* feat(tracker): GitHub issue intake observer
Adds an opt-in daemon poll loop that spawns one worker session per
eligible open GitHub issue, keyed by the canonical "github:<native>"
id so restarts cannot double-spawn. Eligibility requires an explicit
label or assignee rule to avoid draining an entire backlog.
Provider dispatch goes through a TrackerResolver interface
(SingleTrackerResolver for now) so Linear/Jira can be added later as
new adapters plus a resolver-map entry, without touching the poll,
eligibility, or backoff logic. Reuses the existing rate-limit-aware
GitHub tracker adapter and backs off per-project on any poll failure
(including rate limits) instead of retrying in a tight loop.
Closes#2324.
* feat(frontend): surface GitHub tracker intake in project settings
Adds a Tracker Intake card to project settings (enable, repository
override, labels, assignee) with inline validation requiring at
least one label or assignee before intake can be saved. Session
cards and the inspector show the canonical "github:<native>" issue
id when a session was spawned by intake.
Regenerated frontend/src/api/schema.ts against the backend's
TrackerIntakeConfig. The provider is currently fixed to "github";
adding a picker for future providers is additive once the backend
enum grows.
Closes#2324.
* fix(tracker): start the intake observer unconditionally at boot
startTrackerIntake scanned projects once at daemon startup and skipped
starting the observer loop entirely when none had intake enabled yet.
Poll() already re-reads every project's config on each tick and skips
disabled projects there, so the boot-time gate only broke the common
case: enabling intake on a project after the daemon is already running
silently never got picked up until the next restart, with no error or
log line to explain why.
Always start the loop; the adapter (and its token resolution) stays
lazy regardless, so there's no added cost when intake is unused.
Found while manually verifying issue intake end-to-end against a live
dev daemon: enabled intake via the settings UI, saved successfully,
but no session ever spawned for a matching labeled issue.
* fix(frontend): show auto-detected repo link, hide labels input for now
The Electron app only registers git projects today, so the daemon
always has a usable git origin to derive owner/repo from when
trackerIntake.repo is unset (trackerRepo() in observer.go, already
covered by every Poll-level test in observer_test.go). Replace the
manual Repository input with a read-only link derived client-side
from the project's own git origin, purely for display — the daemon's
own derivation at poll time is unaffected either way.
Comment out the Labels input; Assignee is the only intake eligibility
rule editable from this form for now. form.intakeLabels/intakeRepo
stay wired into buildIntake so a value set via the CLI round-trips
on a UI save instead of being silently cleared.
* chore: format with prettier [skip ci]
* feat(frontend): offer issue intake at project creation
Add the GitHub tracker intake controls to the create-project sheet so a
project can opt into issue-driven worker spawning at creation time, not
only later via Settings.
- Extract the shared IntakeFields component (enable toggle, assignee
input, validation, credential hint) plus buildIntake/intakeNeedsRule/
deriveGitHubRepo helpers into IntakeFields.tsx, and consume it from
ProjectSettingsForm so the two surfaces can't drift.
- CreateProjectAgentSheet renders IntakeFields (no repo-preview row,
since the git origin isn't known there; the daemon derives the repo).
The selection now carries an optional trackerIntake payload, gated by
the same "requires a label or assignee" rule the backend enforces.
- Thread trackerIntake through Sidebar's onCreateProject into the
POST /api/v1/projects config. No backend change: the endpoint already
accepts a full ProjectConfig and the intake observer picks up newly
enabled projects on its next tick.
Verified in the web preview: enabling reveals the assignee field and
gates submit until a rule is set; submit builds the intake payload.
* chore: format with prettier [skip ci]
* feat(frontend): simplify intake controls in the create-project sheet
Reduce the create sheet's tracker-intake block to the essentials: the
enable toggle plus an info icon whose hover tooltip explains what
enabling does, then the assignee input. Drop the descriptive intro
paragraph, the inline "requires a label or assignee" guard text, and
the credential hint — the sheet stays minimal and submit gating already
communicates the missing rule via the disabled button.
- IntakeFields gains a `compact` prop: hides the prose, folds the
explanation into an Info tooltip, and drops the trailing help text.
The tooltip is wrapped in its own TooltipProvider so the component is
self-contained regardless of ancestor. The verbose settings card is
unchanged (renders without `compact`).
- Assignee placeholder reworded to "type username or * for any".
Verified in the web preview: the info tooltip surfaces the one-line
description on hover, the assignee placeholder is updated, and no other
copy remains in the create sheet.
* perf(tracker): cache GitHub issue lists with ETag conditional requests
The intake observer polls Tracker.List for the same repo+filter every
tick, and each poll did an uncached GET + full JSON decode even when
nothing changed. Add HTTP conditional requests so unchanged polls are
cheap and don't consume the primary rate limit.
- Tracker holds a per-request-path cache of {etag, mapped issues},
guarded by a mutex. The key space is bounded by intake-enabled
repo/filter pairs, so no eviction is needed.
- List sends If-None-Match with the cached ETag (verbatim, preserving
weak validators). On 304 it returns the cached issues without
re-decoding (GitHub 304s don't count against the primary rate limit);
a rotated ETag on the 304 is recorded. On 200 it stores the new
{etag, issues}, or drops a stale entry if the response omits an ETag.
A 304 without a prior validator falls back to an unconditional refetch.
- Extract the HTTP round-trip into roundTrip(); do() delegates to it so
Get and Preflight keep byte-for-byte identical behavior. roundTrip
owns If-None-Match, ETag capture, and 304 handling before
classifyError.
Tests cover revalidation returning cached issues on 304, ETag rotation
on change, separate cache keys per filter, and no caching when the
response carries no ETag.
* feat(frontend): trim tracker intake copy in project settings
Reduce the settings Tracker Intake card to a one-line description
("Auto-spawn worker sessions from matching tracker issues.") and drop
the trailing credential/daemon-restart hint. The compact create sheet is
unaffected (it already renders neither).
* feat(tracker): scope v1 intake to assignee-only
Per PR review, labels were a persisted/API/CLI eligibility rule while the
UI only ever exposed assignee — surface beyond the intended v1 scope.
Remove labels from intake end-to-end; assignee becomes the required and
only eligibility rule.
- domain: drop TrackerIntakeConfig.Labels; Validate() now requires a
non-empty assignee when enabled (was "labels or assignee").
- observer: pass only State+Assignee into ListFilter; drop the label
match loop in issueMatchesConfig.
- CLI: remove --tracker-label and its plumbing.
- Regenerate openapi.yaml + schema.ts (labels gone from the schema).
- frontend: drop labels from IntakeForm/buildIntake/intakeNeedsRule and
the settings form state; validation copy now "requires an assignee".
Remove the label round-trip test; keep assignee coverage.
The generic domain.ListFilter.Labels adapter capability is retained;
only intake stops using it.
* fix(tracker): paginate GitHub issue listing with page-aware ETag cache
Per PR review, single-page listing is a correctness bug for intake, not
just a bounded v1 tradeoff: with more than a page of eligible open
issues, AO re-sees the same first page every poll, the persisted
issue_id dedupe skips the already-spawned first-page issues, and later
pages are never fetched or spawned.
- List now requests per_page=100 and follows the GitHub Link header
rel="next" until no next link remains, accumulating issues across all
pages. A maxListPages guard fails loud on a pathological Link cycle.
- The ETag cache is page-aware: each entry stores {etag, issues,
nextPath} keyed by the per-page request path, so a 304 Not Modified
still continues to the cached next page. roundTrip now surfaces the
parsed next path alongside the ETag; do() delegates unchanged so
Get/Preflight keep identical behavior.
- ListFilter.Limit becomes an optional total-result cap (page size is
fixed at the provider max).
Tests cover multi-page accumulation, all-304 revalidation continuing the
cached chain, page-count shrink orphaning a stale entry, and Link
header parsing.
* style(session_manager): gofmt manager_test.go to unblock CI
The session-restart test carried a struct-literal alignment that gofmt
(and golangci-lint's goimports) reject, failing the build-test and lint
jobs. Whitespace-only reformat; no test logic changes.
---------
Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
Co-authored-by: whoisasx <adil.business4064@gmail.com>
* fix(daemon): do not tear down live sessions on shutdown; adopt them on boot
Remove SaveAndTeardownAll from the graceful shutdown path. Live tmux/ConPTY
sessions survive daemon exit; Reconcile on the next boot adopts them via
reconcileLive, preserving session IDs and preventing the id-increment bug.
Add runShutdownSessionLifecycle as a testable seam and narrow the
sessionLifecycle interface to Reconcile+RestoreAll only.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
* fix(daemon): make shutdown-teardown regression test falsifiable
Re-add SaveAndTeardownAll to the sessionLifecycle interface and to
fakeSessionLifecycle so TestShutdown_DoesNotCallSaveAndTeardownAll is
genuinely falsifiable: the flag flips if runShutdownSessionLifecycle
ever calls sl.SaveAndTeardownAll, making the assertion meaningful.
Name the sl parameter (was discarded with _) so the seam is visible.
RED: with a temporary sl.SaveAndTeardownAll call, test fails.
