Merge pull request 'v0.31.1: cross-origin POST protection, ffprobe/ffmpeg limits, receive cap, SIGTERM, lint gate (#41 #47 #48 #49 #50)' (#55) from sprint/audio-followups into main

Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>

DECISIONS.md

@@ -1447,6 +1447,25 @@ an hour of Swedish *was* an unknown here; it is now measured, see decision 8.)
    re-uploads. The single-replica assumption gains a second dependent (the semaphore is
    process-local) and is recorded here.
 
+   *Amended 2026-10-03 (#50, #47).* The process now handles SIGTERM (what Kubernetes sends on
+   every deploy; only SIGINT was handled, so shutdown code never ran). On shutdown the running job
+   is recorded `interrupted` at once and the process waits, bounded to 10 s each, for in-flight
+   requests and for that write; the start-up sweep stays the backstop for a kill. **Known
+   limitation, deliberately not built: a deploy still loses a job in flight** (finishing it needs
+   a drain of up to the job time, a ~330 s termination grace and `strategy: Recreate`, i.e.
+   downtime on every deploy; a 90-minute file takes ~4.5 min and a deploy lands on a running job
+   perhaps one time in five at current volume). Jobs still queued at shutdown stay `queued` until
+   the next start's sweep. The user re-uploads, with an honest message.
+
+   *Receive limits (#47).* Request bodies are received at most 4 at a time, 2 per user, answered
+   as busy beyond that. Together with the 20-job queue and the running job that bounds the spool
+   at about (4 + 20 + 1) x 200 MiB = 5 GiB of the 6 Gi `emptyDir` (infra): raising any of those or
+   `TAPIR_UPLOAD_MAX_BYTES` must revisit that sum (pinned by `TestNewIntake_Defaults...`, not
+   enforced against infra). **A slow-drip body holds its slot without a time bound**: the server
+   sets `ReadHeaderTimeout` only, because a `ReadTimeout` would cut legitimate 200 MiB uploads on
+   slow links; two slow bodies take a user's two slots and two such users make everyone's upload
+   busy. It needs a valid session; recorded as a limitation with a follow-up issue.
+
 8. **Chat reuses `chat.Service`; it is not forked.** The uploaded-transcript chat handlers
    look the row up through the RLS-scoped store, so a non-owner gets 404 by the same mechanism
    as ADR-027's summary gate, **before any model is called**. ADR-027's decisions (ephemeral,
@@ -1531,7 +1550,7 @@ deferred. The scope cut — chat first, no rich analysis, no video — is what k
   #33 specifies, with the serving endpoint shown **(recommended, matches the issue)**; (B)
   disabled by default, a failed iguana job fails honestly and the user retries. *Blocks:*
   the production default only; the adapter ships either way.
-- Verify Tapir's ingress `proxy-body-size` against the 200 MB cap (`infra`).
+- ~~Verify Tapir's ingress `proxy-body-size` against the 200 MB cap (`infra`).~~ **Resolved 2026-10-03:** real unauthenticated bodies of 2, 30, 120 and 210 MiB all pass NPM (TLS, piguard) and Traefik to tapir (a 302 to login); there is no body limit in that range. Uploads were enabled in production the same day, local engines only (infra#520).
 - Per-transcript deletion is not built; account deletion cascades. A private-content store
   without a delete button is a gap worth a ticket, not a silent omission.
 

Taskfile.yml

@@ -34,7 +34,7 @@ tasks:
   lint:
     desc: golangci-lint (installed by CI; skipped locally if absent).
     cmds:
-      - 'command -v golangci-lint >/dev/null 2>&1 && golangci-lint run ./... || echo "golangci-lint not installed — skipping (CI installs it)"'
+      - 'if command -v golangci-lint >/dev/null 2>&1; then golangci-lint run ./...; else echo "golangci-lint not installed — skipping (CI installs it)"; fi'
 
   test:
     desc: Run all tests. -p 1 serializes packages so the embedded-postgres tests

cmd/tapir/main.go

@@ -17,9 +17,9 @@ import (
 	"errors"
 	"fmt"
 	"log/slog"
+	"net"
 	"net/http"
 	"os"
-	"os/signal"
 	"sync"
 	"time"
 
@@ -41,7 +41,7 @@ func main() {
 	}
 
 	log := slog.New(slog.NewTextHandler(os.Stderr, nil))
-	ctx, stop := signal.NotifyContext(context.Background(), os.Interrupt)
+	ctx, stop := shutdownContext(context.Background())
 	defer stop()
 
 	var err error
@@ -215,9 +215,11 @@ func cmdServe(ctx context.Context, log *slog.Logger) error {
 	if err != nil {
 		return err
 	}
+	var workerDone chan struct{} // nil without uploads: nothing to wait for at shutdown
 	wireUploads(app, cfg, intake)
 	if intake != nil {
-		go worker.Run(ctx)
+		workerDone = make(chan struct{})
+		go func() { worker.Run(ctx); close(workerDone) }()
 		log.Info("audio upload enabled", "model", cfg.TranscribeModel, "fallback", cfg.TranscribeFallbackModel,
 			"max_mb", cfg.UploadMaxBytes>>20, "max_minutes", int(cfg.UploadMaxDuration.Minutes()))
 		log.Warn("audio upload assumes a SINGLE replica: the transcription queue is process-local (ADR-033, ADR-018)")
@@ -350,20 +352,19 @@ func cmdServe(ctx context.Context, log *slog.Logger) error {
 		}()
 	}
 
-	// Graceful shutdown on signal: stop accepting, drain in-flight requests.
+	// Graceful shutdown on signal: stop accepting, drain in-flight requests, and let the
-	go func() {
+	// worker record the job it was running as interrupted (#50).
-		<-ctx.Done()
+	var extra []*http.Server
-		shutdownCtx, cancel := context.WithTimeout(context.Background(), 10*time.Second)
-		defer cancel()
-		_ = srv.Shutdown(shutdownCtx)
 	if metricsSrv != nil {
-			_ = metricsSrv.Shutdown(shutdownCtx)
+		extra = append(extra, metricsSrv)
+	}
+	ln, err := net.Listen("tcp", srv.Addr)
+	if err != nil {
+		return fmt.Errorf("serve: listen: %w", err)
 	}
-	}()
-
 	log.Info("serving web ui", "addr", cfg.HTTPAddr, "user", cfg.UserID)
-	if err := srv.ListenAndServe(); err != nil && !errors.Is(err, http.ErrServerClosed) {
+	if err := serveHTTP(ctx, srv, ln, extra, workerDone, shutdownGrace); err != nil {
-		return fmt.Errorf("serve: %w", err)
+		return err
 	}
 	return nil
 }

cmd/tapir/shutdown.go

@@ -0,0 +1,55 @@
+package main
+
+import (
+	"context"
+	"errors"
+	"fmt"
+	"net"
+	"net/http"
+	"os"
+	"os/signal"
+	"syscall"
+	"time"
+)
+
+// shutdownGrace bounds each wait at shutdown (in-flight requests, then the worker). Two of
+// them stay inside Kubernetes' default 30 s termination grace.
+const shutdownGrace = 10 * time.Second
+
+// shutdownContext is cancelled by SIGINT (a terminal) or SIGTERM (what Kubernetes sends
+// on every deploy). Handling only SIGINT meant a deploy killed the process before any
+// shutdown code ran (#50).
+func shutdownContext(parent context.Context) (context.Context, context.CancelFunc) {
+	return signal.NotifyContext(parent, os.Interrupt, syscall.SIGTERM)
+}
+
+// serveHTTP serves srv on ln until it fails or ctx ends, then shuts every server down and
+// waits for in-flight requests and for workerDone (nil: no worker) to finish, each for at
+// most grace. It must not return earlier: Serve returns http.ErrServerClosed as soon as
+// Shutdown STARTS, and returning from main kills the drain and the worker's last write.
+func serveHTTP(ctx context.Context, srv *http.Server, ln net.Listener, extra []*http.Server, workerDone <-chan struct{}, grace time.Duration) error {
+	errc := make(chan error, 1)
+	go func() { errc <- srv.Serve(ln) }()
+
+	select {
+	case err := <-errc:
+		if !errors.Is(err, http.ErrServerClosed) {
+			return fmt.Errorf("serve: %w", err)
+		}
+		return nil
+	case <-ctx.Done():
+	}
+
+	shutdownCtx, cancel := context.WithTimeout(context.Background(), grace)
+	defer cancel()
+	for _, s := range append([]*http.Server{srv}, extra...) {
+		_ = s.Shutdown(shutdownCtx)
+	}
+	if workerDone != nil {
+		select {
+		case <-workerDone:
+		case <-time.After(grace):
+		}
+	}
+	return nil
+}

