Host: "localhost"}, false)
+	err := validateURL(t.Context(), "https://localhost/path", false)
 	if !errors.Is(err, ErrSSRFBlocked) {
 		t.Errorf("validateURL localhost = %v, want ErrSSRFBlocked", err)
 	}
@@ -194,7 +218,7 @@ func TestValidateURL_RejectsLocalhost(t *testing.T) {
 func TestValidateURL_EmptyHost(t *testing.T) {
 	t.Parallel()
 
-	err := validateURL(t.Context(), &url.URL{Scheme: "https"}, false)
+	err := validateURL(t.Context(), "https:///path", false)
 	if !errors.Is(err, ErrInvalidHost) {
 		t.Errorf("validateURL empty host = %v, want ErrInvalidHost", err)
 	}
@@ -209,8 +233,7 @@ func TestMockFetcher_FetchesFile(t *testing.T) {
 
 	m := NewMock(mockFS)
 
-	result, err := m.Fetch(context.Background(),
+	result, err := m.Fetch(context.Background(), "https://example.com/images/photo.jpg")
-		imagerequest.Source{Host: testHost, Path: "/images/photo.jpg"})
 	if err != nil {
 		t.Fatalf("Fetch() error = %v", err)
 	}
@@ -241,8 +264,7 @@ func TestMockFetcher_MissingFileReturnsUpstreamError(t *testing.T) {
 	mockFS := fstest.MapFS{}
 	m := NewMock(mockFS)
 
-	_, err := m.Fetch(context.Background(),
+	_, err := m.Fetch(context.Background(), "https://example.com/missing.jpg")
-		imagerequest.Source{Host: testHost, Path: "/missing.jpg"})
 	if !errors.Is(err, ErrUpstreamError) {
 		t.Errorf("Fetch() error = %v, want ErrUpstreamError", err)
 	}
@@ -259,7 +281,7 @@ func TestMockFetcher_RespectsContextCancellation(t *testing.T) {
 	ctx, cancel := context.WithCancel(context.Background())
 	cancel()
 
-	_, err := m.Fetch(ctx, imagerequest.Source{Host: testHost, Path: "/photo.jpg"})
+	_, err := m.Fetch(ctx, "https://example.com/photo.jpg")
 	if !errors.Is(err, context.Canceled) {
 		t.Errorf("Fetch() error = %v, want context.Canceled", err)
 	}

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

@@ -8,20 +8,22 @@ import (
 	"sync"
 	"testing"
 	"time"
-
-	"sneak.berlin/go/pixa/internal/imagerequest"
 )
 
-// imageSourceOn is the fake upstream's image route on host.
+// imageURLOnPort is the fake upstream's image route on testPublicHost at
-func imageSourceOn(host string) imagerequest.Source {
-	return imagerequest.Source{Host: host, Path: "/image"}
-}
-
-// imageSourceOnPort is the fake upstream's image route on testPublicHost at
 // port. Each port is a different host to the per-host limit, while the test
 // dialer sends every port to the one test server.
-func imageSourceOnPort(port int) imagerequest.Source {
+func imageURLOnPort(port int) string {
-	return imageSourceOn(net.JoinHostPort(testPublicHost, strconv.Itoa(port)))
+	return "http://" + net.JoinHostPort(testPublicHost, strconv.Itoa(port)) +
+		"/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
@@ -35,22 +37,18 @@ 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
 
-	first, err := f.Fetch(testContext(t), imageSourceOnPort(81))
+	first, err := f.Fetch(testContext(t), imageURLOnPort(81))
 	if err != nil {
 		t.Fatalf("first Fetch() error = %v", err)
 	}
 
-	second, err := f.Fetch(testContext(t), imageSourceOnPort(82))
+	second, err := f.Fetch(testContext(t), imageURLOnPort(82))
 	if err != nil {
 		t.Fatalf("second Fetch() error = %v", err)
 	}
@@ -59,7 +57,7 @@ func TestFetchLimitsConnectionsToAllHostsTogether(t *testing.T) {
 
 	start := time.Now()
 
-	_, err = f.Fetch(testContext(t), imageSourceOnPort(83))
+	_, err = f.Fetch(testContext(t), imageURLOnPort(83))
 	if !errors.Is(err, ErrTooManyConnections) {
 		t.Fatalf("third Fetch() error = %v, want ErrTooManyConnections", err)
 	}
@@ -78,7 +76,7 @@ func TestFetchLimitsConnectionsToAllHostsTogether(t *testing.T) {
 		t.Fatalf("close first body: %v", err)
 	}
 
-	third, err := f.Fetch(testContext(t), imageSourceOnPort(83))
+	third, err := f.Fetch(testContext(t), imageURLOnPort(83))
 	if err != nil {
 		t.Fatalf("Fetch() after a response was closed: error = %v", err)
 	}
@@ -96,16 +94,12 @@ 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)
 
-	first, err := f.Fetch(testContext(t), imageSourceOnPort(81))
+	first, err := f.Fetch(testContext(t), imageURLOnPort(81))
 	if err != nil {
 		t.Fatalf("first Fetch() error = %v", err)
 	}
@@ -115,7 +109,7 @@ func TestFetchFreesHostSlotWhenContextEndsWaitingForConnection(t *testing.T) {
 	ctx, cancel := context.WithTimeout(t.Context(), 100*time.Millisecond)
 	defer cancel()
 
-	_, err = f.Fetch(ctx, imageSourceOnPort(82))
+	_, err = f.Fetch(ctx, imageURLOnPort(82))
 	if !errors.Is(err, context.DeadlineExceeded) {
 		t.Fatalf("second Fetch() error = %v, want context.DeadlineExceeded", err)
 	}
@@ -140,7 +134,7 @@ func TestFetchRemovesIdleHostSemaphores(t *testing.T) {
 
 	for i := range 100 {
 		wg.Go(func() {
-			res, err := f.Fetch(ctx, imageSourceOnPort(1+i%50))
+			res, err := f.Fetch(ctx, imageURLOnPort(1+i%50))
 			if err != nil {
 				t.Errorf("Fetch() error = %v", err)
 