GREEN: without it, test passes. go test ./internal/daemon/... -race: 23/23.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
* refactor(daemon): guard shutdown-teardown at compile time via narrowed interface
Remove SaveAndTeardownAll from sessionLifecycle so daemon.Run physically
cannot call teardown on shutdown. Delete the no-op runShutdownSessionLifecycle
seam and its test. The narrowed interface is the guard: re-introducing teardown
requires a visible, reviewable interface change.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
* fix(session): make ensure-orchestrator idempotent so POST cannot mint a duplicate
When clean=false, SpawnOrchestrator now checks for an existing active orchestrator
and returns it directly instead of always calling Spawn. Adds RED/GREEN tests.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
* test(session): drop redundant NoCleanSkipsKills, covered by SpawnsWhenNoneExists
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
* feat(daemon): supervisor watchdog
Adds backend/internal/daemon/supervisor: a transport-agnostic watchdog
that fires onLastClientGone() exactly once when the live connection count
drops to zero and stays zero for a configurable grace period. Arms only
after the first accepted connection (headless safety: CLI ao start never
self-stops). Reconnect before grace elapses cancels the pending timer.
Mutex guards liveCount/armed/pendingTimer; sync.Once guards the callback.
Tests use net.Pipe + a fake listener (no OS sockets); all three behavior
contracts verified with -race: never fires pre-connect, fires once on
last disconnect, reconnect within grace cancels and re-arms correctly.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
* fix(daemon): supervisor watchdog review fixes (data race, ErrClosed, leak, cleanup)
- Fix data race: capture liveCount into local inside lock before logging
- Replace io.EOF with errors.Is(err, net.ErrClosed) for correct production behavior; update fakeListener to match
- Fix goroutine leak: derive cancellable child context in Serve so watcher always unblocks on return
- Simplify makePipe: drop dead error return, update 3 call sites
- Remove dead defensive pendingTimer nil-check in armGrace
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
* feat(daemon): OS-native supervisor listener triggers clean shutdown
Creates platform-split Listen() in supervisor package (Unix UDS sibling
of run-file; Windows named pipe via go-winio). Wires it into daemon.Run
before srv.Run: listener failure is non-fatal so headless ao-start works.
Adds RequestShutdown() on Server and three unit tests for listen_unix.go.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
* fix(daemon): log supervisor Serve error instead of discarding it
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
* feat(desktop): supervisor link; daemon self-stops (clean) on frontend exit
Add connectSupervisor() in frontend/src/main/supervisor-link.ts: holds one
client connection to the daemon's OS-native supervisor socket (Unix domain
socket on macOS/Linux, named pipe on Windows). Retries with bounded backoff
until the daemon is up; reconnects automatically on drop.
In main.ts, connect the link from reportBoundPort (once per daemon ready
transition). Remove the quit-time daemon teardown: the before-quit handler
now only disposes the browser view. The process.on("exit") killDaemon call
is also removed. When Electron exits for any reason the OS closes the fd,
the daemon detects EOF, and self-stops after its 5s grace period. tmux and
ConPTY sessions survive and are adopted on the next boot.
killDaemon and stopDaemon are kept for the explicit user-stop path
(ipcMain.handle("daemon:stop", ...)).
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
* fix(desktop): guard against daemon orphan when supervisor link is down; tidy test setup
Expose a live `connected` getter on SupervisorLinkHandle and add a
last-resort process.on("exit") kill that fires only when the link is
not actually connected (UDS never bound or addr was null), preventing
orphan daemons while keeping the OS-fd teardown path for the normal
case. Log a warning when addr is null so the skip is diagnosable.
Invert the setup.ts guard to the natural form, dropping the empty
if/else skeleton.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
* fix(core): restore promptless sessions in place (reboot recovery, no increment)
Drop the empty-prompt early return in restoreArgv that returned ErrNotResumable
when the adapter could not resume and no prompt was saved. Now control falls
through to GetLaunchCommand unconditionally: a saved prompt is replayed, an
empty prompt (orchestrator) launches fresh with the system prompt only, same id,
same workspace. Removes the only producer of ErrNotResumable and deletes the
now-dead sentinel, its service mapping, and the corresponding tests.
Frontend reference to SESSION_NOT_RESUMABLE in TerminalPane.tsx is left intact
(the handler becomes harmlessly dead; the API simply stops returning that code).
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
* test(integration): dead-live session is restored, not abandoned, after reconcile
Task 5 made promptless sessions relaunch fresh instead of hitting ErrNotResumable.
The reconcile crash-recovery path (documented in reconcileLive) terminates a
dead-live session then RestoreAll relaunches it on the same boot. This test
asserted the old promptless-stays-terminated artifact; update it to the intended
restored end state (live again, same id, one fresh runtime Create).
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
* style(session): replace em dashes in service.go messages and comment
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
* docs(desktop): scope supervisor link to spawn path; dispose link on explicit stop
Document that the liveness link is established only when the app spawned the
daemon: the attach path intentionally does not link, to keep an `ao start`
daemon persistent (headless safety). Also dispose the link on an explicit
daemon:stop so its reconnect loop does not retry a deliberately-stopped daemon.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
* chore: format with prettier [skip ci]
* docs: add daemon-lifecycle adopt-on-shutdown implementation plan
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
* chore: format with prettier [skip ci]
* fix(daemon): keep supervisor watchdog alive across transient Accept errors
Review of #2185: Serve previously returned on the first unexpected Accept error,
silently disabling the watchdog (the 'restart is caller's job' comment described
a contract the caller never fulfilled). Back off and keep accepting instead, so
a transient error (e.g. EMFILE) cannot leave the daemon unable to self-stop on
frontend death. Also drop the stale Task 3/4 planning comment.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
* fix(core): leave promptless workers terminated on restore (orchestrators still relaunch fresh)
A promptless, unresumable KindWorker session had no prompt to replay and
no native session id to resume from. Blank-relaunching it via GetLaunchCommand
would silently drop its task. restoreArgv now returns ErrNotResumable for this
case, gated on (meta.Prompt == "" && kind != domain.KindOrchestrator). Orchestrators
are promptless by design and continue to relaunch fresh with the system prompt only.
Re-introduces ErrNotResumable sentinel and its Conflict API mapping.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
* fix(desktop): re-link supervisor on attach for app-owned daemons (close lingering-daemon gap)
- runfile.Info gets Owner field (omitempty): "app" when Electron spawned,
empty for headless `ao start`. server.go reads AO_OWNER env to set it.
- daemonEnv() injects AO_OWNER=app so spawned daemons self-identify.
- Extracted establishSupervisorLink() from inline reportBoundPort code.
Spawn path calls it unconditionally; attach paths call it only when
shouldLinkOnAttach(owner) is true (owner === "app").
- Both attach paths (inspectExistingDaemon, resolveDaemonFromPort) now
read the owner from the run-file and re-link when app-owned, preventing
a lingering app-spawned daemon from self-stopping mid-session.
- Headless ao start daemons stay unlinked: persistent across app quit.
- New daemon-owner.ts + daemon-owner.test.ts (4 vitest cases, all pass).
- Go: 9 tests pass with -race; vet clean.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
* fix: quiet expected ErrNotResumable log in RestoreAll; note attach TOCTOU
Review polish on #2185: a promptless worker left terminated on boot is expected,
not an operational error, so log it at Warn not Error. Document the narrow
run-file re-read TOCTOU on the port-attach re-link path (worst case is linking a
headless daemon; the dispose-idempotency guard prevents any leak).
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
* style: gofmt the review-fix files (CI format/lint check)
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
---------
Co-authored-by: Claude Sonnet 4.6 <noreply@anthropic.com>
Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
* Zellij to Tmux and some other fixes. (#404)
* feat(runtime): add tmux adapter package
Adds backend/internal/adapters/runtime/tmux implementing ports.Runtime via
the tmux CLI. Drop-in replacement for the zellij adapter on Darwin/Linux.
Key design points:
- Handle is a plain session id string (no pane-id split needed for tmux).
- Exact-match session targeting via = prefix for kill-session and has-session.
- Keep-alive shell appended to launch command so sessions survive agent exit.
- send-keys -l chunked for literal text delivery (no key-name interpretation).
- IsAlive distinguishes definitive-dead (missing/no-server output) from probe
errors so the reaper never kills a session on a transient tmux failure.
- 34 tests pass: 32 unit tests via fakeRunner seam, 2 integration tests on
real tmux 3.6b (TestRuntimeIntegration, TestRuntimeIntegrationExactSessionParsing).
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
* fix(tmux): address four code-review findings in tmux runtime adapter
- Remove em dash from tmux_test.go:462 (project hard rule); replace with semicolon
- Derive integration test session IDs from t.Name() so concurrent runs do not collide on the same tmux session
- Remove dead scaffolding variables (r/fr, r2/fr2) in TestCreateDestroysAndReturnsErrorWhenNotAlive
- Quote \${SHELL:-/bin/sh} in buildLaunchCommand and update all asserting tests
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
* feat(runtime): wire tmux on Darwin/Linux via runtimeselect, keep zellij on Windows
- New package runtimeselect: Runtime union interface (ports.Runtime +
SendMessage/GetOutput/AttachCommand) with compile-time assertions for
both adapters. New(log) returns tmux on non-Windows, zellij on Windows
(replicating the old daemon socket-dir setup).