cmd/tapir/shutdown_test.go

@@ -0,0 +1,124 @@
+package main
+
+import (
+	"context"
+	"net/http"
+	"net/http/httptest"
+	"os"
+	"sync"
+	"syscall"
+	"testing"
+	"time"
+)
+
+// Kubernetes stops a pod with SIGTERM; only SIGINT was handled, so a deploy killed the
+// process without running any shutdown code (#50).
+func TestShutdownContext_IsCancelledBySIGTERMAndSIGINT(t *testing.T) {
+	for _, sig := range []syscall.Signal{syscall.SIGTERM, syscall.SIGINT} {
+		t.Run(sig.String(), func(t *testing.T) {
+			ctx, stop := shutdownContext(context.Background())
+			defer stop()
+
+			if err := syscall.Kill(os.Getpid(), sig); err != nil {
+				t.Fatalf("send %v: %v", sig, err)
+			}
+
+			select {
+			case <-ctx.Done():
+			case <-time.After(2 * time.Second):
+				t.Fatalf("context not cancelled by %v", sig)
+			}
+		})
+	}
+}
+
+// serveHTTP must not return while a request is in flight or the worker is still recording
+// its job: Serve returns http.ErrServerClosed as soon as Shutdown STARTS, and returning
+// from it let the process exit before either finished (#50). Each half is tested with the
+// other already satisfied, so neither can hold the call open on the other's behalf.
+
+func pendingFor(t *testing.T, returned <-chan error, why string) {
+	t.Helper()
+	select {
+	case err := <-returned:
+		t.Fatalf("serveHTTP returned (%v) %s", err, why)
+	case <-time.After(150 * time.Millisecond):
+	}
+}
+
+func TestServeHTTP_DrainsAnInFlightRequestBeforeReturning(t *testing.T) {
+	release := make(chan struct{})
+	entered := make(chan struct{})
+	srv := httptest.NewUnstartedServer(http.HandlerFunc(func(w http.ResponseWriter, _ *http.Request) {
+		close(entered)
+		<-release
+		_, _ = w.Write([]byte("ok"))
+	}))
+	srv.Start()
+	defer srv.Close()
+	var once sync.Once
+	releaseHandler := func() { once.Do(func() { close(release) }) }
+	defer releaseHandler() // runs before srv.Close: a failing test must not hang on the blocked handler
+	ctx, cancel := context.WithCancel(context.Background())
+	workerDone := make(chan struct{})
+	close(workerDone) // the worker is already done: only the request can hold serveHTTP open
+	returned := make(chan error, 1)
+	go func() { returned <- serveHTTP(ctx, srv.Config, srv.Listener, nil, workerDone, 5*time.Second) }()
+
+	go func() { _, _ = http.Get(srv.URL) }()
+	<-entered
+	cancel()
+
+	pendingFor(t, returned, "while a request was still in flight")
+	releaseHandler()
+	select {
+	case err := <-returned:
+		if err != nil {
+			t.Fatalf("serveHTTP: %v", err)
+		}
+	case <-time.After(2 * time.Second):
+		t.Fatal("serveHTTP did not return once the request finished")
+	}
+}
+
+func TestServeHTTP_WaitsForTheWorkerBeforeReturning(t *testing.T) {
+	srv := httptest.NewUnstartedServer(http.NotFoundHandler())
+	srv.Start()
+	defer srv.Close()
+	ctx, cancel := context.WithCancel(context.Background())
+	workerDone := make(chan struct{})
+	returned := make(chan error, 1)
+	go func() { returned <- serveHTTP(ctx, srv.Config, srv.Listener, nil, workerDone, 5*time.Second) }() // no request in flight
+
+	cancel()
+
+	pendingFor(t, returned, "before the worker finished")
+	close(workerDone)
+	select {
+	case err := <-returned:
+		if err != nil {
+			t.Fatalf("serveHTTP: %v", err)
+		}
+	case <-time.After(2 * time.Second):
+		t.Fatal("serveHTTP did not return once the worker finished")
+	}
+}
+
+func TestServeHTTP_GivesUpOnAWorkerThatNeverFinishesAfterTheGrace(t *testing.T) {
+	srv := httptest.NewUnstartedServer(http.NotFoundHandler())
+	srv.Start()
+	defer srv.Close()
+	ctx, cancel := context.WithCancel(context.Background())
+	returned := make(chan error, 1)
+	go func() {
+		returned <- serveHTTP(ctx, srv.Config, srv.Listener, nil, make(chan struct{}), 200*time.Millisecond)
+	}()
+
+	cancel()
+
+	select {
+	case <-returned:
+	case <-time.After(3 * time.Second):
+		t.Fatal("a stuck worker must not hold the process past the grace period")
+	}
+}

