Bound username length at creation (closes #184)

A login stores the username in the session cookie, which cannot carry
a value past about 4096 bytes, so a username of about 2 KB or more
could never log in and the login answered 500.

Usernames are now limited to 1024 bytes, about half of what the cookie
can carry. The User model rejects a longer one with
ErrUsernameTooLong, and a check constraint on the users table rejects
it for any path that bypasses the model. The comment on
MaxUsernameBytes gives the arithmetic.

Model: opus-5-5

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

@@ -18,71 +18,159 @@ Issue branches do NOT touch this file — the manager maintains it on
 
 # Status
 
-pre-1.0. No git tags exist. `main` (4f5ecb1) is a working webhook proxy
+The milestone (https://git.eeqj.de/sneak/webhooker/milestone/9) is the
-with auth, CSRF/SSRF protections, login rate limiting, Slack target,
+authoritative list, and the only place to read a count or a state of
-event retention (#63), the database archiving target (#43), the admin
+play from. This file records where the project is, not what is in
-password change flow (#65), policy compliance (#6), pinned lint tooling
+flight: a sentence whose truth depends on a branch being unmerged is
-(#55), and fail-loud configuration parsing (#80).
+wrong the moment it merges, and this file has been wrong that way
+before.
 
-`next` is green — verified both by CI and by cache-defeated container
+The durability defect that held the tag has landed
-runs (`docker build --no-cache-filter=lint --no-cache-filter=builder`) —
+(https://git.eeqj.de/sneak/webhooker/issues/256, commit `8d64259`).
-but the **1.0.0 milestone is no longer complete**. It was reopened on
+Every SQLite handle opens with WAL journaling and a busy timeout, a
-2026-08-20 by a code-level deployability audit that ran the service end
+bookkeeping write that fails leaves its delivery in a recoverable
-to end (verdict:
+state rather than a lying one, and recovery skips a delivery that
-https://git.eeqj.de/sneak/webhooker/issues/33#issuecomment-66686).
+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`.
 
-The bar for 1.0 is not "the milestone is empty" but "sneak can deploy
+Delivery is at-least-once by design, not by accident: a send whose
-this and use it in low-volume production". The audit found the gap
+result row does not land is attempted again, so a receiver can see a
-between those two: two instances on one `DATA_DIR` both deliver
+duplicate. That is deliberate — the alternative is a silent lost
-(reproduced), a failed listen leaves a live non-serving process that
+delivery — and the README says so under Rationale. It is not a defect
-restart policies never fire on, there is no inbound authentication of
+to re-file.
-any kind, delivery failures render as a bare word with no status code or
-error, a terminally failed delivery can never be replayed, the SSRF
-blocklist has no escape hatch so the proxy cannot forward to your own
-network at all, and target credentials leak into the per-webhook event
-databases.
 
-One caveat on reading a green check, narrower than it used to be. A
+One caveat on reading a green check: a docs-only commit deliberately
-docs-only commit deliberately replays from the layer cache (#119), so a
+replays from the layer cache
-green status on such a commit evidences a replay rather than an executed
+(https://git.eeqj.de/sneak/webhooker/issues/119), so a green status on
-run; a code commit invalidates the `COPY` layer and genuinely executes.
+such a commit evidences a replay rather than an executed run. A code
-Superseded runs are no longer the hazard they were: before #152 they
+commit invalidates the `COPY` layer and genuinely executes.
-were recorded as `skipped` and rolled up green, and before #119 a warm
-layer cache let the gate report success without executing anything,
-replaying the previous build's console log so the lie looked like a real
-run. Both are fixed. Note: `TODO.md` was deliberately
-deleted from this repo in f9a9569 (2026-03-01, #6); its content was
-folded into the README TODO section, which this draft reconstructs as
-of 2026-07-06.
 
 # Next Step
 
-Clear the reopened 1.0.0 milestone. The milestone PR
+Clear the rest of the open 1.0.0 milestone
-(https://git.eeqj.de/sneak/webhooker/pulls/111) is held: it carries a
+(https://git.eeqj.de/sneak/webhooker/milestone/9) and tag `v1.0.0`.
-`WIP: ` prefix, no labels and is assigned to `clawbot`, and it stays
+Merging `next` into `main` is a separate act from tagging and waits on
-that way until the milestone is empty. Correctness first — the
+neither of those: `next` is kept mergeable at all times, which is the
-duplicate-delivery lock and the listen-failure shutdown — then the
+point of the branch.
-operability gaps that make the service usable in production, then the
-three credential exposures.
-
-Three items belong to the owner, none of them blocking. #150 was decided
-by the manager rather than left to stall the queue and is flagged on the
-issue for reversal if that call was wrong. #112 (whether `Completed
-Steps` should exist at all, given it once conflicted on every unit) is
-unanswered; the provisional ruling in force is that issue branches do
-not touch this file. #198 records that `make test` is past the org 20s
-target — 46s of test execution inside a 62.8s CI layer — and turns on
-which quantity the 60s hard cap governs; it is scoped as the improvement
-bug the 20-60s band requires, and should be milestoned instead if the
-cap is read as covering the whole invocation.
-
-After the tag, the largest open cluster is the unmilestoned follow-up
-backlog these units generated: #183, #184, #185, #190, #191, #193, #198,
-#211 and #212 (encrypting target config at rest, split out of the
-credential-leak fix because it needs a key-rotation and re-wrap story).
 
 # 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
@@ -308,14 +396,13 @@ credential-leak fix because it needs a key-rotation and re-wrap story).
 
 # Future Steps
 
-- Manual event redelivery from the web UI — the "Replay" capability the
+- Delivery status and retry management UI. Replay of a terminally
-  README describes as planned. No redelivery code exists anywhere in the
+  failed delivery and per-attempt detail already landed
-  tree; events are stored in full, which is all it would be built on
+  (https://git.eeqj.de/sneak/webhooker/issues/203,
-- Delivery status and retry management UI
+  https://git.eeqj.de/sneak/webhooker/issues/202)
 - Per-webhook rate limiting in the receiver handler (per-webhook config
   plus handler enforcement; global limits must not apply to receiver
   endpoints)
-- Webhook signature verification for GitHub and Stripe HMAC formats
 - API key authentication for programmatic access (APIKey model exists;
   Bearer token middleware does not)
 - REST API v1
@@ -325,9 +412,10 @@ credential-leak fix because it needs a key-rotation and re-wrap story).
     - OpenAPI specification
 - Analytics dashboard: success rates, response times, volume
 - A remember-me option at login
-- Password reset flow for a forgotten password. The authenticated
+- Password reset flow for a forgotten password over the web. The
-  password *change* flow already landed on `main` (#65); reset does not
+  authenticated password *change* flow already landed, and a lost
-  exist
+  password is recoverable from the console with `webhooker resetpw`
+  (https://git.eeqj.de/sneak/webhooker/issues/208)
 - Later, nice to have
     - email delivery target type
     - SNS and S3 delivery targets

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
@@ -157,6 +178,10 @@ func newApp() *fx.App {
 			session.New,
 			handlers.New,
 			middleware.New,
+			// The one SSRF guard both target-creation validation
+			// and the delivery dialer consult, so they cannot
+			// disagree about a destination.
+			delivery.NewGuard,
 			delivery.New,
 			delivery.NewArchiveSweeper,
 			// Wire *delivery.Engine as delivery.Notifier so the

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
@@ -128,6 +181,23 @@ type Config struct {
 	// clients.
 	TrustedProxies []netip.Prefix
 
+	// AllowedEgressCIDRs is the set of networks a delivery target
+	// may reach even though the SSRF guard's default blocklist
+	// covers them. It is empty unless ALLOWED_EGRESS_CIDRS is set,
+	// and empty means every private/reserved range stays refused.
+	//
+	// This only ever adds destinations to what the guard would
+	// otherwise refuse. The guard itself is always on: there is no
+	// setting that disables SSRF protection, and delivery's
+	// alwaysBlockedNetworks stays blocked no matter what is listed
+	// here. That set is link-local plus the cloud metadata
+	// endpoints outside it that disclose credentials or user data
+	// at a provider-fixed, non-public address; it is not
+	// exhaustive of every cloud's metadata address. See
+	// alwaysBlockedNetworks for the authoritative list and the
+	// criterion it is built from.
+	AllowedEgressCIDRs []netip.Prefix
+
 	params *ConfigParams
 	log    *slog.Logger
 }
@@ -157,12 +227,62 @@ 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
@@ -371,6 +491,77 @@ 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.
@@ -395,12 +586,14 @@ func resolveMetricsAuth() (string, string, error) {
 	)
 }
 
-// resolveEnvironment reads WEBHOOKER_ENVIRONMENT, defaulting to
+// resolveEnvironment reads WEBHOOKER_ENVIRONMENT, defaulting to prod
-// dev, and rejects unrecognised values.
+// when it is unset so a deployment that forgets the variable is not
+// silently permissive; dev must be set explicitly. It rejects
+// unrecognised values.
 func resolveEnvironment() (string, error) {
 	environment := os.Getenv("WEBHOOKER_ENVIRONMENT")
 	if environment == "" {
-		environment = EnvironmentDev
+		environment = EnvironmentProd
 	}
 
 	if environment != EnvironmentDev &&
@@ -415,6 +608,27 @@ 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
@@ -426,7 +640,7 @@ func loadFromEnv() (*Config, error) {
 		return nil, err
 	}
 
-	port, err := envPort("PORT", defaultPort)
+	port, bindAddress, err := resolveListener()
 	if err != nil {
 		return nil, err
 	}
@@ -472,11 +686,21 @@ func loadFromEnv() (*Config, error) {
 		return nil, err
 	}
 
+	allowedEgressCIDRs, err := envPrefixList("ALLOWED_EGRESS_CIDRS")
+	if err != nil {
+		return nil, err
+	}
+
 	metricsUsername, metricsPassword, err := resolveMetricsAuth()
 	if err != nil {
 		return nil, err
 	}
 
+	sentryDSN, err := envSentryDSN("SENTRY_DSN")
+	if err != nil {
+		return nil, err
+	}
+
 	return &Config{
 		DataDir:                DataDir(),
 		Debug:                  debug,
@@ -485,14 +709,57 @@ func loadFromEnv() (*Config, error) {
 		MetricsUsername:        metricsUsername,
 		MetricsPassword:        metricsPassword,
 		Port:                   port,
-		SentryDSN:              envString("SENTRY_DSN"),
+		BindAddress:            bindAddress,
+		SentryDSN:              sentryDSN,
 		RetentionSweepInterval: retentionSweepInterval,
 		SessionIdleTimeout:     sessionIdleTimeout,
 		ReceiverRateLimit:      receiverRateLimit,
 		TrustedProxies:         trustedProxies,
+		AllowedEgressCIDRs:     allowedEgressCIDRs,
 	}, nil
 }
 
+// PrefixStrings renders a prefix list as its CIDR strings, for
+// logging a list an operator has to be able to read back.
+func PrefixStrings(prefixes []netip.Prefix) []string {
+	out := make([]string, 0, len(prefixes))
+
+	for _, prefix := range prefixes {
+		out = append(out, prefix.String())
+	}
+
+	return out
+}
+
+// warnEgressAllowlist logs the effective ALLOWED_EGRESS_CIDRS
+// whenever it is non-empty.
+//
+// It prints the blocks themselves rather than a count, because
+// this is the one setting that lets a delivery target reach the
+// host's own network: an operator reading the startup log has to
+// be able to see exactly which hole is open. Silence means the
+// list is empty and the SSRF guard is refusing every
+// private/reserved range, which is the default.
+func (c *Config) warnEgressAllowlist(log *slog.Logger) {
+	if len(c.AllowedEgressCIDRs) == 0 {
+		return
+	}
+
+	log.Warn(
+		"ALLOWED_EGRESS_CIDRS lets delivery targets reach these "+
+			"otherwise-blocked networks. Anyone who can create a "+
+			"delivery target can now make this process issue "+
+			"requests into them, and read back the response. Only "+
+			"the addresses the README lists as blocked "+
+			"unconditionally stay blocked regardless of what is "+
+			"listed here; a public cloud metadata address such as "+
+			"168.63.129.16 is reachable once it, or a block "+
+			"covering it, is listed.",
+		"allowedEgressCIDRs",
+		strings.Join(PrefixStrings(c.AllowedEgressCIDRs), ","),
+	)
+}
+
 // warnSharedRateLimitBucket logs a startup warning whenever
 // TRUSTED_PROXIES is empty, in any environment.
 //
@@ -510,10 +777,8 @@ func loadFromEnv() (*Config, error) {
 // everyone else's wrong passwords, and the receiver's limits become
 // service-wide ceilings.
 //
-// The warning is deliberately not gated on WEBHOOKER_ENVIRONMENT. That
+// The warning is deliberately not gated on WEBHOOKER_ENVIRONMENT:
-// variable defaults to dev, so gating on it would silence the warning
+// behind a proxy every client shares one bucket in dev and prod alike.
-// for exactly the operator who forgot to configure the deployment —
-// the case it exists to catch.
 //
 // The default of trusting nobody is deliberate — trusting forwarded
 // headers from arbitrary peers lets any client choose its own bucket —
@@ -564,6 +829,11 @@ 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,
@@ -574,11 +844,13 @@ func New(lc fx.Lifecycle, params ConfigParams) (*Config, error) {
 		"sessionIdleTimeout", s.SessionIdleTimeout.String(),
 		"receiverRateLimit", s.ReceiverRateLimit,
 		"trustedProxies", len(s.TrustedProxies),
-		"hasSentryDSN", s.SentryDSN != "",
+		"allowedEgressCIDRs", len(s.AllowedEgressCIDRs),
+		"sentryEnabled", s.SentryEnabled(),
 		"hasMetricsAuth", s.MetricsAuthEnabled(),
 	)
 
 	s.warnSharedRateLimitBucket(log)
+	s.warnEgressAllowlist(log)
 
 	return s, nil
 }

internal/config/config_test.go

@@ -44,9 +44,9 @@ func TestEnvironmentConfig(t *testing.T) {
 		isProd      bool
 	}{
 		{
-			name:   "default is dev",
+			name:   "default is prod",
-			isDev:  true,
+			isDev:  false,
-			isProd: false,
+			isProd: true,
 		},
 		{
 			name:     "explicit dev",
@@ -663,14 +663,195 @@ func testTrustedProxiesSuccess(
 	assert.Equal(t, expected, got)
 }
 
+// TestAllowedEgressCIDRs covers ALLOWED_EGRESS_CIDRS, the escape
+// hatch that lets a self-hosted deployment forward to its own
+// network. Unset it must stay empty, so the SSRF guard keeps
+// refusing every private/reserved range; a set-but-unparseable
+// value must abort startup naming the variable rather than
+// silently running with a list the operator did not write.
+func TestAllowedEgressCIDRs(t *testing.T) {
+	tests := []struct {
+		name        string
+		set         bool
+		value       string
+		expected    []string
+		expectError bool
+	}{
+		{
+			name:     caseUnsetUsesDefault,
+			set:      false,
+			expected: []string{},
+		},
+		{
+			name:     "empty value yields empty list",
+			set:      true,
+			value:    "",
+			expected: []string{},
+		},
+		{
+			name:     caseValidValueParsed,
+			set:      true,
+			value:    cidrPrivateV4,
+			expected: []string{cidrPrivateV4},
+		},
+		{
+			name:     "multiple blocks with whitespace",
+			set:      true,
+			value:    " 10.0.0.0/8 , 127.0.0.0/8 ",
+			expected: []string{cidrPrivateV4, "127.0.0.0/8"},
+		},
+		{
+			name:     "bare address becomes a single host",
+			set:      true,
+			value:    "172.17.0.5",
+			expected: []string{"172.17.0.5/32"},
+		},
+		{
+			name:        caseUnparseableFails,
+			set:         true,
+			value:       cidrPrivateV4 + ",not-an-address",
+			expectError: true,
+		},
+		{
+			name:        "out-of-range prefix length fails startup",
+			set:         true,
+			value:       "10.0.0.0/33",
+			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.
+			t.Setenv("WEBHOOKER_ENVIRONMENT", "dev")
+
+			if tt.set {
+				t.Setenv("ALLOWED_EGRESS_CIDRS", tt.value)
+			} else {
+				require.NoError(
+					t, os.Unsetenv("ALLOWED_EGRESS_CIDRS"),
+				)
+			}
+
+			if tt.expectError {
+				expectStartupErrorFor(
+					t, "ALLOWED_EGRESS_CIDRS", config.ErrInvalidCIDR,
+				)
+			} else {
+				testAllowedEgressCIDRsSuccess(t, tt.expected)
+			}
+		})
+	}
+}
+
+func testAllowedEgressCIDRsSuccess(
+	t *testing.T,
+	expected []string,
+) {
+	t.Helper()
+
+	var cfg *config.Config
+
+	app := fxtest.New(
+		t,
+		fx.Provide(
+			globals.New,
+			logger.New,
+			config.New,
+		),
+		fx.Populate(&cfg),
+	)
+	require.NoError(t, app.Err())
+
+	app.RequireStart()
+
+	defer app.RequireStop()
+
+	assert.Equal(
+		t, expected, config.PrefixStrings(cfg.AllowedEgressCIDRs),
+	)
+}
+
+// TestEgressAllowlistWarning covers the startup log that shows an
+// operator the hole ALLOWED_EGRESS_CIDRS opened. It must stay
+// silent on the default (empty) list and, when set, print the
+// blocks themselves rather than a count.
+func TestEgressAllowlistWarning(t *testing.T) {
+	tests := []struct {
+		name          string
+		allowed       string
+		expectWarning bool
+	}{
+		{
+			name:          "empty allowlist is quiet",
+			expectWarning: false,
+		},
+		{
+			name:          "non-empty allowlist warns",
+			allowed:       "10.0.0.0/8,127.0.0.0/8",
+			expectWarning: 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.
+			t.Setenv("WEBHOOKER_ENVIRONMENT", config.EnvironmentDev)
+
+			if tt.allowed == "" {
+				require.NoError(
+					t, os.Unsetenv("ALLOWED_EGRESS_CIDRS"),
+				)
+			} else {
+				t.Setenv("ALLOWED_EGRESS_CIDRS", tt.allowed)
+			}
+
+			var buf bytes.Buffer
+
+			log := slog.New(slog.NewJSONHandler(
+				&buf, &slog.HandlerOptions{
+					Level: slog.LevelDebug,
+				},
+			))
+
+			require.NoError(
+				t, config.WarnEgressAllowlistForTest(log),
+			)
+
+			if !tt.expectWarning {
+				assert.Empty(t, buf.String())
+
+				return
+			}
+
+			logged := buf.String()
+
+			assert.Contains(t, logged, `"level":"WARN"`)
+			assert.Contains(t, logged, "ALLOWED_EGRESS_CIDRS")
+			// The blocks themselves, not a count: the operator has
+			// to be able to read back which networks are open.
+			assert.Contains(t, logged, "10.0.0.0/8")
+			assert.Contains(t, logged, "127.0.0.0/8")
+			// What stays shut is the whole unconditional set, not
+			// link-local alone; a public metadata address is not in
+			// it, so a listed block covering it opens it.
+			assert.Contains(t, logged, "blocked unconditionally")
+			assert.Contains(t, logged, "168.63.129.16 is reachable")
+			// The listed blocks need not be private or reserved.
+			assert.NotContains(t, logged, "private/reserved")
+		})
+	}
+}
+
 // TestSharedRateLimitBucketWarning covers the startup warning that
 // tells an operator a deployment behind a reverse proxy shares one
 // rate-limit bucket between every client, which turns the receiver
 // limits into service-wide ceilings and collapses login failure
-// counting. It must fire whenever TRUSTED_PROXIES is empty,
+// counting. It must fire whenever TRUSTED_PROXIES is empty, in any
-// in any environment: WEBHOOKER_ENVIRONMENT defaults to dev, so gating
+// environment, because behind a proxy every client shares one bucket
-// on it would silence the warning for exactly the operator who never
+// in dev and prod alike. It stays quiet once proxies are named.
-// configured the deployment. It stays quiet once proxies are named.
 func TestSharedRateLimitBucketWarning(t *testing.T) {
 	tests := []struct {
 		name           string
@@ -690,10 +871,6 @@ func TestSharedRateLimitBucketWarning(t *testing.T) {
 			expectWarning:  false,
 		},
 		{
-			// The default environment. An internet-exposed
-			// deployment whose operator never set
-			// WEBHOOKER_ENVIRONMENT lands here and has exactly
-			// the exposure the warning announces.
 			name:          "dev without trusted proxies warns",
 			environment:   config.EnvironmentDev,
 			expectWarning: true,

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

@@ -21,6 +21,21 @@ func WarnSharedRateLimitBucketForTest(log *slog.Logger) error {
 	return nil
 }
 
+// WarnEgressAllowlistForTest loads a Config from the current
+// environment and emits its egress-allowlist startup warning to
+// log, so a test can assert both that the warning fires only when
+// the list is non-empty and that it names the blocks it opened.
+func WarnEgressAllowlistForTest(log *slog.Logger) error {
+	c, err := loadFromEnv()
+	if err != nil {
+		return err
+	}
+
+	c.warnEgressAllowlist(log)
+
+	return nil
+}
+
 // EnvBoolForTest exposes envBool.
 func EnvBoolForTest(key string, defaultValue bool) (bool, error) {
 	return envBool(key, defaultValue)
@@ -35,3 +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"
@@ -16,15 +15,14 @@ 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/datadir"
 	"sneak.berlin/go/webhooker/internal/gormlog"
 	"sneak.berlin/go/webhooker/internal/logger"
 )
 
 const (
-	dataDirPerm       = 0750
 	randomPasswordLen = 16
 	sessionKeyLen     = 32
 )
@@ -187,7 +185,9 @@ func (d *Database) connect() error {
 // caller's decision.
 func (d *Database) connectTo(dataDir string) error {
 	// Ensure the data directory exists before opening the database.
-	err := os.MkdirAll(dataDir, dataDirPerm)
+	// datadir.DirPerm is the single source of the directory mode; this
+	// package creates the directory too, since either may run first.
+	err := os.MkdirAll(dataDir, datadir.DirPerm)
 	if err != nil {
 		return fmt.Errorf(
 			"creating data directory %s: %w",
@@ -198,13 +198,11 @@ 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/event_tier_indexes_test.go

@@ -0,0 +1,166 @@
+package database_test
+
+import (
+	"context"
+	"fmt"
+	"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"
+)
+
+// TestWebhookDBManager_OpenAddsEventTierIndexes verifies that opening a
+// per-webhook database that predates these indexes creates them. It
+// stands in for an older database file by dropping the indexes
+// AutoMigrate just created, then reopening the same file.
+func TestWebhookDBManager_OpenAddsEventTierIndexes(t *testing.T) {
+	t.Parallel()
+
+	indexes := []struct {
+		model any
+		name  string
+	}{
+		{&database.Delivery{}, "idx_deliveries_status"},
+		{&database.Delivery{}, "idx_deliveries_event_id"},
+		{&database.DeliveryResult{}, "idx_delivery_results_delivery_id"},
+		{&database.Event{}, "idx_events_deleted_at_created_at"},
+		{&database.Event{}, "idx_events_created_at"},
+	}
+
+	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 fresh database has them.
+	for _, ix := range indexes {
+		require.True(t, db.Migrator().HasIndex(ix.model, ix.name))
+	}
+
+	// Stand in for a database file created before the indexes existed.
+	for _, ix := range indexes {
+		require.NoError(t, db.Migrator().DropIndex(ix.model, ix.name))
+		require.False(t, db.Migrator().HasIndex(ix.model, ix.name))
+	}
+
+	// Drop the cached connection so the next open reopens the file and
+	// runs AutoMigrate against it, as a restart would.
+	require.NoError(t, mgr.CloseAll())
+
+	db, err = mgr.GetDB(webhookID)
+	require.NoError(t, err)
+
+	for _, ix := range indexes {
+		assert.True(t, db.Migrator().HasIndex(ix.model, ix.name),
+			"opening the existing database should create %s", ix.name)
+	}
+}
+
+// TestEventTierQueriesUseTheirIndexes verifies that the statements the
+// indexes are for use them. GORM builds each statement in a dry run as
+// the code named above it does, soft-delete condition included, and
+// SQLite, which keeps no statistics on these tables, must plan to seek
+// on each index listed by the columns in parentheses.
+func TestEventTierQueriesUseTheirIndexes(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)) }()
+
+	db, err := mgr.GetDB(uuid.New().String())
+	require.NoError(t, err)
+
+	dry := db.Session(&gorm.Session{DryRun: true})
+	ids := []string{
+		uuid.New().String(), uuid.New().String(), uuid.New().String(),
+	}
+	cutoff := time.Now()
+
+	var (
+		deliveries []database.Delivery
+		results    []database.DeliveryResult
+		depths     []struct{ Depth int }
+	)
+
+	byStatus := "idx_deliveries_status (status=? AND deleted_at=?)"
+	byEvent := "idx_deliveries_event_id (event_id=? AND deleted_at=?)"
+	byAge := "idx_events_deleted_at_created_at (deleted_at=? AND created_at<?)"
+
+	// The delivery engine: recovery and the retry sweep, the sweep for
+	// stranded pending deliveries, and the queue depth count.
+	assertPlanUses(t, db, dry.Where(
+		"status = ?", database.DeliveryStatusRetrying,
+	).Find(&deliveries), byStatus)
+	assertPlanUses(t, db, dry.Where(
+		"status = ? AND updated_at < ?",
+		database.DeliveryStatusPending, cutoff,
+	).Limit(500).Find(&deliveries), byStatus)
+	assertPlanUses(t, db, dry.Model(&database.Delivery{}).
+		Select("target_id", "status", "count(*) as depth").
+		Where("status IN ?", []database.DeliveryStatus{
+			database.DeliveryStatusPending,
+			database.DeliveryStatusRetrying,
+		}).Group("target_id, status").Find(&depths), byStatus)
+
+	// The event log: each event's deliveries, then their attempts
+	// (loadEventsWithDeliveries, loadDeliveryResults).
+	assertPlanUses(t, db, dry.Where("event_id = ?", ids[0]).
+		Find(&deliveries), byEvent)
+	assertPlanUses(t, db, dry.Where("delivery_id IN ?", ids).
+		Order("attempt_num ASC").Find(&results),
+		"idx_delivery_results_delivery_id (delivery_id=? AND deleted_at=?)")
+
+	// Retention's three deletes (reapExpired), whose subqueries are built
+	// afresh for each statement as it builds them.
+	expiredEventIDs := func() *gorm.DB {
+		return dry.Model(&database.Event{}).Select("id").
+			Where("created_at < ?", cutoff)
+	}
+
+	assertPlanUses(t, db, dry.Unscoped().Where(
+		"delivery_id IN (?)", dry.Model(&database.Delivery{}).
+			Select("id").Where("event_id IN (?)", expiredEventIDs()),
+	).Delete(&database.DeliveryResult{}),
+		"idx_delivery_results_delivery_id (delivery_id=?)", byEvent, byAge)
+	assertPlanUses(t, db, dry.Unscoped().Where(
+		"event_id IN (?)", expiredEventIDs(),
+	).Delete(&database.Delivery{}),
+		"idx_deliveries_event_id (event_id=?)", byAge)
+	assertPlanUses(t, db, dry.Unscoped().Where(
+		"created_at < ?", cutoff,
+	).Delete(&database.Event{}), "idx_events_created_at (created_at<?)")
+}
+
+// assertPlanUses asserts that SQLite's plan for a statement GORM built
+// in a dry run, run with the same SQL and arguments GORM would send,
+// names each of the given indexes.
+func assertPlanUses(
+	t *testing.T, db, built *gorm.DB, indexes ...string,
+) {
+	t.Helper()
+
+	var plan []struct{ Detail string }
+
+	require.NoError(t, db.Raw(
+		"EXPLAIN QUERY PLAN "+built.Statement.SQL.String(),
+		built.Statement.Vars...,
+	).Scan(&plan).Error)
+
+	for _, index := range indexes {
+		assert.Contains(t, fmt.Sprint(plan), index,
+			built.Statement.SQL.String())
+	}
+}

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_delivery.go

@@ -1,5 +1,7 @@
 package database
 
+import "gorm.io/gorm"
+
 // DeliveryStatus represents the status of a delivery
 type DeliveryStatus string
 
@@ -29,12 +31,19 @@ func (s DeliveryStatus) Terminal() bool {
 }
 
 // Delivery represents a delivery attempt for an event to a target
+//
+//nolint:lll // a struct tag cannot wrap
 type Delivery struct {
 	BaseModel
 
-	EventID  string         `gorm:"type:uuid;not null"         json:"eventId"`
+	EventID  string         `gorm:"type:uuid;not null;index:idx_deliveries_event_id,priority:1"       json:"eventId"`
-	TargetID string         `gorm:"type:uuid;not null"         json:"targetId"`
+	TargetID string         `gorm:"type:uuid;not null"                                                json:"targetId"`
-	Status   DeliveryStatus `gorm:"not null;default:'pending'" json:"status"`
+	Status   DeliveryStatus `gorm:"not null;default:'pending';index:idx_deliveries_status,priority:1" json:"status"`
+
+	// DeletedAt repeats the BaseModel field only to be the second column
+	// of the event_id and status indexes, for the reason DeliveryResult
+	// gives.
+	DeletedAt gorm.DeletedAt `gorm:"index:idx_deliveries_event_id,priority:2;index:idx_deliveries_status,priority:2" json:"deletedAt,omitzero"`
 
 	// Relations
 	Event           Event            `json:"event,omitzero"`

internal/database/model_delivery_result.go

@@ -1,10 +1,21 @@
 package database
 
+import "gorm.io/gorm"
+
 // DeliveryResult represents the result of a delivery attempt
+//
+//nolint:lll // a struct tag cannot wrap
 type DeliveryResult struct {
 	BaseModel
 
-	DeliveryID   string `gorm:"type:uuid;not null"   json:"deliveryId"`
+	// DeliveryID and DeletedAt make up one index, in that order.
+	// DeletedAt repeats the BaseModel field only to join it: GORM adds
+	// "deleted_at IS NULL" to almost every query, and where a column is
+	// matched against several values SQLite otherwise reads through the
+	// deleted_at index, which every live row matches.
+	DeliveryID string         `gorm:"type:uuid;not null;index:idx_delivery_results_delivery_id,priority:1" json:"deliveryId"`
+	DeletedAt  gorm.DeletedAt `gorm:"index:idx_delivery_results_delivery_id,priority:2"                    json:"deletedAt,omitzero"`
+
 	AttemptNum   int    `gorm:"not null"             json:"attemptNum"`
 	Success      bool   `json:"success"`
 	StatusCode   int    `json:"statusCode,omitempty"`

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_event.go

@@ -1,9 +1,27 @@
 package database
 
+import (
+	"time"
+
+	"gorm.io/gorm"
+)
+
 // Event represents a captured webhook event
+//
+//nolint:lll // a struct tag cannot wrap
 type Event struct {
 	BaseModel
 
