State the UUID-is-the-credential rule as a rule (closes #301)

The receiver has authenticated on the entrypoint UUID alone since
inbound signature verification was removed in #279. The README
described that as the current state; it did not say it is the
decision. Restate it as the rule, so a proposal to add HMAC, a shared
secret or a bearer token to the receiver is contradicted by the docs
rather than merely unimplemented.

The rule now appears in the intro, in its own section, and in the
Authentication and Security lists, and carries the two consequences an
operator has to act on: the URL is a capability to be kept out of logs
and tickets, and rotation means minting a new entrypoint rather than
changing a key.

Also corrects one stale comment: a redirect test said the inbound
signature was one "the receiver verifies", which in this repo's
vocabulary names webhooker's own receiver. The endpoint that verifies
it is the delivery target's.

Dockerfile

@@ -61,14 +61,28 @@ RUN script/fetch-assets
 
 # Run tests and build
 RUN make test
-RUN make build
+
+# Version stamped into the binary. .dockerignore excludes .git/, so
+# nothing in this stage can derive it: script/docker resolves it on the
+# host and passes it in. The default is what a bare `docker build .`
+# with no --build-arg gets, and it names no tag the tree may not be at.
+#
+# Declared here, below the test and asset steps, so a changed version
+# does not invalidate their cached layers.
+ARG VERSION=unknown
+
+RUN make build VERSION="$VERSION"
 
 # Rebuild with static linking for Alpine runtime.
 # make build already verified compilation.
 # The CGO binary from `make build` is dynamically linked against glibc,
 # which doesn't exist on Alpine (musl). Rebuild with static linking so
 # the binary runs on Alpine without glibc.
-RUN CGO_ENABLED=1 go build -ldflags '-extldflags "-static"' -o bin/webhooker ./cmd/webhooker
+#
+# The static flags go in through GO_LDFLAGS rather than a -ldflags of
+# their own: the build target composes them with the -X that stamps the
+# version, so this relink cannot silently drop the stamp.
+RUN CGO_ENABLED=1 make build VERSION="$VERSION" GO_LDFLAGS='-extldflags "-static"'
 
 # Runtime stage
 # alpine:3.21, 2026-03-17
@@ -95,6 +109,18 @@ USER webhooker
 
 EXPOSE 8080
 
+# The binary defaults BIND_ADDRESS to 127.0.0.1, which is right for a
+# bare host: the cleartext listener serves the admin UI and the
+# unauthenticated receiver, so it must not appear on every interface
+# of a machine that configured nothing. A container is the other case.
+# Its network namespace is already the isolation boundary, so binding
+# every address inside it exposes nothing; what decides exposure is
+# the publish flag, and `-p 127.0.0.1:8080:8080` is the operator's
+# control there. Shipping the image on loopback would buy no security
+# and would make the process unreachable through its own published
+# port.
+ENV BIND_ADDRESS=0.0.0.0
+
 HEALTHCHECK --interval=30s --timeout=3s --start-period=5s --retries=3 \
     CMD wget --no-verbose --tries=1 --spider http://localhost:8080/.well-known/healthcheck || exit 1
 

Makefile

@@ -1,8 +1,26 @@
-.PHONY: bootstrap setup assets test lint fmt fmt-check check build run dev deps docker clean hooks css
+.PHONY: bootstrap setup assets test lint fmt fmt-check check build run dev deps docker clean hooks css version
 
 # Default target
 .DEFAULT_GOAL := check
 
+# Version stamped into the binary. Derived from git by script/version;
+# override it (`make build VERSION=v1.2.3`) where git metadata is
+# unavailable, which is how the Dockerfile passes its build arg in.
+VERSION ?= $(shell script/version)
+
+# An empty override (`make build VERSION=`, or a `--build-arg VERSION=`
+# landing on the Dockerfile's `make build VERSION="$VERSION"`) means unset,
+# exactly as it does in script/version -- stamping "" would leave the binary
+# reporting no version and the footer back on its "dev" fallback. `override`
+# is required: a plain assignment loses to the command-line definition it
+# exists to correct.
+override VERSION := $(or $(strip $(VERSION)),$(shell script/version))
+
+# Extra linker flags for the build target. The static relink in the
+# Dockerfile adds -extldflags here rather than passing its own -ldflags,
+# so composing flags cannot drop the version stamp.
+GO_LDFLAGS ?=
+
 bootstrap:
 	@script/bootstrap
 
@@ -28,7 +46,7 @@ check:
 	@script/check
 
 build:
-	go build -o bin/webhooker ./cmd/webhooker
+	go build -ldflags '$(strip -X main.version=$(VERSION) $(GO_LDFLAGS))' -o bin/webhooker ./cmd/webhooker
 
 run: build
 	./bin/webhooker
@@ -40,6 +58,9 @@ deps:
 	go mod download
 	go mod tidy
 
+version:
+	@echo $(VERSION)
+
 docker:
 	@script/docker
 

TODO.md

@@ -18,29 +18,27 @@ Issue branches do NOT touch this file — the manager maintains it on
 
 # Status
 
-1.0.0 is complete: 55 closed, 0 open. `next` (6874059) is 62 commits
+The milestone (https://git.eeqj.de/sneak/webhooker/milestone/9) is the
-ahead of `main` and a strict fast-forward. No git tags exist yet.
+authoritative list, and the only place to read a count or a state of
+play from. This file records where the project is, not what is in
+flight: a sentence whose truth depends on a branch being unmerged is
+wrong the moment it merges, and this file has been wrong that way
+before.
 
-The bar was not "the milestone is empty" but "sneak can deploy this and
+The durability defect that held the tag has landed
-use it in low-volume production". Every gap the deployability audit
+(https://git.eeqj.de/sneak/webhooker/issues/256, commit `8d64259`).
-named against that bar is now closed:
+Every SQLite handle opens with WAL journaling and a busy timeout, a
+bookkeeping write that fails leaves its delivery in a recoverable
+state rather than a lying one, and recovery skips a delivery that
+already has a successful result row. Final pre-tag verification
+exercised it and confirmed it holds. Whatever the milestone still
+shows open is what remains before `v1.0.0`.
 
-- `DATA_DIR` locking, so two instances cannot both deliver
+Delivery is at-least-once by design, not by accident: a send whose
-  (https://git.eeqj.de/sneak/webhooker/issues/201)
+result row does not land is attempted again, so a receiver can see a
-- shutdown on listener failure, rather than a live non-serving process
+duplicate. That is deliberate — the alternative is a silent lost
-  (https://git.eeqj.de/sneak/webhooker/issues/200)
+delivery — and the README says so under Rationale. It is not a defect
-- inbound signature verification
+to re-file.
-  (https://git.eeqj.de/sneak/webhooker/issues/67)
-- per-attempt delivery detail in the event log
-  (https://git.eeqj.de/sneak/webhooker/issues/202)
-- replay of a terminally failed delivery
-  (https://git.eeqj.de/sneak/webhooker/issues/203)
-- `ALLOWED_EGRESS_CIDRS`, an allowlist escape hatch for the SSRF guard
-  (https://git.eeqj.de/sneak/webhooker/issues/204)
-- the three credential exposures
-  (https://git.eeqj.de/sneak/webhooker/issues/205,
-  https://git.eeqj.de/sneak/webhooker/issues/206,
-  https://git.eeqj.de/sneak/webhooker/issues/207)
 
 One caveat on reading a green check: a docs-only commit deliberately
 replays from the layer cache
@@ -50,23 +48,129 @@ commit invalidates the `COPY` layer and genuinely executes.
 
 # Next Step
 
-Merge the milestone PR (https://git.eeqj.de/sneak/webhooker/pulls/111)
+Clear the rest of the open 1.0.0 milestone
-and tag `v1.0.0`. It is `merge-ready` and assigned to sneak; nothing
+(https://git.eeqj.de/sneak/webhooker/milestone/9) and tag `v1.0.0`.
-else gates it.
+Merging `next` into `main` is a separate act from tagging and waits on
-
+neither of those: `next` is kept mergeable at all times, which is the
-Post-1.0 follow-ups are open, none blocking the tag:
+point of the branch.
-https://git.eeqj.de/sneak/webhooker/issues/245,
-https://git.eeqj.de/sneak/webhooker/issues/246,
-https://git.eeqj.de/sneak/webhooker/issues/247 and
-https://git.eeqj.de/sneak/webhooker/issues/248. Also still open and
-unmilestoned: https://git.eeqj.de/sneak/webhooker/issues/193 (a design
-question, not a defect), https://git.eeqj.de/sneak/webhooker/issues/198
-(`make test` is past the org 20s target) and
-https://git.eeqj.de/sneak/webhooker/issues/212 (encrypting target config
-at rest).
 
 # Completed Steps
 
+- 2026-08-24 Bind the plaintext HTTP listener deliberately, via
+  `BIND_ADDRESS` defaulting to `127.0.0.1`, and document the
+  reverse-proxy deployment. A hostname, an empty value or a value
+  carrying a port is a startup error, and the `Dockerfile` sets
+  `0.0.0.0` because a loopback bind inside a container is unreachable
+  (https://git.eeqj.de/sneak/webhooker/issues/268). The same commit
+  removed the shutdown race: `httpServer` is built in the constructor
+  rather than assigned from the serving goroutine, which orders the
+  write before every fx hook and rules out the nil dereference a
+  SIGTERM arriving first would have caused, and `sentryEnabled` is an
+  `atomic.Bool` (https://git.eeqj.de/sneak/webhooker/issues/226)
+- 2026-08-24 Remove inbound request signature verification. The
+  entrypoint UUID is the authentication secret, so the per-entrypoint
+  shared secret, the `internal/signature` package, the receiver check,
+  the model fields and the forms are all gone. This reverses the
+  feature that landed earlier in the same milestone
+  (https://git.eeqj.de/sneak/webhooker/issues/67,
+  https://git.eeqj.de/sneak/webhooker/issues/279)
+- 2026-08-24 Stamp the build version into the binary and render it in
+  the UI footer. `script/version` is the single source — `$VERSION`,
+  else `git describe --tags --always --dirty`, else `unknown` — so a
+  `make build` binary and a `make docker` image from one checkout
+  report the same thing, and nothing in it varies between two builds
+  of the same commit, which the release gate's byte-identical
+  assertion would catch
+  (https://git.eeqj.de/sneak/webhooker/issues/253)
+- 2026-08-24 Derive cookie `Secure` and CSRF strictness from the
+  request transport rather than from `WEBHOOKER_ENVIRONMENT`. Behind a
+  real TLS proxy with the environment left at its `dev` default, the
+  session cookie silently lost `Secure` while the CSRF cookie on the
+  same response kept it. `X-Forwarded-Proto` is now matched
+  case-insensitively on its first comma-separated element, so `HTTPS`
+  and `https, http` no longer fall to the relaxed CSRF path
+  (https://git.eeqj.de/sneak/webhooker/issues/269)
+- 2026-08-24 Roll back a failed webhook deletion instead of committing
+  it. A failing delete committed whatever had already succeeded,
+  hard-deleted the per-webhook event database anyway, and redirected as
+  though it had worked — orphaned config plus permanently destroyed
+  history, reported as success. All three delete positions now roll
+  back with the event database intact
+  (https://git.eeqj.de/sneak/webhooker/issues/262)
+- 2026-08-24 Name a deleted target on its historical deliveries, marked
+  `(deleted)`, rather than leaving the event log unable to say where a
+  delivery went. A deleted target's credentials stay masked exactly as
+  a live one's, and it cannot become deliverable again through the
+  receiver, resubmit, replay, the edit form or the toggle
+  (https://git.eeqj.de/sneak/webhooker/issues/211)
+- 2026-08-24 Bound both request-controlled `/metrics` label dimensions,
+  so the unauthenticated receiver is no longer a memory-exhaustion
+  vector: `handler` carries the chi route pattern, and `method` folds
+  anything chi cannot route onto a single `(unmatched)` sentinel. Both
+  were reproduced before the fix — 300 random method tokens took the
+  series count from 106 to 7,631, and path flooding reached 62,532 —
+  and a label audit across a live scrape found no third unbounded
+  dimension (https://git.eeqj.de/sneak/webhooker/issues/254,
+  https://git.eeqj.de/sneak/webhooker/issues/261)
+- 2026-08-24 Validate `max_retries` on both target forms. `abc`, `2.7`
+  and `-5` silently became 0 — fire-and-forget — including on the edit
+  path, where it destroyed a working value, and `999999999` stored
+  verbatim. The ceiling of 20 is the `max` both templates already
+  declared (https://git.eeqj.de/sneak/webhooker/issues/221)
+- 2026-08-24 Resubmit a stored event as a new undelivered event, so a
+  backend under development can be tested against real captured
+  traffic. Per-delivery replay cannot serve that: it re-sends one
+  finished delivery to its own original target, and a target created
+  for a dev backend has no prior delivery to replay. Resubmit
+  re-injects the stored event at the top of the receiver path and fans
+  it out to whatever targets are active now
+  (https://git.eeqj.de/sneak/webhooker/issues/250)
+- 2026-08-20 Take an exclusive lock on `DATA_DIR` at startup, so two
+  instances on one directory cannot both deliver
+  (https://git.eeqj.de/sneak/webhooker/issues/201)
+- 2026-08-20 Shut down the app when the HTTP listener fails. The
+  `OnStart` hook returned as soon as the serving goroutine was
+  spawned, so a failed listen left fx reporting RUNNING and a live
+  process with nothing bound — invisible to systemd and Docker restart
+  policies (https://git.eeqj.de/sneak/webhooker/issues/200)
+- 2026-08-20 Stop target credentials leaking into the per-webhook event
+  databases (https://git.eeqj.de/sneak/webhooker/issues/206), log SQL
+  with placeholders rather than bound values
+  (https://git.eeqj.de/sneak/webhooker/issues/207), and fail loudly on
+  half-set metrics auth credentials
+  (https://git.eeqj.de/sneak/webhooker/issues/205)
+- 2026-08-20 Read queue depths with `Find`, not `Scan`. `Scan` swaps
+  GORM's own trace recorder in for the logging adapter, and that
+  recorder does not implement `gorm.ParamsFilter`, so those statements
+  logged their bound values interpolated and bypassed the suppression
+  above. The two units gated green against a `next` that lacked the
+  other, and `next` went red when both landed
+  (https://git.eeqj.de/sneak/webhooker/issues/234)
+- 2026-08-20 Render per-attempt delivery detail in the event log
+  (https://git.eeqj.de/sneak/webhooker/issues/202) and add replay of a
+  terminally failed delivery
+  (https://git.eeqj.de/sneak/webhooker/issues/203)
+- 2026-08-20 Expose delivery metrics on `/metrics`
+  (https://git.eeqj.de/sneak/webhooker/issues/209) and document the
+  backup, restore and upgrade procedures
+  (https://git.eeqj.de/sneak/webhooker/issues/210)
+- 2026-08-20 Add a `webhooker resetpw` subcommand and a bootstrap
+  banner. The admin bootstrap password was printed once among roughly
+  45 fx lines, and under `docker run -d` went to container logs subject
+  to rotation; there was no reset path at all, so recovery meant
+  hand-deleting the users row, documented nowhere. The password is read
+  from stdin or generated, never from argv where `/proc` would publish
+  it (https://git.eeqj.de/sneak/webhooker/issues/208)
+- 2026-08-20 Add `ALLOWED_EGRESS_CIDRS`, an allowlist-only escape hatch
+  for the SSRF guard, so a self-hosted proxy can forward into the
+  operator's own network. The guard's always-blocked set cannot be
+  reopened by configuration
+  (https://git.eeqj.de/sneak/webhooker/issues/204)
+- 2026-08-20 Harden operator-set target headers, which were carried
+  unsafely across a redirect
+  (https://git.eeqj.de/sneak/webhooker/issues/233)
+- 2026-08-20 Add a target edit form with headers and timeout fields
+  (https://git.eeqj.de/sneak/webhooker/issues/127)
 - 2026-08-18 Raise `script/test`'s per-package timeout from 30s to 90s,
   matching the org-wide backstop. `go test` applies `-timeout` per
   package, and `internal/handlers` had grown past the old budget: a
@@ -299,9 +403,6 @@ at rest).
 - Per-webhook rate limiting in the receiver handler (per-webhook config
   plus handler enforcement; global limits must not apply to receiver
   endpoints)
-- Stripe HMAC signature verification. The GitHub and GitLab schemes
-  landed with inbound verification
-  (https://git.eeqj.de/sneak/webhooker/issues/67)
 - API key authentication for programmatic access (APIKey model exists;
   Bearer token middleware does not)
 - REST API v1

cmd/webhooker/dotenv_test.go

@@ -0,0 +1,107 @@
+package main
+
+import (
+	"bytes"
+	"os"
+	"path/filepath"
+	"strings"
+	"testing"
+
+	"github.com/stretchr/testify/assert"
+	"github.com/stretchr/testify/require"
+	"sneak.berlin/go/webhooker/internal/config"
+)
+
+// dotEnvKey is a throwaway variable name these tests write and read,
+// so they cannot disturb real configuration.
+const dotEnvKey = "WEBHOOKER_TEST_DISPATCH_VALUE"
+
+// writeDotEnvInWorkingDir puts contents in a .env file in a fresh
+// temporary directory and moves the process there.
+//
+// The callers are deliberately not parallel and must stay that way:
+// t.Chdir moves the whole process. Go releases parallel tests only
+// after every sequential test in the package has finished, so nothing
+// else runs while these do.
+func writeDotEnvInWorkingDir(t *testing.T, contents string) {
+	t.Helper()
+
+	dir := t.TempDir()
+	require.NoError(t, os.WriteFile(
+		filepath.Join(dir, config.DotEnvPath),
+		[]byte(contents), 0o600,
+	))
+	t.Chdir(dir)
+}
+
+// TestDispatch_MalformedDotEnvRefuses pins the second half of the
+// defect. godotenv applies nothing at all when a file will not parse,
+// so one mistyped line used to revert every variable in it to its
+// default and start the server anyway, with no log line naming the
+// file. The refusal has to arrive before any subcommand runs, which
+// is why `help` — the one subcommand that touches nothing — is still
+// refused here.
+//
+//nolint:paralleltest // t.Chdir moves the whole process.
+func TestDispatch_MalformedDotEnvRefuses(t *testing.T) {
+	writeDotEnvInWorkingDir(t, "PORT 19615\n")
+
+	var stdout, stderr bytes.Buffer
+
+	code := dispatch(
+		[]string{helpCommand}, strings.NewReader(""), &stdout, &stderr,
+	)
+
+	require.Equal(t, 1, code, "a broken .env must exit non-zero")
+	assert.Contains(
+		t, stderr.String(), config.DotEnvPath,
+		"the refusal must name the file",
+	)
+	assert.Empty(
+		t, stdout.String(),
+		"the subcommand must not have run",
+	)
+}
+
+// TestDispatch_LoadsDotEnvBeforeSubcommands pins the ordering the
+// godotenv/autoload import used to provide for free. It ran in an
+// init(), so .env was in the environment before anything read it —
+// including config.DataDir, which both the DATA_DIR lock and resetpw
+// call outside the fx graph. Loading any later would let a .env that
+// sets DATA_DIR lock one directory while the config opened databases
+// in another.
+func TestDispatch_LoadsDotEnvBeforeSubcommands(t *testing.T) {
+	t.Setenv(dotEnvKey, "placeholder")
+	require.NoError(t, os.Unsetenv(dotEnvKey))
+
+	writeDotEnvInWorkingDir(t, dotEnvKey+"=from-dot-env\n")
+
+	var stdout, stderr bytes.Buffer
+
+	code := dispatch(
+		[]string{helpCommand}, strings.NewReader(""), &stdout, &stderr,
+	)
+
+	require.Equal(t, 0, code)
+	assert.Equal(
+		t, "from-dot-env", os.Getenv(dotEnvKey),
+		"the file must be applied before the subcommand runs",
+	)
+}
+
+// TestDispatch_MissingDotEnvIsFine pins the case most deployments are
+// in: no .env at all, which must stay a normal start.
+//
+//nolint:paralleltest // t.Chdir moves the whole process.
+func TestDispatch_MissingDotEnvIsFine(t *testing.T) {
+	t.Chdir(t.TempDir())
+
+	var stdout, stderr bytes.Buffer
+
+	code := dispatch(
+		[]string{helpCommand}, strings.NewReader(""), &stdout, &stderr,
+	)
+
+	require.Equal(t, 0, code)
+	assert.Empty(t, stderr.String())
+}

cmd/webhooker/main.go

@@ -54,6 +54,11 @@ const stopTimeout = 5 * time.Second
 // caller can tell "called wrong" from "declined".
 const exitUsage = 2
 
+// helpCommand is the subcommand that prints usage. The flag spellings
+// beside it in the switch are aliases; this is the name the usage text
+// documents and the one tests invoke.
+const helpCommand = "help"
+
 // Build-time variables set via -ldflags.
 //
 //nolint:gochecknoglobals // Build-time variables injected by the linker.
@@ -75,11 +80,27 @@ func main() {
 // every existing deployment invoke; that path is unchanged, including
 // where the DATA_DIR lock is taken relative to building the fx graph
 // and how fx propagates a non-zero exit itself.
+//
+// The optional .env file is read here, before any subcommand and so
+// before anything reads the environment — config.DataDir, which both
+// the DATA_DIR lock and resetpw call outside the fx graph, above all.
+// It used to be read from an init() in internal/config, which put it
+// earlier still but threw the error away: a single malformed line
+// applied none of the file and said nothing about it. A file that is
+// not there stays fine, since .env is optional and most deployments
+// do not have one.
 func dispatch(
 	args []string,
 	stdin io.Reader,
 	stdout, stderr io.Writer,
 ) int {
+	err := config.LoadDotEnv()
+	if err != nil {
+		_, _ = fmt.Fprintf(stderr, "%s: %v\n", appname, err)
+
+		return 1
+	}
+
 	if len(args) == 0 {
 		return run(stderr)
 	}
@@ -87,7 +108,7 @@ func dispatch(
 	switch args[0] {
 	case resetpw.Name:
 		return resetpw.Run(args[1:], stdin, stdout, stderr)
-	case "help", "-h", "-help", "--help":
+	case helpCommand, "-h", "-help", "--help":
 		usage(stdout)
 
 		return 0

cmd/webhooker/main_test.go

@@ -121,7 +121,7 @@ func TestDispatch_Help(t *testing.T) {
 	var stdout, stderr bytes.Buffer
 
 	code := dispatch(
-		[]string{"help"}, strings.NewReader(""), &stdout, &stderr,
+		[]string{helpCommand}, strings.NewReader(""), &stdout, &stderr,
 	)
 
 	require.Equal(t, 0, code)

internal/config/config.go

@@ -4,6 +4,7 @@ package config
 import (
 	"errors"
 	"fmt"
+	"io/fs"
 	"log/slog"
 	"net/netip"
 	"os"
@@ -11,13 +12,11 @@ import (
 	"strings"
 	"time"
 
+	"github.com/getsentry/sentry-go"
+	"github.com/joho/godotenv"
 	"go.uber.org/fx"
 	"sneak.berlin/go/webhooker/internal/globals"
 	"sneak.berlin/go/webhooker/internal/logger"
-
-	// Populates the environment from a ./.env file automatically for
-	// development configuration. Kept in one place only (here).
-	_ "github.com/joho/godotenv/autoload"
 )
 
 const (
@@ -33,6 +32,34 @@ const (
 	// defaultPort is the default HTTP listen port.
 	defaultPort = 8080
 
+	// defaultBindAddress is the interface the plaintext HTTP
+	// listener claims when BIND_ADDRESS is unset.
+	//
+	// Loopback, because the listener speaks cleartext and serves
+	// both the admin UI and the unauthenticated receiver: a
+	// wildcard default publishes them on every interface of every
+	// host that never configured anything, which is the failure
+	// this default exists to prevent. Reaching webhooker from off
+	// the host is then a deliberate act — a reverse proxy in front
+	// of it, or an explicit BIND_ADDRESS.
+	//
+	// This is the binary's default only. The Dockerfile ships
+	// ENV BIND_ADDRESS=0.0.0.0, so a container deployment needs
+	// nothing set and is unaffected by this constant. The two
+	// differ because they answer different questions: a container's
+	// network namespace is already the boundary this default is
+	// reaching for, so binding every address inside it exposes
+	// nothing, and what decides exposure there is the publish flag
+	// (-p 127.0.0.1:8080:8080). A loopback bind inside a container
+	// buys no security and makes the process unreachable through
+	// its own published port.
+	//
+	// The split is expressed as two explicit defaults rather than
+	// container auto-detection, because a heuristic that guesses
+	// wrong opens the cleartext port exactly where nobody is
+	// looking.
+	defaultBindAddress = "127.0.0.1"
+
 	// defaultRetentionSweepInterval is how often the retention
 	// reaper deletes events older than each webhook's RetentionDays.
 	defaultRetentionSweepInterval = time.Hour
@@ -56,6 +83,12 @@ const (
 	// IPv6 prefix spends on the ::ffff:0:0/96 wrapper, so a /104
 	// covers the same addresses as an IPv4 /8.
 	mappedV4Offset = 96
+
+	// DotEnvPath is the optional file of KEY=value lines read into the
+	// environment at startup, relative to the process working
+	// directory. Exported so that documentation and tests name the
+	// same path the loader opens.
+	DotEnvPath = ".env"
 )
 
 // ErrInvalidEnvironment is returned when WEBHOOKER_ENVIRONMENT
@@ -75,6 +108,19 @@ var ErrInvalidPort = errors.New("invalid port")
 // nor a bare IP address.
 var ErrInvalidCIDR = errors.New("invalid CIDR")
 
+// ErrInvalidBindAddress is returned when BIND_ADDRESS is set to
+// something that is not an IP address literal.
+var ErrInvalidBindAddress = errors.New("invalid bind address")
+
+// ErrInvalidSentryDSN is returned when SENTRY_DSN is set to something
+// the Sentry SDK cannot parse as a DSN.
+var ErrInvalidSentryDSN = errors.New("invalid Sentry DSN")
+
+// ErrDotEnvUnreadable is returned when the optional .env file exists
+// but cannot be read or parsed. A file that is not there is not an
+// error; a file that is there and broken is.
+var ErrDotEnvUnreadable = errors.New("unreadable .env file")
+
 // ErrIncompleteMetricsAuth is returned when exactly one of
 // METRICS_USERNAME and METRICS_PASSWORD carries a value. Neither
 // fallback is acceptable: serving /metrics on the username alone
@@ -105,6 +151,13 @@ type Config struct {
 	Port            int
 	SentryDSN       string
 
+	// BindAddress is the IP address the plaintext HTTP listener
+	// binds, as an address literal. It defaults to
+	// defaultBindAddress and is never empty: an empty string would
+	// mean the wildcard to net.Listen, which is the opposite of the
+	// default this ships.
+	BindAddress string
+
 	// RetentionSweepInterval is how often the retention reaper runs.
 	// Always positive: it becomes a time.NewTicker period.
 	RetentionSweepInterval time.Duration
@@ -173,12 +226,62 @@ func (c *Config) MetricsAuthEnabled() bool {
 	return c.MetricsUsername != "" && c.MetricsPassword != ""
 }
 
+// SentryEnabled reports whether error reporting is shipped to Sentry.
+// It is the only answer to that question in the codebase: the SDK
+// initialisation, the sentryhttp middleware registration and the
+// startup log's sentryEnabled field all read this one method, so the
+// log cannot report reporting as on while nothing is sending.
+//
+// A non-empty DSN is enough because loadFromEnv already parsed it with
+// the SDK's own parser and refused to build a Config around one the
+// SDK would reject, and because initialising the SDK with a DSN that
+// parsed and failed anyway aborts the process rather than leaving this
+// true and the client absent.
+func (c *Config) SentryEnabled() bool {
+	return c.SentryDSN != ""
+}
+
 // envString returns the value of the named environment variable,
 // or an empty string if not set.
 func envString(key string) string {
 	return os.Getenv(key)
 }
 
+// LoadDotEnv reads DotEnvPath into the environment when that file is
+// present, and reports a file that is present but broken.
+//
+// It has to run before anything reads the environment, so that every
+// reader agrees on what the environment holds — the DATA_DIR lock
+// taken before the fx graph exists as much as loadFromEnv itself. A
+// variable already set in the real environment wins: godotenv never
+// overwrites one.
+//
+// A missing file is not an error. It is a development convenience and
+// most deployments set the environment directly.
+//
+// Any other failure is. godotenv parses the whole file before setting
+// anything, so a single malformed line applies none of it: every
+// variable in the file silently reverts to its default, which defeats
+// the fail-loud guarantee for all of them at once.
+func LoadDotEnv() error {
+	return loadDotEnvFile(DotEnvPath)
+}
+
+// loadDotEnvFile is LoadDotEnv over a named file, so tests can point
+// at a temporary one instead of the process working directory.
+func loadDotEnvFile(path string) error {
+	err := godotenv.Load(path)
+	if err == nil || errors.Is(err, fs.ErrNotExist) {
+		return nil
+	}
+
+	return fmt.Errorf(
+		"%w: %s: %w; nothing in it was applied, so fix the file or "+
+			"remove it",
+		ErrDotEnvUnreadable, path, err,
+	)
+}
+
 // DataDir resolves DATA_DIR, applying DefaultDataDir when it is unset
 // or empty. It is exported so that entry points which must act on the
 // data directory before the fx graph exists — taking the exclusive
@@ -387,6 +490,77 @@ func envPrefixList(key string) ([]netip.Prefix, error) {
 	return prefixes, nil
 }
 
+// envBindAddress returns the value of the named environment variable
+// parsed as an IP address literal. An unset (or empty, or
+// whitespace-only) value yields defaultValue.
+//
+// Only literals are accepted: no hostname is resolved, so `localhost`
+// is an error rather than a DNS lookup at startup whose answer could
+// be either loopback family, could change under the process, and
+// could return several addresses of which only one would be bound. A
+// value with a port in it (`127.0.0.1:8080`) is likewise an error —
+// the port is PORT's business, and silently accepting it would bind
+// something other than what was asked for.
+//
+// A set value that is not a literal is a hard error naming the key
+// and the bad value, so startup fails loudly rather than falling back
+// to a default the operator plainly did not want. A literal that is
+// not an address of this host parses here and fails at listen time
+// instead, which ends the process non-zero.
+func envBindAddress(key, defaultValue string) (string, error) {
+	v := strings.TrimSpace(os.Getenv(key))
+	if v == "" {
+		return defaultValue, nil
+	}
+
+	addr, err := netip.ParseAddr(v)
+	if err != nil {
+		return "", fmt.Errorf(
+			"%w: %s: %q must be an IP address literal such as "+
+				"127.0.0.1, 0.0.0.0 or ::, not a hostname and not "+
+				"host:port: %w",
+			ErrInvalidBindAddress, key, v, err,
+		)
+	}
+
+	return addr.String(), nil
+}
+
+// envSentryDSN returns the value of the named environment variable
+// checked as a Sentry DSN. An unset (or empty, or whitespace-only)
+// value yields "", which means error reporting stays off — the common
+// case, and a normal start.
+//
+// A set value is parsed with sentry.NewDsn, which is the call
+// sentry.Init makes on the DSN it is handed, so what passes here is
+// exactly what the SDK will accept later and the two cannot disagree.
+// Reproducing the check by hand instead would cost this package its
+// dependency on the SDK — already a module dependency, already linked
+// into the binary — in exchange for a second definition of "valid DSN"
+// free to drift from the one that decides.
+//
+// A set value that does not parse is a hard error naming the key, so
+// startup fails loudly. Losing error reporting is the failure this
+// variable exists to prevent, and a typo in a DSN is silent forever:
+// nothing later in the process can notice that reports are going
+// nowhere. The bad value is quoted because it is a URL to a public
+// endpoint carrying a public key, not a secret.
+func envSentryDSN(key string) (string, error) {
+	v := strings.TrimSpace(os.Getenv(key))
+	if v == "" {
+		return "", nil
+	}
+
+	_, err := sentry.NewDsn(v)
+	if err != nil {
+		return "", fmt.Errorf(
+			"%w: %s: %q: %w", ErrInvalidSentryDSN, key, v, err,
+		)
+	}
+
+	return v, nil
+}
+
 // resolveMetricsAuth reads the /metrics basic-auth credentials and
 // rejects a half-set pair, naming both variables either way. The
 // error carries neither value: the password is a secret.
@@ -431,6 +605,27 @@ func resolveEnvironment() (string, error) {
 	return environment, nil
 }
 
+// resolveListener reads the two variables that describe the HTTP
+// listener: which port it claims and which address it claims it on.
+// They are read together because neither is meaningful alone, and
+// because a validation failure in either has to abort startup before
+// anything binds.
+func resolveListener() (int, string, error) {
+	port, err := envPort("PORT", defaultPort)
+	if err != nil {
+		return 0, "", err
+	}
+
+	bindAddress, err := envBindAddress(
+		"BIND_ADDRESS", defaultBindAddress,
+	)
+	if err != nil {
+		return 0, "", err
+	}
+
+	return port, bindAddress, nil
+}
+
 // loadFromEnv builds a Config from the environment. Every value that
 // needs parsing fails loudly when it is set but unparseable: the
 // documented defaults apply only to variables that are unset (or
@@ -442,7 +637,7 @@ func loadFromEnv() (*Config, error) {
 		return nil, err
 	}
 
-	port, err := envPort("PORT", defaultPort)
+	port, bindAddress, err := resolveListener()
 	if err != nil {
 		return nil, err
 	}
@@ -498,6 +693,11 @@ func loadFromEnv() (*Config, error) {
 		return nil, err
 	}
 
+	sentryDSN, err := envSentryDSN("SENTRY_DSN")
+	if err != nil {
+		return nil, err
+	}
+
 	return &Config{
 		DataDir:                DataDir(),
 		Debug:                  debug,
@@ -506,7 +706,8 @@ func loadFromEnv() (*Config, error) {
 		MetricsUsername:        metricsUsername,
 		MetricsPassword:        metricsPassword,
 		Port:                   port,
-		SentryDSN:              envString("SENTRY_DSN"),
+		BindAddress:            bindAddress,
+		SentryDSN:              sentryDSN,
 		RetentionSweepInterval: retentionSweepInterval,
 		SessionIdleTimeout:     sessionIdleTimeout,
 		ReceiverRateLimit:      receiverRateLimit,
@@ -625,6 +826,11 @@ func New(lc fx.Lifecycle, params ConfigParams) (*Config, error) {
 	log.Info("Configuration loaded",
 		"environment", s.Environment,
 		"port", s.Port,
+		// Logged because which interfaces the cleartext listener
+		// answers on is not otherwise observable from inside a
+		// container, and it decides whether anything but the local
+		// host can reach the admin UI.
+		"bindAddress", s.BindAddress,
 		"debug", s.Debug,
 		"maintenanceMode", s.MaintenanceMode,
 		"dataDir", s.DataDir,
@@ -636,7 +842,7 @@ func New(lc fx.Lifecycle, params ConfigParams) (*Config, error) {
 		"receiverRateLimit", s.ReceiverRateLimit,
 		"trustedProxies", len(s.TrustedProxies),
 		"allowedEgressCIDRs", len(s.AllowedEgressCIDRs),
-		"hasSentryDSN", s.SentryDSN != "",
+		"sentryEnabled", s.SentryEnabled(),
 		"hasMetricsAuth", s.MetricsAuthEnabled(),
 	)
 

internal/config/dotenv_test.go

@@ -0,0 +1,158 @@
+package config_test
+
+import (
+	"os"
+	"path/filepath"
+	"testing"
+
+	"github.com/stretchr/testify/assert"
+	"github.com/stretchr/testify/require"
+	"sneak.berlin/go/webhooker/internal/config"
+)
+
+// dotEnvKey is a throwaway variable name the .env tests write and
+// read, so they cannot disturb real configuration.
+const dotEnvKey = "WEBHOOKER_TEST_DOTENV_VALUE"
+
+// malformedDotEnv is a file godotenv cannot parse. The first line is
+// the realistic typo — a space where the `=` belongs — and the rest
+// make sure nothing downstream treats the file as salvageable line by
+// line.
+const malformedDotEnv = "PORT 19615\n" +
+	"this is not = valid ! syntax\n" +
+	"\"unclosed\n"
+
+// unsetDotEnvKey makes dotEnvKey genuinely absent for the duration of
+// the test and restores it afterwards. t.Setenv registers the restore;
+// the Unsetenv that follows is what the test actually needs, because a
+// variable set to the empty string is still present in os.Environ and
+// godotenv would refuse to overwrite it.
+func unsetDotEnvKey(t *testing.T) {
+	t.Helper()
+	t.Setenv(dotEnvKey, "placeholder")
+	require.NoError(t, os.Unsetenv(dotEnvKey))
+}
+
+// writeDotEnv writes contents to a .env file in a fresh temporary
+// directory and returns its path.
+func writeDotEnv(t *testing.T, contents string) string {
+	t.Helper()
+
+	path := filepath.Join(t.TempDir(), config.DotEnvPath)
+	require.NoError(t, os.WriteFile(path, []byte(contents), 0o600))
+
+	return path
+}
+
+// TestLoadDotEnv_MissingFileIsFine pins the case most deployments are
+// in. The file is optional: it is a development convenience, and a
+// deployment that configures the environment directly must start
+// normally rather than be refused for a file it was never meant to
+// have.
+//
+//nolint:paralleltest // unsetDotEnvKey uses t.Setenv.
+func TestLoadDotEnv_MissingFileIsFine(t *testing.T) {
+	unsetDotEnvKey(t)
+
+	absent := filepath.Join(t.TempDir(), config.DotEnvPath)
+	require.NoError(t, config.LoadDotEnvFileForTest(absent))
+
+	_, present := os.LookupEnv(dotEnvKey)
+	assert.False(t, present, "nothing may be set from an absent file")
+}
+
+// TestLoadDotEnv_AppliesValues pins that a well-formed file still
+// reaches the environment, which is the whole reason the file is read
+// at all.
+//
+//nolint:paralleltest // unsetDotEnvKey uses t.Setenv.
+func TestLoadDotEnv_AppliesValues(t *testing.T) {
+	unsetDotEnvKey(t)
+
+	path := writeDotEnv(t, "# a comment\n"+dotEnvKey+"=from-dot-env\n")
+
+	require.NoError(t, config.LoadDotEnvFileForTest(path))
+	assert.Equal(t, "from-dot-env", os.Getenv(dotEnvKey))
+}
+
+// TestLoadDotEnv_RealEnvironmentWins pins that the file cannot
+// override a variable the process was actually started with. A
+// deployment that sets DATA_DIR in its unit file must not have it
+// silently replaced by a stale .env left in the working directory.
+func TestLoadDotEnv_RealEnvironmentWins(t *testing.T) {
+	t.Setenv(dotEnvKey, "from-environment")
+
+	path := writeDotEnv(t, dotEnvKey+"=from-dot-env\n")
+
+	require.NoError(t, config.LoadDotEnvFileForTest(path))
+	assert.Equal(t, "from-environment", os.Getenv(dotEnvKey))
+}
+
+// TestLoadDotEnv_MalformedFileAborts is the defect this fixes. One bad
+// line makes godotenv apply none of the file, so every variable in it
+// reverts to its default; the process used to start that way with no
+// log line naming the file at all.
+//
+//nolint:paralleltest // unsetDotEnvKey uses t.Setenv.
+func TestLoadDotEnv_MalformedFileAborts(t *testing.T) {
+	unsetDotEnvKey(t)
+
+	path := writeDotEnv(
+		t, malformedDotEnv+dotEnvKey+"=from-dot-env\n",
+	)
+
+	err := config.LoadDotEnvFileForTest(path)
+
+	require.Error(t, err)
+	require.ErrorIs(t, err, config.ErrDotEnvUnreadable)
+	assert.Contains(
+		t, err.Error(), config.DotEnvPath,
+		"the failure must name the file it could not read",
+	)
+
+	_, present := os.LookupEnv(dotEnvKey)
+	assert.False(
+		t, present,
+		"a rejected file must apply nothing, not part of itself",
+	)
+}
+
+// TestLoadDotEnv_UnreadableFileAborts pins that only absence is
+// tolerated. A .env that exists but cannot be read is a file the
+// operator meant to be applied, so it fails like a malformed one
+// rather than being treated as though it were not there.
+func TestLoadDotEnv_UnreadableFileAborts(t *testing.T) {
+	t.Parallel()
+
+	// A directory in the file's place: open succeeds and the read
+	// fails, which no umask or root-ness can turn back into success
+	// the way a chmod could.
+	path := filepath.Join(t.TempDir(), config.DotEnvPath)
+	require.NoError(t, os.Mkdir(path, 0o750))
+
+	err := config.LoadDotEnvFileForTest(path)
+
+	require.Error(t, err)
+	require.ErrorIs(t, err, config.ErrDotEnvUnreadable)
+}
+
+// TestLoadDotEnv_ReadsTheWorkingDirectory pins the path LoadDotEnv
+// itself opens, which the tests above bypass. It is relative to the
+// process working directory, as it was under godotenv/autoload and as
+// the README documents.
+//
+//nolint:paralleltest // t.Chdir moves the whole process.
+func TestLoadDotEnv_ReadsTheWorkingDirectory(t *testing.T) {
+	unsetDotEnvKey(t)
+
+	dir := t.TempDir()
+	require.NoError(t, os.WriteFile(
+		filepath.Join(dir, config.DotEnvPath),
+		[]byte(dotEnvKey+"=from-working-directory\n"),
+		0o600,
+	))
+	t.Chdir(dir)
+
+	require.NoError(t, config.LoadDotEnv())
+	assert.Equal(t, "from-working-directory", os.Getenv(dotEnvKey))
+}

internal/config/env_test.go

@@ -21,6 +21,22 @@ const (
 	envKeyPort            = "PORT"
 	envKeyDebug           = "DEBUG"
 	envKeyMaintenanceMode = "MAINTENANCE_MODE"
+	envKeyBindAddress     = "BIND_ADDRESS"
+)
+
+// Sample BIND_ADDRESS values used by the tables below.
+const (
+	// bindAddressDefault is the shipped default. It is asserted
+	// against the package's own constant in
+	// TestNewUsesDefaultsWhenUnset, so the two cannot drift.
+	bindAddressDefault = "127.0.0.1"
+
+	// bindAddressWildcard is the value a container deployment sets.
+	bindAddressWildcard = "0.0.0.0"
+
+	// bindAddressSample is an arbitrary specific address, standing
+	// for "one interface of several".
+	bindAddressSample = "10.1.2.3"
 )
 
 // envBoolCase is one row of the envBool table.
@@ -291,6 +307,160 @@ func TestEnvPort(t *testing.T) {
 	}
 }
 