- daemon.go: replace zellij-specific socket-dir block with
runtimeselect.New(log); update comment to be runtime-neutral.
- lifecycle_wiring.go: startSession param changed from *zellij.Runtime
to runtimeselect.Runtime.
- cli/doctor.go: runtime-aware checkTerminalRuntime (tmux on Darwin/Linux,
zellij on Windows); added checkTmux.
- cli/spawn.go: attach hint prints tmux attach -t <name> on non-Windows,
keeps zellij attach hint on Windows.
- wiring_test.go: startSession test uses runtimeselect.New(nil); zellij
direct tests retained for zellij-specific coverage.
- doctor_test.go: replaced three zellij tool tests with tmux equivalents.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
* chore: tidy runtime-neutral comments and doctor import grouping
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
* refactor(tmux): drop unused runner.Start seam
tmux creates sessions detached via new-session -d, so the Start method
(carried over from the zellij runner shape, where it backs the Windows
fire-and-forget spawn) is never called. Remove it from the interface and
its implementations to shrink the seam.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
* feat(conpty): add protocol codec and output ring buffer (pure Go, OS-agnostic)
Ports the ConPTY named-pipe binary framing protocol and rolling output
buffer from pty-host.ts to Go. Implements EncodeMessage, MessageParser
(handles arbitrary chunk boundaries, payload copy guarantee), and Ring
(MaxOutputLines=1000, ANSI-safe, concurrent Append+Snapshot). All 15
unit tests pass on Darwin; GOOS=windows build is also clean.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
* test(conpty): harden copy-safety and add concurrent ring test
Strengthen TestParserPayloadIsCopy to catch internal-buffer aliasing:
feed frame1, capture its payload, feed frame2 of the same length so the
parser's buffer overwrites the frame1 region, then assert frame1's bytes
are unchanged. The prior test only mutated the input slice post-Feed and
did not exercise the real aliasing risk.
Add TestRingConcurrent: 10 writer goroutines (Append) and 10 reader
goroutines (Snapshot + Tail) running concurrently with a WaitGroup. The
test is meaningful only under the race detector and catches any missing
mu coverage on Ring's exported methods.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
* feat(ptyregistry): port Windows pty-host sideband registry to Go
Adds package ptyregistry under backend/internal/adapters/runtime/conpty/ptyregistry.
Ports windows-pty-registry.ts: defensive read, atomic temp+rename write,
delete-on-empty, register-replaces-same-ID, and auto-pruning List.
PID liveness isolated behind build tags (syscall.Kill on Unix,
OpenProcess on Windows). 10 tests all green on Darwin.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
* chore(sdd): phase B briefs and progress for B1-B3
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
* feat(conpty): add pty-host serve engine with loopback TCP transport (B3)
Ports pty-host.ts behavior to Go: ptyConn interface seam, Serve engine
with ring replay, fan-out broadcast, MSG_* handlers, PTY-exit keep-alive,
and graceful shutdown (ConPTY dispose first, 50ms grace, then clients and
listener). Real conptyConn is Windows-only via build tag; non-Windows stub
keeps the package importable on Darwin/Linux. Tests use a fake ptyConn
with real loopback sockets and the B1 MessageParser, passing with -race.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
* fix(conpty): deliver scrollback snapshot and register client atomically
Review of Task B3 found one Important bug and two minors.
Important: in handleConn the ring Snapshot and the client registration
ran under two separate h.mu acquisitions. A PTY chunk arriving in that
gap was in neither the snapshot nor that client's broadcast, so it was
silently dropped (a hole in the client's stream). Now take the snapshot,
write it to the conn, and add the conn to the clients set all under a
single h.mu hold; broadcast also takes h.mu so it cannot interleave.
Added TestScrollbackLiveOrdering_NoDrop, which emits a contiguous
numbered stream while a client connects and asserts the client's stream
has no internal gap. It reliably fails against the old two-step code and
passes under -race -count=20.
Minor (faithfulness): conptyConn.Close() now also best-effort
Process.Kill() (nil-guarded) so a child that ignores ConPTY EOF still
exits and Done() fires, mirroring pty.kill() in pty-host.ts.
Minor (simplify): use os.Environ() instead of
exec.Command(shellCmd).Environ() for the child env.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
* chore(sdd): B4 brief
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
* feat(conpty): add runtime adapter with loopback pty-client and session management (B4)
Implements the conpty Runtime adapter: injectable spawn seam, loopback
TCP client helpers (SendMessage/GetOutput/IsAlive/Kill), and Runtime
methods (Create/Destroy/IsAlive/SendMessage/GetOutput). Session resolution
uses an in-memory map with B2 registry fallback for daemon-restart
recovery. Windows-only detached spawn in spawn_windows.go; stub errors
on other OSes. All adapter methods are unit-tested on Darwin against an
in-process B3 Serve and fakePTY. 48 tests pass, all three GOOS builds
succeed, vet clean.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
* fix(conpty): split IsAlive dead-vs-transient for reaper safety
clientIsAlive collapsed every probe failure (dial timeout, read-deadline
expiry, write error, connection-refused) to false, which the reaper turns
into ProbeDead and the LCM can promote to a permanent reap. A single
transient 2s loopback timeout would spuriously kill a live idle session.
Now clientIsAlive returns (alive bool, transientErr error): a refused dial
is definitively gone (false, nil); a timeout or any connected-then-failed
I/O error is transient (false, err) so the reaper records ProbeFailed and
retries. Wire IsAlive to propagate it. Add regression test covering both
the refused-is-gone and timeout-is-transient paths.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
* chore(sdd): B5 brief + ledger
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
* feat(terminal): stream-based Attach for tmux/zellij/conpty
Evolve the terminal layer from argv-based attach (PTYSource.AttachCommand
+ injected spawnFunc) to stream-based attach (Source embedding
ports.Attacher). tmux/zellij keep spawning their attach CLI on a local
PTY via the new shared ptyexec.Spawn; conpty attaches by dialing its
loopback pty-host directly with a loopbackStream over the B1 framing
protocol. Reattach/backoff/size/SIGWINCH/detach semantics are unchanged.
- ports: add Stream + Attacher.
- ptyexec: new shared package holding the creack/pty (unix) and ConPTY
(windows) spawn, moved verbatim from terminal with its tests.
- terminal: PTYSource -> Source, drop spawnFunc/WithSpawn, run loop calls
src.Attach and uses ports.Stream.
- tmux/zellij: add Attach (argv via ptyexec.Spawn); conpty: add Attach
(loopbackStream); ports.Attacher assertions on all three.
- runtimeselect: union embeds ports.Attacher in place of AttachCommand.
- tests migrated; new conpty attach_test against in-process Serve+fakePTY.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
* style(ptyexec): replace em dashes carried from moved pty files
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
* chore(sdd): B6 brief + B5 ledger
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
* feat(runtime): select conpty on Windows, register pty-host subcommand, delete zellij
- runtimeselect.New: Windows branch now returns conpty.New(conpty.Options{}) instead
of zellij; compile-time assertion updated to conpty.Runtime.
- cli/ptyhost.go: new hidden "ao pty-host" subcommand (DisableFlagParsing so agent
shell args with leading dashes survive); calls conpty.RunHost and exits with its code.
- cli/root.go: wires newPtyHostCommand alongside newLaunchCommand.
- cli/doctor.go: Windows terminal-runtime check replaced with a static ConPTY
built-in pass; zellij import and checkZellij function removed.
- cli/spawn.go: Windows attach hint updated to dashboard message (ConPTY has no
CLI attach); zellij import removed.
- daemon/lifecycle_wiring.go: stale zellij comment updated to tmux/conpty.
- daemon/wiring_test.go: zellij import and TestDaemonZellijSocketDir test removed;
TestWiring_StartLifecycleThreadsMessengerIntoLCM now uses tmux.New.
- terminal/attachment_integration_test.go: re-pointed at real tmux
(TestAttachmentStreamsRealTmuxPane + TestAttachmentReattachAdoptsNewSize);
sessions cleaned up in t.Cleanup.
- internal/adapters/runtime/zellij: deleted entirely.
All three GOOS builds pass; go test -race ./... 1607 passed; go vet clean;
grep -rn "runtime/zellij" returns nothing.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
* docs(daemon): correct terminal-runtime comment to conpty on Windows
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
* docs(ptyexec): drop stale zellij reference in Windows spawn comment
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
* chore(sdd): final phase B ledger
* build(desktop): support local keychain signing for macOS builds
Bridge forge.config.ts to accept the local keychain flow (APPLE_SIGNING_IDENTITY
identity + AO_NOTARY_PROFILE notarytool profile) in addition to the existing CI
secrets path (CSC_LINK + APPLE_ID/app-specific-password). Enables a signed +
notarized macOS build from a developer Mac without exporting a .p12 or the Apple
ID app-specific password.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
* fix(daemon): default TERM so Finder-launched tmux attach works
A Finder/Dock launch starts the supervisor under launchd with no
controlling tty, so TERM is unset. The daemon inherits that, and its
tmux attach client (spawned with env=nil, inheriting the daemon env)
dies immediately with "open terminal failed: terminal does not support
clear" — the orchestrator terminal pane never opens.