+	// CreatedAt and DeletedAt repeat the BaseModel fields only to index
+	// them for retention, which finds events by age. Its lookups carry
+	// GORM's "deleted_at IS NULL" (see DeliveryResult) and compare
+	// created_at with <, so their index has deleted_at first: SQLite
+	// narrows by a < only on the last column it uses. Its final delete
+	// has no deleted_at condition and uses the index on created_at
+	// alone. The other tables keep the unindexed BaseModel created_at.
+	CreatedAt time.Time      `gorm:"index;index:idx_events_deleted_at_created_at,priority:2" json:"createdAt"`
+	DeletedAt gorm.DeletedAt `gorm:"index:idx_events_deleted_at_created_at,priority:1"       json:"deletedAt,omitzero"`
+
 	WebhookID    string `gorm:"type:uuid;not null" json:"webhookId"`
 	EntrypointID string `gorm:"type:uuid;not null" json:"entrypointId"`
 
@@ -13,6 +31,14 @@ type Event struct {
 	Body        string `gorm:"type:text"   json:"body"`
 	ContentType string `json:"contentType"`
 
+	// ResubmittedFromID names the event this one was copied from by
+	// an operator resubmit. It is nil for an event that arrived on
+	// the receiver, which is every event created before the column
+	// existed. It is not a foreign key: the source event can be
+	// reaped by retention while its copies remain, and the id is
+	// kept as the record of where the copy came from either way.
+	ResubmittedFromID *string `gorm:"type:uuid;index" json:"resubmittedFromId,omitempty"`
+
 	// Relations
 	Webhook    Webhook    `json:"webhook,omitzero"`
 	Entrypoint Entrypoint `json:"entrypoint,omitzero"`

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/model_user.go

@@ -1,13 +1,57 @@
 package database
 
+import (
+	"errors"
+	"fmt"
+
+	"gorm.io/gorm"
+)
+
+// MaxUsernameBytes is the longest username, in bytes, that a user may
+// have. The same number appears in the check constraint on
+// User.Username, because a struct tag cannot reference a constant.
+//
+// A login stores the username in the session cookie, and both
+// securecookie and browsers refuse a cookie value past about 4096
+// bytes. That value is the session base64-encoded twice, so it holds
+// 4096 × 3/4 × 3/4 = 2304 bytes of session, and the signature,
+// timestamp and the session's other values take about 270 of those: a
+// username longer than about 2030 bytes can never log in. The limit is
+// about half that, so the session can carry more values later without
+// locking out an account whose username is already at the limit.
+const MaxUsernameBytes = 1024
+
+// ErrUsernameTooLong is returned when a user is saved with a username
+// longer than MaxUsernameBytes.
+var ErrUsernameTooLong = errors.New("username is too long")
+
 // User represents a user of the webhooker service
+//
+//nolint:lll // a struct tag cannot wrap
 type User struct {
 	BaseModel
 
-	Username string `gorm:"uniqueIndex;not null" json:"username"`
+	Username string `gorm:"uniqueIndex;not null;check:length(CAST(username AS BLOB)) <= 1024" json:"username"`
-	Password string `gorm:"not null"             json:"-"` // Argon2 hashed
+	Password string `gorm:"not null"                                                          json:"-"` // Argon2 hashed
 
 	// Relations
 	Webhooks []Webhook `json:"webhooks,omitempty"`
 	APIKeys  []APIKey  `json:"apiKeys,omitempty"`
 }
+
+// BeforeSave rejects a username longer than MaxUsernameBytes, so every
+// path that saves a user through GORM gets ErrUsernameTooLong rather
+// than the database's constraint error. The check constraint behind it
+// holds for any path that writes the table without this model.
+func (u *User) BeforeSave(_ *gorm.DB) error {
+	if len(u.Username) > MaxUsernameBytes {
+		return fmt.Errorf(
+			"%w: %d bytes, limit is %d",
+			ErrUsernameTooLong,
+			len(u.Username),
+			MaxUsernameBytes,
+		)
+	}
+
+	return nil
+}

internal/database/model_user_test.go

@@ -0,0 +1,65 @@
+package database_test
+
+import (
+	"strings"
+	"testing"
+
+	"github.com/google/uuid"
+	"github.com/stretchr/testify/assert"
+	"github.com/stretchr/testify/require"
+	"sneak.berlin/go/webhooker/internal/database"
+)
+
+// usernameAtLimit is exactly MaxUsernameBytes long, built from a
+// two-byte character. A check that counted characters rather than bytes
+// would see half the length and let the one-byte-longer name through.
+func usernameAtLimit() string {
+	return strings.Repeat("é", database.MaxUsernameBytes/2)
+}
+
+func TestUserCreate_RejectsOverlongUsername(t *testing.T) {
+	t.Parallel()
+
+	db := startedTestDB(t)
+
+	err := db.Create(&database.User{
+		Username: usernameAtLimit() + "x",
+		Password: "hash",
+	}).Error
+
+	require.ErrorIs(t, err, database.ErrUsernameTooLong)
+}
+
+func TestUserCreate_AcceptsUsernameAtLimit(t *testing.T) {
+	t.Parallel()
+
+	db := startedTestDB(t)
+
+	require.NoError(t, db.Create(&database.User{
+		Username: usernameAtLimit(),
+		Password: "hash",
+	}).Error)
+}
+
+// TestUsersTable_EnforcesUsernameLimitWithoutTheModel inserts with raw
+// SQL, as a path that bypassed User.BeforeSave would, so only the
+// table's check constraint stands between it and an over-long
+// username. Accepting the name at the limit and refusing the next byte
+// also pins the constraint's number to MaxUsernameBytes.
+func TestUsersTable_EnforcesUsernameLimitWithoutTheModel(t *testing.T) {
+	t.Parallel()
+
+	db := startedTestDB(t)
+
+	insert := "INSERT INTO users (id, username, password) VALUES (?, ?, ?)"
+
+	require.NoError(t, db.Exec(
+		insert, uuid.New().String(), usernameAtLimit(), "hash",
+	).Error)
+
+	err := db.Exec(
+		insert, uuid.New().String(), usernameAtLimit()+"x", "hash",
+	).Error
+	require.Error(t, err)
+	assert.Contains(t, err.Error(), "CHECK constraint failed")
+}

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"
@@ -14,6 +13,7 @@ import (
 	"gorm.io/driver/sqlite"
 	"gorm.io/gorm"
 	"sneak.berlin/go/webhooker/internal/config"
+	"sneak.berlin/go/webhooker/internal/datadir"
 	"sneak.berlin/go/webhooker/internal/gormlog"
 	"sneak.berlin/go/webhooker/internal/logger"
 )
@@ -41,6 +41,11 @@ type WebhookDBManager struct {
 	dataDir string
 	dbs     sync.Map // map[webhookID]*gorm.DB
 	log     *slog.Logger
+
+	// mu is held while a database is opened, deleted, or closed, so
+	// each file has at most one open handle. Reading an already cached
+	// handle does not take it.
+	mu sync.Mutex
 }
 
 // NewWebhookDBManager creates a new WebhookDBManager and
@@ -54,8 +59,9 @@ func NewWebhookDBManager(
 		log:     params.Logger.Get(),
 	}
 
-	// Create data directory if it doesn't exist
+	// Create data directory if it doesn't exist. datadir.DirPerm is the
-	err := os.MkdirAll(m.dataDir, dataDirPerm)
+	// single source of the directory mode; either package may run first.
+	err := os.MkdirAll(m.dataDir, datadir.DirPerm)
 	if err != nil {
 		return nil, fmt.Errorf(
 			"creating data directory %s: %w",
@@ -85,43 +91,39 @@ func (m *WebhookDBManager) GetDB(
 ) (*gorm.DB, error) {
 	// Fast path: already open
 	if val, ok := m.dbs.Load(webhookID); ok {
-		cachedDB, castOK := val.(*gorm.DB)
+		return asGormDB(val, webhookID)
-		if !castOK {
+	}
-			return nil, fmt.Errorf(
-				"%w for webhook %s",
-				errInvalidCachedDBType,
-				webhookID,
-			)
-		}
 
-		return cachedDB, nil
+	// Slow path: open the database under the lock, looking in the
+	// cache again first. A caller that raced another one here then
+	// waits for its handle instead of opening a second one.
+	m.mu.Lock()
+	defer m.mu.Unlock()
+
+	if val, ok := m.dbs.Load(webhookID); ok {
+		return asGormDB(val, webhookID)
 	}
 
-	// Slow path: open/create the database
 	db, err := m.openDB(webhookID)
 	if err != nil {
 		return nil, err
 	}
 
-	// Store it; if another goroutine beat us, close ours
+	m.dbs.Store(webhookID, db)
-	actual, loaded := m.dbs.LoadOrStore(webhookID, db)
-	if loaded {
-		// Another goroutine created it first; close our duplicate
-		sqlDB, closeErr := db.DB()
-		if closeErr == nil {
-			_ = sqlDB.Close()
-		}
 
-		existingDB, castOK := actual.(*gorm.DB)
+	return db, nil
-		if !castOK {
+}
-			return nil, fmt.Errorf(
-				"%w for webhook %s",
-				errInvalidCachedDBType,
-				webhookID,
-			)
-		}
 
-		return existingDB, nil
+// asGormDB returns a value read from the cache as the database
+// handle it is.
+func asGormDB(val any, webhookID string) (*gorm.DB, error) {
+	db, ok := val.(*gorm.DB)
+	if !ok {
+		return nil, fmt.Errorf(
+			"%w for webhook %s",
+			errInvalidCachedDBType,
+			webhookID,
+		)
 	}
 
 	return db, nil
@@ -152,6 +154,11 @@ func (m *WebhookDBManager) DBExists(
 func (m *WebhookDBManager) DeleteDB(
 	webhookID string,
 ) error {
+	// Held until the files are gone, so GetDB cannot open the file
+	// again between the close and the removal.
+	m.mu.Lock()
+	defer m.mu.Unlock()
+
 	// Close and remove from cache
 	if val, ok := m.dbs.LoadAndDelete(webhookID); ok {
 		if gormDB, castOK := val.(*gorm.DB); castOK {
@@ -185,6 +192,11 @@ func (m *WebhookDBManager) DeleteDB(
 // CloseAll closes all open per-webhook database connections.
 // Called during application shutdown.
 func (m *WebhookDBManager) CloseAll() error {
+	// An open already under way finishes and is cached first, so it
+	// is closed here rather than cached after this loop has passed.
+	m.mu.Lock()
+	defer m.mu.Unlock()
+
 	var lastErr error
 
 	m.dbs.Range(func(key, value any) bool {
@@ -234,12 +246,11 @@ 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/database/webhook_db_manager_test.go

@@ -1,10 +1,14 @@
 package database_test
 
 import (
+	"bytes"
 	"context"
+	"log/slog"
 	"net/http"
 	"os"
 	"path/filepath"
+	"strings"
+	"sync"
 	"testing"
 
 	"github.com/google/uuid"
@@ -104,6 +108,54 @@ func TestWebhookDBManager_CreateAndGetDB(t *testing.T) {
 	assert.Equal(t, `{"test": true}`, readEvent.Body)
 }
 
+// Many callers ask for one webhook's database at the same moment,
+// before it is cached. Only one of them may open the file; the others
+// must wait for its handle. openDB logs one "opened per-webhook
+// database" line per open, and those lines are what is counted.
+func TestWebhookDBManager_ConcurrentFirstTouchOpensOnce(t *testing.T) {
+	t.Parallel()
+
+	var logs bytes.Buffer
+
+	mgr := database.NewTestWebhookDBManagerWithLogger(
+		t.TempDir(),
+		slog.New(slog.NewTextHandler(&logs, nil)),
+	)
+
+	t.Cleanup(func() { assert.NoError(t, mgr.CloseAll()) })
+
+	webhookID := uuid.New().String()
+
+	const callers = 16
+
+	start := make(chan struct{})
+	handles := make([]*gorm.DB, callers)
+	errs := make([]error, callers)
+
+	var wg sync.WaitGroup
+
+	for i := range callers {
+		wg.Go(func() {
+			<-start
+
+			handles[i], errs[i] = mgr.GetDB(webhookID)
+		})
+	}
+
+	close(start)
+	wg.Wait()
+
+	for i := range callers {
+		require.NoError(t, errs[i])
+		assert.Same(t, handles[0], handles[i])
+	}
+
+	assert.Equal(
+		t, 1,
+		strings.Count(logs.String(), "opened per-webhook database"),
+	)
+}
+
 func TestWebhookDBManager_DeleteDB(t *testing.T) {
 	t.Parallel()
 

internal/datadir/lock.go

@@ -29,9 +29,11 @@ import (
 // process that was killed with SIGKILL blocks nothing.
 const LockFileName = "webhooker.lock"
 
-// dirPerm is the mode Acquire creates DATA_DIR with. It matches what
+// DirPerm is the mode DATA_DIR is created with. It is the single
-// internal/database uses, since whichever runs first creates it.
+// source of that mode: internal/database consumes it rather than
-const dirPerm = 0o750
+// keeping its own copy, so the two packages that both create the
+// directory cannot drift into disagreeing about its permissions.
+const DirPerm = 0o750
 
 // ErrLocked reports that another live process holds the data
 // directory. Callers that need to know whether a deployment is running
@@ -64,7 +66,7 @@ func Acquire(dir string) (*Lock, error) {
 		return nil, ErrNoDir
 	}
 
-	err := os.MkdirAll(dir, dirPerm)
+	err := os.MkdirAll(dir, DirPerm)
 	if err != nil {
 		return nil, fmt.Errorf(
 			"creating data directory %s: %w", dir, err,

internal/delivery/circuit_breaker.go

@@ -76,12 +76,20 @@ func (cb *CircuitBreaker) Allow() bool {
 	}
 }
 
-// CooldownRemaining returns how much time is left before
+// CooldownRemaining returns how long a delivery that Allow refused
-// an open circuit transitions to half-open.
+// should wait before it is tried again. Closed, it returns zero.
+// Open, it returns what is left of the cooldown, or zero once that
+// has passed. Half-open, it returns the whole cooldown: the one
+// probe delivery is still in flight, and if it fails the circuit
+// reopens for that long.
 func (cb *CircuitBreaker) CooldownRemaining() time.Duration {
 	cb.mu.Lock()
 	defer cb.mu.Unlock()
 
+	if cb.state == CircuitHalfOpen {
+		return cb.cooldown
+	}
+
 	if cb.state != CircuitOpen {
 		return 0
 	}

internal/delivery/circuit_breaker_test.go

@@ -267,7 +267,7 @@ func TestCircuitBreaker_CooldownRemaining_ClosedReturnsZero(
 	)
 }
 
-func TestCircuitBreaker_CooldownRemaining_HalfOpenReturnsZero(
+func TestCircuitBreaker_CooldownRemaining_HalfOpenReturnsCooldown(
 	t *testing.T,
 ) {
 	t.Parallel()
@@ -282,9 +282,11 @@ func TestCircuitBreaker_CooldownRemaining_HalfOpenReturnsZero(
 
 	require.True(t, cb.Allow())
 
-	assert.Equal(t, time.Duration(0),
+	// The cooldown newShortCooldownCB gives the breaker.
+	assert.Equal(t, 50*time.Millisecond,
 		cb.CooldownRemaining(),
-		"half-open circuit should have zero cooldown remaining",
+		"a delivery refused while half-open should wait "+
+			"a whole cooldown",
 	)
 }
 

internal/delivery/client_ssrf_test.go

@@ -18,8 +18,9 @@ func newSSRFTestEngine() *delivery.Engine {
 	log := slog.New(slog.DiscardHandler)
 
 	client := &http.Client{
-		Timeout:   30 * time.Second,
+		Timeout: 30 * time.Second,
-		Transport: delivery.NewSSRFSafeTransport(),
+		Transport: delivery.NewTestGuard().
+			NewSSRFSafeTransport(),
 	}
 
 	return delivery.NewTestEngine(log, client, 1)
@@ -36,8 +37,8 @@ func TestClientForRequest_TimeoutKeepsSSRFGuard(t *testing.T) {
 	engine := newSSRFTestEngine()
 
 	blocked := []string{
-		"http://127.0.0.1/hook",
+		loopbackHookURL,
-		"http://169.254.169.254/latest/meta-data/",
+		metadataURL,
 		"http://[fe80::1]/hook",
 	}
 

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_lifecycle_test.go

@@ -2,6 +2,8 @@ package delivery_test
 
 import (
 	"context"
+	"fmt"
+	"path/filepath"
 	"testing"
 	"time"
 
@@ -269,3 +271,88 @@ func TestEngine_StopHookHonoursStopTimeout(t *testing.T) {
 
 	requireStopHookExpires(t, lc.hooks[0], "delivery engine")
 }
+
+// deliverToArchive runs one delivery to a database target through
+// the running engine and returns the webhook's archive file path.
+// The archive writer holds the file open afterwards.
+func deliverToArchive(t *testing.T, s iSetup) string {
+	t.Helper()
+
+	deliveryID, task := seedLogTask(t, s)
+	task.TargetType = database.TargetTypeDatabase
+
+	s.Engine.Notify([]delivery.Task{task})
+
+	iWaitForDelivered(t, s.WebhookDB, deliveryID)
+
+	return filepath.Join(
+		filepath.Dir(s.DBMgr.DBPath(s.WebhookID)),
+		fmt.Sprintf("archive-%s.db", s.WebhookID),
+	)
+}
+
+// TestEngine_StopHookClosesArchives is the regression test for an
+// archive split across two files by a clean stop. The engine never
+// closed its archive writers, so after a stop the archived rows
+// could sit in archive-{id}.db-wal while archive-{id}.db held no
+// table at all, and copying the .db on its own gave an empty
+// database.
+func TestEngine_StopHookClosesArchives(t *testing.T) {
+	t.Parallel()
+
+	s := newISetup(t)
+
+	lc := startEngineViaHook(t, s.Engine)
+
+	path := deliverToArchive(t, s)
+	require.FileExists(
+		t, path+"-wal",
+		"an open archive should have a -wal for the stop to remove",
+	)
+
+	require.NoError(t, lc.hooks[0].OnStop(context.Background()))
+
+	wals, err := filepath.Glob(
+		filepath.Join(filepath.Dir(path), "archive-*.db-wal"),
+	)
+	require.NoError(t, err)
+	require.Empty(
+		t, wals, "a clean stop must leave no archive -wal behind",
+	)
+
+	// With no -wal beside it, the row can only be in the .db.
+	count, err := countArchivedRows(path)
+	require.NoError(t, err)
+	require.Equal(t, int64(1), count)
+}
+
+// TestEngine_StopHookTimeoutLeavesArchivesOpen covers a stop whose
+// budget runs out while a worker is still running. The archive
+// writers are left open, as a kill would leave them: closing them
+// would wait for any write in progress, and that worker would then
+// open new writers that nothing closes.
+func TestEngine_StopHookTimeoutLeavesArchivesOpen(t *testing.T) {
+	t.Parallel()
+
+	s := newISetup(t)
+
+	lc := startEngineViaHook(t, s.Engine)
+
+	deliverToArchive(t, s)
+
+	release := make(chan struct{})
+
+	t.Cleanup(func() {
+		close(release)
+		s.Engine.EvictWebhook(s.WebhookID)
+	})
+
+	s.Engine.ExportWedgeWorker(release)
+
+	requireStopHookExpires(t, lc.hooks[0], "delivery engine")
+
+	require.True(
+		t, s.Engine.ExportArchiveHandleOpen(s.WebhookID),
+		"a stop that timed out must not close archive writers",
+	)
+}

internal/delivery/engine_test.go

@@ -3,7 +3,6 @@ package delivery_test
 import (
 	"bytes"
 	"context"
-	"database/sql"
 	"encoding/json"
 	"fmt"
 	"log/slog"
@@ -18,6 +17,7 @@ import (
 	"time"
 
 	"github.com/google/uuid"
+	"github.com/prometheus/client_golang/prometheus"
 	"github.com/stretchr/testify/assert"
 	"github.com/stretchr/testify/require"
 	"gorm.io/driver/sqlite"
@@ -25,6 +25,7 @@ import (
 	_ "modernc.org/sqlite"
 	"sneak.berlin/go/webhooker/internal/database"
 	"sneak.berlin/go/webhooker/internal/delivery"
+	"sneak.berlin/go/webhooker/internal/metrics"
 )
 
 // testContentType is the event content type used in tests.
@@ -37,11 +38,12 @@ 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() })
@@ -894,6 +896,100 @@ func TestDeliverHTTP_CircuitBreakerBlocks(t *testing.T) {
 	)
 }
 
+// recordingScheduler keeps the delay of every retry it is asked to
+// schedule, and schedules nothing.
+type recordingScheduler struct {
+	delays []time.Duration
+}
+
+func (s *recordingScheduler) ScheduleRetry(
+	_ delivery.Task, delay time.Duration,
+) {
+	s.delays = append(s.delays, delay)
+}
+
+// TestDeliverHTTP_HalfOpenBreakerDelaysQueuedTasks proves that while a
+// half-open breaker's one probe delivery is in flight, every other task
+// for the target is put back with a whole cooldown as its delay rather
+// than none, and that its status is written the first time the breaker
+// turns it away and not on each pass after that.
+func TestDeliverHTTP_HalfOpenBreakerDelaysQueuedTasks(t *testing.T) {
+	t.Parallel()
+
+	db := testWebhookDB(t)
+	e := testEngine(t, 1)
+
+	// Every write of retrying moves the retry counter, so on a registry
+	// this test owns the counter is the number of those writes.
+	reg := prometheus.NewRegistry()
+	e.ExportSetMetrics(metrics.New(reg))
+
+	targetID := uuid.New().String()
+	cb := newShortCooldownCB(t)
+	e.ExportSetCircuitBreaker(targetID, cb)
+
+	for range delivery.ExportDefaultFailureThreshold {
+		cb.RecordFailure()
+	}
+
+	time.Sleep(60 * time.Millisecond)
+
+	require.True(t, cb.Allow(), "the probe delivery should go through")
+	require.Equal(t, delivery.CircuitHalfOpen, cb.State())
+
+	cfg := newHTTPTargetConfig(
+		"http://will-not-be-called.invalid",
+	)
+	sched := &recordingScheduler{}
+
+	const queued, passes = 3, 4
+
+	for range queued {
+		event := seedEvent(t, db, `{"cb":"half-open"}`)
+		dlv := seedDelivery(
+			t, db, event.ID, targetID,
+			database.DeliveryStatusPending,
+		)
+
+		for range passes {
+			// Each pass starts from the stored row, as a retry does.
+			var row database.Delivery
+
+			require.NoError(t, db.First(
+				&row, "id = ?", dlv.ID,
+			).Error)
+
+			fix := buildHTTPFixture(
+				row, event, targetID,
+				"test-cb-half-open", cfg, 5, 1,
+			)
+
+			e.ExportDeliverHTTPWithScheduler(
+				context.TODO(), db, fix.Delivery, fix.Task, sched,
+			)
+		}
+
+		assertDeliveryStatus(t, db, dlv.ID,
+			database.DeliveryStatusRetrying,
+		)
+	}
+
+	require.Len(t, sched.delays, queued*passes)
+
+	for _, delay := range sched.delays {
+		// The cooldown newShortCooldownCB gives the breaker.
+		assert.Equal(t, 50*time.Millisecond, delay,
+			"a task turned away while half-open should wait "+
+				"a whole cooldown",
+		)
+	}
+
+	assert.InDelta(t, float64(queued),
+		mCounter(t, reg, mRetries, mTypeHTTP), 0,
+		"status should be written once per task, not once per pass",
+	)
+}
+
 func TestGetCircuitBreaker_CreatesOnDemand(t *testing.T) {
 	t.Parallel()
 
@@ -1070,6 +1166,10 @@ func TestIsForwardableHeader(t *testing.T) {
 	assert.False(t,
 		delivery.ExportIsForwardableHeader("Content-Length"),
 	)
+
+	assert.False(t,
+		delivery.ExportIsForwardableHeader("Content-Type"),
+	)
 }
 
 func TestTruncate(t *testing.T) {
@@ -1151,6 +1251,81 @@ func TestDoHTTPRequest_ForwardsHeaders(t *testing.T) {
 	)
 }
 
+// The event's stored inbound headers carry the same Content-Type the
+// receiver saved as the event's ContentType, so a delivery could send
+// it twice. It must go out exactly once, with a Content-Type configured
+// on the target winning, then the event's ContentType.
+func TestApplyRequestHeaders_SendsOneContentType(t *testing.T) {
+	t.Parallel()
+
+	cases := map[string]struct {
+		inbound    string
+		event      string
+		configured string
+		want       []string
+	}{
+		"inbound and event agree": {
+			inbound: testContentType,
+			event:   testContentType,
+			want:    []string{testContentType},
+		},
+		"inbound and event disagree": {
+			inbound: "text/plain",
+			event:   testContentType,
+			want:    []string{testContentType},
+		},
+		"event has none": {
+			inbound: testContentType,
+			want:    nil,
+		},
+		"target configures its own": {
+			inbound:    testContentType,
+			event:      testContentType,
+			configured: "application/xml",
+			want:       []string{"application/xml"},
+		},
+	}
+
+	for name, tc := range cases {
+		t.Run(name, func(t *testing.T) {
+			t.Parallel()
+
+			inbound, err := json.Marshal(map[string][]string{
+				headerContentType: {tc.inbound},
+			})
+			require.NoError(t, err)
+
+			cfg := &delivery.HTTPTargetConfig{}
+			if tc.configured != "" {
+				cfg.Headers = map[string]string{
+					headerContentType: tc.configured,
+				}
+			}
+
+			req, err := http.NewRequestWithContext(
+				context.Background(),
+				http.MethodPost,
+				"https://target.example.com/hook",
+				http.NoBody,
+			)
+			require.NoError(t, err)
+
+			delivery.ExportApplyRequestHeaders(
+				req,
+				&database.Event{
+					Headers:     string(inbound),
+					ContentType: tc.event,
+				},
+				cfg,
+			)
+
+			assert.Equal(t,
+				tc.want, req.Header.Values(headerContentType),
+			)
+		})
+	}
+}
+
 func TestProcessDelivery_RoutesToCorrectHandler(
 	t *testing.T,
 ) {

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

@@ -5,6 +5,7 @@ import (
 	"log/slog"
 	"net"
 	"net/http"
+	"net/netip"
 	"net/url"
 	"time"
 
@@ -32,6 +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.
@@ -39,6 +45,26 @@ func ExportIsBlockedIP(ip net.IP) bool {
 	return isBlockedIP(ip)
 }
 
+// NewTestGuard builds an SSRF Guard from an explicit egress
+// allowlist, without going through config. Passing no prefixes
+// yields the default guard, which blocks every private/reserved
+// range.
+func NewTestGuard(allowed ...netip.Prefix) *Guard {
+	return &Guard{allowed: allowed}
+}
+
+// ExportCheckIP exposes the guard's single decision point, so a
+// test can assert the policy both the validator and the dialer
+// inherit without needing a live destination.
+func (g *Guard) ExportCheckIP(ip net.IP) error {
+	return g.checkIP(ip)
+}
+
+// ExportAlwaysBlockedNetworks exposes alwaysBlockedNetworks.
+func ExportAlwaysBlockedNetworks() []*net.IPNet {
+	return alwaysBlockedNetworks
+}
+
 // ExportBlockedNetworks exposes blockedNetworks.
 func ExportBlockedNetworks() []*net.IPNet {
 	return blockedNetworks
@@ -75,6 +101,19 @@ func (e *Engine) ExportDeliverHTTP(
 	e.httpTarget.Deliver(ctx, webhookDB, d, task, e)
 }
 
+// ExportDeliverHTTPWithScheduler delivers via the http target, handing
+// any retry to sched instead of the engine, so a test can see the
+// delay each retry is given.
+func (e *Engine) ExportDeliverHTTPWithScheduler(
+	ctx context.Context,
+	webhookDB *gorm.DB,
+	d *database.Delivery,
+	task *Task,
+	sched Scheduler,
+) {
+	e.httpTarget.Deliver(ctx, webhookDB, d, task, sched)
+}
+
 // ExportDeliverDatabase delivers via the database target.
 func (e *Engine) ExportDeliverDatabase(
 	webhookDB *gorm.DB, d *database.Delivery,
@@ -125,6 +164,16 @@ 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,
@@ -143,6 +192,14 @@ func (e *Engine) ExportGetCircuitBreaker(
 	return e.httpTarget.getCircuitBreaker(targetID)
 }
 
+// ExportSetCircuitBreaker makes cb the http target's circuit breaker
+// for targetID, so a test can use one with a short cooldown.
+func (e *Engine) ExportSetCircuitBreaker(
+	targetID string, cb *CircuitBreaker,
+) {
+	e.httpTarget.circuitBreakers.Store(targetID, cb)
+}
+
 // ExportParseHTTPConfig exposes parseHTTPConfig.
 func (e *Engine) ExportParseHTTPConfig(
 	configJSON string,
@@ -265,6 +322,51 @@ 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)
+}
+
+// ExportFailMissingTarget exposes failMissingTarget, so a test can hand
+// it a delivery as a batch read it earlier.
+func (e *Engine) ExportFailMissingTarget(
+	webhookDB *gorm.DB,
+	webhookID string,
+	d *database.Delivery,
+) {
+	e.failMissingTarget(webhookDB, webhookID, d)
+}
+
+// ExportSendRecoveredDeliveries exposes sendRecoveredDeliveries, so a
+// test can hand it a target map that lacks a delivery's target.
+func (e *Engine) ExportSendRecoveredDeliveries(
+	ctx context.Context,
+	webhookDB *gorm.DB,
+	deliveries []database.Delivery,
+	webhookID string,
+	targetMap map[string]database.Target,
+	settled map[string]struct{},
+) {
+	e.sendRecoveredDeliveries(
+		ctx, webhookDB, deliveries, webhookID, targetMap, settled,
+	)
+}
+
 // 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 +1,495 @@
+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",
+	)
+}
+
+// TestNotifyAfterRecoveryDoesNotSendAgain is the startup race of
+// https://git.eeqj.de/sneak/webhooker/issues/299. The receiver has
+// written a delivery, restart recovery finds it pending, sends it and
+// releases it, and only then does the receiver's Notify for it arrive.
+// Nothing owns the delivery by then, so Notify takes it.
+func TestNotifyAfterRecoveryDoesNotSendAgain(t *testing.T) {
+	t.Parallel()
+
+	targetID := uuid.New().String()
+	s := fSweepSetup(t, targetID, "recovered")
+
+	event := iSeedEvent(
+		t, s.WebhookDB, s.WebhookID, `{"recovered":true}`,
+	)
+
+	d := iSeedDelivery(
+		t, s.WebhookDB, event.ID, targetID,
+		database.DeliveryStatusPending,
+	)
+
+	s.Engine.ExportStart()
+
+	defer func() {
+		require.NoError(
+			t, s.Engine.ExportStop(context.Background()),
+		)
+	}()
+
+	// Restart recovery sends the delivery and lets it go.
+	iWaitForDelivered(t, s.WebhookDB, d.ID)
+	require.Eventually(
+		t,
+		func() bool {
+			return s.Engine.ExportInflightHeld() == 0
+		},
+		5*time.Second, 20*time.Millisecond,
+	)
+
+	body := event.Body
+
+	s.Engine.Notify([]delivery.Task{{
+		DeliveryID:   d.ID,
+		EventID:      event.ID,
+		WebhookID:    s.WebhookID,
+		TargetID:     targetID,
+		TargetName:   "recovered",
+		TargetType:   database.TargetTypeLog,
+		Body:         &body,
+		EntrypointID: event.EntrypointID,
+	}})
+
+	// Notify took the delivery, and a worker releases it once it has
+	// run the task.
+	require.Eventually(
+		t,
+		func() bool {
+			return s.Engine.ExportInflightHeld() == 0
+		},
+		5*time.Second, 20*time.Millisecond,
+	)
+
+	assert.Len(
+		t, iResults(t, s.WebhookDB, d.ID), 1,
+		"the delivery was sent a second time",
+	)
+}
+
+// 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,
@@ -393,9 +412,10 @@ func TestDeliveryMetrics_BreakerBlockedIsNotAnAttempt(
 
 	s.Engine.ExportProcessRetryTask(context.TODO(), &blocked)
 