+// TestEnvBindAddress covers BIND_ADDRESS parsing.
+//
+// Only IP address literals are accepted. Every rejection below is a
+// value an operator plausibly writes — a hostname, a host:port, a
+// CIDR block — and each has to abort startup rather than fall back to
+// the default, because falling back would bind an address other than
+// the one asked for and, in the wildcard-default case this setting
+// exists to end, publish cleartext on every interface.
+func TestEnvBindAddress(t *testing.T) {
+	for _, tt := range envBindAddressCases() {
+		t.Run(tt.name, func(t *testing.T) {
+			// Cannot use t.Parallel() here because t.Setenv
+			// is incompatible with parallel subtests.
+			if tt.set {
+				t.Setenv(testEnvKey, tt.value)
+			} else {
+				require.NoError(t, os.Unsetenv(testEnvKey))
+			}
+
+			got, err := config.EnvBindAddressForTest(
+				testEnvKey, bindAddressDefault,
+			)
+
+			if tt.expectError {
+				require.Error(t, err)
+				require.ErrorIs(t, err, config.ErrInvalidBindAddress)
+				assert.Contains(t, err.Error(), testEnvKey)
+				assert.Contains(t, err.Error(), tt.value)
+
+				return
+			}
+
+			require.NoError(t, err)
+			assert.Equal(t, tt.expected, got)
+		})
+	}
+}
+
+// envBindAddressCase is one row of the envBindAddress table.
+type envBindAddressCase struct {
+	name        string
+	set         bool
+	value       string
+	expectError bool
+	expected    string
+}
+
+// envBindAddressCases is the envBindAddress table, kept out of the
+// test body so the test itself stays readable.
+func envBindAddressCases() []envBindAddressCase {
+	return append(
+		envBindAddressAcceptedCases(),
+		envBindAddressRejectedCases()...,
+	)
+}
+
+// envBindAddressAcceptedCases are the values that parse: the three
+// spellings of "unset" that take the default, and the literals.
+func envBindAddressAcceptedCases() []envBindAddressCase {
+	return []envBindAddressCase{
+		{
+			name:     "unset returns the default",
+			expected: bindAddressDefault,
+		},
+		{
+			name:     "empty returns the default",
+			set:      true,
+			value:    "",
+			expected: bindAddressDefault,
+		},
+		{
+			name:     "whitespace returns the default",
+			set:      true,
+			value:    "   ",
+			expected: bindAddressDefault,
+		},
+		{
+			name:     "ipv4 wildcard is parsed",
+			set:      true,
+			value:    bindAddressWildcard,
+			expected: bindAddressWildcard,
+		},
+		{
+			name:     "ipv4 literal is parsed",
+			set:      true,
+			value:    bindAddressSample,
+			expected: bindAddressSample,
+		},
+		{
+			name:     "surrounding whitespace is trimmed",
+			set:      true,
+			value:    "  " + bindAddressSample + "  ",
+			expected: bindAddressSample,
+		},
+		{
+			name:     "ipv6 wildcard is parsed",
+			set:      true,
+			value:    "::",
+			expected: "::",
+		},
+		{
+			name:     "ipv6 literal is parsed",
+			set:      true,
+			value:    "2001:db8::5",
+			expected: "2001:db8::5",
+		},
+	}
+}
+
+// envBindAddressRejectedCases are the values that abort startup.
+// Each is something an operator plausibly writes, and none may fall
+// back to the default: the default is loopback, so a silent fallback
+// would bind somewhere other than what was asked for.
+func envBindAddressRejectedCases() []envBindAddressCase {
+	return []envBindAddressCase{
+		{
+			name:        "garbage is rejected",
+			set:         true,
+			value:       "not-an-address",
+			expectError: true,
+		},
+		{
+			name:        "hostname is rejected",
+			set:         true,
+			value:       "localhost",
+			expectError: true,
+		},
+		{
+			name:        "unresolvable hostname is rejected",
+			set:         true,
+			value:       "no-such-host.invalid",
+			expectError: true,
+		},
+		{
+			name:        "host and port is rejected",
+			set:         true,
+			value:       bindAddressDefault + ":8080",
+			expectError: true,
+		},
+		{
+			name:        "bracketed ipv6 is rejected",
+			set:         true,
+			value:       "[::1]",
+			expectError: true,
+		},
+		{
+			name:        "CIDR block is rejected",
+			set:         true,
+			value:       "10.0.0.0/8",
+			expectError: true,
+		},
+	}
+}
+
 // buildConfig constructs a Config through fx exactly as the
 // application does, returning the config and any construction error.
 func buildConfig(t *testing.T) (*config.Config, error) {
@@ -312,58 +482,7 @@ func buildConfig(t *testing.T) (*config.Config, error) {
 }
 
 func TestNewRejectsBadEnvValues(t *testing.T) {
-	tests := []struct {
+	for _, tt := range badEnvValueCases() {
-		name        string
-		key         string
-		value       string
-		expectError bool
-		check       func(t *testing.T, cfg *config.Config)
-	}{
-		{
-			name:  "valid PORT is used",
-			key:   envKeyPort,
-			value: "9001",
-			check: func(t *testing.T, cfg *config.Config) {
-				t.Helper()
-				assert.Equal(t, 9001, cfg.Port)
-			},
-		},
-		{
-			name:        "unparseable PORT aborts startup",
-			key:         envKeyPort,
-			value:       "eighty-eighty",
-			expectError: true,
-		},
-		{
-			name:        "out-of-range PORT aborts startup",
-			key:         envKeyPort,
-			value:       "70000",
-			expectError: true,
-		},
-		{
-			name:  "valid DEBUG is used",
-			key:   envKeyDebug,
-			value: "true",
-			check: func(t *testing.T, cfg *config.Config) {
-				t.Helper()
-				assert.True(t, cfg.Debug)
-			},
-		},
-		{
-			name:        "unparseable DEBUG aborts startup",
-			key:         envKeyDebug,
-			value:       "ture",
-			expectError: true,
-		},
-		{
-			name:        "unparseable MAINTENANCE_MODE aborts startup",
-			key:         envKeyMaintenanceMode,
-			value:       "sometimes",
-			expectError: true,
-		},
-	}
-
-	for _, tt := range tests {
 		t.Run(tt.name, func(t *testing.T) {
 			// Cannot use t.Parallel() here because t.Setenv
 			// is incompatible with parallel subtests.
@@ -387,6 +506,149 @@ func TestNewRejectsBadEnvValues(t *testing.T) {
 	}
 }
 
+// badEnvValueCase is one row of the config.New table: a variable, the
+// value it is set to, and either the assertion that startup fails
+// naming both, or a check on the Config that resulted.
+type badEnvValueCase struct {
+	name        string
+	key         string
+	value       string
+	expectError bool
+	check       func(t *testing.T, cfg *config.Config)
+}
+
+// badEnvValueCases is the config.New table, kept out of the test body
+// so the test itself stays readable. It is assembled from per-variable
+// groups because one literal covering every variable outgrew the
+// function-length budget.
+func badEnvValueCases() []badEnvValueCase {
+	cases := listenerEnvValueCases()
+	cases = append(cases, flagEnvValueCases()...)
+	cases = append(cases, sentryEnvValueCases()...)
+
+	return cases
+}
+
+// listenerEnvValueCases covers the two variables that describe the
+// HTTP listener.
+func listenerEnvValueCases() []badEnvValueCase {
+	return []badEnvValueCase{
+		{
+			name:  "valid PORT is used",
+			key:   envKeyPort,
+			value: "9001",
+			check: func(t *testing.T, cfg *config.Config) {
+				t.Helper()
+				assert.Equal(t, 9001, cfg.Port)
+			},
+		},
+		{
+			name:        "unparseable PORT aborts startup",
+			key:         envKeyPort,
+			value:       "eighty-eighty",
+			expectError: true,
+		},
+		{
+			name:        "out-of-range PORT aborts startup",
+			key:         envKeyPort,
+			value:       "70000",
+			expectError: true,
+		},
+		{
+			name:  "valid BIND_ADDRESS is used",
+			key:   envKeyBindAddress,
+			value: bindAddressWildcard,
+			check: func(t *testing.T, cfg *config.Config) {
+				t.Helper()
+				assert.Equal(
+					t, bindAddressWildcard, cfg.BindAddress,
+				)
+			},
+		},
+		{
+			name:        "unparseable BIND_ADDRESS aborts startup",
+			key:         envKeyBindAddress,
+			value:       "not-an-address",
+			expectError: true,
+		},
+		{
+			name:        "hostname BIND_ADDRESS aborts startup",
+			key:         envKeyBindAddress,
+			value:       "localhost",
+			expectError: true,
+		},
+		{
+			name:        "BIND_ADDRESS with a port aborts startup",
+			key:         envKeyBindAddress,
+			value:       bindAddressDefault + ":8080",
+			expectError: true,
+		},
+	}
+}
+
+// flagEnvValueCases covers the boolean variables.
+func flagEnvValueCases() []badEnvValueCase {
+	return []badEnvValueCase{
+		{
+			name:  "valid DEBUG is used",
+			key:   envKeyDebug,
+			value: "true",
+			check: func(t *testing.T, cfg *config.Config) {
+				t.Helper()
+				assert.True(t, cfg.Debug)
+			},
+		},
+		{
+			name:        "unparseable DEBUG aborts startup",
+			key:         envKeyDebug,
+			value:       "ture",
+			expectError: true,
+		},
+		{
+			name:        "unparseable MAINTENANCE_MODE aborts startup",
+			key:         envKeyMaintenanceMode,
+			value:       "sometimes",
+			expectError: true,
+		},
+	}
+}
+
+// sentryEnvValueCases covers SENTRY_DSN. The three rejected values are
+// the ones measured on the defect: each initialised the SDK with an
+// error and left the process serving with error reporting off.
+func sentryEnvValueCases() []badEnvValueCase {
+	return []badEnvValueCase{
+		{
+			name:  "valid SENTRY_DSN is used",
+			key:   envKeySentryDSN,
+			value: validSentryDSN,
+			check: func(t *testing.T, cfg *config.Config) {
+				t.Helper()
+				assert.Equal(t, validSentryDSN, cfg.SentryDSN)
+				assert.True(t, cfg.SentryEnabled())
+			},
+		},
+		{
+			name:        "unparseable SENTRY_DSN aborts startup",
+			key:         envKeySentryDSN,
+			value:       "not-a-dsn",
+			expectError: true,
+		},
+		{
+			name:        "SENTRY_DSN that is not a URL aborts startup",
+			key:         envKeySentryDSN,
+			value:       "%%%",
+			expectError: true,
+		},
+		{
+			name:        "keyless SENTRY_DSN aborts startup",
+			key:         envKeySentryDSN,
+			value:       "https://example.invalid/1",
+			expectError: true,
+		},
+	}
+}
+
 // TestNewUsesDefaultsWhenUnset proves the fail-loud behaviour did not
 // break the legitimate unset case: absent variables still get their
 // documented defaults.
@@ -395,6 +657,7 @@ func TestNewUsesDefaultsWhenUnset(t *testing.T) {
 
 	for _, key := range []string{
 		envKeyPort, envKeyDebug, envKeyMaintenanceMode,
+		envKeyBindAddress, envKeySentryDSN,
 	} {
 		require.NoError(t, os.Unsetenv(key))
 	}
@@ -406,4 +669,20 @@ func TestNewUsesDefaultsWhenUnset(t *testing.T) {
 	assert.Equal(t, 8080, cfg.Port)
 	assert.False(t, cfg.Debug)
 	assert.False(t, cfg.MaintenanceMode)
+
+	// Loopback, not the wildcard: the default must not publish the
+	// cleartext admin UI and the unauthenticated receiver on every
+	// interface of a host that configured nothing. The value is read
+	// from the package rather than repeated, so the README's
+	// documented default and the compiled-in one are pinned to the
+	// same constant.
+	assert.Equal(
+		t, config.DefaultBindAddressForTest, cfg.BindAddress,
+	)
+	assert.Equal(t, bindAddressDefault, cfg.BindAddress)
+
+	// An absent SENTRY_DSN is the common case and must stay a normal
+	// start with error reporting off, not a refusal.
+	assert.Empty(t, cfg.SentryDSN)
+	assert.False(t, cfg.SentryEnabled())
 }

internal/config/export_test.go

@@ -50,3 +50,25 @@ func EnvPositiveIntForTest(key string, defaultValue int) (int, error) {
 func EnvPortForTest(key string, defaultValue int) (int, error) {
 	return envPort(key, defaultValue)
 }
+
+// EnvSentryDSNForTest exposes envSentryDSN.
+func EnvSentryDSNForTest(key string) (string, error) {
+	return envSentryDSN(key)
+}
+
+// LoadDotEnvFileForTest exposes the loader LoadDotEnv runs, over a
+// caller-named file rather than the process working directory, so
+// each .env state can be covered without moving the test process.
+func LoadDotEnvFileForTest(path string) error {
+	return loadDotEnvFile(path)
+}
+
+// EnvBindAddressForTest exposes envBindAddress.
+func EnvBindAddressForTest(key, defaultValue string) (string, error) {
+	return envBindAddress(key, defaultValue)
+}
+
+// DefaultBindAddressForTest exposes the compiled-in BIND_ADDRESS
+// default, so a test pins the documented value rather than repeating
+// a literal that could drift from it.
+const DefaultBindAddressForTest = defaultBindAddress

internal/config/sentry_test.go

@@ -0,0 +1,141 @@
+package config_test
+
+import (
+	"os"
+	"testing"
+
+	"github.com/stretchr/testify/assert"
+	"github.com/stretchr/testify/require"
+	"sneak.berlin/go/webhooker/internal/config"
+)
+
+// envKeySentryDSN is the variable envSentryDSN reads in production.
+const envKeySentryDSN = "SENTRY_DSN"
+
+// validSentryDSN is a syntactically complete DSN. The host is under
+// .invalid (RFC 2606), so nothing a test builds around it can reach a
+// real Sentry installation.
+const validSentryDSN = "https://abc123@sentry.invalid/42"
+
+// envSentryDSNCase is one row of the envSentryDSN table.
+type envSentryDSNCase struct {
+	name        string
+	set         bool
+	value       string
+	expectError bool
+	expected    string
+}
+
+// envSentryDSNCases is the envSentryDSN table. The three invalid
+// values are the ones measured on the defect: each initialised the SDK
+// with an error and left the process serving with reporting off.
+func envSentryDSNCases() []envSentryDSNCase {
+	return []envSentryDSNCase{
+		{
+			name:     "unset means reporting off",
+			expected: "",
+		},
+		{
+			name:     "empty means reporting off",
+			set:      true,
+			value:    "",
+			expected: "",
+		},
+		{
+			name:     "whitespace means reporting off",
+			set:      true,
+			value:    "   ",
+			expected: "",
+		},
+		{
+			name:     "a valid DSN is kept",
+			set:      true,
+			value:    validSentryDSN,
+			expected: validSentryDSN,
+		},
+		{
+			name:     "surrounding whitespace is trimmed",
+			set:      true,
+			value:    "  " + validSentryDSN + "\t",
+			expected: validSentryDSN,
+		},
+		{
+			name:        "a value that is not a URL is rejected",
+			set:         true,
+			value:       "not-a-dsn",
+			expectError: true,
+		},
+		{
+			name:        "an unparseable URL is rejected",
+			set:         true,
+			value:       "%%%",
+			expectError: true,
+		},
+		{
+			name:        "a DSN without a public key is rejected",
+			set:         true,
+			value:       "https://example.invalid/1",
+			expectError: true,
+		},
+		{
+			name:        "a DSN without a project id is rejected",
+			set:         true,
+			value:       "https://abc123@sentry.invalid/",
+			expectError: true,
+		},
+		{
+			name:        "a non-HTTP scheme is rejected",
+			set:         true,
+			value:       "ftp://abc123@sentry.invalid/42",
+			expectError: true,
+		},
+	}
+}
+
+// TestEnvSentryDSN covers the helper directly. What it pins beyond the
+// value is the failure shape: a set-but-unparseable DSN names the
+// variable and the value, exactly as the other fail-loud helpers do,
+// so an operator reads the fix off the message.
+func TestEnvSentryDSN(t *testing.T) {
+	for _, tt := range envSentryDSNCases() {
+		t.Run(tt.name, func(t *testing.T) {
+			// Cannot use t.Parallel() here because t.Setenv
+			// is incompatible with parallel subtests.
+			if tt.set {
+				t.Setenv(envKeySentryDSN, tt.value)
+			} else {
+				require.NoError(t, os.Unsetenv(envKeySentryDSN))
+			}
+
+			got, err := config.EnvSentryDSNForTest(envKeySentryDSN)
+
+			if tt.expectError {
+				require.Error(t, err)
+				require.ErrorIs(t, err, config.ErrInvalidSentryDSN)
+				assert.Contains(t, err.Error(), envKeySentryDSN)
+				assert.Contains(t, err.Error(), tt.value)
+				assert.Empty(t, got)
+
+				return
+			}
+
+			require.NoError(t, err)
+			assert.Equal(t, tt.expected, got)
+		})
+	}
+}
+
+// TestSentryEnabled_TracksTheDSN pins that the one method answering
+// "is anything being reported" agrees with the DSN in every state. The
+// startup log, the SDK initialisation and the sentryhttp middleware
+// all read it, so a log field cannot report reporting as on while
+// nothing is sending.
+func TestSentryEnabled_TracksTheDSN(t *testing.T) {
+	t.Parallel()
+
+	assert.False(t, (&config.Config{}).SentryEnabled())
+	assert.True(
+		t,
+		(&config.Config{SentryDSN: validSentryDSN}).SentryEnabled(),
+	)
+}

internal/database/database.go

@@ -4,7 +4,6 @@ package database
 import (
 	"context"
 	"crypto/rand"
-	"database/sql"
 	"encoding/base64"
 	"errors"
 	"fmt"
@@ -16,7 +15,6 @@ import (
 	"go.uber.org/fx"
 	"gorm.io/driver/sqlite"
 	"gorm.io/gorm"
-	_ "modernc.org/sqlite" // Pure Go SQLite driver
 	"sneak.berlin/go/webhooker/internal/banner"
 	"sneak.berlin/go/webhooker/internal/config"
 	"sneak.berlin/go/webhooker/internal/gormlog"
@@ -198,13 +196,11 @@ func (d *Database) connectTo(dataDir string) error {
 
 	// Construct the main application database path inside DATA_DIR.
 	dbPath := filepath.Join(dataDir, MainDBFileName)
-	dbURL := fmt.Sprintf(
-		"file:%s?cache=shared&mode=rwc",
-		dbPath,
-	)
 
-	// Open the database with the pure Go SQLite driver
+	// Opened through OpenSQLite so this handle carries the same WAL
-	sqlDB, err := sql.Open("sqlite", dbURL)
+	// journaling, busy timeout, immediate-transaction locking, and pool
+	// bounds as every other database file. See sqlite_open.go.
+	sqlDB, err := OpenSQLite(dbPath, SQLiteModeCreate)
 	if err != nil {
 		d.log.Error(
 			"failed to open database",

internal/database/migration_entrypoint_test.go

@@ -1,85 +0,0 @@
-package database_test
-
-import (
-	"net/http"
-	"testing"
-
-	"github.com/stretchr/testify/assert"
-	"github.com/stretchr/testify/require"
-	"sneak.berlin/go/webhooker/internal/database"
-	"sneak.berlin/go/webhooker/internal/signature"
-)
-
-// TestEntrypointSignatureColumnsMigrateToUnconfigured pins the
-// upgrade path for a deployment that already has entrypoints.
-//
-// The signature columns arrive through GORM's AutoMigrate, so every
-// row written before they existed acquires them with no value. That
-// has to land on "not configured", because the alternative is an
-// upgrade that rejects the traffic the operator was already
-// receiving — a self-inflicted outage on a receiver whose senders
-// cannot be told to start signing.
-//
-// The legacy schema is reproduced by dropping the columns from a
-// migrated database and writing a row through the old shape, so the
-// row really predates them rather than merely being blank.
-func TestEntrypointSignatureColumnsMigrateToUnconfigured(t *testing.T) {
-	t.Parallel()
-
-	db, lc := setupTestDB(t)
-	lc.RequireStart()
-
-	t.Cleanup(lc.RequireStop)
-
-	for _, column := range []string{
-		"signature_scheme", "signature_secret",
-	} {
-		require.NoError(
-			t,
-			db.DB().Exec(
-				"ALTER TABLE entrypoints DROP COLUMN "+column,
-			).Error,
-			"dropping %s to reproduce the pre-upgrade schema",
-			column,
-		)
-	}
-
-	const legacyID = "legacy-entrypoint"
-
-	require.NoError(
-		t,
-		db.DB().Exec(
-			`INSERT INTO entrypoints
-			 (id, created_at, updated_at, webhook_id, path,
-			  description, active)
-			 VALUES (?, ?, ?, ?, ?, ?, ?)`,
-			legacyID, "2026-01-01 00:00:00", "2026-01-01 00:00:00",
-			"legacy-webhook", "legacy-path", "predates signatures",
-			true,
-		).Error,
-	)
-
-	// The upgrade.
-	require.NoError(t, db.Migrate())
-
-	var ep database.Entrypoint
-
-	require.NoError(
-		t,
-		db.DB().Where("id = ?", legacyID).First(&ep).Error,
-		"the migrated row must still load; a NULL landing in a "+
-			"string column would fail here",
-	)
-
-	assert.Equal(t, database.SignatureSchemeNone, ep.SignatureScheme)
-	assert.Empty(t, ep.SignatureSecret)
-	assert.False(t, ep.SignatureConfigured())
-	assert.True(t, ep.Active, "the row's other columns survive")
-
-	// The behaviour that actually matters: an unsigned request to
-	// this entrypoint is still accepted.
-	assert.NoError(
-		t,
-		signature.Verify(&ep, http.Header{}, []byte(`{"a":1}`)),
-	)
-}

internal/database/model_entrypoint.go

@@ -1,71 +1,20 @@
 package database
 
-// SignatureScheme names the way an entrypoint authenticates inbound
-// requests. A scheme fixes both the header the signature arrives in
-// and the algorithm used to check it, so an operator cannot pair one
-// sender's header with another sender's comparison.
-type SignatureScheme string
-
-// Signature scheme values. The empty scheme means the entrypoint
-// performs no inbound verification: it is the default, and it is the
-// state every entrypoint created before this column existed migrates
-// to, so an existing deployment keeps accepting the requests it
-// accepted before.
-const (
-	SignatureSchemeNone   SignatureScheme = ""
-	SignatureSchemeGitHub SignatureScheme = "github"
-	SignatureSchemeGitLab SignatureScheme = "gitlab"
-)
-
 // Entrypoint represents an inbound URL endpoint that feeds into a webhook
 type Entrypoint struct {
 	BaseModel
 
 	WebhookID string `gorm:"type:uuid;not null" json:"webhookId"`
 
-	// Path is the URL path for this entrypoint.
+	// Path is the URL path for this entrypoint. It is the
+	// entrypoint's only credential: possession of the UUID
+	// authorises submission, so the receiver checks nothing else
+	// about the sender.
 	Path string `gorm:"uniqueIndex;not null" json:"path"`
 
 	Description string `json:"description"`
 	Active      bool   `gorm:"default:true" json:"active"`
 
-	// SignatureScheme selects how inbound requests to this
-	// entrypoint are authenticated. Empty means unauthenticated,
-	// which is what a UUID-only entrypoint has always been.
-	SignatureScheme SignatureScheme `gorm:"default:''" json:"signatureScheme"`
-
-	// SignatureSecret is the secret shared with the sender.
-	//
-	// It is stored in the clear because HMAC verification needs the
-	// key itself: a hash of it cannot recompute the sender's digest.
-	// It is therefore a live credential, and json:"-" keeps it out of
-	// any handler that marshals the model, the way APIKey.Key and
-	// Target.Config are kept out. handlers.EntrypointView is the
-	// matching barrier for the HTML path.
-	SignatureSecret string `gorm:"default:''" json:"-"`
-
 	// Relations
 	Webhook Webhook `json:"webhook,omitzero"`
 }
-
-// SignatureConfigured reports whether this entrypoint verifies
-// inbound requests. Both halves must be present: a scheme without a
-// secret, or a secret without a scheme, is a broken configuration
-// rather than a configured one, and signature.Verify fails those
-// closed rather than treating them as "off".
-func (e *Entrypoint) SignatureConfigured() bool {
-	return e.SignatureScheme != SignatureSchemeNone &&
-		e.SignatureSecret != ""
-}
-
-// SignatureHalfConfigured reports whether exactly one half of the
-// scheme/secret pair is present. The receiver refuses such a row on
-// every request, so the UI must not describe it as unverified. It
-// reports the state without exposing the secret, which is why it
-// lives here rather than in the display projection.
-func (e *Entrypoint) SignatureHalfConfigured() bool {
-	hasScheme := e.SignatureScheme != SignatureSchemeNone
-	hasSecret := e.SignatureSecret != ""
-
-	return hasScheme != hasSecret
-}

internal/database/model_secrets_test.go

@@ -34,8 +34,6 @@ func marshalModel(t *testing.T, v any) string {
 //   - APIKey.Key is a bearer token outright.
 //   - Setting.Value holds the session encryption key.
 //   - User.Password holds the Argon2 hash, and was already tagged.
-//   - Entrypoint.SignatureSecret is the secret its senders sign with,
-//     stored in the clear because HMAC verification needs the key.
 func TestModelsDoNotMarshalTheirSecrets(t *testing.T) {
 	t.Parallel()
 
@@ -74,14 +72,6 @@ func TestModelsDoNotMarshalTheirSecrets(t *testing.T) {
 				Password: marker,
 			},
 		},
-		{
-			name: "entrypoint signature secret",
-			model: database.Entrypoint{
-				Description:     keptField,
-				SignatureScheme: database.SignatureSchemeGitHub,
-				SignatureSecret: marker,
-			},
-		},
 	}
 
 	for _, tc := range cases {
@@ -115,24 +105,3 @@ func TestWebhookMarshalsNoTargetConfig(t *testing.T) {
 	assert.NotContains(t, encoded, marker)
 	assert.Contains(t, encoded, keptField)
 }
-
-// TestWebhookMarshalsNoEntrypointSecret covers the same nested case
-// for the entrypoint's inbound signature secret, which reaches a
-// marshalled webhook through the Entrypoints association.
-func TestWebhookMarshalsNoEntrypointSecret(t *testing.T) {
-	t.Parallel()
-
-	const marker = "QQENTRYPOINTMARKERQQ"
-
-	encoded := marshalModel(t, database.Webhook{
-		Name: keptField,
-		Entrypoints: []database.Entrypoint{{
-			Path:            "some-uuid",
-			SignatureScheme: database.SignatureSchemeGitLab,
-			SignatureSecret: marker,
-		}},
-	})
-
-	assert.NotContains(t, encoded, marker)
-	assert.Contains(t, encoded, keptField)
-}

internal/database/sqlite_mode_test.go

@@ -0,0 +1,240 @@
+package database_test
+
+import (
+	"context"
+	"io/fs"
+	"net/http"
+	"os"
+	"path/filepath"
+	"testing"
+
+	"github.com/google/uuid"
+	"github.com/stretchr/testify/assert"
+	"github.com/stretchr/testify/require"
+	"go.uber.org/fx/fxtest"
+	"sneak.berlin/go/webhooker/internal/config"
+	"sneak.berlin/go/webhooker/internal/database"
+	"sneak.berlin/go/webhooker/internal/globals"
+	"sneak.berlin/go/webhooker/internal/logger"
+)
+
+// ownerOnly is the mode every SQLite file the service owns must have.
+// Spelled out rather than referencing database.SQLiteFilePerm so the
+// test fails if the constant itself is loosened.
+const ownerOnly fs.FileMode = 0o600
+
+// requireOwnerOnly asserts that path exists and is readable and
+// writable by its owner and by nobody else.
+func requireOwnerOnly(t *testing.T, path string) {
+	t.Helper()
+
+	info, err := os.Stat(path)
+	require.NoError(t, err, "%s must exist", path)
+	assert.Equal(
+		t,
+		ownerOnly,
+		info.Mode().Perm(),
+		"%s holds credentials and must not be readable by "+
+			"anyone but its owner",
+		path,
+	)
+}
+
+// requireDatabaseSetOwnerOnly asserts the mode of a database file and
+// of both WAL sidecars. The sidecars carry the same rows as the
+// database, so tightening only the main file fixes nothing.
+func requireDatabaseSetOwnerOnly(t *testing.T, dbPath string) {
+	t.Helper()
+
+	requireOwnerOnly(t, dbPath)
+	requireOwnerOnly(t, dbPath+"-wal")
+	requireOwnerOnly(t, dbPath+"-shm")
+}
+
+// TestMainDatabaseFilesAreOwnerOnly covers the tier the defect was
+// reported against: webhooker.db holds targets.config in plaintext —
+// bearer tokens, API keys, Slack webhook URLs — and the session
+// encryption key.
+func TestMainDatabaseFilesAreOwnerOnly(t *testing.T) {
+	t.Parallel()
+
+	lc := fxtest.NewLifecycle(t)
+
+	l, err := logger.New(lc, logger.LoggerParams{
+		Globals: &globals.Globals{
+			Appname: testAppname,
+			Version: testVersion,
+		},
+	})
+	require.NoError(t, err)
+
+	// A directory the application creates itself, not one t.TempDir
+	// made at 0700, so the mode below is the application's.
+	dataDir := filepath.Join(t.TempDir(), "data")
+
+	db, err := database.New(lc, database.DatabaseParams{
+		Config: &config.Config{DataDir: dataDir},
+		Logger: l,
+	})
+	require.NoError(t, err)
+
+	ctx := context.Background()
+	require.NoError(t, lc.Start(ctx))
+
+	defer func() { require.NoError(t, lc.Stop(ctx)) }()
+
+	// Write through the real model so the WAL is populated and both
+	// sidecars are on disk while the handle is open.
+	require.NoError(t, db.DB().Create(&database.Webhook{
+		Name: testWebhookName,
+	}).Error)
+
+	requireDatabaseSetOwnerOnly(
+		t, filepath.Join(dataDir, database.MainDBFileName),
+	)
+
+	// The data directory grants nothing to `other`. Asserted as a
+	// property rather than as an exact 0750, because MkdirAll applies
+	// the ambient umask: the exact mode is the developer's umask as
+	// much as the application's request, and pinning it would make
+	// `make check` pass or fail on where it is run. The group bits are
+	// deliberately left unasserted — deployments may rely on them.
+	info, err := os.Stat(dataDir)
+	require.NoError(t, err)
+	assert.Zero(
+		t,
+		info.Mode().Perm()&0o007,
+		"the data directory must not be world-accessible",
+	)
+}
+
+// TestPerWebhookEventDatabaseFilesAreOwnerOnly covers the events-*.db
+// tier. These carry no credential canaries since
+// https://git.eeqj.de/sneak/webhooker/issues/206, but they hold every
+// received request body and header.
+func TestPerWebhookEventDatabaseFilesAreOwnerOnly(t *testing.T) {
+	t.Parallel()
+
+	mgr, lc := setupTestWebhookDBManager(t)
+	ctx := context.Background()
+	require.NoError(t, lc.Start(ctx))
+
+	defer func() { require.NoError(t, lc.Stop(ctx)) }()
+
+	webhookID := uuid.New().String()
+
+	db, err := mgr.GetDB(webhookID)
+	require.NoError(t, err)
+
+	require.NoError(t, db.Create(&database.Event{
+		WebhookID:    webhookID,
+		EntrypointID: uuid.New().String(),
+		Method:       http.MethodPost,
+		Body:         "{}",
+	}).Error)
+
+	requireDatabaseSetOwnerOnly(t, mgr.DBPath(webhookID))
+}
+
+// TestArchiveDatabaseFilesAreOwnerOnly covers the archive-*.db tier.
+// internal/delivery builds that path and opens it through OpenSQLite,
+// the same single open path exercised here, so the mode is settled for
+// all three tiers in one place.
+func TestArchiveDatabaseFilesAreOwnerOnly(t *testing.T) {
+	t.Parallel()
+
+	ctx := context.Background()
+	path := filepath.Join(
+		t.TempDir(), "archive-"+uuid.New().String()+".db",
+	)
+
+	sqlDB, err := database.OpenSQLite(path, database.SQLiteModeCreate)
+	require.NoError(t, err)
+
+	defer func() { require.NoError(t, sqlDB.Close()) }()
+
+	_, err = sqlDB.ExecContext(ctx, "create table t (id integer)")
+	require.NoError(t, err)
+
+	requireDatabaseSetOwnerOnly(t, path)
+}
+
+// TestOpenSQLiteTightensFilesLeftWorldReadable is the upgrade case: a
+// data directory an earlier build left at 0644, including a
+// developer's own scratch directory, is fixed when it is opened rather
+// than staying exposed until it is recreated.
+func TestOpenSQLiteTightensFilesLeftWorldReadable(t *testing.T) {
+	t.Parallel()
+
+	dir := t.TempDir()
+	path := filepath.Join(dir, database.MainDBFileName)
+
+	// A database and both sidecars as the pre-fix build left them.
+	for _, p := range []string{path, path + "-wal", path + "-shm"} {
+		require.NoError(t, os.WriteFile(p, nil, 0o644)) //nolint:gosec // the mode under test
+	}
+
+	sqlDB, err := database.OpenSQLite(path, database.SQLiteModeCreate)
+	require.NoError(t, err)
+
+	require.NoError(t, sqlDB.Close())
+
+	requireDatabaseSetOwnerOnly(t, path)
+}
+
+// TestOpenSQLiteExistingModeDoesNotCreateTheFile guards the mechanism
+// the fix uses: OpenSQLite now creates the database file itself, and
+// must not do so for a caller that asked for an existing database. An
+// empty file materialized here would turn a missing-database error
+// into a silently empty one.
+func TestOpenSQLiteExistingModeDoesNotCreateTheFile(t *testing.T) {
+	t.Parallel()
+
+	ctx := context.Background()
+	path := filepath.Join(t.TempDir(), "absent.db")
+
+	sqlDB, err := database.OpenSQLite(path, database.SQLiteModeExisting)
+	if err == nil {
+		// sql.Open is lazy: force the connection that fails.
+		require.Error(t, sqlDB.PingContext(ctx))
+		require.NoError(t, sqlDB.Close())
+	}
+
+	_, statErr := os.Stat(path)
+	assert.ErrorIs(t, statErr, fs.ErrNotExist)
+}
+
+// TestReopenAfterRestartKeepsFilesOwnerOnly is the restart case: a
+// process that closed its files must be able to open them again at
+// 0600, including through a gorm handle, and the sidecars must come
+// back at 0600 too rather than at SQLite's own default.
+func TestReopenAfterRestartKeepsFilesOwnerOnly(t *testing.T) {
+	t.Parallel()
+
+	ctx := context.Background()
+	dir := t.TempDir()
+	path := filepath.Join(dir, database.MainDBFileName)
+
+	first, err := database.OpenSQLite(path, database.SQLiteModeCreate)
+	require.NoError(t, err)
+
+	_, err = first.ExecContext(ctx, "create table t (id integer)")
+	require.NoError(t, err)
+	require.NoError(t, first.Close())
+
+	second, err := database.OpenSQLite(path, database.SQLiteModeCreate)
+	require.NoError(t, err)
+
+	defer func() { require.NoError(t, second.Close()) }()
+
+	_, err = second.ExecContext(ctx, "insert into t (id) values (1)")
+	require.NoError(t, err)
+
+	requireDatabaseSetOwnerOnly(t, path)
+
+	var got int
+
+	require.NoError(t,
+		second.QueryRowContext(ctx, "select id from t").Scan(&got))
+	assert.Equal(t, 1, got)
+}

internal/database/sqlite_open.go

@@ -0,0 +1,252 @@
+package database
+
+import (
+	"database/sql"
+	"errors"
+	"fmt"
+	"io/fs"
+	"net/url"
+	"os"
+	"time"
+
+	_ "modernc.org/sqlite" // Pure Go SQLite driver
+)
+
+// Every SQLite file this service opens — the main database, the
+// per-webhook event databases, and the archive databases — is opened
+// through OpenSQLite, so the durability settings below are properties
+// of the service rather than of one call site.
+//
+// modernc.org/sqlite installs no busy handler and issues no pragmas of
+// its own: it executes only the pragmas named in explicit `_pragma=`
+// DSN parameters, and gorm.io/driver/sqlite adds none when it is
+// handed an existing *sql.DB. Every setting therefore has to be
+// spelled out here or it is simply not in effect.
+// SQLite URI open modes.
+const (
+	// SQLiteModeCreate creates the database file when it is missing.
+	SQLiteModeCreate = "rwc"
+
+	// SQLiteModeExisting requires the file to exist already.
+	SQLiteModeExisting = "rw"
+)
+
+const (
+	// SQLiteBusyTimeout is how long SQLite retries a lock conflict
+	// before returning SQLITE_BUSY.
+	//
+	// Under WAL a reader never blocks a writer, so the only conflict
+	// left is writer against writer: this process's delivery workers
+	// against each other, or against another process holding the write
+	// lock. Those clear in milliseconds. Ten seconds is far above that
+	// and still well inside the receiver's request budget, so an
+	// inbound webhook waits rather than being rejected with a 500.
+	SQLiteBusyTimeout = 10 * time.Second
+
+	// sqliteMaxOpenConns bounds the connection pool for one database
+	// file.
+	//
+	// The pool needs a bound at all because database/sql cannot detect
+	// a connection left mid-transaction: modernc.org/sqlite implements
+	// neither driver.Validator nor driver.SessionResetter, so a
+	// connection whose COMMIT failed is returned to the pool with its
+	// transaction still open and handed out again indefinitely. That is
+	// what turned four `database is locked` errors into 593
+	// `cannot start a transaction within a transaction` in
+	// https://git.eeqj.de/sneak/webhooker/issues/256.
+	//
+	// Four is above the one writer SQLite allows at a time, so reads
+	// still proceed while a write is in flight, and low enough that
+	// contention is resolved by the busy handler rather than by piling
+	// up connections against a lock only one of them can hold.
+	sqliteMaxOpenConns = 4
+
+	// sqliteMaxIdleConns keeps the pool warm without holding every
+	// connection open through an idle period.
+	sqliteMaxIdleConns = 2
+
+	// sqliteConnMaxLifetime and sqliteConnMaxIdleTime retire pooled
+	// connections on a schedule. With _txlock=immediate a failed
+	// COMMIT should no longer be reachable, but these bound the damage
+	// if one happens anyway: a poisoned connection is closed and
+	// replaced within the lifetime instead of wedging the file until
+	// the process restarts.
+	sqliteConnMaxLifetime = 5 * time.Minute
+	sqliteConnMaxIdleTime = time.Minute
+)
+
+// SQLiteFilePerm is the mode every SQLite file this service owns is
+// created with and held at: owner read/write, nothing for group or
+// other.
+//
+// These files hold credentials in plaintext. The main database stores
+// `targets.config` — bearer tokens, API keys, Slack webhook URLs — and
+// the session encryption key. SQLite left to itself creates them 0644
+// (see reserveSQLiteFile), which made the 0750 data directory the only
+// barrier; a bind-mounted directory supplied at 0755 removes it and
+// every local user on the host can read every stored credential.
+//
+// This is a file-mode fix and not encryption at rest. An unattended
+// process needs a key it can read without a human, so the key lands
+// beside the data and an attacker who can read the database can read
+// it too. See https://git.eeqj.de/sneak/webhooker/issues/212.
+const SQLiteFilePerm fs.FileMode = 0o600
+
+// reserveSQLiteFile puts path at SQLiteFilePerm before the driver ever
+// touches it, and tightens any sidecar already on disk.
+//
+// The mode has to be settled here rather than by a chmod after opening,
+// because SQLite picks it: robust_open substitutes
+// SQLITE_DEFAULT_FILE_PERMISSIONS (0644) whenever it is handed mode 0,
+// and findCreateFileMode yields 0 for a main database opened by URI
+// with no `modeof` parameter. A chmod afterwards would leave a window
+// in which the credentials are on disk world-readable.
+//
+// Creating the file ourselves also settles the sidecars, which is the
+// half that could quietly not work. SQLite does not create those at a
+// mode we choose — it derives both from the main database file:
+// `-wal` through findCreateFileMode, which stats the path with the
+// suffix stripped, and `-shm` in unixOpenSharedMemory from an fstat of
+// the already-open database descriptor. A main file at 0600 therefore
+// produces sidecars at 0600. A zero-length file is a valid empty
+// database, so reserving it changes nothing else.
+//
+// create says whether the caller is opening in a mode that may create
+// the database. When it is false a missing file is left missing, so
+// SQLite still reports the absence rather than this function
+// materializing an empty database the caller asked not to create.
+//
+// Chmod of a file that already exists is what tightens a data
+// directory an earlier build left at 0644 — including a developer's
+// own scratch directory — without any migration machinery.
+func reserveSQLiteFile(path string, create bool) error {
+	if create {
+		// gosec G304: the path is the database file the caller asked
+		// to open, and the driver is about to open the same path
+		// anyway. Creating it here is what fixes its mode.
+		f, err := os.OpenFile( //nolint:gosec // see above
+			path, os.O_RDWR|os.O_CREATE, SQLiteFilePerm,
+		)
+		if err != nil {
+			return fmt.Errorf("creating %s: %w", path, err)
+		}
+
+		err = f.Close()
+		if err != nil {
+			return fmt.Errorf("closing %s: %w", path, err)
+		}
+	}
+
+	// O_CREATE leaves an existing file's mode alone, and umask can only
+	// have narrowed a new one. Chmod settles both cases at exactly
+	// SQLiteFilePerm.
+	for _, p := range append(
+		[]string{path}, sqliteSidecarPaths(path)...,
+	) {
+		err := os.Chmod(p, SQLiteFilePerm)
+		if err != nil && !errors.Is(err, fs.ErrNotExist) {
+			return fmt.Errorf("securing %s: %w", p, err)
+		}
+	}
+
+	return nil
+}
+
+// sqliteSidecarPaths returns the files SQLite maintains beside a
+// database under WAL. They carry the same rows as the database itself,
+// so a fix that tightens only the main file has fixed nothing.
+func sqliteSidecarPaths(path string) []string {
+	return []string{path + "-wal", path + "-shm"}
+}
+
+// SQLiteDSN builds the connection string for one database file.
+//
+// mode is the SQLite URI open mode: "rwc" to create the file when it
+// is missing, "rw" to require that it already exists.
+//
+// Three settings carry the fix for
+// https://git.eeqj.de/sneak/webhooker/issues/256 and none of them is
+// optional:
+//
+//   - journal_mode=WAL, so a reader — an operator running
+//     `sqlite3 <db> .dump` over their own data — takes a snapshot
+//     instead of blocking every writer behind it.
+//
+//   - busy_timeout, so a writer that does meet a lock waits for it.
+//     Without one SQLite gives up immediately; nothing above it
+//     retries.
+//
+//   - _txlock=immediate, so every transaction takes the write lock at
+//     BEGIN. A deferred transaction acquires it lazily on its first
+//     write, and that upgrade returns SQLITE_BUSY *without* consulting
+//     the busy handler, because SQLite cannot block a transaction that
+//     may already hold a read snapshot. Such a COMMIT then fails while
+//     the transaction stays open on the connection. A busy timeout
+//     alone does not prevent this; BEGIN IMMEDIATE does, by putting
+//     the wait somewhere the handler applies.
+//
+// Note what is absent: `cache=shared`. Under a shared cache an
+// in-process conflict is reported as SQLITE_LOCKED rather than
+// SQLITE_BUSY, and the busy handler does not retry SQLITE_LOCKED — so
+// leaving it in would have defeated the busy timeout for exactly the
+// contention this service generates. Dropping it is part of the fix,
+// not housekeeping.
+//
+// synchronous is deliberately left at SQLite's default of FULL: this
+// is a webhook receiver whose one promise is that an event it answered
+// 200 for is durable.
+// The order of the _pragma parameters is load-bearing.
+// modernc.org/sqlite executes them in the order they appear, on every
+// new connection, before the connection is handed to the pool. Setting
+// journal_mode first means that pragma itself runs with no busy
+// handler installed: the pool opens connections lazily, so the moment
+// a new one is created is a moment the database is under load, and
+// PRAGMA journal_mode takes a lock. It would fail immediately with
+// SQLITE_BUSY and fail the query that caused the connection to be
+// opened. busy_timeout is therefore set first, so every pragma after
+// it — and the whole life of the connection — is covered.
+func SQLiteDSN(path, mode string) string {
+	q := url.Values{}
+	q.Set("mode", mode)
+	q.Set("_txlock", "immediate")
+	q.Add(
+		"_pragma",
+		fmt.Sprintf(
+			"busy_timeout(%d)",
+			SQLiteBusyTimeout.Milliseconds(),
+		),
+	)
+	q.Add("_pragma", "journal_mode(WAL)")
+
+	return "file:" + path + "?" + q.Encode()
+}
+
+// OpenSQLite opens the SQLite file at path with the service's
+// durability settings and pool bounds applied. mode is the SQLite URI
+// open mode ("rwc" or "rw").
+//
+// The file and its WAL sidecars are settled at SQLiteFilePerm before
+// the driver sees the path; see reserveSQLiteFile.
+//
+// The handle is returned rather than a *gorm.DB because the callers
+// wrap it in gorm themselves with their own logger.
+func OpenSQLite(path, mode string) (*sql.DB, error) {
+	err := reserveSQLiteFile(path, mode == SQLiteModeCreate)
+	if err != nil {
+		return nil, err
+	}
+
+	sqlDB, err := sql.Open("sqlite", SQLiteDSN(path, mode))
+	if err != nil {
+		return nil, fmt.Errorf(
+			"opening sqlite database %s: %w", path, err,
+		)
+	}
+
+	sqlDB.SetMaxOpenConns(sqliteMaxOpenConns)
+	sqlDB.SetMaxIdleConns(sqliteMaxIdleConns)
+	sqlDB.SetConnMaxLifetime(sqliteConnMaxLifetime)
+	sqlDB.SetConnMaxIdleTime(sqliteConnMaxIdleTime)
+
+	return sqlDB, nil
+}