Seed TERM=xterm-256color (what the renderer's xterm.js emulates) as the
base of buildDaemonEnv, the same place PATH is reconstructed for the same
class of "Finder launch lacks a terminal's env" bug. A real TERM from the
shell/process env still wins.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
* docs(lifecycle): plan for save-on-close/restore-on-open sessions
Captures the intended daemon lifecycle: on shutdown save every running
session (worker and orchestrator) plus its gitignore-respecting uncommitted
work to refs/ao/preserved/<id>, then force-remove worktrees; on boot recreate
worktrees, replay the preserved work, and restore all sessions. Reuses
existing SQLite state, session_worktrees.preserved_ref, manager.Restore, and
the /shutdown endpoint (no new file, migration, or route).
Also gitignore the built daemon binary copied into frontend/daemon/.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
* chore(frontend): sync regenerated pnpm-lock and routeTree
Working-tree regeneration of the pnpm lockfile and TanStack Router generated
route tree. No hand edits; generated output only.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
* feat(workspace): add ForceDestroy for shutdown-path worktree removal
Adds ForceDestroy(ctx, info) to ports.Workspace and the gitworktree
adapter. It runs `git worktree remove --force`, then prune, then
os.RemoveAll as a backstop. A new worktreeForceRemoveArgs builder in
commands.go emits --force; the existing worktreeRemoveArgs is untouched
so Destroy still refuses dirty worktrees via ErrWorkspaceDirty.
TDD: test first creates a dirty worktree, confirms Destroy refuses with
ErrWorkspaceDirty, then confirms ForceDestroy succeeds and the path is
gone and deregistered. All 1609 backend tests pass.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
* feat(workspace): add StashUncommitted and ApplyPreserved for session lifecycle
Implements the correctness-critical save-on-close / restore-on-open pair
in the gitworktree adapter:
- StashUncommitted: captures uncommitted work (tracked edits and new
non-ignored files) via a temp GIT_INDEX_FILE into a real commit stored
at refs/ao/preserved/<session-id>. Never touches the real index or
stash stack. Returns empty string for clean worktrees. Logs the count
of .gitignore-skipped paths.
- ApplyPreserved: replays the preserve commit onto a freshly re-added
worktree via "git checkout <SHA> -- .". Deletes the ref on clean
success; keeps it and returns ErrPreservedConflict (wrapped) on
content conflicts.
- Adds both methods to ports.Workspace interface and stubs them in
integration and session_manager test doubles.
TDD: wrote two failing tests first (RED confirmed via build failure on
undefined methods), then implemented to GREEN. All 39 adapter tests pass.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
* fix(workspace): replace path-checkout with cherry-pick in ApplyPreserved
git checkout <sha> -- . is a path-checkout that always exits 0 for
content divergence, making ErrPreservedConflict unreachable. Replace
with git cherry-pick --no-commit which performs a true three-way merge,
leaves textual conflict markers on conflict, and exits non-zero so the
sentinel is correctly returned. Conflict detection now uses exit code
only (locale-independent). Add TestWorkspaceIntegrationApplyPreservedConflict
to assert: error is ErrPreservedConflict, preserve ref is kept, conflict
markers appear in the file. All 40 tests pass.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
* feat(session-manager): add SaveAndTeardownAll and RestoreAll for shutdown lifecycle
Implements Task 3: capture-then-destroy on shutdown and restore-all on startup.
- Adds ErrPreservedConflict to ports as a named sentinel; gitworktree aliases it
(following the same pattern as ErrBranchCheckedOutElsewhere).
- Extends the Store interface with UpsertSessionWorktree and ListSessionWorktrees
so the session manager can write the shutdown-saved marker and read it back.
- SaveAndTeardownAll: for every live session with a workspace path, stash
uncommitted work, write the session_worktrees row (DB commit before worktree
removal, crash-safety invariant), mark terminated, destroy runtime, force-remove
the worktree. Best-effort per session; no kind filter.
- RestoreAll: for every terminated session that has a session_worktrees row (the
marker written by SaveAndTeardownAll), re-create the worktree, apply any
preserved ref (conflict logs and continues), then relaunch via the existing
single-session Restore. Sessions killed by the user before shutdown (no row)
are skipped. Best-effort per session; no kind filter.
- TDD: 9 new tests (RED confirmed via build failure, GREEN confirmed 63 pass).
Full suite: 1621 tests across 77 packages.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
* fix(terminal): enable tmux mouse scroll and fix link clicking
On macOS the runtime is tmux, but two mouse interactions were broken in
the embedded terminal while copy/paste kept working:
- Scroll: the renderer drives scrolling by writing SGR mouse-wheel
reports into the pane (the zellij `--mouse-mode true` model), but tmux
ignores those reports unless mouse mode is on. Create only set `status
off`, never `mouse on`, so wheel scrolling silently no-opped. Enable
`set-option -t <id> mouse on`, mirroring the existing status-off step.
- Link clicking: the default WebLinksAddon handler calls window.open()
with an empty URL and then assigns location.href. Electron's
setWindowOpenHandler denies every window.open and only forwards the URL
passed to it, so the empty open is dropped and clicks no-op. Pass the
matched URL to window.open directly so the main process routes it to
shell.openExternal (the OS browser).
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
* test(session-manager): assert UpsertSessionWorktree precedes ForceDestroy
Add a shared ordered call log (sharedLog *[]string) to both fakeStore
and fakeWorkspace. TestSaveAndTeardownAll_CaptureOrderAndMarker now
wires both fakes to the same slice and asserts upsertIdx < forceIdx,
enforcing the crash-safety invariant that the DB write is committed
before the worktree is force-destroyed.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
* feat(daemon): wire RestoreAll/SaveAndTeardownAll into boot/shutdown sequence
Exposes session manager through a minimal sessionLifecycle interface
(RestoreAll, SaveAndTeardownAll) returned from startSession, then calls
RestoreAll (best-effort) before srv.Run and SaveAndTeardownAll with a
fresh 30s-bounded context after srv.Run returns. Both SIGTERM and POST
/shutdown funnel through srv.Run returning, so the single save call site
covers both paths.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
* test(daemon): fix seam-test tautology and lifecycle variable shadow
Finding 1: dispatch both sessionLifecycle methods through an interface
variable (var sl sessionLifecycle = fake) so the runtime body exercises
interface dispatch, not just direct struct method calls.
Finding 2: rename local variable 'lifecycle' to 'lc' in
TestWiring_StartSessionBuildsSessionService to remove the shadow of the
imported lifecycle package.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
* feat(frontend): call POST /shutdown before killing daemon on quit
In before-quit, POST /shutdown (8s AbortSignal.timeout) so the daemon
saves sessions gracefully before the SIGTERM kill. Adds a re-entrancy
guard (quitting flag) so a concurrent app.quit() cannot double-preventDefault.
Falls back to killDaemon on fetch failure or timeout: quit is never blocked.
Keeps the process.on('exit') SIGTERM fallback intact.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
* fix(storage): guard session_worktrees.state against empty-string CHECK violation; add ponytail comments
The save path (saveAndTeardownOne) never sets domain.SessionWorktreeRecord.State,
so it arrives at UpsertSessionWorktree as "". The generated upsert includes state
in the INSERT column list, so the DB default ('active') is never applied and the
CHECK constraint (state IN ('active', ...)) would fire at the first real shutdown.
Fix: default to 'active' in the store adapter when row.State is "". No schema
change, no migration, no gen edit.
Also add ponytail: comments on the State field (domain type), the write path, and
the read path, documenting that state is unused multi-repo scaffolding and that the
upgrade path is to wire a real value when multi-repo worktree lifecycle states ship.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
* test(storage): add real-SQLite test for empty-State guard in UpsertSessionWorktree
Adds TestUpsertSessionWorktreeEmptyStateDefaultsToActive to the store
test file. It inserts a SessionWorktreeRecord with State at zero value
"" via UpsertSessionWorktree against a real SQLite DB, then reads the
row back and asserts State == "active". This directly exercises the
guard added in the prior commit and would fail if the guard were
removed (the CHECK constraint rejects ""). Mirrors the helpers and
setup pattern of TestSessionWorktreesRoundTrip exactly.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
* fix(comments): correct shutdown-mechanism and task-ref inaccuracies
Fix 1: daemon.go comment near SaveAndTeardownAll now correctly states
that POST /shutdown closes the shutdownRequested channel (not cancel ctx).
Also tighten the RestoreAll comment to remove the inaccurate claim.
Fix 2: remove "Task 2's" phrasing from ForceDestroy ponytail comment in
workspace.go; condition still references StashUncommitted by name.