-	// The breaker refused it: rescheduled, so the retry counter
+	// The breaker refused it: rescheduled without rewriting the
-	// moved, but nothing was attempted or timed.
+	// retrying status it already had, so the retry counter did not
-	assert.InDelta(t, retriesBefore+1,
+	// move, and nothing was attempted or timed.
+	assert.InDelta(t, retriesBefore,
 		mCounter(t, reg, mRetries, mTypeHTTP), 0)
 	assert.InDelta(t, threshold,
 		mCounter(t, reg, mAttempts, mTypeHTTP), 0)

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,
 ) {
@@ -338,14 +339,18 @@ func TestRedirectPolicy_StopsAtHopCap(t *testing.T) {
 // The set the redirect policy strips is whatever the delivery path
 // actually put on the wire, so a header added to the forward set is
 // covered without a second edit. A header the event never carried
-// is not in the set, and Content-Type is deliberately excluded: it
+// is not in the set, and neither is the inbound Content-Type, because
-// describes the body, which a 307 carries across hosts.
+// it is not forwarded. Two more are deliberately excluded: a
+// Content-Type configured on the target describes the body, which a
+// 307 carries across hosts, and the inbound User-Agent every real
+// sender supplies is overwritten before the request goes out.
 func TestApplyRequestHeaders_ReportsOriginScopedNames(t *testing.T) {
 	t.Parallel()
 
 	inbound, err := json.Marshal(map[string][]string{
 		inboundHeaderName: {inboundHeaderValue},
 		"Content-Type":    {testContentType},
+		"User-Agent":      {"curl/8.7.1"},
 		"Host":            {"inbound.example.com"},
 	})
 	require.NoError(t, err)
@@ -367,6 +372,7 @@ func TestApplyRequestHeaders_ReportsOriginScopedNames(t *testing.T) {
 		&delivery.HTTPTargetConfig{
 			Headers: map[string]string{
 				probeHeaderName: probeHeaderValue,
+				"Content-Type":  testContentType,
 			},
 		},
 	)
@@ -374,7 +380,11 @@ func TestApplyRequestHeaders_ReportsOriginScopedNames(t *testing.T) {
 	assert.Equal(t,
 		[]string{probeHeaderName, inboundHeaderName}, names,
 		"both header classes are reported, and only those: "+
-			"Host is never forwarded, Content-Type and "+
+			"Host and the inbound Content-Type are never "+
-			"User-Agent are the delivery path's own",
+			"forwarded, User-Agent is the delivery path's own",
+	)
+	assert.NotContains(t, names, "Content-Type",
+		"a Content-Type configured on the target must survive "+
+			"a cross-origin 307/308 with the body it describes",
 	)
 }

internal/delivery/ssrf.go

@@ -6,8 +6,11 @@ import (
 	"fmt"
 	"net"
 	"net/http"
+	"net/netip"
 	"net/url"
 	"time"
+
+	"sneak.berlin/go/webhooker/internal/config"
 )
 
 const (
@@ -23,22 +26,86 @@ var (
 		"hostname resolved to no IP addresses",
 	)
 	errBlockedIP = errors.New(
-		"blocked private/reserved IP range",
+		"blocked private, reserved or cloud metadata address",
+	)
+	errBlockedMetadata = errors.New(
+		"blocked link-local or cloud instance metadata " +
+			"address: ALLOWED_EGRESS_CIDRS cannot open it",
 	)
 	errInvalidScheme = errors.New(
 		"only http and https are allowed",
 	)
 )
 
-// blockedNetworks contains all private/reserved IP ranges
+// blockedNetworks is the default blocklist: the private and
-// that should be blocked to prevent SSRF attacks.
+// reserved IP ranges, plus the public cloud metadata addresses,
+// that are blocked to prevent SSRF attacks. An operator can
+// permit specific blocks out of this set with
+// ALLOWED_EGRESS_CIDRS; see Guard.
 //
 //nolint:gochecknoglobals // package-level network list is appropriate here
 var blockedNetworks []*net.IPNet
 
+// alwaysBlockedNetworks are the ranges no configuration can
+// open: the link-local blocks and the cloud instance metadata
+// endpoints that live outside them. Reaching one is credential
+// or user-data theft rather than delivery to an internal
+// service, so a supplied CIDR that covers such an address still
+// leaves it blocked.
+//
+// Inclusion criterion — an address belongs here only if BOTH
+// hold, and every entry below satisfies both:
+//
+//  1. It is a fixed address assigned by the provider, or a
+//     range reserved by IANA — never one the operator chose.
+//     That is what makes a host route free: it cannot collide
+//     with anything the operator runs.
+//  2. Reaching it discloses credentials, or user data or
+//     bootstrap material — something granting onward access, or
+//     not cheaply rotated.
+//
+// Both halves are load-bearing, so use them to refuse a
+// candidate and say why. An endpoint disclosing only the
+// operator's own inventory (instance id, region, disks, NICs)
+// fails (2): letting a delivery target reach the operator's own
+// infrastructure is the feature ALLOWED_EGRESS_CIDRS exists to
+// provide. But (2) is not "IAM credentials only" either —
+// fd00:42::42 serves /user_data and /conf rather than tokens,
+// and user data routinely carries bootstrap secrets. An address
+// stays out if it fails (1) however well it clears (2): a host
+// route inside a block operators really assign from, such as
+// 10.0.0.0/8, can collide with a real internal service and
+// forfeits the justification in (1).
+//
+// A publicly routable unicast address does not belong here even
+// when it clears both halves. Nothing in this list can be
+// reopened, so putting a public address here leaves the operator
+// no escape hatch at all — the condition ALLOWED_EGRESS_CIDRS
+// exists to remove. Default-block it in blockedNetworks instead,
+// which an allowlist can override.
+//
+// This is a criterion, not an enumeration of every metadata
+// address in existence.
+//
+// Every entry is either already in blockedNetworks — this list is
+// what makes it unconditional — or an alternate encoding of
+// 169.254.169.254 that Contains does not match against
+// 169.254.0.0/16. Every entry outside the link-local blocks is a
+// /32 or /128 host route, so blocking it costs an operator
+// nothing else on the surrounding network.
+//
+// Derive membership from the address, never from the vendor's
+// prose. Several providers call these endpoints "link-local" or
+// even "localhost" in their own documentation while the address
+// is a ULA outside fe80::/10, so a set derived from the docs
+// comes out wrong.
+//
+//nolint:gochecknoglobals // package-level network list is appropriate here
+var alwaysBlockedNetworks []*net.IPNet
+
 //nolint:gochecknoinits // init is the idiomatic way to parse CIDRs once at startup
 func init() {
-	cidrs := []string{
+	blockedNetworks = mustParseCIDRs([]string{
 		"127.0.0.0/8",
 		"10.0.0.0/8",
 		"172.16.0.0/12",
@@ -56,7 +123,74 @@ func init() {
 		"::1/128",
 		"fc00::/7",
 		"fe80::/10",
-	}
+		// Azure WireServer, a public address that serves VM credentials.
+		"168.63.129.16/32",
+	})
+
+	// Every entry is named. The set must not grow or shrink
+	// without a matching change to
+	// TestAlwaysBlockedNetworks_PinnedSet.
+	//
+	// The IPv4-mapped form ::ffff:169.254.169.254 needs no
+	// entry: net.IPNet.Contains normalises it via To4() before
+	// comparing, so 169.254.0.0/16 already matches it. To4()
+	// does not normalise the IPv4-compatible or NAT64 forms,
+	// which is why those are listed separately.
+	alwaysBlockedNetworks = mustParseCIDRs([]string{
+		// IPv4 link-local, carrying the 169.254.169.254
+		// metadata service used by AWS, Azure, DigitalOcean,
+		// Hetzner, OpenStack and others. Not Alibaba, which uses
+		// 100.100.100.200 below exclusively.
+		"169.254.0.0/16",
+		// IPv6 link-local, its IPv6 counterpart.
+		"fe80::/10",
+
+		// IPv6 metadata endpoints in ULA space. Each is a host
+		// route, and fd00::/8 is an ordinary block for an
+		// operator to allowlist, so without these entries that
+		// one allowlist line hands out cloud credentials on
+		// every provider below.
+		//
+		// AWS IPv6 IMDS.
+		"fd00:ec2::254/128",
+		// AWS EKS Pod Identity Agent, which issues pod identity
+		// credentials. A second AWS endpoint, distinct from
+		// IMDS above. AWS's own docs call it "localhost".
+		"fd00:ec2::23/128",
+		// GCP metadata server for IPv6-only instances.
+		"fd20:ce::254/128",
+		// Oracle OCI IMDS, serving /opc/v2 instance principals.
+		"fd00:c1::a9fe:a9fe/128",
+		// Scaleway metadata, serving /user_data and /conf.
+		"fd00:42::42/128",
+		// Linode/Akamai metadata. Akamai's docs call it
+		// "link-local"; it is not.
+		"fd00:a9fe:a9fe::1/128",
+
+		// IPv4 metadata endpoints outside link-local.
+		//
+		// Alibaba Cloud metadata. It sits in CGNAT
+		// 100.64.0.0/10, which Tailscale also uses, so an
+		// operator allowlisting a Tailscale peer's range would
+		// otherwise reopen it.
+		"100.100.100.200/32",
+		// Oracle Cloud Classic metadata. Inside the blocked
+		// 192.0.0.0/24, so this entry is what stops an
+		// allowlist from opening it.
+		"192.0.0.192/32",
+
+		// 169.254.169.254 as an IPv4-compatible IPv6 address.
+		"::a9fe:a9fe/128",
+		// 169.254.169.254 behind the NAT64 well-known prefix.
+		"64:ff9b::a9fe:a9fe/128",
+	})
+}
+
+// mustParseCIDRs parses a list of CIDR literals, panicking on a
+// bad one. The inputs are compile-time constants, so a failure
+// is a programming error rather than a runtime condition.
+func mustParseCIDRs(cidrs []string) []*net.IPNet {
+	networks := make([]*net.IPNet, 0, len(cidrs))
 
 	for _, cidr := range cidrs {
 		_, network, err := net.ParseCIDR(cidr)
@@ -67,16 +201,15 @@ func init() {
 			))
 		}
 
-		blockedNetworks = append(
+		networks = append(networks, network)
-			blockedNetworks, network,
-		)
 	}
+
+	return networks
 }
 
-// isBlockedIP checks whether an IP address falls within
+// matchesAny reports whether ip falls inside any of networks.
-// any blocked private/reserved network range.
+func matchesAny(networks []*net.IPNet, ip net.IP) bool {
-func isBlockedIP(ip net.IP) bool {
+	for _, network := range networks {
-	for _, network := range blockedNetworks {
 		if network.Contains(ip) {
 			return true
 		}
@@ -85,9 +218,40 @@ func isBlockedIP(ip net.IP) bool {
 	return false
 }
 
+// isBlockedIP checks whether an IP address falls within
+// the default blocklist, before any operator allowlist is
+// considered.
+func isBlockedIP(ip net.IP) bool {
+	return matchesAny(blockedNetworks, ip)
+}
+
+// Guard makes every SSRF decision in the process.
+//
+// It holds the operator's ALLOWED_EGRESS_CIDRS allowlist and
+// applies it in exactly one place, checkIP, which both the
+// target-creation validator (ValidateTargetURL) and the delivery
+// dialer call. Routing both through the same function is the
+// point: when the two paths decided separately they drifted and
+// disagreed, which is what made a target creatable but
+// undeliverable.
+//
+// The guard is always on. The allowlist only ever adds specific
+// networks to what the default blocklist refuses, and no
+// configuration turns the guard off wholesale.
+type Guard struct {
+	// allowed is the operator's ALLOWED_EGRESS_CIDRS. Empty
+	// (the default) means the default blocklist stands as-is.
+	allowed []netip.Prefix
+}
+
+// NewGuard builds the process-wide SSRF guard from configuration.
+func NewGuard(cfg *config.Config) *Guard {
+	return &Guard{allowed: cfg.AllowedEgressCIDRs}
+}
+
 // ValidateTargetURL checks that an HTTP delivery target
 // URL is safe from SSRF attacks.
-func ValidateTargetURL(
+func (g *Guard) ValidateTargetURL(
 	ctx context.Context, targetURL string,
 ) error {
 	parsed, err := url.Parse(targetURL)
@@ -111,36 +275,79 @@ func ValidateTargetURL(
 	}
 
 	if ip := net.ParseIP(host); ip != nil {
-		return checkBlockedIP(ip)
+		return g.checkIP(ip)
 	}
 
-	return validateHostname(ctx, host)
+	return g.validateHostname(ctx, host)
 }
 
-func validateScheme(scheme string) error {
+// NewSSRFSafeTransport creates an http.Transport with a
-	if scheme != "http" && scheme != "https" {
+// custom DialContext that refuses connections to any address
+// this guard blocks. It resolves and checks at dial time, so a
+// name that passed validation but now answers with a blocked
+// address (DNS rebinding) is still refused.
+func (g *Guard) NewSSRFSafeTransport() *http.Transport {
+	return &http.Transport{
+		DialContext: g.ssrfDialContext,
+	}
+}
+
+// allows reports whether ip falls inside the operator's
+// configured egress allowlist.
+func (g *Guard) allows(ip net.IP) bool {
+	if len(g.allowed) == 0 {
+		return false
+	}
+
+	addr, ok := netip.AddrFromSlice(ip)
+	if !ok {
+		return false
+	}
+
+	// Config unmaps every parsed prefix, so an IPv4-mapped
+	// address has to be unmapped too or it would never match.
+	addr = addr.Unmap()
+
+	for _, prefix := range g.allowed {
+		if prefix.Contains(addr) {
+			return true
+		}
+	}
+
+	return false
+}
+
+// checkIP is the single point at which SSRF policy is decided.
+//
+// The order is the policy:
+//
+//  1. alwaysBlockedNetworks is refused before the allowlist is
+//     consulted, so no configured CIDR reaches link-local or a
+//     cloud metadata endpoint at a non-public address.
+//  2. The allowlist is consulted next, so a listed private
+//     network becomes reachable.
+//  3. Everything else keeps the default blocklist's answer.
+func (g *Guard) checkIP(ip net.IP) error {
+	if matchesAny(alwaysBlockedNetworks, ip) {
 		return fmt.Errorf(
-			"unsupported URL scheme %q: %w",
+			"target IP %s: %w", ip, errBlockedMetadata,
-			scheme, errInvalidScheme,
 		)
 	}
 
-	return nil
+	if g.allows(ip) {
-}
+		return nil
+	}
 
-func checkBlockedIP(ip net.IP) error {
 	if isBlockedIP(ip) {
 		return fmt.Errorf(
-			"target IP %s is in a blocked "+
+			"target IP %s: %w", ip, errBlockedIP,
-				"private/reserved range: %w",
-			ip, errBlockedIP,
 		)
 	}
 
 	return nil
 }
 
-func validateHostname(
+func (g *Guard) validateHostname(
 	ctx context.Context, host string,
 ) error {
 	dnsCtx, cancel := context.WithTimeout(
@@ -165,11 +372,11 @@ func validateHostname(
 	}
 
 	for _, ipAddr := range ips {
-		if isBlockedIP(ipAddr.IP) {
+		err = g.checkIP(ipAddr.IP)
+		if err != nil {
 			return fmt.Errorf(
-				"hostname %q resolves to blocked "+
+				"hostname %q resolves to a blocked address: %w",
-					"IP %s: %w",
+				host, err,
-				host, ipAddr.IP, errBlockedIP,
 			)
 		}
 	}
@@ -177,16 +384,7 @@ func validateHostname(
 	return nil
 }
 
-// NewSSRFSafeTransport creates an http.Transport with a
+func (g *Guard) ssrfDialContext(
-// custom DialContext that blocks connections to
-// private/reserved IP addresses.
-func NewSSRFSafeTransport() *http.Transport {
-	return &http.Transport{
-		DialContext: ssrfDialContext,
-	}
-}
-
-func ssrfDialContext(
 	ctx context.Context,
 	network, addr string,
 ) (net.Conn, error) {
@@ -209,11 +407,11 @@ func ssrfDialContext(
 	}
 
 	for _, ipAddr := range ips {
-		if isBlockedIP(ipAddr.IP) {
+		err = g.checkIP(ipAddr.IP)
+		if err != nil {
 			return nil, fmt.Errorf(
-				"ssrf: connection to %s (%s) "+
+				"ssrf: connection to %s blocked: %w",
-					"blocked: %w",
+				host, err,
-				host, ipAddr.IP, errBlockedIP,
 			)
 		}
 	}
@@ -225,3 +423,14 @@ func ssrfDialContext(
 		net.JoinHostPort(ips[0].IP.String(), port),
 	)
 }
+
+func validateScheme(scheme string) error {
+	if scheme != "http" && scheme != "https" {
+		return fmt.Errorf(
+			"unsupported URL scheme %q: %w",
+			scheme, errInvalidScheme,
+		)
+	}
+
+	return nil
+}

internal/delivery/ssrf_allowlist_test.go

@@ -0,0 +1,597 @@
+package delivery_test
+
+import (
+	"context"
+	"net"
+	"net/http"
+	"net/http/httptest"
+	"net/netip"
+	"net/url"
+	"testing"
+	"time"
+
+	"github.com/stretchr/testify/assert"
+	"github.com/stretchr/testify/require"
+	"sneak.berlin/go/webhooker/internal/delivery"
+)
+
+// Addresses the SSRF tests in this package share.
+const (
+	// metadataIP is the cloud instance metadata address, and
+	// metadataURL an endpoint on it. The guard must never reach
+	// either, whatever an operator lists.
+	metadataIP  = "169.254.169.254"
+	metadataURL = "http://" + metadataIP + "/latest/meta-data/"
+
+	// loopbackHookURL is a target on this host: blocked by
+	// default, reachable only once an operator allowlists
+	// loopback.
+	loopbackHookURL = "http://127.0.0.1/hook"
+
+	// publicIP is an ordinary public address, which the guard
+	// permits with or without an allowlist.
+	publicIP = "93.184.216.34"
+
+	// allowAllIPv4 and allowAllIPv6 are the widest allowlist
+	// entries expressible: the whole internet, in each family.
+	// Nothing unconditionally blocked may be reachable under
+	// them.
+	allowAllIPv4 = "0.0.0.0/0"
+	allowAllIPv6 = "::/0"
+
+	// allowAllULA is the ordinary ULA block an operator lists to
+	// reach their own IPv6 network. Several providers park a
+	// metadata endpoint inside it.
+	allowAllULA = "fd00::/8"
+
+	// metadataRefusalClause is the part of the refusal that only
+	// alwaysBlockedNetworks produces. Asserting it, rather than
+	// the bare word "blocked", is what proves the unconditional
+	// set did the refusing and not the default blocklist.
+	metadataRefusalClause = "ALLOWED_EGRESS_CIDRS cannot open it"
+)
+
+// TestGuardAllowlist_PermittedCIDRDelivers proves the escape
+// hatch actually works end to end: with 127.0.0.0/8 allowed, the
+// guard's own transport connects to a loopback server and gets a
+// response back. The default guard, given the identical URL,
+// refuses it — so the delivery succeeds because of the allowlist
+// and nothing else.
+func TestGuardAllowlist_PermittedCIDRDelivers(t *testing.T) {
+	t.Parallel()
+
+	srv := httptest.NewServer(http.HandlerFunc(
+		func(w http.ResponseWriter, _ *http.Request) {
+			w.WriteHeader(http.StatusNoContent)
+		},
+	))
+	t.Cleanup(srv.Close)
+
+	// httptest listens on loopback, which the default blocklist
+	// covers: exactly the "forward to a service on this host"
+	// case the allowlist exists for.
+	requireLoopback(t, srv.URL)
+
+	guard := delivery.NewTestGuard(
+		netip.MustParsePrefix("127.0.0.0/8"),
+	)
+
+	require.NoError(t,
+		guard.ValidateTargetURL(context.Background(), srv.URL),
+		"an allowlisted loopback target must pass validation",
+	)
+
+	client := &http.Client{
+		Timeout:   5 * time.Second,
+		Transport: guard.NewSSRFSafeTransport(),
+	}
+
+	req, err := http.NewRequestWithContext(
+		context.Background(), http.MethodPost, srv.URL, nil,
+	)
+	require.NoError(t, err)
+
+	resp, err := client.Do(req)
+	require.NoError(t,
+		err, "an allowlisted loopback target must be deliverable",
+	)
+
+	defer func() { _ = resp.Body.Close() }()
+
+	assert.Equal(t, http.StatusNoContent, resp.StatusCode)
+
+	// The same URL through the default guard must still fail, or
+	// this test would pass without the allowlist doing anything.
+	assert.Error(t,
+		delivery.NewTestGuard().ValidateTargetURL(
+			context.Background(), srv.URL,
+		),
+		"without the allowlist the same target must be refused",
+	)
+}
+
+// TestGuardAllowlist_UnlistedPrivateStillRefused proves the
+// allowlist grants only what it names. A guard that opens one
+// private block must keep refusing every other one, at both the
+// validation and the delivery entry point.
+func TestGuardAllowlist_UnlistedPrivateStillRefused(t *testing.T) {
+	t.Parallel()
+
+	// Only 10.1.0.0/16 is open — a narrow block inside a much
+	// wider private range, so the test can tell "permits the
+	// listed block" from "permits anything private".
+	guard := delivery.NewTestGuard(
+		netip.MustParsePrefix("10.1.0.0/16"),
+	)
+
+	refused := []string{
+		"http://192.168.1.10/hook",
+		"http://172.16.0.1/hook",
+		loopbackHookURL,
+		"http://[fc00::1]/hook",
+		"http://100.64.0.1/hook",
+		// Private, adjacent to the allowed block, outside it.
+		"http://10.2.0.1/hook",
+	}
+
+	for _, target := range refused {
+		t.Run(target, func(t *testing.T) {
+			t.Parallel()
+
+			err := guard.ValidateTargetURL(
+				context.Background(), target,
+			)
+			require.Error(t,
+				err, "%s is not allowlisted and must be refused",
+				target,
+			)
+			assert.Contains(t, err.Error(), "blocked")
+
+			assertDialRefused(t, guard, target)
+		})
+	}
+
+	// The block that is listed must in fact be permitted, so the
+	// refusals above are selective rather than a guard that
+	// ignores its allowlist entirely.
+	assert.NoError(t,
+		guard.ValidateTargetURL(
+			context.Background(), "http://10.1.2.3/hook",
+		),
+		"the allowlisted block must be permitted",
+	)
+}
+
+// TestGuardAllowlist_MetadataAlwaysRefused is the load-bearing
+// case: cloud instance metadata endpoints are credential theft
+// rather than delivery to an internal service, so no allowlist
+// reaches one. Every guard below names a CIDR that covers its
+// target — including 0.0.0.0/0, ::/0, and the ordinary ULA and
+// CGNAT blocks an operator would really list — and the address
+// must stay refused anyway, on both the validation and the
+// delivery path.
+func TestGuardAllowlist_MetadataAlwaysRefused(t *testing.T) {
+	t.Parallel()
+
+	for _, tt := range metadataAlwaysRefusedCases() {
+		t.Run(tt.name, func(t *testing.T) {
+			t.Parallel()
+
+			guard := delivery.NewTestGuard(
+				netip.MustParsePrefix(tt.allow),
+			)
+
+			err := guard.ValidateTargetURL(
+				context.Background(), tt.target,
+			)
+			require.Error(t,
+				err,
+				"%s must stay blocked even though %s covers it",
+				tt.target, tt.allow,
+			)
+			assert.Contains(t,
+				err.Error(),
+				metadataRefusalClause,
+				"the refusal must say why it cannot be opened",
+			)
+
+			// The metadata clause, not just "blocked": that is
+			// what distinguishes the unconditional set from the
+			// ordinary blocklist.
+			assertDialRefusedWith(
+				t, guard, tt.target, metadataRefusalClause,
+			)
+		})
+	}
+}
+
+// metadataAlwaysRefusedCase is one (allowlist, target) pair that
+// must be refused: allow covers target, and target must stay
+// blocked regardless.
+type metadataAlwaysRefusedCase struct {
+	name   string
+	allow  string
+	target string
+}
+
+// metadataAlwaysRefusedCases enumerates every unconditionally
+// blocked address together with an allowlist entry that would
+// otherwise reach it. Split by family of address only to stay
+// under the function-length limit.
+func metadataAlwaysRefusedCases() []metadataAlwaysRefusedCase {
+	cases := linkLocalRefusedCases()
+	cases = append(cases, ulaMetadataRefusedCases()...)
+	cases = append(cases, ipv4MetadataRefusedCases()...)
+
+	return append(cases, encodedMetadataRefusedCases()...)
+}
+
+// linkLocalRefusedCases covers the link-local blocks, including
+// an operator naming the metadata address outright.
+func linkLocalRefusedCases() []metadataAlwaysRefusedCase {
+	return []metadataAlwaysRefusedCase{
+		{
+			name:   "exact metadata host",
+			allow:  "169.254.169.254/32",
+			target: metadataURL,
+		},
+		{
+			name:   "whole link-local block",
+			allow:  "169.254.0.0/16",
+			target: metadataURL,
+		},
+		{
+			name:   "supernet covering link-local",
+			allow:  "169.0.0.0/8",
+			target: metadataURL,
+		},
+		{
+			name:   "the entire IPv4 internet",
+			allow:  allowAllIPv4,
+			target: metadataURL,
+		},
+		{
+			name:   "other link-local address",
+			allow:  allowAllIPv4,
+			target: "http://169.254.1.1/",
+		},
+		{
+			name:   "IPv6 link-local",
+			allow:  allowAllIPv6,
+			target: "http://[fe80::1]/",
+		},
+	}
+}
+
+// ulaMetadataRefusedCases covers the metadata endpoints parked
+// in ULA space. Every one is opened by the single ordinary
+// allowlist entry fd00::/8, which is the whole reason they need
+// their own /128 host routes: fe80::/10 does not cover a ULA,
+// whatever the vendor's documentation calls the address.
+func ulaMetadataRefusedCases() []metadataAlwaysRefusedCase {
+	return []metadataAlwaysRefusedCase{
+		{
+			name:   "AWS IPv6 IMDS under an allowlisted ULA block",
+			allow:  allowAllULA,
+			target: "http://[fd00:ec2::254]/latest/meta-data/",
+		},
+		{
+			// A second AWS credential endpoint, distinct from
+			// IMDS. AWS's own docs call this one "localhost".
+			name:   "AWS EKS Pod Identity under an allowlisted ULA block",
+			allow:  allowAllULA,
+			target: "http://[fd00:ec2::23]/v1/credentials",
+		},
+		{
+			name:   "GCP IPv6 metadata under an allowlisted ULA block",
+			allow:  allowAllULA,
+			target: "http://[fd20:ce::254]/computeMetadata/v1/",
+		},
+		{
+			name:   "Oracle OCI IPv6 IMDS under an allowlisted ULA block",
+			allow:  allowAllULA,
+			target: "http://[fd00:c1::a9fe:a9fe]/opc/v2/instance/",
+		},
+		{
+			name:   "Scaleway IPv6 metadata under an allowlisted ULA block",
+			allow:  allowAllULA,
+			target: "http://[fd00:42::42]/conf",
+		},
+		{
+			// Akamai's docs call this "link-local"; it is a ULA,
+			// so fe80::/10 does not cover it.
+			name:   "Linode IPv6 metadata under an allowlisted ULA block",
+			allow:  allowAllULA,
+			target: "http://[fd00:a9fe:a9fe::1]/v1/instance",
+		},
+	}
+}
+
+// ipv4MetadataRefusedCases covers the IPv4 metadata endpoints
+// that sit outside link-local: one in CGNAT and one in the
+// blocked 192.0.0.0/24, each reachable only through an allowlist
+// that this set overrides.
+func ipv4MetadataRefusedCases() []metadataAlwaysRefusedCase {
+	return []metadataAlwaysRefusedCase{
+		{
+			// Tailscale uses 100.64.0.0/10, so an operator
+			// forwarding to a Tailscale peer lists exactly this.
+			name:   "Alibaba metadata under allowlisted CGNAT",
+			allow:  "100.64.0.0/10",
+			target: "http://100.100.100.200/latest/meta-data/",
+		},
+		{
+			// Inside the already-blocked 192.0.0.0/24, so only
+			// an allowlist can reach it — and must not.
+			name:   "Oracle Cloud Classic metadata under 0.0.0.0/0",
+			allow:  allowAllIPv4,
+			target: "http://192.0.0.192/latest/meta-data/",
+		},
+	}
+}
+
+// encodedMetadataRefusedCases covers the alternate IPv6
+// encodings of 169.254.169.254.
+func encodedMetadataRefusedCases() []metadataAlwaysRefusedCase {
+	return []metadataAlwaysRefusedCase{
+		{
+			// To4() does not normalise the IPv4-compatible form,
+			// so this needs its own always-blocked entry.
+			name:   "IPv4-compatible IPv6 form of the metadata IP",
+			allow:  allowAllIPv6,
+			target: "http://[::a9fe:a9fe]/latest/meta-data/",
+		},
+		{
+			// Nor the NAT64 well-known prefix form.
+			name:   "NAT64 form of the metadata IP",
+			allow:  allowAllIPv6,
+			target: "http://[64:ff9b::a9fe:a9fe]/latest/meta-data/",
+		},
+		{
+			// Already refused before this change: IPNet.Contains
+			// calls To4() first, so the mapped form matches
+			// 169.254.0.0/16. Pinned so it cannot regress.
+			//
+			// Allowed under 0.0.0.0/0 rather than ::/0: allows()
+			// unmaps before matching, so ::/0 would not cover the
+			// unmapped v4 address and the case would not prove
+			// the allowlist was overridden.
+			name:   "IPv4-mapped IPv6 form of the metadata IP",
+			allow:  allowAllIPv4,
+			target: "http://[::ffff:169.254.169.254]/latest/meta-data/",
+		},
+	}
+}
+
+// TestGuardAllowlist_PublicUnaffected asserts the allowlist does
+// not narrow anything: public addresses were reachable before it
+// existed and stay reachable, whether or not a list is set.
+func TestGuardAllowlist_PublicUnaffected(t *testing.T) {
+	t.Parallel()
+
+	guards := map[string]*delivery.Guard{
+		"default": delivery.NewTestGuard(),
+		"with allowlist": delivery.NewTestGuard(
+			netip.MustParsePrefix("10.0.0.0/8"),
+		),
+	}
+
+	for name, guard := range guards {
+		t.Run(name, func(t *testing.T) {
+			t.Parallel()
+
+			assert.NoError(t,
+				guard.ValidateTargetURL(
+					context.Background(),
+					"http://"+publicIP+"/webhook",
+				),
+			)
+		})
+	}
+}
+
+// TestGuardAllowlist_AzureWireServerReopenable covers Azure's
+// WireServer, a public address that serves VM credentials. The
+// default guard refuses it, but because it is public it sits in
+// the default blocklist rather than the unconditional set, so an
+// operator who lists it can reach it.
+func TestGuardAllowlist_AzureWireServerReopenable(t *testing.T) {
+	t.Parallel()
+
+	const wireServerIP = "168.63.129.16"
+
+	target := "http://" + wireServerIP + "/?comp=versions"
+
+	defaultGuard := delivery.NewTestGuard()
+
+	err := defaultGuard.ValidateTargetURL(context.Background(), target)
+	require.Error(t, err,
+		"WireServer must be refused with no allowlist set",
+	)
+	assert.NotContains(t, err.Error(), metadataRefusalClause,
+		"WireServer must be refused by the default blocklist, "+
+			"which an allowlist can override",
+	)
+
+	assertDialRefused(t, defaultGuard, target)
+
+	listed := delivery.NewTestGuard(
+		netip.MustParsePrefix(wireServerIP + "/32"),
+	)
+
+	assert.NoError(t,
+		listed.ValidateTargetURL(context.Background(), target),
+		"an operator who lists WireServer must be able to reach it",
+	)
+}
+
+// TestGuardCheckIP_BothPathsShareOneDecision asserts that the
+// validator and the dialer are not two policies that happen to
+// agree: both are defined in terms of checkIP, so the exported
+// decision function is the whole answer for a given address.
+func TestGuardCheckIP_BothPathsShareOneDecision(t *testing.T) {
+	t.Parallel()
+
+	guard := delivery.NewTestGuard(
+		netip.MustParsePrefix("10.0.0.0/8"),
+	)
+
+	tests := []struct {
+		ip      string
+		allowed bool
+	}{
+		{"10.1.2.3", true},
+		{publicIP, true},
+		{"192.168.1.1", false},
+		{"127.0.0.1", false},
+		{metadataIP, false},
+	}
+
+	for _, tt := range tests {
+		t.Run(tt.ip, func(t *testing.T) {
+			t.Parallel()
+
+			ip := net.ParseIP(tt.ip)
+			require.NotNil(t, ip)
+
+			decision := guard.ExportCheckIP(ip)
+
+			validation := guard.ValidateTargetURL(
+				context.Background(), "http://"+hostFor(tt.ip)+"/x",
+			)
+
+			if tt.allowed {
+				require.NoError(t, decision)
+				require.NoError(t, validation)
+
+				return
+			}
+
+			require.Error(t, decision)
+			require.Error(t, validation,
+				"validation must refuse what checkIP refuses",
+			)
+		})
+	}
+}
+
+// TestAlwaysBlockedNetworks_PinnedSet pins the unconditional set
+// exactly, so it cannot quietly grow or shrink.
+//
+// It stays deliberately small. Everything else in the default
+// blocklist is an operator's own network and must remain
+// openable, or the escape hatch would not work — which is why
+// the metadata endpoints outside the link-local range are host
+// routes rather than the blocks that contain them.
+func TestAlwaysBlockedNetworks_PinnedSet(t *testing.T) {
+	t.Parallel()
+
+	nets := delivery.ExportAlwaysBlockedNetworks()
+
+	got := make([]string, 0, len(nets))
+	for _, n := range nets {
+		got = append(got, n.String())
+	}
+
+	want := []string{
+		// IPv4 link-local: the 169.254.169.254 metadata
+		// service on AWS, Azure and others.
+		"169.254.0.0/16",
+		// IPv6 link-local.
+		"fe80::/10",
+		// AWS IPv6 IMDS, inside the ULA space an operator may
+		// legitimately allowlist.
+		"fd00:ec2::254/128",
+		// AWS EKS Pod Identity Agent, likewise ULA.
+		"fd00:ec2::23/128",
+		// GCP metadata for IPv6-only instances, likewise ULA.
+		"fd20:ce::254/128",
+		// Oracle OCI IMDS over IPv6, likewise ULA.
+		"fd00:c1::a9fe:a9fe/128",
+		// Scaleway metadata over IPv6, likewise ULA.
+		"fd00:42::42/128",
+		// Linode/Akamai metadata over IPv6, likewise ULA.
+		"fd00:a9fe:a9fe::1/128",
+		// Alibaba Cloud metadata, inside CGNAT.
+		"100.100.100.200/32",
+		// Oracle Cloud Classic metadata, inside the blocked
+		// 192.0.0.0/24.
+		"192.0.0.192/32",
+		// 169.254.169.254 as an IPv4-compatible IPv6 address.
+		"::a9fe:a9fe/128",
+		// 169.254.169.254 behind the NAT64 well-known prefix.
+		"64:ff9b::a9fe:a9fe/128",
+	}
+
+	assert.Equal(t, want, got)
+}
+
+// requireLoopback fails the test unless rawURL's host is a
+// loopback address, so the allowlist test cannot silently stop
+// exercising a blocked range.
+func requireLoopback(t *testing.T, rawURL string) {
+	t.Helper()
+
+	parsed, err := url.Parse(rawURL)
+	require.NoError(t, err)
+
+	ip := net.ParseIP(parsed.Hostname())
+	require.NotNil(t, ip, "test server host must be an IP literal")
+	require.True(t, ip.IsLoopback(),
+		"test server must listen on loopback, got %s", ip,
+	)
+}
+
+// assertDialRefused asserts the guard's transport refuses to
+// connect to target, which is the delivery-time half of the
+// policy. It never reaches the network: the guard checks the
+// resolved address before dialling.
+func assertDialRefused(
+	t *testing.T, guard *delivery.Guard, target string,
+) {
+	t.Helper()
+
+	assertDialRefusedWith(t, guard, target, "blocked")
+}
+
+// assertDialRefusedWith is assertDialRefused with the refusal
+// text pinned. Callers testing the unconditional set pass
+// metadataRefusalClause so the subtest cannot pass on an
+// ordinary blocklist refusal instead.
+func assertDialRefusedWith(
+	t *testing.T, guard *delivery.Guard, target, clause string,
+) {
+	t.Helper()
+
+	client := &http.Client{
+		Timeout:   5 * time.Second,
+		Transport: guard.NewSSRFSafeTransport(),
+	}
+
+	req, err := http.NewRequestWithContext(
+		context.Background(), http.MethodPost, target, nil,
+	)
+	require.NoError(t, err)
+
+	resp, err := client.Do(req)
+	if resp != nil {
+		_ = resp.Body.Close()
+	}
+
+	require.Error(t, err,
+		"delivery to %s must be refused by the dialer", target,
+	)
+	assert.Contains(t, err.Error(), clause,
+		"the refusal must come from the SSRF guard",
+	)
+}
+
+// hostFor renders an IP as it appears in a URL host, bracketing
+// IPv6 literals.
+func hostFor(ip string) string {
+	if net.ParseIP(ip).To4() == nil {
+		return "[" + ip + "]"
+	}
+
+	return ip
+}