internal/database/sqlite_open_test.go

@@ -0,0 +1,178 @@
+package database_test
+
+import (
+	"context"
+	"path/filepath"
+	"strings"
+	"testing"
+
+	"github.com/google/uuid"
+	"github.com/stretchr/testify/assert"
+	"github.com/stretchr/testify/require"
+	"gorm.io/gorm"
+	"sneak.berlin/go/webhooker/internal/database"
+)
+
+// livePragma reads a pragma off a live handle. Reading the DSN back
+// would prove only that the string was built; these tests assert that
+// SQLite actually applied it.
+func livePragma(t *testing.T, db *gorm.DB, name string) string {
+	t.Helper()
+
+	var v string
+
+	row := db.Raw("pragma " + name).Row()
+	require.NoError(t, row.Scan(&v))
+
+	return v
+}
+
+func TestSQLiteDSNCarriesTheDurabilitySettings(t *testing.T) {
+	t.Parallel()
+
+	dsn := database.SQLiteDSN(
+		"/var/lib/webhooker/webhooker.db",
+		database.SQLiteModeCreate,
+	)
+
+	assert.Contains(t, dsn, "journal_mode%28WAL%29")
+	assert.Contains(t, dsn, "busy_timeout%2810000%29")
+	assert.Contains(t, dsn, "_txlock=immediate")
+	assert.Contains(t, dsn, "mode=rwc")
+
+	// busy_timeout must come first. The driver runs these in order on
+	// every new connection, and PRAGMA journal_mode takes a lock — a
+	// connection opened while the database is busy would fail on that
+	// pragma, with no busy handler yet installed to wait it out.
+	assert.Less(
+		t,
+		strings.Index(dsn, "busy_timeout"),
+		strings.Index(dsn, "journal_mode"),
+		"busy_timeout must be applied before journal_mode",
+	)
+
+	// cache=shared turns an in-process conflict into SQLITE_LOCKED,
+	// which the busy handler does not retry. It must never come back.
+	// See https://git.eeqj.de/sneak/webhooker/issues/256.
+	assert.NotContains(t, strings.ToLower(dsn), "cache=shared")
+}
+
+// TestPerWebhookDBAppliesPragmasOnALiveHandle is the check the issue
+// asks for by name: the settings are confirmed by querying the running
+// database, not by inspecting the connection string.
+func TestPerWebhookDBAppliesPragmasOnALiveHandle(t *testing.T) {
+	t.Parallel()
+
+	mgr, lc := setupTestWebhookDBManager(t)
+	ctx := context.Background()
+	require.NoError(t, lc.Start(ctx))
+
+	defer func() { require.NoError(t, lc.Stop(ctx)) }()
+
+	webhookID := uuid.New().String()
+
+	db, err := mgr.GetDB(webhookID)
+	require.NoError(t, err)
+
+	assert.Equal(
+		t, "wal",
+		strings.ToLower(livePragma(t, db, "journal_mode")),
+	)
+	assert.Equal(
+		t, "10000", livePragma(t, db, "busy_timeout"),
+	)
+}
+
+func TestMainDBAppliesPragmasOnALiveHandle(t *testing.T) {
+	t.Parallel()
+
+	ctx := context.Background()
+	dir := t.TempDir()
+
+	sqlDB, err := database.OpenSQLite(
+		filepath.Join(dir, database.MainDBFileName),
+		database.SQLiteModeCreate,
+	)
+	require.NoError(t, err)
+
+	defer func() { require.NoError(t, sqlDB.Close()) }()
+
+	var journal string
+
+	require.NoError(t, sqlDB.
+		QueryRowContext(ctx, "pragma journal_mode").
+		Scan(&journal))
+	assert.Equal(t, "wal", strings.ToLower(journal))
+
+	var busy string
+
+	require.NoError(t, sqlDB.
+		QueryRowContext(ctx, "pragma busy_timeout").
+		Scan(&busy))
+	assert.Equal(t, "10000", busy)
+}
+
+// TestConcurrentReaderDoesNotBlockWrites is the unit-scale form of the
+// reproduction in
+// https://git.eeqj.de/sneak/webhooker/issues/256: an operator's
+// long-held read of their own data used to make every concurrent write
+// fail. Under WAL the reader takes a snapshot and the writes proceed.
+func TestConcurrentReaderDoesNotBlockWrites(t *testing.T) {
+	t.Parallel()
+
+	mgr, lc := setupTestWebhookDBManager(t)
+	ctx := context.Background()
+	require.NoError(t, lc.Start(ctx))
+
+	defer func() { require.NoError(t, lc.Stop(ctx)) }()
+
+	webhookID := uuid.New().String()
+
+	db, err := mgr.GetDB(webhookID)
+	require.NoError(t, err)
+
+	// A second handle on the same file, holding a read transaction
+	// open across every write below — what `sqlite3 <db> .dump` is.
+	readerSQL, err := database.OpenSQLite(
+		mgr.DBPath(webhookID), database.SQLiteModeExisting,
+	)
+	require.NoError(t, err)
+
+	defer func() { require.NoError(t, readerSQL.Close()) }()
+
+	readerConn, err := readerSQL.Conn(ctx)
+	require.NoError(t, err)
+
+	defer func() { require.NoError(t, readerConn.Close()) }()
+
+	_, err = readerConn.ExecContext(ctx, "begin deferred")
+	require.NoError(t, err)
+
+	_, err = readerConn.ExecContext(
+		ctx, "select count(*) from events",
+	)
+	require.NoError(t, err)
+
+	for range 25 {
+		err = db.Transaction(func(tx *gorm.DB) error {
+			return tx.Create(&database.Event{
+				WebhookID:    webhookID,
+				EntrypointID: uuid.New().String(),
+				Method:       "POST",
+				Body:         "{}",
+			}).Error
+		})
+		require.NoError(t, err)
+	}
+
+	_, err = readerConn.ExecContext(ctx, "commit")
+	require.NoError(t, err)
+
+	var count int64
+
+	require.NoError(
+		t,
+		db.Model(&database.Event{}).Count(&count).Error,
+	)
+	assert.Equal(t, int64(25), count)
+}

internal/database/webhook_db_manager.go

@@ -2,7 +2,6 @@ package database
 
 import (
 	"context"
-	"database/sql"
 	"errors"
 	"fmt"
 	"log/slog"
@@ -234,12 +233,11 @@ func (m *WebhookDBManager) openDB(
 	webhookID string,
 ) (*gorm.DB, error) {
 	path := m.dbPath(webhookID)
-	dbURL := fmt.Sprintf(
-		"file:%s?cache=shared&mode=rwc",
-		path,
-	)
 
-	sqlDB, err := sql.Open("sqlite", dbURL)
+	// See sqlite_open.go: WAL, a busy timeout, immediate-transaction
+	// locking, and a bounded pool, all of which this file needs most —
+	// it is the one every delivery worker writes to concurrently.
+	sqlDB, err := OpenSQLite(path, SQLiteModeCreate)
 	if err != nil {
 		return nil, fmt.Errorf(
 			"opening webhook database %s: %w",

internal/delivery/engine_integration_test.go

@@ -2,7 +2,6 @@ package delivery_test
 
 import (
 	"context"
-	"database/sql"
 	"encoding/json"
 	"fmt"
 	"io"
@@ -70,11 +69,12 @@ func iMainDB(t *testing.T) *gorm.DB {
 		t.TempDir(), "main-test.db",
 	)
 
-	dsn := fmt.Sprintf(
+	// Opened the way the service opens the main database, so these
-		"file:%s?cache=shared&mode=rwc", dbPath,
+	// tests cannot pass against journal and locking settings
+	// production does not use.
+	sqlDB, err := database.OpenSQLite(
+		dbPath, database.SQLiteModeCreate,
 	)
-
-	sqlDB, err := sql.Open("sqlite", dsn)
 	require.NoError(t, err)
 
 	t.Cleanup(func() { _ = sqlDB.Close() })
@@ -377,6 +377,17 @@ func TestProcessRetryTask_SuccessfulRetry(t *testing.T) {
 
 	bodyStr := event.Body
 	cfg := iHTTPConfig(ts.URL)
+
+	// The target row exists because the engine confirms a scheduled
+	// retry's target has not been deleted before it runs it. A retry
+	// task whose target id names no row at all is a state the service
+	// does not produce: the handler read that target to build the
+	// task. See https://git.eeqj.de/sneak/webhooker/issues/107.
+	iCreateTarget(
+		t, s.MainDB, targetID, s.WebhookID, "retry-target",
+		database.TargetTypeHTTP, cfg, 5,
+	)
+
 	task := iTask(
 		d, event, s.WebhookID, targetID,
 		"retry-target", cfg, 5, 2, &bodyStr,
@@ -456,6 +467,12 @@ func TestProcessRetryTask_LargeBody_FetchFromDB(
 	)
 
 	cfg := iHTTPConfig(ts.URL)
+
+	iCreateTarget(
+		t, s.MainDB, targetID, s.WebhookID, "retry-large",
+		database.TargetTypeHTTP, cfg, 5,
+	)
+
 	task := iTask(
 		d, event, s.WebhookID, targetID,
 		"retry-large", cfg, 5, 2, nil,
@@ -558,6 +575,12 @@ func TestWorkerLifecycle_ProcessesRetryChannel(
 
 	bodyStr := event.Body
 	cfg := iHTTPConfig(ts.URL)
+
+	iCreateTarget(
+		t, s.MainDB, targetID, s.WebhookID, "retry-chan-test",
+		database.TargetTypeHTTP, cfg, 5,
+	)
+
 	task := iTask(
 		d, event, s.WebhookID, targetID,
 		"retry-chan-test", cfg, 5, 2, &bodyStr,

internal/delivery/engine_test.go

@@ -3,7 +3,6 @@ package delivery_test
 import (
 	"bytes"
 	"context"
-	"database/sql"
 	"encoding/json"
 	"fmt"
 	"log/slog"
@@ -37,11 +36,12 @@ func testWebhookDB(t *testing.T) *gorm.DB {
 		t.TempDir(), "events-test.db",
 	)
 
-	dsn := fmt.Sprintf(
+	// Opened the way the service opens a per-webhook database, so
-		"file:%s?cache=shared&mode=rwc", dbPath,
+	// these tests cannot pass against journal and locking settings
+	// production does not use.
+	sqlDB, err := database.OpenSQLite(
+		dbPath, database.SQLiteModeCreate,
 	)
-
-	sqlDB, err := sql.Open("sqlite", dsn)
 	require.NoError(t, err)
 
 	t.Cleanup(func() { _ = sqlDB.Close() })

internal/delivery/event_db_isolation_test.go

@@ -96,7 +96,15 @@ func TestEventDBHoldsNoTargetRows(t *testing.T) {
 	)
 	assertNoTargetRows(t, dbPath)
 
-	// A retry.
+	// A retry. Its target exists in the main database, because the
+	// engine confirms a scheduled retry's target has not been
+	// deleted before running it; see
+	// https://git.eeqj.de/sneak/webhooker/issues/107.
+	iCreateTarget(
+		t, s.MainDB, targetID, s.WebhookID, "leaky-target",
+		database.TargetTypeHTTP, cfg, 5,
+	)
+
 	rd := iSeedDelivery(
 		t, s.WebhookDB, event.ID, targetID,
 		database.DeliveryStatusRetrying,

internal/delivery/event_timestamp_test.go

@@ -0,0 +1,442 @@
+package delivery_test
+
+import (
+	"context"
+	"encoding/json"
+	"io"
+	"net/http"
+	"net/http/httptest"
+	"testing"
+	"time"
+
+	"github.com/google/uuid"
+	"github.com/stretchr/testify/assert"
+	"github.com/stretchr/testify/require"
+	"gorm.io/gorm"
+	"sneak.berlin/go/webhooker/internal/database"
+	"sneak.berlin/go/webhooker/internal/delivery"
+)
+
+// tsEventCreatedAt is the receipt time seeded on the events these
+// tests deliver. It is far enough from both the zero time and from
+// now that neither can be mistaken for it.
+func tsEventCreatedAt() time.Time {
+	return time.Date(
+		2026, time.March, 4, 5, 6, 7, 0, time.UTC,
+	)
+}
+
+// tsZeroStamp is what a Slack message renders when the event handed
+// to FormatSlackMessage carries no CreatedAt.
+const tsZeroStamp = "*Timestamp:* `0001-01-01T00:00:00Z`"
+
+// tsEventBody is the body seeded on every event in this file. It is
+// small enough that a Task can inline it.
+const tsEventBody = `{"hello":"world"}`
+
+// tsUndeliverableHook stands in for a Slack incoming webhook on the
+// tests that never send: the config parser requires a URL, but no
+// request is made.
+const tsUndeliverableHook = "https://hooks.slack.com/services/T/B/x"
+
+// tsSink is a stand-in Slack incoming webhook that records the raw
+// body posted to it.
+type tsSink struct {
+	*httptest.Server
+
+	bodies chan []byte
+}
+
+func newTSSink(t *testing.T) *tsSink {
+	t.Helper()
+
+	s := &tsSink{bodies: make(chan []byte, 8)}
+
+	s.Server = httptest.NewServer(http.HandlerFunc(
+		func(w http.ResponseWriter, r *http.Request) {
+			body, _ := io.ReadAll(r.Body)
+
+			select {
+			case s.bodies <- body:
+			default:
+			}
+
+			w.WriteHeader(http.StatusOK)
+		},
+	))
+
+	t.Cleanup(s.Close)
+
+	return s
+}
+
+// text returns the Slack message text from the single payload the
+// sink received.
+func (s *tsSink) text(t *testing.T) string {
+	t.Helper()
+
+	select {
+	case raw := <-s.bodies:
+		t.Logf("raw slack payload: %s", raw)
+
+		var payload struct {
+			Text string `json:"text"`
+		}
+
+		require.NoError(t, json.Unmarshal(raw, &payload))
+
+		return payload.Text
+	case <-time.After(5 * time.Second):
+		t.Fatal("slack sink received no payload")
+
+		return ""
+	}
+}
+
+func tsSlackConfig(t *testing.T, url string) string {
+	t.Helper()
+
+	data, err := json.Marshal(
+		delivery.SlackTargetConfig{WebhookURL: url},
+	)
+	require.NoError(t, err)
+
+	return string(data)
+}
+
+// tsSeedEvent writes an event whose CreatedAt is tsEventCreatedAt
+// rather than the write time, so an assertion on the rendered
+// timestamp cannot pass by accident against "roughly now".
+func tsSeedEvent(
+	t *testing.T, db *gorm.DB, webhookID string,
+) database.Event {
+	t.Helper()
+
+	event := database.Event{
+		WebhookID:    webhookID,
+		EntrypointID: uuid.New().String(),
+		Method:       http.MethodPost,
+		Headers:      `{}`,
+		Body:         tsEventBody,
+		ContentType:  "application/json",
+	}
+	event.ID = uuid.New().String()
+	event.CreatedAt = tsEventCreatedAt()
+	event.UpdatedAt = tsEventCreatedAt()
+
+	require.NoError(t, db.Create(&event).Error)
+
+	var stored database.Event
+
+	require.NoError(t,
+		db.First(&stored, "id = ?", event.ID).Error,
+	)
+	require.Equal(t,
+		tsEventCreatedAt().UTC(), stored.CreatedAt.UTC(),
+		"seeded created_at did not round-trip",
+	)
+
+	return event
+}
+
+// tsSeedTarget writes the slack target row into the main database.
+// The retry path confirms the target still exists before sending.
+func tsSeedTarget(
+	t *testing.T, mainDB *gorm.DB, webhookID, config string,
+) database.Target {
+	t.Helper()
+
+	target := database.Target{
+		WebhookID: webhookID,
+		Name:      "slack-sink",
+		Type:      database.TargetTypeSlack,
+		Config:    config,
+		Active:    true,
+	}
+
+	require.NoError(t, mainDB.Create(&target).Error)
+
+	return target
+}
+
+func tsTask(
+	d database.Delivery,
+	event database.Event,
+	webhookID string,
+	target database.Target,
+	attemptNum int,
+	body *string,
+) delivery.Task {
+	return delivery.Task{
+		DeliveryID:   d.ID,
+		EventID:      event.ID,
+		WebhookID:    webhookID,
+		EntrypointID: event.EntrypointID,
+		TargetID:     target.ID,
+		TargetName:   target.Name,
+		TargetType:   database.TargetTypeSlack,
+		TargetConfig: target.Config,
+		MaxRetries:   0,
+		Method:       event.Method,
+		Headers:      event.Headers,
+		ContentType:  event.ContentType,
+		Body:         body,
+		AttemptNum:   attemptNum,
+	}
+}
+
+func tsAssertRealTimestamp(t *testing.T, text string) {
+	t.Helper()
+
+	assert.NotContains(t, text, tsZeroStamp,
+		"slack message carries the zero timestamp",
+	)
+	assert.Contains(t, text,
+		"*Timestamp:* `"+
+			tsEventCreatedAt().UTC().Format(time.RFC3339)+"`",
+		"slack message does not carry the event's receipt time",
+	)
+}
+
+// tsCase is one end-to-end delivery of a seeded event to a slack
+// sink, over whichever engine path `process` names.
+type tsCase struct {
+	// status is the delivery row's status before the engine runs.
+	// The retry path refuses a delivery that is not retrying.
+	status database.DeliveryStatus
+
+	// inlineBody mirrors a Task built for a body under
+	// MaxInlineBodySize. When false the engine reads the body back
+	// from the stored row.
+	inlineBody bool
+
+	attemptNum int
+
+	process func(
+		ctx context.Context, e *delivery.Engine, task *delivery.Task,
+	)
+}
+
+// run delivers one event through the named path and returns the
+// Slack message text the sink received.
+func (c tsCase) run(t *testing.T) (iSetup, database.Delivery, string) {
+	t.Helper()
+
+	s := newISetup(t)
+	sink := newTSSink(t)
+
+	cfg := tsSlackConfig(t, sink.URL)
+	target := tsSeedTarget(t, s.MainDB, s.WebhookID, cfg)
+	event := tsSeedEvent(t, s.WebhookDB, s.WebhookID)
+
+	d := iSeedDelivery(
+		t, s.WebhookDB, event.ID, target.ID, c.status,
+	)
+
+	var body *string
+
+	if c.inlineBody {
+		bodyStr := event.Body
+		body = &bodyStr
+	}
+
+	task := tsTask(
+		d, event, s.WebhookID, target, c.attemptNum, body,
+	)
+
+	c.process(context.TODO(), s.Engine, &task)
+
+	return s, d, sink.text(t)
+}
+
+// TestSlackFirstAttemptCarriesEventTimestamp covers the path an
+// event takes on its first delivery: the task comes from the
+// receiver and the engine reconstructs the event from it.
+func TestSlackFirstAttemptCarriesEventTimestamp(t *testing.T) {
+	t.Parallel()
+
+	s, d, text := tsCase{
+		status:     database.DeliveryStatusPending,
+		inlineBody: true,
+		attemptNum: 1,
+		process: func(
+			ctx context.Context,
+			e *delivery.Engine,
+			task *delivery.Task,
+		) {
+			e.ExportProcessNewTask(ctx, task)
+		},
+	}.run(t)
+
+	tsAssertRealTimestamp(t, text)
+
+	iAssertStatus(t, s.WebhookDB, d.ID,
+		database.DeliveryStatusDelivered,
+	)
+}
+
+// TestSlackFirstAttemptLargeBodyCarriesEventTimestamp covers the
+// first-attempt path for an event whose body exceeded
+// MaxInlineBodySize, so the task carries no body and the engine
+// reads it back from the stored row.
+func TestSlackFirstAttemptLargeBodyCarriesEventTimestamp(
+	t *testing.T,
+) {
+	t.Parallel()
+
+	_, _, text := tsCase{
+		status:     database.DeliveryStatusPending,
+		inlineBody: false,
+		attemptNum: 1,
+		process: func(
+			ctx context.Context,
+			e *delivery.Engine,
+			task *delivery.Task,
+		) {
+			e.ExportProcessNewTask(ctx, task)
+		},
+	}.run(t)
+
+	tsAssertRealTimestamp(t, text)
+}
+
+// TestSlackRetryCarriesEventTimestamp covers the retry path, which
+// reconstructs the event from the same task the first attempt used.
+func TestSlackRetryCarriesEventTimestamp(t *testing.T) {
+	t.Parallel()
+
+	s, d, text := tsCase{
+		status:     database.DeliveryStatusRetrying,
+		inlineBody: true,
+		attemptNum: 2,
+		process: func(
+			ctx context.Context,
+			e *delivery.Engine,
+			task *delivery.Task,
+		) {
+			e.ExportProcessRetryTask(ctx, task)
+		},
+	}.run(t)
+
+	tsAssertRealTimestamp(t, text)
+
+	iAssertStatus(t, s.WebhookDB, d.ID,
+		database.DeliveryStatusDelivered,
+	)
+}
+
+// TestFormatSlackMessageOverTaskReconstructedEvent asserts on the
+// formatted message directly, over the event the delivery paths
+// reconstruct from a Task. It is the unit-level guard under the
+// end-to-end tests: revert the CreatedAt population in hydrateEvent
+// and this fails on the zero timestamp.
+func TestFormatSlackMessageOverTaskReconstructedEvent(
+	t *testing.T,
+) {
+	t.Parallel()
+
+	s := newISetup(t)
+
+	cfg := tsSlackConfig(t, tsUndeliverableHook)
+	target := tsSeedTarget(t, s.MainDB, s.WebhookID, cfg)
+	event := tsSeedEvent(t, s.WebhookDB, s.WebhookID)
+
+	d := iSeedDelivery(
+		t, s.WebhookDB, event.ID, target.ID,
+		database.DeliveryStatusPending,
+	)
+
+	bodyStr := event.Body
+	task := tsTask(d, event, s.WebhookID, target, 1, &bodyStr)
+
+	rebuilt, err := s.Engine.ExportEventForTask(
+		s.WebhookDB, &task,
+	)
+	require.NoError(t, err)
+	assert.False(t, rebuilt.CreatedAt.IsZero(),
+		"reconstructed event carries the zero time",
+	)
+	assert.Equal(t,
+		tsEventCreatedAt().UTC(), rebuilt.CreatedAt.UTC(),
+	)
+
+	tsAssertRealTimestamp(
+		t, delivery.FormatSlackMessage(&rebuilt),
+	)
+}
+
+// TestFormatSlackMessageZeroTimestamp asserts the rendering choice
+// directly, without going through the engine: a zero CreatedAt (the
+// shape a reaped-row fallback produces) renders as "unknown" rather
+// than the year-1 zero time, while a real CreatedAt still renders as
+// RFC3339.
+func TestFormatSlackMessageZeroTimestamp(t *testing.T) {
+	t.Parallel()
+
+	zeroEvent := database.Event{
+		Method:      http.MethodPost,
+		ContentType: testContentType,
+		Body:        tsEventBody,
+	}
+
+	zeroText := delivery.FormatSlackMessage(&zeroEvent)
+
+	assert.NotContains(t, zeroText, "0001-01-01",
+		"slack message carries the zero-time year",
+	)
+	assert.Contains(t, zeroText, "*Timestamp:* `unknown`",
+		"slack message does not mark an unset receipt time as unknown",
+	)
+
+	nonZeroEvent := zeroEvent
+	nonZeroEvent.CreatedAt = tsEventCreatedAt()
+
+	nonZeroText := delivery.FormatSlackMessage(&nonZeroEvent)
+
+	assert.Contains(t, nonZeroText,
+		"*Timestamp:* `"+
+			tsEventCreatedAt().UTC().Format(time.RFC3339)+"`",
+		"slack message does not render a real receipt time as RFC3339",
+	)
+}
+
+// TestEventReconstructionSurvivesAReapedRow pins the fallback: an
+// event row reaped by retention while its delivery still holds the
+// body inline is still delivered, with the receipt time unset,
+// rather than dropped.
+func TestEventReconstructionSurvivesAReapedRow(t *testing.T) {
+	t.Parallel()
+
+	s := newISetup(t)
+
+	cfg := tsSlackConfig(t, tsUndeliverableHook)
+	target := tsSeedTarget(t, s.MainDB, s.WebhookID, cfg)
+	event := tsSeedEvent(t, s.WebhookDB, s.WebhookID)
+
+	d := iSeedDelivery(
+		t, s.WebhookDB, event.ID, target.ID,
+		database.DeliveryStatusPending,
+	)
+
+	bodyStr := event.Body
+	task := tsTask(d, event, s.WebhookID, target, 1, &bodyStr)
+
+	require.NoError(t, s.WebhookDB.Unscoped().Delete(
+		&database.Event{}, "id = ?", event.ID,
+	).Error)
+
+	rebuilt, err := s.Engine.ExportEventForTask(
+		s.WebhookDB, &task,
+	)
+	require.NoError(t, err)
+	assert.Equal(t, bodyStr, rebuilt.Body)
+	assert.True(t, rebuilt.CreatedAt.IsZero())
+
+	// A task with no inlined body has nothing left to deliver, so
+	// the same reaped row is an error there.
+	noBody := task
+	noBody.Body = nil
+
+	_, err = s.Engine.ExportEventForTask(s.WebhookDB, &noBody)
+	require.Error(t, err)
+}

internal/delivery/export_test.go

@@ -33,6 +33,11 @@ const (
 	// response is written against this number, so a test has to
 	// be able to name it.
 	ExportMaxBodyLog = maxBodyLog
+
+	// ExportPendingSweepMinAge is how long a delivery must sit at
+	// pending before the sweep treats it as stranded. A test has to
+	// name it to age a row past the bound.
+	ExportPendingSweepMinAge = pendingSweepMinAge
 )
 
 // ExportIsBlockedIP exposes isBlockedIP for testing.
@@ -146,6 +151,16 @@ func (e *Engine) ExportProcessRetryTask(
 	e.processRetryTask(ctx, task)
 }
 
+// ExportEventForTask exposes the event reconstruction the delivery
+// paths run: buildEventFromTask followed by hydrateEvent.
+func (e *Engine) ExportEventForTask(
+	webhookDB *gorm.DB, task *Task,
+) (database.Event, error) {
+	return e.hydrateEvent(
+		webhookDB, buildEventFromTask(task), task,
+	)
+}
+
 // ExportProcessDelivery exposes processDelivery.
 func (e *Engine) ExportProcessDelivery(
 	ctx context.Context,
@@ -286,6 +301,26 @@ func (e *Engine) ExportWedgeWorker(release <-chan struct{}) {
 	})
 }
 
+// ExportInflightHeld reports how many deliveries the engine currently
+// owns, so a test can prove ownership is released rather than leaked.
+func (e *Engine) ExportInflightHeld() int {
+	return e.inflight.held()
+}
+
+// ExportRetainDelivery takes the first reference on a delivery, as the
+// queueing side does. It lets a test put a delivery into the state a
+// worker or a full channel would, without running the pool.
+func (e *Engine) ExportRetainDelivery(deliveryID string) bool {
+	return e.inflight.retainIdle(deliveryID)
+}
+
+// ExportRecoverRetryingDeliveries exposes recoverRetryingDeliveries.
+func (e *Engine) ExportRecoverRetryingDeliveries(
+	webhookDB *gorm.DB, webhookID string,
+) {
+	e.recoverRetryingDeliveries(webhookDB, webhookID)
+}
+
 // ExportDeliveryCh returns the delivery channel.
 func (e *Engine) ExportDeliveryCh() chan Task {
 	return e.deliveryCh

internal/delivery/inflight.go

@@ -0,0 +1,110 @@
+package delivery
+
+import "sync"
+
+// inflightSet records which deliveries the engine currently owns.
+//
+// A delivery is owned from the moment a task for it is handed to a
+// channel or to a retry timer until the engine has no further plan for
+// it in memory. Restart recovery and both arms of the periodic sweep
+// re-dispatch only deliveries the set does not hold, which is what
+// makes them exact rather than a guess about how long a row has sat at
+// pending.
+//
+// This replaces reasoning from timestamps. A delivery's row says
+// pending from creation until its outcome is written, which covers
+// four different situations — never dispatched, waiting in a channel,
+// being attempted right now, and genuinely stranded — and no column
+// distinguishes them. Only the engine knows which, and it knows
+// exactly. `deliveryChannelSize` is 10000 against 10 workers, so a
+// perfectly healthy delivery can wait far longer than any age bound
+// worth setting before its attempt even begins; an age bound alone
+// re-sends it. See
+// https://git.eeqj.de/sneak/webhooker/issues/256.
+//
+// In-memory state is sufficient because a data directory admits one
+// process: internal/datadir takes an flock on it at startup and a
+// second instance refuses to run. Deliveries owned by a process that
+// died are not in any successor's set, and restart recovery is what
+// picks those up.
+//
+// References are counted rather than held as a plain set because
+// ownership outlives the worker that took it. A target that schedules
+// a retry from inside Deliver adds a reference while the worker still
+// holds one, so the delivery stays owned across the gap between the
+// worker returning and the timer firing — the window in which a sweep
+// would otherwise find the row at retrying and send it again.
+//
+// The zero value is ready to use, and the Engine holds one by value.
+// That is deliberate: an engine built by a constructor that forgot to
+// initialise this would not refuse to re-dispatch anything, and the
+// symptom would be duplicate deliveries rather than a failure anybody
+// notices.
+type inflightSet struct {
+	mu  sync.Mutex
+	ids map[string]int
+}
+
+// retain adds a reference to a delivery the caller already knows the
+// engine owns, so that ownership survives the current holder letting
+// go. It cannot fail.
+func (s *inflightSet) retain(deliveryID string) {
+	s.mu.Lock()
+	defer s.mu.Unlock()
+
+	if s.ids == nil {
+		s.ids = make(map[string]int)
+	}
+
+	s.ids[deliveryID]++
+}
+
+// retainIdle takes the first reference on a delivery, and reports
+// whether it got it. It fails when the engine already owns the
+// delivery, which is what makes two claimants — restart recovery and
+// the sweep run concurrently, or two sweep arms — mutually exclusive
+// rather than merely atomic.
+func (s *inflightSet) retainIdle(deliveryID string) bool {
+	s.mu.Lock()
+	defer s.mu.Unlock()
+
+	if s.ids[deliveryID] > 0 {
+		return false
+	}
+
+	if s.ids == nil {
+		s.ids = make(map[string]int)
+	}
+
+	s.ids[deliveryID] = 1
+
+	return true
+}
+
+// release drops one reference. The delivery becomes eligible for
+// re-dispatch again once the last one goes.
+func (s *inflightSet) release(deliveryID string) {
+	s.mu.Lock()
+	defer s.mu.Unlock()
+
+	n := s.ids[deliveryID] - 1
+	if n <= 0 {
+		delete(s.ids, deliveryID)
+
+		return
+	}
+
+	s.ids[deliveryID] = n
+}
+
+// held reports how many deliveries the engine currently owns. It
+// exists so a test can assert that ownership is released rather than
+// leaked: a reference that is never dropped hides its delivery from
+// every sweep for the life of the process, which is the one way this
+// mechanism can fail silently.
+func (s *inflightSet) held() int {
+	s.mu.Lock()
+	defer s.mu.Unlock()
+
+	return len(s.ids)
+}

internal/delivery/inflight_test.go

@@ -0,0 +1,428 @@
+package delivery_test
+
+import (
+	"context"
+	"path/filepath"
+	"strings"
+	"sync"
+	"testing"
+	"time"
+
+	"github.com/google/uuid"
+	"github.com/stretchr/testify/assert"
+	"github.com/stretchr/testify/require"
+	"sneak.berlin/go/webhooker/internal/database"
+	"sneak.berlin/go/webhooker/internal/delivery"
+)
+
+// These tests pin the rule that decides whether a delivery may be
+// handed back to a worker: the engine re-dispatches only what it does
+// not already own. Age alone is not that rule — a healthy delivery
+// waiting in a 10000-deep channel is old and must not be re-sent. See
+// https://git.eeqj.de/sneak/webhooker/issues/256.
+
+// fSweepSetup seeds the main database with the webhook row the sweep
+// enumerates, and returns the setup.
+func fSweepSetup(
+	t *testing.T, targetID, name string,
+) iSetup {
+	t.Helper()
+
+	s := newISetup(t)
+
+	iCreateTarget(t, s.MainDB, targetID,
+		s.WebhookID, name,
+		database.TargetTypeLog, "", 0,
+	)
+
+	require.NoError(t, s.MainDB.Create(&database.Webhook{
+		BaseModel: database.BaseModel{ID: s.WebhookID},
+		UserID:    uuid.New().String(),
+		Name:      name,
+	}).Error)
+
+	return s
+}
+
+// fDrain collects every task the engine has queued.
+//
+// Every caller drives the dispatch paths synchronously and has already
+// waited for them to return, so anything they queued is in the channel
+// by now. The short grace covers nothing but scheduler jitter, and is
+// kept small because one of these tests runs the drain forty times.
+func fDrain(e *delivery.Engine) []delivery.Task {
+	var out []delivery.Task
+
+	for {
+		select {
+		case task := <-e.ExportDeliveryCh():
+			out = append(out, task)
+		case task := <-e.ExportRetryCh():
+			out = append(out, task)
+		case <-time.After(25 * time.Millisecond):
+			return out
+		}
+	}
+}
+
+// TestArchiveHandleIsWAL closes the last gap in the durability
+// evidence: the main and per-webhook tiers each assert their journal
+// mode on a live handle, and the archive tier gets its settings from
+// the same code path but nothing checked the running file.
+func TestArchiveHandleIsWAL(t *testing.T) {
+	t.Parallel()
+
+	w := delivery.NewExportArchiveWriter(
+		filepath.Join(t.TempDir(), "archive-wal.db"),
+		archiveTestLogger(), 0,
+	)
+
+	require.NoError(t, w.Open(0))
+
+	var mode string
+
+	row := w.DB().Raw("pragma journal_mode").Row()
+	require.NoError(t, row.Scan(&mode))
+	assert.Equal(t, "wal", strings.ToLower(mode))
+
+	var busy string
+
+	row = w.DB().Raw("pragma busy_timeout").Row()
+	require.NoError(t, row.Scan(&busy))
+	assert.Equal(t, "10000", busy)
+}
+
+// TestSweepLeavesAQueuedDeliveryAlone is the case the age bound cannot
+// see. The delivery is queued and untouched, so its row is arbitrarily
+// old and still perfectly healthy; only ownership distinguishes it
+// from a stranded one.
+func TestSweepLeavesAQueuedDeliveryAlone(t *testing.T) {
+	t.Parallel()
+
+	targetID := uuid.New().String()
+	s := fSweepSetup(t, targetID, "queued")
+
+	event := iSeedEvent(
+		t, s.WebhookDB, s.WebhookID, `{"queued":true}`,
+	)
+
+	d := iSeedDelivery(
+		t, s.WebhookDB, event.ID, targetID,
+		database.DeliveryStatusPending,
+	)
+	rAgePending(t, s.WebhookDB, d.ID)
+
+	// Queued exactly as the receiver queues it, and never dequeued:
+	// no workers are running in this engine.
+	s.Engine.Notify([]delivery.Task{{
+		DeliveryID: d.ID,
+		EventID:    event.ID,
+		WebhookID:  s.WebhookID,
+		TargetID:   targetID,
+	}})
+
+	require.Equal(t, 1, s.Engine.ExportInflightHeld())
+
+	s.Engine.ExportSweepWebhookRetries(
+		context.Background(), s.WebhookID,
+	)
+
+	tasks := fDrain(s.Engine)
+	assert.Len(
+		t, tasks, 1,
+		"the sweep must not queue a delivery that is "+
+			"already waiting for a worker",
+	)
+}
+
+// TestRecoveryAndSweepDoNotDoubleDispatch drives the two entry points
+// the engine starts concurrently against one aged pending row. Before
+// ownership they both dispatched it.
+func TestRecoveryAndSweepDoNotDoubleDispatch(t *testing.T) {
+	t.Parallel()
+
+	targetID := uuid.New().String()
+	s := fSweepSetup(t, targetID, "racing")
+
+	event := iSeedEvent(
+		t, s.WebhookDB, s.WebhookID, `{"racing":true}`,
+	)
+
+	ctx := context.Background()
+
+	for range 40 {
+		d := iSeedDelivery(
+			t, s.WebhookDB, event.ID, targetID,
+			database.DeliveryStatusPending,
+		)
+		rAgePending(t, s.WebhookDB, d.ID)
+
+		var wg sync.WaitGroup
+
+		wg.Go(func() {
+			s.Engine.ExportRecoverPendingDeliveries(
+				ctx, s.WebhookDB, s.WebhookID,
+			)
+		})
+		wg.Go(func() {
+			s.Engine.ExportSweepWebhookRetries(
+				ctx, s.WebhookID,
+			)
+		})
+		wg.Wait()
+
+		tasks := fDrain(s.Engine)
+		require.Len(
+			t, tasks, 1,
+			"delivery %s dispatched %d times",
+			d.ID, len(tasks),
+		)
+
+		// No worker runs in this engine, so the reference the winner
+		// took is never released and earlier iterations' deliveries
+		// stay owned — which is itself the property under test, since
+		// both paths see them on every subsequent pass.
+	}
+}
+
+// TestConcurrentClaimsOfOneDeliveryYieldOneOwner exercises the
+// exclusion directly, rather than arguing it from a SQL predicate.
+func TestConcurrentClaimsOfOneDeliveryYieldOneOwner(
+	t *testing.T,
+) {
+	t.Parallel()
+
+	eng := newISetup(t).Engine
+	deliveryID := uuid.New().String()
+
+	var (
+		wg  sync.WaitGroup
+		mu  sync.Mutex
+		won int
+	)
+
+	for range 64 {
+		wg.Go(func() {
+			if eng.ExportRetainDelivery(deliveryID) {
+				mu.Lock()
+				won++
+				mu.Unlock()
+			}
+		})
+	}
+
+	wg.Wait()
+
+	assert.Equal(t, 1, won)
+	assert.Equal(t, 1, eng.ExportInflightHeld())
+}
+
+// TestOwnershipIsReleasedAfterDelivery guards the other direction: a
+// leaked reference hides a delivery from every sweep for the life of
+// the process.
+func TestOwnershipIsReleasedAfterDelivery(t *testing.T) {
+	t.Parallel()
+
+	s := newISetup(t)
+	targetID := uuid.New().String()
+
+	iCreateTarget(t, s.MainDB, targetID,
+		s.WebhookID, "released",
+		database.TargetTypeLog, "", 0,
+	)
+
+	event := iSeedEvent(
+		t, s.WebhookDB, s.WebhookID, `{"released":true}`,
+	)
+
+	d := iSeedDelivery(
+		t, s.WebhookDB, event.ID, targetID,
+		database.DeliveryStatusPending,
+	)
+
+	s.Engine.ExportStart()
+
+	defer func() {
+		require.NoError(
+			t, s.Engine.ExportStop(context.Background()),
+		)
+	}()
+
+	body := `{"released":true}`
+
+	s.Engine.Notify([]delivery.Task{{
+		DeliveryID:   d.ID,
+		EventID:      event.ID,
+		WebhookID:    s.WebhookID,
+		TargetID:     targetID,
+		TargetName:   "released",
+		TargetType:   database.TargetTypeLog,
+		Body:         &body,
+		EntrypointID: event.EntrypointID,
+	}})
+
+	iWaitForDelivered(t, s.WebhookDB, d.ID)
+
+	assert.Eventually(
+		t,
+		func() bool {
+			return s.Engine.ExportInflightHeld() == 0
+		},
+		2*time.Second, 20*time.Millisecond,
+		"the delivery stayed owned after it was delivered",
+	)
+}
+
+// TestRetryingRecoverySkipsASuccessfulResult is the retrying-side twin
+// of the pending reconcile. A second attempt that reached the receiver
+// and whose status write then failed sits at retrying holding a
+// successful result, and re-sending it is the same duplicate.
+func TestRetryingRecoverySkipsASuccessfulResult(t *testing.T) {
+	t.Parallel()
+
+	targetID := uuid.New().String()
+	s := fSweepSetup(t, targetID, "retry-settled")
+
+	event := iSeedEvent(
+		t, s.WebhookDB, s.WebhookID, `{"retry":true}`,
+	)
+
+	d := iSeedDelivery(
+		t, s.WebhookDB, event.ID, targetID,
+		database.DeliveryStatusRetrying,
+	)
+	rSeedResult(t, s.WebhookDB, d.ID, 1, false)
+	rSeedResult(t, s.WebhookDB, d.ID, 2, true)
+
+	s.Engine.ExportRecoverRetryingDeliveries(
+		s.WebhookDB, s.WebhookID,
+	)
+
+	assert.Empty(
+		t, fDrain(s.Engine),
+		"a retrying delivery holding a successful result "+
+			"must not be sent again",
+	)
+
+	iAssertStatus(
+		t, s.WebhookDB, d.ID,
+		database.DeliveryStatusDelivered,
+	)
+}
+
+// TestRetryingSweepSkipsASuccessfulResult is the same rule on the
+// periodic sweep's retrying arm.
+func TestRetryingSweepSkipsASuccessfulResult(t *testing.T) {
+	t.Parallel()
+
+	targetID := uuid.New().String()
+	s := fSweepSetup(t, targetID, "retry-swept")
+
+	event := iSeedEvent(
+		t, s.WebhookDB, s.WebhookID, `{"swept":true}`,
+	)
+
+	d := iSeedDelivery(
+		t, s.WebhookDB, event.ID, targetID,
+		database.DeliveryStatusRetrying,
+	)
+	rSeedResult(t, s.WebhookDB, d.ID, 1, false)
+	rSeedResult(t, s.WebhookDB, d.ID, 2, true)
+
+	s.Engine.ExportSweepWebhookRetries(
+		context.Background(), s.WebhookID,
+	)
+
+	assert.Empty(t, fDrain(s.Engine))
+
+	iAssertStatus(
+		t, s.WebhookDB, d.ID,
+		database.DeliveryStatusDelivered,
+	)
+
+	var attempts int64
+
+	require.NoError(t, s.WebhookDB.
+		Model(&database.DeliveryResult{}).
+		Where("delivery_id = ?", d.ID).
+		Count(&attempts).Error)
+	assert.Equal(
+		t, int64(2), attempts,
+		"settling must not invent an attempt",
+	)
+}
+
+// TestScheduledRetryIsNotSweptDuringBackoff closes the window between
+// a target scheduling a retry and the timer firing. The row says
+// retrying and nothing is running, which is exactly what an orphaned
+// retry looks like from the database.
+func TestScheduledRetryIsNotSweptDuringBackoff(t *testing.T) {
+	t.Parallel()
+
+	targetID := uuid.New().String()
+	s := fSweepSetup(t, targetID, "backoff")
+
+	event := iSeedEvent(
+		t, s.WebhookDB, s.WebhookID, `{"backoff":true}`,
+	)
+
+	d := iSeedDelivery(
+		t, s.WebhookDB, event.ID, targetID,
+		database.DeliveryStatusRetrying,
+	)
+
+	s.Engine.ExportScheduleRetry(delivery.Task{
+		DeliveryID: d.ID,
+		EventID:    event.ID,
+		WebhookID:  s.WebhookID,
+		TargetID:   targetID,
+		AttemptNum: 2,
+	}, time.Hour)
+
+	require.Equal(t, 1, s.Engine.ExportInflightHeld())
+
+	s.Engine.ExportSweepWebhookRetries(
+		context.Background(), s.WebhookID,
+	)
+
+	assert.Empty(
+		t, fDrain(s.Engine),
+		"the sweep must not duplicate a retry that is "+
+			"already scheduled",
+	)
+}
+
+// TestRedispatchStampsTheRow pins the cadence control: a stranded
+// delivery that has just been handed out is not selected again by the
+// next tick a minute later.
+func TestRedispatchStampsTheRow(t *testing.T) {
+	t.Parallel()
+
+	targetID := uuid.New().String()
+	s := fSweepSetup(t, targetID, "stamped")
+
+	event := iSeedEvent(
+		t, s.WebhookDB, s.WebhookID, `{"stamped":true}`,
+	)
+
+	d := iSeedDelivery(
+		t, s.WebhookDB, event.ID, targetID,
+		database.DeliveryStatusPending,
+	)
+	rAgePending(t, s.WebhookDB, d.ID)
+
+	ctx := context.Background()
+
+	s.Engine.ExportSweepWebhookRetries(ctx, s.WebhookID)
+	require.Len(t, fDrain(s.Engine), 1)
+
+	var row database.Delivery
+
+	require.NoError(t, s.WebhookDB.
+		First(&row, "id = ?", d.ID).Error)
+	assert.WithinDuration(
+		t, time.Now(), row.UpdatedAt, time.Minute,
+		"a re-dispatched delivery must be stamped so the "+
+			"next tick does not select it again",
+	)
+}

internal/delivery/metrics_test.go

@@ -229,6 +229,13 @@ func mExhaustRetries(t *testing.T, s iSetup) {
 	body := event.Body
 	cfg := iHTTPConfig(ts.URL)
 