Fix 3: add note in main.ts that the 8s fetch timeout is shorter than the
daemon's 30s save bound, so a SIGTERM after fetch abort does not cut the
in-flight save short.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
* chore: remove .superpowers workflow scratch from repo
These SDD workflow artifacts (task briefs, agent reports, progress ledger,
review packages) were committed by accident in prior work, against the
.superpowers/sdd/.gitignore intent. Remove them from the repo; they remain
local-only scratch.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
* docs(spec): graceful restore + post-failure orchestrator recreate
Fix the opaque 500 when restoring an un-resumable session (typed 409
SESSION_NOT_RESUMABLE), and add a post-failure popup that offers to recreate a
fresh orchestrator on the same branch (cleaning the worktree, preserving
committed history). Orchestrators only; recreate fires only after a restore
attempt confirms the session cannot be resumed.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
* docs(plan): restore-recreate orchestrator; reuse existing /orchestrators clean=true
Planning discovery: the recreate capability already ships via POST /orchestrators
(clean=true), which kills the dead orchestrator and re-spawns on the canonical
branch (addWorktree reattaches an existing branch). So the feature collapses to a
typed-error fix plus a frontend popup. Spec updated to match.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
* fix(session): return typed SESSION_NOT_RESUMABLE instead of 500 on un-resumable restore
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
* feat(renderer): offer recreate-orchestrator popup when a session cannot be restored
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
* docs(spec): drop stale OpenAPI-regen note (feature adds no route)
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
* fix(ci): gofmt/goimports, golangci-lint hygiene, and Windows-aware doctor tests
Formatting: ran gofmt and goimports (with local-prefixes) on the 8 listed
files plus ptyexec/spawn_unix.go which the linter also flagged.
Lint (25 issues fixed):
- gosec G115: EncodeMessage now returns ([]byte, error) with an explicit
bounds check before the int->uint32 conversion; all callers updated.
- govet nilness: removed dead `if lastErr == nil` branch in clientIsAlive;
lastErr is provably non-nil at that point (real bug).
- nilerr: extracted runAcceptLoop helper so Accept-error-on-close is not
flagged; listener close is normal shutdown, not a caller error.
- staticcheck SA4010: removed dead `full = append(...)` loop in host_test.
- revive var-declaration: `var prev int = -1` -> `prev := -1`.
- revive redefines-builtin-id: deleted local `min` helper; builtin covers it.
- unparam (2): dropped always-nil env return from attachCommand; dropped
unused shellPath param from buildLaunchCommand; updated callers.
- errcheck (8): deferred Close/Remove calls wrapped in func(){_ = ...}();
type assertion in host_main.go uses ok-form; fmt.Fprintf to stdout uses
_, _ = pattern; workspace.go tmpIdx.Close() uses _ =.
- gocritic nestingReduce: inverted if+continue in runtime.go resolve loop.
Windows E2E: skip TestDoctorChecksTmuxVersion,
TestDoctorChecksTmuxVersionFailsOnError, TestDoctorWarnsWhenTmuxMissing on
windows (ao doctor emits a conpty check there, not tmux).
Verified: gofmt -l . clean, golangci-lint 0 issues, go build ok,
go test -race 1624/1624 pass.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
* test(ci): set git identity in worktree clone fixture; loosen tmux reattach timeouts
The preserve round-trip/conflict tests commit inside a worktree of the cloned
repo, which had no git identity; CI runners cannot auto-derive one, failing with
"empty ident name". Set user.email/user.name on the clone in setupOriginClone so
its worktrees inherit it.
The tmux reattach test drives a real shell and parses stty output, which is slow
under -race on CI; raise its echo-write and SIZE-output waits.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
* test(terminal): resend size probe on tmux reattach until the shell answers
Bumping timeouts was the wrong fix: a 30s wait still failed, so the probe output
deterministically never appeared, not slowness. onOpen signals the stream accepts
input, not that the reattached sh -i is at a prompt, so the first echo keystroke
can be dropped. Resend the probe each poll until SIZE output lands, and on timeout
dump the captured pane buffer so a remaining failure is self-explaining.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
* test(terminal): set TERM for real-tmux attach tests so they run in CI
Root cause (from the buffer dump the prior commit added): with TERM unset on CI
runners, tmux refuses to attach a client and prints "open terminal failed:
terminal does not support clear", so the pane never runs the size probe. The
daemon defaults TERM in production; the tests bypass it. Set TERM=xterm-256color
in both real-tmux tests. Reproduced locally with `env -u TERM` (fails the same
way) and verified the fix passes under it.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
* docs(spec): crash-proof session reconcile design
Boot-time reconcile makes live tmux + worktree state match the DB on every
daemon start, so a SIGKILL/crash/force-quit that skips SaveAndTeardownAll no
longer leaks an orphaned daemon, tmux sessions, or worktrees. Adopt
crash-surviving tmux sessions, preserve-and-terminate dead ones, reap
in-namespace orphans, and add a frontend kill+replace branch for a wedged
orphan daemon.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
* docs(spec): simplify reconcile to per-session IsAlive, drop ListSessions
Every leak in the incident maps to a DB row, so orphan-reap is a per-session
IsAlive+Destroy over terminated rows; no runtime enumeration, no ports/conpty/
runtimeselect changes. Reaping a tmux session with no DB row is deferred (YAGNI).
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
* docs(plan): crash-proof session reconcile implementation plan
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
* feat(session): reconcile live pass (adopt alive, stash+terminate dead)
* feat(session): reconcile reap pass and Reconcile entry point
* feat(daemon): run Reconcile on boot in place of bare RestoreAll
* test(integration): reconcile terminates dead-live sessions and reaps leaked tmux
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
* test(integration): correct misleading CreateSession comment in reconcile test
* feat(frontend): kill+replace a wedged orphan daemon on launch
When both inspectExistingDaemon and resolveDaemonFromPort return null but
a process still holds the daemon port (a crashed/orphaned daemon), spawning
a new Go child would collide on the port and exit 1. Detect this case, SIGTERM
the holder (via the run-file PID, falling back to the probe PID), poll until the
port is free (up to 8s), clear the stale run-file, then proceed to spawn fresh.
The healthy-daemon reuse path is unchanged.
Pure helper: src/shared/daemon-takeover.ts (planDaemonTakeover)
Unit tests: src/shared/daemon-takeover.test.ts (3 tests, TDD red-green)
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
* fix(frontend): fire orphan-daemon takeover when a holder actually exists
Replace planDaemonTakeover (inverted logic: ran kill block only when probe
was null) with shouldReplacePortHolder(probe, holderPidAlive) which returns
true when a real holder exists: non-null probe (rejected responder) OR a
run-file PID that is still alive (hung holder). Update main.ts call site to
compute PID liveness before gating the kill block. Update tests to cover all
three distinct outcomes non-vacuously.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
* docs+test: accurate takeover comments, reconcileLive probe-error test, Reconcile doc
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
* fix(session): restore promptless orchestrators and crash-orphaned sessions
The orchestrator was abandoned on every app open: a fresh orchestrator
spawned each launch and the prior conversation appeared lost (it was not;
the transcript stays in ~/.claude, resumable by the deterministic
--session-id AO pins). Two defects combined:
1. Restore's guard rejected any session with no agentSessionId AND no
prompt as ErrNotResumable. But Claude resumes via a deterministic
session id regardless of those fields, so promptless orchestrators
were perfectly resumable yet always rejected. Workers slipped through
only because they carry a prompt. Move the resumability decision to the
adapter: restoreArgv returns ErrNotResumable only when GetRestoreCommand
reports it cannot resume AND there is no prompt to fresh-launch from.
2. reconcileLive marked a crash-orphaned (dead-runtime) session terminated
without a restore marker, so RestoreAll skipped it and it stayed dead.
It now saves-and-tears-down to the same end state a graceful shutdown
produces (capture work, write the session_worktrees marker, terminate,
remove the worktree), so RestoreAll relaunches it on the same boot,
resuming history. Crash recovery now matches graceful restart. If work
capture fails it terminates without a marker rather than risk losing
un-preserved work.
Tests: promptless orchestrator restores via adapter resume; promptless
session with a non-resuming adapter still returns ErrNotResumable;
reconcileLive writes the marker + tears down the worktree. Full backend
suite green (1632), gofmt/vet clean.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 4.8 <noreply@anthropic.com>
(cherry picked from commit 9ae05735d6f06ac989857534bae2766392772c71)
* chore: format with prettier [skip ci]
* docs: scrub stale zellij references after tmux/conpty migration (#409)
PR #404 migrated the runtime adapter from Zellij to tmux (Darwin/Linux)
plus conpty (Windows), selected via runtimeselect, but ~30 stale zellij
references lingered in comments and docs describing zellij as the current
runtime. This is a comments/docs-only cleanup with no behavioral change:
comments now say tmux (or tmux/conpty when both platforms are relevant),
terminal/doc.go and docs/backend-code-structure.md are rewritten to
reflect the tmux + conpty + runtimeselect attach model, and the daemon
environment, STATUS, stack, architecture, and CLI docs are updated.
Also gitignore the local .codegraph/ and .cursor/ tooling dirs.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
* chore: format with prettier [skip ci]
---------
Co-authored-by: Claude Opus 4.8 <noreply@anthropic.com>
Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
* fix(review): message worker on changes_requested instead of relying on SCM poll (#337)
review.Engine.Submit previously only persisted the verdict/body and left the
worker to learn about requested changes via the SCM poll loop, which is gated on
GitHub's reviewDecision and never reaches CHANGES_REQUESTED for self-reviews or
COMMENT-state reviews. Submit now nudges the worker's live pane directly via
ports.AgentMessenger (the same mechanism lifecycle uses) whenever the verdict is
changes_requested.