docs/sprints/audio-upload-followups-2026-10.md

@@ -0,0 +1,88 @@
+# Sprint: audio upload follow-ups (Sweep Sprint, 2026-10)
+
+Method: Sweep Sprint (phase 1 parallel read-only research per issue: **done**; phase 2 sequential
+execution, one issue per commit: **not started, waits for the owner's go**). Closing oath below.
+
+Milestones: [v0.31.1 - security and robustness](https://git.d-ma.be/mathias/tapir/milestone/10),
+[v0.32.0 - audio upload follow-ups](https://git.d-ma.be/mathias/tapir/milestone/11).
+
+Context: v0.31.0 shipped audio upload (ADR-033/034/035) and is live in production behind auth at
+`/uploads`, with the Berget cloud fallback on for audio (infra#522). A real 63.7 min upload
+transcribed in 2m53s with no errors. The phase-1 investigation found two pre-existing or new
+weaknesses an authenticated user can reach, so the first release is a hotfix.
+
+## Oath (closing gates, every clause must hold; blocked = descoped and tracked, never "done")
+
+| # | Clause | Evidence |
+|---|--------|----------|
+| SG1 | Every issue in the sprint is closed with a linked commit, or moved out with a stated reason | issue list of both milestones |
+| SG2 | Each fix has a test that was seen red on main first, named after the mechanism it observes | red/green output in the issue |
+| SG3 | `task check` AND `golangci-lint run ./...` exit 0 (checked by `$?`, not by grep); `task check` does not gate lint until #41 | gate output |
+| SG4 | Control code (#48, #49, the upload cap in #47) has a recorded adversarial review verified by execution, verdict in the issue | gatekeeper verdict comment |
+| SG5 | Docs current in the same commit: ADR-033/035 text, feature file, use-case coverage test | diff |
+| SG6 | Each release tagged (v0.31.1, v0.32.0), pushed, deployed, and observed live (pod running the new image, no restart loop, a real upload still works) | `kubectl`/log + one upload |
+| SG7 | Learnings written to the brain; deferred work filed as issues; decisions that are the owner's recorded as DECISION NEEDED | brain ids + issue numbers |
+
+## Work order
+
+### v0.31.1 (security and robustness; hotfix, do first)
+
+1. **#41 lint gate.** `task check` swallows lint findings (`|| echo`). Make the gate fail on findings,
+   fix what it surfaces. First, so every later gate means something. (Decision D1.)
+2. **#48 cross-origin POST protection.** `http.NewCrossOriginProtection()` around `Router()`.
+   Red: foreign-origin POST to `/account/delete`, `/uploads`, `/uploads/{id}/chat` is refused.
+3. **#49 ffprobe/ffmpeg limits.** `-max_streams 32` + narrower probe output; probe stdout cap;
+   probe deadline. Three commits.
+4. **#47 concurrent-upload cap (remaining item).** Bound the spool: reservation per accepted upload
+   against the 6Gi emptyDir so concurrent uploads cannot evict the pod.
+5. **#50 SIGTERM interim.** Handle SIGTERM; record the interrupted job at once; fix the false
+   comment. Full drain recorded as a limitation. (Decision D2.)
+
+Release v0.31.1: one adversarial review round over 2-5, then tag, push, observe.
+
+### v0.32.0 (follow-ups)
+
+6. **#52** label a cloud-served transcript in plain words; document the empty-transcript trigger.
+7. **#53** bound the LLM client's response body read.
+8. **#51** tracker: save timeout, then app-clock heartbeat.
+9. **#37** nav link to uploads and per-recording delete (queued/transcribing: refuse until it
+   ends). (Decision D3.)
+10. **#36** chat default model after measurement. (Decision D4.)
+11. **#38** measurements (Berget length limit, large models on production iguana). (D5, D6.)
+12. **#46** remainder of the hardening list after the items above are split out.
+13. **#45** evaluate Berget as the reconciler: a question, not work. (D8.)
+
+## DECISION NEEDED (owner's call; recommendation first)
+
+| # | Question | Recommendation | Blocks |
+|---|----------|----------------|--------|
+| D1 | #41: should any linter be allowed to opt out of the gate? | No opt-out; fix findings | #41 |
+| D2 | #50: full SIGTERM drain, or record as a limitation and ship the interim fix? | Limitation + interim; a drain costs 4-6 h and downtime on every deploy at current volume | #50 |
+| D3 | #37: delete of a queued/transcribing recording | Refuse until it ends | #37 |
+| D4 | #36: make a 31B model the chat default? | Only after measurement, conditional | #36 |
+| D5 | #38: Berget length measurement needs a throwaway key | Yes, throwaway key | #38 |
+| D6 | #38: load large models on production iguana | Yes, in a quiet window with the owner present | #38 |
+| D7 | #46: where the ffmpeg tarball lives | Do nothing now; file an issue | none |
+| D8 | #45: evaluate Berget as the reconciler | No; stay local-only | #45 |
+| D9 | Who judges ADR-034's second blind check | The owner; do not reuse the one-off Opus authorisation | ADR-034 |
+| D10 | When to enable reconcile in production | Needs `iguana/pianissimo` in the key pin and env vars; owner present | ADR-034 |
+
+## Dropped or reduced, with reasons
+
+- **#46 item 1 (`alis`/`dref` external reference):** checked, not a problem. Under the application's
+  flags ffmpeg skips the external track and writes a 78-byte WAV.
+- **#46 item 2 / #47 item 2:** merged into #49.
+- **#47 item 3 (full drain):** reduced to #50 plus a recorded limitation.
+- **#46 `Beat` taking the tracker mutex:** incorrect in #46; only `logStill` does. Corrected in #51.
+
+## Human-present items (do not run unattended)
+
+- Production iguana model loads (#38, D6).
+- Enabling reconcile in production (D10).
+- Any key change or `apply` in infra (infra#523, infra#524 are open and not part of this sprint).
+
+## Release plan
+
+SemVer: v0.31.1 patch (fixes, no new behaviour); v0.32.0 minor (nav link, delete, cloud labelling).
+Every push to tapir main redeploys the pod and fails any job in flight: push when no upload is
+running (check the pod log first).

internal/adapters/audio/ffmpeg.go

@@ -47,11 +47,15 @@ func (f *FFmpeg) ToWAV(ctx context.Context, src, dst string) error {
 	args = append(args, "-f", "wav", dst)
 	cmd := exec.CommandContext(ctx, bin, args...)
 	cmd.WaitDelay = killGrace
-	if out, err := cmd.CombinedOutput(); err != nil {
+	// Only a bounded head of ffmpeg's output is kept: a hostile file made it print ~0.4
+	// bytes per input byte, all of which CombinedOutput would buffer and copy (#49).
+	out := &headWriter{max: maxStderr}
+	cmd.Stdout, cmd.Stderr = out, out
+	if err := cmd.Run(); err != nil {
 		if ctxErr := ctx.Err(); ctxErr != nil {
 			return fmt.Errorf("audio: ffmpeg: %w", ctxErr)
 		}
-		return fmt.Errorf("audio: ffmpeg: %w: %s", err, strings.TrimSpace(string(out)))
+		return fmt.Errorf("audio: ffmpeg: %w: %s", err, strings.TrimSpace(out.buf.String()))
 	}
 	// A zero exit that wrote nothing is still a failure: never hand whisper a
 	// missing file and let the error surface three layers later.

internal/adapters/audio/ffmpeg_test.go

@@ -109,3 +109,32 @@ printf data > "$last"`)
 	require.NoError(t, err)
 	assert.NotContains(t, " "+strings.ReplaceAll(string(raw), "\n", " ")+" ", " -t ")
 }
+
+func TestFFmpegToWAV_CapsTheStreamCountBeforeTheInput(t *testing.T) {
+	// ffmpeg also allocated ~570 MB opening the 900-stream file (#49).
+	rec := filepath.Join(t.TempDir(), "argv")
+	bin := stub(t, `printf '%s\n' "$@" > `+rec+`
+for a; do last="$a"; done
+printf data > "$last"`)
+
+	err := (&audio.FFmpeg{Bin: bin}).ToWAV(context.Background(), "/spool/in", filepath.Join(t.TempDir(), "o.wav"))
+
+	require.NoError(t, err)
+	args := argvOf(t, rec)
+	ms, in := indexOf(args, "-max_streams"), indexOf(args, "-i")
+	require.GreaterOrEqual(t, ms, 0, "argv: %v", args)
+	assert.Equal(t, "32", args[ms+1])
+	assert.Less(t, ms, in, "an input option placed after -i is applied to the output")
+}
+
+func TestFFmpegToWAV_ABoundedPartOfAFloodingStderrIsKept(t *testing.T) {
+	// A hostile mp3 made ffmpeg print ~0.4 bytes of stderr per input byte (83 MB for a
+	// 209 MB file), all of it buffered, then copied twice into the error (#49 review).
+	bin := stub(t, `head -c 5000000 /dev/zero | tr '\0' 'e' >&2; exit 1`)
+
+	err := (&audio.FFmpeg{Bin: bin}).ToWAV(context.Background(), "/spool/in", filepath.Join(t.TempDir(), "o.wav"))
+
+	require.Error(t, err)
+	assert.Less(t, len(err.Error()), 16*1024, "the error carries a bounded head of stderr, not all of it")
+	assert.Contains(t, err.Error(), "eeee", "and still carries some of it")
+}

internal/adapters/audio/ffprobe.go

@@ -4,6 +4,7 @@
 package audio
 
 import (
+	"bytes"
 	"context"
 	"encoding/json"
 	"errors"
@@ -19,6 +20,51 @@ import (
 type FFprobe struct {
 	// Bin is the ffprobe executable ("ffprobe" resolves via PATH).
 	Bin string
+	// MaxOutput bounds how much of ffprobe's stdout is read; zero means DefaultMaxOutput.
+	MaxOutput int
+	// Timeout bounds one probe; zero means DefaultProbeTimeout. A probe is milliseconds of
+	// work on a real file, so one that runs this long is the FILE's doing (#49).
+	Timeout time.Duration
+}
+
+// DefaultProbeTimeout is the probe deadline when FFprobe.Timeout is unset.
+const DefaultProbeTimeout = 45 * time.Second
+
+// DefaultMaxOutput is far above the narrowed probe output of a legitimate file (a few
+// hundred bytes) and far below what a hostile one can make ffprobe print.
+const DefaultMaxOutput = 1 << 20
+
+// maxStderr is how much of ffprobe's stderr is kept for the error message.
+const maxStderr = 4096
+
+// errOutputCap is the write error that stops ffprobe once it prints past the cap.
+var errOutputCap = errors.New("audio: ffprobe output exceeds the cap")
+
+// capWriter collects up to max bytes and then refuses further writes, which closes the
+// pipe and ends the process instead of buffering whatever it prints.
+type capWriter struct {
+	buf bytes.Buffer
+	max int
+}
+
+func (w *capWriter) Write(p []byte) (int, error) {
+	if w.buf.Len()+len(p) > w.max {
+		return 0, errOutputCap
+	}
+	return w.buf.Write(p)
+}
+
+// headWriter keeps the first max bytes and silently drops the rest.
+type headWriter struct {
+	buf bytes.Buffer
+	max int
+}
+
+func (w *headWriter) Write(p []byte) (int, error) {
+	if room := w.max - w.buf.Len(); room > 0 {
+		w.buf.Write(p[:min(room, len(p))])
+	}
+	return len(p), nil
 }
 