+	// The retry below is only run if its target still exists; see
+	// https://git.eeqj.de/sneak/webhooker/issues/107.
+	iCreateTarget(
+		t, s.MainDB, targetID, s.WebhookID, "metrics-fail",
+		database.TargetTypeHTTP, cfg, 2,
+	)
+
 	first := iTask(
 		d, event, s.WebhookID, targetID,
 		"metrics-fail", cfg, 2, 1, &body,
@@ -289,6 +296,13 @@ func TestDeliveryMetrics_CircuitBreakerGauge(t *testing.T) {
 	// rather than the budget is what stops the delivery.
 	maxRetries := delivery.ExportDefaultFailureThreshold + 5
 
+	// The retries below are only run if their target still exists;
+	// see https://git.eeqj.de/sneak/webhooker/issues/107.
+	iCreateTarget(
+		t, s.MainDB, targetID, s.WebhookID, "metrics-trip",
+		database.TargetTypeHTTP, cfg, maxRetries,
+	)
+
 	first := iTask(
 		d, event, s.WebhookID, targetID,
 		"metrics-trip", cfg, maxRetries, 1, &body,
@@ -353,6 +367,11 @@ func TestDeliveryMetrics_BreakerBlockedIsNotAnAttempt(
 	cfg := iHTTPConfig(ts.URL)
 	maxRetries := delivery.ExportDefaultFailureThreshold + 5
 
+	iCreateTarget(
+		t, s.MainDB, targetID, s.WebhookID, "metrics-blocked",
+		database.TargetTypeHTTP, cfg, maxRetries,
+	)
+
 	first := iTask(
 		d, event, s.WebhookID, targetID,
 		"metrics-blocked", cfg, maxRetries, 1, &body,

internal/delivery/queue_depth_gormlog_test.go

@@ -3,8 +3,6 @@ package delivery_test
 import (
 	"bytes"
 	"context"
-	"database/sql"
-	"fmt"
 	"log/slog"
 	"net/http"
 	"path/filepath"
@@ -54,12 +52,10 @@ func (q *qdSyncBuf) String() string {
 func qdMainDB(t *testing.T, log *slog.Logger) *gorm.DB {
 	t.Helper()
 
-	dsn := fmt.Sprintf(
+	sqlDB, err := database.OpenSQLite(
-		"file:%s?cache=shared&mode=rwc",
 		filepath.Join(t.TempDir(), "main-gormlog.db"),
+		database.SQLiteModeCreate,
 	)
-
-	sqlDB, err := sql.Open("sqlite", dsn)
 	require.NoError(t, err)
 
 	t.Cleanup(func() { _ = sqlDB.Close() })

internal/delivery/recovery_durability_test.go

@@ -0,0 +1,378 @@
+package delivery_test
+
+import (
+	"context"
+	"net/http"
+	"net/http/httptest"
+	"sync/atomic"
+	"testing"
+	"time"
+
+	"github.com/google/uuid"
+	"github.com/stretchr/testify/assert"
+	"github.com/stretchr/testify/require"
+	"gorm.io/gorm"
+	"sneak.berlin/go/webhooker/internal/database"
+	"sneak.berlin/go/webhooker/internal/delivery"
+)
+
+// These tests cover the delivery half of
+// https://git.eeqj.de/sneak/webhooker/issues/256: a delivery that
+// reached its receiver but whose bookkeeping write failed used to be
+// left at pending and re-sent on the next restart, giving the receiver
+// a second copy while the event log recorded one attempt.
+
+// rSeedResult records a DeliveryResult against a delivery, standing in
+// for the attempt row the send path writes before the status.
+func rSeedResult(
+	t *testing.T,
+	db *gorm.DB,
+	deliveryID string,
+	attemptNum int,
+	success bool,
+) {
+	t.Helper()
+
+	require.NoError(t, db.Create(&database.DeliveryResult{
+		DeliveryID: deliveryID,
+		AttemptNum: attemptNum,
+		Success:    success,
+	}).Error)
+}
+
+// rAgePending backdates a delivery past the sweep's age bound, which is
+// what separates a stranded delivery from one a worker still holds.
+func rAgePending(
+	t *testing.T, db *gorm.DB, deliveryID string,
+) {
+	t.Helper()
+
+	old := time.Now().Add(
+		-2 * delivery.ExportPendingSweepMinAge,
+	)
+
+	require.NoError(t, db.Model(&database.Delivery{}).
+		Where("id = ?", deliveryID).
+		UpdateColumn("updated_at", old).Error)
+}
+
+func TestRecoverySkipsPendingWithSuccessfulResult(
+	t *testing.T,
+) {
+	t.Parallel()
+
+	s := newISetup(t)
+	targetID := uuid.New().String()
+
+	iCreateTarget(t, s.MainDB, targetID,
+		s.WebhookID, "already-delivered",
+		database.TargetTypeLog, "", 0,
+	)
+
+	event := iSeedEvent(
+		t, s.WebhookDB, s.WebhookID, `{"delivered":true}`,
+	)
+
+	// The delivery whose send succeeded and whose result row landed:
+	// only the status write failed, so it sits at pending.
+	done := iSeedDelivery(
+		t, s.WebhookDB, event.ID, targetID,
+		database.DeliveryStatusPending,
+	)
+	rSeedResult(t, s.WebhookDB, done.ID, 1, true)
+
+	// A delivery that was genuinely never attempted.
+	fresh := iSeedDelivery(
+		t, s.WebhookDB, event.ID, targetID,
+		database.DeliveryStatusPending,
+	)
+
+	s.Engine.ExportRecoverPendingDeliveries(
+		context.Background(), s.WebhookDB, s.WebhookID,
+	)
+
+	select {
+	case task := <-s.Engine.ExportDeliveryCh():
+		assert.Equal(
+			t, fresh.ID, task.DeliveryID,
+			"only the unattempted delivery may be re-sent",
+		)
+	case <-time.After(2 * time.Second):
+		t.Fatal("expected the unattempted delivery")
+	}
+
+	select {
+	case task := <-s.Engine.ExportDeliveryCh():
+		t.Fatalf(
+			"re-sent an already delivered delivery: %s",
+			task.DeliveryID,
+		)
+	case <-time.After(200 * time.Millisecond):
+	}
+
+	// It is settled rather than merely skipped: leaving it pending
+	// would strand it again on the next sweep.
+	iAssertStatus(
+		t, s.WebhookDB, done.ID,
+		database.DeliveryStatusDelivered,
+	)
+}
+
+// TestRecoveryContinuesTheAttemptNumbering pins the audit trail: a
+// recovered delivery that already recorded two attempts is re-sent as
+// attempt three, not as attempt one again.
+func TestRecoveryContinuesTheAttemptNumbering(t *testing.T) {
+	t.Parallel()
+
+	s := newISetup(t)
+	targetID := uuid.New().String()
+
+	iCreateTarget(t, s.MainDB, targetID,
+		s.WebhookID, "numbering",
+		database.TargetTypeLog, "", 0,
+	)
+
+	event := iSeedEvent(
+		t, s.WebhookDB, s.WebhookID, `{"numbering":true}`,
+	)
+
+	d := iSeedDelivery(
+		t, s.WebhookDB, event.ID, targetID,
+		database.DeliveryStatusPending,
+	)
+
+	rSeedResult(t, s.WebhookDB, d.ID, 1, false)
+	rSeedResult(t, s.WebhookDB, d.ID, 2, false)
+
+	s.Engine.ExportRecoverPendingDeliveries(
+		context.Background(), s.WebhookDB, s.WebhookID,
+	)
+
+	select {
+	case task := <-s.Engine.ExportDeliveryCh():
+		assert.Equal(t, d.ID, task.DeliveryID)
+		assert.Equal(t, 3, task.AttemptNum)
+	case <-time.After(2 * time.Second):
+		t.Fatal("expected the delivery to be recovered")
+	}
+}
+
+// TestSweepRecoversStrandedPending is the half that removes the
+// restart requirement: a delivery left at pending is picked up by the
+// periodic sweep.
+func TestSweepRecoversStrandedPending(t *testing.T) {
+	t.Parallel()
+
+	targetID := uuid.New().String()
+	s := fSweepSetup(t, targetID, "stranded")
+
+	event := iSeedEvent(
+		t, s.WebhookDB, s.WebhookID, `{"stranded":true}`,
+	)
+
+	stranded := iSeedDelivery(
+		t, s.WebhookDB, event.ID, targetID,
+		database.DeliveryStatusPending,
+	)
+	rAgePending(t, s.WebhookDB, stranded.ID)
+
+	// A delivery a worker may still be holding: young, and therefore
+	// none of the sweep's business.
+	inFlight := iSeedDelivery(
+		t, s.WebhookDB, event.ID, targetID,
+		database.DeliveryStatusPending,
+	)
+
+	s.Engine.ExportSweepWebhookRetries(
+		context.Background(), s.WebhookID,
+	)
+
+	select {
+	case task := <-s.Engine.ExportDeliveryCh():
+		assert.Equal(t, stranded.ID, task.DeliveryID)
+	case <-time.After(2 * time.Second):
+		t.Fatal("expected the stranded delivery")
+	}
+
+	select {
+	case task := <-s.Engine.ExportDeliveryCh():
+		t.Fatalf(
+			"swept an in-flight delivery: %s",
+			task.DeliveryID,
+		)
+	case <-time.After(200 * time.Millisecond):
+	}
+
+	iAssertStatus(
+		t, s.WebhookDB, inFlight.ID,
+		database.DeliveryStatusPending,
+	)
+}
+
+// TestSweepClaimsAStrandedDeliveryOnlyOnce guards the repeat the sweep
+// would otherwise be: the row stays pending for as long as the attempt
+// runs, and a sweep a minute later must not send it a second time.
+func TestSweepClaimsAStrandedDeliveryOnlyOnce(t *testing.T) {
+	t.Parallel()
+
+	targetID := uuid.New().String()
+	s := fSweepSetup(t, targetID, "claimed")
+
+	event := iSeedEvent(
+		t, s.WebhookDB, s.WebhookID, `{"claimed":true}`,
+	)
+
+	d := iSeedDelivery(
+		t, s.WebhookDB, event.ID, targetID,
+		database.DeliveryStatusPending,
+	)
+	rAgePending(t, s.WebhookDB, d.ID)
+
+	ctx := context.Background()
+
+	s.Engine.ExportSweepWebhookRetries(ctx, s.WebhookID)
+
+	select {
+	case task := <-s.Engine.ExportDeliveryCh():
+		assert.Equal(t, d.ID, task.DeliveryID)
+	case <-time.After(2 * time.Second):
+		t.Fatal("expected the stranded delivery")
+	}
+
+	// The delivery is still pending — nothing has run it yet — but
+	// the claim must keep the next sweep off it.
+	iAssertStatus(
+		t, s.WebhookDB, d.ID,
+		database.DeliveryStatusPending,
+	)
+
+	s.Engine.ExportSweepWebhookRetries(ctx, s.WebhookID)
+
+	select {
+	case task := <-s.Engine.ExportDeliveryCh():
+		t.Fatalf(
+			"sent a claimed delivery again: %s",
+			task.DeliveryID,
+		)
+	case <-time.After(200 * time.Millisecond):
+	}
+}
+
+// TestSweepSettlesStrandedPendingWithoutResending is the sweep's own
+// version of the reconcile: a stranded delivery holding a successful
+// result is settled where it stands, and the receiver hears nothing.
+func TestSweepSettlesStrandedPendingWithoutResending(
+	t *testing.T,
+) {
+	t.Parallel()
+
+	targetID := uuid.New().String()
+	s := fSweepSetup(t, targetID, "settled")
+
+	event := iSeedEvent(
+		t, s.WebhookDB, s.WebhookID, `{"settled":true}`,
+	)
+
+	d := iSeedDelivery(
+		t, s.WebhookDB, event.ID, targetID,
+		database.DeliveryStatusPending,
+	)
+	rSeedResult(t, s.WebhookDB, d.ID, 1, true)
+	rAgePending(t, s.WebhookDB, d.ID)
+
+	s.Engine.ExportSweepWebhookRetries(
+		context.Background(), s.WebhookID,
+	)
+
+	select {
+	case task := <-s.Engine.ExportDeliveryCh():
+		t.Fatalf(
+			"re-sent a delivery that already succeeded: %s",
+			task.DeliveryID,
+		)
+	case <-time.After(200 * time.Millisecond):
+	}
+
+	iAssertStatus(
+		t, s.WebhookDB, d.ID,
+		database.DeliveryStatusDelivered,
+	)
+
+	var attempts int64
+
+	require.NoError(t, s.WebhookDB.
+		Model(&database.DeliveryResult{}).
+		Where("delivery_id = ?", d.ID).
+		Count(&attempts).Error)
+	assert.Equal(
+		t, int64(1), attempts,
+		"settling must not invent an attempt",
+	)
+}
+
+// TestFailedResultWriteLeavesDeliveryRecoverable is the rule the
+// targets now follow: a bookkeeping write that fails must not advance
+// the status, because pending and retrying are the states the sweeps
+// recover and delivered is a claim the database refused to record.
+func TestFailedResultWriteLeavesDeliveryRecoverable(
+	t *testing.T,
+) {
+	t.Parallel()
+
+	s := newISetup(t)
+	targetID := uuid.New().String()
+
+	var hits atomic.Int64
+
+	ts := httptest.NewServer(http.HandlerFunc(
+		func(w http.ResponseWriter, _ *http.Request) {
+			hits.Add(1)
+			w.WriteHeader(http.StatusOK)
+		},
+	))
+	defer ts.Close()
+
+	event := iSeedEvent(
+		t, s.WebhookDB, s.WebhookID, `{"unwritable":true}`,
+	)
+
+	d := iSeedDelivery(
+		t, s.WebhookDB, event.ID, targetID,
+		database.DeliveryStatusPending,
+	)
+
+	// Drop the table the attempt row goes in, so the send succeeds
+	// and only the bookkeeping write fails.
+	require.NoError(
+		t,
+		s.WebhookDB.Exec("drop table delivery_results").Error,
+	)
+
+	full := &database.Delivery{
+		EventID:  event.ID,
+		TargetID: targetID,
+		Status:   database.DeliveryStatusPending,
+		Event:    event,
+		Target: database.Target{
+			Name:   "unwritable",
+			Type:   database.TargetTypeHTTP,
+			Config: iHTTPConfig(ts.URL),
+		},
+	}
+	full.ID = d.ID
+
+	s.Engine.ExportDeliverHTTP(
+		context.Background(), s.WebhookDB, full,
+		&delivery.Task{DeliveryID: d.ID, AttemptNum: 1},
+	)
+
+	assert.Equal(
+		t, int64(1), hits.Load(),
+		"the send itself must still happen",
+	)
+
+	iAssertStatus(
+		t, s.WebhookDB, d.ID,
+		database.DeliveryStatusPending,
+	)
+}

internal/delivery/redirect_test.go

@@ -170,7 +170,8 @@ func TestDelivery_CrossOriginRedirectDropsOriginScopedHeaders(
 // Stripping must not fire within the configured origin, or every
 // destination that redirects its own path would lose its
 // credential and start answering 401 — and would lose the inbound
-// signature the receiver verifies.
+// signature header the target endpoint verifies. webhooker's own
+// receiver verifies no signature; it only forwards the header.
 func TestDelivery_SameOriginRedirectKeepsOriginScopedHeaders(
 	t *testing.T,
 ) {

internal/delivery/target_database.go

@@ -58,12 +58,17 @@ func (t *databaseTarget) Deliver(
 			"error", err,
 		)
 
-		t.eng.recordResult(
+		recErr := t.eng.recordResult(
 			webhookDB, d, 1, false, 0, "",
 			err.Error(), elapsed.Milliseconds(),
 		)
+		if recErr != nil {
+			t.eng.bookkeepingFailed(d, recErr)
 
-		t.eng.updateDeliveryStatus(
+			return
+		}
+
+		t.eng.settleStatus(
 			webhookDB, d, d.Target.Type,
 			database.DeliveryStatusFailed,
 		)
@@ -71,12 +76,17 @@ func (t *databaseTarget) Deliver(
 		return
 	}
 
-	t.eng.recordResult(
+	recErr := t.eng.recordResult(
 		webhookDB, d, 1, true, 0, "", "",
 		elapsed.Milliseconds(),
 	)
+	if recErr != nil {
+		t.eng.bookkeepingFailed(d, recErr)
 
-	t.eng.updateDeliveryStatus(
+		return
+	}
+
+	t.eng.settleStatus(
 		webhookDB, d, d.Target.Type,
 		database.DeliveryStatusDelivered,
 	)

internal/delivery/target_database_archive.go

@@ -1,7 +1,6 @@
 package delivery
 
 import (
-	"database/sql"
 	"encoding/json"
 	"errors"
 	"fmt"
@@ -12,6 +11,7 @@ import (
 
 	"gorm.io/driver/sqlite"
 	"gorm.io/gorm"
+	"sneak.berlin/go/webhooker/internal/database"
 	"sneak.berlin/go/webhooker/internal/gormlog"
 )
 
@@ -30,13 +30,13 @@ const (
 	// path: open the archive file, creating it if missing, so a
 	// first write (or a write after the operator moved the file
 	// away) recreates it.
-	archiveModeCreate = "rwc"
+	archiveModeCreate = database.SQLiteModeCreate
 
 	// archiveModeExisting is the SQLite URI mode used by the idle
 	// sweep: open read-write but never create. A sweep must never
 	// conjure an empty archive file for a webhook that has a
 	// database target but has never received an event.
-	archiveModeExisting = "rw"
+	archiveModeExisting = database.SQLiteModeExisting
 )
 
 var (
@@ -273,9 +273,11 @@ func (w *archiveWriter) open(expiry time.Duration) error {
 func (w *archiveWriter) openMode(
 	mode string, expiry time.Duration,
 ) error {
-	dbURL := fmt.Sprintf("file:%s?mode=%s", w.path, mode)
+	// Opened through database.OpenSQLite so an archive file carries
-
+	// the same WAL journaling, busy timeout, immediate-transaction
-	sqlDB, err := sql.Open("sqlite", dbURL)
+	// locking, and pool bounds as every other database file. See
+	// internal/database/sqlite_open.go.
+	sqlDB, err := database.OpenSQLite(w.path, mode)
 	if err != nil {
 		return fmt.Errorf(
 			"opening archive database %s: %w", w.path, err,

internal/delivery/target_http.go

@@ -77,14 +77,19 @@ func (c *httpCore) fireAndForget(
 ) {
 	c.eng.observeAttempt(d.Target.Type, res.elapsed())
 
-	c.eng.recordResult(
+	err := c.eng.recordResult(
 		webhookDB, d, 1, res.success,
 		res.statusCode, res.respBody, res.errMsg,
 		res.duration,
 	)
+	if err != nil {
+		c.eng.bookkeepingFailed(d, err)
+
+		return
+	}
 
 	if res.success {
-		c.eng.updateDeliveryStatus(
+		c.eng.settleStatus(
 			webhookDB, d, d.Target.Type,
 			database.DeliveryStatusDelivered,
 		)
@@ -92,7 +97,7 @@ func (c *httpCore) fireAndForget(
 		return
 	}
 
-	c.eng.updateDeliveryStatus(
+	c.eng.settleStatus(
 		webhookDB, d, d.Target.Type,
 		database.DeliveryStatusFailed,
 	)
@@ -122,16 +127,25 @@ func (c *httpCore) withRetry(
 
 	c.eng.observeAttempt(d.Target.Type, res.elapsed())
 
-	c.eng.recordResult(
+	err := c.eng.recordResult(
 		webhookDB, d, attemptNum, res.success,
 		res.statusCode, res.respBody, res.errMsg,
 		res.duration,
 	)
+	if err != nil {
+		// The breaker still learns the outcome: it describes the
+		// target's health, which is unaffected by this database's.
+		c.recordCircuitOutcome(cb, res.success)
+
+		c.eng.bookkeepingFailed(d, err)
+
+		return
+	}
 
 	if res.success {
 		cb.RecordSuccess()
 
-		c.eng.updateDeliveryStatus(
+		c.eng.settleStatus(
 			webhookDB, d, d.Target.Type,
 			database.DeliveryStatusDelivered,
 		)
@@ -146,6 +160,20 @@ func (c *httpCore) withRetry(
 	)
 }
 
+// recordCircuitOutcome feeds one attempt's outcome to the target's
+// circuit breaker.
+func (c *httpCore) recordCircuitOutcome(
+	cb *CircuitBreaker, success bool,
+) {
+	if success {
+		cb.RecordSuccess()
+
+		return
+	}
+
+	cb.RecordFailure()
+}
+
 func (c *httpCore) circuitBreakerBlock(
 	webhookDB *gorm.DB,
 	d *database.Delivery,
@@ -169,7 +197,7 @@ func (c *httpCore) circuitBreakerBlock(
 		"cooldown_remaining", remaining,
 	)
 
-	c.eng.updateDeliveryStatus(
+	c.eng.settleStatus(
 		webhookDB, d, d.Target.Type,
 		database.DeliveryStatusRetrying,
 	)
@@ -189,7 +217,7 @@ func (c *httpCore) handleRetry(
 	attemptNum int,
 ) {
 	if attemptNum >= maxRetries {
-		c.eng.updateDeliveryStatus(
+		c.eng.settleStatus(
 			webhookDB, d, d.Target.Type,
 			database.DeliveryStatusFailed,
 		)
@@ -197,7 +225,7 @@ func (c *httpCore) handleRetry(
 		return
 	}
 
-	c.eng.updateDeliveryStatus(
+	c.eng.settleStatus(
 		webhookDB, d, d.Target.Type,
 		database.DeliveryStatusRetrying,
 	)
@@ -332,12 +360,17 @@ func (t *httpTarget) Deliver(
 			"error", err,
 		)
 
-		t.eng.recordResult(
+		recErr := t.eng.recordResult(
 			webhookDB, d, task.AttemptNum,
 			false, 0, "", err.Error(), 0,
 		)
+		if recErr != nil {
+			t.eng.bookkeepingFailed(d, recErr)
 
-		t.eng.updateDeliveryStatus(
+			return
+		}
+
+		t.eng.settleStatus(
 			webhookDB, d, d.Target.Type,
 			database.DeliveryStatusFailed,
 		)

internal/delivery/target_http_secret_test.go

@@ -1,142 +0,0 @@
-package delivery_test
-
-import (
-	"context"
-	"encoding/json"
-	"net/http"
-	"testing"
-
-	"github.com/stretchr/testify/assert"
-	"github.com/stretchr/testify/require"
-	"sneak.berlin/go/webhooker/internal/database"
-	"sneak.berlin/go/webhooker/internal/delivery"
-	"sneak.berlin/go/webhooker/internal/signature"
-)
-
-// gitlabDeliverySecret is the shared secret the entrypoint in these
-// tests is configured with. No outbound request may contain it.
-const gitlabDeliverySecret = "QQDELIVERYSECRETQQ"
-
-// receivedEventHeaders builds the Event.Headers value the receiver
-// stores for an inbound request, by running the request's headers
-// through the same sanitizer the receive path uses. Going through
-// signature.SanitizeHeaders rather than a literal is the point of
-// the test: it joins the two egresses at the field they share, so a
-// regression at either end shows up here.
-func receivedEventHeaders(
-	t *testing.T,
-	scheme database.SignatureScheme,
-	inbound http.Header,
-) string {
-	t.Helper()
-
-	ep := &database.Entrypoint{
-		SignatureScheme: scheme,
-		SignatureSecret: gitlabDeliverySecret,
-	}
-
-	encoded, err := json.Marshal(
-		signature.SanitizeHeaders(ep, inbound),
-	)
-	require.NoError(t, err)
-
-	return string(encoded)
-}
-
-// TestApplyRequestHeadersDropsInboundCredential proves a delivery to
-// an HTTP target does not carry the GitLab shared secret.
-//
-// isForwardableHeader is a blocklist of hop-by-hop names, so it
-// forwards X-Gitlab-Token like any other header; what keeps the
-// secret out of the outbound request is that the receiver never
-// stored it. Handing a target operator the token would hand them the
-// ability to forge requests to the entrypoint it authenticates,
-// which is the one control the receiver has.
-func TestApplyRequestHeadersDropsInboundCredential(t *testing.T) {
-	t.Parallel()
-
-	inbound := http.Header{}
-	inbound.Set(signature.HeaderGitLab, gitlabDeliverySecret)
-	inbound.Set("X-Gitlab-Event", "Push Hook")
-
-	event := &database.Event{
-		Headers: receivedEventHeaders(
-			t, database.SignatureSchemeGitLab, inbound,
-		),
-		ContentType: "application/json",
-	}
-
-	req, err := http.NewRequestWithContext(
-		context.Background(),
-		http.MethodPost,
-		"https://target.example.com/hook",
-		http.NoBody,
-	)
-	require.NoError(t, err)
-
-	delivery.ExportApplyRequestHeaders(
-		req, event, &delivery.HTTPTargetConfig{},
-	)
-
-	assert.Empty(
-		t,
-		req.Header.Values(signature.HeaderGitLab),
-		"the shared secret header must not reach a target",
-	)
-
-	// Header.Values canonicalises, so a differently-cased spelling
-	// would be caught above; this catches the value arriving under
-	// some other name.
-	for name, values := range req.Header {
-		for _, v := range values {
-			assert.NotContains(
-				t, v, gitlabDeliverySecret,
-				"secret present in outbound header %s", name,
-			)
-		}
-	}
-
-	// The rest of the sender's headers still arrive. A fix that
-	// dropped everything would pass the assertions above while
-	// breaking delivery.
-	assert.Equal(
-		t,
-		"Push Hook",
-		req.Header.Get("X-Gitlab-Event"),
-	)
-}
-
-// TestApplyRequestHeadersKeepsGitHubDigest proves the stripping is
-// scoped to headers that carry the secret itself. GitHub's
-// X-Hub-Signature-256 is an HMAC over the body, so a target can be
-// shown it without being handed the key.
-func TestApplyRequestHeadersKeepsGitHubDigest(t *testing.T) {
-	t.Parallel()
-
-	const digest = "sha256=deadbeef"
-
-	inbound := http.Header{}
-	inbound.Set(signature.HeaderGitHub, digest)
-
-	event := &database.Event{
-		Headers: receivedEventHeaders(
-			t, database.SignatureSchemeGitHub, inbound,
-		),
-	}
-
-	req, err := http.NewRequestWithContext(
-		context.Background(),
-		http.MethodPost,
-		"https://target.example.com/hook",
-		http.NoBody,
-	)
-	require.NoError(t, err)
-
-	delivery.ExportApplyRequestHeaders(
-		req, event, &delivery.HTTPTargetConfig{},
-	)
-
-	assert.Equal(
-		t, digest, req.Header.Get(signature.HeaderGitHub),
-	)
-}

internal/delivery/target_log.go

@@ -55,12 +55,17 @@ func (t *logTarget) Deliver(
 
 	t.eng.observeAttempt(d.Target.Type, elapsed)
 
-	t.eng.recordResult(
+	err := t.eng.recordResult(
 		webhookDB, d, 1, true, 0, "", "",
 		elapsed.Milliseconds(),
 	)
+	if err != nil {
+		t.eng.bookkeepingFailed(d, err)
 
-	t.eng.updateDeliveryStatus(
+		return
+	}
+
+	t.eng.settleStatus(
 		webhookDB, d, d.Target.Type,
 		database.DeliveryStatusDelivered,
 	)

internal/delivery/target_slack.go

@@ -95,12 +95,17 @@ func (t *slackTarget) failConfig(
 	d *database.Delivery,
 	err error,
 ) {
-	t.eng.recordResult(
+	recErr := t.eng.recordResult(
 		webhookDB, d, 1,
 		false, 0, "", err.Error(), 0,
 	)
+	if recErr != nil {
+		t.eng.bookkeepingFailed(d, recErr)
 
-	t.eng.updateDeliveryStatus(
+		return
+	}
+
+	t.eng.settleStatus(
 		webhookDB, d, d.Target.Type,
 		database.DeliveryStatusFailed,
 	)
@@ -226,10 +231,15 @@ func FormatSlackMessage(
 		event.ContentType,
 	)
 
+	timestamp := "unknown"
+	if !event.CreatedAt.IsZero() {
+		timestamp = event.CreatedAt.UTC().Format(time.RFC3339)
+	}
+
 	fmt.Fprintf(
 		&b,
 		"*Timestamp:* `%s`\n",
-		event.CreatedAt.UTC().Format(time.RFC3339),
+		timestamp,
 	)
 
 	fmt.Fprintf(

internal/delivery/terminal_state_test.go

@@ -0,0 +1,531 @@
+package delivery_test
+
+import (
+	"context"
+	"net/http"
+	"net/http/httptest"
+	"sync/atomic"
+	"testing"
+
+	"github.com/google/uuid"
+	"github.com/stretchr/testify/assert"
+	"github.com/stretchr/testify/require"
+	"sneak.berlin/go/webhooker/internal/database"
+	"sneak.berlin/go/webhooker/internal/delivery"
+)
+
+// The two terminal-state gaps of
+// https://git.eeqj.de/sneak/webhooker/issues/107: a delivery failed
+// with nothing in its event log to say why, and a retrying delivery
+// whose target was deleted, which used to keep sending and then never
+// terminalise.
+
+// tUnknownType is a target type no build implements. It stands in for
+// a target whose type was written by a build that knew a type this one
+// does not.
+const tUnknownType = database.TargetType("pubsub")
+
+// tSeedDeletedTarget creates a target, a retrying delivery against it
+// with one recorded failed attempt, and then deletes the target the
+// way the source page does.
+//
+// It asserts the delete is soft, because that is the whole reason the
+// engine could not tell a deleted target from a target id that never
+// named a row: the surviving row is invisible to a scoped read.
+func tSeedDeletedTarget(
+	t *testing.T,
+	s iSetup,
+	name, url string,
+) string {
+	t.Helper()
+
+	targetID := uuid.New().String()
+
+	iCreateTarget(
+		t, s.MainDB, targetID, s.WebhookID, name,
+		database.TargetTypeHTTP, iHTTPConfig(url), 5,
+	)
+
+	event := iSeedEvent(
+		t, s.WebhookDB, s.WebhookID, `{"target":"deleted"}`,
+	)
+
+	d := iSeedDelivery(
+		t, s.WebhookDB, event.ID, targetID,
+		database.DeliveryStatusRetrying,
+	)
+
+	iSeedFailedResult(t, s.WebhookDB, d.ID)
+
+	require.NoError(t, s.MainDB.Delete(
+		&database.Target{}, "id = ?", targetID,
+	).Error)
+
+	var scoped, unscoped int64
+
+	require.NoError(t, s.MainDB.
+		Model(&database.Target{}).
+		Where("id = ?", targetID).
+		Count(&scoped).Error)
+
+	require.NoError(t, s.MainDB.Unscoped().
+		Model(&database.Target{}).
+		Where("id = ?", targetID).
+		Count(&unscoped).Error)
+
+	require.Zero(t, scoped,
+		"the deleted target is still visible to a scoped read",
+	)
+	require.Equal(t, int64(1), unscoped,
+		"the delete was hard, so this test proves nothing about "+
+			"the soft-delete case it exists for",
+	)
+
+	return d.ID
+}
+
+// tLastResult returns a delivery's final recorded attempt, asserting
+// the expected number of them.
+func tLastResult(
+	t *testing.T,
+	s iSetup,
+	deliveryID string,
+	want int,
+) database.DeliveryResult {
+	t.Helper()
+
+	results := iResults(t, s.WebhookDB, deliveryID)
+	require.Len(t, results, want)
+
+	return results[want-1]
+}
+
+// --- 1. A failure with nothing recorded ---
+
+func TestProcessDelivery_UnknownTargetType_RecordsWhy(
+	t *testing.T,
+) {
+	t.Parallel()
+
+	s := newISetup(t)
+
+	targetID := uuid.New().String()
+
+	event := iSeedEvent(
+		t, s.WebhookDB, s.WebhookID, `{"unknown":"type"}`,
+	)
+
+	seeded := iSeedDelivery(
+		t, s.WebhookDB, event.ID, targetID,
+		database.DeliveryStatusPending,
+	)
+
+	target := database.Target{
+		Name:   "mystery",
+		Type:   tUnknownType,
+		Config: iHTTPConfig("http://example.com/hook"),
+	}
+	target.ID = targetID
+
+	d := database.Delivery{
+		EventID:  event.ID,
+		TargetID: targetID,
+		Status:   database.DeliveryStatusPending,
+		Event:    event,
+		Target:   target,
+	}
+	d.ID = seeded.ID
+
+	body := event.Body
+	task := iTask(
+		seeded, event, s.WebhookID, targetID, "mystery",
+		target.Config, 0, 1, &body,
+	)
+	task.TargetType = tUnknownType
+
+	s.Engine.ExportProcessDelivery(
+		context.Background(), s.WebhookDB, &d, &task,
+	)
+
+	iAssertStatus(
+		t, s.WebhookDB, d.ID, database.DeliveryStatusFailed,
+	)
+
+	last := tLastResult(t, s, d.ID, 1)
+
+	assert.False(t, last.Success)
+	assert.Equal(t, 1, last.AttemptNum)
+	assert.Contains(t, last.Error, string(tUnknownType),
+		"the recorded reason does not name the offending type",
+	)
+}
+
+// --- 2. A retrying delivery whose target is gone ---
+
+func TestRecoverSingleRetry_TargetDeleted(t *testing.T) {
+	t.Parallel()
+
+	s := newISetup(t)
+
+	iCreateWebhook(
+		t, s.MainDB, s.WebhookID, "deleted-target-recovery",
+	)
+
+	deliveryID := tSeedDeletedTarget(
+		t, s, "gone-on-recovery", "http://example.com/hook",
+	)
+
+	s.Engine.ExportRecoverWebhookDeliveries(
+		context.Background(), s.WebhookID,
+	)
+
+	iAssertStatus(
+		t, s.WebhookDB, deliveryID,
+		database.DeliveryStatusFailed,
+	)
+
+	last := tLastResult(t, s, deliveryID, 2)
+
+	assert.False(t, last.Success)
+	assert.Equal(t, 2, last.AttemptNum)
+	assert.Contains(t, last.Error, "gone-on-recovery")
+	assert.Contains(t, last.Error, "was deleted")
+
+	assert.Empty(t, s.Engine.ExportRetryCh(),
+		"a delivery whose target is gone was rescheduled",
+	)
+	assert.Zero(t, s.Engine.ExportInflightHeld(),
+		"the terminal path leaked its ownership reference",
+	)
+}
+
+func TestSweepSingleRetry_TargetDeleted(t *testing.T) {
+	t.Parallel()
+
+	s := newISetup(t)
+
+	iCreateWebhook(
+		t, s.MainDB, s.WebhookID, "deleted-target-sweep",
+	)
+
+	deliveryID := tSeedDeletedTarget(
+		t, s, "gone-on-sweep", "http://example.com/hook",
+	)
+
+	// Twice, because the bug was an error the sweep repeated every
+	// minute for the life of the database: the second sweep must
+	// find nothing left to do.
+	s.Engine.ExportSweepWebhookRetries(
+		context.Background(), s.WebhookID,
+	)
+	s.Engine.ExportSweepWebhookRetries(
+		context.Background(), s.WebhookID,
+	)
+
+	iAssertStatus(
+		t, s.WebhookDB, deliveryID,
+		database.DeliveryStatusFailed,
+	)
+
+	last := tLastResult(t, s, deliveryID, 2)
+
+	assert.Contains(t, last.Error, "gone-on-sweep")
+	assert.Contains(t, last.Error, "was deleted")
+
+	assert.Empty(t, s.Engine.ExportRetryCh())
+	assert.Zero(t, s.Engine.ExportInflightHeld())
+}
+
+// TestSweepSingleRetry_TargetNeverExisted covers the other half of the
+// soft-delete distinction: an id with no row at all, deleted or
+// otherwise, must not be reported as something the operator deleted.
+func TestSweepSingleRetry_TargetNeverExisted(t *testing.T) {
+	t.Parallel()
+
+	s := newISetup(t)
+
+	iCreateWebhook(
+		t, s.MainDB, s.WebhookID, "target-never-existed",
+	)
+
+	targetID := uuid.New().String()
+
+	event := iSeedEvent(
+		t, s.WebhookDB, s.WebhookID, `{"target":"absent"}`,
+	)
+
+	d := iSeedDelivery(
+		t, s.WebhookDB, event.ID, targetID,
+		database.DeliveryStatusRetrying,
+	)
+
+	iSeedFailedResult(t, s.WebhookDB, d.ID)
+
+	s.Engine.ExportSweepWebhookRetries(
+		context.Background(), s.WebhookID,
+	)
+
+	iAssertStatus(
+		t, s.WebhookDB, d.ID, database.DeliveryStatusFailed,
+	)
+
+	last := tLastResult(t, s, d.ID, 2)
+
+	assert.Contains(t, last.Error, targetID)
+	assert.Contains(t, last.Error, "no longer exists")
+	assert.NotContains(t, last.Error, "was deleted",
+		"an id that never named a row was reported as a deletion",
+	)
+}
+
+// TestFailMissingTargetRetry_WritesNoTargetRow holds the new terminal
+// path to the same rule as the existing one: no target row, and so no
+// plaintext target config, may be written into the per-webhook event
+// database. See https://git.eeqj.de/sneak/webhooker/issues/206.
+func TestFailMissingTargetRetry_WritesNoTargetRow(
+	t *testing.T,
+) {
+	t.Parallel()
+
+	s := newISetup(t)
+
+	iCreateWebhook(
+		t, s.MainDB, s.WebhookID, "no-target-row-deleted",
+	)
+
+	hookURL := "https://hooks.slack.com/services/T00/B00/x"
+
+	deliveryID := tSeedDeletedTarget(
+		t, s, "credential-bearing", hookURL,
+	)
+
+	s.Engine.ExportSweepWebhookRetries(
+		context.Background(), s.WebhookID,
+	)
+
+	iAssertStatus(
+		t, s.WebhookDB, deliveryID,
+		database.DeliveryStatusFailed,
+	)
+
+	var configs []string
+
+	require.NoError(t, s.WebhookDB.
+		Table("targets").
+		Pluck("config", &configs).Error)
+
+	assert.Empty(t, configs,
+		"the deleted-target terminal path wrote a target row "+
+			"into the per-webhook event database",
+	)
+}
+
+// --- 3. The scheduled retry chain ---
+
+// tRetryChainSetup wires a counting sink and a retrying delivery
+// against a live target pointing at it, and returns the task a
+// scheduled retry would carry — config and all, snapshotted as
+// ScheduleRetry snapshots it.
+func tRetryChainSetup(
+	t *testing.T,
+	s iSetup,
+	name string,
+	hits *atomic.Int64,
+) (delivery.Task, string) {
+	t.Helper()
+
+	ts := httptest.NewServer(http.HandlerFunc(
+		func(w http.ResponseWriter, _ *http.Request) {
+			hits.Add(1)
+			w.WriteHeader(http.StatusOK)
+		},
+	))
+	t.Cleanup(ts.Close)
+
+	iCreateWebhook(t, s.MainDB, s.WebhookID, name)
+
+	targetID := uuid.New().String()
+	cfg := iHTTPConfig(ts.URL)
+
+	iCreateTarget(
+		t, s.MainDB, targetID, s.WebhookID, name,
+		database.TargetTypeHTTP, cfg, 5,
+	)
+
+	event := iSeedEvent(
+		t, s.WebhookDB, s.WebhookID, `{"chain":"retry"}`,
+	)
+
+	d := iSeedDelivery(
+		t, s.WebhookDB, event.ID, targetID,
+		database.DeliveryStatusRetrying,
+	)
+
+	iSeedFailedResult(t, s.WebhookDB, d.ID)
+
+	body := event.Body
+
+	return iTask(
+		d, event, s.WebhookID, targetID, name, cfg, 5, 2, &body,
+	), targetID
+}
+
+// TestProcessRetryTask_TargetDeleted_MakesNoAttempt is the half the
+// deployability audit found worse than filed: terminalising on
+// recovery and sweep alone leaves the already-scheduled timer chain
+// running, and it holds the target's configuration from before the
+// deletion, so it goes on sending to a destination that was removed.
+func TestProcessRetryTask_TargetDeleted_MakesNoAttempt(
+	t *testing.T,
+) {
+	t.Parallel()
+
+	s := newISetup(t)
+
+	var hits atomic.Int64
+
+	task, targetID := tRetryChainSetup(
+		t, s, "gone-mid-chain", &hits,
+	)
+
+	require.NoError(t, s.MainDB.Delete(
+		&database.Target{}, "id = ?", targetID,
+	).Error)
+
+	s.Engine.ExportProcessRetryTask(
+		context.Background(), &task,
+	)
+
+	assert.Zero(t, hits.Load(),
+		"a scheduled retry fired at a target the operator "+
+			"had already deleted",
+	)
+
+	iAssertStatus(
+		t, s.WebhookDB, task.DeliveryID,
+		database.DeliveryStatusFailed,
+	)
+
+	last := tLastResult(t, s, task.DeliveryID, 2)
+
+	assert.False(t, last.Success)
+	assert.Contains(t, last.Error, "was deleted")
+
+	assert.Zero(t, s.Engine.ExportInflightHeld())
+}
+
+// TestProcessRetryTask_TargetPresent_StillDelivers is the guard's
+// mutation check: a liveness check that refused every retry would pass
+// the test above and break every retry there is.
+func TestProcessRetryTask_TargetPresent_StillDelivers(
+	t *testing.T,
+) {
+	t.Parallel()
+
+	s := newISetup(t)
+
+	var hits atomic.Int64
+
+	task, _ := tRetryChainSetup(t, s, "still-there", &hits)
+
+	s.Engine.ExportProcessRetryTask(
+		context.Background(), &task,
+	)
+
+	assert.Equal(t, int64(1), hits.Load())
+
+	iAssertStatus(
+		t, s.WebhookDB, task.DeliveryID,
+		database.DeliveryStatusDelivered,
+	)
+}
+
+// TestProcessRetryTask_TargetUnreadable_StillDelivers pins the other
+// half of the guard: only a target that is confirmed gone stops a
+// retry. A main database that cannot be read is a transient fault, and
+// a guard that abandoned deliveries on one would be a worse bug than
+// the one it fixes.
+func TestProcessRetryTask_TargetUnreadable_StillDelivers(
+	t *testing.T,
+) {
+	t.Parallel()
+
+	s := newISetup(t)
+
+	var hits atomic.Int64
+
+	task, _ := tRetryChainSetup(t, s, "unreadable-main", &hits)
+
+	sqlDB, err := s.MainDB.DB()
+	require.NoError(t, err)
+	require.NoError(t, sqlDB.Close())
+
+	s.Engine.ExportProcessRetryTask(
+		context.Background(), &task,
+	)
+
+	assert.Equal(t, int64(1), hits.Load(),
+		"a retry was abandoned because the main database "+
+			"could not be read, not because its target was gone",
+	)
+
+	iAssertStatus(
+		t, s.WebhookDB, task.DeliveryID,
+		database.DeliveryStatusDelivered,
+	)
+}
+
+// TestRecoverSingleRetry_TargetUnreadable_LeavesDeliveryAlone is the
+// same rule on the recovery path. A read failure that is not
+// "record not found" must leave every retrying delivery of every
+// webhook exactly as it was.
+func TestRecoverSingleRetry_TargetUnreadable_LeavesDeliveryAlone(
+	t *testing.T,
+) {
+	t.Parallel()
+
+	s := newISetup(t)
+
+	iCreateWebhook(
+		t, s.MainDB, s.WebhookID, "unreadable-on-recovery",
+	)
+
+	targetID := uuid.New().String()
+
+	iCreateTarget(
+		t, s.MainDB, targetID, s.WebhookID, "healthy",
+		database.TargetTypeHTTP,
+		iHTTPConfig("http://example.com/hook"), 5,
+	)
+
+	event := iSeedEvent(
+		t, s.WebhookDB, s.WebhookID, `{"still":"retrying"}`,
+	)
+
+	d := iSeedDelivery(
+		t, s.WebhookDB, event.ID, targetID,
+		database.DeliveryStatusRetrying,
+	)
+
+	iSeedFailedResult(t, s.WebhookDB, d.ID)
+
+	sqlDB, err := s.MainDB.DB()
+	require.NoError(t, err)
+	require.NoError(t, sqlDB.Close())
+
+	s.Engine.ExportRecoverRetryingDeliveries(
+		s.WebhookDB, s.WebhookID,
+	)
+
+	iAssertStatus(
+		t, s.WebhookDB, d.ID,
+		database.DeliveryStatusRetrying,
+	)
+
+	assert.Len(t, iResults(t, s.WebhookDB, d.ID), 1,
+		"an unreadable main database produced a terminal "+
+			"failure row",
+	)
+
+	assert.Zero(t, s.Engine.ExportInflightHeld())
+}