Extended flow: the reviewer reads back the GitHub review id it posted and passes
it through `ao review submit --review-id`; the id is stored on the review_run row
(new column + migration 0016) and included in the worker message so the worker
knows exactly which review to address and reply to.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
* fix(review): mark worker nudge as AO internal review, ask to reply + resolve
Distinguish the AO internal review nudge from the external GitHub-reviewer
feedback the lifecycle SCM loop relays. For an AO review the worker is now asked,
once it has pushed its fix, to reply on the review referencing its id with what
it changed and resolve the inline review comment threads it addressed (the
reviewer posts inline comments, so the per-finding threads are resolvable via
resolveReviewThread; the top-level review object is not, hence the reply).
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
* fix(review): generalise the changes-requested worker nudge wording
Drop the "not an external GitHub PR reviewer" aside and the assumption that the
worker pushes a fix — it may resolve the feedback without code changes. The nudge
now reads "Review the feedback below and address it" and asks the worker to reply
with how it addressed the review and resolve the threads it addressed.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
* fix(review): harden the review-id read-back against array order and empty results
The reviewer read the just-posted review id with `--jq '.[-1].id'`, which trusts
the REST API to return reviews in ascending submission order and errors when no
review exists. Review ids are monotonic, so select the highest id instead and
emit nothing when the list is empty: `--jq 'map(.id) | max // empty'`. Update the
matching `--review-id` flag help.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
* fix(review): post the review via gh api and capture its id from that response
The reviewer must use `gh api --method POST .../reviews` to attach inline
comments anyway (`gh pr review` cannot), and that response already contains the
created review's id. Capture `.id` from that single call instead of a second
read-back, dropping the array-ordering/pagination heuristics entirely — the id is
the exact review just created.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
* fix(review): send the review as a JSON body so inline comments are a real array
gh api -f/-F cannot build an array of objects: comments[][path] is sent as a
literal key, so the inline comments are dropped — defeating the reason for using
gh api over gh pr review. Post the review via --input JSON instead, keeping the
.id capture and the approve/COMMENT fallback.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
* chore: format with prettier [skip ci]
* chore(review): drop accidentally committed reviewer scratch, write review out of tree
review.md was the reviewer agent's own writeup, swept onto the worker branch by a
stray `git add -A` in 5df20c9. Remove it, gitignore `/review.md` as a backstop,
and change the reviewer prompt to write its review to a temp file outside the
checkout instead of into the worktree (where it could be committed onto the
worker's branch).
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
* fix(review): message the worker before marking the run complete
If messenger.Send failed after UpdateReviewRunResult had already flipped the run
to complete, a retried `ao review submit` tripped the status='running' guard and
could never record the result. Send first; only mark the run complete once the
worker has been notified, so a failed send leaves the run retryable. A landed
message followed by a failed DB write degrades to one extra nudge on retry — the
same trade lifecycle's sendOnce makes.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
* feat(review): accept the review body on stdin so the reviewer writes no file
`ao review submit --body -` now reads the review from stdin, and the reviewer
prompt pipes its writeup via a heredoc instead of writing a file. Previously the
reviewer wrote review.md into its checkout to pass as --body, which could be
committed onto the worker's branch (as it just was). A file path is still
accepted for backward compatibility.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
* fix(review): always post approvals as COMMENT, drop the APPROVE attempt
The reviewer posts from the PR author's own GitHub account, so event=APPROVE
always 422s. Drop it: request changes with REQUEST_CHANGES, approve with a
COMMENT-event review whose body states it is an approval.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
* fix(review): post every review as event=COMMENT (author can't APPROVE or REQUEST_CHANGES own PR)
The reviewer posts from the PR author's own account, where GitHub rejects both
APPROVE and REQUEST_CHANGES. Always post a COMMENT-event review and state the
verdict in the body; the machine-readable verdict still reaches AO via
`ao review submit --verdict`.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
* fix(cli): accept underscore flag names on `ao review submit`
Reviewer agents routinely invoke the submit command with --review_id
instead of --review-id, which cobra rejected as an unknown flag and
dropped the GitHub review id from the worker notification. Normalize
underscores to hyphens on the command's flags so both spellings resolve
to the same flag.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
* fix: sanitize review id in worker notifications
---------
Co-authored-by: Claude Opus 4.8 <noreply@anthropic.com>
Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
Co-authored-by: Vaibhaav <user@example.com>
* feat(review): configurable AO code review backend (V1)
Add per-project configurable code review of a worker's PR. A reviewer
agent runs one-shot over the worker's own worktree and posts its result
to the PR; the worker picks the feedback up through the existing SCM
observer review-nudge path.
- domain: ProjectConfig.reviewers (+ default reviewer harness), Review /
ReviewRun types and verdict/status vocab.
- storage: review + review_run tables (0011), sqlc queries, store methods.
- service/review: rewrite the in-memory stub as a persisted ReviewService
(Trigger/Submit/List) with a reviewer Runner over agent resolver +
runtime; ports.PRReviewPoster implemented on the GitHub adapter.
- http: session-scoped routes POST /sessions/{id}/reviews/trigger,
POST .../submit, GET .../reviews; regenerated OpenAPI + TS types.
- cli: ao review trigger|submit|list.
- frontend: adapt ReviewDashboard to the per-worker reviews API.
Closes#192
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
* refactor(review): address review — drop submit/poster/CLI, default reviewer to worker harness
Per PR #197 review feedback:
- Reviewer agent posts its review to the PR itself, so remove the
ports.PRReviewPoster port, the GitHub review poster, the submit HTTP
route + DTO, and the service Submit method (#1, #4, #7).
- Trigger spawns the reviewer agent over the worker's worktree with its
own review prompt, mirroring the session launch flow (resolve agent by
harness -> argv -> runtime.Create) (#8, #9).
- Default reviewer harness reuses the worker's harness when supported,
falling back to claude-code; reviewer config stays independent of the
worker override (#5, #6).
- Drop the `ao review` CLI for this PR's scope (#2, #3).
Regenerated OpenAPI + TS types.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
* feat(review): restore ao review submit (records verdict+body in AO)
Per maintainer request, bring back `ao review submit`. AO records the
reviewer's verdict and body on the review_run and marks the pass complete;
it does not post to GitHub — the reviewer agent posts its review to the PR
itself.
- storage: add review_run.body (0011), persist via Insert/UpdateReviewRunResult.
- service: restore Submit (no SCM poster) storing verdict + body.
- http: restore POST /sessions/{id}/reviews/submit + SubmitReviewInput.
- cli: ao review submit [worker] --verdict --body (worker from arg/--session/$AO_REVIEW_WORKER).
- runner: reviewer prompt instructs posting to GitHub and recording via ao review submit.
Regenerated OpenAPI + TS types.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
* refactor(review): move reviewer runner to its own package; sharpen prompt
Per PR #197 review:
- Move the concrete reviewer runner out of the service layer into a new
internal/review_runner package (package reviewrunner), beside other
orchestration packages like session_manager. The service keeps only the
Runner interface + RunSpec it depends on; the agent-resolver + runtime
launch flow lives in review_runner.
- Sharpen the reviewer prompt: tell the agent to diff against the PR base,
focus on high-confidence findings, post via `gh pr review`, and record
the result with `ao review submit`; review-only (no commits/edits).
- Add unit tests for the runner.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
* refactor(review): simplify review_run schema; provider-agnostic reviewer prompt
Per PR #197 review:
- review_run: status default 'running' (drop 'pending'), drop CHECK
constraints on status/verdict, drop the updated_at column and the
session/iteration index. Propagated through queries, domain, store,
service, and tests.
- Reviewer prompt no longer hardcodes GitHub/gh commands — it instructs the
agent to use whatever review tooling the provider offers, keeping the
flow extensible across SCM providers.
Regenerated sqlc + OpenAPI/TS.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
* refactor(review): launch reviewer before persisting the run
Trigger now spawns the reviewer agent first and then writes the review_run
with a status derived from the launch outcome (running on success, failed
if it never started), instead of inserting a running row and correcting it
to failed afterwards.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
* refactor(review): pluggable reviewer registry distinct from worker harnesses
Reviewers are now their own pluggable adapter set, separate from the worker
agent registry — adding a reviewer (claude-code today, greptile tomorrow) is
a one-line registration that does not widen the worker harness vocabulary,
and a worker harness does not automatically become a valid reviewer.
- domain.ReviewerHarness: a distinct vocabulary (AllReviewerHarnesses) with
its own IsKnown; ReviewerConfig/Review/ReviewRun use it. ResolveReviewerHarness
reuses the worker harness only when it is itself a supported reviewer, else
falls back to claude-code.
- ports.Reviewer: a reviewer-specific contract (ReviewCommand → argv + env)
that models one-shot / non-prompt CLIs natively instead of forcing every
reviewer through the worker's interactive GetLaunchCommand(Prompt:...).
- internal/adapters/reviewer: a separate registry + resolver (mirrors the
worker agent registry) with the claude-code reviewer adapter, which owns the
review prompt and reuses the worker claude-code launch construction.