 // AllowedDemuxers are the input formats an upload may be. The input is
@@ -30,9 +76,22 @@ type FFprobe struct {
 // formats. "mov" covers .mp4/.m4a/.3gp; "matroska" covers .webm.
 const AllowedDemuxers = "wav,mov,mp4,m4a,3gp,mp3,ogg,matroska,webm,flac,aac,opus,aiff,amr,asf"
 
+// MaxStreams bounds how many streams a file may declare. A 1.3 MB file declaring 900 of
+// them cost ~570 MB of RSS in each of ffprobe and ffmpeg (#49), against a 512 Mi pod;
+// real recordings have a handful.
+const MaxStreams = "32"
+
 // inputRestrictions are ffmpeg/ffprobe INPUT options and must precede the input.
-// Local files and pipes only: no network, no other protocols.
+// Local files and pipes only: no network, no other protocols, and a bounded stream count.
-var inputRestrictions = []string{"-protocol_whitelist", "file,pipe", "-format_whitelist", AllowedDemuxers}
+var inputRestrictions = []string{
+	"-protocol_whitelist", "file,pipe",
+	"-format_whitelist", AllowedDemuxers,
+	"-max_streams", MaxStreams,
+}
+
+// probeEntries is exactly what ParseProbe reads. -show_format/-show_streams print every
+// tag too, and a 120 MB WAV made 491 MB of JSON that Output() buffers.
+const probeEntries = "format=duration:stream=codec_type:stream_disposition=attached_pic"
 
 // killGrace bounds how long Probe waits for a cancelled ffprobe's pipes to close.
 const killGrace = 2 * time.Second
@@ -48,21 +107,38 @@ func (f *FFprobe) Probe(ctx context.Context, path string) (uploads.Probe, error)
 		bin = "ffprobe"
 	}
 	args := append([]string{"-v", "error"}, inputRestrictions...)
-	args = append(args, "-print_format", "json", "-show_format", "-show_streams", path)
+	args = append(args, "-print_format", "json", "-show_entries", probeEntries, path)
-	cmd := exec.CommandContext(ctx, bin, args...)
+	timeout := f.Timeout
+	if timeout <= 0 {
+		timeout = DefaultProbeTimeout
+	}
+	probeCtx, cancel := context.WithTimeout(ctx, timeout)
+	defer cancel()
+	cmd := exec.CommandContext(probeCtx, bin, args...)
 	cmd.WaitDelay = killGrace
-	out, err := cmd.Output()
+	maxOut := f.MaxOutput
-	if err != nil {
+	if maxOut <= 0 {
-		if ctxErr := ctx.Err(); ctxErr != nil {
+		maxOut = DefaultMaxOutput
+	}
+	stdout, stderr := &capWriter{max: maxOut}, &headWriter{max: maxStderr}
+	cmd.Stdout, cmd.Stderr = stdout, stderr
+	if err := cmd.Run(); err != nil {
+		if ctxErr := ctx.Err(); ctxErr != nil { // the caller gave up: not a verdict on the file
 			return uploads.Probe{}, fmt.Errorf("audio: ffprobe: %w", ctxErr)
 		}
+		if probeCtx.Err() != nil { // our own deadline passed while the caller was still waiting
+			return uploads.Probe{}, fmt.Errorf("%w: ffprobe did not finish within %s", uploads.ErrUnreadable, timeout)
+		}
+		if errors.Is(err, errOutputCap) {
+			return uploads.Probe{}, fmt.Errorf("%w: ffprobe printed more than %d bytes", uploads.ErrUnreadable, maxOut)
+		}
 		var exit *exec.ExitError
 		if errors.As(err, &exit) {
-			return uploads.Probe{}, fmt.Errorf("%w: ffprobe: %s", uploads.ErrUnreadable, exit.Stderr)
+			return uploads.Probe{}, fmt.Errorf("%w: ffprobe: %s", uploads.ErrUnreadable, stderr.buf.String())
 		}
 		return uploads.Probe{}, fmt.Errorf("audio: run ffprobe: %w", err)
 	}
-	p, err := ParseProbe(out)
+	p, err := ParseProbe(stdout.buf.Bytes())
 	if err != nil {
 		return uploads.Probe{}, fmt.Errorf("audio: ffprobe output: %w", err)
 	}

internal/adapters/audio/ffprobe_test.go

@@ -184,3 +184,78 @@ func TestAllowedDemuxers_ExcludeThePlaylistFormats(t *testing.T) {
 		assert.Contains(t, strings.Split(audio.AllowedDemuxers, ","), good)
 	}
 }
+
+func TestFFprobeProbe_CapsTheStreamCountBeforeTheInput(t *testing.T) {
+	// A 1.3 MB file declaring 900 streams cost ~570 MB of RSS in ffprobe (#49) against
+	// a 512 Mi pod. -max_streams is an input option: it must precede the path.
+	bin, argvFile := argvStub(t)
+
+	_, err := (&audio.FFprobe{Bin: bin}).Probe(context.Background(), "/spool/upload-1")
+
+	require.NoError(t, err)
+	args := argvOf(t, argvFile)
+	ms := indexOf(args, "-max_streams")
+	require.GreaterOrEqual(t, ms, 0, "argv: %v", args)
+	assert.Equal(t, "32", args[ms+1])
+	assert.Less(t, ms, len(args)-1, "must come before the path, which stays last")
+}
+
+func TestFFprobeProbe_AsksOnlyForTheFieldsParseProbeReads(t *testing.T) {
+	// -show_format/-show_streams print every tag: a 120 MB WAV produced 491 MB of JSON
+	// that cmd.Output() buffers in Go (#49).
+	bin, argvFile := argvStub(t)
+
+	_, err := (&audio.FFprobe{Bin: bin}).Probe(context.Background(), "/spool/upload-1")
+
+	require.NoError(t, err)
+	args := argvOf(t, argvFile)
+	assert.Equal(t, -1, indexOf(args, "-show_format"), "argv: %v", args)
+	assert.Equal(t, -1, indexOf(args, "-show_streams"), "argv: %v", args)
+	se := indexOf(args, "-show_entries")
+	require.GreaterOrEqual(t, se, 0, "argv: %v", args)
+	assert.Equal(t, "format=duration:stream=codec_type:stream_disposition=attached_pic", args[se+1])
+}
+
+func TestFFprobeProbe_OutputPastTheCapIsUnreadableNotBuffered(t *testing.T) {
+	// ffprobe's stdout is attacker-influenced (tags, 491 MB observed). Past the cap the
+	// probe is stopped and the file is reported as unreadable (#49).
+	bin := stub(t, `head -c 200000 /dev/zero | tr '\0' 'a'`)
+
+	_, err := (&audio.FFprobe{Bin: bin, MaxOutput: 4096}).Probe(context.Background(), "/x")
+
+	assert.ErrorIs(t, err, uploads.ErrUnreadable)
+}
+
+func TestFFprobeProbe_OutputWithinTheCapIsParsed(t *testing.T) {
+	bin := stub(t, `echo '{"streams":[{"codec_type":"audio"}],"format":{"duration":"90"}}'`)
+
+	got, err := (&audio.FFprobe{Bin: bin, MaxOutput: 4096}).Probe(context.Background(), "/x")
+
+	require.NoError(t, err)
+	assert.True(t, got.HasAudio)
+}
+
+func TestFFprobeProbe_AHungProbeTimesOutOnItsOwnDeadlineAsUnreadableNotAsOurFault(t *testing.T) {
+	// Accept runs the probe on the request context, which has no deadline of its own;
+	// a probe that never returns would pin a request (#49). `exec` so the sleep is the
+	// process itself and not a child holding the pipe open.
+	bin := stub(t, `exec sleep 30`)
+
+	start := time.Now()
+	_, err := (&audio.FFprobe{Bin: bin, Timeout: 200 * time.Millisecond}).Probe(context.Background(), "/x")
+
+	assert.ErrorIs(t, err, uploads.ErrUnreadable)
+	assert.Less(t, time.Since(start), 3*time.Second)
+}
+
+func TestFFprobeProbe_ParentCancellationIsStillNotUnreadableWhenATimeoutIsSet(t *testing.T) {
+	bin := stub(t, `exec sleep 30`)
+	ctx, cancel := context.WithTimeout(context.Background(), 100*time.Millisecond)
+	defer cancel()
+
+	_, err := (&audio.FFprobe{Bin: bin, Timeout: time.Minute}).Probe(ctx, "/x")
+
+	require.Error(t, err)
+	assert.False(t, errors.Is(err, uploads.ErrUnreadable), "the caller giving up is not a verdict on the file")
+	assert.ErrorIs(t, err, context.DeadlineExceeded)
+}