internal/delivery/ssrf_test.go

@@ -31,10 +31,10 @@ func TestIsBlockedIP_PrivateRanges(t *testing.T) {
 		{"192.168.0.1", "192.168.0.1", true},
 		{"192.168.255.255", "192.168.255.255", true},
 		{"169.254.0.1", "169.254.0.1", true},
-		{"169.254.169.254", "169.254.169.254", true},
+		{metadataIP, metadataIP, true},
 		{"8.8.8.8", "8.8.8.8", false},
 		{"1.1.1.1", "1.1.1.1", false},
-		{"93.184.216.34", "93.184.216.34", false},
+		{publicIP, publicIP, false},
 		{"::1", "::1", true},
 		{"fd00::1", "fd00::1", true},
 		{"fc00::1", "fc00::1", true},
@@ -72,12 +72,12 @@ func TestValidateTargetURL_Blocked(t *testing.T) {
 	t.Parallel()
 
 	blockedURLs := []string{
-		"http://127.0.0.1/hook",
+		loopbackHookURL,
 		"http://127.0.0.1:8080/hook",
 		"https://10.0.0.1/hook",
 		"http://192.168.1.1/webhook",
 		"http://172.16.0.1/api",
-		"http://169.254.169.254/latest/meta-data/",
+		metadataURL,
 		"http://[::1]/hook",
 		"http://[fc00::1]/hook",
 		"http://[fe80::1]/hook",
@@ -88,7 +88,7 @@ func TestValidateTargetURL_Blocked(t *testing.T) {
 		t.Run(u, func(t *testing.T) {
 			t.Parallel()
 
-			err := delivery.ValidateTargetURL(
+			err := delivery.NewTestGuard().ValidateTargetURL(
 				context.Background(), u,
 			)
 
@@ -112,7 +112,7 @@ func TestValidateTargetURL_Allowed(t *testing.T) {
 		t.Run(u, func(t *testing.T) {
 			t.Parallel()
 
-			err := delivery.ValidateTargetURL(
+			err := delivery.NewTestGuard().ValidateTargetURL(
 				context.Background(), u,
 			)
 
@@ -126,7 +126,7 @@ func TestValidateTargetURL_Allowed(t *testing.T) {
 func TestValidateTargetURL_InvalidScheme(t *testing.T) {
 	t.Parallel()
 
-	err := delivery.ValidateTargetURL(
+	err := delivery.NewTestGuard().ValidateTargetURL(
 		context.Background(), "ftp://example.com/hook",
 	)
 
@@ -140,7 +140,7 @@ func TestValidateTargetURL_InvalidScheme(t *testing.T) {
 func TestValidateTargetURL_EmptyHost(t *testing.T) {
 	t.Parallel()
 
-	err := delivery.ValidateTargetURL(
+	err := delivery.NewTestGuard().ValidateTargetURL(
 		context.Background(), "http:///path",
 	)
 
@@ -150,7 +150,7 @@ func TestValidateTargetURL_EmptyHost(t *testing.T) {
 func TestValidateTargetURL_InvalidURL(t *testing.T) {
 	t.Parallel()
 
-	err := delivery.ValidateTargetURL(
+	err := delivery.NewTestGuard().ValidateTargetURL(
 		context.Background(), "://invalid",
 	)
 

internal/delivery/target_config_view.go

@@ -23,21 +23,51 @@ type ConfigField struct {
 	Value string
 }
 
+// deletedNameSuffix marks the name of a target that no longer
+// exists. Deletes are soft and delivery history outlives the
+// target, so the event log shows names of targets that are gone;
+// an operator reading one needs to know it cannot be delivered
+// to, replayed to, or configured.
+const deletedNameSuffix = " (deleted)"
+
 // TargetView is the display-safe projection of a target for
 // the UI. It deliberately has no raw configuration field, so
 // no template — present or future — can render the stored
 // blob.
 type TargetView struct {
-	ID     string
+	ID   string
-	Name   string
+	Name string
+
+	// Deleted reports that this target's row is soft deleted.
+	// Only views built for historical display carry it set:
+	// every other projection is of a live row.
+	Deleted bool
+
 	Type   database.TargetType
 	Active bool
 	Config []ConfigField
 }
 
+// DisplayName is the name to render, marked when the target has
+// been deleted. Templates showing a name against historical data
+// must use it rather than Name, which stays the stored name.
+func (v TargetView) DisplayName() string {
+	if v.Deleted {
+		return v.Name + deletedNameSuffix
+	}
+
+	return v.Name
+}
+
 // NewTargetViews projects targets for rendering, replacing
 // each stored configuration blob with named, display-safe
 // fields.
+//
+// A soft-deleted row projects exactly as a live one does, minus
+// the deleted marker on its name: masking is a property of the
+// projection, not of the row's state, so a deleted target's
+// credential is as unreachable from a template as a live
+// target's.
 func NewTargetViews(
 	targets []database.Target,
 ) []TargetView {
@@ -47,11 +77,12 @@ func NewTargetViews(
 		t := &targets[i]
 
 		views = append(views, TargetView{
-			ID:     t.ID,
+			ID:      t.ID,
-			Name:   t.Name,
+			Name:    t.Name,
-			Type:   t.Type,
+			Deleted: t.DeletedAt.Valid,
-			Active: t.Active,
+			Type:    t.Type,
-			Config: targetConfigFields(t),
+			Active:  t.Active,
+			Config:  targetConfigFields(t),
 		})
 	}
 

internal/delivery/target_config_view_test.go

@@ -2,9 +2,11 @@ package delivery_test
 
 import (
 	"testing"
+	"time"
 
 	"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"
 )
@@ -17,6 +19,14 @@ const (
 	slackWebhookURL = "https://hooks.slack.com" +
 		slackSecretPath
 
+	// slackMaskedURL is what a Slack webhook URL renders as
+	// once masked: scheme and host, path elided.
+	slackMaskedURL = "https://hooks.slack.com/..."
+
+	// slackTargetName is the target name the Slack projection
+	// tests use.
+	slackTargetName = "slack-target"
+
 	viewExampleOrigin = "https://example.com"
 	viewExampleHook   = viewExampleOrigin + "/hook"
 	viewMaskedOrigin  = viewExampleOrigin + "/..."
@@ -33,7 +43,7 @@ func TestMaskedWebhookURL(t *testing.T) {
 	}{
 		"slack webhook": {
 			url:  slackWebhookURL,
-			want: "https://hooks.slack.com/...",
+			want: slackMaskedURL,
 		},
 		"query string dropped": {
 			url:  viewExampleOrigin + "/a?token=secret",
@@ -125,23 +135,61 @@ func viewFor(
 	return views[0]
 }
 
-func TestNewTargetViews_Slack(t *testing.T) {
+// TestNewTargetViews_DeletedTarget proves the projection marks
+// a soft-deleted target's name and masks its configuration by
+// the same rules a live target's is. Delivery history outlives
+// the target it names, so this projection is what an operator
+// reads about a target that no longer exists.
+func TestNewTargetViews_DeletedTarget(t *testing.T) {
 	t.Parallel()
 
-	view := viewFor(t, database.Target{
+	target := slackTarget()
-		Name:   "slack-target",
+	target.DeletedAt = gorm.DeletedAt{
+		Time:  time.Now(),
+		Valid: true,
+	}
+
+	view := viewFor(t, target)
+
+	assert.True(t, view.Deleted)
+	assert.Equal(t, slackTargetName, view.Name)
+	assert.Equal(
+		t, slackTargetName+" (deleted)", view.DisplayName(),
+	)
+	assert.Equal(
+		t,
+		map[string]string{"Webhook URL": slackMaskedURL},
+		fieldMap(view.Config),
+	)
+}
+
+// slackTarget is the live Slack target the projection tests
+// share.
+func slackTarget() database.Target {
+	return database.Target{
+		Name:   slackTargetName,
 		Type:   database.TargetTypeSlack,
 		Active: true,
 		Config: `{"webhookUrl":"` +
 			slackWebhookURL + `"}`,
-	})
+	}
+}
+
+func TestNewTargetViews_Slack(t *testing.T) {
+	t.Parallel()
+
+	view := viewFor(t, slackTarget())
+
+	assert.Equal(t, slackTargetName, view.Name)
+
+	// A live target is never marked, so the marker cannot
+	// reach a name that still exists.
+	assert.False(t, view.Deleted)
+	assert.Equal(t, slackTargetName, view.DisplayName())
 
-	assert.Equal(t, "slack-target", view.Name)
 	assert.Equal(
 		t,
-		map[string]string{
+		map[string]string{"Webhook URL": slackMaskedURL},
-			"Webhook URL": "https://hooks.slack.com/...",
-		},
 		fieldMap(view.Config),
 	)
 }
@@ -212,7 +260,7 @@ func TestNewTargetViews_HTTPMasksDestinationURL(t *testing.T) {
 
 	assert.Equal(
 		t,
-		"https://hooks.slack.com/...",
+		slackMaskedURL,
 		fields["Destination URL"],
 	)
 

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,
 	)
@@ -267,6 +277,24 @@ func (t *databaseTarget) evict(webhookID string) {
 	)
 }
 
+// evictAll evicts every cached archive writer, exactly as evict
+// does for one webhook. The engine calls it at shutdown, once its
+// workers have returned. Closing the last handle on an archive
+// moves the contents of its -wal into the .db and removes the
+// -wal, so a clean stop leaves each archive as a single file.
+func (t *databaseTarget) evictAll() {
+	t.mu.Lock()
+
+	writers := t.writers
+	t.writers = nil
+
+	t.mu.Unlock()
+
+	for _, w := range writers {
+		w.evict()
+	}
+}
+
 // sweepWebhook prunes one webhook's archive of rows older than
 // expiry, without requiring a write. It returns nil (nothing to
 // do) when the archive file does not exist, so a sweep never

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_database_evict_test.go

@@ -1,6 +1,7 @@
 package delivery_test
 
 import (
+	"context"
 	"errors"
 	"fmt"
 	"net/http"
@@ -361,3 +362,46 @@ func TestEvictWebhook_LaterDeliveryRecreatesWriter(t *testing.T) {
 		"a later delivery should recreate the writer",
 	)
 }
+
+// TestEngineStop_WriteAfterStopIsRefused proves the engine's stop
+// closes each archive writer the way deleting its webhook does: a
+// write that reaches a writer after the stop is refused, reopens
+// nothing and adds no row.
+func TestEngineStop_WriteAfterStopIsRefused(t *testing.T) {
+	t.Parallel()
+
+	eng, _ := evictTestEngine(t)
+
+	webhookDB := testWebhookDB(t)
+	event := seedEvent(t, webhookDB, `{"archived":true}`)
+	d := seedDatabaseTargetDelivery(t, webhookDB, event, "")
+
+	eng.ExportDeliverDatabase(webhookDB, d)
+
+	w := eng.ExportArchiveWriterFor(event.WebhookID)
+	require.NotNil(t, w)
+	require.True(t, w.HandleOpen())
+
+	require.NoError(t, eng.ExportStop(context.Background()))
+
+	err := w.Write(evictTestRow("ev-after-stop"), 0)
+
+	require.ErrorIs(
+		t, err, delivery.ErrExportArchiveWriterEvicted,
+		"a write after the stop must be refused",
+	)
+	assert.False(
+		t, w.HandleOpen(),
+		"a refused write must not reopen the archive",
+	)
+	assert.False(
+		t, eng.ExportHasArchiveWriter(event.WebhookID),
+		"the stop should empty the registry",
+	)
+
+	count, err := countArchivedRows(w.Path())
+	require.NoError(t, err)
+	assert.Equal(
+		t, int64(1), count, "the refused row must not be written",
+	)
+}

internal/delivery/target_headers_test.go

@@ -11,10 +11,11 @@ import (
 	"sneak.berlin/go/webhooker/internal/delivery"
 )
 
-// Literals these tests repeat, named so that the header name and the
+// Literals these tests repeat, named so that the header names and the
 // keep-forever archive config each have one definition.
 const (
 	headerAuthorization = "Authorization"
+	headerContentType   = "Content-Type"
 	bearerValue         = "Bearer abc"
 	archiveConfigNever  = "{\"expiry\":\"never\"}"
 )

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,
@@ -169,10 +197,14 @@ func (c *httpCore) circuitBreakerBlock(
 		"cooldown_remaining", remaining,
 	)
 
-	c.eng.updateDeliveryStatus(
+	// A delivery already at retrying is left as it is, so a task
-		webhookDB, d, d.Target.Type,
+	// the breaker keeps turning away writes nothing each time.
-		database.DeliveryStatusRetrying,
+	if d.Status != database.DeliveryStatusRetrying {
-	)
+		c.eng.settleStatus(
+			webhookDB, d, d.Target.Type,
+			database.DeliveryStatusRetrying,
+		)
+	}
 
 	retryTask := *task
 	sched.ScheduleRetry(retryTask, remaining)
@@ -189,7 +221,7 @@ func (c *httpCore) handleRetry(
 	attemptNum int,
 ) {
 	if attemptNum >= maxRetries {
-		c.eng.updateDeliveryStatus(
+		c.eng.settleStatus(
 			webhookDB, d, d.Target.Type,
 			database.DeliveryStatusFailed,
 		)
@@ -197,7 +229,7 @@ func (c *httpCore) handleRetry(
 		return
 	}
 
-	c.eng.updateDeliveryStatus(
+	c.eng.settleStatus(
 		webhookDB, d, d.Target.Type,
 		database.DeliveryStatusRetrying,
 	)
@@ -332,12 +364,17 @@ 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,
 		)
@@ -504,6 +541,11 @@ func isForwardableHeader(name string) bool {
 		"Upgrade", "Proxy-Authorization",
 		"Proxy-Connection", "Content-Length":
 		return false
+	case "Content-Type":
+		// applyRequestHeaders sets Content-Type itself. The receiver
+		// already stored this inbound value as the event's
+		// ContentType, so forwarding it too would send it twice.
+		return false
 	default:
 		return true
 	}
@@ -516,6 +558,10 @@ func isForwardableHeader(name string) bool {
 // policy strips exactly that set on a hop that leaves the origin,
 // so the forward set is decided here and only here — a header added
 // to it is covered off-origin without a second edit elsewhere.
+//
+// Content-Type goes out once: a Content-Type configured on the target
+// wins, otherwise the event's ContentType, otherwise none. The inbound
+// Content-Type in the event's headers is never forwarded.
 func applyRequestHeaders(
 	req *http.Request,
 	event *database.Event,
@@ -536,12 +582,18 @@ func applyRequestHeaders(
 
 	req.Header.Set("User-Agent", "webhooker/1.0")
 
-	// Content-Type describes the body being sent rather than the
+	// A Content-Type configured on the target describes the body
-	// sender, and the delivery path sets it from the event itself.
+	// being sent rather than the sender. A 307/308 preserves the
-	// A 307/308 preserves the body across hosts, so stripping it
+	// body across hosts, so stripping it would send that body
-	// would send that body untyped.
+	// untyped.
 	delete(originScoped, "Content-Type")
 
+	// User-Agent is overwritten just above, so an inbound one never
+	// reaches the wire and the value that does identifies this
+	// delivery path rather than the sender. Reporting it would strip
+	// it off-origin and leave net/http's own default in its place.
+	delete(originScoped, "User-Agent")
+
 	names := make([]string, 0, len(originScoped))
 	for name := range originScoped {
 		names = append(names, name)

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 +1,792 @@
+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. Section 4 is the same deleted-target gap for a pending
+// delivery: https://git.eeqj.de/sneak/webhooker/issues/293.
+
+// 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 delivery against it at the
+// given status 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,
+	status database.DeliveryStatus,
+) 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, status,
+	)
+
+	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",
+		database.DeliveryStatusRetrying,
+	)
+
+	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",
+		database.DeliveryStatusRetrying,
+	)
+
+	// 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",
+	)
+}
+
+// TestFailMissingTarget_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 TestFailMissingTarget_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,
+		database.DeliveryStatusRetrying,
+	)
+
+	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())
+}
+
+// --- 4. A pending delivery whose target is gone ---
+
+func TestRecoverPending_TargetDeleted(t *testing.T) {
+	t.Parallel()
+
+	s := newISetup(t)
+
+	deliveryID := tSeedDeletedTarget(
+		t, s, "gone-while-pending", "http://example.com/hook",
+		database.DeliveryStatusPending,
+	)
+
+	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-while-pending")
+	assert.Contains(t, last.Error, "was deleted")
+
+	assert.Empty(t, fDrain(s.Engine),
+		"a delivery whose target is gone was sent",
+	)
+	assert.Zero(t, s.Engine.ExportInflightHeld(),
+		"the terminal path leaked its ownership reference",
+	)
+}
+
+// TestRecoverPending_TargetDeleted_LeavesAnOwnedDeliveryAlone: the
+// terminal write takes ownership like every other recovery write, so a
+// delivery the engine still holds is not failed underneath its worker.
+func TestRecoverPending_TargetDeleted_LeavesAnOwnedDeliveryAlone(
+	t *testing.T,
+) {
+	t.Parallel()
+
+	s := newISetup(t)
+
+	deliveryID := tSeedDeletedTarget(
+		t, s, "gone-but-owned", "http://example.com/hook",
+		database.DeliveryStatusPending,
+	)
+
+	require.True(t, s.Engine.ExportRetainDelivery(deliveryID))
+
+	s.Engine.ExportRecoverWebhookDeliveries(
+		context.Background(), s.WebhookID,
+	)
+
+	iAssertStatus(
+		t, s.WebhookDB, deliveryID,
+		database.DeliveryStatusPending,
+	)
+
+	assert.Len(t, iResults(t, s.WebhookDB, deliveryID), 1,
+		"a delivery the engine owns was failed underneath it",
+	)
+}
+
+// TestFailMissingTarget_LeavesASettledDeliveryAlone: the recovery paths
+// read their batch before taking ownership, and a worker may send a
+// delivery and let it go in between. The terminal write goes by the row
+// as it is now, not as the batch read it.
+func TestFailMissingTarget_LeavesASettledDeliveryAlone(
+	t *testing.T,
+) {
+	t.Parallel()
+
+	s := newISetup(t)
+
+	deliveryID := tSeedDeletedTarget(
+		t, s, "gone-after-sending", "http://example.com/hook",
+		database.DeliveryStatusPending,
+	)
+
+	var batch database.Delivery
+
+	require.NoError(t, s.WebhookDB.First(
+		&batch, "id = ?", deliveryID,
+	).Error)
+
+	// A worker settles the delivery after the batch was read.
+	require.NoError(t, s.WebhookDB.Model(&database.Delivery{}).
+		Where("id = ?", deliveryID).
+		Update("status", database.DeliveryStatusDelivered).Error)
+
+	s.Engine.ExportFailMissingTarget(
+		s.WebhookDB, s.WebhookID, &batch,
+	)
+
+	iAssertStatus(
+		t, s.WebhookDB, deliveryID,
+		database.DeliveryStatusDelivered,
+	)
+
+	assert.Len(t, iResults(t, s.WebhookDB, deliveryID), 1,
+		"a delivery settled after the batch read was then failed",
+	)
+	assert.Zero(t, s.Engine.ExportInflightHeld())
+}
+
+// TestSweepPending_TargetDeleted sweeps twice over a batch that also
+// holds a healthy stranded delivery. The one whose target is gone is
+// failed once and then left alone; the healthy one is queued by the
+// first sweep and not again by the second.
+func TestSweepPending_TargetDeleted(t *testing.T) {
+	t.Parallel()
+
+	liveTargetID := uuid.New().String()
+	s := fSweepSetup(t, liveTargetID, "still-there")
+
+	deliveryID := tSeedDeletedTarget(
+		t, s, "gone-on-pending-sweep", "http://example.com/hook",
+		database.DeliveryStatusPending,
+	)
+	rAgePending(t, s.WebhookDB, deliveryID)
+
+	event := iSeedEvent(
+		t, s.WebhookDB, s.WebhookID, `{"target":"live"}`,
+	)
+
+	healthy := iSeedDelivery(
+		t, s.WebhookDB, event.ID, liveTargetID,
+		database.DeliveryStatusPending,
+	)
+	rAgePending(t, s.WebhookDB, healthy.ID)
+
+	ctx := context.Background()
+
+	s.Engine.ExportSweepWebhookRetries(ctx, s.WebhookID)
+
+	tasks := fDrain(s.Engine)
+	require.Len(t, tasks, 1,
+		"the first sweep did not queue the healthy delivery",
+	)
+	assert.Equal(t, healthy.ID, tasks[0].DeliveryID)
+
+	s.Engine.ExportSweepWebhookRetries(ctx, s.WebhookID)
+
+	assert.Empty(t, fDrain(s.Engine),
+		"the second sweep queued a delivery again",
+	)
+
+	iAssertStatus(
+		t, s.WebhookDB, deliveryID,
+		database.DeliveryStatusFailed,
+	)
+
+	last := tLastResult(t, s, deliveryID, 2)
+
+	assert.Contains(t, last.Error, "gone-on-pending-sweep")
+	assert.Contains(t, last.Error, "was deleted")
+}
+
+// TestSendRecoveredDeliveries_TargetMissingFromMap: the batch's target
+// map is empty when its query failed, so every delivery in the batch is
+// looked up on its own. A healthy one is sent to the target that lookup
+// finds.
+func TestSendRecoveredDeliveries_TargetMissingFromMap(
+	t *testing.T,
+) {
+	t.Parallel()
+
+	s := newISetup(t)
+
+	targetID := uuid.New().String()
+
+	iCreateTarget(
+		t, s.MainDB, targetID, s.WebhookID, "found-on-lookup",
+		database.TargetTypeLog, "", 0,
+	)
+
+	event := iSeedEvent(
+		t, s.WebhookDB, s.WebhookID, `{"map":"empty"}`,
+	)
+
+	d := iSeedDelivery(
+		t, s.WebhookDB, event.ID, targetID,
+		database.DeliveryStatusPending,
+	)
+
+	s.Engine.ExportSendRecoveredDeliveries(
+		context.Background(), s.WebhookDB,
+		[]database.Delivery{d}, s.WebhookID,
+		map[string]database.Target{}, nil,
+	)
+
+	tasks := fDrain(s.Engine)
+	require.Len(t, tasks, 1,
+		"the healthy delivery was not queued exactly once",
+	)
+	assert.Equal(t, d.ID, tasks[0].DeliveryID)
+	assert.Equal(t, targetID, tasks[0].TargetID)
+	assert.Equal(t, database.TargetTypeLog, tasks[0].TargetType)
+
+	iAssertStatus(
+		t, s.WebhookDB, d.ID,
+		database.DeliveryStatusPending,
+	)
+}
+
+// TestRecoverPending_TargetUnreadable_LeavesDeliveryAlone: a failed
+// read of the main database is not a deleted target. Restart recovery
+// holds every pending delivery of the webhook in one batch, so failing
+// on this would fail all of them.
+func TestRecoverPending_TargetUnreadable_LeavesDeliveryAlone(
+	t *testing.T,
+) {
+	t.Parallel()
+
+	s := newISetup(t)
+
+	targetID := uuid.New().String()
+
+	iCreateTarget(
+		t, s.MainDB, targetID, s.WebhookID, "healthy",
+		database.TargetTypeLog, "", 0,
+	)
+
+	event := iSeedEvent(
+		t, s.WebhookDB, s.WebhookID, `{"still":"pending"}`,
+	)
+
+	d := iSeedDelivery(
+		t, s.WebhookDB, event.ID, targetID,
+		database.DeliveryStatusPending,
+	)
+
+	sqlDB, err := s.MainDB.DB()
+	require.NoError(t, err)
+	require.NoError(t, sqlDB.Close())
+
+	s.Engine.ExportRecoverPendingDeliveries(
+		context.Background(), s.WebhookDB, s.WebhookID,
+	)
+
+	iAssertStatus(
+		t, s.WebhookDB, d.ID,
+		database.DeliveryStatusPending,
+	)
+
+	assert.Empty(t, iResults(t, s.WebhookDB, d.ID),
+		"an unreadable main database produced a terminal "+
+			"failure row",
+	)
+	assert.Empty(t, fDrain(s.Engine))
+	assert.Zero(t, s.Engine.ExportInflightHeld())
+}

internal/delivery/url_mask_test.go

@@ -185,7 +185,7 @@ func TestDoHTTPRequest_TransportErrorMasksURL(t *testing.T) {
 func TestValidateTargetURL_UnparsableURLIsMasked(t *testing.T) {
 	t.Parallel()
 