- review_runner resolves via the reviewer registry (not the worker
AgentResolver) and merges AO_REVIEW_WORKER into the adapter's env.
- daemon wires the reviewer resolver. Registry/domain parity is test-enforced.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
* test(review): cover run-scoped reviewer submit
* fix(api): update generated review submit schema
* refactor(review): split core engine (internal/review) from API service
Move the review orchestration (Trigger/Submit/List, run-id generation,
deps, RunSpec/Runner, sentinels) into a transport-independent core package
internal/review (Engine). internal/service/review is now a thin API-flow
boundary: the controller-facing Manager interface + a Service that delegates
to the engine + error re-exports.
This keeps the service layer to API concerns and lets the same engine back a
future in-process CLI trigger without going through HTTP. review_runner now
depends on the core package; daemon builds the engine and wraps it in the
service. No API/schema changes.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
* feat(review): commit-aware trigger, reviewer handle for UI, no env vars
Reworks the review trigger lifecycle and drops env-based coupling:
- review_run gains target_sha (the reviewed commit) and drops iteration.
A repeat trigger for the same PR head short-circuits to the existing run.
- review gains reviewer_handle_id: the live reviewer pane's runtime handle,
reused across passes and exposed in the reviews API so the UI can attach
its terminal over /mux.
- Trigger flow: if a live reviewer pane exists and a new commit arrived,
message it to re-review; otherwise spawn a fresh reviewer. The run is
recorded only after the reviewer is launched.
- No environment variables: the reviewer adapter embeds the explicit
`ao review submit --session <w> --run <id>` command in the spawn prompt
and the re-review message. CLI submit requires --run/--session (no env
fallbacks).
- Merge review_runner into internal/review as a Launcher (spawn/notify/alive).
- Trigger returns 201 for a new pass, 200 when reusing an existing run.
Regenerated sqlc + OpenAPI/TS.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
* refactor(review): author the reviewer prompt centrally, not in the adapter
Mirror the worker model (session_manager builds the prompt; adapters just
place it via LaunchConfig.Prompt). The reviewer prompt now lives in
internal/review/prompt.go and is passed through ports.ReviewInvocation.Prompt;
the claude-code reviewer adapter just feeds inv.Prompt to its launch command
and returns it as the re-review message. One-shot CLI reviewers may ignore it.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
* refactor(review): split reviewer prompt into system+task, mirroring buildSpawnTexts
Mirror session_manager.buildSpawnTexts for the reviewer: a standing role goes
in the system prompt, the per-pass task (PR/commit + exact `ao review submit`
command) goes in the user prompt. internal/review/prompt.go now returns
(prompt, systemPrompt); both flow through ports.ReviewInvocation and the
claude-code adapter places them via LaunchConfig{Prompt, SystemPrompt}. The
re-review message reuses the per-pass prompt (role already established in the
running pane).
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 4.8 <noreply@anthropic.com>
Co-authored-by: Vaibhaav <user@example.com>
Co-authored-by: copilot-swe-agent[bot] <198982749+Copilot@users.noreply.github.com>
A spawn with no explicit harness ran the daemon default (claude-code) but
stored an empty harness: effectiveHarness returned "", seedRecord persisted it,
and the empty->default resolution lived only inside agentRegistry.Agent. The API
then omitted harness and the UI defaulted to "codex" — mislabelling a Claude
Code session.
Inject the daemon's default agent (AO_AGENT / config.DefaultAgent) into the
session manager and resolve an unspecified harness to it before the seed row is
written, so the stored/returned harness matches the agent that actually runs.
Closes#220
* fix(codex): deliver activity hooks via -c session flags, trust worktree at launch
Codex (0.136+) never loads hook config from AO's per-session worktrees:
project-local .codex/ layers only load from trusted directories, and for
linked git worktrees codex sources hook declarations from the matching
folder in the root checkout — so the workspace-local .codex/hooks.json AO
wrote was dead config and codex sessions never reported activity.
Deliver the hooks on the launch/resume command instead:
- -c 'hooks.<Event>=[...]' session-flag config for SessionStart,
UserPromptSubmit, PermissionRequest, and Stop; the session-flags layer
is not trust-gated and aggregates with the user's own hooks. The
existing --dangerously-bypass-hook-trust flag lets them run without a
persisted trust hash.
- -c 'projects={"<worktree>"={trust_level="trusted"}}' (inline-table
form; the dotted projects."<path>".trust_level key is corrupted by
codex's naive -c dot-split) so spawns into never-trusted repos don't
hang invisibly on the interactive directory-trust prompt. Both the
literal and symlink-resolved worktree paths are trusted.
- -c notice.hide_rate_limit_model_nudge=true so the "switch to a cheaper
model?" dialog can't hang a headless pane and swallow the spawn prompt.
GetAgentHooks no longer writes workspace files (worktrees stay clean); it
only strips entries older AO versions left in .codex/hooks.json,
preserving user hooks. UninstallHooks/AreHooksInstalled now operate on
those legacy files only.
Verified with a real spawn into a fresh untrusted repo: activity
transitions idle -> active -> idle hands-free, no .codex dir in the
worktree, no hook delivery failures.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
* feat(sessions): activity-signal watchdog + hook delivery hardening
A codex upgrade broke activity tracking silently: sessions showed a
confident "idle" forever while the agent worked. This bundle makes hook
delivery verifiable end to end and makes any future breakage loud
instead of invisible.
Watchdog (no_signal status):
- sessions.first_signal_at (migration 0010) records the FIRST hook
callback per spawn/restore — raw signal receipt, independent of the
derived activity state. lifecycle.ApplyActivitySignal stamps it (and
writes through same-state repeats until stamped, e.g. Codex
SessionStart reporting idle on an idle-seeded row); MarkSpawned clears
it so every relaunch re-proves its hook pipeline.
- deriveStatus downgrades a live session with no receipt to the new
no_signal display status after a 90s grace, instead of idle.
Terminated/PR-derived statuses still win. The sessions CDC update
trigger now also fires on first-signal receipt so the dashboard
transition is pushed live.
- frontend maps no_signal -> needs_you (a human should look at the pane).
Hook callback hardening (re-landed from the closed redesign PR #156):
- the session manager pins each spawned session's PATH with the daemon
executable's directory first, so the bare `ao` in hook commands
resolves to the daemon that installed them, with a spawn-time warning
when the pin cannot apply.
- `ao hooks` failures append to $AO_DATA_DIR/hooks.log (size-capped);
`ao doctor` gains a hooks-log check that warns on failures from the
last 24h, and an ao-binary identity check.
Codex launch-surface canary:
- `ao doctor` gains codex-launch-flags: it runs probes exported by the
codex adapter (built from the same flag builders as the real spawn
argv) against the installed binary, warning when codex rejects the
hook-trust bypass flag or AO's -c session-flag overrides.
- codex hook callback timeout drops 30s -> 5s so a hung daemon cannot
stall the agent's turn.
Docs: the agent PRD callback section now describes the implemented flow
(derive state, POST /sessions/{id}/activity, hooks.log) instead of the
unbuilt SQLite/metadata merge, and notes that hook-derived metadata
persistence (codex resume) is still not implemented.
Frontend note: main's renderer test suite has 7 pre-existing failing
files and a vite-config typecheck error unrelated to this change;
workspace.test.ts (the only frontend file touched) passes 26/26.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
* test(store): restore TestSessionWorktreesRoundTrip lost in the re-landing port
The branch ported store_test.go wholesale from the closed redesign
branch, whose copy predates #165 — silently dropping the
session-worktrees round-trip test #165 added. Restore main's file and
re-apply only this branch's addition (TestSessionFirstSignalRoundTrip).
No other ported file lost main-side content (audited per-file against
main; the remaining deletions are this branch's intended refactors).
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
* fix(status): only derive no_signal for harnesses that have a hook pipeline
Review finding: the no_signal downgrade had no harness-capability gate, but
first_signal_at can only ever be stamped by an `ao hooks` callback. Ten
spawnable harnesses (amp, aider, crush, grok, kimi, devin, auggie, continue,
vibe, pi) install no hooks at all, so every live session of theirs would have
flipped from idle to a permanent no_signal -> needs_you after the 90s grace.
The session service now takes a SignalCapable predicate; daemon wiring injects
activitydispatch.SupportsHarness (the deriver registry is the source of truth
for "this harness can signal"). Left nil, the service never claims no_signal.
A new dispatch test pins that every deriver token is a known harness name.
Also from the same review:
- lifecycle/manager.go and the 0010 migration claimed Codex's SessionStart
reports idle as the first signal; both codex and claude-code derivers
deliberately return no signal for session-start, so the comments now cite a
real case (a lost "active" POST followed by a Stop hook landing idle).
- docs/agent/README.md documents the gate and the restore caveat: a restored
session the user never prompts has nothing to signal, so it shows no_signal
after the grace until a receipt-only session-start signal exists.
- 0010 migration uses DROP TRIGGER IF EXISTS per house style.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
---------
Co-authored-by: Claude Fable 5 <noreply@anthropic.com>
Introduces the shared platform that per-agent adapters plug into, wired for the
three shipped harnesses (claude-code, codex, opencode):
- adapters/agent/registry: single source of truth for shipped adapters
(Constructors), consumed by the daemon to resolve a session's harness.