internal/adapters/store/uploaded_transcripts.go

@@ -88,12 +88,16 @@ func (s *Store) Heartbeat(ctx context.Context, userID, id string) error {
 		  WHERE id = $1 AND user_id = $2`)
 }
 
-// FailUpload moves an upload to failed with a typed reason.
+// FailUpload moves a queued or transcribing upload to failed with a typed reason. A
+// finished upload is left as it was: a shutdown can record a job as failed after its
+// transcript was already committed (the commit lands, the caller sees a cancelled
+// context), and that must not hide the text. Such a call touches no row and returns
+// ErrUploadNotFound.
 func (s *Store) FailUpload(ctx context.Context, userID, id string, kind domain.UploadErrorKind) error {
 	return s.updateUpload(ctx, userID, id, "fail upload",
 		`UPDATE uploaded_transcripts
 		    SET status = 'failed', error_kind = $3, finished_at = NOW()
-		  WHERE id = $1 AND user_id = $2`,
+		  WHERE id = $1 AND user_id = $2 AND status IN ('queued', 'transcribing')`,
 		string(kind))
 }
 

internal/adapters/store/uploaded_transcripts_failguard_test.go

@@ -0,0 +1,47 @@
+package store_test
+
+// A shutdown can record a job as failed after its transcript was already committed (the
+// commit lands, the caller sees a cancelled context). FailUpload must not be able to turn a
+// finished row into a failed one and hide the text (#50 review).
+
+import (
+	"context"
+	"testing"
+
+	"github.com/stretchr/testify/assert"
+	"github.com/stretchr/testify/require"
+
+	"git.d-ma.be/mathias/tapir/internal/domain"
+)
+
+func TestFailUpload_LeavesAFinishedUploadAsItWas(t *testing.T) {
+	s := newStore(t)
+	ctx := context.Background()
+	id := startedUpload(t, s)
+	require.NoError(t, s.StartTranscribing(ctx, userA, id))
+	require.NoError(t, s.CompleteUpload(ctx, userA, id, domain.Transcription{Text: "synthetic text", Endpoint: "iguana/kb-whisper"}))
+
+	_ = s.FailUpload(ctx, userA, id, domain.UploadErrInterrupted)
+
+	got, err := s.GetUpload(ctx, userA, id)
+	require.NoError(t, err)
+	assert.Equal(t, domain.UploadDone, got.Status)
+	assert.Equal(t, "synthetic text", got.Content)
+	assert.Empty(t, got.ErrorKind)
+}
+
+func TestFailUpload_StillFailsAQueuedOrTranscribingUpload(t *testing.T) {
+	s := newStore(t)
+	ctx := context.Background()
+	queued := startedUpload(t, s)
+	running, err := s.CreateUpload(ctx, userA, "r", false)
+	require.NoError(t, err)
+	require.NoError(t, s.StartTranscribing(ctx, userA, running))
+
+	for _, id := range []string{queued, running} {
+		require.NoError(t, s.FailUpload(ctx, userA, id, domain.UploadErrBusy))
+		got, err := s.GetUpload(ctx, userA, id)
+		require.NoError(t, err)
+		assert.Equal(t, domain.UploadFailed, got.Status)
+	}
+}

internal/uploads/intake.go

@@ -6,6 +6,7 @@ import (
 	"fmt"
 	"io"
 	"os"
+	"sync"
 	"time"
 
 	"git.d-ma.be/mathias/tapir/internal/domain"
@@ -51,6 +52,53 @@ type Intake struct {
 	sub    Submitter
 	limits Limits
 	tmpDir string
+
+	// MaxReceives and MaxReceivesPerUser bound how many request bodies Accept reads at
+	// once; zero means the defaults. Without them N parallel POSTs each spool up to
+	// MaxBytes while the queue still looks empty, and the spool volume fills (#47).
+	MaxReceives        int
+	MaxReceivesPerUser int
+
+	mu       sync.Mutex
+	receives int
+	byUser   map[string]int
+}
+
+const (
+	defaultMaxReceives        = 4
+	defaultMaxReceivesPerUser = 2
+)
+
+// acquireReceive reserves a receive slot for userID, or reports there is none. Every
+// successful call must be paired with releaseReceive.
+func (in *Intake) acquireReceive(userID string) bool {
+	maxAll, maxUser := in.MaxReceives, in.MaxReceivesPerUser
+	if maxAll <= 0 {
+		maxAll = defaultMaxReceives
+	}
+	if maxUser <= 0 {
+		maxUser = defaultMaxReceivesPerUser
+	}
+	in.mu.Lock()
+	defer in.mu.Unlock()
+	if in.receives >= maxAll || in.byUser[userID] >= maxUser {
+		return false
+	}
+	if in.byUser == nil {
+		in.byUser = map[string]int{}
+	}
+	in.receives++
+	in.byUser[userID]++
+	return true
+}
+
+func (in *Intake) releaseReceive(userID string) {
+	in.mu.Lock()
+	defer in.mu.Unlock()
+	in.receives--
+	if in.byUser[userID]--; in.byUser[userID] <= 0 {
+		delete(in.byUser, userID)
+	}
 }
 
 // NewIntake wires an Intake. tmpDir is where uploads are spooled; it must exist.
@@ -94,6 +142,11 @@ func (in *Intake) Accept(ctx context.Context, userID, title string, src io.Reade
 	if rc, ok := in.sub.(interface{ HasRoom(userID string) bool }); ok && !rc.HasRoom(userID) {
 		return "", &RejectError{Reason: ReasonBusy, Message: busyMessage}
 	}
+	// HasRoom cannot see bodies still being received; bound those separately.
+	if !in.acquireReceive(userID) {
+		return "", &RejectError{Reason: ReasonBusy, Message: busyMessage}
+	}
+	defer in.releaseReceive(userID)
 	f, err := os.CreateTemp(in.tmpDir, "upload-*")
 	if err != nil {
 		return "", fmt.Errorf("uploads: spool: %w", err)