-	err := delivery.ValidateTargetURL(
+	err := delivery.NewTestGuard().ValidateTargetURL(
 		context.TODO(),
 		"https://hooks.slack.com"+maskSecretPath+"\n",
 	)

internal/handlers/auth_test.go

@@ -453,3 +453,33 @@ func TestLogin_SuccessCreatesSession(t *testing.T) {
 		"the issued cookie must carry an authenticated session",
 	)
 }
+
+// TestLogin_UsernameAtLimitCanLogIn shows that a username of exactly
+// database.MaxUsernameBytes still fits in the session cookie. Past
+// what the cookie can carry, a correct login answers 500.
+func TestLogin_UsernameAtLimitCanLogIn(t *testing.T) {
+	t.Parallel()
+
+	var (
+		h  *handlers.Handlers
+		db *database.Database
+	)
+
+	app := newTestApp(t, &h, &db)
+	app.RequireStart()
+
+	t.Cleanup(app.RequireStop)
+
+	username := strings.Repeat("a", database.MaxUsernameBytes)
+
+	hash, err := database.HashPassword(operatorPassword)
+	require.NoError(t, err)
+	require.NoError(t, db.DB().Create(&database.User{
+		Username: username,
+		Password: hash,
+	}).Error)
+
+	w := submitLogin(h, sharedProxyPeer, username, operatorPassword)
+
+	assert.Equal(t, http.StatusSeeOther, w.Code)
+}

internal/handlers/delivery_replay.go

@@ -368,7 +368,7 @@ func (h *Handlers) finishReplay(
 	// The page is read from the form rather than the query string:
 	// this is a POST, and its query string is what logs and Referer
 	// headers record.
-	if page := parseNonNegativeInt(
+	if page := pageOrFirst(
 		r.PostFormValue("page"),
 	); page > 1 {
 		dest += "&page=" + strconv.Itoa(page)

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_log_view.go

@@ -20,6 +20,7 @@ const maxRenderedBodyBytes = 8192
 // rather than in Go is the point of the projection — an
 // oversized body never becomes a Go string at all.
 const eventLogColumns = "id, created_at, method, content_type, " +
+	"resubmitted_from_id, " +
 	"substr(cast(body as blob), 1, ?) AS body, " +
 	"length(cast(body as blob)) AS body_bytes"
 
@@ -45,9 +46,25 @@ type EventLogView struct {
 	// than the cap, so the page owes the reader a marker.
 	BodyTruncated bool
 
+	// ResubmittedFromID names the event this one was copied
+	// from, empty for an event that arrived on the receiver.
+	ResubmittedFromID string
+
+	// ResubmitCount is how many events have been resubmitted
+	// from this one. Both directions are shown, because after
+	// a few resubmits of one captured event the log is
+	// otherwise a row of identical bodies with nothing saying
+	// which came from which.
+	ResubmitCount int
+
 	Deliveries []DeliveryView
 }
 
+// ResubmittedFrom reports that this event is a copy of another.
+func (v EventLogView) ResubmittedFrom() bool {
+	return v.ResubmittedFromID != ""
+}
+
 // BodyShownBytes is how many body bytes the page is actually
 // rendering, which the truncation marker reports beside the
 // true size.
@@ -59,12 +76,13 @@ func (v EventLogView) BodyShownBytes() int {
 // body column arrives already cut to the cap by SQLite, with
 // the true size beside it.
 type eventLogRow struct {
-	ID          string
+	ID                string
-	CreatedAt   time.Time
+	CreatedAt         time.Time
-	Method      string
+	Method            string
-	ContentType string
+	ContentType       string
-	Body        []byte
+	ResubmittedFromID *string
-	BodyBytes   int64
+	Body              []byte
+	BodyBytes         int64
 }
 
 // view projects a loaded row for rendering.
@@ -79,14 +97,20 @@ func (r *eventLogRow) view() EventLogView {
 		body = trimPartialRune(body)
 	}
 
+	var from string
+	if r.ResubmittedFromID != nil {
+		from = *r.ResubmittedFromID
+	}
+
 	return EventLogView{
-		ID:            r.ID,
+		ID:                r.ID,
-		CreatedAt:     r.CreatedAt,
+		CreatedAt:         r.CreatedAt,
-		Method:        r.Method,
+		Method:            r.Method,
-		ContentType:   r.ContentType,
+		ContentType:       r.ContentType,
-		Body:          string(body),
+		Body:              string(body),
-		BodyBytes:     r.BodyBytes,
+		BodyBytes:         r.BodyBytes,
-		BodyTruncated: truncated,
+		BodyTruncated:     truncated,
+		ResubmittedFromID: from,
 	}
 }
 

internal/handlers/event_resubmit.go

@@ -0,0 +1,273 @@
+package handlers
+
+import (
+	"errors"
+	"net/http"
+	"strconv"
+
+	"github.com/go-chi/chi"
+	"github.com/google/uuid"
+	"gorm.io/gorm"
+	"sneak.berlin/go/webhooker/internal/database"
+)
+
+// resubmitOutcomeParam is the query parameter the resubmit POST
+// redirects with and the event log page reads its banner from.
+const resubmitOutcomeParam = "resubmit"
+
+// resubmitOutcomeCode is the outcome of a resubmit POST. The redirect
+// carries one of these fixed codes rather than a message, so nothing a
+// client submits can reach the rendered page through it.
+type resubmitOutcomeCode string
+
+const (
+	// resubmitQueued reports that a new event was stored and its
+	// deliveries handed to the delivery engine.
+	resubmitQueued resubmitOutcomeCode = "queued"
+
+	// resubmitNoTargets reports a source with no active targets. The
+	// new event is stored either way, exactly as a received event
+	// with no targets is.
+	resubmitNoTargets resubmitOutcomeCode = "no-targets"
+)
+
+// resubmitOutcome returns the banner the event log page shows for an
+// outcome code, and whether the resubmit was queued. An unrecognised
+// code yields no banner.
+func resubmitOutcome(code string) (string, bool) {
+	switch resubmitOutcomeCode(code) {
+	case resubmitQueued:
+		return "Resubmitted: a new event was created from the stored " +
+			"one and queued to every active target.", true
+	case resubmitNoTargets:
+		return "Resubmitted: a new event was created, but this " +
+				"source has no active targets, so nothing was queued.",
+			true
+	default:
+		return "", false
+	}
+}
+
+// resubmitSource is the stored event a resubmit copies. Its body is
+// read as bytes rather than as a string so the copy is byte-identical
+// to what was received, whatever the payload's encoding.
+type resubmitSource struct {
+	ID           string
+	EntrypointID string
+	Method       string
+	Headers      string
+	ContentType  string
+	Body         []byte
+}
+
+// resubmitColumns is the projection resubmitSource is loaded through.
+// The cast to blob is what makes the driver hand back the stored bytes
+// rather than a string conversion, the same reason eventBodyQuery
+// casts.
+const resubmitColumns = "id, entrypoint_id, method, headers, " +
+	"content_type, cast(body as blob) AS body"
+
+// HandleEventResubmit re-injects a stored event as a new undelivered
+// event.
+//
+// This is the testing counterpart to per-delivery replay, and the two
+// select targets differently on purpose. A replay re-sends ONE
+// finished delivery to ITS OWN target, which is recovery. A resubmit
+// stores a NEW event copied from the stored one and fans it out to the
+// webhook's currently ACTIVE targets, resolved fresh by the query the
+// receiver uses — so a target created after the original event arrived
+// receives it, which is what makes capturing real traffic and firing
+// it at a backend under development possible. The original event's
+// deliveries have no bearing on where the copy goes.
+//
+// Nothing about the original delivery is re-sent: what is re-injected
+// is the stored EVENT. The response bodies and headers the original
+// deliveries received stay where they are.
+//
+// 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
+// button.
+func (h *Handlers) HandleEventResubmit() 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
+		}
+
+		h.resubmitEvent(w, r, webhook)
+	}
+}
+
+// resubmitEvent performs the resubmit for a webhook the caller has
+// already established the session's user owns.
+func (h *Handlers) resubmitEvent(
+	w http.ResponseWriter,
+	r *http.Request,
+	webhook database.Webhook,
+) {
+	// Parsing the id before use keeps a malformed id out of the SQL
+	// and makes the value the query sees come from uuid's own fixed
+	// alphabet rather than from the request.
+	eventID, err := uuid.Parse(chi.URLParam(r, "eventID"))
+	if err != nil {
+		http.NotFound(w, r)
+
+		return
+	}
+
+	if !h.dbMgr.DBExists(webhook.ID) {
+		http.NotFound(w, r)
+
+		return
+	}
+
+	webhookDB, err := h.dbMgr.GetDB(webhook.ID)
+	if err != nil {
+		h.serverError(w, "failed to get webhook database", err)
+
+		return
+	}
+
+	// Read before the write transaction is opened. The body can be up
+	// to the 1 MB ingest cap, and every transaction on these files
+	// takes the write lock at BEGIN (_txlock=immediate, see
+	// internal/database/sqlite_open.go), so reading inside it would
+	// hold that lock against the receiver for the length of the read.
+	src, found, err := loadResubmitSource(
+		webhookDB, webhook.ID, eventID.String(),
+	)
+	if err != nil {
+		h.serverError(w, "failed to load event to resubmit", err)
+
+		return
+	}
+
+	// A miss is a 404 whether the event was reaped, belongs to
+	// another webhook, or never existed.
+	if !found {
+		http.NotFound(w, r)
+
+		return
+	}
+
+	h.queueResubmit(w, r, webhook, src)
+}
+
+// loadResubmitSource reads the stored event a resubmit copies, and
+// whether it exists within the webhook.
+//
+// The webhook_id predicate is currently redundant against the
+// per-webhook database files — a sibling webhook's event is not in the
+// database being queried at all — and is there so the scoping survives
+// any future change that puts more than one webhook's events in one
+// file. Going through Model applies GORM's soft-delete scope, which is
+// what stops a reaped event being resubmitted.
+func loadResubmitSource(
+	webhookDB *gorm.DB,
+	webhookID, eventID string,
+) (resubmitSource, bool, error) {
+	var src resubmitSource
+
+	err := webhookDB.Model(&database.Event{}).
+		Select(resubmitColumns).
+		Where("id = ? AND webhook_id = ?", eventID, webhookID).
+		First(&src).Error
+
+	if errors.Is(err, gorm.ErrRecordNotFound) {
+		return src, false, nil
+	}
+
+	if err != nil {
+		return src, false, err
+	}
+
+	return src, true, nil
+}
+
+// queueResubmit stores the copy and fans it out to the webhook's
+// active targets.
+func (h *Handlers) queueResubmit(
+	w http.ResponseWriter,
+	r *http.Request,
+	webhook database.Webhook,
+	src resubmitSource,
+) {
+	// The receiver's own query, run now: an active target created
+	// after the original event arrived is included, and an
+	// inactive one is skipped rather than refused.
+	targets, err := h.loadActiveTargets(webhook.ID)
+	if err != nil {
+		h.serverError(w, "failed to query targets", err)
+
+		return
+	}
+
+	event, tasks, err := h.createAndFanOut(
+		eventSource{
+			WebhookID:         webhook.ID,
+			EntrypointID:      src.EntrypointID,
+			Method:            src.Method,
+			HeadersJSON:       src.Headers,
+			ContentType:       src.ContentType,
+			Body:              src.Body,
+			ResubmittedFromID: &src.ID,
+		},
+		targets,
+	)
+	if err != nil {
+		h.serverError(w, "failed to store resubmitted event", err)
+
+		return
+	}
+
+	h.mtr.EventResubmitted()
+
+	h.log.Info(
+		"event resubmitted",
+		"webhook_id", webhook.ID,
+		"event_id", event.ID,
+		"resubmitted_from_id", src.ID,
+		"target_count", len(tasks),
+	)
+
+	code := resubmitQueued
+	if len(tasks) == 0 {
+		code = resubmitNoTargets
+	}
+
+	h.finishResubmit(w, r, webhook, code)
+}
+
+// finishResubmit redirects back to the event log the resubmit was
+// triggered from, carrying the outcome code the page turns into a
+// banner and the page number the form submitted.
+func (h *Handlers) finishResubmit(
+	w http.ResponseWriter,
+	r *http.Request,
+	webhook database.Webhook,
+	code resubmitOutcomeCode,
+) {
+	dest := "/source/" + webhook.ID + "/logs?" +
+		resubmitOutcomeParam + "=" + string(code)
+
+	// The page is read from the form rather than the query string:
+	// this is a POST, and its query string is what logs and Referer
+	// headers record.
+	if page := pageOrFirst(
+		r.PostFormValue("page"),
+	); page > 1 {
+		dest += "&page=" + strconv.Itoa(page)
+	}
+
+	http.Redirect(w, r, dest, http.StatusSeeOther)
+}

internal/handlers/event_resubmit_test.go

@@ -0,0 +1,603 @@
+package handlers_test
+
+import (
+	"net/http"
+	"net/http/httptest"
+	"strings"
+	"testing"
+
+	"github.com/google/uuid"
+	"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/delivery"
+	"sneak.berlin/go/webhooker/internal/handlers"
+	"sneak.berlin/go/webhooker/internal/session"
+)
+
+// resubmitTargetURL is a public destination, so a target configured
+// with it is one the SSRF guard would accept. Nothing in these tests
+// dispatches to it: the notifier is recorded, not run.
+const resubmitTargetURL = "http://93.184.216.34/hook"
+
+// resubmitEventHeaders is the stored header JSON a seeded event
+// carries, so a test can prove the copy takes it verbatim.
+const resubmitEventHeaders = `{"X-Test":["yes"],"X-Trace":["abc"]}`
+
+// seedStoredEvent records one event in a webhook's own database with
+// no deliveries at all, which is the state a captured event is in when
+// the operator has yet to create the target to test.
+func seedStoredEvent(
+	t *testing.T,
+	dbMgr *database.WebhookDBManager,
+	webhookID, body string,
+) *database.Event {
+	t.Helper()
+
+	webhookDB, err := dbMgr.GetDB(webhookID)
+	require.NoError(t, err)
+
+	event := &database.Event{
+		WebhookID:    webhookID,
+		EntrypointID: "entrypoint-" + webhookID,
+		Method:       http.MethodPost,
+		Headers:      resubmitEventHeaders,
+		Body:         body,
+		ContentType:  contentTypeJSON,
+	}
+
+	require.NoError(t, webhookDB.Omit(
+		clause.Associations,
+	).Create(event).Error)
+
+	return event
+}
+
+// postResubmit runs the real resubmit handler for one event.
+func postResubmit(
+	t *testing.T,
+	h *handlers.Handlers,
+	sess *session.Session,
+	webhookID, eventID string,
+) *httptest.ResponseRecorder {
+	t.Helper()
+
+	req := postRequest(
+		"/source/"+webhookID+"/events/"+eventID+"/resubmit",
+		authenticatedCookies(
+			t, sess, deleteTestUserID, deleteTestUsername,
+		),
+		map[string]string{
+			paramSourceID: webhookID,
+			paramEventID:  eventID,
+		},
+	)
+
+	w := httptest.NewRecorder()
+	h.HandleEventResubmit().ServeHTTP(w, req)
+
+	return w
+}
+
+// listEvents reads every event in a webhook's database, oldest first.
+func listEvents(
+	t *testing.T, webhookDB *gorm.DB,
+) []database.Event {
+	t.Helper()
+
+	var events []database.Event
+
+	require.NoError(t, webhookDB.
+		Order("created_at ASC, id ASC").
+		Find(&events).Error)
+
+	return events
+}
+
+// theOtherEvent returns the one event that is not excludeID.
+func theOtherEvent(
+	t *testing.T, events []database.Event, excludeID string,
+) database.Event {
+	t.Helper()
+
+	var found []database.Event
+
+	for _, e := range events {
+		if e.ID != excludeID {
+			found = append(found, e)
+		}
+	}
+
+	require.Len(t, found, 1)
+
+	return found[0]
+}
+
+// TestHandleEventResubmit_DeliversToTargetCreatedAfterTheEvent is the
+// core of the feature and the thing per-delivery replay cannot do: the
+// event was captured before the target existed, so it has no delivery
+// to replay, and the resubmit must still reach the new target.
+func TestHandleEventResubmit_DeliversToTargetCreatedAfterTheEvent(
+	t *testing.T,
+) {
+	t.Parallel()
+
+	var (
+		h     *handlers.Handlers
+		sess  *session.Session
+		db    *database.Database
+		dbMgr *database.WebhookDBManager
+		notif *recordingNotifier
+	)
+
+	app := newTestApp(t, &h, &sess, &db, &dbMgr, &notif)
+	app.RequireStart()
+
+	t.Cleanup(app.RequireStop)
+
+	wh := seedWebhook(t, db)
+	original := seedStoredEvent(
+		t, dbMgr, wh.ID, `{"captured":"traffic"}`,
+	)
+
+	// The dev backend is registered only now, after the traffic was
+	// captured. It has no prior delivery of anything.
+	tgt := seedConfiguredTarget(
+		t, db, wh.ID, database.TargetTypeHTTP,
+		`{"url":"`+resubmitTargetURL+`"}`,
+	)
+
+	w := postResubmit(t, h, sess, wh.ID, original.ID)
+
+	require.Equal(t, http.StatusSeeOther, w.Code)
+	assert.Equal(
+		t,
+		"/source/"+wh.ID+"/logs?resubmit=queued",
+		w.Header().Get("Location"),
+	)
+
+	webhookDB, err := dbMgr.GetDB(wh.ID)
+	require.NoError(t, err)
+
+	events := listEvents(t, webhookDB)
+	require.Len(
+		t, events, 2,
+		"resubmit must create a new event, not mark the old one",
+	)
+
+	fresh := theOtherEvent(t, events, original.ID)
+	assertEventCopy(t, original, fresh)
+
+	// The delivery hangs off the NEW event, and the original event
+	// still has none.
+	assert.Empty(
+		t, listDeliveries(t, webhookDB, original.ID),
+		"the original event must be left untouched",
+	)
+
+	deliveries := listDeliveries(t, webhookDB, fresh.ID)
+	require.Len(t, deliveries, 1)
+	assert.Equal(t, tgt.ID, deliveries[0].TargetID)
+	assert.Equal(
+		t, database.DeliveryStatusPending, deliveries[0].Status,
+	)
+
+	tasks := notif.Tasks()
+	require.Len(t, tasks, 1)
+	assert.Equal(t, deliveries[0].ID, tasks[0].DeliveryID)
+	assertResubmitTask(t, tasks[0], wh.ID, &fresh, tgt)
+
+	assertNoLeakedTarget(t, webhookDB)
+}
+
+// assertEventCopy proves the resubmitted event copies every stored
+// field of the event it came from, and records the provenance that
+// keeps the log readable. It also pins that a received event carries
+// no source event of its own.
+func assertEventCopy(
+	t *testing.T, original *database.Event, fresh database.Event,
+) {
+	t.Helper()
+
+	assert.Equal(t, original.Method, fresh.Method)
+	assert.Equal(t, original.Headers, fresh.Headers)
+	assert.Equal(t, original.Body, fresh.Body)
+	assert.Equal(t, original.ContentType, fresh.ContentType)
+	assert.Equal(t, original.EntrypointID, fresh.EntrypointID)
+	assert.Equal(t, original.WebhookID, fresh.WebhookID)
+	assert.NotEqual(t, original.ID, fresh.ID)
+
+	require.NotNil(t, fresh.ResubmittedFromID)
+	assert.Equal(t, original.ID, *fresh.ResubmittedFromID)
+
+	assert.Nil(
+		t, original.ResubmittedFromID,
+		"a received event records no source event",
+	)
+}
+
+// assertResubmitTask proves the task handed to the delivery engine is
+// the one the receiver would build for the NEW event and this target.
+func assertResubmitTask(
+	t *testing.T,
+	task delivery.Task,
+	webhookID string,
+	fresh *database.Event,
+	target *database.Target,
+) {
+	t.Helper()
+
+	assert.Equal(t, fresh.ID, task.EventID)
+	assert.Equal(t, webhookID, task.WebhookID)
+	assert.Equal(t, fresh.EntrypointID, task.EntrypointID)
+	assert.Equal(t, target.ID, task.TargetID)
+	assert.Equal(t, target.Type, task.TargetType)
+	assert.Equal(t, fresh.Method, task.Method)
+	assert.Equal(t, fresh.Headers, task.Headers)
+	assert.Equal(t, fresh.ContentType, task.ContentType)
+	assert.Equal(t, 1, task.AttemptNum)
+
+	require.NotNil(t, task.Body)
+	assert.Equal(t, fresh.Body, *task.Body)
+}
+
+// TestHandleEventResubmit_IsRepeatable proves the requirement replay
+// deliberately does not meet: firing the same captured event at a
+// backend over and over must work, with no in-flight refusal, and each
+// press must produce its own event and its own delivery.
+func TestHandleEventResubmit_IsRepeatable(t *testing.T) {
+	t.Parallel()
+
+	var (
+		h     *handlers.Handlers
+		sess  *session.Session
+		db    *database.Database
+		dbMgr *database.WebhookDBManager
+		notif *recordingNotifier
+	)
+
+	app := newTestApp(t, &h, &sess, &db, &dbMgr, &notif)
+	app.RequireStart()
+
+	t.Cleanup(app.RequireStop)
+
+	wh := seedWebhook(t, db)
+	tgt := seedConfiguredTarget(
+		t, db, wh.ID, database.TargetTypeHTTP,
+		`{"url":"`+resubmitTargetURL+`"}`,
+	)
+	original := seedStoredEvent(t, dbMgr, wh.ID, `{"fire":"again"}`)
+
+	// Nothing between the presses marks the earlier deliveries
+	// finished, so every one of these is submitted while the last is
+	// still pending.
+	const presses = 5
+
+	for range presses {
+		w := postResubmit(t, h, sess, wh.ID, original.ID)
+
+		require.Equal(t, http.StatusSeeOther, w.Code)
+		assert.Equal(
+			t,
+			"/source/"+wh.ID+"/logs?resubmit=queued",
+			w.Header().Get("Location"),
+			"a resubmit must not be refused while an earlier "+
+				"one is in flight",
+		)
+	}
+
+	webhookDB, err := dbMgr.GetDB(wh.ID)
+	require.NoError(t, err)
+
+	events := listEvents(t, webhookDB)
+	require.Len(t, events, presses+1)
+
+	tasks := notif.Tasks()
+	require.Len(t, tasks, presses)
+
+	seen := make(map[string]struct{}, presses)
+
+	for _, task := range tasks {
+		assert.Equal(t, tgt.ID, task.TargetID)
+		assert.NotEqual(
+			t, original.ID, task.EventID,
+			"each resubmit delivers its own new event",
+		)
+
+		_, dup := seen[task.EventID]
+		assert.False(t, dup, "each resubmit creates its own event")
+
+		seen[task.EventID] = struct{}{}
+
+		require.Len(t, listDeliveries(t, webhookDB, task.EventID), 1)
+	}
+
+	// Every copy names the same source event, so twenty presses stay
+	// traceable to the one captured request.
+	for _, e := range events {
+		if e.ID == original.ID {
+			continue
+		}
+
+		require.NotNil(t, e.ResubmittedFromID)
+		assert.Equal(t, original.ID, *e.ResubmittedFromID)
+	}
+}
+
+// TestHandleEventResubmit_OversizeBodySurvivesIntact covers the
+// non-inline case: a body above delivery.MaxInlineBodySize is not
+// carried on the task at all, so it has to be copied into the new
+// event row byte-identically for the engine to load it from there.
+func TestHandleEventResubmit_OversizeBodySurvivesIntact(t *testing.T) {
+	t.Parallel()
+
+	var (
+		h     *handlers.Handlers
+		sess  *session.Session
+		db    *database.Database
+		dbMgr *database.WebhookDBManager
+		notif *recordingNotifier
+	)
+
+	app := newTestApp(t, &h, &sess, &db, &dbMgr, &notif)
+	app.RequireStart()
+
+	t.Cleanup(app.RequireStop)
+
+	// Well over the inline limit, and not text: a multibyte rune, a
+	// NUL and a byte that is not valid UTF-8, so a copy that went
+	// through a re-encode or a truncation is visible in the compare.
+	const sentinel = "TAIL-SENTINEL-1f4a9c"
+
+	stored := strings.Repeat("A", delivery.MaxInlineBodySize) +
+		"é\x00\xff" +
+		strings.Repeat("B", 4096) + sentinel
+
+	require.Greater(t, len(stored), delivery.MaxInlineBodySize)
+
+	wh := seedWebhook(t, db)
+	seedConfiguredTarget(
+		t, db, wh.ID, database.TargetTypeHTTP,
+		`{"url":"`+resubmitTargetURL+`"}`,
+	)
+	original := seedStoredEvent(t, dbMgr, wh.ID, stored)
+
+	w := postResubmit(t, h, sess, wh.ID, original.ID)
+	require.Equal(t, http.StatusSeeOther, w.Code)
+
+	webhookDB, err := dbMgr.GetDB(wh.ID)
+	require.NoError(t, err)
+
+	fresh := theOtherEvent(t, listEvents(t, webhookDB), original.ID)
+
+	assert.Len(t, fresh.Body, len(stored))
+	assert.Equal(
+		t, stored, fresh.Body,
+		"the stored body must be copied byte for byte",
+	)
+
+	tasks := notif.Tasks()
+	require.Len(t, tasks, 1)
+	assert.Nil(
+		t, tasks[0].Body,
+		"a body over the inline limit is fetched from the new "+
+			"event row rather than carried on the task",
+	)
+
+	// The engine's own read of the body, against the new event id:
+	// what it would send is what was stored.
+	var loaded database.Event
+
+	require.NoError(t, webhookDB.Select("body").
+		First(&loaded, "id = ?", tasks[0].EventID).Error)
+	assert.Equal(t, stored, loaded.Body)
+}
+
+// TestHandleEventResubmit_SkipsInactiveTarget proves a deactivated
+// target is skipped exactly as the receiver skips it — not an error,
+// and not a delivery the operator switched off.
+func TestHandleEventResubmit_SkipsInactiveTarget(t *testing.T) {
+	t.Parallel()
+
+	var (
+		h     *handlers.Handlers
+		sess  *session.Session
+		db    *database.Database
+		dbMgr *database.WebhookDBManager
+		notif *recordingNotifier
+	)
+
+	app := newTestApp(t, &h, &sess, &db, &dbMgr, &notif)
+	app.RequireStart()
+
+	t.Cleanup(app.RequireStop)
+
+	wh := seedWebhook(t, db)
+	active := seedConfiguredTarget(
+		t, db, wh.ID, database.TargetTypeHTTP,
+		`{"url":"`+resubmitTargetURL+`"}`,
+	)
+	off := seedConfiguredTarget(
+		t, db, wh.ID, database.TargetTypeHTTP,
+		`{"url":"`+resubmitTargetURL+`/off"}`,
+	)
+
+	require.NoError(t, db.DB().Model(&database.Target{}).
+		Where("id = ?", off.ID).
+		Update("active", false).Error)
+
+	original := seedStoredEvent(t, dbMgr, wh.ID, `{"skip":"one"}`)
+
+	w := postResubmit(t, h, sess, wh.ID, original.ID)
+
+	require.Equal(t, http.StatusSeeOther, w.Code)
+	assert.Equal(
+		t,
+		"/source/"+wh.ID+"/logs?resubmit=queued",
+		w.Header().Get("Location"),
+		"an inactive target is skipped, not an error",
+	)
+
+	tasks := notif.Tasks()
+	require.Len(t, tasks, 1)
+	assert.Equal(t, active.ID, tasks[0].TargetID)
+
+	webhookDB, err := dbMgr.GetDB(wh.ID)
+	require.NoError(t, err)
+
+	fresh := theOtherEvent(t, listEvents(t, webhookDB), original.ID)
+	require.Len(t, listDeliveries(t, webhookDB, fresh.ID), 1)
+}
+
+// TestHandleEventResubmit_NoActiveTargetsStillStoresEvent proves a
+// source with nothing to deliver to behaves as the receiver does: the
+// event is stored, nothing is queued, and the operator is told so
+// rather than being shown an error.
+func TestHandleEventResubmit_NoActiveTargetsStillStoresEvent(
+	t *testing.T,
+) {
+	t.Parallel()
+
+	var (
+		h     *handlers.Handlers
+		sess  *session.Session
+		db    *database.Database
+		dbMgr *database.WebhookDBManager
+		notif *recordingNotifier
+	)
+
+	app := newTestApp(t, &h, &sess, &db, &dbMgr, &notif)
+	app.RequireStart()
+
+	t.Cleanup(app.RequireStop)
+
+	wh := seedWebhook(t, db)
+	original := seedStoredEvent(t, dbMgr, wh.ID, `{"no":"targets"}`)
+
+	w := postResubmit(t, h, sess, wh.ID, original.ID)
+
+	require.Equal(t, http.StatusSeeOther, w.Code)
+	assert.Equal(
+		t,
+		"/source/"+wh.ID+"/logs?resubmit=no-targets",
+		w.Header().Get("Location"),
+	)
+
+	assert.Empty(t, notif.Tasks())
+
+	webhookDB, err := dbMgr.GetDB(wh.ID)
+	require.NoError(t, err)
+
+	assert.Len(t, listEvents(t, webhookDB), 2)
+}
+
+// TestHandleEventResubmit_RefusesEventOfAnotherWebhook proves the
+// route cannot re-inject an event out of a webhook the session's user
+// does not own, and reports the same 404 for an id that names nothing.
+func TestHandleEventResubmit_RefusesEventOfAnotherWebhook(
+	t *testing.T,
+) {
+	t.Parallel()
+
+	var (
+		h     *handlers.Handlers
+		sess  *session.Session
+		db    *database.Database
+		dbMgr *database.WebhookDBManager
+		notif *recordingNotifier
+	)
+
+	app := newTestApp(t, &h, &sess, &db, &dbMgr, &notif)
+	app.RequireStart()
+
+	t.Cleanup(app.RequireStop)
+
+	theirs := seedWebhookFor(t, db, otherTestUserID)
+	theirEvent := seedStoredEvent(t, dbMgr, theirs.ID, `{"not":"mine"}`)
+
+	mine := seedWebhook(t, db)
+	seedConfiguredTarget(
+		t, db, mine.ID, database.TargetTypeHTTP,
+		`{"url":"`+resubmitTargetURL+`"}`,
+	)
+	seedStoredEvent(t, dbMgr, mine.ID, `{"mine":true}`)
+
+	// Their webhook, as its owner would address it.
+	w := postResubmit(t, h, sess, theirs.ID, theirEvent.ID)
+	assert.Equal(t, http.StatusNotFound, w.Code)
+
+	// Their event id, addressed through a webhook the user does own.
+	w = postResubmit(t, h, sess, mine.ID, theirEvent.ID)
+	assert.Equal(t, http.StatusNotFound, w.Code)
+
+	// An id that names no event at all.
+	w = postResubmit(t, h, sess, mine.ID, uuid.NewString())
+	assert.Equal(t, http.StatusNotFound, w.Code)
+
+	// A malformed id never reaches the query.
+	w = postResubmit(t, h, sess, mine.ID, "not-a-uuid")
+	assert.Equal(t, http.StatusNotFound, w.Code)
+
+	assert.Empty(
+		t, notif.Tasks(),
+		"a refused resubmit must queue nothing",
+	)
+}
+
+// TestHandleSourceLogs_ShowsResubmitProvenance proves the event log
+// reports the relationship in both directions, which is what keeps it
+// readable once one captured event has been fired repeatedly.
+func TestHandleSourceLogs_ShowsResubmitProvenance(t *testing.T) {
+	t.Parallel()
+
+	var (
+		h     *handlers.Handlers
+		sess  *session.Session
+		db    *database.Database
+		dbMgr *database.WebhookDBManager
+	)
+
+	app := newTestApp(t, &h, &sess, &db, &dbMgr)
+	app.RequireStart()
+
+	t.Cleanup(app.RequireStop)
+
+	wh := seedWebhook(t, db)
+	seedConfiguredTarget(
+		t, db, wh.ID, database.TargetTypeHTTP,
+		`{"url":"`+resubmitTargetURL+`"}`,
+	)
+	original := seedStoredEvent(t, dbMgr, wh.ID, `{"trace":"me"}`)
+
+	for range 2 {
+		require.Equal(
+			t,
+			http.StatusSeeOther,
+			postResubmit(t, h, sess, wh.ID, original.ID).Code,
+		)
+	}
+
+	webhookDB, err := dbMgr.GetDB(wh.ID)
+	require.NoError(t, err)
+
+	events := listEvents(t, webhookDB)
+	require.Len(t, events, 3)
+
+	body := renderSourceLogsPage(t, h, sess, wh.ID)
+
+	assert.Contains(
+		t, body, "Resubmitted as 2 new events",
+		"the source event must show it has been resubmitted",
+	)
+	assert.Contains(
+		t, body, "Resubmitted from event",
+		"a copy must show where it came from",
+	)
+	assert.Contains(
+		t, body,
+		"/source/"+wh.ID+"/events/"+original.ID+"/resubmit",
+		"the log must offer the resubmit action per event",
+	)
+}

internal/handlers/export_test.go

@@ -27,6 +27,17 @@ const MaxRenderedResponseBytesForTest = maxRenderedResponseBytes
 // per-delivery attempt ceiling to the handlers_test package.
 const MaxRenderedAttemptsForTest = maxRenderedAttempts
 