internal/handlers/entrypoint_secret_test.go

@@ -1,342 +0,0 @@
-package handlers_test
-
-import (
-	"net/http"
-	"net/http/httptest"
-	"net/url"
-	"testing"
-
-	"github.com/stretchr/testify/assert"
-	"github.com/stretchr/testify/require"
-	"sneak.berlin/go/webhooker/internal/database"
-	"sneak.berlin/go/webhooker/internal/handlers"
-	"sneak.berlin/go/webhooker/internal/session"
-)
-
-// submitEntrypointSecret posts the signature configuration form for
-// an entrypoint and returns the recorder.
-func submitEntrypointSecret(
-	t *testing.T,
-	h *handlers.Handlers,
-	cookies []*http.Cookie,
-	webhookID, entrypointID, scheme, secret string,
-) *httptest.ResponseRecorder {
-	t.Helper()
-
-	form := url.Values{}
-	form.Set("signature_scheme", scheme)
-	form.Set("secret", secret)
-
-	req := formRequest(
-		"/source/"+webhookID+"/entrypoints/"+
-			entrypointID+"/secret",
-		cookies,
-		form,
-		map[string]string{
-			paramSourceID:     webhookID,
-			entrypointIDParam: entrypointID,
-		},
-	)
-	w := httptest.NewRecorder()
-
-	h.HandleEntrypointSecret().ServeHTTP(w, req)
-
-	return w
-}
-
-// reloadEntrypoint reads an entrypoint back from the database,
-// including the columns the model keeps out of JSON.
-func reloadEntrypoint(
-	t *testing.T,
-	db *database.Database,
-	id string,
-) database.Entrypoint {
-	t.Helper()
-
-	var ep database.Entrypoint
-
-	require.NoError(
-		t, db.DB().Where("id = ?", id).First(&ep).Error,
-	)
-
-	return ep
-}
-
-// TestEntrypointSecretSetRotateAndRemove walks the whole lifecycle
-// the UI has to support: turning verification on, rotating the secret
-// to a new value, and turning it back off.
-func TestEntrypointSecretSetRotateAndRemove(t *testing.T) {
-	t.Parallel()
-
-	var (
-		h    *handlers.Handlers
-		sess *session.Session
-		db   *database.Database
-	)
-
-	app := newTestApp(t, &h, &sess, &db)
-	app.RequireStart()
-
-	t.Cleanup(app.RequireStop)
-
-	cookies := authenticatedCookies(
-		t, sess, deleteTestUserID, deleteTestUsername,
-	)
-	wh := seedWebhook(t, db)
-	ep := seedSignedEntrypoint(
-		t, db, wh.ID, database.SignatureSchemeNone, "",
-	)
-
-	// Set.
-	w := submitEntrypointSecret(
-		t, h, cookies, wh.ID, ep.ID, "github", inboundSecret,
-	)
-	require.Equal(t, http.StatusSeeOther, w.Code)
-
-	stored := reloadEntrypoint(t, db, ep.ID)
-	assert.Equal(
-		t, database.SignatureSchemeGitHub, stored.SignatureScheme,
-	)
-	assert.Equal(t, inboundSecret, stored.SignatureSecret)
-	assert.True(t, stored.SignatureConfigured())
-
-	// Rotate: a new secret and a different scheme in one submission.
-	// The new value is submitted with surrounding whitespace, the way
-	// a secret pasted out of a password manager arrives; storing that
-	// verbatim would make every later request fail verification with
-	// nothing visible on either side to explain it.
-	const rotated = "QQROTATEDSECRETQQ"
-
-	w = submitEntrypointSecret(
-		t, h, cookies, wh.ID, ep.ID, "gitlab", "  "+rotated+"\t",
-	)
-	require.Equal(t, http.StatusSeeOther, w.Code)
-
-	stored = reloadEntrypoint(t, db, ep.ID)
-	assert.Equal(
-		t, database.SignatureSchemeGitLab, stored.SignatureScheme,
-	)
-	assert.Equal(t, rotated, stored.SignatureSecret)
-
-	// Remove. The secret has to go with the scheme: a stored
-	// credential nothing reads is one more copy to leak.
-	w = submitEntrypointSecret(t, h, cookies, wh.ID, ep.ID, "", "")
-	require.Equal(t, http.StatusSeeOther, w.Code)
-
-	stored = reloadEntrypoint(t, db, ep.ID)
-	assert.Equal(
-		t, database.SignatureSchemeNone, stored.SignatureScheme,
-	)
-	assert.Empty(t, stored.SignatureSecret)
-	assert.False(t, stored.SignatureConfigured())
-}
-
-// TestEntrypointSecretRejectsBadInput proves the form cannot create a
-// row the receiver would later have to refuse. Both rejections leave
-// the stored configuration untouched rather than half-applied.
-func TestEntrypointSecretRejectsBadInput(t *testing.T) {
-	t.Parallel()
-
-	cases := []struct {
-		name   string
-		scheme string
-		secret string
-	}{
-		{
-			name:   "unsupported scheme",
-			scheme: "stripe",
-			secret: inboundSecret,
-		},
-		{
-			name:   "scheme with no secret",
-			scheme: "github",
-			secret: "",
-		},
-		{
-			// Whitespace is stripped, so a secret of spaces is an
-			// empty one.
-			name:   "scheme with blank secret",
-			scheme: "github",
-			secret: "   ",
-		},
-	}
-
-	var (
-		h    *handlers.Handlers
-		sess *session.Session
-		db   *database.Database
-	)
-
-	app := newTestApp(t, &h, &sess, &db)
-	app.RequireStart()
-
-	t.Cleanup(app.RequireStop)
-
-	cookies := authenticatedCookies(
-		t, sess, deleteTestUserID, deleteTestUsername,
-	)
-
-	for _, tc := range cases {
-		wh := seedWebhook(t, db)
-		ep := seedSignedEntrypoint(
-			t, db, wh.ID,
-			database.SignatureSchemeGitLab, inboundSecret,
-		)
-
-		w := submitEntrypointSecret(
-			t, h, cookies, wh.ID, ep.ID, tc.scheme, tc.secret,
-		)
-
-		assert.Equal(
-			t, http.StatusBadRequest, w.Code, "case %s", tc.name,
-		)
-
-		stored := reloadEntrypoint(t, db, ep.ID)
-		assert.Equal(
-			t,
-			database.SignatureSchemeGitLab,
-			stored.SignatureScheme,
-			"case %s", tc.name,
-		)
-		assert.Equal(
-			t, inboundSecret, stored.SignatureSecret,
-			"case %s", tc.name,
-		)
-	}
-}
-
-// TestEntrypointSecretRequiresOwnership proves the configuration
-// endpoint is bound by the same ownership check as the rest of the
-// webhook's pages: another user's entrypoint is a 404, and the secret
-// is not touched.
-func TestEntrypointSecretRequiresOwnership(t *testing.T) {
-	t.Parallel()
-
-	var (
-		h    *handlers.Handlers
-		sess *session.Session
-		db   *database.Database
-	)
-
-	app := newTestApp(t, &h, &sess, &db)
-	app.RequireStart()
-
-	t.Cleanup(app.RequireStop)
-
-	wh := seedWebhook(t, db)
-	ep := seedSignedEntrypoint(
-		t, db, wh.ID,
-		database.SignatureSchemeGitLab, inboundSecret,
-	)
-
-	stranger := authenticatedCookies(
-		t, sess, "someone-else", "someoneelse",
-	)
-
-	w := submitEntrypointSecret(
-		t, h, stranger, wh.ID, ep.ID, "github", "hijacked",
-	)
-
-	assert.Equal(t, http.StatusNotFound, w.Code)
-	assert.Equal(
-		t,
-		inboundSecret,
-		reloadEntrypoint(t, db, ep.ID).SignatureSecret,
-	)
-}
-
-// TestHandleSourceDetail_MasksEntrypointSecret is the regression test
-// for the credential on the entrypoint: the page has to say that
-// verification is configured and which header carries it, without the
-// secret itself ever reaching the rendered HTML.
-func TestHandleSourceDetail_MasksEntrypointSecret(t *testing.T) {
-	t.Parallel()
-
-	var (
-		h    *handlers.Handlers
-		sess *session.Session
-		db   *database.Database
-	)
-
-	app := newTestApp(t, &h, &sess, &db)
-	app.RequireStart()
-
-	t.Cleanup(app.RequireStop)
-
-	wh := seedWebhook(t, db)
-	seedSignedEntrypoint(
-		t, db, wh.ID,
-		database.SignatureSchemeGitHub, inboundSecret,
-	)
-
-	body := renderSourceDetailPage(t, h, sess, wh.ID)
-
-	assert.NotContains(t, body, inboundSecret)
-	assert.Contains(t, body, "GitHub")
-	assert.Contains(t, body, "X-Hub-Signature-256")
-}
-
-// TestEntrypointViewsDropTheSecret pins the projection itself, so the
-// barrier survives a template rewrite that stops rendering the field
-// the page test above looks at.
-func TestEntrypointViewsDropTheSecret(t *testing.T) {
-	t.Parallel()
-
-	views := handlers.NewEntrypointViews([]database.Entrypoint{
-		{
-			Path:            "p1",
-			Active:          true,
-			SignatureScheme: database.SignatureSchemeGitHub,
-			SignatureSecret: inboundSecret,
-		},
-		{
-			Path: "p2",
-		},
-		{
-			// Half a configuration. The receiver 500s every request
-			// to this row, so the UI must not call it unverified.
-			Path:            "p2a",
-			SignatureScheme: database.SignatureSchemeGitLab,
-		},
-		{
-			// The other half.
-			Path:            "p2b",
-			SignatureSecret: inboundSecret,
-		},
-		{
-			// A scheme this build does not know: described as
-			// unavailable, never echoed back.
-			Path:            "p3",
-			SignatureScheme: database.SignatureScheme("stripe"),
-			SignatureSecret: inboundSecret,
-		},
-	})
-
-	require.Len(t, views, 5)
-
-	assert.True(t, views[0].Configured)
-	assert.Equal(t, "GitHub", views[0].SchemeLabel)
-	assert.Equal(t, "X-Hub-Signature-256", views[0].SchemeHeader)
-
-	assert.False(t, views[1].Configured)
-	assert.Equal(t, "not verified", views[1].SchemeLabel)
-	assert.Empty(t, views[1].SchemeHeader)
-
-	for _, v := range []handlers.EntrypointView{views[2], views[3]} {
-		assert.False(t, v.Configured)
-		assert.Equal(t, "misconfigured", v.SchemeLabel)
-		assert.Empty(t, v.SchemeHeader)
-	}
-
-	assert.True(t, views[4].Configured)
-	assert.Equal(t, "(unavailable)", views[4].SchemeLabel)
-
-	// The struct has no field that could carry the secret, so this
-	// fails to compile rather than fails at runtime if one is added
-	// and populated. The assertion covers the labels it derives.
-	for _, v := range views {
-		assert.NotContains(t, v.SchemeLabel, inboundSecret)
-		assert.NotContains(t, v.SchemeHeader, inboundSecret)
-		assert.NotContains(t, string(v.Scheme), inboundSecret)
-	}
-}

internal/handlers/entrypoint_view.go

@@ -2,56 +2,18 @@ package handlers
 
 import (
 	"sneak.berlin/go/webhooker/internal/database"
-	"sneak.berlin/go/webhooker/internal/signature"
 )
 
-// signatureUnavailable is what an entrypoint's scheme renders as when
-// the stored value is not one this build supports. The stored string
-// is never echoed as a fallback: it is operator-supplied and the row
-// is already in a state the receiver refuses, so the UI says so
-// rather than inventing a description for it.
-const signatureUnavailable = "(unavailable)"
-
-// signatureNotVerified is the label for an entrypoint that performs
-// no inbound verification.
-const signatureNotVerified = "not verified"
-
-// signatureMisconfigured is the label for a row holding one half of
-// the scheme/secret pair. The receiver answers every request to such
-// an entrypoint 500, so calling it "not verified" would describe a
-// receiver that is refusing everything as one that is accepting
-// everything. The form cannot create the state; a hand-edited
-// database or a downgrade past a scheme can.
-const signatureMisconfigured = "misconfigured"
-
 // EntrypointView is the display-safe projection of an entrypoint for
-// the UI. It deliberately has no secret field, so no template —
+// the UI, in the same way delivery.TargetView is one for a target.
-// present or future — can render the shared secret, in the same way
-// delivery.TargetView keeps a target's stored credential away from
-// one.
 type EntrypointView struct {
 	ID          string
 	Path        string
 	Description string
 	Active      bool
-
-	// Configured reports whether inbound requests to this entrypoint
-	// are verified.
-	Configured bool
-
-	// Scheme is the stored scheme, carried so the form can preselect
-	// it. It names an algorithm, not a secret.
-	Scheme database.SignatureScheme
-
-	// SchemeLabel and SchemeHeader describe the configured scheme for
-	// display: the sender's name, and the header its signature
-	// arrives in.
-	SchemeLabel  string
-	SchemeHeader string
 }
 
-// NewEntrypointViews projects entrypoints for rendering, dropping the
+// NewEntrypointViews projects entrypoints for rendering.
-// shared secret on the way.
 func NewEntrypointViews(
 	entrypoints []database.Entrypoint,
 ) []EntrypointView {
@@ -60,31 +22,12 @@ func NewEntrypointViews(
 	for i := range entrypoints {
 		e := &entrypoints[i]
 
-		view := EntrypointView{
+		views = append(views, EntrypointView{
-			ID:           e.ID,
+			ID:          e.ID,
-			Path:         e.Path,
+			Path:        e.Path,
-			Description:  e.Description,
+			Description: e.Description,
-			Active:       e.Active,
+			Active:      e.Active,
-			Configured:   e.SignatureConfigured(),
+		})
-			Scheme:       e.SignatureScheme,
-			SchemeLabel:  signatureNotVerified,
-			SchemeHeader: "",
-		}
-
-		switch {
-		case view.Configured:
-			view.SchemeLabel = signatureUnavailable
-
-			info, ok := signature.Info(e.SignatureScheme)
-			if ok {
-				view.SchemeLabel = info.Label
-				view.SchemeHeader = info.Header
-			}
-		case e.SignatureHalfConfigured():
-			view.SchemeLabel = signatureMisconfigured
-		}
-
-		views = append(views, view)
 	}
 
 	return views

internal/handlers/event_body.go

@@ -92,11 +92,10 @@ func (h *Handlers) HandleEventBodyDownload() http.HandlerFunc {
 // once per range.
 //
 // One consequence is worth keeping in view: the read finishes
-// before the client is written to, so no read lock is held for
+// before the client is written to, so nothing is held open for
-// the length of a slow download. These per-webhook databases
+// the length of a slow download. Under WAL a read no longer
-// run in SQLite's default journal mode rather than WAL, so a
+// blocks the receiver, but it does pin the WAL against
-// lock held that long would block the receiver from recording
+// checkpointing, and a download can last minutes.
-// new events.
 func (h *Handlers) serveEventBody(
 	w http.ResponseWriter,
 	r *http.Request,

internal/handlers/event_resubmit.go

@@ -84,10 +84,6 @@ const resubmitColumns = "id, entrypoint_id, method, headers, " +
 // is the stored EVENT. The response bodies and headers the original
 // deliveries received stay where they are.
 //
-// Inbound signature verification is deliberately not re-run. There is
-// no inbound signature to check on a copy the operator submits; the
-// route is authenticated and CSRF-protected as an operator action.
-//
 // Resubmitting the same event repeatedly is supported and is the point
 // of the feature, so replay's in-flight refusal is deliberately not
 // applied here. The route's rate limit is what bounds a held-down
@@ -143,10 +139,10 @@ func (h *Handlers) resubmitEvent(
 	}
 
 	// Read before the write transaction is opened. The body can be up
-	// to the 1 MB ingest cap, and holding a read of it inside the
+	// to the 1 MB ingest cap, and every transaction on these files
-	// transaction would extend how long the per-webhook database is
+	// takes the write lock at BEGIN (_txlock=immediate, see
-	// locked against the receiver, which runs these files in
+	// internal/database/sqlite_open.go), so reading inside it would
-	// SQLite's default journal mode rather than WAL.
+	// hold that lock against the receiver for the length of the read.
 	src, found, err := loadResubmitSource(
 		webhookDB, webhook.ID, eventID.String(),
 	)

internal/handlers/footer_version_test.go

@@ -0,0 +1,38 @@
+package handlers_test
+
+import (
+	"testing"
+
+	"github.com/stretchr/testify/assert"
+	"sneak.berlin/go/webhooker/internal/globals"
+	"sneak.berlin/go/webhooker/internal/handlers"
+	"sneak.berlin/go/webhooker/internal/session"
+)
+
+// The footer in base.html falls back to the literal "dev" when the
+// template data carries no version, which is what every page rendered
+// while nothing supplied one. The operator uses the footer to tell
+// which build is live, so it has to carry the stamped value.
+func TestFooterReportsStampedVersion(t *testing.T) {
+	t.Parallel()
+
+	var (
+		h    *handlers.Handlers
+		sess *session.Session
+		g    *globals.Globals
+	)
+
+	app := newTestApp(t, &h, &sess, &g)
+	app.RequireStart()
+
+	t.Cleanup(app.RequireStop)
+
+	g.Version = "v9.9.9-test"
+
+	html := renderPage(t, h, sess, "login.html", map[string]any{
+		dataKeyError: "",
+	})
+
+	assert.Contains(t, html, "<span>v9.9.9-test</span>")
+	assert.NotContains(t, html, "<span>dev</span>")
+}

internal/handlers/handlers.go

@@ -184,6 +184,7 @@ type UserInfo struct {
 type templateDataWrapper struct {
 	User      *UserInfo
 	CSRFToken string
+	Version   string
 	Data      any
 }
 
@@ -234,9 +235,16 @@ func (s *Handlers) renderTemplate(
 	userInfo := s.getUserInfo(r)
 	csrfToken := middleware.CSRFToken(r)
 
+	// The footer in base.html renders .Version. Every page reaches it
+	// through here, so this is the one place that has to supply it;
+	// left unset, the footer falls back to its literal "dev" and the
+	// UI reports a build that is not the one running.
+	version := s.params.Globals.Version
+
 	if m, ok := data.(map[string]any); ok {
 		m["User"] = userInfo
 		m["CSRFToken"] = csrfToken
+		m["Version"] = version
 		s.executeTemplate(w, tmpl, m)
 
 		return
@@ -245,6 +253,7 @@ func (s *Handlers) renderTemplate(
 	wrapper := templateDataWrapper{
 		User:      userInfo,
 		CSRFToken: csrfToken,
+		Version:   version,
 		Data:      data,
 	}
 

internal/handlers/source_delete_test.go

@@ -2,6 +2,7 @@ package handlers_test
 
 import (
 	"context"
+	"errors"
 	"net/http"
 	"net/http/httptest"
 	"os"
@@ -11,6 +12,7 @@ import (
 	"github.com/go-chi/chi"
 	"github.com/stretchr/testify/assert"
 	"github.com/stretchr/testify/require"
+	"gorm.io/gorm"
 	"gorm.io/gorm/clause"
 	"sneak.berlin/go/webhooker/internal/database"
 	"sneak.berlin/go/webhooker/internal/handlers"
@@ -73,6 +75,77 @@ func seedTarget(
 	return tgt
 }
 
+// errInjectedDelete is the failure failDeleteOnTable reports
+// from a delete statement.
+var errInjectedDelete = errors.New("injected delete failure")
+
+// seedEntrypoint inserts an entrypoint for a webhook.
+func seedEntrypoint(
+	t *testing.T,
+	db *database.Database,
+	webhookID string,
+) {
+	t.Helper()
+
+	ep := &database.Entrypoint{
+		WebhookID: webhookID,
+		Path:      "ep-" + webhookID,
+		Active:    true,
+	}
+
+	require.NoError(
+		t,
+		db.DB().Omit(clause.Associations).Create(ep).Error,
+	)
+}
+
+// countRows counts the live (not soft-deleted) rows of a model
+// matching column = value.
+func countRows(
+	t *testing.T,
+	db *database.Database,
+	model any,
+	column, value string,
+) int64 {
+	t.Helper()
+
+	var n int64
+
+	require.NoError(
+		t,
+		db.DB().Model(model).
+			Where(column+" = ?", value).
+			Count(&n).Error,
+	)
+
+	return n
+}
+
+// failDeleteOnTable makes every delete against the named table
+// fail the way a database-level error does: the statement
+// reports an error but leaves the surrounding transaction
+// usable, so a caller that does not check it can go on to
+// commit the statements that did succeed.
+func failDeleteOnTable(
+	t *testing.T,
+	db *database.Database,
+	table string,
+) {
+	t.Helper()
+
+	require.NoError(t, db.DB().Callback().Delete().
+		Before("gorm:delete").
+		Register(
+			"test:fail_delete_"+table,
+			func(tx *gorm.DB) {
+				if tx.Statement.Table == table {
+					_ = tx.AddError(errInjectedDelete)
+				}
+			},
+		),
+	)
+}
+
 // archivePathFor returns the archive database path the
 // delivery engine would use for a webhook: beside the webhook's
 // event database in the data directory.
@@ -209,6 +282,159 @@ func TestHandleSourceDelete_KeepsArchiveFile(t *testing.T) {
 	)
 }
 
+// TestHandleSourceDelete_FailedDeleteKeepsEverything proves
+// that a failing delete statement loses nothing: the
+// configuration is rolled back whole, the event database
+// survives, and the operator is told the deletion failed
+// instead of being redirected as though it worked.
+func TestHandleSourceDelete_FailedDeleteKeepsEverything(
+	t *testing.T,
+) {
+	t.Parallel()
+
+	var (
+		h    *handlers.Handlers
+		sess *session.Session
+		db   *database.Database
+		mgr  *database.WebhookDBManager
+	)
+
+	app := newTestApp(t, &h, &sess, &db, &mgr)
+	app.RequireStart()
+
+	t.Cleanup(app.RequireStop)
+
+	wh := seedWebhook(t, db)
+	seedEntrypoint(t, db, wh.ID)
+	seedTarget(t, db, wh.ID, database.TargetTypeDatabase)
+
+	require.NoError(t, mgr.CreateDB(wh.ID))
+
+	eventDBPath := mgr.DBPath(wh.ID)
+	require.FileExists(t, eventDBPath)
+
+	// The entrypoint delete runs first and succeeds; the target
+	// delete then fails, which is what the whole transaction has
+	// to be rolled back over.
+	failDeleteOnTable(t, db, "targets")
+
+	cookies := authenticatedCookies(
+		t, sess, deleteTestUserID, deleteTestUsername,
+	)
+
+	req := postRequest(
+		"/source/"+wh.ID+"/delete",
+		cookies,
+		map[string]string{paramSourceID: wh.ID},
+	)
+	w := httptest.NewRecorder()
+
+	h.HandleSourceDelete().ServeHTTP(w, req)
+
+	assert.Equal(
+		t, http.StatusInternalServerError, w.Code,
+		"a failed deletion must be reported, not redirected",
+	)
+	assert.Empty(
+		t, w.Header().Get("Location"),
+		"a failed deletion must not redirect to /sources",
+	)
+
+	assert.Equal(
+		t, int64(1),
+		countRows(t, db, &database.Webhook{}, "id", wh.ID),
+		"the webhook must survive a failed deletion",
+	)
+	assert.Equal(
+		t, int64(1),
+		countRows(
+			t, db, &database.Entrypoint{}, "webhook_id", wh.ID,
+		),
+		"the entrypoint delete must be rolled back",
+	)
+	assert.Equal(
+		t, int64(1),
+		countRows(
+			t, db, &database.Target{}, "webhook_id", wh.ID,
+		),
+		"the target must survive a failed deletion",
+	)
+
+	assert.FileExists(
+		t, eventDBPath,
+		"event history must not be destroyed when the "+
+			"configuration delete did not commit",
+	)
+}
+
+// TestHandleSourceDelete_RemovesConfigAndEventDatabase is the
+// positive control for the rollback above: an ordinary deletion
+// still removes the webhook, its children and its event
+// database.
+func TestHandleSourceDelete_RemovesConfigAndEventDatabase(
+	t *testing.T,
+) {
+	t.Parallel()
+
+	var (
+		h    *handlers.Handlers
+		sess *session.Session
+		db   *database.Database
+		mgr  *database.WebhookDBManager
+	)
+
+	app := newTestApp(t, &h, &sess, &db, &mgr)
+	app.RequireStart()
+
+	t.Cleanup(app.RequireStop)
+
+	wh := seedWebhook(t, db)
+	seedEntrypoint(t, db, wh.ID)
+	seedTarget(t, db, wh.ID, database.TargetTypeDatabase)
+
+	require.NoError(t, mgr.CreateDB(wh.ID))
+
+	eventDBPath := mgr.DBPath(wh.ID)
+	require.FileExists(t, eventDBPath)
+
+	cookies := authenticatedCookies(
+		t, sess, deleteTestUserID, deleteTestUsername,
+	)
+
+	req := postRequest(
+		"/source/"+wh.ID+"/delete",
+		cookies,
+		map[string]string{paramSourceID: wh.ID},
+	)
+	w := httptest.NewRecorder()
+
+	h.HandleSourceDelete().ServeHTTP(w, req)
+
+	require.Equal(t, http.StatusSeeOther, w.Code)
+	assert.Equal(t, "/sources", w.Header().Get("Location"))
+
+	assert.Equal(
+		t, int64(0),
+		countRows(t, db, &database.Webhook{}, "id", wh.ID),
+	)
+	assert.Equal(
+		t, int64(0),
+		countRows(
+			t, db, &database.Entrypoint{}, "webhook_id", wh.ID,
+		),
+	)
+	assert.Equal(
+		t, int64(0),
+		countRows(
+			t, db, &database.Target{}, "webhook_id", wh.ID,
+		),
+	)
+	assert.NoFileExists(
+		t, eventDBPath,
+		"a successful deletion removes the event database",
+	)
+}
+
 // TestHandleTargetDelete_EvictsWhenLastDatabaseTargetGone
 // proves that removing the last database target releases the
 // archive writer.

internal/handlers/source_detail_baseurl_test.go

@@ -0,0 +1,283 @@
+package handlers_test
+
+import (
+	"context"
+	"crypto/tls"
+	"net/http"
+	"net/http/httptest"
+	"regexp"
+	"testing"
+
+	"github.com/go-chi/chi"
+	"github.com/stretchr/testify/assert"
+	"github.com/stretchr/testify/require"
+	"sneak.berlin/go/webhooker/internal/database"
+	"sneak.berlin/go/webhooker/internal/handlers"
+	"sneak.berlin/go/webhooker/internal/session"
+)
+
+// The only two schemes a rendered entrypoint URL may carry,
+// whatever the request claimed.
+const (
+	schemeHTTPS = "https"
+	schemeHTTP  = "http"
+)
+
+// entrypointURLPattern captures the entrypoint URL the source
+// detail page renders, which is the operator-visible product of
+// BaseURL. Asserting on the extracted string rather than on a
+// substring of the page proves the raw header value cannot reach
+// the scheme by any route.
+var entrypointURLPattern = regexp.MustCompile(
+	`<code id="entrypoint-url-[^"]*"[^>]*>([^<]*)</code>`,
+)
+
+// baseURLFixture is one started app plus the webhook whose
+// entrypoint URL the BaseURL cases read.
+type baseURLFixture struct {
+	handlers *handlers.Handlers
+	session  *session.Session
+	webhook  string
+	path     string
+}
+
+// newBaseURLFixture starts the app and seeds a webhook with one
+// entrypoint.
+func newBaseURLFixture(t *testing.T) *baseURLFixture {
+	t.Helper()
+
+	var (
+		h    *handlers.Handlers
+		sess *session.Session
+		db   *database.Database
+	)
+
+	app := newTestApp(t, &h, &sess, &db)
+	app.RequireStart()
+
+	t.Cleanup(app.RequireStop)
+
+	wh := seedWebhook(t, db)
+	seedEntrypoint(t, db, wh.ID)
+
+	return &baseURLFixture{
+		handlers: h,
+		session:  sess,
+		webhook:  wh.ID,
+		path:     "ep-" + wh.ID,
+	}
+}
+
+// entrypointURL renders the source detail page for the fixture's
+// webhook over a request the caller shapes, and returns the
+// entrypoint URL as an operator would copy it.
+func (f *baseURLFixture) entrypointURL(
+	t *testing.T,
+	host string,
+	shape func(*http.Request),
+) string {
+	t.Helper()
+
+	req := httptest.NewRequestWithContext(
+		context.Background(),
+		http.MethodGet,
+		"/source/"+f.webhook,
+		nil,
+	)
+	req.Host = host
+
+	shape(req)
+
+	for _, c := range authenticatedCookies(
+		t, f.session, deleteTestUserID, deleteTestUsername,
+	) {
+		req.AddCookie(c)
+	}
+
+	rctx := chi.NewRouteContext()
+	rctx.URLParams.Add(paramSourceID, f.webhook)
+	req = req.WithContext(
+		context.WithValue(
+			req.Context(), chi.RouteCtxKey, rctx,
+		),
+	)
+
+	w := httptest.NewRecorder()
+	f.handlers.HandleSourceDetail().ServeHTTP(w, req)
+
+	require.Equal(t, http.StatusOK, w.Code)
+
+	match := entrypointURLPattern.FindStringSubmatch(w.Body.String())
+	require.Len(
+		t, match, 2,
+		"the page must render exactly one entrypoint URL",
+	)
+
+	return match[1]
+}
+
+// forwardedProto returns a request shaper setting
+// X-Forwarded-Proto, or leaving the request alone for "".
+func forwardedProto(value string) func(*http.Request) {
+	return func(r *http.Request) {
+		if value == "" {
+			return
+		}
+
+		r.Header.Set("X-Forwarded-Proto", value)
+	}
+}
+
+// baseURLCase is one X-Forwarded-Proto spelling and the scheme
+// the rendered entrypoint URL owes it.
+type baseURLCase struct {
+	name   string
+	header string
+	scheme string
+	why    string
+}
+
+// baseURLCases enumerate the spellings a proxy really emits. The
+// scheme is only ever http or https: the header value itself is
+// never a scheme, however it is spelled.
+func baseURLCases() []baseURLCase {
+	return []baseURLCase{
+		{
+			name:   "lowercase",
+			header: schemeHTTPS,
+			scheme: schemeHTTPS,
+			why:    "the ordinary spelling",
+		},
+		{
+			name:   "uppercase",
+			header: "HTTPS",
+			scheme: schemeHTTPS,
+			why: "the token is case-insensitive; the scheme " +
+				"in a copyable URL is not",
+		},
+		{
+			name:   "chain with plaintext inner hop",
+			header: "https, http",
+			scheme: schemeHTTPS,
+			why: "a chained proxy appends its hop; the " +
+				"leftmost element faces the client",
+		},
+		{
+			name:   "chain of two TLS hops",
+			header: "https,https",
+			scheme: schemeHTTPS,
+			why:    "appended chain with no space after the comma",
+		},
+		{
+			name:   "trailing space",
+			header: "https ",
+			scheme: schemeHTTPS,
+			why:    "whitespace is not part of the token",
+		},
+		{
+			name:   "plaintext",
+			header: schemeHTTP,
+			scheme: schemeHTTP,
+			why:    "the negative control: the proxy reports plaintext",
+		},
+		{
+			name:   "no header",
+			header: "",
+			scheme: schemeHTTP,
+			why:    "a plaintext request asserting nothing is http",
+		},
+		{
+			name:   "garbage token",
+			header: "javascript:alert(1)//",
+			scheme: schemeHTTP,
+			why: "anything that is not https is not TLS, and " +
+				"the token never becomes the scheme",
+		},
+	}
+}
+
+// TestSourceDetailBaseURL_ForwardedProtoSpellings is the
+// regression test for the entrypoint URL an operator pastes into
+// the sending system: a header spelling that used to land in the
+// scheme verbatim produced a URL no sender could deliver to.
+func TestSourceDetailBaseURL_ForwardedProtoSpellings(t *testing.T) {
+	t.Parallel()
+
+	const host = "hooks.example.com"
+
+	fixture := newBaseURLFixture(t)
+
+	for _, tc := range baseURLCases() {
+		t.Run(tc.name, func(t *testing.T) {
+			t.Parallel()
+
+			assert.Equal(
+				t,
+				tc.scheme+"://"+host+"/webhook/"+fixture.path,
+				fixture.entrypointURL(
+					t, host, forwardedProto(tc.header),
+				),
+				"X-Forwarded-Proto %q: %s", tc.header, tc.why,
+			)
+		})
+	}
+}
+
+// TestSourceDetailBaseURL_DirectTLSBeatsPlaintextHeader pins the
+// precedence the old code had backwards: it let any present
+// header overwrite what the connection itself proved, so a
+// direct-TLS request behind a proxy reporting http rendered an
+// http URL.
+func TestSourceDetailBaseURL_DirectTLSBeatsPlaintextHeader(
+	t *testing.T,
+) {
+	t.Parallel()
+
+	const host = "hooks.example.com"
+
+	fixture := newBaseURLFixture(t)
+
+	got := fixture.entrypointURL(t, host, func(r *http.Request) {
+		r.TLS = &tls.ConnectionState{}
+		r.Header.Set("X-Forwarded-Proto", "http")
+	})
+
+	assert.Equal(
+		t,
+		"https://"+host+"/webhook/"+fixture.path,
+		got,
+		"a connection this process terminated with TLS "+
+			"outranks a header claiming plaintext",
+	)
+}
+
+// TestSourceDetailBaseURL_KeepsHostAuthority pins the host half
+// of the URL: it is taken from the request unchanged, so the
+// deployments that do not sit on port 443 still get a URL that
+// works. Constraining the host would break exactly these.
+func TestSourceDetailBaseURL_KeepsHostAuthority(t *testing.T) {
+	t.Parallel()
+
+	fixture := newBaseURLFixture(t)
+
+	hosts := []string{
+		"hooks.example.com:8443",
+		"[2001:db8::1]:8443",
+		"internal-host",
+	}
+
+	for _, host := range hosts {
+		t.Run(host, func(t *testing.T) {
+			t.Parallel()
+
+			assert.Equal(
+				t,
+				"https://"+host+"/webhook/"+fixture.path,
+				fixture.entrypointURL(
+					t, host, forwardedProto("HTTPS"),
+				),
+				"the authority must survive verbatim, port and all",
+			)
+		})
+	}
+}

internal/handlers/source_management.go

@@ -13,7 +13,7 @@ import (
 	"gorm.io/gorm"
 	"sneak.berlin/go/webhooker/internal/database"
 	"sneak.berlin/go/webhooker/internal/delivery"
-	"sneak.berlin/go/webhooker/internal/signature"
+	"sneak.berlin/go/webhooker/internal/reqtls"
 )
 
 // WebhookListItem holds data for the webhook list view.
@@ -428,31 +428,28 @@ func (h *Handlers) renderSourceDetail(
 		}
 	}
 
-	host := r.Host
+	scheme := "http"
-	scheme := "https"
+	if reqtls.IsTLS(r) {
-
+		scheme = "https"
-	if r.TLS == nil {
-		scheme = "http"
 	}
 
-	if fwdProto := r.Header.Get("X-Forwarded-Proto"); fwdProto != "" {
+	// The host is the client's Host header, unvalidated. It is
-		scheme = fwdProto
+	// inert only because source_detail.html renders BaseURL as
-	}
+	// text inside a <code> element; putting it in an href or any
+	// other URL context needs it constrained first.
+	baseURL := scheme + "://" + r.Host
 
 	// The template calls Webhook methods, which take pointer
 	// receivers; html/template cannot address a value stored in a map.
 	data := map[string]any{
 		tmplKeyWebhook: &webhook,
-		// Entrypoints and targets are both projected to
+		// Targets are projected to a display-safe view: a
-		// display-safe views: an entrypoint carries the shared
+		// target's stored config blob holds a credential, and it
-		// secret its senders sign with and a target's stored
+		// must never reach a template.
-		// config blob holds a credential, and neither must ever
+		"Entrypoints": NewEntrypointViews(entrypoints),
-		// reach a template.
+		"Targets":     delivery.NewTargetViews(targets),
-		"Entrypoints":      NewEntrypointViews(entrypoints),
+		"Events":      events,
-		"Targets":          delivery.NewTargetViews(targets),
+		"BaseURL":     baseURL,
-		"SignatureSchemes": signature.Schemes(),
-		"Events":           events,
-		"BaseURL":          scheme + "://" + host,
 	}
 
 	h.renderTemplate(w, r, "source_detail.html", data)
@@ -625,43 +622,27 @@ func (h *Handlers) deleteWebhookResources(
 	webhook database.Webhook,
 	userID string,
 ) {
-	tx := h.db.DB().Begin()
+	// The configuration delete commits before the event database
-	if tx.Error != nil {
+	// is touched. No transaction spans the main database and the
-		h.log.Error(
+	// filesystem, so one side has to go first: committing the
-			"failed to begin transaction",
+	// configuration first means a later failure leaves an unused
-			"error", tx.Error,
+	// event database file on disk, while removing the event
-		)
+	// database first would mean a failed commit destroys the
-		http.Error(
+	// history of a webhook that still exists. A leftover file can
-			w, "Internal server error",
+	// be removed by hand; deleted history cannot be recovered.
-			http.StatusInternalServerError,
+	err := h.commitWebhookDeletion(&webhook)
-		)
-
-		return
-	}
-
-	tx.Where(
-		"webhook_id = ?", webhook.ID,
-	).Delete(&database.Entrypoint{})
-
-	tx.Where(
-		"webhook_id = ?", webhook.ID,
-	).Delete(&database.Target{})
-
-	tx.Delete(&webhook)
-
-	err := tx.Commit().Error
 	if err != nil {
-		h.log.Error(
+		h.serverError(w, "failed to delete webhook", err)
-			"failed to commit deletion", "error", err,
-		)
-		http.Error(
-			w, "Internal server error",
-			http.StatusInternalServerError,
-		)
 
 		return
 	}
 
+	h.log.Info(
+		"webhook deleted",
+		"webhook_id", webhook.ID,
+		"user_id", userID,
+	)
+
 	// Release the delivery engine's per-webhook archiving state
 	// so a deleted webhook's archive writer (and any handle open
 	// within its debounce window) does not linger for the
@@ -671,22 +652,63 @@ func (h *Handlers) deleteWebhookResources(
 
 	err = h.dbMgr.DeleteDB(webhook.ID)
 	if err != nil {
-		h.log.Error(
+		// The configuration is committed, so the webhook is gone,
-			"failed to delete webhook event database",
+		// but its event database file is still on disk with
-			"webhook_id", webhook.ID,
+		// nothing referencing it. Report the failure rather than
-			"error", err,
+		// redirecting as though everything succeeded: the file
+		// needs removing by hand, and the logged error names it.
+		h.serverError(
+			w, "failed to delete webhook event database", err,
 		)
+
+		return
 	}
 