internal/uploads/intake_concurrency_test.go

@@ -0,0 +1,131 @@
+package uploads_test
+
+// Observes how many request bodies Accept will read at once (#47). HasRoom and the
+// per-user queue cap act before and after the receive; N parallel POSTs all pass
+// HasRoom while the queue is still empty, so the receive itself is bounded.
+
+import (
+	"context"
+	"errors"
+	"io"
+	"strings"
+	"testing"
+	"time"
+
+	"github.com/stretchr/testify/assert"
+	"github.com/stretchr/testify/require"
+
+	"git.d-ma.be/mathias/tapir/internal/uploads"
+)
+
+// slowReceive starts an Accept whose body stays open until the returned writer is closed,
+// and waits until it holds a spool file, which proves it is inside the receive.
+type slowReceive struct {
+	w        *io.PipeWriter
+	done     chan error
+	finished bool
+}
+
+func startSlowReceive(t *testing.T, r *rig, in *uploads.Intake, user string, wantFiles int) *slowReceive {
+	t.Helper()
+	pr, pw := io.Pipe()
+	s := &slowReceive{w: pw, done: make(chan error, 1)}
+	go func() {
+		_, err := in.Accept(context.Background(), user, "t", pr)
+		s.done <- err
+	}()
+	require.Eventually(t, func() bool { return len(r.tmpFiles(t)) == wantFiles }, 2*time.Second, 5*time.Millisecond,
+		"the receive for %s should have started", user)
+	// An abandoned receive ends in a read error, so it never reaches the rig's fakes, which
+	// are not safe for concurrent use. A receive that finish() already ended is a no-op.
+	t.Cleanup(func() {
+		if s.finished {
+			return
+		}
+		_ = pw.CloseWithError(errors.New("test over"))
+		select {
+		case <-s.done:
+		case <-time.After(2 * time.Second):
+		}
+	})
+	return s
+}
+
+func (s *slowReceive) finish(t *testing.T) error {
+	t.Helper()
+	_, _ = s.w.Write([]byte("data"))
+	require.NoError(t, s.w.Close())
+	s.finished = true
+	select {
+	case err := <-s.done:
+		return err
+	case <-time.After(2 * time.Second):
+		t.Fatal("Accept did not return after its body ended")
+		return nil
+	}
+}
+
+func requireBusy(t *testing.T, err error) {
+	t.Helper()
+	var rej *uploads.RejectError
+	require.True(t, errors.As(err, &rej), "want a busy rejection, got %v", err)
+	assert.Equal(t, uploads.ReasonBusy, rej.Reason)
+}
+
+func TestAccept_APerUserLimitOnConcurrentReceivesRefusesTheNextBodyBeforeSpoolingIt(t *testing.T) {
+	r := newRig(t)
+	in := uploads.NewIntake(r.st, r.pr, r.sub, uploads.Limits{MaxBytes: 1024, MaxDuration: time.Hour}, r.tmp)
+	in.MaxReceivesPerUser = 2
+	in.MaxReceives = 10
+	startSlowReceive(t, r, in, "user-1", 1)
+	startSlowReceive(t, r, in, "user-1", 2)
+
+	_, err := in.Accept(context.Background(), "user-1", "t", strings.NewReader("data"))
+
+	requireBusy(t, err)
+	assert.Len(t, r.tmpFiles(t), 2, "the refused body was never spooled")
+	// Another user is not blocked by user-1's two receives.
+	other := startSlowReceive(t, r, in, "user-2", 3)
+	require.NoError(t, other.finish(t))
+}
+
+func TestAccept_AnOverallLimitOnConcurrentReceivesRefusesTheNextUser(t *testing.T) {
+	r := newRig(t)
+	in := uploads.NewIntake(r.st, r.pr, r.sub, uploads.Limits{MaxBytes: 1024, MaxDuration: time.Hour}, r.tmp)
+	in.MaxReceivesPerUser = 5
+	in.MaxReceives = 3
+	for i, u := range []string{"a", "b", "c"} {
+		startSlowReceive(t, r, in, u, i+1)
+	}
+
+	_, err := in.Accept(context.Background(), "d", "t", strings.NewReader("data"))
+
+	requireBusy(t, err)
+	assert.Len(t, r.tmpFiles(t), 3)
+}
+
+func TestAccept_AFinishedReceiveFreesItsSlot(t *testing.T) {
+	r := newRig(t)
+	in := uploads.NewIntake(r.st, r.pr, r.sub, uploads.Limits{MaxBytes: 1024, MaxDuration: time.Hour}, r.tmp)
+	in.MaxReceivesPerUser = 1
+	in.MaxReceives = 5
+	first := startSlowReceive(t, r, in, "user-1", 1)
+	require.NoError(t, first.finish(t))
+
+	_, err := in.Accept(context.Background(), "user-1", "t", strings.NewReader("data"))
+
+	require.NoError(t, err, "the slot is released when Accept returns")
+}
+
+func TestAccept_AFailedReceiveFreesItsSlot(t *testing.T) {
+	r := newRig(t)
+	in := uploads.NewIntake(r.st, r.pr, r.sub, uploads.Limits{MaxBytes: 1024, MaxDuration: time.Hour}, r.tmp)
+	in.MaxReceivesPerUser = 1
+	in.MaxReceives = 5
+	_, err := in.Accept(context.Background(), "user-1", "t", &brokenBody{n: 1})
+	require.ErrorIs(t, err, uploads.ErrClientRead)
+
+	_, err = in.Accept(context.Background(), "user-1", "t", strings.NewReader("data"))
+
+	require.NoError(t, err, "a dropped client must not leak a slot")
+}

internal/uploads/intake_defaults_test.go

@@ -0,0 +1,31 @@
+package uploads_test
+
+// The limits production runs on are the DEFAULTS: nothing outside tests sets
+// MaxReceives or MaxReceivesPerUser. Pinned here with the literal numbers, so changing a
+// default is a visible decision (#47 review). With 4 receives, 20 queued and 1 running at
+// the 200 MiB cap, the spool needs ~5 GiB of the 6 Gi emptyDir (infra); raising any of
+// them or TAPIR_UPLOAD_MAX_BYTES must revisit that arithmetic.
+
+import (
+	"context"
+	"strings"
+	"testing"
+	"time"
+
+	"git.d-ma.be/mathias/tapir/internal/uploads"
+)
+
+func TestNewIntake_DefaultsAllowTwoReceivesPerUserAndFourOverall(t *testing.T) {
+	r := newRig(t)
+	in := uploads.NewIntake(r.st, r.pr, r.sub, uploads.Limits{MaxBytes: 1024, MaxDuration: time.Hour}, r.tmp)
+	startSlowReceive(t, r, in, "a", 1)
+	startSlowReceive(t, r, in, "a", 2)
+
+	_, err := in.Accept(context.Background(), "a", "t", strings.NewReader("x"))
+	requireBusy(t, err) // a third body from one user
+
+	startSlowReceive(t, r, in, "b", 3)
+	startSlowReceive(t, r, in, "b", 4)
+	_, err = in.Accept(context.Background(), "c", "t", strings.NewReader("x"))
+	requireBusy(t, err) // a fifth body overall
+}

internal/uploads/worker.go

@@ -176,9 +176,10 @@ func (w *Worker) Submit(j Job) error {
 }
 
 // Run processes queued jobs until ctx ends, then deletes the audio of anything
-// still queued and refuses new jobs. The rows of those jobs stay queued or
+// still queued and refuses new jobs. The job running at shutdown is recorded interrupted
-// transcribing and are failed as interrupted by the start-up sweep
+// by Process; the rows of jobs still queued stay queued and are failed as interrupted by
-// (store.FailInterruptedUploads): the audio is not retained, so they cannot resume.
+// the start-up sweep (store.FailInterruptedUploads): the audio is not retained, so they
+// cannot resume.
 func (w *Worker) Run(ctx context.Context) {
 	defer w.stop()
 	for {
@@ -227,7 +228,7 @@ func (w *Worker) stop() {
 // Process runs one job: row -> transcribing, convert, transcribe, store. The
 // uploaded file and the converted WAV are deleted on every path — the audio is
 // never retained (ADR-033). A failure is recorded with a TYPED kind; a shutdown
-// mid-job is not a failure and leaves the row for the start-up sweep.
+// mid-job is recorded as interrupted at once (see fail).
 //
 // Every phase is reported through one progress.Tracker, which saves it to the row for
 // the page and logs it, and a heartbeat stamps the row on its own while the job runs
@@ -269,7 +270,7 @@ func (w *Worker) Process(ctx context.Context, job Job) {
 	defer func() { stopBeat(); <-hbDone }() // no heartbeat outlives its job
 