+// MaxTargetRetriesForTest exposes the target max_retries ceiling to
+// the handlers_test package, so the tests assert against the constant
+// the handlers enforce rather than a number copied beside it.
+const MaxTargetRetriesForTest = maxTargetRetries
+
+// PageOrFirstForTest exposes pageOrFirst for use in the handlers_test
+// package.
+func PageOrFirstForTest(s string) int {
+	return pageOrFirst(s)
+}
+
 // DummyVerificationsForTest reports how many equivalent-cost
 // verifications were charged for usernames that do not exist. It
 // lets a test prove the anti-enumeration path ran without timing

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

@@ -60,6 +60,7 @@ type HandlersParams struct {
 	Middleware   *middleware.Middleware
 	Notifier     delivery.Notifier
 	Evictor      delivery.WebhookEvictor
+	SSRFGuard    *delivery.Guard
 }
 
 // Handlers provides HTTP handler methods for all application
@@ -77,6 +78,11 @@ type Handlers struct {
 	mtr       *metrics.Set
 	templates map[string]*template.Template
 
+	// ssrf validates submitted target URLs. It is the same guard
+	// the delivery engine dials through, so a URL accepted here
+	// is one delivery will actually attempt.
+	ssrf *delivery.Guard
+
 	// dummyVerifications counts the equivalent-cost verifications
 	// charged for usernames that do not exist. It exists so a test
 	// can prove that path runs without measuring wall-clock time.
@@ -117,6 +123,7 @@ func New(
 	s.notifier = params.Notifier
 	s.evictor = params.Evictor
 	s.mtr = metrics.Default()
+	s.ssrf = params.SSRFGuard
 
 	// Parse all page templates once at startup
 	s.templates = map[string]*template.Template{
@@ -177,6 +184,7 @@ type UserInfo struct {
 type templateDataWrapper struct {
 	User      *UserInfo
 	CSRFToken string
+	Version   string
 	Data      any
 }
 
@@ -227,9 +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
@@ -238,6 +253,7 @@ func (s *Handlers) renderTemplate(
 	wrapper := templateDataWrapper{
 		User:      userInfo,
 		CSRFToken: csrfToken,
+		Version:   version,
 		Data:      data,
 	}
 

internal/handlers/handlers_test.go

@@ -110,6 +110,7 @@ func newTestApp(
 				return r
 			},
 			middleware.New,
+			delivery.NewGuard,
 			handlers.New,
 		),
 		fx.Populate(targets...),

internal/handlers/logbound_test.go

@@ -339,11 +339,9 @@ const storedUserPassword = "correct-horse-battery-staple"
 // storedFillBytes is the raw length of the client-chosen value in
 // those accounts' usernames. It is well past the 512-byte field
 // budget, so the line is still truncated, but short enough that the
-// session cookie a successful login writes stays inside
+// whole username, markers and fill name included, stays within
-// securecookie's 4 KB limit: the cookie is written BEFORE the
+// database.MaxUsernameBytes.
-// "user logged in" line, so an 8 KB username answers 500 and never
+const storedFillBytes = 960
-// reaches it.
-const storedFillBytes = 1024
 
 // storedFill builds a username fill of storedFillBytes raw bytes out
 // of repetitions of ch, with both markers at its far end.

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_logs_deleted_target_test.go

@@ -0,0 +1,144 @@
+package handlers_test
+
+import (
+	"net/http"
+	"net/http/httptest"
+	"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"
+)
+
+// deletedMarker is the suffix the event log appends to the name
+// of a target that no longer exists.
+const deletedMarker = " (deleted)"
+
+// deleteTargetThroughHandler removes a target through the real
+// deletion handler, so the test soft-deletes exactly the way the
+// UI does rather than by writing the timestamp itself.
+func deleteTargetThroughHandler(
+	t *testing.T,
+	h *handlers.Handlers,
+	sess *session.Session,
+	webhookID, targetID string,
+) {
+	t.Helper()
+
+	req := postRequest(
+		"/source/"+webhookID+"/targets/"+targetID+"/delete",
+		authenticatedCookies(
+			t, sess, deleteTestUserID, deleteTestUsername,
+		),
+		map[string]string{
+			paramSourceID: webhookID,
+			paramTargetID: targetID,
+		},
+	)
+	w := httptest.NewRecorder()
+
+	h.HandleTargetDelete().ServeHTTP(w, req)
+
+	require.Equal(t, http.StatusSeeOther, w.Code)
+}
+
+// TestHandleSourceLogs_NamesDeletedTarget proves a delivery
+// produced by a since-deleted target still names it on the event
+// log, marked as deleted.
+//
+// Deletes are soft and deliveries carry no foreign key to the
+// target row, so the history outlives the target. Against a
+// scoped lookup the delivery resolves to a zero view and the page
+// renders ": delivered" with nothing saying what it was delivered
+// to.
+func TestHandleSourceLogs_NamesDeletedTarget(t *testing.T) {
+	t.Parallel()
+
+	var (
+		h     *handlers.Handlers
+		sess  *session.Session
+		db    *database.Database
+		dbMgr *database.WebhookDBManager
+	)
+
+	app := newTestApp(t, &h, &sess, &db, &dbMgr)
+	app.RequireStart()
+
+	t.Cleanup(app.RequireStop)
+
+	wh := seedWebhook(t, db)
+	tgt := seedTarget(t, db, wh.ID, database.TargetTypeLog)
+
+	seedDeliveredEvent(t, dbMgr, wh.ID, tgt.ID)
+
+	// The control: the name is on the page while the target
+	// lives, and is not yet marked as deleted.
+	before := renderSourceLogsPage(t, h, sess, wh.ID)
+	assert.Contains(t, before, tgt.Name)
+	assert.NotContains(t, before, tgt.Name+deletedMarker)
+
+	deleteTargetThroughHandler(t, h, sess, wh.ID, tgt.ID)
+
+	after := renderSourceLogsPage(t, h, sess, wh.ID)
+
+	assert.Contains(
+		t, after, tgt.Name+deletedMarker,
+		"a delivery from a deleted target must keep its name, "+
+			"marked as no longer existing",
+	)
+	assert.Contains(
+		t, after, "delivered",
+		"the delivery history itself must survive the delete",
+	)
+}
+
+// TestHandleSourceLogs_MasksDeletedTargetConfig proves that
+// naming a deleted target does not widen what the page shows of
+// it: its stored configuration stays masked by exactly the rules
+// a live target's is.
+//
+// The lookup behind the name reads soft-deleted rows, so it
+// carries a full target row — credential blob included — into the
+// place a zero value used to sit. The projection to TargetView is
+// what keeps that blob away from the template, and it must hold
+// for a deleted row too.
+func TestHandleSourceLogs_MasksDeletedTargetConfig(t *testing.T) {
+	t.Parallel()
+
+	var (
+		h     *handlers.Handlers
+		sess  *session.Session
+		db    *database.Database
+		dbMgr *database.WebhookDBManager
+	)
+
+	app := newTestApp(t, &h, &sess, &db, &dbMgr)
+	app.RequireStart()
+
+	t.Cleanup(app.RequireStop)
+
+	wh := seedWebhook(t, db)
+	tgt := seedConfiguredTarget(
+		t, db, wh.ID,
+		database.TargetTypeSlack,
+		`{"webhookUrl":"`+slackWebhookURL+`"}`,
+	)
+
+	seedDeliveredEvent(t, dbMgr, wh.ID, tgt.ID)
+	deleteTargetThroughHandler(t, h, sess, wh.ID, tgt.ID)
+
+	body := renderSourceLogsPage(t, h, sess, wh.ID)
+
+	assert.NotContains(t, body, slackSecretPath)
+	assert.NotContains(t, body, "T00000000")
+	assert.NotContains(t, body, "B00000000")
+	assert.NotContains(
+		t, body, "XXXXXXXXXXXXXXXXXXXXXXXX",
+	)
+	assert.NotContains(t, body, "webhookUrl")
+
+	// The name is there; only the credential is not.
+	assert.Contains(t, body, tgt.Name+deletedMarker)
+}

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.
@@ -821,25 +843,31 @@ func (h *Handlers) HandleSourceLogs() http.HandlerFunc {
 			totalPages++
 		}
 
-		// The banner a replay POST redirected back with. The
+		// The banner a replay or resubmit POST redirected back
-		// message comes from a fixed set keyed by the outcome
+		// with. The message comes from a fixed set keyed by the
-		// code, never from the query string itself.
+		// outcome code, never from the query string itself.
 		replayMsg, replayOK := replayOutcome(
 			r.URL.Query().Get(replayOutcomeParam),
 		)
 
+		resubmitMsg, resubmitOK := resubmitOutcome(
+			r.URL.Query().Get(resubmitOutcomeParam),
+		)
+
 		data := map[string]any{
-			tmplKeyWebhook:  &webhook,
+			tmplKeyWebhook:    &webhook,
-			"Events":        evts,
+			"Events":          evts,
-			"ReplayMessage": replayMsg,
+			"ReplayMessage":   replayMsg,
-			"ReplayQueued":  replayOK,
+			"ReplayQueued":    replayOK,
-			"Page":          page,
+			"ResubmitMessage": resubmitMsg,
-			"TotalPages":    totalPages,
+			"ResubmitQueued":  resubmitOK,
-			"TotalEvents":   total,
+			"Page":            page,
-			"HasPrev":       page > 1,
+			"TotalPages":      totalPages,
-			"HasNext":       page < totalPages,
+			"TotalEvents":     total,
-			"PrevPage":      page - 1,
+			"HasPrev":         page > 1,
-			"NextPage":      page + 1,
+			"HasNext":         page < totalPages,
+			"PrevPage":        page - 1,
+			"NextPage":        page + 1,
 		}
 
 		h.renderTemplate(w, r, "source_logs.html", data)
@@ -854,11 +882,16 @@ func (h *Handlers) HandleSourceLogs() http.HandlerFunc {
 //
 // The load is Unscoped because deleting a target only soft
 // deletes the row while its deliveries survive in the
-// per-webhook database: a scoped load leaves those deliveries
+// per-webhook database. Both halves of the map need those rows:
-// with a zero redactor, which renders their response bodies
+// a scoped load leaves an old delivery with a zero redactor,
-// unredacted. Only the redactor half of the map is built from
+// which renders its response bodies unredacted, and with a zero
-// deleted rows. The view half, which is what the page lists,
+// view, which renders its target as a blank name.
-// stays scoped.
+//
+// This map is historical display only. It is built for the event
+// log page and reaches nothing but DeliveryView.Target: the
+// target list on the source detail page, the edit form and the
+// replay path each resolve targets themselves, and a deleted row
+// is refused there as before.
 func (h *Handlers) loadTargetMap(
 	webhookID string,
 ) (map[string]eventLogTarget, error) {
@@ -874,21 +907,18 @@ func (h *Handlers) loadTargetMap(
 	targetMap := make(
 		map[string]eventLogTarget, len(targets),
 	)
-	live := make([]database.Target, 0, len(targets))
 
 	for i := range targets {
 		targetMap[targets[i].ID] = eventLogTarget{
 			Redactor: delivery.NewRedactor(&targets[i]),
 		}
-
-		if !targets[i].DeletedAt.Valid {
-			live = append(live, targets[i])
-		}
 	}
 
 	// The views come from NewTargetViews rather than being
-	// rebuilt here, so the masking rules stay in one place.
+	// rebuilt here, so the masking rules stay in one place and a
-	for _, v := range delivery.NewTargetViews(live) {
+	// deleted target's configuration is masked by the same code
+	// that masks a live one's.
+	for _, v := range delivery.NewTargetViews(targets) {
 		entry := targetMap[v.ID]
 		entry.View = v
 		targetMap[v.ID] = entry
@@ -899,16 +929,7 @@ func (h *Handlers) loadTargetMap(
 
 // parsePage extracts a page number from the query string.
 func (h *Handlers) parsePage(r *http.Request) int {
-	page := 1
+	return pageOrFirst(r.URL.Query().Get("page"))
-
-	if p := r.URL.Query().Get("page"); p != "" {
-		v, err := strconv.Atoi(p)
-		if err == nil && v > 0 {
-			page = v
-		}
-	}
-
-	return page
 }
 
 // loadEventsWithDeliveries loads paginated events and their
@@ -925,12 +946,10 @@ func (h *Handlers) loadEventsWithDeliveries(
 	targetMap map[string]eventLogTarget,
 	page int,
 ) ([]EventLogView, int64, bool) {
-	var totalEvents int64
-
 	var result []EventLogView
 
 	if !h.dbMgr.DBExists(webhook.ID) {
-		return result, totalEvents, true
+		return result, 0, true
 	}
 
 	webhookDB, err := h.dbMgr.GetDB(webhook.ID)
@@ -942,29 +961,20 @@ func (h *Handlers) loadEventsWithDeliveries(
 		return nil, 0, false
 	}
 
-	webhookDB.Model(&database.Event{}).Where(
+	rows, totalEvents := loadEventLogRows(
-		"webhook_id = ?", webhook.ID,
+		webhookDB, webhook.ID, page,
-	).Count(&totalEvents)
+	)
-
-	offset := (page - 1) * paginationPerPage
-
-	var rows []eventLogRow
-
-	webhookDB.Model(&database.Event{}).Select(
-		eventLogColumns, maxRenderedBodyBytes,
-	).Where(
-		"webhook_id = ?", webhook.ID,
-	).Order("created_at DESC").Offset(offset).Limit(
-		paginationPerPage,
-	).Find(&rows)
 
 	result = make([]EventLogView, len(rows))
 	eventDeliveries := make([][]database.Delivery, len(rows))
 
 	var deliveryIDs []string
 
+	eventIDs := make([]string, len(rows))
+
 	for i := range rows {
 		result[i] = rows[i].view()
+		eventIDs[i] = rows[i].ID
 
 		webhookDB.Where(
 			"event_id = ?", rows[i].ID,
@@ -988,15 +998,86 @@ func (h *Handlers) loadEventsWithDeliveries(
 		return nil, 0, false
 	}
 
+	resubmits, err := resubmitCounts(webhookDB, eventIDs)
+	if err != nil {
+		h.serverError(
+			w, "failed to count event resubmissions", err,
+		)
+
+		return nil, 0, false
+	}
+
 	for i := range rows {
 		result[i].Deliveries = newDeliveryViews(
 			eventDeliveries[i], targetMap, attempts,
 		)
+		result[i].ResubmitCount = resubmits[rows[i].ID]
 	}
 
 	return result, totalEvents, true
 }
 
+// loadEventLogRows reads one page of the event log projection, newest
+// first, and the total number of events the pager counts against.
+func loadEventLogRows(
+	webhookDB *gorm.DB, webhookID string, page int,
+) ([]eventLogRow, int64) {
+	var totalEvents int64
+
+	webhookDB.Model(&database.Event{}).Where(
+		"webhook_id = ?", webhookID,
+	).Count(&totalEvents)
+
+	var rows []eventLogRow
+
+	webhookDB.Model(&database.Event{}).Select(
+		eventLogColumns, maxRenderedBodyBytes,
+	).Where(
+		"webhook_id = ?", webhookID,
+	).Order("created_at DESC").Offset(
+		(page - 1) * paginationPerPage,
+	).Limit(paginationPerPage).Find(&rows)
+
+	return rows, totalEvents
+}
+
+// resubmitCounts reports, for each of the page's events, how many
+// events have been resubmitted from it.
+//
+// One grouped query covers the page rather than one query per event.
+// A page holds paginationPerPage ids, far below SQLite's bound
+// parameter ceiling, so it needs no chunking as the delivery result
+// load does.
+func resubmitCounts(
+	webhookDB *gorm.DB, eventIDs []string,
+) (map[string]int, error) {
+	counts := make(map[string]int, len(eventIDs))
+
+	if len(eventIDs) == 0 {
+		return counts, nil
+	}
+
+	var rows []struct {
+		ResubmittedFromID string
+		Total             int
+	}
+
+	err := webhookDB.Model(&database.Event{}).
+		Select("resubmitted_from_id, count(*) AS total").
+		Where("resubmitted_from_id IN ?", eventIDs).
+		Group("resubmitted_from_id").
+		Find(&rows).Error
+	if err != nil {
+		return nil, err
+	}
+
+	for _, row := range rows {
+		counts[row.ResubmittedFromID] = row.Total
+	}
+
+	return counts, nil
+}
+
 // deliveryIDChunkSize bounds how many delivery IDs go into one
 // IN clause. SQLite refuses a statement carrying more than
 // SQLITE_MAX_VARIABLE_NUMBER (32766) bound parameters, and a
@@ -1181,145 +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) {
@@ -1377,7 +1319,6 @@ func (h *Handlers) processTargetCreate(
 	// Referer headers and error trackers record.
 	name := r.PostFormValue("name")
 	targetType := database.TargetType(r.PostFormValue("type"))
-	maxRetriesStr := r.PostFormValue("max_retries")
 
 	if name == "" {
 		http.Error(
@@ -1403,7 +1344,14 @@ func (h *Handlers) processTargetCreate(
 		return
 	}
 
-	maxRetries := parseNonNegativeInt(maxRetriesStr)
+	// A new target has no stored retry count, so an absent field
+	// takes the fire-and-forget default. A field the operator filled
+	// in with something invalid is rejected rather than becoming
+	// that default.
+	maxRetries, ok := targetMaxRetries(w, r, 0)
+	if !ok {
+		return
+	}
 
 	target := &database.Target{
 		WebhookID:  webhook.ID,
@@ -1439,19 +1387,22 @@ func isValidTargetType(tt database.TargetType) bool {
 	}
 }
 
-// parseNonNegativeInt parses s as a non-negative integer,
+// pageOrFirst parses a paginated page number, answering 1 for
-// returning 0 if s is empty or invalid.
+// anything empty, unparseable or out of range.
-func parseNonNegativeInt(s string) int {
+//
-	if s == "" {
+// Falling back rather than rejecting is correct here and only here:
-		return 0
+// a page number is where to send the browser next, not configuration
+// the operator is storing, and the actions that submit one have
+// already completed by the time it is read — answering 400 would
+// report a failure that did not happen. Anything an operator SETS
+// must be validated instead; see parseMaxRetries.
+func pageOrFirst(s string) int {
+	v, err := strconv.Atoi(strings.TrimSpace(s))
+	if err != nil || v < 1 {
+		return 1
 	}
 
-	v, err := strconv.Atoi(s)
+	return v
-	if err == nil && v >= 0 {
-		return v
-	}
-
-	return 0
 }
 
 // targetFormInput carries the raw form values describing a target's
@@ -1607,7 +1558,7 @@ func (h *Handlers) validateTargetURL(
 		return errMissingURL
 	}
 
-	err := delivery.ValidateTargetURL(
+	err := h.ssrf.ValidateTargetURL(
 		r.Context(), targetURL,
 	)
 	if err != nil {

internal/handlers/target_edit.go

@@ -133,20 +133,28 @@ func (h *Handlers) applyTargetEdit(
 		return
 	}
 
-	target.Name = name
-	target.Config = configJSON
-
 	// Retries are offered only by the forms for target types that
 	// retry, so an absent field means "this form does not edit
 	// retries" rather than "set them to zero". Reading it
 	// unconditionally would silently disable retries on any target
 	// saved from a form that does not render the input.
+	//
+	// A field that IS submitted but does not parse is a 400, through
+	// the same validator the create path uses. It is rejected before
+	// anything is written, so a typo cannot destroy the retry count
+	// the target is already delivering with.
 	if r.PostForm.Has("max_retries") {
-		target.MaxRetries = parseNonNegativeInt(
+		retries, ok := targetMaxRetries(w, r, target.MaxRetries)
-			r.PostFormValue("max_retries"),
+		if !ok {
-		)
+			return
+		}
+
+		target.MaxRetries = retries
 	}
 
+	target.Name = name
+	target.Config = configJSON
+
 	err = h.db.DB().Save(target).Error
 	if err != nil {
 		h.serverError(w, "failed to update target", err)

internal/handlers/target_retries.go

@@ -0,0 +1,119 @@
+package handlers
+
+import (
+	"errors"
+	"net/http"
+	"strconv"
+	"strings"
+)
+
+// maxTargetRetries bounds a target's max_retries.
+//
+// Both target forms already declare max="20" on the input, so this
+// enforces server-side what the UI has always advertised rather than
+// introducing a new limit.
+//
+// The number is not cosmetic. Every attempt writes a delivery_results
+// row that the event log then loads and renders, and the engine backs
+// off by 2^(n-1) seconds, so attempt 20 is already about six days
+// after the first. A value beyond this buys no additional durability
+// and only costs rows.
+const maxTargetRetries = 20
+
+// Errors returned when a max_retries form value cannot be turned into
+// a retry count.
+var (
+	// errRetriesInvalid signals a max_retries form value that is not
+	// a non-negative whole number.
+	errRetriesInvalid = errors.New(
+		"retries must be a whole number of attempts",
+	)
+
+	// errRetriesTooLarge signals a max_retries form value that is a
+	// whole number but above maxTargetRetries. It is distinguished
+	// from errRetriesInvalid so the message can name the ceiling
+	// instead of implying the input was not a number.
+	errRetriesTooLarge = errors.New("retries out of range")
+)
+
+// parseMaxRetries interprets a max_retries form value.
+//
+// An ABSENT value — the field empty or not submitted — yields
+// fallback, which lets the create path apply its default and the edit
+// path leave the stored value alone. A value that is SET BUT INVALID
+// is an error: unparseable, negative, or above maxTargetRetries.
+//
+// The distinction is the whole point of this function. max_retries=0
+// means fire-and-forget, so returning 0 for input the operator typed
+// but that did not parse silently disables retries on a
+// store-and-forward proxy — and on the edit path it destroys a
+// working retry configuration over a typo. A default answers a
+// question that was not asked; it never answers one that was asked
+// badly.
+//
+// A target stored with a count above the ceiling before this
+// validation existed keeps rendering and keeps delivering — nothing
+// clamps the row. Re-saving it from the edit form does have to bring
+// it into range, because the form submits the pre-filled value back
+// and accepting it would be the ceiling not applying to the edit
+// path. The 400 names the ceiling, so the fix is one field.
+func parseMaxRetries(raw string, fallback int) (int, error) {
+	raw = strings.TrimSpace(raw)
+	if raw == "" {
+		return fallback, nil
+	}
+
+	v, err := strconv.Atoi(raw)
+	if err != nil || v < 0 {
+		return 0, errRetriesInvalid
+	}
+
+	if v > maxTargetRetries {
+		return 0, errRetriesTooLarge
+	}
+
+	return v, nil
+}
+
+// retriesErrorMessage returns the message the create and edit forms
+// show for a rejected max_retries value. Any error other than
+// errRetriesTooLarge falls back to the generic wording, so an
+// unrecognised parse failure still produces a sensible 400.
+func retriesErrorMessage(err error) string {
+	if errors.Is(err, errRetriesTooLarge) {
+		return errRetriesTooLarge.Error() +
+			": at most " + strconv.Itoa(maxTargetRetries) +
+			" retries"
+	}
+
+	return errRetriesInvalid.Error() +
+		", or 0 for fire-and-forget"
+}
+
+// targetMaxRetries reads and validates max_retries from a target form
+// submission, answering the request with a 400 and reporting false
+// when the value is set but invalid.
+//
+// Both the create and the edit path go through here, so the two
+// cannot come to disagree about what a valid retry count is. The
+// wording matches the timeout control on the same submission.
+func targetMaxRetries(
+	w http.ResponseWriter,
+	r *http.Request,
+	fallback int,
+) (int, bool) {
+	retries, err := parseMaxRetries(
+		r.PostFormValue("max_retries"), fallback,
+	)
+	if err != nil {
+		http.Error(
+			w,
+			"Invalid max retries: "+retriesErrorMessage(err),
+			http.StatusBadRequest,
+		)
+
+		return 0, false
+	}
+
+	return retries, true
+}