@@ -169,22 +163,19 @@ 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
 
-	open, err := f.Fetch(testContext(t), imageSourceOnPort(81))
+	open, err := f.Fetch(testContext(t), imageURLOnPort(81))
 	if err != nil {
 		t.Fatalf("first Fetch() error = %v", err)
 	}
 
-	_, err = f.Fetch(testContext(t), imageSourceOnPort(82))
+	_, err = f.Fetch(testContext(t), imageURLOnPort(82))
 	if !errors.Is(err, ErrTooManyConnections) {
 		t.Fatalf("Fetch() from another host: error = %v, "+
 			"want ErrTooManyConnections", err)
@@ -193,7 +184,7 @@ func TestFetchRemovesHostSemaphoreWhenNoConnection(t *testing.T) {
 	ctx, cancel := context.WithTimeout(t.Context(), 100*time.Millisecond)
 	defer cancel()
 
-	_, err = f.Fetch(ctx, imageSourceOnPort(81))
+	_, err = f.Fetch(ctx, imageURLOnPort(81))
 	if !errors.Is(err, context.DeadlineExceeded) {
 		t.Fatalf("Fetch() from the busy host: error = %v, "+
 			"want context.DeadlineExceeded", err)
@@ -205,7 +196,7 @@ func TestFetchRemovesHostSemaphoreWhenNoConnection(t *testing.T) {
 	ctx, cancel = context.WithTimeout(t.Context(), 100*time.Millisecond)
 	defer cancel()
 
-	_, err = f.Fetch(ctx, imageSourceOnPort(83))
+	_, err = f.Fetch(ctx, imageURLOnPort(83))
 	if !errors.Is(err, context.DeadlineExceeded) {
 		t.Fatalf("Fetch() from a host with nothing open: error = %v, "+
 			"want context.DeadlineExceeded", err)
@@ -229,14 +220,14 @@ func TestFetchReleasesConnectionOnError(t *testing.T) {
 
 	cases := []struct {
 		name string
-		source imagerequest.Source
+		url  string
 		want error
 	}{
-		{"upstream answers 500", upstreamSource("/status/500"), ErrUpstreamError},
+		{"upstream answers 500", upstreamURL("/status/500"), ErrUpstreamError},
-		{"upstream sends HTML", upstreamSource("/html"), ErrInvalidContentType},
+		{"upstream sends HTML", upstreamURL("/html"), ErrInvalidContentType},
 		// 198.51.100.7 (TEST-NET-2) passes the SSRF checks, and the test
 		// dialer refuses every host but testPublicHost.
-		{"connecting fails", imageSourceOn("198.51.100.7"), errUnexpectedDial},
+		{"connecting fails", "http://198.51.100.7/image", errUnexpectedDial},
 	}
 
 	for _, tc := range cases {
@@ -245,17 +236,13 @@ 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
 
-			_, err := f.Fetch(testContext(t), tc.source)
+			_, err := f.Fetch(testContext(t), tc.url)
 			if !errors.Is(err, tc.want) {
 				t.Fatalf("Fetch() error = %v, want %v", err, tc.want)
 			}

internal/httpfetcher/mock.go

@@ -7,14 +7,14 @@ import (
 	"io/fs"
 	"net/http"
 	"strings"
-
-	"sneak.berlin/go/pixa/internal/imagerequest"
 )
 
+// errEmptyURLPath is returned when a mock URL has no usable path.
+var errEmptyURLPath = errors.New("empty URL path")
+
 // MockFetcher implements Fetcher using an embedded filesystem.
 // Files are organized as: hostname/path/to/file.ext
-// The source with host example.com and path /images/photo.jpg maps to
+// URLs like https://example.com/images/photo.jpg map to example.com/images/photo.jpg.
-// example.com/images/photo.jpg; the source query is ignored.
 type MockFetcher struct {
 	fs fs.FS
 }
@@ -24,10 +24,8 @@ func NewMock(fsys fs.FS) *MockFetcher {
 	return &MockFetcher{fs: fsys}
 }
 
-// Fetch retrieves the source's content from the mock filesystem.
+// Fetch retrieves content from the mock filesystem.
-func (m *MockFetcher) Fetch(
+func (m *MockFetcher) Fetch(ctx context.Context, url string) (*FetchResult, error) {
-	ctx context.Context, source imagerequest.Source,
-) (*FetchResult, error) {
 	// Check context cancellation
 	select {
 	case <-ctx.Done():
@@ -35,7 +33,11 @@ func (m *MockFetcher) Fetch(
 	default:
 	}
 
-	path := source.Host + source.Path
+	// Parse URL to get filesystem path
+	path, err := urlToFSPath(url)
+	if err != nil {
+		return nil, err
+	}
 
 	// Open the file
 	f, err := m.fs.Open(path)
@@ -66,6 +68,32 @@ func (m *MockFetcher) Fetch(
 	}, nil
 }
 
+// urlToFSPath converts a URL to a filesystem path.
+// https://example.com/images/photo.jpg -> example.com/images/photo.jpg
+func urlToFSPath(rawURL string) (string, error) {
+	// Strip scheme
+	url := rawURL
+	if idx := strings.Index(url, "://"); idx != -1 {
+		url = url[idx+3:]
+	}
+
+	// Remove query string
+	if idx := strings.Index(url, "?"); idx != -1 {
+		url = url[:idx]
+	}
+
+	// Remove fragment
+	if idx := strings.Index(url, "#"); idx != -1 {
+		url = url[:idx]
+	}
+
+	if url == "" {
+		return "", errEmptyURLPath
+	}
+
+	return url, nil
+}
+
 // detectContentTypeFromPath returns the MIME type based on file extension.
 func detectContentTypeFromPath(path string) string {
 	path = strings.ToLower(path)

internal/httpfetcher/request_id_internal_test.go

@@ -34,7 +34,7 @@ func TestFetchSendsRequestID(t *testing.T) {
 
 	ctx := context.WithValue(testContext(t), middleware.RequestIDKey, requestID)
 