-	h.log.Info(
-		"webhook deleted",
-		"webhook_id", webhook.ID,
-		"user_id", userID,
-	)
-
 	http.Redirect(w, r, "/sources", http.StatusSeeOther)
 }
 
+// commitWebhookDeletion soft-deletes a webhook's entrypoints,
+// targets and the webhook row in one transaction. Every
+// statement is checked and any failure rolls the whole
+// transaction back, so a caller that gets an error knows the
+// configuration is untouched and the event database must be
+// left alone.
+func (h *Handlers) commitWebhookDeletion(
+	webhook *database.Webhook,
+) error {
+	tx := h.db.DB().Begin()
+	if tx.Error != nil {
+		return tx.Error
+	}
+
+	err := tx.Where(
+		"webhook_id = ?", webhook.ID,
+	).Delete(&database.Entrypoint{}).Error
+	if err != nil {
+		tx.Rollback()
+
+		return err
+	}
+
+	err = tx.Where(
+		"webhook_id = ?", webhook.ID,
+	).Delete(&database.Target{}).Error
+	if err != nil {
+		tx.Rollback()
+
+		return err
+	}
+
+	err = tx.Delete(webhook).Error
+	if err != nil {
+		tx.Rollback()
+
+		return err
+	}
+
+	return tx.Commit().Error
+}
+
 // evictArchiveWriter asks the delivery engine to drop its
 // cached archive writer for a webhook, closing the archive file
 // handle.
@@ -1240,145 +1262,6 @@ func (h *Handlers) HandleEntrypointCreate() http.HandlerFunc {
 	}
 }
 
-// HandleEntrypointSecret sets, rotates or removes the shared secret
-// an entrypoint verifies inbound requests with.
-//
-// Setting and rotating are the same operation: the form always takes
-// the secret afresh and the stored value is never sent to the browser
-// to be edited, so there is no path by which the page can display a
-// credential it holds. Rotation is therefore "submit the new secret",
-// and the operator already has that value — both supported senders
-// require them to enter the same string on the sender's side, so
-// there is no generated value for webhooker to reveal once.
-func (h *Handlers) HandleEntrypointSecret() http.HandlerFunc {
-	return func(w http.ResponseWriter, r *http.Request) {
-		webhook, ok := h.ownedWebhook(w, r)
-		if !ok {
-			return
-		}
-
-		// The body size cap is enforced by the MaxBodySize
-		// middleware, which runs before CSRF parses the form.
-		err := r.ParseForm()
-		if err != nil {
-			http.Error(
-				w, "Bad request", http.StatusBadRequest,
-			)
-
-			return
-		}
-
-		var entrypoint database.Entrypoint
-
-		err = h.db.DB().Where(
-			"id = ? AND webhook_id = ?",
-			chi.URLParam(r, "entrypointID"), webhook.ID,
-		).First(&entrypoint).Error
-		if err != nil {
-			http.NotFound(w, r)
-
-			return
-		}
-
-		h.applyEntrypointSecret(w, r, &entrypoint)
-	}
-}
-
-// applyEntrypointSecret validates the submitted scheme and secret and
-// stores them.
-//
-// A scheme this build does not support is a 400, never a stored value
-// the receiver would later have to interpret: the receiver fails such
-// a row closed, so letting one be created would take the entrypoint
-// offline through a form that reported success.
-func (h *Handlers) applyEntrypointSecret(
-	w http.ResponseWriter,
-	r *http.Request,
-	entrypoint *database.Entrypoint,
-) {
-	// PostFormValue, not FormValue: a credential must come from the
-	// body. FormValue falls back to the query string, and the request
-	// line — unlike the body — is what logs, proxies, Referer headers
-	// and error trackers record.
-	scheme := database.SignatureScheme(
-		r.PostFormValue("signature_scheme"),
-	)
-
-	// Surrounding whitespace is stripped, because a secret pasted from
-	// a password manager routinely carries some and the resulting
-	// mismatch is undiagnosable from the sender's side. A secret whose
-	// own first or last character is a space cannot be stored; the
-	// README says so.
-	secret := strings.TrimSpace(r.PostFormValue("secret"))
-
-	if !signature.Supported(scheme) {
-		http.Error(
-			w, "Invalid signature scheme",
-			http.StatusBadRequest,
-		)
-
-		return
-	}
-
-	if scheme == database.SignatureSchemeNone {
-		// Turning verification off drops the secret with it: a stored
-		// credential nothing reads is one more copy to leak, and
-		// Verify refuses that pairing in any case.
-		secret = ""
-	} else if secret == "" {
-		http.Error(
-			w,
-			"A shared secret is required for this signature scheme.",
-			http.StatusBadRequest,
-		)
-
-		return
-	}
-
-	h.storeEntrypointSecret(w, r, entrypoint, scheme, secret)
-}
-
-// storeEntrypointSecret writes a validated scheme and secret to an
-// entrypoint and returns the operator to the webhook page.
-func (h *Handlers) storeEntrypointSecret(
-	w http.ResponseWriter,
-	r *http.Request,
-	entrypoint *database.Entrypoint,
-	scheme database.SignatureScheme,
-	secret string,
-) {
-	// Updates with a map rather than a struct: a struct update skips
-	// zero values, and the empty pair is exactly what has to be
-	// written when verification is being turned off.
-	err := h.db.DB().Model(entrypoint).Updates(map[string]any{
-		"signature_scheme": scheme,
-		"signature_secret": secret,
-	}).Error
-	if err != nil {
-		// The error is logged by serverError; GORM's error text
-		// carries the statement, not the bound values, so the secret
-		// does not travel with it.
-		h.serverError(
-			w, "failed to update entrypoint signature", err,
-		)
-
-		return
-	}
-
-	h.log.Info(
-		"entrypoint signature configuration updated",
-		"entrypoint_id", entrypoint.ID,
-		"webhook_id", entrypoint.WebhookID,
-		"scheme", string(scheme),
-	)
-
-	http.Redirect(
-		w, r,
-		"/source/"+entrypoint.WebhookID,
-		http.StatusSeeOther,
-	)
-}
-
 // HandleTargetCreate handles adding a new target to a webhook.
 func (h *Handlers) HandleTargetCreate() http.HandlerFunc {
 	return func(w http.ResponseWriter, r *http.Request) {

internal/handlers/ui_copy_test.go

@@ -13,7 +13,6 @@ import (
 	"sneak.berlin/go/webhooker/internal/delivery"
 	"sneak.berlin/go/webhooker/internal/handlers"
 	"sneak.berlin/go/webhooker/internal/session"
-	"sneak.berlin/go/webhooker/internal/signature"
 )
 
 // Template data keys the page templates read. The handlers package has
@@ -269,16 +268,15 @@ func TestEntrypointCopyButtonIsProgressiveEnhancement(t *testing.T) {
 
 	body := renderPage(t, h, sess, "source_detail.html", map[string]any{
 		dataKeyWebhook: webhook,
-		// The handler passes projected views, never raw rows — an
+		// The handler passes projected views, never raw rows — a
-		// entrypoint carries its shared secret and a target its
+		// target carries its stored credential — so the test data
-		// stored credential — so the test data has that same shape.
+		// has that same shape.
 		"Entrypoints": handlers.NewEntrypointViews(
 			[]database.Entrypoint{entrypoint},
 		),
-		"Targets":          delivery.NewTargetViews(nil),
+		"Targets": delivery.NewTargetViews(nil),
-		"SignatureSchemes": signature.Schemes(),
+		"Events":  []database.Event{},
-		"Events":           []database.Event{},
+		"BaseURL": "https://hooks.example.com",
-		"BaseURL":          "https://hooks.example.com",
 	})
 
 	assert.Contains(

internal/handlers/webhook.go

@@ -2,7 +2,6 @@ package handlers
 
 import (
 	"encoding/json"
-	"errors"
 	"fmt"
 	"io"
 	"net/http"
@@ -12,7 +11,6 @@ import (
 	"sneak.berlin/go/webhooker/internal/database"
 	"sneak.berlin/go/webhooker/internal/delivery"
 	"sneak.berlin/go/webhooker/internal/logfield"
-	"sneak.berlin/go/webhooker/internal/signature"
 )
 
 const (
@@ -72,8 +70,12 @@ func (h *Handlers) HandleWebhook() http.HandlerFunc {
 	}
 }
 
-// processWebhookRequest reads the body, verifies the sender,
+// processWebhookRequest reads the body, serializes headers, loads
-// serializes headers, loads targets, and delivers the event.
+// targets, and delivers the event.
+//
+// Nothing about the request itself is authenticated: the entrypoint
+// UUID in the path is the credential, and reaching here means it
+// matched an active entrypoint.
 func (h *Handlers) processWebhookRequest(
 	w http.ResponseWriter,
 	r *http.Request,
@@ -84,26 +86,7 @@ func (h *Handlers) processWebhookRequest(
 		return
 	}
 
-	// Before anything is written. An unverified request must leave no
+	headersJSON, err := json.Marshal(r.Header)
-	// event row, no delivery row and no delivery task behind, so this
-	// sits above every write rather than inside the transaction that
-	// performs them. It has to sit below the body read because the
-	// signature is computed over the body; readWebhookBody is what
-	// bounds that read, so an unauthenticated sender still cannot make
-	// the process hold more than the 1 MB cap.
-	if !h.verifyInboundSignature(w, entrypoint, r.Header, body) {
-		return
-	}
-
-	// These headers are about to be stored verbatim and handed to
-	// every delivery target, so the scheme's credential comes out
-	// first. Under GitLab's scheme the header is the shared secret
-	// itself, and leaving it in would hand the ability to forge
-	// signed requests to exactly the parties the signature is meant
-	// to exclude.
-	headersJSON, err := json.Marshal(
-		signature.SanitizeHeaders(&entrypoint, r.Header),
-	)
 	if err != nil {
 		h.serverError(w, "failed to serialize headers", err)
 
@@ -122,63 +105,6 @@ func (h *Handlers) processWebhookRequest(
 	)
 }
 
-// verifyInboundSignature authenticates the request against the
-// entrypoint's configured secret, reporting false once it has written
-// the response.
-//
-// An entrypoint with no secret configured is not checked and this
-// returns true, which is the unchanged behaviour every existing
-// entrypoint keeps.
-//
-// A configuration that cannot be applied — an unknown scheme, or one
-// half of the pair missing — is a 500, not a 401: the request may well
-// be authentic, and calling it unauthorized would tell a legitimate
-// sender to go fix its own signing. Either way it is refused. Failing
-// open here would mean an entrypoint the operator has protected
-// quietly accepting anything.
-func (h *Handlers) verifyInboundSignature(
-	w http.ResponseWriter,
-	entrypoint database.Entrypoint,
-	header http.Header,
-	body []byte,
-) bool {
-	err := signature.Verify(&entrypoint, header, body)
-	if err == nil {
-		return true
-	}
-
-	if errors.Is(err, signature.ErrConfig) {
-		h.log.Error(
-			"entrypoint signature configuration cannot be applied",
-			"entrypoint_id", entrypoint.ID,
-			"webhook_id", entrypoint.WebhookID,
-			"error", err,
-		)
-		http.Error(
-			w, "Internal server error",
-			http.StatusInternalServerError,
-		)
-
-		return false
-	}
-
-	// Every field here is bounded and none is client-chosen: the ids
-	// are ours, the scheme is one of a fixed set, and the error is a
-	// static string carrying no part of the secret or of what the
-	// client presented. Reaching this line also requires a real
-	// entrypoint UUID, so it is not a line a stranger can drive.
-	h.log.Warn(
-		"inbound signature verification failed",
-		"entrypoint_id", entrypoint.ID,
-		"webhook_id", entrypoint.WebhookID,
-		"scheme", string(entrypoint.SignatureScheme),
-		"error", err,
-	)
-	http.Error(w, "Unauthorized", http.StatusUnauthorized)
-
-	return false
-}
-
 // loadActiveTargets returns all active targets for a webhook.
 func (h *Handlers) loadActiveTargets(
 	webhookID string,

internal/handlers/webhook_signature_test.go

@@ -1,468 +0,0 @@
-package handlers_test
-
-import (
-	"bytes"
-	"context"
-	"crypto/hmac"
-	"crypto/sha256"
-	"encoding/hex"
-	"log/slog"
-	"net/http"
-	"net/http/httptest"
-	"strings"
-	"testing"
-
-	"github.com/go-chi/chi"
-	"github.com/stretchr/testify/assert"
-	"github.com/stretchr/testify/require"
-	"gorm.io/gorm/clause"
-	"sneak.berlin/go/webhooker/internal/database"
-	"sneak.berlin/go/webhooker/internal/handlers"
-	"sneak.berlin/go/webhooker/internal/signature"
-)
-
-const (
-	// inboundSecret is the shared secret the signed-receiver tests
-	// configure on their entrypoint. It doubles as a marker: no log
-	// line and no rendered page may contain it.
-	inboundSecret = "QQINBOUNDSECRETQQ"
-
-	// inboundBody is the payload the sender signs.
-	inboundBody = `{"zen":"Non-blocking is better than blocking."}`
-
-	// entrypointIDParam is the chi URL parameter naming an entrypoint.
-	entrypointIDParam = "entrypointID"
-)
-
-// hubSignature returns the X-Hub-Signature-256 value a GitHub sender
-// holding secret would send for inboundBody.
-func hubSignature(secret string) string {
-	mac := hmac.New(sha256.New, []byte(secret))
-	_, _ = mac.Write([]byte(inboundBody))
-
-	return "sha256=" + hex.EncodeToString(mac.Sum(nil))
-}
-
-// seedSignedEntrypoint inserts an active entrypoint for a webhook
-// with the given signature configuration and returns it.
-func seedSignedEntrypoint(
-	t *testing.T,
-	db *database.Database,
-	webhookID string,
-	scheme database.SignatureScheme,
-	secret string,
-) *database.Entrypoint {
-	t.Helper()
-
-	ep := &database.Entrypoint{
-		WebhookID:       webhookID,
-		Path:            "path-" + webhookID,
-		Description:     "signed",
-		Active:          true,
-		SignatureScheme: scheme,
-		SignatureSecret: secret,
-	}
-
-	require.NoError(
-		t,
-		db.DB().Omit(clause.Associations).Create(ep).Error,
-	)
-
-	return ep
-}
-
-// postToEntrypoint drives the real receiver handler at an
-// entrypoint's path with one optional header set.
-func postToEntrypoint(
-	t *testing.T,
-	h *handlers.Handlers,
-	path, body, headerName, headerValue string,
-) *httptest.ResponseRecorder {
-	t.Helper()
-
-	req := httptest.NewRequestWithContext(
-		context.Background(),
-		http.MethodPost,
-		"/webhook/"+path,
-		strings.NewReader(body),
-	)
-	req.Header.Set("Content-Type", "application/json")
-
-	if headerName != "" {
-		req.Header.Set(headerName, headerValue)
-	}
-
-	rctx := chi.NewRouteContext()
-	rctx.URLParams.Add("uuid", path)
-
-	req = req.WithContext(
-		context.WithValue(req.Context(), chi.RouteCtxKey, rctx),
-	)
-
-	w := httptest.NewRecorder()
-	h.HandleWebhook().ServeHTTP(w, req)
-
-	return w
-}
-
-// storedEvents counts the event rows a webhook's per-webhook database
-// holds. A database that was never opened holds none, which is the
-// state a rejected request has to leave behind.
-func storedEvents(
-	t *testing.T,
-	mgr *database.WebhookDBManager,
-	webhookID string,
-) int64 {
-	t.Helper()
-
-	if !mgr.DBExists(webhookID) {
-		return 0
-	}
-
-	db, err := mgr.GetDB(webhookID)
-	require.NoError(t, err)
-
-	var count int64
-
-	require.NoError(
-		t,
-		db.Model(&database.Event{}).
-			Where("webhook_id = ?", webhookID).
-			Count(&count).Error,
-	)
-
-	return count
-}
-
-// storedEventHeaders reads back the Headers column of the single
-// event row a webhook's per-webhook database holds.
-//
-// It reads the database rather than an in-memory struct on purpose:
-// what matters is what an operator, a backup or the reaper's archive
-// would find on disk, not what the handler passed around.
-func storedEventHeaders(
-	t *testing.T,
-	mgr *database.WebhookDBManager,
-	webhookID string,
-) string {
-	t.Helper()
-
-	require.True(t, mgr.DBExists(webhookID))
-
-	db, err := mgr.GetDB(webhookID)
-	require.NoError(t, err)
-
-	var events []database.Event
-
-	require.NoError(
-		t,
-		db.Where("webhook_id = ?", webhookID).
-			Find(&events).Error,
-	)
-	require.Len(t, events, 1)
-
-	return events[0].Headers
-}
-
-// signedReceiverCase is one inbound request against an entrypoint
-// with a given stored signature configuration.
-type signedReceiverCase struct {
-	name        string
-	scheme      database.SignatureScheme
-	secret      string
-	headerName  string
-	headerValue string
-	body        string
-	wantStatus  int
-}
-
-// signedReceiverCases covers each supported scheme with a valid
-// signature, an invalid one and none at all, plus the two states that
-// are not "a client got it wrong": an entrypoint with nothing
-// configured, and one whose stored configuration cannot be applied.
-func signedReceiverCases() []signedReceiverCase {
-	return append(
-		schemeReceiverCases(), unverifiedReceiverCases()...,
-	)
-}
-
-// schemeReceiverCases covers the two supported schemes.
-func schemeReceiverCases() []signedReceiverCase {
-	return []signedReceiverCase{
-		{
-			name:        "github valid",
-			scheme:      database.SignatureSchemeGitHub,
-			secret:      inboundSecret,
-			headerName:  signature.HeaderGitHub,
-			headerValue: hubSignature(inboundSecret),
-			body:        inboundBody,
-			wantStatus:  http.StatusOK,
-		},
-		{
-			name:        "github wrong secret",
-			scheme:      database.SignatureSchemeGitHub,
-			secret:      inboundSecret,
-			headerName:  signature.HeaderGitHub,
-			headerValue: hubSignature("wrong"),
-			body:        inboundBody,
-			wantStatus:  http.StatusUnauthorized,
-		},
-		{
-			// A digest that was valid for a different body: the
-			// check is over the bytes as received.
-			name:        "github body tampered",
-			scheme:      database.SignatureSchemeGitHub,
-			secret:      inboundSecret,
-			headerName:  signature.HeaderGitHub,
-			headerValue: hubSignature(inboundSecret),
-			body:        inboundBody + " ",
-			wantStatus:  http.StatusUnauthorized,
-		},
-		{
-			name:       "github unsigned",
-			scheme:     database.SignatureSchemeGitHub,
-			secret:     inboundSecret,
-			body:       inboundBody,
-			wantStatus: http.StatusUnauthorized,
-		},
-		{
-			name:        "gitlab valid",
-			scheme:      database.SignatureSchemeGitLab,
-			secret:      inboundSecret,
-			headerName:  signature.HeaderGitLab,
-			headerValue: inboundSecret,
-			body:        inboundBody,
-			wantStatus:  http.StatusOK,
-		},
-		{
-			name:        "gitlab wrong token",
-			scheme:      database.SignatureSchemeGitLab,
-			secret:      inboundSecret,
-			headerName:  signature.HeaderGitLab,
-			headerValue: "wrong",
-			body:        inboundBody,
-			wantStatus:  http.StatusUnauthorized,
-		},
-		{
-			name:       "gitlab unsigned",
-			scheme:     database.SignatureSchemeGitLab,
-			secret:     inboundSecret,
-			body:       inboundBody,
-			wantStatus: http.StatusUnauthorized,
-		},
-	}
-}
-
-// unverifiedReceiverCases covers the two entrypoint states that are
-// not about a client getting its signature wrong: nothing configured
-// at all, and a configuration the receiver cannot apply.
-func unverifiedReceiverCases() []signedReceiverCase {
-	return []signedReceiverCase{
-		{
-			// The pass-through case. An entrypoint with nothing
-			// configured is what every deployment already has, and
-			// it must keep accepting unsigned requests so that an
-			// upgrade does not lock an operator out of their own
-			// receivers.
-			name:       "unconfigured accepts unsigned",
-			scheme:     database.SignatureSchemeNone,
-			body:       inboundBody,
-			wantStatus: http.StatusOK,
-		},
-		{
-			// A stray signature header changes nothing when nothing
-			// is configured to check it.
-			name:        "unconfigured ignores a stray header",
-			scheme:      database.SignatureSchemeNone,
-			headerName:  signature.HeaderGitHub,
-			headerValue: "sha256=deadbeef",
-			body:        inboundBody,
-			wantStatus:  http.StatusOK,
-		},
-		{
-			// A scheme this build cannot apply, reachable only by
-			// editing the database: refused, not waved through as
-			// unverified.
-			name:        "unknown scheme fails closed",
-			scheme:      database.SignatureScheme("stripe"),
-			secret:      inboundSecret,
-			headerName:  signature.HeaderGitHub,
-			headerValue: hubSignature(inboundSecret),
-			body:        inboundBody,
-			wantStatus:  http.StatusInternalServerError,
-		},
-	}
-}
-
-// TestReceiverVerifiesConfiguredEntrypoints is the load-bearing test
-// for the feature: for each supported scheme a correctly signed
-// request is accepted and stored, and an incorrectly signed or
-// unsigned one is answered 401 having stored nothing.
-//
-// The event count is the half that matters most. A rejection that
-// still wrote a row would leave the receiver a place for a stranger
-// who knows a URL to deposit content, which is exactly what the
-// signature is there to prevent.
-//
-// The cases share one application and take a webhook each, rather
-// than each standing up its own: every newTestApp seeds an admin user
-// and so pays an Argon2id hash at 64 MB, and this package's test
-// budget is not large enough to spend one per table row.
-func TestReceiverVerifiesConfiguredEntrypoints(t *testing.T) {
-	t.Parallel()
-
-	var (
-		h   *handlers.Handlers
-		db  *database.Database
-		mgr *database.WebhookDBManager
-	)
-
-	app := newTestApp(t, &h, &db, &mgr)
-	app.RequireStart()
-
-	t.Cleanup(app.RequireStop)
-
-	for _, tc := range signedReceiverCases() {
-		wh := seedWebhook(t, db)
-		ep := seedSignedEntrypoint(
-			t, db, wh.ID, tc.scheme, tc.secret,
-		)
-
-		w := postToEntrypoint(
-			t, h, ep.Path, tc.body,
-			tc.headerName, tc.headerValue,
-		)
-
-		assert.Equal(t, tc.wantStatus, w.Code, "case %s", tc.name)
-
-		want := int64(0)
-		if tc.wantStatus == http.StatusOK {
-			want = 1
-		}
-
-		assert.Equal(
-			t, want, storedEvents(t, mgr, wh.ID),
-			"case %s: stored event rows after a %d response",
-			tc.name, w.Code,
-		)
-	}
-}
-
-// TestReceiverLogsNoSecret proves the rejection path does not write
-// the shared secret, or what the client presented, into the log. A
-// GitLab token arrives as the credential itself, so echoing the
-// header value would put a live secret in the log of every deployment
-// whose sender is briefly misconfigured.
-func TestReceiverLogsNoSecret(t *testing.T) {
-	t.Parallel()
-
-	const presented = "QQPRESENTEDVALUEQQ"
-
-	var (
-		h  *handlers.Handlers
-		db *database.Database
-	)
-
-	app := newTestApp(t, &h, &db)
-	app.RequireStart()
-
-	t.Cleanup(app.RequireStop)
-
-	var buf bytes.Buffer
-
-	h.SetLogForTest(slog.New(slog.NewJSONHandler(&buf, nil)))
-
-	wh := seedWebhook(t, db)
-	ep := seedSignedEntrypoint(
-		t, db, wh.ID,
-		database.SignatureSchemeGitLab, inboundSecret,
-	)
-
-	w := postToEntrypoint(
-		t, h, ep.Path, inboundBody,
-		signature.HeaderGitLab, presented,
-	)
-	require.Equal(t, http.StatusUnauthorized, w.Code)
-
-	// The rejection is recorded at all — a silent 401 leaves an
-	// operator no way to see a sender failing to authenticate.
-	assert.Contains(t, buf.String(), "verification failed")
-	assert.NotContains(t, buf.String(), inboundSecret)
-	assert.NotContains(t, buf.String(), presented)
-}
-
-// TestReceiverDoesNotStoreInboundCredential proves an accepted
-// request leaves no copy of the shared secret in the event store.
-//
-// GitLab's X-Gitlab-Token is the credential itself, not a digest
-// over the request. Stored headers are read back by the UI, copied
-// into every backup and archive, and handed verbatim to every
-// delivery target, so a stored token is the entrypoint's only
-// authentication control disclosed to precisely the parties it
-// exists to exclude.
-//
-// The two cases share one application: every newTestApp seeds an
-// admin user and pays an Argon2id hash at 64 MB, and this package's
-// test budget does not stretch to one per case.
-func TestReceiverDoesNotStoreInboundCredential(t *testing.T) {
-	t.Parallel()
-
-	var (
-		h   *handlers.Handlers
-		db  *database.Database
-		mgr *database.WebhookDBManager
-	)
-
-	app := newTestApp(t, &h, &db, &mgr)
-	app.RequireStart()
-
-	t.Cleanup(app.RequireStop)
-
-	gitlab := seedWebhook(t, db)
-	gitlabEP := seedSignedEntrypoint(
-		t, db, gitlab.ID,
-		database.SignatureSchemeGitLab, inboundSecret,
-	)
-
-	w := postToEntrypoint(
-		t, h, gitlabEP.Path, inboundBody,
-		signature.HeaderGitLab, inboundSecret,
-	)
-	require.Equal(t, http.StatusOK, w.Code)
-
-	stored := storedEventHeaders(t, mgr, gitlab.ID)
-
-	assert.NotContains(
-		t, stored, inboundSecret,
-		"the shared secret must not be persisted",
-	)
-	assert.NotContains(
-		t, stored, signature.HeaderGitLab,
-		"the credential header must not be persisted at all",
-	)
-
-	// Everything else the sender set is still there. A fix that
-	// stored no headers would satisfy the assertions above while
-	// discarding the record the receiver exists to keep.
-	assert.Contains(t, stored, "Content-Type")
-
-	// A GitHub digest is an HMAC over the body, so the key cannot be
-	// recovered from it and it stays: the stripping is scoped to
-	// what actually carries the secret.
-	github := seedWebhook(t, db)
-	githubEP := seedSignedEntrypoint(
-		t, db, github.ID,
-		database.SignatureSchemeGitHub, inboundSecret,
-	)
-
-	w = postToEntrypoint(
-		t, h, githubEP.Path, inboundBody,
-		signature.HeaderGitHub, hubSignature(inboundSecret),
-	)
-	require.Equal(t, http.StatusOK, w.Code)
-
-	stored = storedEventHeaders(t, mgr, github.ID)
-
-	assert.Contains(t, stored, signature.HeaderGitHub)
-	assert.NotContains(t, stored, inboundSecret)
-}

internal/middleware/csrf.go

@@ -5,6 +5,7 @@ import (
 
 	"github.com/gorilla/csrf"
 	"sneak.berlin/go/webhooker/internal/logfield"
+	"sneak.berlin/go/webhooker/internal/reqtls"
 )
 
 // CSRFToken retrieves the CSRF token from the request context.
@@ -13,13 +14,6 @@ func CSRFToken(r *http.Request) string {
 	return csrf.Token(r)
 }
 
-// isClientTLS reports whether the client-facing connection uses TLS.
-// It checks for a direct TLS connection (r.TLS) or a TLS-terminating
-// reverse proxy that sets the standard X-Forwarded-Proto header.
-func isClientTLS(r *http.Request) bool {
-	return r.TLS != nil || r.Header.Get("X-Forwarded-Proto") == "https"
-}
-
 // CSRF returns middleware that provides CSRF protection using the
 // gorilla/csrf library. The middleware uses the session authentication
 // key to sign a CSRF cookie and validates a masked token submitted via
@@ -27,9 +21,10 @@ func isClientTLS(r *http.Request) bool {
 // POST/PUT/PATCH/DELETE requests. Requests with an invalid or missing
 // token receive a 403 Forbidden response.
 //
-// The middleware detects the client-facing transport protocol per-request
+// The middleware detects the client-facing transport protocol
-// using r.TLS and the X-Forwarded-Proto header. This allows correct
+// per-request via reqtls.IsTLS, the single TLS predicate the session
-// behavior in all deployment scenarios:
+// cookie also uses. This allows correct behavior in all deployment
+// scenarios:
 //
 //   - Direct HTTPS: strict Referer/Origin checks, Secure cookies.
 //   - Behind a TLS-terminating reverse proxy: strict checks (the
@@ -83,7 +78,7 @@ func (m *Middleware) CSRF() func(http.Handler) http.Handler {
 		httpCSRF := httpProtect(next)
 
 		return http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
-			if isClientTLS(r) {
+			if reqtls.IsTLS(r) {
 				// Client is on TLS (directly or via reverse proxy).
 				// Use Secure cookies and strict Origin/Referer checks.
 				tlsCSRF.ServeHTTP(w, r)

internal/middleware/csrf_test.go

@@ -297,55 +297,176 @@ func TestCSRFToken_NoMiddleware(t *testing.T) {
 }
 
 // --- TLS Detection Tests ---
+//
+// The predicate itself is tested in internal/reqtls. What is tested
+// here is the consequence that actually matters: which of the two
+// gorilla/csrf instances a request is routed to.
+//
+// The two are told apart behaviourally rather than by inspection. On
+// the STRICT (TLS) instance, a state-changing request carrying no
+// Origin header must supply a Referer -- gorilla/csrf rejects it with
+// ErrNoReferer before it ever looks at the token, to defend a
+// TLS site against an HTTP machine-in-the-middle injecting a form. On
+// the RELAXED (plaintext) instance that check is skipped and a valid
+// token is enough. So: valid token, no Origin, no Referer, and the
+// outcome names the instance.
+//
+// Landing on the relaxed instance for a genuinely-HTTPS deployment is
+// the defect: an exact == "https" comparison did exactly that for the
+// uppercase and comma-appended spellings below.
 
-func TestIsClientTLS_DirectTLS(t *testing.T) {
+// csrfTookStrictPath reports whether the CSRF middleware routed a
+// request with the given transport to the strict instance. It also
+// asserts the CSRF cookie's Secure attribute agrees, since the two are
+// set by the same choice and must never disagree.
+func csrfTookStrictPath(
+	t *testing.T,
+	env string,
+	directTLS bool,
+	fwdProto string,
+) bool {
+	t.Helper()
+
+	m, _ := testMiddleware(t, env)
+	csrfMW := m.CSRF()
+
+	newReq := func(method string) *http.Request {
+		r := httptest.NewRequestWithContext(
+			context.Background(), method,
+			"http://example.com/form", nil,
+		)
+
+		if directTLS {
+			r.TLS = &tls.ConnectionState{}
+		}
+
+		if fwdProto != "" {
+			r.Header.Set("X-Forwarded-Proto", fwdProto)
+		}
+
+		return r
+	}
+
+	token, cookies := csrfGetToken(t, csrfMW, newReq(http.MethodGet))
+
+	// Deliberately no Origin and no Referer: that is what makes the
+	// two instances distinguishable.
+	called, code := csrfPostWithToken(
+		t, csrfMW, newReq(http.MethodPost), token, cookies,
+	)
+
+	strict := !called
+
+	if strict {
+		assert.Equal(
+			t, http.StatusForbidden, code,
+			"the strict instance rejects a Referer-less POST",
+		)
+	}
+
+	for _, c := range cookies {
+		if c.Name == csrfCookieName {
+			assert.Equal(
+				t, strict, c.Secure,
+				"the CSRF cookie's Secure attribute and the "+
+					"chosen instance come from one decision "+
+					"and must agree",
+			)
+		}
+	}
+
+	return strict
+}
+
+// TestCSRF_ForwardedProtoSpellingsTakeStrictPath runs the header
+// spellings a real proxy emits through the middleware. The environment
+// is dev -- the DEFAULT when WEBHOOKER_ENVIRONMENT is unset -- to pin
+// that the routing is a per-request transport decision and owes
+// nothing to configuration.
+func TestCSRF_ForwardedProtoSpellingsTakeStrictPath(t *testing.T) {
 	t.Parallel()
 
-	r := httptest.NewRequestWithContext(
+	cases := []struct {
-		context.Background(), http.MethodGet, "/", nil)
+		name   string
-	r.TLS = &tls.ConnectionState{}
+		header string
+		strict bool
+		why    string
+	}{
+		{
+			name:   "lowercase",
+			header: "https",
+			strict: true,
+			why:    "the ordinary spelling",
+		},
+		{
+			name:   "uppercase",
+			header: "HTTPS",
+			strict: true,
+			why:    "the header value is a case-insensitive token",
+		},
+		{
+			name:   "chain with plaintext inner hop",
+			header: "https, http",
+			strict: true,
+			why: "a chained proxy appends its hop; the leftmost " +
+				"element is the browser's connection",
+		},
+		{
+			name:   "chain of two TLS hops",
+			header: "https,https",
+			strict: true,
+			why:    "appended chain with no space after the comma",
+		},
+		{
+			name:   "trailing space",
+			header: "https ",
+			strict: true,
+			why:    "whitespace is not part of the token",
+		},
+		{
+			name:   "plaintext",
+			header: "http",
+			strict: false,
+			why: "the negative control: the proxy reports a " +
+				"plaintext client connection",
+		},
+	}
+
+	for _, tc := range cases {
+		t.Run(tc.name, func(t *testing.T) {
+			t.Parallel()
+
+			assert.Equal(
+				t, tc.strict,
+				csrfTookStrictPath(
+					t, config.EnvironmentDev, false, tc.header,
+				),
+				"X-Forwarded-Proto %q: %s", tc.header, tc.why,
+			)
+		})
+	}
+}
+
+// TestCSRF_DirectTLSTakesStrictPath covers the no-proxy TLS
+// deployment, and TestCSRF_PlaintextTakesRelaxedPath the no-proxy
+// plaintext one -- the local development case that must keep working.
+func TestCSRF_DirectTLSTakesStrictPath(t *testing.T) {
+	t.Parallel()
 
 	assert.True(
-		t, middleware.IsClientTLS(r),
+		t,
-		"should detect direct TLS connection",
+		csrfTookStrictPath(t, config.EnvironmentDev, true, ""),
+		"a request that arrived over TLS takes the strict path",
 	)
 }
 
-func TestIsClientTLS_XForwardedProto(t *testing.T) {
+func TestCSRF_PlaintextTakesRelaxedPath(t *testing.T) {
 	t.Parallel()
 
-	r := httptest.NewRequestWithContext(
-		context.Background(), http.MethodGet, "/", nil)
-	r.Header.Set("X-Forwarded-Proto", "https")
-
-	assert.True(
-		t, middleware.IsClientTLS(r),
-		"should detect TLS via X-Forwarded-Proto",
-	)
-}
-
-func TestIsClientTLS_PlaintextHTTP(t *testing.T) {
-	t.Parallel()
-
-	r := httptest.NewRequestWithContext(
-		context.Background(), http.MethodGet, "/", nil)
-
 	assert.False(
-		t, middleware.IsClientTLS(r),
+		t,
-		"should detect plaintext HTTP",
+		csrfTookStrictPath(t, config.EnvironmentProd, false, ""),
-	)
+		"no TLS and no proxy header is plaintext, in any environment",
-}
-
-func TestIsClientTLS_XForwardedProtoHTTP(t *testing.T) {
-	t.Parallel()
-
-	r := httptest.NewRequestWithContext(
-		context.Background(), http.MethodGet, "/", nil)
-	r.Header.Set("X-Forwarded-Proto", "http")
-
-	assert.False(
-		t, middleware.IsClientTLS(r),
-		"should detect plaintext when X-Forwarded-Proto is http",
 	)
 }
 

internal/middleware/export_test.go

@@ -56,11 +56,6 @@ func ClientKeyForTest(m *Middleware, r *http.Request) string {
 	return m.clientKey(r)
 }
 
-// IsClientTLS exposes isClientTLS for testing.
-func IsClientTLS(r *http.Request) bool {
-	return isClientTLS(r)
-}
-
 // LoginRateLimitConst exposes the loginRateLimit constant: the
 // number of FAILED login attempts one client may make against one
 // submitted username per interval.