internal/handlers/target_retries_test.go

@@ -0,0 +1,402 @@
+package handlers_test
+
+import (
+	"net/http"
+	"net/url"
+	"strconv"
+	"testing"
+
+	"github.com/stretchr/testify/assert"
+	"github.com/stretchr/testify/require"
+	"sneak.berlin/go/webhooker/internal/database"
+	"sneak.berlin/go/webhooker/internal/handlers"
+)
+
+// retriesTargetURL is the destination the retry-validation targets
+// point at. It is a literal public address rather than a hostname so
+// the SSRF check resolves nothing and a sandbox without DNS cannot
+// make these cases pass or fail for the wrong reason.
+const retriesTargetURL = "https://93.184.216.34/hooks/retries"
+
+const (
+	// wayAboveCeiling is the typo'd-extra-zero case from the report.
+	wayAboveCeiling = "999999999"
+
+	// notANumber is the plainest garbage an operator can type, and
+	// the value the report submitted on the edit form.
+	notANumber = "abc"
+
+	// workingRetries is the retry count a seeded target is already
+	// delivering with, which a rejected submission must not disturb.
+	workingRetries = 2
+)
+
+// aboveCeiling is the smallest rejected whole number.
+func aboveCeiling() string {
+	return strconv.Itoa(handlers.MaxTargetRetriesForTest + 1)
+}
+
+// overCeilingRetries is whole-number input past the limit, which is
+// rejected with the limit named.
+func overCeilingRetries() []string {
+	return []string{aboveCeiling(), wayAboveCeiling}
+}
+
+// unparseableRetries is input an operator can type into the field
+// that is not a retry count. Each must be REJECTED: silently reading
+// any of them as 0 turns a store-and-forward proxy into
+// fire-and-forget without saying so.
+//
+// The twenty-digit case is here because it parses as digits but
+// overflows int, which is the one failure the field's own min/max
+// attributes cannot describe.
+func unparseableRetries() []string {
+	return []string{
+		notANumber,
+		"2.7",
+		"-5",
+		"12345678901234567890",
+		"1e3",
+	}
+}
+
+// createRetriesForm is a complete, otherwise-valid HTTP target
+// creation, so the only thing any case below varies is max_retries.
+func createRetriesForm(retries string) url.Values {
+	form := url.Values{}
+	form.Set("name", "retries-target")
+	form.Set("type", string(database.TargetTypeHTTP))
+	form.Set("url", retriesTargetURL)
+
+	if retries != absentField {
+		form.Set("max_retries", retries)
+	}
+
+	return form
+}
+
+// absentField marks a field the form does not submit at all, which is
+// the case that legitimately takes a default and must stay distinct
+// from a field submitted with garbage in it.
+const absentField = "\x00absent"
+
+// absentRetries is every way of saying "the operator did not set
+// this", each of which takes the default rather than a 400. Blank and
+// whitespace-only count as absent here because they do in the timeout
+// and retention controls on the same forms; a rule the fields do not
+// share would be its own surprise.
+func absentRetries() []string {
+	return []string{absentField, "", "  "}
+}
+
+// createWithRetries posts the target create form for a fresh webhook
+// and returns the webhook and the response.
+func createWithRetries(
+	t *testing.T,
+	env *sourceTestEnv,
+	retries string,
+) (database.Webhook, int, string) {
+	t.Helper()
+
+	webhook := seedWebhookWithRetention(t, env.db, 30)
+
+	w := serveTarget(
+		env, http.MethodPost,
+		"/source/"+webhook.ID+"/targets",
+		createRetriesForm(retries),
+	)
+
+	return webhook, w.Code, w.Body.String()
+}
+
+// TestTargetCreate_RetriesAboveCeilingRejected proves the create form
+// enforces a ceiling at all, and that the 400 names it — a rejection
+// that does not say what the limit is leaves the operator guessing.
+func TestTargetCreate_RetriesAboveCeilingRejected(t *testing.T) {
+	t.Parallel()
+
+	env := setupSourceTest(t)
+	ceiling := strconv.Itoa(handlers.MaxTargetRetriesForTest)
+
+	for _, retries := range overCeilingRetries() {
+		webhook, code, body := createWithRetries(t, env, retries)
+
+		assert.Equal(t, http.StatusBadRequest, code,
+			"max_retries=%s should be rejected", retries)
+		assert.Contains(t, body, ceiling,
+			"the rejection for %s should name the ceiling",
+			retries)
+		assert.Empty(t,
+			targetsForWebhook(t, env.db, webhook.ID),
+			"no target should be created for %s", retries)
+	}
+}
+
+// TestTargetCreate_UnparseableRetriesRejected is the core of the
+// defect: each of these was accepted with HTTP 200 and stored as 0.
+func TestTargetCreate_UnparseableRetriesRejected(t *testing.T) {
+	t.Parallel()
+
+	env := setupSourceTest(t)
+
+	for _, retries := range unparseableRetries() {
+		webhook, code, body := createWithRetries(t, env, retries)
+
+		assert.Equal(t, http.StatusBadRequest, code,
+			"max_retries=%q should be rejected, not coerced",
+			retries)
+		assert.Contains(t, body, "whole number",
+			"the rejection for %q should say why", retries)
+		assert.Empty(t,
+			targetsForWebhook(t, env.db, webhook.ID),
+			"no target should be created for %q", retries)
+	}
+}
+
+// TestTargetCreate_ValidRetriesStored covers the accepting half,
+// including the ceiling itself: a bound that rejects its own limit
+// would make the advertised maximum unreachable.
+func TestTargetCreate_ValidRetriesStored(t *testing.T) {
+	t.Parallel()
+
+	env := setupSourceTest(t)
+
+	for _, want := range []int{0, 3, handlers.MaxTargetRetriesForTest} {
+		webhook, code, body := createWithRetries(
+			t, env, strconv.Itoa(want),
+		)
+
+		require.Equal(t, http.StatusSeeOther, code, body)
+
+		targets := targetsForWebhook(t, env.db, webhook.ID)
+		require.Len(t, targets, 1)
+		assert.Equal(t, want, targets[0].MaxRetries)
+	}
+}
+
+// TestTargetCreate_AbsentRetriesTakesDefault keeps the two cases
+// distinct. An omitted field is not an operator asking for something
+// invalid, so it still gets the fire-and-forget default rather than a
+// 400 — otherwise the fix above would make the form unusable.
+func TestTargetCreate_AbsentRetriesTakesDefault(t *testing.T) {
+	t.Parallel()
+
+	env := setupSourceTest(t)
+
+	for _, retries := range absentRetries() {
+		webhook, code, body := createWithRetries(t, env, retries)
+
+		require.Equal(t, http.StatusSeeOther, code, body)
+
+		targets := targetsForWebhook(t, env.db, webhook.ID)
+		require.Len(t, targets, 1)
+		assert.Equal(t, 0, targets[0].MaxRetries,
+			"an absent max_retries should take the default")
+	}
+}
+
+// seedRetriesTarget creates an HTTP target already delivering with
+// workingRetries retries, through the real create handler.
+func seedRetriesTarget(
+	t *testing.T,
+	env *sourceTestEnv,
+) (database.Webhook, database.Target) {
+	t.Helper()
+
+	webhook, code, body := createWithRetries(
+		t, env, strconv.Itoa(workingRetries),
+	)
+	require.Equal(t, http.StatusSeeOther, code, body)
+
+	targets := targetsForWebhook(t, env.db, webhook.ID)
+	require.Len(t, targets, 1)
+	require.Equal(t, workingRetries, targets[0].MaxRetries)
+
+	return webhook, targets[0]
+}
+
+// editRetriesForm is a complete edit submission that changes the
+// target's name as well, so a rejected submission can be shown to
+// have written nothing at all rather than merely to have left
+// max_retries alone.
+func editRetriesForm(retries string) url.Values {
+	form := url.Values{}
+	form.Set("name", "renamed-by-edit")
+	form.Set("url", retriesTargetURL)
+
+	if retries != absentField {
+		form.Set("max_retries", retries)
+	}
+
+	return form
+}
+
+// assertEditRejectedAndUnchanged submits an edit expected to fail and
+// checks both halves of the requirement: the 400 explains itself, and
+// the target it was submitted against is untouched.
+func assertEditRejectedAndUnchanged(
+	t *testing.T,
+	env *sourceTestEnv,
+	retries, wantReason string,
+) {
+	t.Helper()
+
+	webhook, target := seedRetriesTarget(t, env)
+
+	w := submitTargetEdit(
+		env, webhook.ID, target.ID, editRetriesForm(retries),
+	)
+
+	assert.Equal(t, http.StatusBadRequest, w.Code,
+		"max_retries=%q should be rejected on edit", retries)
+	assert.Contains(t, w.Body.String(), wantReason,
+		"the rejection for %q should say why", retries)
+
+	stored := storedTarget(t, env, target.ID)
+	assert.Equal(t, workingRetries, stored.MaxRetries,
+		"a rejected edit must not destroy the working retry "+
+			"count with %q", retries)
+	assert.Equal(t, "retries-target", stored.Name,
+		"a rejected edit must write nothing at all")
+}
+
+// TestTargetEdit_UnparseableRetriesRejected is the damaging half of
+// the defect. A target delivering with two retries, re-saved with a
+// typo in the field, returned 200 and was left with retries disabled
+// and nothing said.
+func TestTargetEdit_UnparseableRetriesRejected(t *testing.T) {
+	t.Parallel()
+
+	env := setupSourceTest(t)
+
+	for _, retries := range unparseableRetries() {
+		assertEditRejectedAndUnchanged(
+			t, env, retries, "whole number",
+		)
+	}
+}
+
+// TestTargetEdit_RetriesAboveCeilingRejected proves the ceiling
+// applies to the edit path too, naming itself, so the two paths
+// cannot disagree about what is storable.
+func TestTargetEdit_RetriesAboveCeilingRejected(t *testing.T) {
+	t.Parallel()
+
+	env := setupSourceTest(t)
+	ceiling := strconv.Itoa(handlers.MaxTargetRetriesForTest)
+
+	for _, retries := range overCeilingRetries() {
+		assertEditRejectedAndUnchanged(t, env, retries, ceiling)
+	}
+}
+
+// TestTargetEdit_ValidRetriesStored covers the accepting half of the
+// edit path, so the ceiling cannot be enforced by simply refusing
+// every submission.
+func TestTargetEdit_ValidRetriesStored(t *testing.T) {
+	t.Parallel()
+
+	env := setupSourceTest(t)
+
+	for _, want := range []int{0, 9, handlers.MaxTargetRetriesForTest} {
+		webhook, target := seedRetriesTarget(t, env)
+
+		w := submitTargetEdit(
+			env, webhook.ID, target.ID,
+			editRetriesForm(strconv.Itoa(want)),
+		)
+		require.Equal(t,
+			http.StatusSeeOther, w.Code, w.Body.String(),
+		)
+
+		assert.Equal(t, want,
+			storedTarget(t, env, target.ID).MaxRetries)
+	}
+}
+
+// TestTargetEdit_AbsentRetriesLeavesStoredValue is the edit path's
+// absent-versus-invalid case. Retries are only offered by the forms
+// for types that retry, so a submission without the field must leave
+// the stored count alone rather than be rejected or zeroed.
+func TestTargetEdit_AbsentRetriesLeavesStoredValue(t *testing.T) {
+	t.Parallel()
+
+	env := setupSourceTest(t)
+
+	for _, retries := range absentRetries() {
+		webhook, target := seedRetriesTarget(t, env)
+
+		w := submitTargetEdit(
+			env, webhook.ID, target.ID,
+			editRetriesForm(retries),
+		)
+		require.Equal(t,
+			http.StatusSeeOther, w.Code, w.Body.String(),
+		)
+
+		assert.Equal(t, workingRetries,
+			storedTarget(t, env, target.ID).MaxRetries,
+			"an absent max_retries must leave the stored "+
+				"count alone (%q)", retries)
+	}
+}
+
+// TestTargetRetries_CreateAndEditAgreeOnEveryCase proves the two
+// paths cannot disagree, which is what let the create form and the
+// edit form drift apart in the first place. Every input is submitted
+// to both and the accept/reject verdicts are compared.
+func TestTargetRetries_CreateAndEditAgreeOnEveryCase(t *testing.T) {
+	t.Parallel()
+
+	env := setupSourceTest(t)
+
+	accepted := []string{
+		"0", "1",
+		strconv.Itoa(handlers.MaxTargetRetriesForTest),
+	}
+	overCeiling := overCeilingRetries()
+	unparseable := unparseableRetries()
+
+	cases := make(
+		[]string, 0,
+		len(accepted)+len(overCeiling)+len(unparseable),
+	)
+	cases = append(cases, accepted...)
+	cases = append(cases, overCeiling...)
+	cases = append(cases, unparseable...)
+
+	for _, retries := range cases {
+		_, createCode, _ := createWithRetries(t, env, retries)
+
+		webhook, target := seedRetriesTarget(t, env)
+		editCode := submitTargetEdit(
+			env, webhook.ID, target.ID,
+			editRetriesForm(retries),
+		).Code
+
+		assert.Equal(t,
+			createCode == http.StatusBadRequest,
+			editCode == http.StatusBadRequest,
+			"create and edit must agree on max_retries=%q "+
+				"(create %d, edit %d)",
+			retries, createCode, editCode,
+		)
+	}
+}
+
+// TestPageOrFirst_CoercesRatherThanRejects pins the one place a
+// non-numeric form value legitimately falls back. A page number says
+// where to send the browser after an action that has already
+// happened, so it is not configuration and rejecting it would report
+// a failure that did not occur.
+func TestPageOrFirst_CoercesRatherThanRejects(t *testing.T) {
+	t.Parallel()
+
+	for _, s := range []string{"", "abc", "0", "-1", "2.7", " "} {
+		assert.Equal(t, 1, handlers.PageOrFirstForTest(s),
+			"%q should fall back to the first page", s)
+	}
+
+	assert.Equal(t, 4, handlers.PageOrFirstForTest("4"))
+	assert.Equal(t, 4, handlers.PageOrFirstForTest(" 4 "))
+}

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(
@@ -302,3 +300,80 @@ func TestEntrypointCopyButtonIsProgressiveEnhancement(t *testing.T) {
 		"the page must render to completion, not abort partway",
 	)
 }
+
+// maxRetriesHelp is the wording both target forms must carry. The
+// delivery core makes max_retries attempts in total, not that many
+// retries on top of a first try (a fresh delivery starts at attempt 1
+// and target_http gives up once the attempt number reaches
+// max_retries), and 0 is special-cased to a single fire-and-forget
+// attempt with no circuit breaker.
+const maxRetriesHelp = "This is the total number of delivery attempts, " +
+	"not retries on top of the first: a value of 3 makes three attempts " +
+	"in all. 0 means a single attempt with no retries and no circuit " +
+	"breaker."
+
+// TestTargetFormMaxRetriesCopyMatchesBehaviour pins the max_retries
+// help text on both the create form (the add-target form on the webhook
+// detail page) and the edit form, so the copy cannot drift back to
+// calling the number a retry count.
+func TestTargetFormMaxRetriesCopyMatchesBehaviour(t *testing.T) {
+	t.Parallel()
+
+	var h *handlers.Handlers
+
+	var sess *session.Session
+
+	app := newTestApp(t, &h, &sess)
+	app.RequireStart()
+
+	t.Cleanup(app.RequireStop)
+
+	webhook := &database.Webhook{Name: "wh", RetentionDays: 14}
+	webhook.ID = testWebhookID
+
+	entrypoint := database.Entrypoint{Path: "abc123"}
+	entrypoint.ID = "ep-1"
+
+	createBody := renderPage(
+		t, h, sess, "source_detail.html", map[string]any{
+			dataKeyWebhook: webhook,
+			"Entrypoints": handlers.NewEntrypointViews(
+				[]database.Entrypoint{entrypoint},
+			),
+			"Targets": delivery.NewTargetViews(nil),
+			"Events":  []database.Event{},
+			"BaseURL": "https://hooks.example.com",
+		},
+	)
+
+	assert.Contains(
+		t, createBody, maxRetriesHelp,
+		"the add-target form must explain max_retries as total attempts",
+	)
+
+	// A slack target exercises the same max_retries field while needing
+	// only Config.URL from the edit template, so the test data stays
+	// minimal. The Target key mirrors the field names the template reads
+	// off the handler's view value.
+	editBody := renderPage(
+		t, h, sess, "target_edit.html", map[string]any{
+			dataKeyWebhook: webhook,
+			"Target": map[string]any{
+				"ID":         "tg-1",
+				"Name":       "t",
+				"Type":       "slack",
+				"Active":     true,
+				"MaxRetries": 3,
+				"Config": map[string]any{
+					"URL": "https://hooks.slack.com/services/x",
+				},
+			},
+			dataKeyError: "",
+		},
+	)
+
+	assert.Contains(
+		t, editBody, maxRetriesHelp,
+		"the target edit form must explain max_retries as total attempts",
+	)
+}

internal/handlers/webhook.go

@@ -2,7 +2,7 @@ package handlers
 
 import (
 	"encoding/json"
-	"errors"
+	"fmt"
 	"io"
 	"net/http"
 
@@ -11,7 +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 (
@@ -71,8 +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,
@@ -83,26 +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)
 
@@ -121,63 +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,
@@ -255,8 +182,8 @@ func (h *Handlers) readWebhookBody(
 	return body, true
 }
 
-// createAndDeliverEvent creates the event and delivery records
+// createAndDeliverEvent stores the received event, fans it out to the
-// then notifies the delivery engine.
+// webhook's targets, and answers the sender.
 func (h *Handlers) createAndDeliverEvent(
 	w http.ResponseWriter,
 	r *http.Request,
@@ -264,69 +191,130 @@ func (h *Handlers) createAndDeliverEvent(
 	body, headersJSON []byte,
 	targets []database.Target,
 ) {
-	tx, err := h.beginWebhookTx(w, entrypoint.WebhookID)
+	event, tasks, err := h.createAndFanOut(
-	if err != nil {
+		requestEventSource(r, entrypoint, headersJSON, body),
-		return
+		targets,
-	}
-
-	event := h.buildEvent(r, entrypoint, headersJSON, body)
-
-	err = tx.Create(event).Error
-	if err != nil {
-		tx.Rollback()
-		h.serverError(w, "failed to create event", err)
-
-		return
-	}
-
-	bodyPtr := inlineBody(body)
-
-	tasks := h.buildDeliveryTasks(
-		w, tx, event, entrypoint, targets, bodyPtr,
 	)
-	if tasks == nil {
-		return
-	}
-
-	err = tx.Commit().Error
 	if err != nil {
-		h.serverError(w, "failed to commit transaction", err)
+		h.serverError(w, "failed to store webhook event", err)
 
 		return
 	}
 
-	// Counted here, after the commit: an event is received once it
-	// is durably stored, which is what the delivery counters are
-	// compared against on a dashboard.
-	h.mtr.EventReceived()
-
 	h.finishWebhookResponse(w, event, entrypoint, tasks)
 }
 
-// beginWebhookTx opens a transaction on the per-webhook DB.
+// eventSource carries the fields a new event is built from. The
-func (h *Handlers) beginWebhookTx(
+// receiver fills it from the live request; the resubmit handler fills
-	w http.ResponseWriter,
+// it from a stored event. Both then go through createAndFanOut, so an
-	webhookID string,
+// event is constructed and fanned out in one place however it entered
-) (*gorm.DB, error) {
+// the system.
-	webhookDB, err := h.dbMgr.GetDB(webhookID)
+type eventSource struct {
-	if err != nil {
+	WebhookID    string
-		h.serverError(
+	EntrypointID string
-			w, "failed to get webhook database", err,
+	Method       string
-		)
+	HeadersJSON  string
+	ContentType  string
+	Body         []byte
 
-		return nil, err
+	// ResubmittedFromID names the event this one copies. Only the
+	// resubmit path sets it.
+	ResubmittedFromID *string
+}
+
+// event builds the row this source stores.
+func (s eventSource) event() *database.Event {
+	return &database.Event{
+		WebhookID:         s.WebhookID,
+		EntrypointID:      s.EntrypointID,
+		Method:            s.Method,
+		Headers:           s.HeadersJSON,
+		Body:              string(s.Body),
+		ContentType:       s.ContentType,
+		ResubmittedFromID: s.ResubmittedFromID,
+	}
+}
+
+// requestEventSource describes the event a live receiver request
+// stores.
+func requestEventSource(
+	r *http.Request,
+	entrypoint database.Entrypoint,
+	headersJSON, body []byte,
+) eventSource {
+	return eventSource{
+		WebhookID:    entrypoint.WebhookID,
+		EntrypointID: entrypoint.ID,
+		Method:       r.Method,
+		HeadersJSON:  string(headersJSON),
+		ContentType:  r.Header.Get("Content-Type"),
+		Body:         body,
+	}
+}
+
+// createAndFanOut writes the event and one pending delivery per target
+// in a single transaction, then hands the tasks to the delivery
+// engine. It is the only path by which an event and its deliveries are
+// created, so a resubmitted event is retried, SSRF-guarded and
+// circuit-broken exactly as a received one is.
+//
+// The tasks are returned as well as queued, so a caller can report how
+// many targets the event went to.
+func (h *Handlers) createAndFanOut(
+	src eventSource,
+	targets []database.Target,
+) (*database.Event, []delivery.Task, error) {
+	webhookDB, err := h.dbMgr.GetDB(src.WebhookID)
+	if err != nil {
+		return nil, nil, fmt.Errorf(
+			"getting webhook database: %w", err,
+		)
 	}
 
 	tx := webhookDB.Begin()
 	if tx.Error != nil {
-		h.serverError(
+		return nil, nil, fmt.Errorf(
-			w, "failed to begin transaction", tx.Error,
+			"beginning transaction: %w", tx.Error,
 		)
-
-		return nil, tx.Error
 	}
 
-	return tx, nil
+	event := src.event()
+
+	err = tx.Create(event).Error
+	if err != nil {
+		tx.Rollback()
+
+		return nil, nil, fmt.Errorf("creating event: %w", err)
+	}
+
+	tasks, err := buildDeliveryTasks(
+		tx, event, targets, inlineBody(src.Body),
+	)
+	if err != nil {
+		tx.Rollback()
+
+		return nil, nil, err
+	}
+
+	err = tx.Commit().Error
+	if err != nil {
+		return nil, nil, fmt.Errorf(
+			"committing transaction: %w", err,
+		)
+	}
+
+	// Counted here, after the commit: an event exists once it is
+	// durably stored, which is what the delivery counters are
+	// compared against on a dashboard. A resubmitted event counts
+	// too, because it produces deliveries that the delivery side
+	// counts; the resubmit counter is what separates the two.
+	h.mtr.EventReceived()
+
+	if len(tasks) > 0 {
+		h.notifier.Notify(tasks)
+	}
+
+	return event, tasks, nil
 }
 
 // inlineBody returns a pointer to body as a string if it fits
@@ -341,18 +329,13 @@ func inlineBody(body []byte) *string {
 	return nil
 }
 
-// finishWebhookResponse notifies the delivery engine, logs the
+// finishWebhookResponse logs the event and writes the HTTP response.
-// event, and writes the HTTP response.
 func (h *Handlers) finishWebhookResponse(
 	w http.ResponseWriter,
 	event *database.Event,
 	entrypoint database.Entrypoint,
 	tasks []delivery.Task,
 ) {
-	if len(tasks) > 0 {
-		h.notifier.Notify(tasks)
-	}
-
 	h.log.Info("webhook event created",
 		"event_id", event.ID,
 		"webhook_id", entrypoint.WebhookID,
@@ -370,33 +353,15 @@ func (h *Handlers) finishWebhookResponse(
 	}
 }
 
-// buildEvent creates a new Event struct from request data.
+// buildDeliveryTasks creates one pending delivery per target in the
-func (h *Handlers) buildEvent(
+// transaction and returns the tasks for the delivery engine. The
-	r *http.Request,
+// caller owns the transaction and rolls it back on error.
-	entrypoint database.Entrypoint,
+func buildDeliveryTasks(
-	headersJSON, body []byte,
-) *database.Event {
-	return &database.Event{
-		WebhookID:    entrypoint.WebhookID,
-		EntrypointID: entrypoint.ID,
-		Method:       r.Method,
-		Headers:      string(headersJSON),
-		Body:         string(body),
-		ContentType:  r.Header.Get("Content-Type"),
-	}
-}
-
-// buildDeliveryTasks creates delivery records in the
-// transaction and returns tasks for the delivery engine.
-// Returns nil if an error occurred.
-func (h *Handlers) buildDeliveryTasks(
-	w http.ResponseWriter,
 	tx *gorm.DB,
 	event *database.Event,
-	entrypoint database.Entrypoint,
 	targets []database.Target,
 	bodyPtr *string,
-) []delivery.Task {
+) ([]delivery.Task, error) {
 	tasks := make([]delivery.Task, 0, len(targets))
 
 	for i := range targets {
@@ -408,25 +373,17 @@ func (h *Handlers) buildDeliveryTasks(
 
 		err := tx.Create(dlv).Error
 		if err != nil {
-			tx.Rollback()
+			return nil, fmt.Errorf(
-			h.log.Error(
+				"creating delivery for target %s: %w",
-				"failed to create delivery",
+				targets[i].ID, err,
-				"target_id", targets[i].ID,
-				"error", err,
 			)
-			http.Error(
-				w, "Internal server error",
-				http.StatusInternalServerError,
-			)
-
-			return nil
 		}
 
 		tasks = append(tasks, delivery.Task{
 			DeliveryID:   dlv.ID,
 			EventID:      event.ID,
-			WebhookID:    entrypoint.WebhookID,
+			WebhookID:    event.WebhookID,
-			EntrypointID: entrypoint.ID,
+			EntrypointID: event.EntrypointID,
 			TargetID:     targets[i].ID,
 			TargetName:   targets[i].Name,
 			TargetType:   targets[i].Type,
@@ -440,5 +397,5 @@ func (h *Handlers) buildDeliveryTasks(
 		})
 	}
 
-	return tasks
+	return tasks, nil
 }

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/metrics/metrics.go

@@ -83,6 +83,7 @@ type Set struct {
 	deliveriesFailed    *prometheus.CounterVec
 	deliveryRetries     *prometheus.CounterVec
 	deliveryReplays     *prometheus.CounterVec
+	eventsResubmitted   prometheus.Counter
 	deliveryDuration    *prometheus.HistogramVec
 	deliveriesPending   *prometheus.GaugeVec
 	deliveriesRetrying  *prometheus.GaugeVec
@@ -166,6 +167,23 @@ func (s *Set) DeliveryReplayed(t database.TargetType) {
 		Inc()
 }
 
+// EventResubmitted counts one stored event an operator re-injected
+// from the event log.
+//
+// It counts the operator action once, not the deliveries it fans out
+// to: those already move the attempt, outcome and duration series, and
+// the new event moves events_received_total, since it is a stored
+// event that the delivery side will be compared against. This counter
+// is what separates a resubmitted event from a received one.
+//
+// It carries no labels. The only label available at the call site
+// would be the route pattern, which has exactly one value and so would
+// distinguish nothing; the target types the event fans out to belong
+// to the delivery series, not to this one.
+func (s *Set) EventResubmitted() {
+	s.eventsResubmitted.Inc()
+}
+
 // DeliveryStatusChanged counts a delivery's transition into a new
 // status. The mapping from status to counter lives here, next to the
 // collectors, so the engine has a single call for every transition it
@@ -298,6 +316,15 @@ func (s *Set) registerCounters(factory promauto.Factory) {
 		},
 		[]string{targetTypeLabel},
 	)
+
+	s.eventsResubmitted = factory.NewCounter(
+		prometheus.CounterOpts{
+			Namespace: namespace,
+			Name:      "events_resubmitted_total",
+			Help: "Stored events an operator re-injected from " +
+				"the event log as new events.",
+		},
+	)
 }
 
 func (s *Set) registerGauges(factory promauto.Factory) {

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 +297,175 @@ 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 set to dev -- the permissive setting -- 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

@@ -4,8 +4,32 @@ import (
 	"context"
 	"net/http"
 	"time"
+
+	httpmetrics "github.com/slok/go-http-metrics/metrics"
 )
 
+// MetricsMiddlewareForTest builds the metrics recording middleware
+// against a caller-supplied recorder, so a test can gather from its
+// own Prometheus registry rather than the process-wide default one
+// that Middleware.Metrics uses.
+func MetricsMiddlewareForTest(
+	rec httpmetrics.Recorder,
+) func(http.Handler) http.Handler {
+	return metricsMiddleware(rec)
+}
+
+// UnmatchedRouteConst exposes the sentinel that stands in for a
+// request matching no route pattern.
+const UnmatchedRouteConst = unmatchedRoute
+
+// InflightHandlerConst exposes the fixed handler label on the
+// inflight gauge.
+const InflightHandlerConst = inflightHandler
+
+// UnmatchedMethodConst exposes the sentinel that stands in for a
+// method the router can never route.
+const UnmatchedMethodConst = unmatchedMethod
+
 // NewLoggingResponseWriterForTest wraps newLoggingResponseWriter
 // for use in external test packages.
 func NewLoggingResponseWriterForTest(
@@ -32,11 +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/middleware/metrics.go

@@ -0,0 +1,182 @@
+package middleware
+
+import (
+	"context"
+	"net/http"
+	"time"
+
+	"github.com/go-chi/chi"
+	httpmetrics "github.com/slok/go-http-metrics/metrics"
+	prommetrics "github.com/slok/go-http-metrics/metrics/prometheus"
+	ghmm "github.com/slok/go-http-metrics/middleware"
+	"github.com/slok/go-http-metrics/middleware/std"
+)
+
+// inflightHandler is the fixed `handler` label on
+// http_requests_inflight, the one HTTP metric here that cannot carry
+// a route pattern.
+//
+// The gauge is incremented before the wrapped handler runs and
+// decremented after it returns, and the pattern only exists between
+// those two moments. Deriving the label from the route would
+// therefore increment one series and decrement another, leaving every
+// pattern permanently off by the number of requests it served — a
+// broken gauge, on top of the per-path cardinality this file exists
+// to remove. So the gauge is deliberately aggregate: one series,
+// counting the requests in flight across the whole service.
+const inflightHandler = "(all)"
+
+// unmatchedMethod is the `method` label for a request whose method
+// the router can never route.
+//
+// It is deliberately the same sentinel as unmatchedRoute rather than
+// a spelling of its own: both stand for a client-chosen token that
+// matched nothing this service registers, and giving one idea two
+// spellings would read in a scrape as two different unmatched states.
+const unmatchedMethod = unmatchedRoute
+
+// routePatternID is the `handler` label for a request: the chi route
+// pattern, never the concrete path.
+//
+// The pattern is what bounds the label's domain to the routes the
+// service registers. The path does not bound it at all — every byte
+// after /webhook/ is client-chosen, so labelling by path lets any
+// unauthenticated client mint permanent series at will, and publishes
+// the entrypoint UUID (the receiver's only credential) in the scrape
+// while doing it.
+//
+// chi populates the route context during routeHTTP, so this is only
+// valid once routing has run. Every caller below is on the recording
+// side of the middleware, which go-http-metrics defers until after
+// the wrapped handler returns.
+func routePatternID(ctx context.Context) string {
+	if rc := chi.RouteContext(ctx); rc != nil {
+		if pattern := rc.RoutePattern(); pattern != "" {
+			return pattern
+		}
+	}
+
+	return unmatchedRoute
+}
+
+// methodID is the `method` label for a request: the request method
+// when the router can route it, and the unmatched sentinel otherwise.
+//
+// net/http accepts any RFC 9110 token as a method and hands it
+// through verbatim, so the raw method is client-chosen bytes and
+// bounds the label at nothing — the same unauthenticated
+// series-minting the handler label carried, reached through a second
+// dimension. What bounds it is the set chi's router will match a
+// route for: its methodMap, which is unexported, so it is restated
+// here against the net/http constants it is built from. A token
+// outside that set can only ever produce chi's 405, so folding every
+// one of them onto a single series loses no information a scrape
+// could have used, while the nine methods that can reach a handler
+// stay distinguishable.
+//
+// chi.RegisterMethod would extend the router's set at runtime; this
+// service never calls it, and a caller that started to would have to
+// extend this switch with it.
+func methodID(method string) string {
+	switch method {
+	case http.MethodConnect,
+		http.MethodDelete,
+		http.MethodGet,
+		http.MethodHead,
+		http.MethodOptions,
+		http.MethodPatch,
+		http.MethodPost,
+		http.MethodPut,
+		http.MethodTrace:
+		return method
+	default:
+		return unmatchedMethod
+	}
+}
+
+// boundedLabelRecorder wraps a go-http-metrics recorder and replaces
+// the request-controlled labels on every observation with bounded
+// ones: the handler id becomes the request's route pattern, and the
+// method becomes one the router can route.
+//
+// This is the seam that makes the pattern usable at all. The metrics
+// middleware is global (see Server.setupGlobalMiddleware), so it is
+// entered before chi has matched anything, and go-http-metrics fixes
+// its handler id up front — passing the pattern in as that id is not
+// possible, and leaving the id empty makes the library substitute the
+// raw URL path, which is the defect. What the library does hand over
+// is the request context, unchanged, on each recorder call; that
+// context carries the same *chi.Context pointer routing mutates in
+// place, and the duration and size calls happen after the wrapped
+// handler has returned. Reading the pattern there is what the access
+// log already does in accessLogURL.
+//
+// Recording after the whole chain returns is also what makes this
+// hold for requests the route-level receiver rate limiter rejects.
+// Those never reach a handler, but chi has already matched the route
+// by the time the limiter runs, so their 429s land on the pattern
+// like any other response.
+type boundedLabelRecorder struct {
+	inner httpmetrics.Recorder
+}
+
+func (r boundedLabelRecorder) ObserveHTTPRequestDuration(
+	ctx context.Context,
+	props httpmetrics.HTTPReqProperties,
+	duration time.Duration,
+) {
+	props.ID = routePatternID(ctx)
+	props.Method = methodID(props.Method)
+	r.inner.ObserveHTTPRequestDuration(ctx, props, duration)
+}
+
+func (r boundedLabelRecorder) ObserveHTTPResponseSize(
+	ctx context.Context,
+	props httpmetrics.HTTPReqProperties,
+	sizeBytes int64,
+) {
+	props.ID = routePatternID(ctx)
+	props.Method = methodID(props.Method)
+	r.inner.ObserveHTTPResponseSize(ctx, props, sizeBytes)
+}
+
+func (r boundedLabelRecorder) AddInflightRequests(
+	ctx context.Context,
+	props httpmetrics.HTTPProperties,
+	quantity int,
+) {
+	props.ID = inflightHandler
+	r.inner.AddInflightRequests(ctx, props, quantity)
+}
+
+var _ httpmetrics.Recorder = boundedLabelRecorder{}
+
+// Metrics returns middleware that records Prometheus HTTP metrics on
+// the default registry, which is the one the /metrics route gathers.
+func (s *Middleware) Metrics() func(http.Handler) http.Handler {
+	return metricsMiddleware(
+		prommetrics.NewRecorder(prommetrics.Config{}),
+	)
+}
+
+// metricsMiddleware builds the recording middleware against a given
+// recorder, so tests can gather from a registry of their own instead
+// of the process-wide default.
+func metricsMiddleware(
+	rec httpmetrics.Recorder,
+) func(http.Handler) http.Handler {
+	mdlw := ghmm.New(ghmm.Config{
+		Recorder: boundedLabelRecorder{inner: rec},
+	})
+
+	return func(next http.Handler) http.Handler {
+		// The handler id is unmatchedRoute rather than "" so that
+		// the client-chosen URL path never enters the metrics
+		// pipeline at all: an empty id is the library's signal to
+		// substitute it. boundedLabelRecorder overwrites this value
+		// on every observation, so it is reachable only if that
+		// decorator is removed — in which case the metrics collapse
+		// to one series instead of leaking again.
+		return std.Handler(unmatchedRoute, mdlw, next)
+	}
+}