-	res, err := f.Fetch(ctx, upstreamSource("/image"))
+	res, err := f.Fetch(ctx, upstreamURL("/image"))
 	if err != nil {
 		t.Fatalf("Fetch() error = %v", err)
 	}

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

@@ -1,106 +0,0 @@
-package imageprocessor
-
-import (
-	"bytes"
-	"context"
-	"errors"
-	"io"
-	"testing"
-	"time"
-)
-
-// readerAfterDeadline is a Process input whose first Read waits until done
-// is closed, so the deadline passes after Process has taken its slot and
-// before it encodes.
-type readerAfterDeadline struct {
-	data   *bytes.Reader
-	done   <-chan struct{}
-	waited bool
-}
-
-func (r *readerAfterDeadline) Read(p []byte) (int, error) {
-	if !r.waited {
-		r.waited = true
-
-		<-r.done
-	}
-
-	return r.data.Read(p)
-}
-
-// inputNotToBeRead is a Process input that fails the test when it is read.
-type inputNotToBeRead struct {
-	t *testing.T
-}
-
-func (r inputNotToBeRead) Read([]byte) (int, error) {
-	r.t.Error("Process read its input although its deadline had passed")
-
-	return 0, io.EOF
-}
-
-// TestProcessStopsWhenDeadlinePassed checks that Process returns
-// context.DeadlineExceeded, and holds no slot afterwards, when its context's
-// deadline has passed before it starts, then without reading its input, or
-// while it reads its input. govips gives pixa no way to stop libvips once an
-// encode has begun, so Process must not begin one for a request that has
-// ended.
-func TestProcessStopsWhenDeadlinePassed(t *testing.T) {
-	t.Parallel()
-
-	input := createTestJPEG(t, 50, 50)
-
-	t.Run("before Process starts", func(t *testing.T) {
-		t.Parallel()
-
-		ctx, cancel := context.WithDeadline(t.Context(),
-			time.Now().Add(-time.Second))
-		defer cancel()
-
-		// With a slot free, the select in acquireSlot takes the slot or sees
-		// the ended context at random, so Process is called many times
-		for range 100 {
-			checkProcessStopsAtDeadline(ctx, t, inputNotToBeRead{t: t})
-		}
-	})
-
-	t.Run("while Process reads its input", func(t *testing.T) {
-		t.Parallel()
-
-		ctx, cancel := context.WithTimeout(t.Context(), 100*time.Millisecond)
-		defer cancel()
-
-		checkProcessStopsAtDeadline(ctx, t, &readerAfterDeadline{
-			data: bytes.NewReader(input), done: ctx.Done(),
-		})
-	})
-}
-
-// checkProcessStopsAtDeadline runs Process on input with ctx, whose deadline
-// has passed by the time Process could encode, and fails the test unless
-// Process returns context.DeadlineExceeded and gives its slot back.
-func checkProcessStopsAtDeadline(
-	ctx context.Context, t *testing.T, input io.Reader,
-) {
-	t.Helper()
-
-	proc := New(Params{MaxInputBytes: 50 << 20, MaxConcurrentProcessing: 1})
-
-	result, err := proc.Process(ctx, input, smallJPEGTransform())
-	if result != nil {
-		t.Logf("Process() made a %dx%d image after its deadline passed",
-			result.Width, result.Height)
-
-		_ = result.Content.Close()
-	}
-
-	t.Logf("Process() error = %v", err)
-
-	if !errors.Is(err, context.DeadlineExceeded) {
-		t.Errorf("Process() error = %v, want context.DeadlineExceeded", err)
-	}
-
-	if held := len(proc.processingSemaphore); held != 0 {
-		t.Errorf("%d slots still held after Process() returned", held)
-	}
-}