internal/reqtls/reqtls.go

@@ -0,0 +1,59 @@
+// Package reqtls answers one question, in one place, for the whole
+// application: did this request reach the service over TLS?
+//
+// It exists because that question used to be answered independently in
+// several packages, by hand, and the answers disagreed. The session
+// cookie's Secure attribute was decided at startup from the configured
+// environment while the CSRF cookie's was decided per-request, so a
+// deployment behind a TLS proxy in the default environment emitted one
+// Secure cookie and one non-Secure cookie on the same response.
+// Everything kept working, which is exactly why nobody noticed.
+//
+// Any code that needs a scheme or a Secure flag must call IsTLS rather
+// than reading the request itself.
+package reqtls
+
+import (
+	"net/http"
+	"strings"
+)
+
+// forwardedProtoHeader is the de-facto standard header by which a
+// TLS-terminating reverse proxy reports the protocol the CLIENT used.
+const forwardedProtoHeader = "X-Forwarded-Proto"
+
+// IsTLS reports whether the client-facing connection uses TLS: either
+// the request arrived over TLS directly, or a reverse proxy terminated
+// TLS and said so in X-Forwarded-Proto.
+//
+// The header is only as trustworthy as whatever sits in front of the
+// listener. A proxy that overwrites it -- which is what the deployment
+// documentation requires -- makes it authoritative; a listener exposed
+// directly to clients lets any client assert it. That is the same
+// exposure every X-Forwarded-* consumer carries.
+func IsTLS(r *http.Request) bool {
+	return r.TLS != nil || forwardedProto(r) == "https"
+}
+
+// forwardedProto reduces X-Forwarded-Proto to a bare, comparable
+// protocol token, or "" when the header is absent or blank.
+//
+// Two shapes that real infrastructure emits do not survive an exact
+// comparison against "https", and both name a TLS client connection:
+//
+//   - "HTTPS", because the header value is a case-insensitive token and
+//     nothing obliges a proxy to emit it lowercased.
+//   - "https, http", because a proxy chained behind another proxy
+//     APPENDS its own hop instead of replacing the value. As with
+//     X-Forwarded-For, the leftmost element is the one nearest the
+//     client, so it is the element that describes the browser's
+//     connection -- the only hop a cookie's Secure attribute is about.
+//
+// Landing on the plaintext path for either of those spellings is not a
+// cosmetic error: it stops gorilla/csrf enforcing the strict Referer
+// check on a site that genuinely is HTTPS.
+func forwardedProto(r *http.Request) string {
+	first, _, _ := strings.Cut(r.Header.Get(forwardedProtoHeader), ",")
+
+	return strings.ToLower(strings.TrimSpace(first))
+}

internal/reqtls/reqtls_test.go

@@ -0,0 +1,209 @@
+package reqtls_test
+
+import (
+	"context"
+	"crypto/tls"
+	"net/http"
+	"net/http/httptest"
+	"testing"
+
+	"github.com/stretchr/testify/assert"
+	"sneak.berlin/go/webhooker/internal/reqtls"
+)
+
+// newReq builds a plaintext request with no forwarding headers.
+func newReq(t *testing.T) *http.Request {
+	t.Helper()
+
+	return httptest.NewRequestWithContext(
+		context.Background(), http.MethodGet, "/", nil,
+	)
+}
+
+func TestIsTLS_DirectTLS(t *testing.T) {
+	t.Parallel()
+
+	r := newReq(t)
+	r.TLS = &tls.ConnectionState{}
+
+	assert.True(
+		t, reqtls.IsTLS(r),
+		"a request that arrived over TLS is TLS",
+	)
+}
+
+func TestIsTLS_PlaintextNoHeader(t *testing.T) {
+	t.Parallel()
+
+	assert.False(
+		t, reqtls.IsTLS(newReq(t)),
+		"no TLS connection and no header means plaintext",
+	)
+}
+
+// protoCase is one X-Forwarded-Proto spelling and the answer IsTLS
+// owes it.
+type protoCase struct {
+	name   string
+	header string
+	want   bool
+	why    string
+}
+
+// protoCases enumerates the header values real infrastructure emits.
+func protoCases() []protoCase {
+	return append(protoTLSCases(), protoPlaintextCases()...)
+}
+
+// protoTLSCases are the spellings that name a TLS client connection.
+// Every one but the first is a spelling an exact == "https"
+// comparison used to miss, silently downgrading a genuinely-HTTPS
+// deployment to the plaintext path.
+func protoTLSCases() []protoCase {
+	return []protoCase{
+		{
+			name:   "lowercase",
+			header: "https",
+			want:   true,
+			why:    "the ordinary spelling",
+		},
+		{
+			name:   "uppercase",
+			header: "HTTPS",
+			want:   true,
+			why: "the value is a case-insensitive token; " +
+				"nothing obliges a proxy to lowercase it",
+		},
+		{
+			name:   "mixed case",
+			header: "HttpS",
+			want:   true,
+			why:    "case folding must be total, not just the two extremes",
+		},
+		{
+			name:   "chain with plaintext inner hop",
+			header: "https, http",
+			want:   true,
+			why: "a chained proxy appends its hop; the leftmost " +
+				"element is the client-facing one",
+		},
+		{
+			name:   "chain of two TLS hops",
+			header: "https,https",
+			want:   true,
+			why:    "appended chain with no space after the comma",
+		},
+		{
+			name:   "trailing space",
+			header: "https ",
+			want:   true,
+			why:    "surrounding whitespace is not part of the token",
+		},
+		{
+			name:   "leading space",
+			header: " https",
+			want:   true,
+			why:    "surrounding whitespace is not part of the token",
+		},
+		{
+			name:   "uppercase chain",
+			header: "HTTPS, HTTP",
+			want:   true,
+			why:    "case folding and chain splitting must compose",
+		},
+	}
+}
+
+// protoPlaintextCases are the values that must NOT be read as TLS.
+func protoPlaintextCases() []protoCase {
+	return []protoCase{
+		{
+			name:   "plaintext",
+			header: "http",
+			want:   false,
+			why:    "the negative control: the proxy reports plaintext",
+		},
+		{
+			name:   "plaintext chain with TLS inner hop",
+			header: "http, https",
+			want:   false,
+			why: "the client-facing hop is plaintext even though " +
+				"an inner hop used TLS",
+		},
+		{
+			name:   "empty",
+			header: "",
+			want:   false,
+			why:    "an empty header asserts nothing",
+		},
+		{
+			name:   "whitespace only",
+			header: "   ",
+			want:   false,
+			why:    "a blank header asserts nothing",
+		},
+		{
+			name:   "unrelated token",
+			header: "ftp",
+			want:   false,
+			why:    "only https means TLS",
+		},
+		{
+			name:   "https as a substring",
+			header: "nothttps",
+			want:   false,
+			why:    "matching must be on the whole token, not a substring",
+		},
+	}
+}
+
+func TestIsTLS_ForwardedProtoSpellings(t *testing.T) {
+	t.Parallel()
+
+	for _, tc := range protoCases() {
+		t.Run(tc.name, func(t *testing.T) {
+			t.Parallel()
+
+			r := newReq(t)
+			r.Header.Set("X-Forwarded-Proto", tc.header)
+
+			assert.Equal(
+				t, tc.want, reqtls.IsTLS(r),
+				"X-Forwarded-Proto %q: %s", tc.header, tc.why,
+			)
+		})
+	}
+}
+
+// TestIsTLS_DirectTLSBeatsPlaintextHeader pins the precedence: a
+// connection this process itself terminated with TLS is a fact, and a
+// header claiming otherwise does not override it.
+func TestIsTLS_DirectTLSBeatsPlaintextHeader(t *testing.T) {
+	t.Parallel()
+
+	r := newReq(t)
+	r.TLS = &tls.ConnectionState{}
+	r.Header.Set("X-Forwarded-Proto", "http")
+
+	assert.True(
+		t, reqtls.IsTLS(r),
+		"an actual TLS connection outranks a header claiming plaintext",
+	)
+}
+
+// TestIsTLS_FirstHeaderValueWins covers a proxy that adds a second
+// header line rather than appending to the existing one. net/http
+// keeps them as separate values; the first is the client-facing hop,
+// matching how the comma-separated form is read.
+func TestIsTLS_FirstHeaderValueWins(t *testing.T) {
+	t.Parallel()
+
+	r := newReq(t)
+	r.Header.Add("X-Forwarded-Proto", "https")
+	r.Header.Add("X-Forwarded-Proto", "http")
+
+	assert.True(
+		t, reqtls.IsTLS(r),
+		"the first header line is the client-facing hop",
+	)
+}

internal/server/bind_address_test.go

@@ -0,0 +1,336 @@
+package server_test
+
+import (
+	"context"
+	"net"
+	"net/http"
+	"strconv"
+	"testing"
+	"time"
+
+	"github.com/stretchr/testify/assert"
+	"github.com/stretchr/testify/require"
+	"go.uber.org/fx"
+	"sneak.berlin/go/webhooker/internal/config"
+	"sneak.berlin/go/webhooker/internal/globals"
+	"sneak.berlin/go/webhooker/internal/server"
+)
+
+const (
+	// loopbackV4 is the shipped BIND_ADDRESS default.
+	loopbackV4 = "127.0.0.1"
+
+	// wildcardV4 is the value a container deployment must set,
+	// where a loopback-bound process is unreachable from outside
+	// its network namespace even with a published port.
+	wildcardV4 = "0.0.0.0"
+
+	// unavailableAddr is a TEST-NET-1 address (RFC 5737). It is a
+	// well-formed literal that no host is assigned, so binding it
+	// fails with EADDRNOTAVAIL rather than succeeding somewhere
+	// unexpected.
+	unavailableAddr = "192.0.2.1"
+
+	// listenReadyTimeout bounds the wait for the listener to accept
+	// connections. The bind itself is immediate; this only covers
+	// goroutine scheduling.
+	listenReadyTimeout = 3 * time.Second
+
+	// listenPollInterval is how often the readiness wait retries.
+	listenPollInterval = 10 * time.Millisecond
+
+	// dialTimeout bounds a single connection attempt in these
+	// tests. Everything dialled here is on this host, so a dial
+	// that is not answered immediately is a failure, not slowness.
+	dialTimeout = time.Second
+)
+
+// freePort returns a TCP port that is free on every local address at
+// the moment it returns, by taking one on the wildcard and releasing
+// it. The window between release and re-bind is the standard one
+// every "pick a free port" helper carries.
+func freePort(t *testing.T) int {
+	t.Helper()
+
+	var listenCfg net.ListenConfig
+
+	l, err := listenCfg.Listen(t.Context(), "tcp", "0.0.0.0:0")
+	require.NoError(t, err)
+
+	addr, ok := l.Addr().(*net.TCPAddr)
+	require.True(t, ok, "listener is not TCP")
+	require.NoError(t, l.Close())
+
+	return addr.Port
+}
+
+// otherLocalAddr returns a local IPv4 address that is not
+// loopbackV4, or skips the test when the host has none.
+//
+// The bind-address tests need a second address of this host to stand
+// in for "another interface": what a wildcard bind claims and a
+// loopback bind does not. 127.0.0.2 is that address on Linux, where
+// the whole 127.0.0.0/8 is local; elsewhere an interface address is
+// used instead. Each candidate is proven bindable before it is
+// returned, so a host that offers neither skips rather than fails on
+// something that was never about the code under test.
+func otherLocalAddr(t *testing.T) string {
+	t.Helper()
+
+	candidates := []string{"127.0.0.2"}
+
+	ifaceAddrs, err := net.InterfaceAddrs()
+	require.NoError(t, err)
+
+	for _, a := range ifaceAddrs {
+		ipNet, ok := a.(*net.IPNet)
+		if !ok {
+			continue
+		}
+
+		ip4 := ipNet.IP.To4()
+		if ip4 == nil || ip4.String() == loopbackV4 {
+			continue
+		}
+
+		candidates = append(candidates, ip4.String())
+	}
+
+	var listenCfg net.ListenConfig
+
+	for _, candidate := range candidates {
+		l, listenErr := listenCfg.Listen(
+			t.Context(), "tcp", net.JoinHostPort(candidate, "0"),
+		)
+		if listenErr != nil {
+			continue
+		}
+
+		require.NoError(t, l.Close())
+
+		return candidate
+	}
+
+	t.Skip("host has no second local IPv4 address to bind")
+
+	return ""
+}
+
+// startBoundServer starts the wired app with the given bind address
+// on a free port and returns that port. The app is stopped on
+// cleanup.
+func startBoundServer(t *testing.T, bindAddress string) int {
+	t.Helper()
+
+	port := freePort(t)
+
+	env := newTestEnv(t)
+	env.cfg.BindAddress = bindAddress
+	env.cfg.Port = port
+
+	app := fx.New(
+		fx.NopLogger,
+		fx.Supply(env.log, env.cfg, env.mw, env.hnd),
+		fx.Provide(globals.New, server.New),
+		fx.Invoke(func(*server.Server) {}),
+	)
+
+	startCtx, cancelStart := context.WithTimeout(
+		context.Background(), lifecycleTimeout,
+	)
+	defer cancelStart()
+
+	require.NoError(t, app.Start(startCtx))
+
+	t.Cleanup(func() {
+		stopCtx, cancelStop := context.WithTimeout(
+			context.Background(), lifecycleTimeout,
+		)
+		defer cancelStop()
+
+		require.NoError(t, app.Stop(stopCtx))
+	})
+
+	return port
+}
+
+// dialable reports whether a TCP connection to addr succeeds.
+func dialable(ctx context.Context, addr string) bool {
+	dialer := net.Dialer{Timeout: dialTimeout}
+
+	conn, err := dialer.DialContext(ctx, "tcp", addr)
+	if err != nil {
+		return false
+	}
+
+	_ = conn.Close()
+
+	return true
+}
+
+// requireDialable waits for addr to accept connections, failing the
+// test if it never does.
+func requireDialable(t *testing.T, addr string) {
+	t.Helper()
+
+	deadline := time.Now().Add(listenReadyTimeout)
+	for time.Now().Before(deadline) {
+		if dialable(t.Context(), addr) {
+			return
+		}
+
+		time.Sleep(listenPollInterval)
+	}
+
+	t.Fatalf("nothing accepted connections on %s", addr)
+}
+
+// TestListenAddr pins how BindAddress and Port are rendered into the
+// listen address.
+//
+// The defect this covers was a bare fmt.Sprintf(":%d", port), which
+// binds every interface with no way to say otherwise. The IPv6 rows
+// are here because an unbracketed IPv6 host would produce an address
+// net.Listen rejects, turning a valid configuration into a startup
+// failure.
+func TestListenAddr(t *testing.T) {
+	t.Parallel()
+
+	tests := []struct {
+		name        string
+		bindAddress string
+		port        int
+		expected    string
+	}{
+		{
+			name:        "loopback default",
+			bindAddress: loopbackV4,
+			port:        8080,
+			expected:    "127.0.0.1:8080",
+		},
+		{
+			name:        "ipv4 wildcard",
+			bindAddress: wildcardV4,
+			port:        8080,
+			expected:    "0.0.0.0:8080",
+		},
+		{
+			name:        "ipv6 wildcard is bracketed",
+			bindAddress: "::",
+			port:        8080,
+			expected:    "[::]:8080",
+		},
+		{
+			name:        "ipv6 literal is bracketed",
+			bindAddress: "2001:db8::5",
+			port:        9001,
+			expected:    "[2001:db8::5]:9001",
+		},
+	}
+
+	for _, tt := range tests {
+		t.Run(tt.name, func(t *testing.T) {
+			t.Parallel()
+
+			assert.Equal(t, tt.expected, server.ListenAddrForTest(
+				&config.Config{
+					BindAddress: tt.bindAddress,
+					Port:        tt.port,
+				},
+			))
+		})
+	}
+}
+
+// TestBindAddress_LoopbackIsNotOnOtherAddresses proves the fix end to
+// end: with BIND_ADDRESS at its loopback default, the cleartext
+// listener answers on loopback and has not claimed any other address
+// of this host.
+//
+// The second address is proven free by binding it on the same port
+// while the server runs. That is the assertion that fails against the
+// old wildcard bind — a wildcard listener owns the port on every
+// address, so this bind would return EADDRINUSE. Dialling from
+// another machine is what the operator cares about, and this is the
+// in-process form of it: the socket the remote host would connect to
+// does not exist.
+func TestBindAddress_LoopbackIsNotOnOtherAddresses(t *testing.T) {
+	t.Parallel()
+
+	other := otherLocalAddr(t)
+	port := startBoundServer(t, loopbackV4)
+
+	// Positive control: the service really is up and serving.
+	requireDialable(t, net.JoinHostPort(loopbackV4, strconv.Itoa(port)))
+
+	var listenCfg net.ListenConfig
+
+	l, err := listenCfg.Listen(
+		t.Context(), "tcp",
+		net.JoinHostPort(other, strconv.Itoa(port)),
+	)
+	require.NoError(
+		t, err,
+		"port %d on %s is taken while bound to %s: the listener "+
+			"claimed more than its configured address",
+		port, other, loopbackV4,
+	)
+
+	require.NoError(t, l.Close())
+}
+
+// TestBindAddress_WildcardReachesOtherAddresses is the counterpart:
+// the value a container deployment sets does reach the addresses the
+// default withholds. Without this, a loopback-only bind would pass
+// the test above by never listening at all.
+func TestBindAddress_WildcardReachesOtherAddresses(t *testing.T) {
+	t.Parallel()
+
+	other := otherLocalAddr(t)
+	port := startBoundServer(t, wildcardV4)
+
+	requireDialable(t, net.JoinHostPort(other, strconv.Itoa(port)))
+}
+
+// TestBindAddress_ServesRequestsOnConfiguredAddress proves the bound
+// listener serves the application rather than merely accepting TCP,
+// so a bind address that is honoured cannot be mistaken for one that
+// is honoured and broken.
+func TestBindAddress_ServesRequestsOnConfiguredAddress(t *testing.T) {
+	t.Parallel()
+
+	port := startBoundServer(t, loopbackV4)
+	addr := net.JoinHostPort(loopbackV4, strconv.Itoa(port))
+	requireDialable(t, addr)
+
+	req, err := http.NewRequestWithContext(
+		t.Context(), http.MethodGet,
+		"http://"+addr+"/.well-known/healthcheck", nil,
+	)
+	require.NoError(t, err)
+
+	client := &http.Client{Timeout: dialTimeout}
+
+	resp, err := client.Do(req)
+	require.NoError(t, err)
+
+	defer func() { _ = resp.Body.Close() }()
+
+	assert.Equal(t, http.StatusOK, resp.StatusCode)
+}
+
+// TestBindAddress_UnavailableAddressShutsDownTheApp covers the half
+// of the fail-loud rule that configuration parsing cannot reach. A
+// syntactically valid address that is not assigned to this host
+// parses fine and fails at bind time, after fx has already reported
+// RUNNING. It must end the process non-zero rather than leave it
+// alive with nothing listening.
+func TestBindAddress_UnavailableAddressShutsDownTheApp(t *testing.T) {
+	t.Parallel()
+
+	env := newTestEnv(t)
+	env.cfg.BindAddress = unavailableAddr
+	env.cfg.Port = freePort(t)
+
+	requireListenFailureExit(t, env)
+}

internal/server/early_shutdown_test.go

@@ -0,0 +1,91 @@
+package server_test
+
+import (
+	"context"
+	"testing"
+
+	"github.com/stretchr/testify/require"
+	"go.uber.org/fx"
+	"sneak.berlin/go/webhooker/internal/globals"
+	"sneak.berlin/go/webhooker/internal/server"
+)
+
+// earlyStopIterations is how many start/stop cycles the race test
+// runs. The window it aims at is the gap between the OnStart hook
+// returning and the serving goroutine reaching its first field
+// access, which is microseconds wide. The race detector reports an
+// unsynchronised pair whenever it observes one, but it has to observe
+// one, so a single cycle can miss purely on scheduling. Repetition
+// makes the observation reliable; the collaborators are built once,
+// so the cycles themselves are cheap.
+const earlyStopIterations = 25
+
+// TestEarlyShutdown_NoPanicAndNoRace stops the application
+// immediately after starting it, before the serving goroutine has
+// necessarily run at all.
+//
+// Two defects live in that window. The OnStart hook returns as soon
+// as it has spawned the serving goroutine, so fx runs the stop
+// sequence against a Server whose serving goroutine may not have
+// executed a single line. cleanShutdown called Shutdown on an
+// httpServer that goroutine was supposed to assign, which was a nil
+// dereference on an early SIGTERM; and it read httpServer and
+// sentryEnabled with nothing ordering those reads against the
+// goroutine's writes, which is a data race that only surfaces once
+// something both starts and stops the server. Nothing did before this
+// test: the listen-failure test never binds, and the router tests
+// bypass the lifecycle entirely.
+//
+// httpServer is now built in New, on the constructing goroutine, so
+// it is written before any hook exists and can never be nil.
+// sentryEnabled is atomic. This test is what catches either one
+// coming back — under -race, which is how the suite runs.
+func TestEarlyShutdown_NoPanicAndNoRace(t *testing.T) {
+	t.Parallel()
+
+	// Built once: the collaborators are not what is under test, and
+	// standing up a database per iteration would make repetition too
+	// expensive to be worth having.
+	env := newTestEnv(t)
+	env.cfg.BindAddress = loopbackV4
+
+	for range earlyStopIterations {
+		requireStartStopIsClean(t, env)
+	}
+}
+
+// requireStartStopIsClean runs one start/stop cycle with no wait in
+// between, failing the test if either half errors.
+//
+// Each cycle gets a fresh fx app, so the Server under test is
+// constructed anew every time — that construction is where the
+// httpServer write now happens, and reusing one Server would test it
+// only once.
+func requireStartStopIsClean(t *testing.T, env *testEnv) {
+	t.Helper()
+
+	env.cfg.Port = freePort(t)
+
+	app := fx.New(
+		fx.NopLogger,
+		fx.Supply(env.log, env.cfg, env.mw, env.hnd),
+		fx.Provide(globals.New, server.New),
+		fx.Invoke(func(*server.Server) {}),
+	)
+
+	startCtx, cancelStart := context.WithTimeout(
+		context.Background(), lifecycleTimeout,
+	)
+	defer cancelStart()
+
+	require.NoError(t, app.Start(startCtx))
+
+	// No sleep and no readiness wait: stopping while the serving
+	// goroutine is still in flight is the whole point.
+	stopCtx, cancelStop := context.WithTimeout(
+		context.Background(), lifecycleTimeout,
+	)
+	defer cancelStop()
+
+	require.NoError(t, app.Stop(stopCtx))
+}

internal/server/export_test.go

@@ -55,6 +55,16 @@ func NewRouterForTest(
 	return s.router
 }
 
+// ListenAddrForTest exposes the address the HTTP listener binds for
+// a given Config, so the rendering of host and port — IPv6
+// bracketing above all — can be pinned without standing up a
+// listener.
+func ListenAddrForTest(cfg *config.Config) string {
+	s := &Server{params: ServerParams{Config: cfg}}
+
+	return s.listenAddr()
+}
+
 // ProbePattern is the route NewRouterWithProbeForTest adds to the
 // production route tree.
 const ProbePattern = "/probe"
@@ -80,12 +90,12 @@ func NewRouterWithProbeForTest(
 	probe http.HandlerFunc,
 ) http.Handler {
 	s := &Server{
-		log:           log,
+		log:    log,
-		mw:            mw,
+		mw:     mw,
-		h:             h,
+		h:      h,
-		params:        ServerParams{Config: cfg},
+		params: ServerParams{Config: cfg},
-		sentryEnabled: sentryEnabled,
 	}
+	s.sentryEnabled.Store(sentryEnabled)
 	s.SetupRoutes()
 	s.router.Handle(ProbePattern, probe)
 

internal/server/http.go

@@ -2,8 +2,9 @@ package server
 
 import (
 	"errors"
-	"fmt"
+	"net"
 	"net/http"
+	"strconv"
 	"time"
 )
 
@@ -24,26 +25,52 @@ const (
 	httpMaxHeaderBytes = 1 << 20
 )
 
-func (s *Server) serveUntilShutdown() {
+// listenAddr renders the address the HTTP listener binds.
-	listenAddr := fmt.Sprintf(":%d", s.params.Config.Port)
+//
-	s.httpServer = &http.Server{
+// The host half is always present: an empty host would be the
-		Addr:           listenAddr,
+// wildcard, and the whole point of BIND_ADDRESS is that binding every
+// interface is a choice the operator makes rather than one the
+// process makes for them. Config guarantees a literal, so
+// JoinHostPort's bracketing is enough to make IPv6 well formed.
+func (s *Server) listenAddr() string {
+	return net.JoinHostPort(
+		s.params.Config.BindAddress,
+		strconv.Itoa(s.params.Config.Port),
+	)
+}
+
+// newHTTPServer builds the HTTP server for this Server's
+// configuration.
+//
+// It is called from New, on the constructing goroutine, rather than
+// from the serving goroutine that used to assign s.httpServer
+// directly. Two goroutines reach that field — the serving goroutine
+// and the fx stop hook, which calls Shutdown on it — with nothing
+// ordering them. Constructing it during New puts the write before
+// every hook fx will later run, which both removes the race and rules
+// out the nil dereference a stop that arrived before the serving
+// goroutine had run would have caused.
+func (s *Server) newHTTPServer() *http.Server {
+	return &http.Server{
+		Addr:           s.listenAddr(),
 		ReadTimeout:    httpReadTimeout,
 		WriteTimeout:   httpWriteTimeout,
 		MaxHeaderBytes: httpMaxHeaderBytes,
 		Handler:        s,
 	}
+}
 
+func (s *Server) serveUntilShutdown() {
 	// add routes
 	// this does any necessary setup in each handler
 	s.SetupRoutes()
 
-	s.log.Info("http begin listen", "listenaddr", listenAddr)
+	s.log.Info("http begin listen", "listenaddr", s.httpServer.Addr)
 
 	err := s.httpServer.ListenAndServe()
 	if err != nil && !errors.Is(err, http.ErrServerClosed) {
 		s.log.Error("listen error", "error", err)
-		s.shutdownOnListenFailure()
+		s.shutdownWithFailure()
 	}
 }
 

internal/server/listen_failure_test.go

@@ -36,9 +36,9 @@ const lifecycleTimeout = 15 * time.Second
 //
 // The port is occupied by a listener this test holds open, on a
 // kernel-chosen port, so the failure is the real EADDRINUSE the
-// operator hits when a second instance starts. Loopback is enough to
+// operator hits when a second instance starts. The server is pointed
-// collide with the server's wildcard bind: a listening socket on a
+// at the same loopback address, so the collision is a direct one on
-// specific address blocks the wildcard from claiming the same port.
+// the exact address it asks the kernel for.
 func TestListenFailure_ShutsDownTheApp(t *testing.T) {
 	t.Parallel()
 
@@ -55,11 +55,27 @@ func TestListenFailure_ShutsDownTheApp(t *testing.T) {
 	require.True(t, ok, "listener is not TCP")
 
 	// The collaborators come from the wired graph rather than stubs,
-	// so the Server under test is the one that ships. Only the port
+	// so the Server under test is the one that ships. Only the
-	// is test-specific.
+	// listen address is test-specific.
 	env := newTestEnv(t)
+	env.cfg.BindAddress = loopbackV4
 	env.cfg.Port = addr.Port
 
+	requireListenFailureExit(t, env)
+}
+
+// requireListenFailureExit starts the wired app over env and asserts
+// that it gives up on its own with the listen-failure status, then
+// completes its stop sequence.
+//
+// Two different listen failures share it — a port already in use and
+// an address that is not on this host — because what has to hold for
+// both is the same: the failure is discovered after fx has already
+// reported RUNNING, so the only thing that can turn it into a visible
+// exit is the shutdown path under test.
+func requireListenFailureExit(t *testing.T, env *testEnv) {
+	t.Helper()
+
 	app := fx.New(
 		fx.NopLogger,
 		fx.Supply(env.log, env.cfg, env.mw, env.hnd),
@@ -77,7 +93,7 @@ func TestListenFailure_ShutsDownTheApp(t *testing.T) {
 	select {
 	case sig := <-app.Wait():
 		require.Equal(
-			t, server.ListenFailureExitCode, sig.ExitCode,
+			t, server.StartupFailureExitCode, sig.ExitCode,
 			"listen failure must exit non-zero",
 		)
 	case <-time.After(listenFailureDeadline):

internal/server/routes.go

@@ -81,7 +81,7 @@ func (s *Server) setupGlobalMiddleware() {
 	// Sentry error reporting (if SENTRY_DSN is set). Repanic is
 	// true so panics still bubble up to the Recoverer middleware
 	// registered immediately above.
-	if s.sentryEnabled {
+	if s.sentryEnabled.Load() {
 		sentryHandler := sentryhttp.New(sentryhttp.Options{
 			Repanic: true,
 		})
@@ -237,10 +237,6 @@ func (s *Server) setupSourceRoutes() {
 			"/entrypoints/{entrypointID}/toggle",
 			s.h.HandleEntrypointToggle(),
 		)
-		r.Post(
-			"/entrypoints/{entrypointID}/secret",
-			s.h.HandleEntrypointSecret(),
-		)
 		r.Post("/targets", s.h.HandleTargetCreate())
 		// The edit form is the one page that renders a target's
 		// destination URL and header values in full; see

internal/server/sentry.go

@@ -147,10 +147,13 @@ func sentryRoutePattern(hint *sentry.EventHint) string {
 //
 // The scheme is load-bearing and is kept: the SDK derives it from
 // r.TLS != nil || r.Header.Get("X-Forwarded-Proto") == "https"
-// (interfaces.go:180), byte for byte the predicate
+// (interfaces.go:180), which is the reason dropping X-Forwarded-Proto
-// internal/middleware/csrf.go uses, so it is the CSRF TLS decision and
+// from the header allowlist costs nothing. That predicate is the SDK's
-// the reason dropping X-Forwarded-Proto from the header allowlist
+// own and is stricter than reqtls.IsTLS, which this service now uses
-// costs nothing. The host is parsed.Host of the SDK's
+// everywhere it decides transport: the SDK reports "http" for the
+// "HTTPS" and "https, http" spellings reqtls accepts. Only a reported
+// scheme is affected, no decision is, so it is left to the SDK rather
+// than reimplemented. The host is parsed.Host of the SDK's
 // scheme://r.Host/path, so it is whatever the client's Host header
 // carried: this service validates no hostname. It is kept because that
 // same header is on the allowlist, so scrubbing it here would withhold

internal/server/sentry_failure_test.go

@@ -0,0 +1,99 @@
+package server_test
+
+import (
+	"context"
+	"net"
+	"strconv"
+	"testing"
+	"time"
+
+	"github.com/stretchr/testify/require"
+	"go.uber.org/fx"
+	"sneak.berlin/go/webhooker/internal/config"
+	"sneak.berlin/go/webhooker/internal/globals"
+	"sneak.berlin/go/webhooker/internal/server"
+)
+
+// TestSentryInitFailure_ShutsDownTheApp pins that error reporting
+// which is configured and cannot be started ends the application
+// instead of serving without it.
+//
+// The measured defect logged `sentry init failure` and kept running,
+// so the deployment served traffic with reporting off while every
+// other signal — SENTRY_DSN still set, the startup summary's own
+// field — said it was on. Nothing later in the process can notice
+// that reports are going nowhere, which is why this exits rather than
+// degrades.
+//
+// The DSN is placed on a hand-built Config, which is the only way to
+// reach this branch at all: loadFromEnv now parses SENTRY_DSN with
+// sentry.NewDsn, the same call sentry.Init makes, so a DSN that
+// survives configuration cannot fail initialisation in the SDK
+// version this pins. The branch stays because that is a property of
+// the SDK's current implementation rather than of its contract.
+func TestSentryInitFailure_ShutsDownTheApp(t *testing.T) {
+	t.Parallel()
+
+	port := freePort(t)
+
+	env := newTestEnvWithConfig(t, &config.Config{
+		DataDir:     t.TempDir(),
+		Environment: config.EnvironmentDev,
+		BindAddress: loopbackV4,
+		Port:        port,
+		SentryDSN:   "not-a-dsn",
+	})
+
+	app := fx.New(
+		fx.NopLogger,
+		fx.Supply(env.log, env.cfg, env.mw, env.hnd),
+		fx.Provide(globals.New, server.New),
+		fx.Invoke(func(*server.Server) {}),
+	)
+
+	startCtx, cancelStart := context.WithTimeout(
+		context.Background(), lifecycleTimeout,
+	)
+	defer cancelStart()
+
+	require.NoError(t, app.Start(startCtx))
+
+	select {
+	case sig := <-app.Wait():
+		require.Equal(
+			t, server.StartupFailureExitCode, sig.ExitCode,
+			"a sentry failure must exit non-zero",
+		)
+	case <-time.After(listenFailureDeadline):
+		t.Fatal("a sentry failure left the app running")
+	}
+
+	// The stop sequence still has to complete: the failure must reach
+	// shutdown through fx rather than around it.
+	stopCtx, cancelStop := context.WithTimeout(
+		context.Background(), lifecycleTimeout,
+	)
+	defer cancelStop()
+
+	require.NoError(t, app.Stop(stopCtx))
+
+	// And it must give up before it listens. A process that bound the
+	// port and then exited would have accepted requests it could not
+	// report on, which is the state under test in miniature.
+	requireBindable(t, port)
+}
+
+// requireBindable asserts that the port is free, which it is only if
+// the server under test never claimed it.
+func requireBindable(t *testing.T, port int) {
+	t.Helper()
+
+	var listenCfg net.ListenConfig
+
+	listener, err := listenCfg.Listen(
+		t.Context(), "tcp",
+		net.JoinHostPort(loopbackV4, strconv.Itoa(port)),
+	)
+	require.NoError(t, err, "the server bound a port it then gave up")
+	require.NoError(t, listener.Close())
+}

internal/server/server.go

@@ -9,6 +9,7 @@ import (
 	"net/http"
 	"os"
 	"os/signal"
+	"sync/atomic"
 	"syscall"
 	"time"
 
@@ -50,12 +51,13 @@ const (
 	minSentryFlush = 250 * time.Millisecond
 )
 
-// ListenFailureExitCode is the status the process exits with when the
+// StartupFailureExitCode is the status the process exits with when
-// HTTP listener cannot be established, or dies for a reason other
+// the serving goroutine gives up: the HTTP listener cannot be
-// than a requested shutdown. It must stay non-zero: systemd
+// established or dies for a reason other than a requested shutdown, or
-// `Restart=on-failure` and Docker's restart policies key off it, and a
+// error reporting is configured and cannot be started. It must stay
-// zero exit would read as a deliberate stop.
+// non-zero: systemd `Restart=on-failure` and Docker's restart policies
-const ListenFailureExitCode = 1
+// key off it, and a zero exit would read as a deliberate stop.
+const StartupFailureExitCode = 1
 
 // SentryFlushBudget reports how long the Sentry flush may run when
 // remaining is the time left on the fx stop context after the HTTP
@@ -88,8 +90,15 @@ type ServerParams struct {
 // Server is the main HTTP server that wires up routes and manages
 // graceful shutdown.
 type Server struct {
-	startupTime   time.Time
+	startupTime time.Time
-	sentryEnabled bool
+
+	// sentryEnabled is written by the serving goroutine, in
+	// enableSentry, and read by the fx stop hook in cleanShutdown.
+	// Nothing orders those two: the OnStart hook returns as soon as
+	// the goroutine is spawned, so a stop can be running while
+	// enableSentry is still deciding. It is atomic to supply the
+	// edge the goroutines do not.
+	sentryEnabled atomic.Bool
 	log           *slog.Logger
 	cancelFunc    context.CancelFunc
 	httpServer    *http.Server
@@ -107,6 +116,7 @@ func New(lc fx.Lifecycle, params ServerParams) (*Server, error) {
 	s.mw = params.Middleware
 	s.h = params.Handlers
 	s.log = params.Logger.Get()
+	s.httpServer = s.newHTTPServer()
 
 	lc.Append(fx.Hook{
 		OnStart: func(_ context.Context) error {
@@ -126,11 +136,25 @@ func New(lc fx.Lifecycle, params ServerParams) (*Server, error) {
 }
 
 // Run configures Sentry and starts serving HTTP requests.
+//
+// A Sentry failure ends the application instead of listening. It runs
+// before the listener rather than after it so that the process never
+// binds a port it is about to give up.
 func (s *Server) Run() {
 	s.configure()
 
 	// logging before sentry, because sentry logs
-	s.enableSentry()
+	err := s.enableSentry()
+	if err != nil {
+		s.log.Error(
+			"SENTRY_DSN is set but error reporting could not be "+
+				"started; refusing to serve with it off",
+			"error", err,
+		)
+		s.shutdownWithFailure()
+
+		return
+	}
 
 	s.serve()
 }
@@ -141,11 +165,23 @@ func (s *Server) MaintenanceMode() bool {
 	return s.params.Config.MaintenanceMode
 }
 
-func (s *Server) enableSentry() {
+// enableSentry initialises the Sentry SDK when error reporting is
-	s.sentryEnabled = false
+// configured, and reports the failure when it is configured and cannot
+// be initialised. A DSN that is not set is not a failure: reporting
+// stays off and the server starts normally.
+//
+// There is no fallback to running with reporting off. An operator who
+// set SENTRY_DSN asked for failures to be visible, and serving traffic
+// with reporting quietly off is the one state nothing can ever tell
+// them about — the DSN is still set, so every later signal says it is
+// on. Config already refused a DSN the SDK cannot parse, which is what
+// a typo produces, so reaching this branch means the SDK refused
+// something that parsed: not a condition to guess at either.
+func (s *Server) enableSentry() error {
+	s.sentryEnabled.Store(false)
 
-	if s.params.Config.SentryDSN == "" {
+	if !s.params.Config.SentryEnabled() {
-		return
+		return nil
 	}
 
 	err := sentry.Init(sentryClientOptions(
@@ -157,19 +193,19 @@ func (s *Server) enableSentry() {
 		),
 	))
 	if err != nil {
-		s.log.Error("sentry init failure", "error", err)
+		return fmt.Errorf("initialising sentry: %w", err)
-		// Don't use fatal since we still want the service to run
-		return
 	}
 
 	s.log.Info("sentry error reporting activated")
-	s.sentryEnabled = true
+	s.sentryEnabled.Store(true)
+
+	return nil
 }
 
 // serve installs the signal watcher, starts the listener and blocks
 // until the server's context is cancelled. The process exit status is
 // fx's to decide — from a signal, or from the code
-// shutdownOnListenFailure hands the Shutdowner — so this reports
+// shutdownWithFailure hands the Shutdowner — so this reports
 // nothing back to its caller.
 func (s *Server) serve() {
 	ctx, cancelFunc := context.WithCancel(context.Background())
@@ -199,20 +235,24 @@ func (s *Server) serve() {
 	// Do not call cleanShutdown() here to avoid double invocation.
 }
 
-// shutdownOnListenFailure ends the application after the HTTP
+// shutdownWithFailure ends the application non-zero from the serving
-// listener failed. The fx OnStart hook returns as soon as the serving
+// goroutine. It is how anything on that goroutine fails fatally: the
-// goroutine is spawned, so nothing downstream of it ever learns that
+// fx OnStart hook returns as soon as the goroutine is spawned, so
-// the listen failed: fx reports RUNNING and the process sits alive
+// nothing downstream of it ever learns that the goroutine gave up. fx
-// with nothing bound, which is invisible to systemd and Docker
+// reports RUNNING and the process sits alive having done neither what
-// restart policies. Asking the Shutdowner to stop the app with a
+// it was asked nor anything visible instead, which systemd and
-// non-zero code is what turns that into a visible failure.
+// Docker restart policies cannot see. Asking the Shutdowner to stop
+// the app with a non-zero code is what turns that into a visible
+// failure, and it is the whole of "fatal" here — no panic, no
+// os.Exit, and every stop hook still runs.
 //
-// The context cancel that follows only unwinds serve()'s own wait.
+// The context cancel that follows only unwinds serve()'s own wait,
-// The shutdown itself runs through fx's normal stop sequence, so the
+// and is skipped before serve has installed one. The shutdown itself
-// clean-shutdown drain in cleanShutdown is reached unchanged.
+// runs through fx's normal stop sequence, so the clean-shutdown drain
-func (s *Server) shutdownOnListenFailure() {
+// in cleanShutdown is reached unchanged.
+func (s *Server) shutdownWithFailure() {
 	err := s.params.Shutdowner.Shutdown(
-		fx.ExitCode(ListenFailureExitCode),
+		fx.ExitCode(StartupFailureExitCode),
 	)
 	if err != nil {
 		s.log.Error("shutdown request failed", "error", err)
@@ -242,7 +282,7 @@ func (s *Server) cleanShutdown(ctx context.Context) {
 
 	s.cleanupForExit()
 
-	if s.sentryEnabled {
+	if s.sentryEnabled.Load() {
 		s.flushSentry(ctx)
 	}
 }

internal/session/export_test.go

@@ -5,6 +5,6 @@ import "github.com/gorilla/sessions"
 // NewStore exposes the production cookie-store constructor so tests
 // exercise the store the application actually runs with, rather than a
 // lookalike assembled in the test.
-func NewStore(key []byte, secure bool) *sessions.CookieStore {
+func NewStore(key []byte) *sessions.CookieStore {
-	return newStore(key, secure)
+	return newStore(key)
 }

internal/session/session.go

@@ -17,6 +17,7 @@ import (
 	"sneak.berlin/go/webhooker/internal/config"
 	"sneak.berlin/go/webhooker/internal/database"
 	"sneak.berlin/go/webhooker/internal/logger"
+	"sneak.berlin/go/webhooker/internal/reqtls"
 )
 
 const (
@@ -84,10 +85,9 @@ type Params struct {
 
 // Session manages encrypted session storage.
 type Session struct {
-	store  *sessions.CookieStore
+	store *sessions.CookieStore
-	key    []byte // raw 32-byte auth key, also used for CSRF cookie signing
+	key   []byte // raw 32-byte auth key, also used for CSRF cookie signing
-	log    *slog.Logger
+	log   *slog.Logger
-	config *config.Config
 
 	// idleTimeout is the sliding inactivity window. A session that
 	// sees no authenticated request within this window expires,
@@ -104,6 +104,10 @@ type Session struct {
 // cookie. MaxAge is deliberately left at its zero value: for a store
 // it is set through CookieStore.MaxAge (see newStore), and for a
 // single session it is copied from the store's options.
+//
+// Secure is a parameter rather than a constant because it is the one
+// attribute here that is not a policy -- it is a fact about the
+// connection carrying this particular response. See applyTransport.
 func cookieOptions(secure bool) *sessions.Options {
 	return &sessions.Options{
 		Path:     "/",
@@ -121,14 +125,52 @@ func cookieOptions(secure bool) *sessions.Options {
 // Options never touches Codecs -- so a store configured that way still
 // decodes a 30-day-old cookie, leaving the cookie attribute and the
 // codec disagreeing about the same policy. store.MaxAge sets both.
-func newStore(key []byte, secure bool) *sessions.CookieStore {
+//
+// The store's Secure is fixed at true, and is only a template: every
+// write path overwrites it for the request in hand (applyTransport).
+// It is true rather than false so that a write path added later which
+// forgets to call applyTransport fails loudly -- the browser drops the
+// cookie over plaintext HTTP and the developer sees it immediately --
+// instead of silently shipping the authentication credential without
+// Secure, which is the exact failure this store already had once.
+func newStore(key []byte) *sessions.CookieStore {
 	store := sessions.NewCookieStore(key)
-	store.Options = cookieOptions(secure)
+	store.Options = cookieOptions(true)
 	store.MaxAge(secondsPerDay * sessionMaxAgeDays)
 
 	return store
 }
 
+// applyTransport sets the session cookie's Secure attribute from the
+// transport of the request being answered.
+//
+// This is decided per-request, not once at startup. Deciding it at
+// startup from the configured environment is what this replaces, and
+// it got the DEFAULT posture wrong: "dev" is the environment when
+// WEBHOOKER_ENVIRONMENT is unset, so a deployment terminating TLS at a
+// proxy without also setting the environment emitted the
+// authentication cookie with no Secure attribute -- silently, and on
+// the same response as a CSRF cookie that did have one.
+//
+// gorilla/sessions makes this cheap and local: CookieStore.New gives
+// every session its own copy of the store's Options, and
+// CookieStore.Save renders the cookie from that copy rather than from
+// the store. So the flag is set on the one session being saved,
+// without a second store and without reaching across concurrent
+// requests.
+//
+// The flag tracks the transport in BOTH directions rather than being
+// latched on once seen. Secure on a plaintext response is worse than
+// useless: the browser discards such a cookie without any error, so a
+// latched flag would make a plain-HTTP local run impossible to log
+// into. It is also why every write path must call this, including the
+// deletion cookies in Destroy and Regenerate -- a Secure deletion
+// cookie sent over plaintext is dropped too, leaving the session the
+// caller believed it had just revoked.
+func applyTransport(r *http.Request, sess *sessions.Session) {
+	sess.Options.Secure = reqtls.IsTLS(r)
+}
+
 // New creates a new session manager. The cookie store is
 // initialized during the fx OnStart phase after the database is
 // connected, using a session key that is auto-generated and stored
@@ -139,7 +181,6 @@ func New(
 ) (*Session, error) {
 	s := &Session{
 		log:         params.Logger.Get(),
-		config:      params.Config,
 		idleTimeout: params.Config.SessionIdleTimeout,
 		now:         time.Now,
 	}
@@ -172,7 +213,7 @@ func New(
 			}
 
 			s.key = keyBytes
-			s.store = newStore(keyBytes, !params.Config.IsDev())
+			s.store = newStore(keyBytes)
 			s.log.Info("session manager initialized")
 
 			return nil
@@ -196,12 +237,16 @@ func (s *Session) GetKey() []byte {
 	return s.key
 }
 
-// Save saves the session.
+// Save saves the session. Every session-cookie write in the
+// application goes through here or through Regenerate, which is what
+// makes applyTransport a complete answer rather than a best effort.
 func (s *Session) Save(
 	r *http.Request,
 	w http.ResponseWriter,
 	sess *sessions.Session,
 ) error {
+	applyTransport(r, sess)
+
 	return sess.Save(r, w)
 }
 