internal/middleware/metrics_method_test.go

@@ -0,0 +1,309 @@
+package middleware_test
+
+import (
+	"net/http"
+	"net/http/httptest"
+	"strings"
+	"testing"
+
+	"github.com/google/uuid"
+	"github.com/prometheus/client_golang/prometheus"
+	"github.com/prometheus/client_golang/prometheus/promhttp"
+	dto "github.com/prometheus/client_model/go"
+	"github.com/stretchr/testify/assert"
+	"github.com/stretchr/testify/require"
+	"sneak.berlin/go/webhooker/internal/middleware"
+)
+
+const (
+	// metricsProbeMethods is how many distinct invented method tokens
+	// each cardinality assertion drives. The measurement on the issue
+	// took 300 tokens from 106 exposition lines to 7,631 — about 25
+	// permanent lines per token, never reclaimed — so a probe of this
+	// size puts a regression thousands of lines over the bound rather
+	// than leaving it to a rounding argument.
+	metricsProbeMethods = 300
+
+	// probeMethodLen is how many characters each invented method
+	// token carries, matching the 12 the issue measured with.
+	probeMethodLen = 12
+
+	// methodLabel is the label these tests are about.
+	methodLabel = "method"
+)
+
+// realMethods is the positive control's domain: the methods chi's
+// router can match a route for, every one of which a client
+// legitimately sends and every one of which must keep a series of its
+// own. Bounding the label by collapsing these into one bucket would
+// destroy the metric it is meant to protect.
+func realMethods() []string {
+	return []string{
+		http.MethodConnect, http.MethodDelete, http.MethodGet,
+		http.MethodHead, http.MethodOptions, http.MethodPatch,
+		http.MethodPost, http.MethodPut, http.MethodTrace,
+	}
+}
+
+// methodProbePath returns the one receiver path a method probe
+// targets. Holding the path fixed leaves the method as the only
+// dimension varying, so any series growth a probe produces is the
+// method label's and nothing else's.
+func methodProbePath() string {
+	return "/webhook/" + uuid.NewString()
+}
+
+// inventedMethods returns n distinct RFC 9110 method tokens that no
+// router will ever match: uppercase hex from a fresh UUID, which is
+// both the shape and the length an unauthenticated flood would send.
+// net/http accepts any token as a method, so every one of these
+// reaches the metrics pipeline exactly as a real method does.
+func inventedMethods(n int) []string {
+	methods := make([]string, 0, n)
+
+	for range n {
+		token := strings.ToUpper(
+			strings.ReplaceAll(uuid.NewString(), "-", ""),
+		)
+		methods = append(methods, token[:probeMethodLen])
+	}
+
+	return methods
+}
+
+// driveMethods sends one request per supplied method to a single
+// fixed path.
+func driveMethods(
+	t *testing.T,
+	h http.Handler,
+	path string,
+	methods []string,
+) map[int]int {
+	t.Helper()
+
+	probes := make([]probe, 0, len(methods))
+
+	for _, m := range methods {
+		probes = append(probes, probe{method: m, path: path})
+	}
+
+	return drive(t, h, probes)
+}
+
+// methodLabels returns the set of distinct `method` values across
+// every gathered series that carries the label at all. The inflight
+// gauge does not carry it, and so contributes nothing rather than an
+// empty-string member.
+func methodLabels(families []*dto.MetricFamily) map[string]struct{} {
+	seen := make(map[string]struct{})
+
+	for _, fam := range families {
+		for _, m := range fam.GetMetric() {
+			for _, pair := range m.GetLabel() {
+				if pair.GetName() == methodLabel {
+					seen[pair.GetValue()] = struct{}{}
+				}
+			}
+		}
+	}
+
+	return seen
+}
+
+// scrapeLines renders the registry through the same promhttp handler
+// /metrics is mounted on and counts the sample lines it produced.
+//
+// This is the quantity the issue measured and the one a Prometheus
+// server pays for on every scrape: one histogram label set is a
+// single gathered series but around 25 lines of exposition, which is
+// why 300 method tokens cost thousands of lines rather than hundreds.
+func scrapeLines(t *testing.T, reg *prometheus.Registry) int {
+	t.Helper()
+
+	h := promhttp.HandlerFor(reg, promhttp.HandlerOpts{})
+	req := httptest.NewRequestWithContext(
+		t.Context(), http.MethodGet, "/metrics", nil,
+	)
+	w := httptest.NewRecorder()
+	h.ServeHTTP(w, req)
+	require.Equal(t, http.StatusOK, w.Code)
+
+	lines := 0
+
+	for line := range strings.SplitSeq(w.Body.String(), "\n") {
+		if line == "" || strings.HasPrefix(line, "#") {
+			continue
+		}
+
+		lines++
+	}
+
+	return lines
+}
+
+// TestMetrics_MethodSentinelIsTheRouteSentinel pins the convention
+// rather than the mechanism. An unroutable method and an unmatched
+// path are the same fact — a client-chosen token matching nothing
+// this service registers — so they carry one spelling. Two spellings
+// would read in a scrape as two different unmatched states.
+func TestMetrics_MethodSentinelIsTheRouteSentinel(t *testing.T) {
+	t.Parallel()
+
+	assert.Equal(
+		t,
+		middleware.UnmatchedRouteConst,
+		middleware.UnmatchedMethodConst,
+		"the unmatched sentinel must have exactly one spelling",
+	)
+}
+
+// TestMetrics_InventedMethodsMintOneLabelSet is the direct assertion
+// the issue asks for: N requests carrying N distinct invented method
+// tokens must produce exactly ONE method label. Before the fix this
+// produced N of them, on an unauthenticated route with no rate
+// limiter.
+func TestMetrics_InventedMethodsMintOneLabelSet(t *testing.T) {
+	t.Parallel()
+
+	h, reg := metricsTestRouter(t, generousReceiverLimit)
+
+	methods := inventedMethods(metricsProbeMethods)
+
+	codes := driveMethods(t, h, methodProbePath(), methods)
+	require.Equal(
+		t, metricsProbeMethods, codes[http.StatusMethodNotAllowed],
+		"every invented token should have been unroutable",
+	)
+
+	labels := methodLabels(gatherMetrics(t, reg))
+
+	// Asserted on the count rather than on the set, so that a
+	// regression reports one number instead of dumping every token it
+	// minted.
+	distinct := len(labels)
+
+	assert.Equal(
+		t, 1, distinct,
+		"invented methods must collapse onto one label",
+	)
+	assert.Contains(
+		t, keys(labels), middleware.UnmatchedMethodConst,
+		"that one label must be the unmatched sentinel",
+	)
+
+	// The scrape must not republish the tokens it was driven with
+	// either: a label that merely looks bounded while still echoing
+	// client bytes is the same defect wearing a different name.
+	echoed := 0
+
+	for _, m := range methods {
+		for label := range labels {
+			if strings.Contains(label, m) {
+				echoed++
+			}
+		}
+	}
+
+	assert.Equal(
+		t, 0, echoed,
+		"invented method tokens reached the metrics labels",
+	)
+}
+
+// TestMetrics_MethodSeriesCountIsFlatUnderAFlood reproduces the
+// measurement on the issue in miniature: scrape, drive several
+// hundred distinct method tokens, scrape again, and require the
+// second scrape to be no larger than the first. The first batch
+// establishes every label set the route can produce; a flood five
+// times its size must land on exactly those.
+func TestMetrics_MethodSeriesCountIsFlatUnderAFlood(t *testing.T) {
+	t.Parallel()
+
+	h, reg := metricsTestRouter(t, generousReceiverLimit)
+
+	path := methodProbePath()
+
+	driveMethods(t, h, path, inventedMethods(metricsProbeMethods))
+	seededSeries := seriesCount(gatherMetrics(t, reg))
+	seededLines := scrapeLines(t, reg)
+
+	driveMethods(t, h, path, inventedMethods(metricsProbeMethods*4))
+	floodedSeries := seriesCount(gatherMetrics(t, reg))
+	floodedLines := scrapeLines(t, reg)
+
+	t.Logf(
+		"after %d invented methods: %d series, %d lines; "+
+			"after %d more: %d series, %d lines",
+		metricsProbeMethods, seededSeries, seededLines,
+		metricsProbeMethods*4, floodedSeries, floodedLines,
+	)
+
+	assert.Equal(
+		t, seededSeries, floodedSeries,
+		"a flood of invented methods must not mint series",
+	)
+	assert.Equal(
+		t, seededLines, floodedLines,
+		"a flood of invented methods must not grow the scrape",
+	)
+}
+
+// TestMetrics_RealMethodsStayDistinct is the positive control. The
+// bound is worth nothing if it is bought by flattening the metric:
+// every method the router can route must still carry a series of its
+// own, one sample each, under the route pattern it was sent to.
+func TestMetrics_RealMethodsStayDistinct(t *testing.T) {
+	t.Parallel()
+
+	h, reg := metricsTestRouter(t, generousReceiverLimit)
+
+	methods := realMethods()
+
+	codes := driveMethods(t, h, methodProbePath(), methods)
+	require.Equal(
+		t, len(methods), codes[http.StatusNotFound],
+		"every real method should have reached the receiver",
+	)
+
+	families := gatherMetrics(t, reg)
+
+	want := make(map[string]struct{}, len(methods))
+	for _, m := range methods {
+		want[m] = struct{}{}
+	}
+
+	assert.Equal(
+		t, want, methodLabels(families),
+		"real methods must remain distinguishable",
+	)
+
+	// Appearing somewhere in the scrape is not enough: each method
+	// must own its duration series, holding the one sample it sent.
+	observed := 0
+
+	for _, fam := range families {
+		if !strings.HasSuffix(fam.GetName(), "request_duration_seconds") {
+			continue
+		}
+
+		for _, m := range fam.GetMetric() {
+			observed++
+
+			assert.Equal(
+				t, receiverRoutePattern,
+				labelValue(m, "handler"),
+			)
+			assert.Equal(
+				t, uint64(1),
+				m.GetHistogram().GetSampleCount(),
+				"method %q shares a series",
+				labelValue(m, methodLabel),
+			)
+		}
+	}
+
+	assert.Equal(
+		t, len(methods), observed,
+		"one duration series per routable method",
+	)
+}

internal/middleware/metrics_test.go

@@ -0,0 +1,457 @@
+package middleware_test
+
+import (
+	"log/slog"
+	"net/http"
+	"net/http/httptest"
+	"strings"
+	"testing"
+
+	"github.com/go-chi/chi"
+	"github.com/google/uuid"
+	"github.com/prometheus/client_golang/prometheus"
+	dto "github.com/prometheus/client_model/go"
+	prommetrics "github.com/slok/go-http-metrics/metrics/prometheus"
+	"github.com/stretchr/testify/assert"
+	"github.com/stretchr/testify/require"
+	"sneak.berlin/go/webhooker/internal/config"
+	"sneak.berlin/go/webhooker/internal/middleware"
+)
+
+const (
+	// metricsProbePaths is how many distinct receiver paths each
+	// cardinality assertion drives. The defect these tests pin cost
+	// roughly 26 permanent series per distinct path, so a couple of
+	// hundred puts a regression thousands of series over the bound
+	// rather than leaving it to a rounding argument.
+	metricsProbePaths = 250
+
+	// receiverRoutePattern is the one handler label every receiver
+	// request must produce, however the client varies the path.
+	receiverRoutePattern = "/webhook/{uuid}"
+
+	// okRoute is a static route used to pin that the response-writer
+	// interceptor still reports status and size after the handler id
+	// stopped coming from the URL.
+	okRoute = "/ok"
+
+	// okBody is what okRoute writes, so the recorded response size is
+	// a number the test knows.
+	okBody = "ok"
+
+	// generousReceiverLimit is a per-entrypoint receiver limit high
+	// enough that no probe in this file trips the limiter unless it
+	// means to.
+	generousReceiverLimit = 100000
+
+	// tightReceiverLimit forces the receiver's aggregate limiter to
+	// reject: the aggregate ceiling is ten times this, so a probe of
+	// metricsProbePaths requests spends it many times over.
+	tightReceiverLimit = 1
+)
+
+// metricsTestRouter builds a router whose middleware ordering mirrors
+// the real server's: the metrics recorder is GLOBAL, installed by
+// Server.setupGlobalMiddleware before chi has matched anything, and
+// the receiver rate limiter is ROUTE-LEVEL, installed by
+// Server.setupWebhookRoutes inside it. That ordering is the whole
+// defect, so a test that flattens it would prove nothing.
+//
+// The recorder writes to a registry of the test's own rather than the
+// process-wide default one, so each test observes only its own
+// traffic.
+func metricsTestRouter(
+	t *testing.T,
+	receiverLimit int,
+) (http.Handler, *prometheus.Registry) {
+	t.Helper()
+
+	log := slog.New(slog.DiscardHandler)
+	cfg := &config.Config{
+		Environment:       "prod",
+		ReceiverRateLimit: receiverLimit,
+	}
+	m := middleware.NewForTest(
+		log, cfg, newTestSessionManager(cfg, log, nil),
+	)
+
+	reg := prometheus.NewRegistry()
+	rec := prommetrics.NewRecorder(prommetrics.Config{Registry: reg})
+
+	r := chi.NewRouter()
+	r.Use(middleware.MetricsMiddlewareForTest(rec))
+
+	r.Get(okRoute, func(w http.ResponseWriter, _ *http.Request) {
+		_, _ = w.Write([]byte(okBody))
+	})
+
+	// The real receiver answers 404 for a UUID naming no stored
+	// entrypoint, which is what every invented path here is.
+	r.With(m.ReceiverRateLimit()).HandleFunc(
+		receiverRoutePattern,
+		func(w http.ResponseWriter, _ *http.Request) {
+			w.WriteHeader(http.StatusNotFound)
+		},
+	)
+
+	return r, reg
+}
+
+// probe is one request a cardinality assertion sends. Both label
+// dimensions that have leaked are request-controlled — the path and
+// the method — so both vary here and one driver sends them.
+type probe struct {
+	method string
+	path   string
+}
+
+// drive sends every probe and returns how many responses carried each
+// status code.
+func drive(t *testing.T, h http.Handler, probes []probe) map[int]int {
+	t.Helper()
+
+	codes := make(map[int]int)
+
+	for _, p := range probes {
+		req := httptest.NewRequestWithContext(
+			t.Context(), p.method, p.path, nil,
+		)
+		w := httptest.NewRecorder()
+		h.ServeHTTP(w, req)
+		codes[w.Code]++
+	}
+
+	return codes
+}
+
+// drivePaths sends one POST per supplied path.
+func drivePaths(
+	t *testing.T,
+	h http.Handler,
+	paths []string,
+) map[int]int {
+	t.Helper()
+
+	probes := make([]probe, 0, len(paths))
+
+	for _, p := range paths {
+		probes = append(
+			probes, probe{method: http.MethodPost, path: p},
+		)
+	}
+
+	return drive(t, h, probes)
+}
+
+// receiverPaths returns n distinct /webhook/ paths, each naming a
+// fresh UUID exactly as an unauthenticated flood would.
+func receiverPaths(n int) []string {
+	paths := make([]string, 0, n)
+
+	for range n {
+		paths = append(paths, "/webhook/"+uuid.NewString())
+	}
+
+	return paths
+}
+
+// gatherMetrics returns the registry's current families, failing the
+// test if gathering does.
+func gatherMetrics(
+	t *testing.T,
+	reg *prometheus.Registry,
+) []*dto.MetricFamily {
+	t.Helper()
+
+	families, err := reg.Gather()
+	require.NoError(t, err)
+
+	return families
+}
+
+// labelValue returns the named label from a gathered metric.
+func labelValue(m *dto.Metric, name string) string {
+	for _, pair := range m.GetLabel() {
+		if pair.GetName() == name {
+			return pair.GetValue()
+		}
+	}
+
+	return ""
+}
+
+// handlerLabels returns the set of distinct `handler` label values
+// across every gathered series.
+func handlerLabels(families []*dto.MetricFamily) map[string]struct{} {
+	seen := make(map[string]struct{})
+
+	for _, fam := range families {
+		for _, m := range fam.GetMetric() {
+			seen[labelValue(m, "handler")] = struct{}{}
+		}
+	}
+
+	return seen
+}
+
+// seriesCount is the number of distinct label sets held across every
+// family: the quantity that grew without bound and was never
+// reclaimed.
+func seriesCount(families []*dto.MetricFamily) int {
+	total := 0
+
+	for _, fam := range families {
+		total += len(fam.GetMetric())
+	}
+
+	return total
+}
+
+// keys returns the members of a set, for assertion messages.
+func keys(set map[string]struct{}) []string {
+	out := make([]string, 0, len(set))
+
+	for k := range set {
+		out = append(out, k)
+	}
+
+	return out
+}
+
+// TestMetrics_DistinctReceiverPathsMintOneLabelSet is the direct
+// assertion the issue asks for: N requests to N distinct
+// /webhook/<uuid> paths must produce exactly ONE handler label, the
+// route pattern. Before the fix this produced N of them.
+func TestMetrics_DistinctReceiverPathsMintOneLabelSet(t *testing.T) {
+	t.Parallel()
+
+	h, reg := metricsTestRouter(t, generousReceiverLimit)
+
+	paths := receiverPaths(metricsProbePaths)
+	codes := drivePaths(t, h, paths)
+	require.Equal(
+		t, metricsProbePaths, codes[http.StatusNotFound],
+		"every invented UUID should have reached the receiver",
+	)
+
+	families := gatherMetrics(t, reg)
+	labels := handlerLabels(families)
+
+	assert.Equal(
+		t,
+		map[string]struct{}{
+			receiverRoutePattern:            {},
+			middleware.InflightHandlerConst: {},
+		},
+		labels,
+		"receiver traffic must collapse onto the route pattern",
+	)
+
+	// The scrape must not republish the UUIDs it was driven with.
+	// They are the receiver's only credential.
+	for _, p := range paths {
+		id := strings.TrimPrefix(p, "/webhook/")
+		for label := range labels {
+			assert.NotContains(
+				t, label, id,
+				"an entrypoint UUID reached a metrics label",
+			)
+		}
+	}
+}
+
+// TestMetrics_SeriesCountIsFlatUnderAFlood pins the property the
+// issue measured against a live instance: driving thousands more
+// distinct paths must not add series. The first batch establishes
+// every label set the route can produce; the second must land on
+// exactly those.
+func TestMetrics_SeriesCountIsFlatUnderAFlood(t *testing.T) {
+	t.Parallel()
+
+	h, reg := metricsTestRouter(t, generousReceiverLimit)
+
+	drivePaths(t, h, receiverPaths(metricsProbePaths))
+	before := seriesCount(gatherMetrics(t, reg))
+
+	drivePaths(t, h, receiverPaths(metricsProbePaths*4))
+	after := seriesCount(gatherMetrics(t, reg))
+
+	assert.Equal(
+		t, before, after,
+		"a flood of distinct paths must not mint series",
+	)
+}
+
+// TestMetrics_RateLimitedRequestsCarryTheRoutePattern covers the
+// majority case: most of the leaked series were 429s. Those requests
+// never reach a handler, so they take a different path through the
+// stack — but chi has already matched the route by the time the
+// route-level limiter rejects them, and the recording happens after
+// the whole chain returns, so they must land on the pattern too.
+func TestMetrics_RateLimitedRequestsCarryTheRoutePattern(t *testing.T) {
+	t.Parallel()
+
+	h, reg := metricsTestRouter(t, tightReceiverLimit)
+
+	codes := drivePaths(t, h, receiverPaths(metricsProbePaths))
+	require.Positive(
+		t, codes[http.StatusTooManyRequests],
+		"the probe must actually exhaust the aggregate limiter",
+	)
+
+	families := gatherMetrics(t, reg)
+
+	assert.Equal(
+		t,
+		map[string]struct{}{
+			receiverRoutePattern:            {},
+			middleware.InflightHandlerConst: {},
+		},
+		handlerLabels(families),
+		"rejected requests must collapse onto the route pattern",
+	)
+
+	rejected := 0
+
+	for _, fam := range families {
+		for _, m := range fam.GetMetric() {
+			if labelValue(m, "code") != "429" {
+				continue
+			}
+
+			rejected++
+
+			assert.Equal(
+				t, receiverRoutePattern,
+				labelValue(m, "handler"),
+				"a 429 series carried a non-pattern handler",
+			)
+		}
+	}
+
+	assert.Positive(
+		t, rejected, "no 429 series was recorded at all",
+	)
+}
+
+// TestMetrics_UnmatchedPathsCollapseToTheSentinel decides and pins the
+// unmatched-route case. A path matching no route has no pattern, so
+// it carries the same fixed sentinel the access log uses. Without
+// that, an unmatched flood leaks exactly as the receiver did.
+func TestMetrics_UnmatchedPathsCollapseToTheSentinel(t *testing.T) {
+	t.Parallel()
+
+	h, reg := metricsTestRouter(t, generousReceiverLimit)
+
+	paths := make([]string, 0, metricsProbePaths)
+
+	for i := range metricsProbePaths {
+		id := uuid.NewString()
+
+		// Two shapes: one matching no prefix at all, and one under
+		// the receiver prefix but with a segment count the pattern
+		// cannot match.
+		if i%2 == 0 {
+			paths = append(paths, "/"+id)
+		} else {
+			paths = append(paths, "/webhook/"+id+"/"+id)
+		}
+	}
+
+	codes := drivePaths(t, h, paths)
+	require.Equal(
+		t, metricsProbePaths, codes[http.StatusNotFound],
+		"every probe path should have gone unmatched",
+	)
+
+	labels := handlerLabels(gatherMetrics(t, reg))
+
+	assert.Equal(
+		t,
+		map[string]struct{}{
+			middleware.UnmatchedRouteConst:  {},
+			middleware.InflightHandlerConst: {},
+		},
+		labels,
+		"unmatched paths must collapse onto one sentinel, got %v",
+		keys(labels),
+	)
+}
+
+// TestMetrics_InflightGaugeIsAggregateAndBalanced pins the one metric
+// that cannot carry a pattern. It is incremented before routing and
+// decremented after, so it gets a fixed label -- and the two calls
+// must therefore agree, leaving the gauge at zero once the traffic
+// has drained rather than stuck above it.
+func TestMetrics_InflightGaugeIsAggregateAndBalanced(t *testing.T) {
+	t.Parallel()
+
+	h, reg := metricsTestRouter(t, generousReceiverLimit)
+
+	drivePaths(t, h, receiverPaths(metricsProbePaths))
+
+	var inflight []*dto.Metric
+
+	for _, fam := range gatherMetrics(t, reg) {
+		if strings.HasSuffix(fam.GetName(), "requests_inflight") {
+			inflight = fam.GetMetric()
+		}
+	}
+
+	require.Len(
+		t, inflight, 1,
+		"the inflight gauge must hold exactly one series",
+	)
+	assert.Equal(
+		t, middleware.InflightHandlerConst,
+		labelValue(inflight[0], "handler"),
+	)
+	assert.InDelta(
+		t, 0.0, inflight[0].GetGauge().GetValue(), 0.0,
+		"the gauge must balance back to zero",
+	)
+}
+
+// TestMetrics_StatusAndSizeStillRecorded guards the response-writer
+// interceptor the recording middleware wraps around every request.
+// The handler label changed; what the interceptor reports must not
+// have.
+func TestMetrics_StatusAndSizeStillRecorded(t *testing.T) {
+	t.Parallel()
+
+	h, reg := metricsTestRouter(t, generousReceiverLimit)
+
+	req := httptest.NewRequestWithContext(
+		t.Context(), http.MethodGet, okRoute, nil,
+	)
+	w := httptest.NewRecorder()
+	h.ServeHTTP(w, req)
+
+	require.Equal(t, http.StatusOK, w.Code)
+	require.Equal(t, okBody, w.Body.String())
+
+	var size *dto.Metric
+
+	for _, fam := range gatherMetrics(t, reg) {
+		if !strings.HasSuffix(fam.GetName(), "response_size_bytes") {
+			continue
+		}
+
+		for _, m := range fam.GetMetric() {
+			if labelValue(m, "handler") == okRoute {
+				size = m
+			}
+		}
+	}
+
+	require.NotNil(
+		t, size, "no response size series for the static route",
+	)
+	assert.Equal(t, "200", labelValue(size, "code"))
+	assert.Equal(t, uint64(1), size.GetHistogram().GetSampleCount())
+	assert.InDelta(
+		t, float64(len(okBody)),
+		size.GetHistogram().GetSampleSum(), 0.0,
+		"the interceptor must still count written bytes",
+	)
+}

internal/middleware/middleware.go

@@ -13,9 +13,6 @@ import (
 	"github.com/go-chi/chi"
 	"github.com/go-chi/chi/middleware"
 	"github.com/go-chi/cors"
-	metrics "github.com/slok/go-http-metrics/metrics/prometheus"
-	ghmm "github.com/slok/go-http-metrics/middleware"
-	"github.com/slok/go-http-metrics/middleware/std"
 	"go.uber.org/fx"
 	"sneak.berlin/go/webhooker/internal/config"
 	"sneak.berlin/go/webhooker/internal/globals"
@@ -29,10 +26,15 @@ const (
 	// preflight response can be cached.
 	corsMaxAge = 300
 
-	// unmatchedRoute is logged in the access log's url field when a
+	// unmatchedRoute stands in for a request that matched no route
-	// redirected or rejected request matched no route pattern at
+	// pattern at all. Every byte of such a path is client-chosen, so
-	// all. Every byte of such a path is client-chosen, so none of it
+	// none of it is kept.
-	// is logged.
+	//
+	// It is the access log's url field on a redirected or rejected
+	// request, and it is the metrics `handler` label on the same
+	// request; see metrics.go. Both surfaces are written once per
+	// request from a path the client picks, so both have to collapse
+	// the unmatched case into one fixed value.
 	unmatchedRoute = "(unmatched)"
 
 	// redactedQuery stands in for the query string on the access log
@@ -438,17 +440,6 @@ func (s *Middleware) RequireAuth() func(http.Handler) http.Handler {
 	}
 }
 
-// Metrics returns middleware that records Prometheus HTTP metrics.
-func (s *Middleware) Metrics() func(http.Handler) http.Handler {
-	mdlw := ghmm.New(ghmm.Config{
-		Recorder: metrics.NewRecorder(metrics.Config{}),
-	})
-
-	return func(next http.Handler) http.Handler {
-		return std.Handler("", mdlw, next)
-	}
-}
-
 // MetricsAuth returns middleware that protects metrics endpoints
 // with basic auth.
 func (s *Middleware) MetricsAuth() func(http.Handler) http.Handler {

internal/middleware/ratelimit.go

@@ -44,6 +44,18 @@ const (
 	// replayRateInterval is the time window for the replay limit.
 	replayRateInterval = 1 * time.Minute
 
+	// resubmitRateLimit is the maximum number of event resubmits one
+	// client may queue per interval. A resubmit stores an event and
+	// queues one delivery per active target, so it costs more
+	// outbound work per press than a replay does. Firing a captured
+	// event repeatedly at a backend under development is the point of
+	// the action, so the ceiling stays well above the rate a person
+	// iterates at.
+	resubmitRateLimit = 30
+
+	// resubmitRateInterval is the time window for the resubmit limit.
+	resubmitRateInterval = 1 * time.Minute
+
 	// receiverRateInterval is the time window for the webhook
 	// receiver rate limit. The configured limit is expressed in
 	// requests per minute.
@@ -315,6 +327,22 @@ func (m *Middleware) ReplayRateLimit() func(http.Handler) http.Handler {
 	)
 }
 
+// ResubmitRateLimit returns middleware that enforces per-IP rate
+// limiting on event resubmits.
+//
+// It is a separate bucket from the replay limit so that exhausting one
+// does not take the other away: replay is a recovery action and
+// resubmit is a testing action, and an operator iterating on a backend
+// must not lose the ability to re-send a failed delivery.
+func (m *Middleware) ResubmitRateLimit() func(http.Handler) http.Handler {
+	return m.postRateLimit(
+		resubmitRateLimit,
+		resubmitRateInterval,
+		"event resubmit rate limit exceeded",
+		"Too many resubmits. Please try again later.",
+	)
+}
+
 // postRateLimit builds middleware that enforces a per-IP rate
 // limit on POST requests only; all other methods pass through
 // unaffected. Requests over the limit receive a 429 with the

internal/middleware/recoverer.go

@@ -133,6 +133,11 @@ func (w *recoverResponseWriter) Unwrap() http.ResponseWriter {
 // what the access log records and the metrics count, and outside the
 // sentryhttp handler, whose Repanic option depends on something
 // further out recovering what it re-raises.
+//
+// Unlike http.Error on its own, it deletes any Set-Cookie the handler
+// set before panicking, because a request that failed must not hand
+// the client a credential; every other header is left to http.Error.
+// See https://git.eeqj.de/sneak/webhooker/issues/193.
 func (s *Middleware) Recoverer() func(http.Handler) http.Handler {
 	return func(next http.Handler) http.Handler {
 		return http.HandlerFunc(func(
@@ -164,6 +169,8 @@ func (s *Middleware) Recoverer() func(http.Handler) http.Handler {
 					return
 				}
 
+				rw.Header().Del("Set-Cookie")
+
 				http.Error(
 					rw,
 					http.StatusText(

internal/middleware/recoverer_test.go

@@ -304,16 +304,44 @@ func TestRecovererRepanicsErrAbortHandler(t *testing.T) {
 	)
 }
 
+// TestRecovererDropsSetCookieFromTheRecovered500 covers a handler that
+// sets a cookie and a redirect target and then panics before sending
+// anything. A request that failed must not hand the client a
+// credential, so the 500 carries no cookie; Location is left alone.
+func TestRecovererDropsSetCookieFromTheRecovered500(t *testing.T) {
+	t.Parallel()
+
+	probe := newRecovererProbe(
+		t, false,
+		func(w http.ResponseWriter, _ *http.Request) {
+			w.Header().Set("Set-Cookie", "session=x")
+			w.Header().Set("Location", "/after")
+
+			panic(panicMarker)
+		},
+	)
+
+	resp, err := probe.get(t)
+	require.NoError(t, err)
+	require.NoError(t, resp.Body.Close())
+
+	assert.Equal(t, http.StatusInternalServerError, resp.StatusCode)
+	assert.Empty(t, resp.Cookies())
+	assert.Equal(t, "/after", resp.Header.Get("Location"))
+}
+
 // TestRecovererKeepsAnAlreadyCommittedResponse covers a handler that
 // panics after sending its status. The bytes are already on the wire,
-// so a second WriteHeader would change nothing the client sees and
+// cookie included, so a second WriteHeader would change nothing the
-// would draw net/http's "superfluous response.WriteHeader" report.
+// client sees and would draw net/http's "superfluous
+// response.WriteHeader" report.
 func TestRecovererKeepsAnAlreadyCommittedResponse(t *testing.T) {
 	t.Parallel()
 
 	probe := newRecovererProbe(
 		t, false,
 		func(w http.ResponseWriter, _ *http.Request) {
+			w.Header().Set("Set-Cookie", "session=x")
 			w.WriteHeader(committedStatus)
 			_, _ = w.Write([]byte("partial"))
 
@@ -331,6 +359,7 @@ func TestRecovererKeepsAnAlreadyCommittedResponse(t *testing.T) {
 
 	assert.Equal(t, committedStatus, resp.StatusCode)
 	assert.Equal(t, "partial", string(body))
+	assert.Len(t, resp.Cookies(), 1)
 
 	record := probe.panicRecord(t)
 	assert.Equal(t, panicMarker, record["panic"])

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 dev 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/resetpw/resetpw_test.go

@@ -164,6 +164,7 @@ func newServerApp(
 			func() delivery.Notifier { return &noopNotifier{} },
 			func() delivery.WebhookEvictor { return &noopEvictor{} },
 			middleware.New,
+			delivery.NewGuard,
 			handlers.New,
 		),
 		fx.Populate(&h),

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)