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

@@ -1,287 +0,0 @@
-package imageprocessor
-
-import (
-	"bytes"
-	"image"
-	"image/color"
-	"image/png"
-	"math"
-	"testing"
-
-	"sneak.berlin/go/pixa/internal/imagerequest"
-)
-
-// TestImageProcessor_FitCoverServesThinSource verifies that FitCover serves
-// a thin source at the requested size. An 8192x1 source scaled to cover
-// 8192x8192 is 8192 times as long as the output on its long side. The centre
-// of an 8192x1 source with the proportions of 1x8192 is 1/8192 of a pixel
-// wide. Each case is also turned on its side.
-func TestImageProcessor_FitCoverServesThinSource(t *testing.T) {
-	t.Parallel()
-
-	tests := []struct {
-		name                    string
-		inputWidth, inputHeight int
-		size                    imagerequest.Size
-	}{
-		{"8192x1 at 8192x8192", 8192, 1, imagerequest.Size{Width: 8192, Height: 8192}},
-		{"8192x1 at 1x8192", 8192, 1, imagerequest.Size{Width: 1, Height: 8192}},
-		{"1x8192 at 8192x8192", 1, 8192, imagerequest.Size{Width: 8192, Height: 8192}},
-		{"1x8192 at 8192x1", 1, 8192, imagerequest.Size{Width: 8192, Height: 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.FitCover,
-				})
-			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.size.Width || result.Height != tt.size.Height {
-				t.Errorf("Process() made %dx%d, want %dx%d",
-					result.Width, result.Height, tt.size.Width, tt.size.Height)
-			}
-		})
-	}
-}
-
-// createBandsPNG creates a PNG of three equal bands, red, green and blue,
-// side by side when it is wider than tall and top to bottom otherwise.
-func createBandsPNG(t *testing.T, width, height int) []byte {
-	t.Helper()
-
-	bands := []color.RGBA{
-		{R: 255, A: 255},
-		{G: 255, A: 255},
-		{B: 255, A: 255},
-	}
-
-	img := image.NewRGBA(image.Rect(0, 0, width, height))
-	for y := range height {
-		for x := range width {
-			band := 3 * y / height
-			if width > height {
-				band = 3 * x / width
-			}
-
-			img.Set(x, y, bands[band])
-		}
-	}
-
-	return encodePNG(t, img)
-}
-
-// TestImageProcessor_FitCoverCropsTheCentre verifies that FitCover keeps the
-// centre of the source: a 300x100 source of red, green and blue bands side
-// by side, or a 100x300 one with them top to bottom, comes out at 50x50 as
-// its green band.
-func TestImageProcessor_FitCoverCropsTheCentre(t *testing.T) {
-	t.Parallel()
-
-	tests := []struct {
-		name                    string
-		inputWidth, inputHeight int
-	}{
-		{"bands side by side", 300, 100},
-		{"bands top to bottom", 100, 300},
-	}
-
-	for _, tt := range tests {
-		t.Run(tt.name, func(t *testing.T) {
-			t.Parallel()
-
-			input := createBandsPNG(t, tt.inputWidth, tt.inputHeight)
-
-			result, err := New(Params{
-				MaxInputBytes:           50 << 20,
-				MaxConcurrentProcessing: 1,
-			}).Process(t.Context(),
-				bytes.NewReader(input),
-				&imagerequest.Transform{
-					Size:    imagerequest.Size{Width: 50, Height: 50},
-					Format:  imagerequest.FormatPNG,
-					FitMode: imagerequest.FitCover,
-				})
-			if err != nil {
-				t.Fatalf("Process() error = %v", err)
-			}
-
-			defer func() { _ = result.Content.Close() }()
-
-			output, err := png.Decode(result.Content)
-			if err != nil {
-				t.Fatalf("failed to decode output: %v", err)
-			}
-
-			bounds := output.Bounds()
-			t.Logf("Process() made %dx%d", bounds.Dx(), bounds.Dy())
-
-			if bounds.Dx() != 50 || bounds.Dy() != 50 {
-				t.Fatalf("Process() made %dx%d, want 50x50",
-					bounds.Dx(), bounds.Dy())
-			}
-
-			// Resampling may blend a little of the bands beside the
-			// green one into the output's edges.
-			for y := bounds.Min.Y; y < bounds.Max.Y; y++ {
-				for x := bounds.Min.X; x < bounds.Max.X; x++ {
-					r, g, b, _ := output.At(x, y).RGBA()
-					if r>>8 > 64 || g>>8 < 192 || b>>8 > 64 {
-						t.Fatalf("output pixel %d,%d is %d,%d,%d, want green",
-							x, y, r>>8, g>>8, b>>8)
-					}
-				}
-			}
-		})
-	}
-}
-
-// The greys of createSquarePNG, and the grey halfway between them.
-const (
-	backgroundGrey = 192
-	squareGrey     = 64
-	halfwayGrey    = (backgroundGrey + squareGrey) / 2
-)
-
-// createSquarePNG creates a grey PNG side pixels square with a darker grey
-// square squareSide pixels wide in its centre.
-func createSquarePNG(t *testing.T, side, squareSide int) []byte {
-	t.Helper()
-
-	first := (side - squareSide) / 2
-	last := first + squareSide - 1
-
-	img := image.NewGray(image.Rect(0, 0, side, side))
-	for y := range side {
-		for x := range side {
-			grey := uint8(backgroundGrey)
-			if x >= first && x <= last && y >= first && y <= last {
-				grey = squareGrey
-			}
-
-			img.SetGray(x, y, color.Gray{Y: grey})
-		}
-	}
-
-	return encodePNG(t, img)
-}
-
-// squareLength returns how long the square is along greys, the greys of a
-// row or column of the output that crosses it: the distance between the
-// first and the last point where greys passes halfwayGrey, or 0 when there
-// is no such point. Resampling blurs the square's edges over several
-// pixels, and each point is placed between the two pixels on either side
-// of it in proportion to their greys, so the length is measured to a
-// fraction of a pixel.
-func squareLength(greys []float64) float64 {
-	first, last := -1.0, -1.0
-
-	for i := 1; i < len(greys); i++ {
-		before, after := greys[i-1], greys[i]
-		if (before > halfwayGrey) == (after > halfwayGrey) {
-			continue
-		}
-
-		point := float64(i-1) + (before-halfwayGrey)/(before-after)
-		if first < 0 {
-			first = point
-		}
-
-		last = point
-	}
-
-	return last - first
-}
-
-// TestImageProcessor_FitCoverKeepsProportions verifies that FitCover scales
-// both sides of the source by the same amount: a square in the centre of
-// the source comes out square. Its width and height are measured along the
-// output's middle row and column.
-func TestImageProcessor_FitCoverKeepsProportions(t *testing.T) {
-	t.Parallel()
-
-	tests := []struct {
-		name             string
-		side, squareSide int
-		size             imagerequest.Size
-	}{
-		{"16x16 at 100x60", 16, 8, imagerequest.Size{Width: 100, Height: 60}},
-		{"16x16 at 60x100", 16, 8, imagerequest.Size{Width: 60, Height: 100}},
-		{"10x10 at 100x35", 10, 2, imagerequest.Size{Width: 100, Height: 35}},
-		{"10x10 at 35x100", 10, 2, imagerequest.Size{Width: 35, Height: 100}},
-		{"64x64 at 300x100", 64, 16, imagerequest.Size{Width: 300, Height: 100}},
-		{"64x64 at 100x300", 64, 16, imagerequest.Size{Width: 100, Height: 300}},
-	}
-
-	for _, tt := range tests {
-		t.Run(tt.name, func(t *testing.T) {
-			t.Parallel()
-
-			input := createSquarePNG(t, tt.side, tt.squareSide)
-
-			result, err := New(Params{
-				MaxInputBytes:           50 << 20,
-				MaxConcurrentProcessing: 1,
-			}).Process(t.Context(),
-				bytes.NewReader(input),
-				&imagerequest.Transform{
-					Size:    tt.size,
-					Format:  imagerequest.FormatPNG,
-					FitMode: imagerequest.FitCover,
-				})
-			if err != nil {
-				t.Fatalf("Process() error = %v", err)
-			}
-
-			defer func() { _ = result.Content.Close() }()
-
-			output, err := png.Decode(result.Content)
-			if err != nil {
-				t.Fatalf("failed to decode output: %v", err)
-			}
-
-			bounds := output.Bounds()
-			if bounds.Dx() != tt.size.Width || bounds.Dy() != tt.size.Height {
-				t.Fatalf("Process() made %dx%d, want %dx%d",
-					bounds.Dx(), bounds.Dy(), tt.size.Width, tt.size.Height)
-			}
-
-			row := make([]float64, bounds.Dx())
-			for x := range row {
-				r, _, _, _ := output.At(x, bounds.Dy()/2).RGBA()
-				row[x] = float64(r >> 8)
-			}
-
-			column := make([]float64, bounds.Dy())
-			for y := range column {
-				r, _, _, _ := output.At(bounds.Dx()/2, y).RGBA()
-				column[y] = float64(r >> 8)
-			}
-
-			width, height := squareLength(row), squareLength(column)
-			t.Logf("square is %.2f wide and %.2f high", width, height)
-
-			if width == 0 || math.Abs(width-height) > 0.5 {
-				t.Errorf("square is %.2f wide and %.2f high, want it square",
-					width, height)
-			}
-		})
-	}
-}