 	// abort records where the job stopped. A shutdown (the parent context ended) is not
-	// a failure: the row is left for the start-up sweep, so the step stays as it was.
+	// a failure of the step: it stays as it was, and fail records the row as interrupted.
 	abort := func(kind domain.UploadErrorKind) {
 		if ctx.Err() == nil {
 			tr.FailRunning()
@@ -332,11 +333,19 @@ func (w *Worker) Process(ctx context.Context, job Job) {
 		"segments", len(t.Segments), "elapsed", time.Since(start).Round(time.Second))
 }
 
-// fail records a transcription failure — unless the PARENT context ended, which
+// interruptedWriteTimeout bounds the one write a dying process makes to record its job.
-// is a shutdown, not a failure: the row is left for the start-up sweep.
+const interruptedWriteTimeout = 3 * time.Second
+
+// fail records a transcription failure. When the PARENT context ended the process is
+// shutting down: the job is recorded interrupted at once, on a short context of its own,
+// because the process may exit before any other pod's start-up sweep would do it (#50).
+// The sweep remains the backstop for a process that is killed outright.
 func (w *Worker) fail(ctx context.Context, job Job, log *slog.Logger, kind domain.UploadErrorKind) {
 	if ctx.Err() != nil {
-		return
+		kind = domain.UploadErrInterrupted
+		var cancel context.CancelFunc
+		ctx, cancel = context.WithTimeout(context.WithoutCancel(ctx), interruptedWriteTimeout)
+		defer cancel()
 	}
 	if err := w.store.FailUpload(ctx, job.UserID, job.UploadID, kind); err != nil {
 		log.Error("upload: record failure", "kind", errkind.Of(err))

internal/uploads/worker_test.go

@@ -53,7 +53,10 @@ func (s *wStore) CompleteUpload(_ context.Context, _, id string, t domain.Transc
 	return nil
 }
 
-func (s *wStore) FailUpload(_ context.Context, _, id string, k domain.UploadErrorKind) error {
+func (s *wStore) FailUpload(ctx context.Context, _, id string, k domain.UploadErrorKind) error {
+	if err := ctx.Err(); err != nil { // like the real store: a cancelled context cannot write
+		return err
+	}
 	s.mu.Lock()
 	defer s.mu.Unlock()
 	s.failed[id] = k
@@ -242,7 +245,9 @@ func TestWorkerProcess_FailuresAreTypedAndStillDeleteTheAudio(t *testing.T) {
 	})
 }
 
-func TestWorkerProcess_ShutdownMidJobLeavesTheRowForTheStartupSweep(t *testing.T) {
+func TestWorkerProcess_ShutdownMidJobRecordsTheRowInterruptedAtOnce(t *testing.T) {
+	// SIGTERM on a deploy used to leave the row "transcribing" until the NEXT pod's
+	// start-up sweep; the process may exit before any sweep runs (#50).
 	r := newWRig(t, time.Minute)
 	r.tr.block = make(chan struct{})
 	ctx, cancel := context.WithCancel(context.Background())
@@ -255,8 +260,8 @@ func TestWorkerProcess_ShutdownMidJobLeavesTheRowForTheStartupSweep(t *testing.T
 	<-done
 
 	_, f := r.st.snapshot()
-	assert.Empty(t, f, "a shutdown is not a transcription failure: the row stays for FailInterruptedUploads to mark interrupted")
+	assert.Equal(t, domain.UploadErrInterrupted, f["a"], "the row is recorded interrupted by the dying process, not left for a sweep")
-	assert.Empty(t, r.leftovers(t), "but the audio is still deleted")
+	assert.Empty(t, r.leftovers(t), "and the audio is still deleted")
 }
 
 func TestWorkerProcess_AJobThatOutlivesItsTimeoutIsFailedNotStuck(t *testing.T) {

internal/web/crossorigin_test.go

@@ -0,0 +1,137 @@
+package web_test
+
+// Observes the cross-origin gate around Router (#48): SameSite=Lax does not stop a POST
+// from a sibling *.d-ma.be origin, so the router itself must refuse a non-safe request
+// whose Origin or Sec-Fetch-Site says it did not come from this site's own pages.
+
+import (
+	"context"
+	"net/http"
+	"net/http/httptest"
+	"net/url"
+	"strings"
+	"testing"
+
+	"github.com/stretchr/testify/assert"
+	"github.com/stretchr/testify/require"
+)
+
+// foreign is a header set a browser sends for a form post made by another page.
+var foreign = map[string]map[string]string{
+	"sibling subdomain, Sec-Fetch-Site": {"Origin": "https://evil.d-ma.be", "Sec-Fetch-Site": "same-site"},
+	"other site, Sec-Fetch-Site":        {"Origin": "https://evil.example", "Sec-Fetch-Site": "cross-site"},
+	"sibling subdomain, Origin only":    {"Origin": "https://evil.d-ma.be"},
+	"opaque origin":                     {"Origin": "null"},
+}
+
+// own is a header set for the app's own pages (or a non-browser client): must pass.
+var own = map[string]map[string]string{
+	"same-origin Sec-Fetch-Site": {"Sec-Fetch-Site": "same-origin", "Origin": "http://example.com"},
+	"matching Origin only":       {"Origin": "http://example.com"},
+	"no browser headers":         {},
+}
+
+func withHeaders(req *http.Request, h map[string]string) *http.Request {
+	for k, v := range h {
+		req.Header.Set(k, v)
+	}
+	return req
+}
+
+func userCount(t *testing.T) int {
+	t.Helper()
+	var n int
+	require.NoError(t, rawPool(t).QueryRow(context.Background(), `SELECT count(*) FROM users WHERE id = $1`, userID).Scan(&n))
+	return n
+}
+
+func TestCrossOrigin_ARefusedDeleteAccountPostLeavesTheAccountInPlace(t *testing.T) {
+	for name, h := range foreign {
+		t.Run(name, func(t *testing.T) {
+			app, _ := newAccountApp(t)
+			resetDB(t, rawPool(t))
+			seedConnection(t, app, "youtube", "ada@channel", "ref")
+
+			rec := do(t, app, withHeaders(httptest.NewRequest(http.MethodPost, "/account/delete", nil), h))
+
+			assert.Equal(t, http.StatusForbidden, rec.Code)
+			assert.Equal(t, 1, userCount(t), "the account must survive a refused post")
+		})
+	}
+}
+
+func TestCrossOrigin_ASameOriginOrHeaderlessDeleteAccountPostIsServed(t *testing.T) {
+	for name, h := range own {
+		t.Run(name, func(t *testing.T) {
+			app, _ := newAccountApp(t)
+			resetDB(t, rawPool(t))
+			seedConnection(t, app, "youtube", "ada@channel", "ref")
+
+			rec := do(t, app, withHeaders(httptest.NewRequest(http.MethodPost, "/account/delete", nil), h))
+
+			assert.Equal(t, http.StatusSeeOther, rec.Code)
+			assert.Equal(t, "/auth/logout", rec.Header().Get("Location"))
+		})
+	}
+}
+
+func TestCrossOrigin_ARefusedUploadPostSubmitsNoJob(t *testing.T) {
+	for name, h := range foreign {
+		t.Run(name, func(t *testing.T) {
+			app, sub := newUploadApp(t, audioOK, 200<<20)
+
+			rec := do(t, app, withHeaders(uploadReq(t, "m", "m.wav", []byte("RIFF....WAVE")), h))
+
+			assert.Equal(t, http.StatusForbidden, rec.Code)
+			assert.Empty(t, sub.jobs, "a refused post must not enqueue transcription")
+		})
+	}
+}
+
+func TestCrossOrigin_ARefusedUploadChatPostCallsNoModel(t *testing.T) {
+	for name, h := range foreign {
+		t.Run(name, func(t *testing.T) {
+			app, fc := newUploadChatApp(t)
+			id := seedUpload(t, userID, "Roadmap sync", "done", meetingText)
+
+			req := chatPost("/uploads/"+id+"/chat", url.Values{"message": {"hej"}})
+			rec := do(t, app, withHeaders(req, h))
+
+			assert.Equal(t, http.StatusForbidden, rec.Code)
+			assert.Zero(t, fc.callCount)
+		})
+	}
+}
+
+func TestCrossOrigin_AForeignPostIsRefusedOnEachListedStateChangingPath(t *testing.T) {
+	routes := []string{
+		"/account/disconnect/youtube",
+		"/account/summarize-mode",
+		"/register",
+		"/paste",
+		"/v/abc/action",
+		"/v/abc/summarize",
+		"/v/abc/retry-now",
+		"/v/abc/chat",
+	}
+	for _, path := range routes {
+		t.Run(path, func(t *testing.T) {
+			app := newApp(t)
+			req := httptest.NewRequest(http.MethodPost, path, strings.NewReader(""))
+			req.Header.Set("Content-Type", "application/x-www-form-urlencoded")
+			rec := do(t, app, withHeaders(req, foreign["sibling subdomain, Sec-Fetch-Site"]))
+			assert.Equal(t, http.StatusForbidden, rec.Code)
+		})
+	}
+}
+
+// A login redirect comes back to /auth/callback as a cross-site GET navigation, and
+// health probes carry no headers: safe methods must never be refused on origin grounds.
+func TestCrossOrigin_ACrossSiteGETIsNotRefused(t *testing.T) {
+	app := newApp(t)
+	for _, path := range []string{"/healthz", "/welcome"} {
+		req := httptest.NewRequest(http.MethodGet, path, nil)
+		req.Header.Set("Sec-Fetch-Site", "cross-site")
+		assert.Equal(t, http.StatusOK, do(t, app, req).Code, path)
+	}
+}