@@ -340,6 +385,7 @@ func (s *Session) Regenerate(
 	// Destroy the old session
 	oldSess.Options.MaxAge = -1
 	s.ClearUser(oldSess)
+	applyTransport(r, oldSess)
 
 	err := oldSess.Save(r, w)
 	if err != nil {
@@ -368,7 +414,7 @@ func (s *Session) Regenerate(
 	// Apply the standard session options (the destroyed old
 	// session had MaxAge = -1, which store.New might inherit
 	// from the cookie).
-	newSess.Options = cookieOptions(!s.config.IsDev())
+	newSess.Options = cookieOptions(reqtls.IsTLS(r))
 	newSess.Options.MaxAge = secondsPerDay * sessionMaxAgeDays
 
 	return newSess, nil

internal/session/session_test.go

@@ -2,6 +2,7 @@ package session_test
 
 import (
 	"context"
+	"crypto/tls"
 	"log/slog"
 	"net/http"
 	"net/http/httptest"
@@ -73,7 +74,7 @@ func testSessionWithClock(
 	t.Helper()
 
 	key := testKey()
-	store := session.NewStore(key, false)
+	store := session.NewStore(key)
 
 	cfg := &config.Config{
 		Environment:        config.EnvironmentDev,
@@ -880,3 +881,264 @@ func TestDestroy_ThenSave_DeletesCookie(t *testing.T) {
 		"destroyed session cookie should have negative MaxAge",
 	)
 }
+
+// --- Secure Attribute / Transport Tests ---
+
+// transportCase describes one client-facing transport and the Secure
+// attribute the session cookie must carry for it.
+type transportCase struct {
+	name   string
+	tls    bool
+	header string
+	want   bool
+	why    string
+}
+
+// transportCases enumerates the transports the session cookie has to
+// get right. Every https spelling here is one a real proxy emits.
+func transportCases() []transportCase {
+	return []transportCase{
+		{
+			name: "direct TLS",
+			tls:  true,
+			want: true,
+			why:  "this process terminated TLS itself",
+		},
+		{
+			name:   "proxy reports https",
+			header: "https",
+			want:   true,
+			why:    "the ordinary reverse-proxy deployment",
+		},
+		{
+			name:   "proxy reports HTTPS",
+			header: "HTTPS",
+			want:   true,
+			why:    "the header value is a case-insensitive token",
+		},
+		{
+			name:   "appended chain https, http",
+			header: "https, http",
+			want:   true,
+			why:    "the leftmost hop is the browser's connection",
+		},
+		{
+			name:   "appended chain https,https",
+			header: "https,https",
+			want:   true,
+			why:    "two TLS hops, no space after the comma",
+		},
+		{
+			name:   "trailing space",
+			header: "https ",
+			want:   true,
+			why:    "whitespace is not part of the token",
+		},
+		{
+			name:   "proxy reports http",
+			header: "http",
+			want:   false,
+			why: "the negative control: Secure over plaintext is " +
+				"dropped by the browser without a word",
+		},
+		{
+			name: "plaintext, no proxy",
+			want: false,
+			why:  "a plain local run must stay loggable-in",
+		},
+	}
+}
+
+// transportRequest builds a request carrying the case's transport.
+func (tc transportCase) request(t *testing.T) *http.Request {
+	t.Helper()
+
+	r := httptest.NewRequestWithContext(
+		context.Background(), http.MethodGet,
+		"http://example.com/", nil,
+	)
+
+	if tc.tls {
+		r.TLS = &tls.ConnectionState{}
+	}
+
+	if tc.header != "" {
+		r.Header.Set("X-Forwarded-Proto", tc.header)
+	}
+
+	return r
+}
+
+// sessionCookieFrom returns the session cookie from a response, or
+// fails the test if there is none.
+func sessionCookieFrom(
+	t *testing.T,
+	w *httptest.ResponseRecorder,
+) *http.Cookie {
+	t.Helper()
+
+	for _, c := range w.Result().Cookies() {
+		if c.Name == session.SessionName {
+			return c
+		}
+	}
+
+	require.FailNow(t, "no session cookie in response")
+
+	return nil
+}
+
+// TestSave_SecureFollowsRequestTransport is the regression test for
+// the defect this replaces: Secure was fixed at startup from the
+// configured environment, and "dev" is the environment when
+// WEBHOOKER_ENVIRONMENT is unset. A deployment behind a TLS proxy in
+// that DEFAULT posture shipped the authentication cookie with no
+// Secure attribute and said nothing about it.
+//
+// testSession builds its config with EnvironmentDev precisely so that
+// the https cases below fail against the old startup-fixed behaviour.
+func TestSave_SecureFollowsRequestTransport(t *testing.T) {
+	t.Parallel()
+
+	for _, tc := range transportCases() {
+		t.Run(tc.name, func(t *testing.T) {
+			t.Parallel()
+
+			s := testSession(t)
+			r := tc.request(t)
+			w := httptest.NewRecorder()
+
+			sess, err := s.Get(r)
+			require.NoError(t, err)
+
+			s.SetUser(sess, "user-1", "alice")
+			require.NoError(t, s.Save(r, w, sess))
+
+			assert.Equal(
+				t, tc.want, sessionCookieFrom(t, w).Secure,
+				"session cookie Secure for %q: %s",
+				tc.name, tc.why,
+			)
+		})
+	}
+}
+
+// TestSave_SecureTracksTransportBothWays pins that the flag is not
+// latched. One store serves every request, so a Secure cookie set for
+// a proxied request must not leak into a later plaintext response --
+// the browser would silently discard that one, and a local run would
+// become impossible to log into.
+func TestSave_SecureTracksTransportBothWays(t *testing.T) {
+	t.Parallel()
+
+	s := testSession(t)
+
+	secureReq := httptest.NewRequestWithContext(
+		context.Background(), http.MethodGet,
+		"http://example.com/", nil,
+	)
+	secureReq.Header.Set("X-Forwarded-Proto", "https")
+
+	secureW := httptest.NewRecorder()
+
+	secureSess, err := s.Get(secureReq)
+	require.NoError(t, err)
+	require.NoError(t, s.Save(secureReq, secureW, secureSess))
+	require.True(
+		t, sessionCookieFrom(t, secureW).Secure,
+		"proxied request should produce a Secure cookie",
+	)
+
+	plainReq := httptest.NewRequestWithContext(
+		context.Background(), http.MethodGet,
+		"http://example.com/", nil,
+	)
+	plainW := httptest.NewRecorder()
+
+	plainSess, err := s.Get(plainReq)
+	require.NoError(t, err)
+	require.NoError(t, s.Save(plainReq, plainW, plainSess))
+
+	assert.False(
+		t, sessionCookieFrom(t, plainW).Secure,
+		"a later plaintext request must not inherit Secure from "+
+			"the earlier proxied one",
+	)
+}
+
+// TestDestroy_DeletionCookieFollowsTransport covers the trap in the
+// deletion path. The store's template Secure is true, so a logout over
+// plaintext that failed to track the transport would emit a Secure
+// deletion cookie -- which the browser drops, leaving the session the
+// user just tried to end still sitting in the jar.
+func TestDestroy_DeletionCookieFollowsTransport(t *testing.T) {
+	t.Parallel()
+
+	s := testSession(t)
+
+	r := httptest.NewRequestWithContext(
+		context.Background(), http.MethodGet,
+		"http://example.com/", nil,
+	)
+	w := httptest.NewRecorder()
+
+	sess, err := s.Get(r)
+	require.NoError(t, err)
+
+	s.Destroy(sess)
+	require.NoError(t, s.Save(r, w, sess))
+
+	cookie := sessionCookieFrom(t, w)
+
+	require.Negative(
+		t, cookie.MaxAge,
+		"Destroy then Save should emit a deletion cookie",
+	)
+	assert.False(
+		t, cookie.Secure,
+		"a deletion cookie sent over plaintext must not be Secure, "+
+			"or the browser discards it and the session survives",
+	)
+}
+
+// TestRegenerate_BothCookiesFollowTransport covers the login path.
+// Regenerate writes two cookies -- a deletion for the pre-login
+// session and the new authenticated one -- and both have to match the
+// transport or one of them is silently dropped.
+func TestRegenerate_BothCookiesFollowTransport(t *testing.T) {
+	t.Parallel()
+
+	for _, tc := range transportCases() {
+		t.Run(tc.name, func(t *testing.T) {
+			t.Parallel()
+
+			s := testSession(t)
+			r := tc.request(t)
+			w := httptest.NewRecorder()
+
+			oldSess, err := s.Get(r)
+			require.NoError(t, err)
+
+			newSess, err := s.Regenerate(r, w, oldSess)
+			require.NoError(t, err)
+
+			s.SetUser(newSess, "user-1", "alice")
+			require.NoError(t, s.Save(r, w, newSess))
+
+			cookies := w.Result().Cookies()
+			require.Len(
+				t, cookies, 2,
+				"Regenerate then Save writes a deletion cookie "+
+					"and a replacement",
+			)
+
+			for _, c := range cookies {
+				assert.Equal(
+					t, tc.want, c.Secure,
+					"cookie %d Secure for %q: %s",
+					c.MaxAge, tc.name, tc.why,
+				)
+			}
+		})
+	}
+}

internal/session/testing.go

@@ -32,7 +32,6 @@ func NewForTest(
 	return &Session{
 		store:       store,
 		key:         key,
-		config:      cfg,
 		log:         log,
 		idleTimeout: cfg.SessionIdleTimeout,
 		now:         now,

internal/signature/signature.go

@@ -1,283 +0,0 @@
-// Package signature verifies that an inbound webhook request really
-// came from the sender an entrypoint was configured for.
-//
-// Verification is optional and per entrypoint. An entrypoint with no
-// scheme configured is not verified at all, which is what every
-// entrypoint was before this package existed. An entrypoint whose
-// configuration is present but incoherent is failed closed, never
-// treated as unverified: the whole point of the feature is that
-// turning it on cannot silently turn itself back off.
-package signature
-
-import (
-	"crypto/hmac"
-	"crypto/sha256"
-	"encoding/hex"
-	"errors"
-	"fmt"
-	"net/http"
-	"strings"
-
-	"sneak.berlin/go/webhooker/internal/database"
-)
-
-// Header names each supported scheme reads its signature from.
-const (
-	// HeaderGitHub is GitHub's HMAC-SHA256 signature header. GitHub
-	// also sends the older SHA-1 X-Hub-Signature; it is not accepted.
-	HeaderGitHub = "X-Hub-Signature-256"
-
-	// HeaderGitLab is GitLab's plain shared-token header.
-	HeaderGitLab = "X-Gitlab-Token"
-)
-
-// githubPrefix is the algorithm label GitHub puts in front of the hex
-// digest. It is required, not optional: accepting a bare digest too
-// would mean accepting a spelling no supported sender produces.
-const githubPrefix = "sha256="
-
-// ErrConfig marks a failure caused by the entrypoint's stored
-// configuration rather than by the request. A caller must fail these
-// closed — refuse the request — because the alternative is an
-// entrypoint the operator believes is verified silently accepting
-// anything.
-var ErrConfig = errors.New("entrypoint signature configuration invalid")
-
-// ErrUnauthorized marks a request that failed verification. A caller
-// answers these 401.
-var ErrUnauthorized = errors.New("inbound signature verification failed")
-
-// Configuration failures. None of these carry any part of the secret.
-var (
-	errSchemeUnknown = fmt.Errorf(
-		"%w: unsupported scheme", ErrConfig,
-	)
-	errSecretMissing = fmt.Errorf(
-		"%w: scheme set with no secret", ErrConfig,
-	)
-	errSchemeMissing = fmt.Errorf(
-		"%w: secret set with no scheme", ErrConfig,
-	)
-)
-
-// Request failures. These are logged, so none of them carries the
-// value the client sent: under the GitLab scheme that value is a
-// guess at the token, and under either scheme a misconfigured sender
-// could be presenting the real one.
-var (
-	errHeaderMissing = fmt.Errorf(
-		"%w: signature header absent", ErrUnauthorized,
-	)
-	errHeaderMalformed = fmt.Errorf(
-		"%w: signature header malformed", ErrUnauthorized,
-	)
-	errSignatureMismatch = fmt.Errorf(
-		"%w: signature does not match", ErrUnauthorized,
-	)
-)
-
-// SchemeInfo describes one supported scheme for the UI.
-type SchemeInfo struct {
-	Scheme database.SignatureScheme
-	Label  string
-	Header string
-
-	// HeaderIsDigest reports that Header carries a value derived from
-	// the request rather than the shared secret itself, and so may be
-	// kept when the request is stored and forwarded.
-	//
-	// The polarity is deliberate: false — the zero value — means the
-	// header is the credential and must be stripped. A scheme added
-	// later is therefore stripped unless whoever adds it positively
-	// declares the header safe to keep.
-	HeaderIsDigest bool
-}
-
-// Schemes returns the supported schemes in the order the UI offers
-// them. It returns a fresh slice per call so no caller can edit the
-// set out from under another.
-func Schemes() []SchemeInfo {
-	return []SchemeInfo{
-		{
-			Scheme: database.SignatureSchemeGitHub,
-			Label:  "GitHub",
-			Header: HeaderGitHub,
-			// An HMAC over the body, not the key. Keeping it lets an
-			// operator see what the sender sent.
-			HeaderIsDigest: true,
-		},
-		{
-			Scheme: database.SignatureSchemeGitLab,
-			Label:  "GitLab",
-			Header: HeaderGitLab,
-			// X-Gitlab-Token is the shared secret in plaintext.
-			HeaderIsDigest: false,
-		},
-	}
-}
-
-// Info returns the description of a supported scheme. It reports
-// false for the empty scheme and for anything unrecognised, which is
-// what a row hand-edited in the database could hold.
-func Info(scheme database.SignatureScheme) (SchemeInfo, bool) {
-	for _, s := range Schemes() {
-		if s.Scheme == scheme {
-			return s, true
-		}
-	}
-
-	return SchemeInfo{}, false
-}
-
-// Supported reports whether a scheme may be stored on an entrypoint.
-// The empty scheme is supported: it means no verification.
-func Supported(scheme database.SignatureScheme) bool {
-	if scheme == database.SignatureSchemeNone {
-		return true
-	}
-
-	_, ok := Info(scheme)
-
-	return ok
-}
-
-// SanitizeHeaders returns a copy of an accepted request's headers
-// with the entrypoint's credential removed.
-//
-// Under a scheme whose header is the shared secret itself — GitLab's
-// X-Gitlab-Token — every downstream use of the inbound headers is a
-// disclosure of the credential: they are persisted verbatim in the
-// per-webhook event store and forwarded to every delivery target, so
-// a target operator or anyone who reads the event database could
-// forge signed requests to the very entrypoint the secret protects.
-// Stripping happens here, once, above the first write, rather than
-// at each egress, so a new consumer of Event.Headers cannot reopen
-// the leak by forgetting to filter.
-//
-// header is never modified; the caller's request keeps its headers
-// intact for anything that still needs the original.
-//
-// An entrypoint with no scheme, or one whose stored scheme this
-// build does not know, is returned unchanged: there is no configured
-// credential to remove, and the unknown case is refused by Verify
-// before a request reaches storage.
-func SanitizeHeaders(
-	entrypoint *database.Entrypoint,
-	header http.Header,
-) http.Header {
-	clone := header.Clone()
-	if clone == nil {
-		return header
-	}
-
-	info, ok := Info(entrypoint.SignatureScheme)
-	if !ok || info.HeaderIsDigest {
-		return clone
-	}
-
-	clone.Del(info.Header)
-
-	return clone
-}
-
-// Verify checks an inbound request against an entrypoint's
-// configuration and returns nil when the request may be accepted.
-//
-// body must be the raw bytes exactly as received, before any parsing
-// or normalisation: the sender computed its digest over those bytes,
-// so anything that re-encodes them produces a different digest and a
-// spurious rejection. The caller is also responsible for bounding
-// that read; this package hashes what it is handed.
-//
-// Every non-nil error is either ErrConfig or ErrUnauthorized, so a
-// caller can tell "the server is misconfigured" from "the client did
-// not authenticate" with errors.Is.
-func Verify(
-	entrypoint *database.Entrypoint,
-	header http.Header,
-	body []byte,
-) error {
-	scheme := entrypoint.SignatureScheme
-	secret := entrypoint.SignatureSecret
-
-	if scheme == database.SignatureSchemeNone {
-		// A secret with no scheme names no header and no algorithm,
-		// so there is nothing to check it with. Accepting the request
-		// would make a half-applied configuration indistinguishable
-		// from no configuration at all.
-		if secret != "" {
-			return errSchemeMissing
-		}
-
-		return nil
-	}
-
-	if secret == "" {
-		return errSecretMissing
-	}
-
-	switch scheme {
-	case database.SignatureSchemeGitHub:
-		return verifyGitHub(secret, header.Get(HeaderGitHub), body)
-	case database.SignatureSchemeGitLab:
-		return verifyGitLab(secret, header.Get(HeaderGitLab))
-	case database.SignatureSchemeNone:
-		// Handled above; restated so the switch stays exhaustive and
-		// adding a scheme has to be decided here.
-		return nil
-	default:
-		return errSchemeUnknown
-	}
-}
-
-// verifyGitHub checks a GitHub-style X-Hub-Signature-256: the string
-// "sha256=" followed by the hex HMAC-SHA256 of the raw body under the
-// shared secret.
-func verifyGitHub(secret, provided string, body []byte) error {
-	if provided == "" {
-		return errHeaderMissing
-	}
-
-	encoded, ok := strings.CutPrefix(provided, githubPrefix)
-	if !ok {
-		return errHeaderMalformed
-	}
-
-	got, err := hex.DecodeString(encoded)
-	if err != nil {
-		return errHeaderMalformed
-	}
-
-	mac := hmac.New(sha256.New, []byte(secret))
-
-	// hash.Hash.Write is documented never to return an error.
-	_, _ = mac.Write(body)
-
-	// hmac.Equal, never ==: string comparison stops at the first
-	// differing byte, which tells a client how much of a forged
-	// digest it got right and turns forgery into a per-byte search.
-	if !hmac.Equal(mac.Sum(nil), got) {
-		return errSignatureMismatch
-	}
-
-	return nil
-}
-
-// verifyGitLab checks a GitLab-style X-Gitlab-Token, which is the
-// shared secret itself rather than a digest over the body.
-//
-// The comparison is constant time in the same way as the HMAC one.
-// hmac.Equal returns early for unequal lengths, so the length of the
-// token is not hidden; its contents are, and length alone does not
-// let a client search for the value.
-func verifyGitLab(secret, provided string) error {
-	if provided == "" {
-		return errHeaderMissing
-	}
-
-	if !hmac.Equal([]byte(provided), []byte(secret)) {
-		return errSignatureMismatch
-	}
-
-	return nil
-}

internal/signature/signature_test.go

@@ -1,340 +0,0 @@
-package signature_test
-
-import (
-	"crypto/hmac"
-	"crypto/sha256"
-	"encoding/hex"
-	"net/http"
-	"testing"
-
-	"github.com/stretchr/testify/assert"
-	"github.com/stretchr/testify/require"
-	"sneak.berlin/go/webhooker/internal/database"
-	"sneak.berlin/go/webhooker/internal/signature"
-)
-
-const (
-	// testSharedKey is the shared secret under test. It is not named
-	// "secret": gosec reads a credential-shaped name bound to a
-	// high-entropy literal as a leaked credential, which is the right
-	// rule and the wrong finding here.
-	testSharedKey = "s3kr1t-shared-value"
-	testBody      = `{"action":"opened","number":1}`
-)
-
-// githubSignature returns the X-Hub-Signature-256 value GitHub would
-// send for testBody signed with secret.
-func githubSignature(secret string) string {
-	mac := hmac.New(sha256.New, []byte(secret))
-	_, _ = mac.Write([]byte(testBody))
-
-	return "sha256=" + hex.EncodeToString(mac.Sum(nil))
-}
-
-// headerWith builds a request header carrying one value.
-func headerWith(name, value string) http.Header {
-	h := http.Header{}
-	if name != "" {
-		h.Set(name, value)
-	}
-
-	return h
-}
-
-// entrypoint builds an entrypoint with a signature configuration.
-func entrypoint(
-	scheme database.SignatureScheme, secret string,
-) *database.Entrypoint {
-	return &database.Entrypoint{
-		SignatureScheme: scheme,
-		SignatureSecret: secret,
-	}
-}
-
-// TestVerifyUnconfiguredAcceptsAnything pins the pass-through case:
-// an entrypoint with no scheme is the entrypoint every deployment
-// already has, and it must keep accepting requests that carry no
-// signature at all.
-func TestVerifyUnconfiguredAcceptsAnything(t *testing.T) {
-	t.Parallel()
-
-	ep := entrypoint(database.SignatureSchemeNone, "")
-
-	require.NoError(
-		t, signature.Verify(ep, http.Header{}, []byte(testBody)),
-	)
-	require.NoError(
-		t,
-		signature.Verify(
-			ep,
-			headerWith(signature.HeaderGitHub, "sha256=deadbeef"),
-			[]byte(testBody),
-		),
-	)
-}
-
-// githubCase is one inbound request against a GitHub-scheme
-// entrypoint.
-type githubCase struct {
-	name   string
-	header string
-	value  string
-	body   string
-	want   error
-}
-
-// githubCases enumerates the shapes a GitHub signature can arrive in.
-func githubCases() []githubCase {
-	valid := githubSignature(testSharedKey)
-
-	return []githubCase{
-		{
-			name:   "valid",
-			header: signature.HeaderGitHub,
-			value:  valid,
-			body:   testBody,
-			want:   nil,
-		},
-		{
-			name:   "absent header",
-			header: "",
-			body:   testBody,
-			want:   signature.ErrUnauthorized,
-		},
-		{
-			name:   "wrong secret",
-			header: signature.HeaderGitHub,
-			value:  githubSignature("not-the-shared-value"),
-			body:   testBody,
-			want:   signature.ErrUnauthorized,
-		},
-		{
-			// The digest is valid for a different body: the check
-			// has to be over the bytes actually received.
-			name:   "body altered in flight",
-			header: signature.HeaderGitHub,
-			value:  valid,
-			body:   testBody + " ",
-			want:   signature.ErrUnauthorized,
-		},
-		{
-			name:   "missing algorithm prefix",
-			header: signature.HeaderGitHub,
-			value:  valid[len("sha256="):],
-			body:   testBody,
-			want:   signature.ErrUnauthorized,
-		},
-		{
-			name:   "not hex",
-			header: signature.HeaderGitHub,
-			value:  "sha256=zzzz",
-			body:   testBody,
-			want:   signature.ErrUnauthorized,
-		},
-		{
-			name:   "empty digest",
-			header: signature.HeaderGitHub,
-			value:  "sha256=",
-			body:   testBody,
-			want:   signature.ErrUnauthorized,
-		},
-		{
-			// GitLab's header does not authenticate a GitHub
-			// entrypoint, even holding the right secret.
-			name:   "wrong header for the scheme",
-			header: signature.HeaderGitLab,
-			value:  testSharedKey,
-			body:   testBody,
-			want:   signature.ErrUnauthorized,
-		},
-	}
-}
-
-func TestVerifyGitHub(t *testing.T) {
-	t.Parallel()
-
-	for _, tc := range githubCases() {
-		t.Run(tc.name, func(t *testing.T) {
-			t.Parallel()
-
-			err := signature.Verify(
-				entrypoint(
-					database.SignatureSchemeGitHub, testSharedKey,
-				),
-				headerWith(tc.header, tc.value),
-				[]byte(tc.body),
-			)
-
-			if tc.want == nil {
-				require.NoError(t, err)
-
-				return
-			}
-
-			require.ErrorIs(t, err, tc.want)
-		})
-	}
-}
-
-func TestVerifyGitLab(t *testing.T) {
-	t.Parallel()
-
-	cases := []struct {
-		name   string
-		header string
-		value  string
-		want   error
-	}{
-		{
-			name:   "valid",
-			header: signature.HeaderGitLab,
-			value:  testSharedKey,
-			want:   nil,
-		},
-		{
-			name:   "absent header",
-			header: "",
-			want:   signature.ErrUnauthorized,
-		},
-		{
-			name:   "wrong token",
-			header: signature.HeaderGitLab,
-			value:  "not-the-shared-value",
-			want:   signature.ErrUnauthorized,
-		},
-		{
-			name:   "token prefix only",
-			header: signature.HeaderGitLab,
-			value:  testSharedKey[:5],
-			want:   signature.ErrUnauthorized,
-		},
-		{
-			name:   "wrong header for the scheme",
-			header: signature.HeaderGitHub,
-			value:  githubSignature(testSharedKey),
-			want:   signature.ErrUnauthorized,
-		},
-	}
-
-	for _, tc := range cases {
-		t.Run(tc.name, func(t *testing.T) {
-			t.Parallel()
-
-			err := signature.Verify(
-				entrypoint(
-					database.SignatureSchemeGitLab, testSharedKey,
-				),
-				headerWith(tc.header, tc.value),
-				[]byte(testBody),
-			)
-
-			if tc.want == nil {
-				require.NoError(t, err)
-
-				return
-			}
-
-			require.ErrorIs(t, err, tc.want)
-		})
-	}
-}
-
-// TestVerifyBrokenConfigurationFailsClosed covers the rows a caller
-// must refuse rather than wave through. Each is a state an operator
-// could only reach outside the UI, and each one would otherwise be
-// indistinguishable from "verification is off".
-func TestVerifyBrokenConfigurationFailsClosed(t *testing.T) {
-	t.Parallel()
-
-	cases := []struct {
-		name   string
-		scheme database.SignatureScheme
-		secret string
-	}{
-		{
-			name:   "unknown scheme",
-			scheme: database.SignatureScheme("stripe"),
-			secret: testSharedKey,
-		},
-		{
-			name:   "scheme without secret",
-			scheme: database.SignatureSchemeGitHub,
-			secret: "",
-		},
-		{
-			name:   "secret without scheme",
-			scheme: database.SignatureSchemeNone,
-			secret: testSharedKey,
-		},
-	}
-
-	for _, tc := range cases {
-		t.Run(tc.name, func(t *testing.T) {
-			t.Parallel()
-
-			err := signature.Verify(
-				entrypoint(tc.scheme, tc.secret),
-				headerWith(
-					signature.HeaderGitHub,
-					githubSignature(testSharedKey),
-				),
-				[]byte(testBody),
-			)
-
-			require.ErrorIs(t, err, signature.ErrConfig)
-			assert.NotErrorIs(t, err, signature.ErrUnauthorized)
-		})
-	}
-}
-
-// TestErrorsCarryNoSecret proves the strings that reach the log hold
-// no part of the shared secret or of what the client presented.
-func TestErrorsCarryNoSecret(t *testing.T) {
-	t.Parallel()
-
-	const presented = "QQPRESENTEDTOKENQQ"
-
-	for _, scheme := range []database.SignatureScheme{
-		database.SignatureSchemeGitHub,
-		database.SignatureSchemeGitLab,
-	} {
-		for _, header := range []string{
-			signature.HeaderGitHub, signature.HeaderGitLab,
-		} {
-			err := signature.Verify(
-				entrypoint(scheme, testSharedKey),
-				headerWith(header, presented),
-				[]byte(testBody),
-			)
-			require.Error(t, err)
-			assert.NotContains(t, err.Error(), testSharedKey)
-			assert.NotContains(t, err.Error(), presented)
-		}
-	}
-}
-
-func TestSchemeMetadata(t *testing.T) {
-	t.Parallel()
-
-	assert.True(t, signature.Supported(database.SignatureSchemeNone))
-	assert.True(t, signature.Supported(database.SignatureSchemeGitHub))
-	assert.True(t, signature.Supported(database.SignatureSchemeGitLab))
-	assert.False(
-		t, signature.Supported(database.SignatureScheme("stripe")),
-	)
-
-	// The empty scheme describes no sender, so it has no info even
-	// though it is a storable value.
-	_, ok := signature.Info(database.SignatureSchemeNone)
-	assert.False(t, ok)
-
-	info, ok := signature.Info(database.SignatureSchemeGitHub)
-	require.True(t, ok)
-	assert.Equal(t, "GitHub", info.Label)
-	assert.Equal(t, signature.HeaderGitHub, info.Header)
-
-	info, ok = signature.Info(database.SignatureSchemeGitLab)
-	require.True(t, ok)
-	assert.Equal(t, "GitLab", info.Label)
-	assert.Equal(t, signature.HeaderGitLab, info.Header)
-}

internal/versionscript/doc.go

@@ -0,0 +1,12 @@
+// Package versionscript holds the tests for script/version and for the
+// build files that consume it. It carries no runtime code: the version
+// string is produced by a shell script at build time and reaches the
+// binary through a linker flag, so nothing in the Go build graph can
+// assert it, but the behaviour still has to be verified by the test
+// suite.
+//
+// The files under test are outside the Go build graph, so `go test`'s
+// result cache serves a stale PASS when only script/version, the
+// Makefile or the Dockerfile changed: run the container build, or
+// GOFLAGS=-count=1, to trust a result here after editing them.
+package versionscript

internal/versionscript/version_script_test.go

@@ -0,0 +1,345 @@
+package versionscript_test
+
+import (
+	"os"
+	"os/exec"
+	"path/filepath"
+	"strings"
+	"testing"
+
+	"github.com/stretchr/testify/require"
+)
+
+const (
+	repoRoot       = "../.."
+	scriptPath     = "../../script/version"
+	makefilePath   = "../../Makefile"
+	dockerfilePath = "../../Dockerfile"
+
+	// unknown is what a tree with no git metadata and no $VERSION must
+	// report: a source tarball has no way to know its version, and the
+	// one thing it must not do is name a tag it may not be at.
+	unknown = "unknown"
+
+	// scriptMode keeps the copied script runnable; dirMode and fileMode
+	// are the ordinary permissions for the throwaway tree around it.
+	scriptMode = 0o755
+	dirMode    = 0o750
+	fileMode   = 0o600
+)
+
+// checkout is a throwaway working tree carrying a copy of the script
+// under test at the same path it lives at in this repository, since the
+// script resolves the checkout root from its own location.
+type checkout struct {
+	dir  string
+	head string
+}
+
+func TestVersion_CleanTagReportsExactlyTheTag(t *testing.T) {
+	t.Parallel()
+
+	c := newCheckout(t)
+	c.git(t, "tag", "v1.2.3")
+
+	require.Equal(t, "v1.2.3", c.version(t))
+}
+
+func TestVersion_CommitAfterTagCarriesDistanceAndSHA(t *testing.T) {
+	t.Parallel()
+
+	c := newCheckout(t)
+	c.git(t, "tag", "v1.2.3")
+	head := c.commit(t, "after the tag")
+
+	got := c.version(t)
+
+	require.NotEqual(t, "v1.2.3", got,
+		"a commit past the tag must not claim to be the tag")
+	require.True(t, strings.HasPrefix(got, "v1.2.3-1-g"),
+		"want describe form v1.2.3-1-g<sha>, got %q", got)
+	require.True(t, strings.HasPrefix(head, strings.TrimPrefix(
+		got, "v1.2.3-1-g")),
+		"%q must carry the abbreviated head SHA of %q", got, head)
+}
+
+func TestVersion_UntaggedHistoryReportsShortSHA(t *testing.T) {
+	t.Parallel()
+
+	c := newCheckout(t)
+
+	got := c.version(t)
+
+	require.NotEmpty(t, got)
+	require.NotEqual(t, unknown, got)
+	require.True(t, strings.HasPrefix(c.head, got),
+		"%q must be an abbreviation of head %q", got, c.head)
+}
+
+func TestVersion_UncommittedChangesAreMarkedDirty(t *testing.T) {
+	t.Parallel()
+
+	c := newCheckout(t)
+	c.git(t, "tag", "v1.2.3")
+
+	require.NoError(t, os.WriteFile(
+		filepath.Join(c.dir, "tracked.txt"), []byte("edited\n"), fileMode,
+	))
+
+	require.Equal(t, "v1.2.3-dirty", c.version(t))
+}
+
+// A source tarball, or any build context without .git, still has to
+// build. It reports "unknown" rather than failing or naming a tag.
+func TestVersion_NoGitMetadataReportsUnknown(t *testing.T) {
+	t.Parallel()
+
+	c := newCheckout(t)
+	require.NoError(t, os.RemoveAll(filepath.Join(c.dir, ".git")))
+
+	require.Equal(t, unknown, c.version(t))
+}
+
+// An unpacked tarball can sit inside an unrelated working copy. The
+// enclosing repository's version is not this tree's version.
+func TestVersion_EnclosingRepositoryIsNotUsed(t *testing.T) {
+	t.Parallel()
+
+	outer := newCheckout(t)
+	outer.git(t, "tag", "v9.9.9")
+
+	inner := filepath.Join(outer.dir, "unpacked")
+	require.NoError(t, os.MkdirAll(filepath.Join(inner, "script"), dirMode))
+	copyScript(t, inner)
+
+	require.Equal(t, unknown, runScript(t, inner, nil))
+}
+
+// The Docker build has no git metadata, so the version arrives as an
+// environment override. It wins over anything derivable.
+func TestVersion_EnvironmentOverrideWins(t *testing.T) {
+	t.Parallel()
+
+	c := newCheckout(t)
+	c.git(t, "tag", "v1.2.3")
+
+	require.Equal(t, "v4.5.6",
+		runScript(t, c.dir, []string{"VERSION=v4.5.6"}))
+}
+
+// An empty VERSION is treated as unset rather than stamping an empty
+// string: the Dockerfile's build arg has a non-empty default, but a
+// caller exporting VERSION= must not produce a binary reporting "".
+func TestVersion_EmptyOverrideFallsBackToGit(t *testing.T) {
+	t.Parallel()
+
+	c := newCheckout(t)
+	c.git(t, "tag", "v1.2.3")
+
+	require.Equal(t, "v1.2.3", runScript(t, c.dir, []string{"VERSION="}))
+}
+
+// Two builds of the same commit must produce a byte-identical binary,
+// which they cannot if the stamped value moves between invocations.
+func TestVersion_IsStableAcrossInvocations(t *testing.T) {
+	t.Parallel()
+
+	c := newCheckout(t)
+	c.git(t, "tag", "v1.2.3")
+
+	first := c.version(t)
+	second := c.version(t)
+
+	require.Equal(t, first, second)
+}
+
+// The build target is the only place composing linker flags. If a
+// future edit drops either half, the binary silently reports "dev"
+// again (the defect this package exists for) or fails to link on
+// Alpine.
+func TestMakefile_BuildComposesVersionAndExtraFlags(t *testing.T) {
+	t.Parallel()
+
+	makefile := read(t, makefilePath)
+
+	require.Contains(t, makefile, "-X main.version=$(VERSION)")
+	require.Contains(t, makefile, "$(GO_LDFLAGS)")
+	require.Contains(t, makefile, "VERSION ?= $(shell script/version)")
+}
+
+// A caller can define VERSION as the empty string -- `make build
+// VERSION=`, or a `--build-arg VERSION=` reaching the Dockerfile's `make
+// build VERSION="$VERSION"`. script/version's own guard does not cover
+// that: the value never passes through the script. Stamping "" would
+// leave the binary reporting no version and the footer on "dev", which
+// is the defect this package exists for.
+func TestMakefile_EmptyOverrideResolvesLikeAnUnsetOne(t *testing.T) {
+	t.Parallel()
+
+	// A plain assignment would be ignored here: a command-line
+	// definition outranks it, and that is the case being corrected.
+	require.Contains(t, read(t, makefilePath), "override VERSION :=")
+
+	requireMake(t)
+
+	derived := makeVersion(t)
+	require.NotEmpty(t, derived)
+
+	require.Equal(t, derived, makeVersion(t, "VERSION="),
+		"an empty VERSION must resolve the way an unset one does")
+	require.Equal(t, "v9.9.9", makeVersion(t, "VERSION=v9.9.9"),
+		"the empty guard must not clobber a real override")
+}
+
+// makeVersion runs this repository's `version` target, which prints the
+// value `make build` would stamp, with the given command-line
+// definitions.
+func makeVersion(t *testing.T, defs ...string) string {
+	t.Helper()
+
+	//nolint:gosec // fixed argv, arguments are test constants
+	cmd := exec.CommandContext(t.Context(), "make",
+		append([]string{"--no-print-directory", "version"}, defs...)...)
+	cmd.Dir = repoRoot
+
+	// Only the command-line definitions may decide the outcome: an
+	// inherited VERSION would change what an unset one resolves to, and
+	// an inherited MAKEFLAGS carries the parent's jobserver.
+	cmd.Env = append(os.Environ(), "VERSION=", "MAKEFLAGS=", "MAKELEVEL=")
+
+	out, err := cmd.CombinedOutput()
+	require.NoError(t, err, string(out))
+
+	return strings.TrimSpace(string(out))
+}
+
+func requireMake(t *testing.T) {
+	t.Helper()
+
+	_, err := exec.LookPath("make")
+	if err != nil {
+		t.Skipf("make is not installed: %v", err)
+	}
+}
+
+// Every compile in the image goes through the build target, so the
+// static relink cannot replace the flags that carry the stamp.
+func TestDockerfile_BuildsThroughTheMakeTarget(t *testing.T) {
+	t.Parallel()
+
+	dockerfile := read(t, dockerfilePath)
+
+	require.NotContains(t, dockerfile, "go build",
+		"a raw go build bypasses the Makefile's -X flag")
+	require.Contains(t, dockerfile, "ARG VERSION=")
+	require.Contains(t, dockerfile,
+		`make build VERSION="$VERSION" GO_LDFLAGS='-extldflags "-static"'`)
+}
+
+func read(t *testing.T, path string) string {
+	t.Helper()
+
+	//nolint:gosec // repo-local build file under test, fixed path
+	b, err := os.ReadFile(path)
+	require.NoError(t, err)
+
+	return string(b)
+}
+
+// version runs the script in this checkout with no overrides.
+func (c checkout) version(t *testing.T) string {
+	t.Helper()
+
+	return runScript(t, c.dir, nil)
+}
+
+func runScript(t *testing.T, dir string, env []string) string {
+	t.Helper()
+
+	//nolint:gosec // fixed argv, repo-local script under test
+	cmd := exec.CommandContext(t.Context(), "sh",
+		filepath.Join(dir, "script", "version"))
+	cmd.Dir = dir
+
+	cmd.Env = append(os.Environ(), env...)
+
+	out, err := cmd.CombinedOutput()
+	require.NoError(t, err, string(out))
+
+	return strings.TrimSpace(string(out))
+}
+
+func (c checkout) git(t *testing.T, args ...string) string {
+	t.Helper()
+
+	//nolint:gosec // fixed argv, arguments are test constants
+	cmd := exec.CommandContext(t.Context(), "git", args...)
+	cmd.Dir = c.dir
+
+	out, err := cmd.CombinedOutput()
+	require.NoError(t, err, string(out))
+
+	return strings.TrimSpace(string(out))
+}
+
+func (c checkout) commit(t *testing.T, message string) string {
+	t.Helper()
+
+	c.git(t,
+		"-c", "user.email=ci@example.invalid",
+		"-c", "user.name=ci",
+		"-c", "commit.gpgsign=false",
+		"commit", "-q", "--allow-empty", "-m", message,
+	)
+
+	return c.git(t, "rev-parse", "HEAD")
+}
+
+// newCheckout builds a one-commit repository with a tracked file, so a
+// later edit to that file makes the tree dirty, and with a copy of the
+// script at the path it occupies in this repository.
+func newCheckout(t *testing.T) checkout {
+	t.Helper()
+
+	requireGit(t)
+
+	dir := t.TempDir()
+	c := checkout{dir: dir}
+
+	require.NoError(t, os.MkdirAll(filepath.Join(dir, "script"), dirMode))
+	copyScript(t, dir)
+
+	require.NoError(t, os.WriteFile(
+		filepath.Join(dir, "tracked.txt"), []byte("original\n"), fileMode,
+	))
+
+	c.git(t, "init", "-q", "-b", "main")
+	c.git(t, "add", "tracked.txt")
+	c.head = c.commit(t, "initial")
+
+	return c
+}
+
+func copyScript(t *testing.T, dir string) {
+	t.Helper()
+
+	body, err := os.ReadFile(scriptPath)
+	require.NoError(t, err)
+
+	//nolint:gosec // the copy has to stay executable to be run
+	err = os.WriteFile(
+		filepath.Join(dir, "script", "version"), body, scriptMode,
+	)
+	require.NoError(t, err)
+}
+
+func requireGit(t *testing.T) {
+	t.Helper()
+
+	for _, tool := range []string{"sh", "git"} {
+		_, err := exec.LookPath(tool)
+		if err != nil {
+			t.Skipf("%s is not installed: %v", tool, err)
+		}
+	}
+}

script/docker

@@ -1,7 +1,10 @@
 #!/bin/sh
 # script/docker: build the Docker image tagged with the project name.
-# Identical in all repos; the tag comes from script/projectname.
+# The tag comes from script/projectname.
-# Generic: needs no adaptation.
+#
+# .dockerignore excludes .git/, so the builder stage cannot derive the
+# version itself. It is resolved here, where the checkout is, and passed
+# in as a build arg; without it the image would stamp itself "unknown".
 set -eu
 
 SCRIPT_DIR="$(cd "$(dirname "$0")" && pwd -P)"
@@ -9,7 +12,9 @@ ROOT="$(cd "$SCRIPT_DIR/.." && pwd -P)"
 
 main() {
     cd "$ROOT"
-    docker build -t "$("$SCRIPT_DIR/projectname")" .
+    docker build \
+        --build-arg VERSION="$("$SCRIPT_DIR/version")" \
+        -t "$("$SCRIPT_DIR/projectname")" .
 }
 
 main "$@"

script/version

@@ -0,0 +1,65 @@
+#!/bin/sh
+# script/version: output the version string the binary is stamped with.
+# Our own extension to scripts-to-rule-them-all. The Makefile's build
+# target and script/docker both take the value from here, so a `make
+# build` binary and a `make docker` image built from the same checkout
+# report the same thing.
+#
+# Order of precedence:
+#
+#   1. $VERSION, if set and non-empty. This is how the value reaches a
+#      build that cannot derive it: .dockerignore excludes .git/, so the
+#      builder stage has no git metadata and the Dockerfile takes the
+#      value as a build arg instead.
+#   2. `git describe --tags --always --dirty` against this checkout. At
+#      a clean tagged commit that is exactly the tag; otherwise it
+#      carries the short SHA, the commit distance when a tag is
+#      reachable, and a -dirty suffix for uncommitted changes.
+#   3. "unknown", for a tree with no git metadata and no $VERSION -- a
+#      source tarball, or `docker build .` with no --build-arg. That
+#      case must not fail the build and must not name a tag the tree may
+#      not be at, so it names nothing.
+#
+# The git step insists the enclosing repository is this checkout, not
+# merely some repository above it: an unpacked tarball sitting inside an
+# unrelated working copy would otherwise be stamped with that copy's
+# version.
+#
+# Nothing here may vary between two builds of the same commit: the
+# release gate asserts the binary is byte-identical across builds. That
+# rules out a build timestamp, a hostname, and a builder identity.
+set -eu
+
+ROOT="$(cd "$(dirname "$0")/.." && pwd -P)"
+
+# in_this_checkout succeeds when git can read metadata for a repository
+# whose work tree root is $ROOT.
+in_this_checkout() {
+    command -v git >/dev/null 2>&1 || return 1
+
+    top="$(git rev-parse --show-toplevel 2>/dev/null)" || return 1
+    [ -n "$top" ] || return 1
+
+    top="$(cd "$top" 2>/dev/null && pwd -P)" || return 1
+    [ "$top" = "$ROOT" ]
+}
+
+main() {
+    if [ -n "${VERSION:-}" ]; then
+        echo "$VERSION"
+
+        return 0
+    fi
+
+    cd "$ROOT"
+
+    if in_this_checkout; then
+        # --always keeps an untagged history from failing the build: it
+        # falls back to the bare short SHA.
+        git describe --tags --always --dirty 2>/dev/null && return 0
+    fi
+
+    echo "unknown"
+}
+
+main "$@"

templates/source_detail.html

@@ -48,7 +48,7 @@
 
             <div class="divide-y divide-gray-100">
                 {{range .Entrypoints}}
-                <div class="p-4" x-data="{ showSecret: false }">
+                <div class="p-4">
                     <div class="flex items-center justify-between mb-1">
                         <span class="text-sm font-medium text-gray-900">{{if .Description}}{{.Description}}{{else}}Entrypoint{{end}}</span>
                         <div class="flex items-center gap-2">
@@ -75,38 +75,8 @@
                              script the URL above stays selectable. -->
                         <button type="button" hidden data-copy-target="entrypoint-url-{{.ID}}" class="text-xs text-gray-500 hover:text-primary-600">Copy</button>
                     </div>
-                    <div class="flex items-center gap-2 mt-2">
+                    <!-- The URL above is the entrypoint's credential:
-                        <span class="text-xs text-gray-500">
+                         anyone holding it can submit events. -->
-                            Signature: {{.SchemeLabel}}{{if .SchemeHeader}} ({{.SchemeHeader}}){{end}}
-                        </span>
-                        <button type="button" @click="showSecret = !showSecret" class="text-xs text-gray-500 hover:text-primary-600">
-                            {{if .Configured}}Rotate{{else}}Configure{{end}}
-                        </button>
-                    </div>
-                    <!-- The stored secret is never sent to the browser: the
-                         form takes a new one every time, so setting and
-                         rotating are the same submission. -->
-                    <div x-show="showSecret" x-cloak class="mt-2">
-                        <form method="POST" action="/source/{{$.Webhook.ID}}/entrypoints/{{.ID}}/secret" class="flex gap-2">
-                            <input type="hidden" name="csrf_token" value="{{$.CSRFToken}}">
-                            <select name="signature_scheme" class="input text-sm w-28">
-                                <!-- Selection follows the stored scheme, not
-                                     whether the pair is complete: a row with a
-                                     scheme and no secret would otherwise mark
-                                     both this option and its own selected. -->
-                                <option value="" {{if not .Scheme}}selected{{end}}>None</option>
-                                {{$current := .Scheme}}
-                                {{range $.SignatureSchemes}}
-                                <option value="{{.Scheme}}" {{if eq .Scheme $current}}selected{{end}}>{{.Label}}</option>
-                                {{end}}
-                            </select>
-                            <input type="password" name="secret" autocomplete="new-password" placeholder="Shared secret" class="input text-sm flex-1">
-                            <button type="submit" class="btn-primary text-sm">Save</button>
-                        </form>
-                        <p class="text-xs text-gray-500 mt-1">
-                            Enter the same secret you configured at the sender. Selecting None removes verification.
-                        </p>
-                    </div>
                 </div>
                 {{else}}
                 <div class="p-4 text-sm text-gray-500">No entrypoints configured.</div>