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

@@ -7,11 +7,11 @@ import (
 	"errors"
 	"fmt"
 	"io"
+	"runtime"
 	"sync"
 	"time"
 
 	"github.com/davidbyttow/govips/v2/vips"
-	"sneak.berlin/go/pixa/internal/imagerequest"
 )
 
 // vipsOnce ensures vips is initialized exactly once.
@@ -20,10 +20,11 @@ import (
 var vipsOnce sync.Once
 
 // initVips initializes libvips with quiet logging, one worker thread per
-// image and no operation cache. Each request decodes different source
+// image and no operation cache. Process already works on one image per CPU
-// bytes, so the operation cache would rarely be hit and would hold memory
+// by default, so more threads per image would only compete for the CPUs.
-// outside MaxConcurrentProcessing; repeated requests are served from
+// Each request decodes different source bytes, so the operation cache
-// pixa's disk cache instead.
+// would rarely be hit and would hold memory outside MaxConcurrentProcessing;
+// repeated requests are served from pixa's disk cache instead.
 func initVips() {
 	vipsOnce.Do(func() {
 		vips.LoggingSettings(nil, vips.LogLevelError)
@@ -54,6 +55,49 @@ 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 +122,10 @@ 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 +134,8 @@ 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 +143,6 @@ 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 +172,47 @@ 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, the number of CPUs Go uses (runtime.GOMAXPROCS(0)) 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 = runtime.GOMAXPROCS(0)
+	}
+
 	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
+// ErrTooManyImages.
-// 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
-// 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 +221,18 @@ 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 +270,27 @@ 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(img, outputFormat, req.Quality)
 	if err != nil {
 		return nil, fmt.Errorf("failed to encode: %w", err)
 	}
@@ -265,13 +309,9 @@ 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 +320,10 @@ 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 +344,46 @@ 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"
@@ -353,45 +417,25 @@ func (p *ImageProcessor) WaitForProcessing(ctx context.Context) int {
 
 // acquireSlot takes a slot in processingSemaphore, waiting at most
 // processingWaitTimeout for one to free up, and returns the func that gives
-// it back. When ctx has ended by the time it has a slot, it gives the slot
+// it back. A free slot is taken even when ctx has ended; only the wait for
-// back and returns ctx's error.
+// one stops when ctx ends, as the rest of Process does not check ctx.
 func (p *ImageProcessor) acquireSlot(ctx context.Context) (func(), error) {
+	release := func() { <-p.processingSemaphore }
+
 	select {
 	case p.processingSemaphore <- struct{}{}:
+		return release, nil
+	default:
+	}
+
+	select {
+	case p.processingSemaphore <- struct{}{}:
+		return release, nil
 	case <-time.After(p.processingWaitTimeout):
 		return nil, ErrTooManyImages
 	case <-ctx.Done():
 		return nil, ctx.Err()
 	}
-
-	release := func() { <-p.processingSemaphore }
-
-	// select takes the slot even when ctx has ended at the same moment
-	err := ctx.Err()
-	if err != nil {
-		release()
-
-		return nil, err
-	}
-
-	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.
@@ -406,9 +450,9 @@ 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:
@@ -418,143 +462,75 @@ 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)
+		// Resize and crop to fill exact dimensions (default)
-		return cropCentreAndResize(img, width, height)
+		return img.Thumbnail(width, height, vips.InterestingCentre)
 
-	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)
 	}
 }
 
-// cropCentreAndResize scales img by the same amount on both sides, the
-// least that makes it cover width x height, and cuts the centre width x
-// height out of it, as libvips' thumbnail does with InterestingCentre.
-// thumbnail alone scales the whole image and copies the result into memory
-// before it cuts, and for a thin image that is far larger than the image or
-// the output: 8192x64 at 8192x8192 is 1048576x8192, about 24 GiB. So the
-// centre is cut from img first, widened to whole pixels of img, which adds
-// less than one pixel of img on each side, and thumbnail scales and cuts
-// only that.
-func cropCentreAndResize(img *vips.ImageRef, width, height int) error {
-	imgW, imgH := img.Width(), img.Height()
-
-	// An image wider than the requested proportions keeps its height and
-	// loses width down to imgH*width/height, any other keeps its width and
-	// loses height down to imgW*height/width. Half of what is lost comes
-	// off each side, rounded down to whole pixels, so the part kept holds
-	// all of the centre.
-	left, top := 0, 0
-	if imgW*height > imgH*width {
-		left = (imgW*height - imgH*width) / (2 * height) //nolint:mnd // each side
-	} else {
-		top = (imgH*width - imgW*height) / (2 * width) //nolint:mnd // each side
-	}
-
-	err := img.ExtractArea(left, top, imgW-2*left, imgH-2*top)
-	if err != nil {
-		return err
-	}
-
-	return img.Thumbnail(width, height, vips.InterestingCentre)
-}
-
 const defaultQuality = 85
 