internal/web/handlers.go

@@ -229,7 +229,12 @@ func (a *App) Router() http.Handler {
 	// resolved user_id. /register lives inside the auth guard but is exempt from
 	// the registration gate (you must be able to reach it before you have a user).
 	root.Handle("/", a.Auth.Middleware(a.registrationGate(app)))
-	return root
+
+	// The session cookie is SameSite=Lax, which still travels on a POST made from a
+	// sibling *.d-ma.be page (same site, different origin). Refuse any non-safe request
+	// whose Origin or Sec-Fetch-Site says it did not come from this origin (#48). It wraps
+	// everything, so a route added later is covered without remembering to ask.
+	return http.NewCrossOriginProtection().Handler(root)
 }
 
 // handleWelcome renders the public landing page (/welcome). It is mounted outside

test/lintgate/lintgate_test.go

@@ -0,0 +1,143 @@
+package lintgate
+
+// Observes the exit status of `task lint` (the lint step of `task check`), not the lint
+// rules themselves. It runs the repo's real Taskfile in a scratch module so a change to the
+// lint command that stops it failing on findings (#41) turns this red.
+
+import (
+	"bytes"
+	"errors"
+	"os"
+	"os/exec"
+	"path/filepath"
+	"regexp"
+	"strings"
+	"testing"
+)
+
+const scratchWithFinding = `package main
+
+import "os"
+
+func main() { os.Remove("x") }
+`
+
+func scratchModule(t *testing.T) string {
+	t.Helper()
+	taskfile, err := os.ReadFile(filepath.Join("..", "..", "Taskfile.yml"))
+	if err != nil {
+		t.Fatalf("read Taskfile.yml: %v", err)
+	}
+	dir := t.TempDir()
+	for name, body := range map[string]string{
+		"Taskfile.yml": string(taskfile),
+		"go.mod":       "module scratch\n\ngo 1.21\n",
+		"main.go":      scratchWithFinding,
+	} {
+		if err := os.WriteFile(filepath.Join(dir, name), []byte(body), 0o644); err != nil {
+			t.Fatalf("write %s: %v", name, err)
+		}
+	}
+	return dir
+}
+
+// ansi matches the colour escape sequences task prints when it thinks it has a terminal.
+var ansi = regexp.MustCompile("\x1b\\[[0-9;]*m")
+
+// hasSkipNotice reports whether the skip notice was printed as output. Task echoes the command
+// line first, and that line contains the same words, so a substring match would be vacuous.
+func hasSkipNotice(out string) bool {
+	for _, line := range strings.Split(ansi.ReplaceAllString(out, ""), "\n") {
+		if strings.HasPrefix(line, "golangci-lint not installed") {
+			return true
+		}
+	}
+	return false
+}
+
+// runLint runs `task lint` in dir with the given PATH and returns its combined output and exit code.
+func runLint(t *testing.T, dir, path string) (string, int) {
+	t.Helper()
+	return runTask(t, dir, path, "lint")
+}
+
+func runTask(t *testing.T, dir, path string, args ...string) (string, int) {
+	t.Helper()
+	taskBin, err := exec.LookPath("task")
+	if err != nil {
+		t.Skip("task not installed")
+	}
+	cmd := exec.Command(taskBin, args...)
+	cmd.Dir = dir
+	cmd.Env = append(os.Environ(), "PATH="+path)
+	var out bytes.Buffer
+	cmd.Stdout, cmd.Stderr = &out, &out
+	err = cmd.Run()
+	var exitErr *exec.ExitError
+	switch {
+	case err == nil:
+		return out.String(), 0
+	case errors.As(err, &exitErr):
+		return out.String(), exitErr.ExitCode()
+	default:
+		t.Fatalf("run task lint: %v", err)
+		return "", -1
+	}
+}
+
+func TestTaskLint_ExitsNonZeroWhenGolangciLintReportsAFinding(t *testing.T) {
+	if _, err := exec.LookPath("golangci-lint"); err != nil {
+		t.Skip("golangci-lint not installed")
+	}
+	out, code := runLint(t, scratchModule(t), os.Getenv("PATH"))
+	if code == 0 {
+		t.Fatalf("task lint exited 0 on a module with an unchecked error; output:\n%s", out)
+	}
+	if hasSkipNotice(out) {
+		t.Fatalf("task lint blamed a missing binary for a lint failure; output:\n%s", out)
+	}
+	if !strings.Contains(out, "errcheck") {
+		t.Fatalf("a non-zero exit without the finding means the linter crashed, not that it found something; output:\n%s", out)
+	}
+}
+
+// The lint step only gates anything if `task check` runs it.
+func TestTaskCheck_RunsTheLintStep(t *testing.T) {
+	out, code := runTask(t, scratchModule(t), os.Getenv("PATH"), "--dry", "check")
+	if code != 0 {
+		t.Fatalf("task --dry check exited %d; output:\n%s", code, out)
+	}
+	if !strings.Contains(out, "task: [lint]") {
+		t.Fatalf("task check no longer runs the lint step; output:\n%s", out)
+	}
+}
+
+func TestTaskLint_SkipsWithANoticeWhenGolangciLintIsAbsent(t *testing.T) {
+	taskBin, err := exec.LookPath("task")
+	if err != nil {
+		t.Skip("task not installed")
+	}
+	bin := t.TempDir() // a PATH holding task and nothing else
+	if err := os.Symlink(taskBin, filepath.Join(bin, "task")); err != nil {
+		t.Fatalf("symlink task: %v", err)
+	}
+	out, code := runLint(t, scratchModule(t), bin)
+	if code != 0 {
+		t.Fatalf("task lint exited %d without golangci-lint on PATH; output:\n%s", code, out)
+	}
+	if !hasSkipNotice(out) {
+		t.Fatalf("expected the skip notice; output:\n%s", out)
+	}
+}
+
+// CI runs task with colour on, so the notice line starts with an escape sequence; a bare
+// prefix match missed it there while passing on a terminal-less local run.
+func TestHasSkipNotice_SeesTheNoticeBehindColourCodes(t *testing.T) {
+	out := "\x1b[32mtask: [lint] ...\n\x1b[0mgolangci-lint not installed — skipping (CI installs it)\n"
+	if !hasSkipNotice(out) {
+		t.Fatalf("notice not found in coloured output: %q", out)
+	}
+	if hasSkipNotice("\x1b[32mtask: [lint] if command -v golangci-lint ...; echo \"golangci-lint not installed\"\n") {
+		t.Fatal("the echoed command line must not count as the notice")
+	}
+}