-// encode encodes an image to the specified format. govips gives pixa no way
+// encode encodes an image to the specified format.
-// 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,
+	img *vips.ImageRef, format Format, quality int,
-	quality int,
 ) ([]byte, error) {
-	err := ctx.Err()
-	if err != nil {
-		return nil, err
-	}
-
 	if quality <= 0 {
 		quality = defaultQuality
 	}
@@ -564,32 +540,32 @@ func (p *ImageProcessor) encode(
 	// libvips' built-in profile; govips' own sRGB path variable is set on
 	// first use but read without a lock, so concurrent requests race on it.
 	if img.HasICCProfile() {
-		err = img.TransformICCProfileWithFallback("srgb", "srgb")
+		err := img.TransformICCProfileWithFallback("srgb", "srgb")
 		if err != nil {
 			return nil, fmt.Errorf("failed to convert to sRGB: %w", err)
 		}
 	}
 
 	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 +615,11 @@ 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 +631,11 @@ 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 image of random pixels, the worst case,
-// and about 96 with an alpha channel, against the default
+// against the default downstream_timeout of 60 seconds. On an image of
-// downstream_timeout of 60 seconds, so an AVIF output is held to
+// milder noise, which 1 saves in about 12 seconds, 2 takes nearly a minute
-// MaxAVIFOutputPixels. On an image of milder noise, which 1 saves in about
+// and libvips' default, 4, takes minutes.
-// 12 seconds, 2 takes nearly a minute and libvips' default, 4, takes
-// minutes.
 const avifEffort = 1
 
 // avifBitdepth is the AVIF bit depth, 8 bits per sample for every image.
@@ -693,18 +662,10 @@ 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 +704,6 @@ 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 +731,20 @@ 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()
 		}
@@ -116,10 +115,18 @@ func waitForEntries(t *testing.T, entered <-chan struct{}, count int) {
 	}
 }
 
-func TestNewMakesMaxConcurrentProcessingSlots(t *testing.T) {
+func TestNewDefaultsMaxConcurrentProcessingToCPUs(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 != runtime.GOMAXPROCS(0) {
+			t.Errorf("MaxConcurrentProcessing %d: %d slots, want %d, one per CPU",
+				limit, got, runtime.GOMAXPROCS(0))
+		}
+	}
+
+	proc := New(Params{MaxConcurrentProcessing: 3})
 	if got := cap(proc.processingSemaphore); got != 3 {
 		t.Errorf("MaxConcurrentProcessing 3: %d slots, want 3", got)
 	}
@@ -138,7 +145,7 @@ 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 +192,7 @@ 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 +213,7 @@ 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)
 	}
@@ -232,37 +239,37 @@ func TestProcessReleasesSlotOnError(t *testing.T) {
 
 	valid := createTestJPEG(t, 10, 10)
 
-	unsupported := smallJPEGTransform()
+	unsupported := smallJPEGRequest()
 	unsupported.Format = "bmp"
 
 	cases := []struct {
 		name  string
 		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",
 			input: iotest.ErrReader(errTestReadFailed),
-			transform: smallJPEGTransform(),
+			req:   smallJPEGRequest(),
 			want:  errTestReadFailed,
 		},
 		{
 			name:  "input over the byte limit",
 			input: bytes.NewReader(createTestJPEG(t, 800, 600)),
-			transform: smallJPEGTransform(),
+			req:   smallJPEGRequest(),
 			want:  ErrInputDataTooLarge,
 		},
 		{
 			name:  "input not an image",
 			input: strings.NewReader("not an image"),
-			transform: smallJPEGTransform(),
+			req:   smallJPEGRequest(),
 		},
 		{
 			name:  "output format not supported",
 			input: bytes.NewReader(valid),
-			transform: unsupported,
+			req:   unsupported,
 			want:  ErrUnsupportedOutputFormat,
 		},
 	}
@@ -274,7 +281,7 @@ 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 +291,7 @@ 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 +308,7 @@ 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

@@ -1,137 +0,0 @@
-// Package imagerequest holds the image request type, its parts, its checks,
-// the parsing of the /v1/image/ path, the variant key, the source key and the
-// source's upstream URL. 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"
-)
-
-// 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. It holds exactly what the variant key
-// covers.
-type Request struct {
-	// Source is what to fetch
-	Source Source
-	// Transform is what to do to it
-	Transform Transform
-}
-
-// 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
-}
-
-// URL returns the source's upstream URL, with the scheme http when allowHTTP
-// is true and https otherwise. net/url writes its path percent-encoded again,
-// so each source path is one upstream path. Its query is the source query as
-// it is, with the characters escapeQuery encodes percent-encoded.
-func (s Source) URL(allowHTTP bool) *url.URL {
-	scheme := "https"
-	if allowHTTP {
-		scheme = "http"
-	}
-
-	return &url.URL{
-		Scheme:   scheme,
-		Host:     s.Host,
-		Path:     s.Path,
-		RawQuery: escapeQuery(s.Query),
-	}
-}

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/sourceurl_internal_test.go

@@ -1,50 +0,0 @@
-package imagerequest
-
-import "testing"
-
-func TestSource_URL_DefaultHTTPS(t *testing.T) {
-	t.Parallel()
-
-	source := Source{
-		Host:  testHostCDN,
-		Path:  testPathCat,
-		Query: "v=2",
-	}
-
-	got := source.URL(false).String()
-
-	want := "https://cdn.example.com/photos/cat.jpg?v=2"
-	if got != want {
-		t.Errorf("URL() = %q, want %q", got, want)
-	}
-}
-
-func TestSource_URL_AllowHTTP(t *testing.T) {
-	t.Parallel()
-
-	source := Source{
-		Host: "localhost:8080",
-		Path: testPathCat,
-	}
-
-	got := source.URL(true).String()
-
-	want := "http://localhost:8080/photos/cat.jpg"
-	if got != want {
-		t.Errorf("URL() = %q, want %q", got, want)
-	}
-}
-
-func TestSource_URL_AllowHTTPFalse(t *testing.T) {
-	t.Parallel()
-
-	source := Source{
-		Host: testHostCDN,
-		Path: "/img.jpg",
-	}
-
-	got := source.URL(false).String()
-	if got != "https://cdn.example.com/img.jpg" {
-		t.Errorf("URL() = %q, want https scheme", got)
-	}
-}

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
@@ -46,11 +69,16 @@ type CacheConfig struct {
 // Cache implements the caching layer for the image proxy.
 type Cache struct {
 	db          *sql.DB
-	srcContent *ContentStorage // source images by source key
+	srcContent  *ContentStorage  // source images by content hash
 	variants    *VariantStorage  // processed variants by cache key
+	srcMetadata *MetadataStorage // source metadata by host/path
 	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.
 	// evictionCancel, set by StartEviction, cancels the eviction
@@ -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
+	headersJSON, err := json.Marshal(result.Headers)
-			size_bytes = excluded.size_bytes,
-			last_accessed_at = CURRENT_TIMESTAMP
-	`, string(key), size)
 	if err != nil {
-		deleteErr := c.srcContent.Delete(key)
+		return "", fmt.Errorf("failed to marshal response headers: %w", err)
-		if deleteErr != nil {
-			c.log.Warn("failed to remove source file whose row was not written",
-				"source_key", key, "error", deleteErr)
 	}
 
+	_, 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 between a store's writing of the variant file and of its
+// .meta file, 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 +1,89 @@
+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)
+
+	// gosec cannot see that min() above bounds computed, so it reads
+	// this conversion as potentially overflowing. It cannot: computed is
+	// at most math.MaxInt64 on every path here.
+	//nolint:gosec // G115: clamped to MaxInt64 by min above
+	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

@@ -15,8 +15,6 @@ 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"
 )
 
@@ -36,7 +34,7 @@ type heldFetcher struct {
 }
 
 func (f *heldFetcher) Fetch(
-	ctx context.Context, source imagerequest.Source,
+	ctx context.Context, url string,
 ) (*httpfetcher.FetchResult, error) {
 	f.fetches.Add(1)
 
@@ -48,7 +46,7 @@ func (f *heldFetcher) Fetch(
 		return nil, ctx.Err()
 	}
 
-	return f.upstream.Fetch(ctx, source)
+	return f.upstream.Fetch(ctx, url)
 }
 
 // releaseFetches lets every held fetch, and every later one, go on.
@@ -79,22 +77,16 @@ 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, which a test
+// given quality and fit mode. Each call returns a new request, as Get writes
-// may change.
+// 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,
-		},
-		Transform: imagerequest.Transform{
-			Size:    imagerequest.Size{Width: 50, Height: 25},
-			Format:  imagerequest.FormatJPEG,
 		Quality:    quality,
 		FitMode:    fit,
-		},
 	}
 }
 
@@ -107,7 +99,7 @@ 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 +145,7 @@ 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 +183,9 @@ 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 +198,9 @@ 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 +252,12 @@ 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 +299,11 @@ 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 +330,8 @@ 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 +345,8 @@ 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 +355,9 @@ 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 +399,7 @@ 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 +423,7 @@ 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:
@@ -444,52 +435,11 @@ func TestService_Get_ReturnsByItsDeadline(t *testing.T) {
 	}
 }
 
-// TestService_Get_WaiterGetsProcessingTimedOut has a request with no deadline
-// join the held fetch of a first request with a short one. With the only
-// processing slot held, the first request's transcode waits for it until the
-// first request's deadline ends, and stops then. The waiting request, whose
-// own context has not ended, must get ErrProcessingTimedOut, which the image
-// routes answer 503 as when pixa is busy.
-func TestService_Get_WaiterGetsProcessingTimedOut(t *testing.T) {
-	t.Parallel()
-
-	svc, fixtures, fetcher := setupHeldFetchService(t)
-	svc.processor = imageprocessor.New(
-		imageprocessor.Params{MaxInputBytes: 50 << 20, MaxConcurrentProcessing: 1},
-	)
-
-	holdProcessingSlot(t, svc.processor)
-
-	const firstTimeout = 500 * time.Millisecond
-
-	firstCtx, cancelFirst := context.WithTimeout(t.Context(), firstTimeout)
-	defer cancelFirst()
-
-	first := startGet(firstCtx, svc, photoVariant(fixtures, 85, imagerequest.FitCover))
-
-	<-fetcher.started
-
-	waiter := startGet(t.Context(), svc, photoVariant(fixtures, 85, imagerequest.FitCover))
-
-	time.Sleep(arrivalWait)
-	fetcher.releaseFetches()
-
-	t.Logf("first request: Get() error = %v", (<-first).err)
-
-	got := <-waiter
-	t.Logf("waiting request: Get() error = %v", got.err)
-
-	if !errors.Is(got.err, ErrProcessingTimedOut) {
-		t.Errorf("waiting request: Get() error = %v, want %v",
-			got.err, ErrProcessingTimedOut)
-	}
-}
-
 // panickingFetcher panics on every fetch.
 type panickingFetcher struct{}
 
 func (panickingFetcher) Fetch(
-	context.Context, imagerequest.Source,
+	context.Context, string,
 ) (*httpfetcher.FetchResult, error) {
 	panic("upstream fetcher panicked")
 }
@@ -512,7 +462,7 @@ 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 +499,7 @@ 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

@@ -3,15 +3,13 @@ package imgcache
 import (
 	"context"
 	"database/sql"
-	"errors"
+	"encoding/json"
 	"fmt"
 	"io/fs"
 	"os"
 	"path/filepath"
 	"strings"
 	"time"
-
-	"sneak.berlin/go/pixa/internal/imagerequest"
 )
 
 // DefaultEvictionInterval is how often the background evictor checks
@@ -19,14 +17,6 @@ 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 +41,27 @@ 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 +73,20 @@ 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 +149,7 @@ 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 +168,7 @@ 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 +231,7 @@ 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 +248,9 @@ 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 +267,14 @@ 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 +287,19 @@ 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 +308,117 @@ 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 +426,7 @@ 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 +437,10 @@ 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 +481,7 @@ 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 +493,16 @@ 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 +526,17 @@ 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 +555,20 @@ 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), sweeps stale temp files left
-// size their rows record, sweeps stale temp files left behind by crashed
+// behind by crashed writes, and last checks the total cache usage
-// writes, and last checks the total cache usage against the tables. It
+// against the tables. It reads the tables a page at a time. Running it
-// reads the tables a page at a time.
+// periodically, not just once, bounds how long such drift can
-// Running it periodically, not just once, bounds how long such drift can
+// accumulate unaccounted for on a long-running process to one eviction
-// accumulate unaccounted for on a long-running process to about one
+// interval. Once ctx is cancelled, it stops at the next file or row and
-// eviction interval plus ten times the last pass's time.
+// returns ctx's error.
-// Once ctx is cancelled, it stops at the next file or row and returns
-// ctx's error.
 func (c *Cache) reconcileAccounting(ctx context.Context) error {
-	if c.config.MaxBytes == 0 {
+	if c.disabled {
 		return nil
 	}
 
@@ -511,19 +587,19 @@ 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, adopting
-// sweeping stale temp files and passing each other file, with its name, to
+// files without accounting rows and sweeping stale temp files.
-// reconcileFile. Once ctx is cancelled it stops at the next file and
+func (c *Cache) reconcileVariantFiles(ctx context.Context) error {
-// returns ctx's 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()
@@ -541,67 +617,46 @@ func (c *Cache) reconcileFiles(
 				return nil
 			}
 
-			return reconcileFile(path, entry, name)
+			if strings.HasSuffix(name, variantMetaSuffix) {
-		},
-	)
-}
-
-// 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,
-) error {
-	info, err := entry.Info()
-	if err != nil {
-		return fmt.Errorf("failed to stat variant file: %w", err)
-	}
-
-	var recordedSize int64
-
-	err = c.db.QueryRowContext(ctx,
-		`SELECT size_bytes FROM variant_content WHERE cache_key = ?`, string(cacheKey),
-	).Scan(&recordedSize)
-
-	switch {
-	case errors.Is(err, sql.ErrNoRows) && info.Size() > 0:
-		return c.adoptVariantFile(ctx, 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:
 				return nil
 			}
 
-	// The file is empty, or not the size its row records
+			return c.adoptVariantFile(ctx, path, entry, VariantKey(name))
-	c.log.Warn("removing damaged cached variant file", "path", path,
+		},
-		"file_bytes", info.Size(), "recorded_bytes", recordedSize)
+	)
-
-	return c.evictVariant(ctx, cacheKey)
 }
 
 // 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, entry fs.DirEntry, cacheKey VariantKey,
 ) error {
-	modTime := info.ModTime().UTC().Format(sqliteTimestampLayout)
+	var rowExists int
 
-	_, err := c.db.ExecContext(ctx, `
+	err := c.db.QueryRowContext(ctx,
-		INSERT INTO variant_content (cache_key, size_bytes, last_accessed_at)
+		`SELECT COUNT(*) FROM variant_content WHERE cache_key = ?`, string(cacheKey),
-		VALUES (?, ?, ?)
+	).Scan(&rowExists)
-	`, string(cacheKey), info.Size(), modTime)
+	if err != nil {
+		return fmt.Errorf("failed to check variant accounting row: %w", err)
+	}
+
+	if rowExists > 0 {
+		return nil
+	}
+
+	info, err := entry.Info()
+	if err != nil {
+		return fmt.Errorf("failed to stat variant file: %w", err)
+	}
+
+	modTime := info.ModTime().UTC().Format(sqliteTimestampLayout)
+	contentType := c.variantContentTypeFromSidecar(path)
+
+	_, err = c.db.ExecContext(ctx, `
+		INSERT INTO variant_content
+			(cache_key, size_bytes, content_type, created_at, last_accessed_at)
+		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 +667,27 @@ 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 +728,9 @@ 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)
@@ -699,78 +771,135 @@ func queryStringColumn[T ~string](
 	return values, nil
 }
 
-// reconcileSourceFiles walks the source content directory, checking
+// reconcileSourceFiles walks the source content directory, removing
-// each blob file against its source_content row (reconcileSourceFile)
+// blob files the database does not track (they are unreachable: source
-// and sweeping stale temp files.
+// lookups always go through source_metadata) 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()
-
-// reconcileSourceFile checks one source blob file against its
-// source_content row. A file without a row is removed, as no lookup
-// serves it and no eviction removes it. 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 source is
-// fetched again.
-func (c *Cache) reconcileSourceFile(
-	ctx context.Context, path string, entry fs.DirEntry, key imagerequest.SourceKey,
-) error {
-	info, err := entry.Info()
-	if err != nil {
-		return fmt.Errorf("failed to stat source content file: %w", err)
 			}
 
-	var recordedSize int64
+			if err != nil || entry.IsDir() {
+				return err
+			}
 
-	err = c.db.QueryRowContext(ctx,
+			name := entry.Name()
-		`SELECT size_bytes FROM source_content WHERE source_key = ?`,
+
-		string(key),
+			if strings.HasPrefix(name, tempFilePrefix) {
-	).Scan(&recordedSize)
+				c.sweepStaleTempFile(path, entry)
 
-	switch {
-	case errors.Is(err, sql.ErrNoRows):
-		return c.removeUntrackedSourceFile(path, key)
-	case err != nil:
-		return fmt.Errorf("failed to check source content row: %w", err)
-	case info.Size() > 0 && info.Size() == recordedSize:
 				return nil
 			}
 
-	// The file is empty, or not the size its row records
+			return c.removeUntrackedSourceFile(ctx, path, ContentHash(name))
-	c.log.Warn("removing damaged cached source file", "path", path,
+		},
-		"file_bytes", info.Size(), "recorded_bytes", recordedSize)
+	)
-
-	return c.evictSourceBlob(ctx, key)
 }
 
 // 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)
+	var rowExists int
+
+	err := c.db.QueryRowContext(ctx,
+		`SELECT COUNT(*) FROM source_content WHERE content_hash = ?`, string(contentHash),
+	).Scan(&rowExists)
+	if err != nil {
+		return fmt.Errorf("failed to check source content row: %w", err)
+	}
+
+	if rowExists > 0 {
+		return nil
+	}
+
+	_, 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(*)