- adapters/agent/activitydispatch + 'ao hooks' command: maps an agent's native
hook callbacks onto AO activity states (active/idle/waiting/...).
- claudecode/codex/opencode: emit SessionStart/UserPromptSubmit/Stop activity.
- HTTP + OpenAPI: report session activity state.
- db: single migration widening sessions.harness to all shipped harnesses, so
adding an adapter needs no further migration.
- domain: harness constants + --agent alias for 'ao spawn'.
Adding a new agent is now one adapter package plus a line in Constructors().
Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Co-authored-by: Harshit Singh Bhandari <claudeagain@pkarnal.com>
* feat(daemon): thread runtime messenger into Lifecycle Manager (#108)
The daemon used to construct the LCM with a nil messenger, so every
SCM-driven nudge dropped silently inside sendOnce. Move newSessionMessenger
above startLifecycle and pass the real messenger through, so CI-failure,
review-feedback, and merge-conflict nudges actually reach the agent.
Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
* feat(project): populate RepoOriginURL at add + lazy observer backfill (#108)
project.Add now shells out to `git -C path remote get-url origin` and
captures the result on the new project row, so the SCM observer can parse
it on the first poll. A missing remote falls back to "" rather than failing
project add — non-git roots and remoteless repos stay registerable.
To cover projects added before this change, the observer's discoverSubjects
lazily backfills RepoOriginURL via the same shell-out and persists it
through UpsertProject, so subsequent polls skip the fork-exec.
Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
* feat(lifecycle): persist reaction-dedup signatures across restart (#108)
Add migration 0005 with `pr.last_nudge_signature TEXT NOT NULL DEFAULT ''`
and two scoped sqlc queries (Get/UpdatePRLastNudgeSignature). Lifecycle
serialises the per-PR slice of its seen/attempts maps to that column as a
small JSON document; sendOnce loads it lazily on first touch of each PR
and persists after every successful send.
This closes the post-restart re-nudge gap: the daemon used to lose the
seen map on bounce, so a still-failing CI re-prompted the agent on the
first post-restart observer poll even when it had already been told.
Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
* fix(lifecycle): silence nilerr on intentional corrupt-payload swallow
golangci-lint's nilerr flagged the `if err := json.Unmarshal(...); err != nil { return nil }`
path in loadPRSignaturesLocked. The swallow is deliberate (a corrupt persisted
payload should not crash the lifecycle write path), so compare against nil
directly so no `err` is bound and the lint goes quiet.
Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
* fix: silence nilerr, address reviewer notes, drop task-tagged comments
- reactions.go: discard the json.Unmarshal error explicitly via `_ =` so
golangci-lint's nilerr stops flagging the intentional corrupt-payload
swallow; behavior unchanged.
- reactions.go: document the Send → memory → persist order in sendOnce so
the "one extra nudge on restart after a transient persist failure"
trade-off is explicit (vs. the inverse risk of losing a real nudge).
- service.go: stop reaching for slog.Default() in resolveGitOriginURL;
align with the observer's identical helper that just returns "" on git
failure rather than logging through the global logger.
- tests: drop "issue #108" / "guards the regression from #X" framing in
test docstrings — explain WHAT the test asserts, not the PR context.
Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
* feat(agent): add opencode adapter + activity plugin hooks
Add an opencode (sst/opencode) agent adapter implementing the 6-method
ports.Agent interface and register it in the daemon's agent resolver, so a
session with harness "opencode" spawns and restores a real opencode worker.
opencode diverges from the claude-code/codex adapters in two ways the adapter
bridges:
- No native command-hook config. Unlike Claude Code (.claude/settings.local.json)
and Codex (.codex/hooks.json), opencode has no "run this command on event"
config (see sst/opencode#5409). Its only lifecycle surface is a JS/TS plugin
loaded from .opencode/plugins/. GetAgentHooks therefore //go:embeds an
AO-owned plugin (assets/ao-activity.ts) and writes it atomically; install is an
idempotent overwrite and uninstall is a sentinel-guarded delete, so
user-authored plugins are never touched. The plugin maps opencode events onto
AO's three normalized activity events: session.created -> session-start,
message.updated/message.part.updated -> user-prompt-submit, and
session.status(idle) -> stop (NOT the deprecated session.idle, which is
unreliable under `opencode run`). It shells `ao hooks opencode <event>` via a
guarded sh -c so a missing `ao` binary is a silent no-op.
- A single approval flag. opencode exposes only --dangerously-skip-permissions
(no graduated accept-edits/auto) and no system-prompt flag, so those map to a
bypass-only permission flag and a documented no-op for the system prompt
(deferred to opencode's own config).
Launch uses the interactive TUI (`opencode --prompt <p>`); restore continues a
captured native session via `opencode --session <id>`.
opencode_test.go mirrors codex_test.go (12 tests) and the daemon wiring test now
asserts the opencode harness resolves.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
* fix(agent): address Greptile review on opencode adapter (#80)
- Dispatch all opencode plugin hooks synchronously (Bun.spawnSync). The
session.created handler previously fired session-start via an async
Bun.spawn; if opencode does not await the event handler, a following
message.updated -> user-prompt-submit (sync) could complete before the
in-flight async session-start, so AO would see the prompt before the session
was registered. A sync spawn blocks opencode's single-threaded event loop, so
events are now reported strictly in dispatch order. Removes the now-unused
async callHook helper.
- Fix package/doc comments that said .opencode/plugin/ (singular) to match the
plural .opencode/plugins/ the adapter actually writes to.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
* fix(agent): surface opencode hook failures instead of swallowing them
The activity plugin previously discarded every failure: callHookSync ignored
the subprocess exit code/stderr and both catch blocks were empty, so a failing
`ao hooks` invocation or a malformed event payload was completely invisible.
Now failures are reported through opencode's structured logger (client.app.log)
while still never crashing opencode:
- callHookSync pipes stderr and checks result.success; a non-zero exit (a real
`ao hooks` failure — the `command -v ao` guard makes a missing binary exit 0)
is logged with its exit code and stderr.
- spawn exceptions (e.g. no `sh`) are caught and logged.
- the event-handler catch logs the offending event type instead of swallowing.
- logHookFailure is itself best-effort (optional-chained, rejection swallowed),
so logging can never throw back into opencode.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
* fix(agent): address opencode adapter review — install guard, prompt dedup, hook timeout
Maintainer review on #80 surfaced three pre-merge issues:
- GetAgentHooks could clobber a user file: install overwrote
.opencode/plugins/ao-activity.ts unconditionally while uninstall was
sentinel-guarded. Install now refuses (loud error) to overwrite a file that
isn't AO-managed; absent/AO-managed targets still write idempotently.
- Empty-prompt report poisoned the dedup: message.updated fired
user-prompt-submit with an empty prompt AND marked the message seen, so the
text from the following message.part.updated was deduped away and never
reached AO — breaking title-from-prompt. reportUserPrompt now reports at most
twice: an optional early empty report (keeps run-mode flows active) that does
NOT block a later text report, and a text report that is terminal.
- Bun.spawnSync had no timeout, so a hung `ao hooks` could block opencode
indefinitely. Each spawn is now time-boxed at 30s, matching the claude-code
and codex hook timeouts.
Adds TestGetAgentHooksRefusesToClobberForeignFile and a spawn-timeout assertion.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
* fix: harden opencode activity hooks
---------
Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Co-authored-by: harshitsinghbhandari <24b4506@iitb.ac.in>
* feat(messenger): ao send + live zellij pane ping (live agent nudges)
Replace the daemon's noopMessenger stub with a composite AgentMessenger
that writes a durable inbox file (primary) and types a live pointer into
the running zellij pane (best-effort secondary), plus the `ao send` CLI
that drives the existing POST /api/v1/sessions/{id}/send route.
- composite: fans Send to inbox then panep, pinning one timestamp so both
derive the same filename; a secondary failure is logged at WARN and
swallowed (the file is on disk), a primary failure aborts the call.
- inbox: writes <workspace>/.ao/inbox/<rfc3339nano>_<hash>.md.
- panep: types "new message at .ao/inbox/<file>" + Enter via a new narrow
zellij WriteChars seam (RuntimePaneWriter), kept off ports.Runtime.
- wiring: newSessionMessenger composes inbox+panep over the shared store;
startSession takes the messenger instead of the noop stub.
Carries across @aa-43's work from PR #74 (staging), adapted to main's
post-#65/#77 daemon wiring shape.
Closes#79
Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
* fix(inbox): use O_EXCL so a filename collision errors instead of clobbering
os.WriteFile opens with O_CREATE|O_WRONLY|O_TRUNC, which silently overwrites
an existing file. The doc comment already stated the intent ("we do not retry
on EEXIST"), but O_TRUNC never yields EEXIST — two identical messages sent on
the same composite-pinned nanosecond would produce the same filename and the
second Send would silently lose the first message. Switch to
O_CREATE|O_EXCL|O_WRONLY so a collision surfaces as an error; O_EXCL also
refuses to follow a symlink at the final path component. Add a regression test.
Addresses greptile review on PR #83.
Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
* fix(inbox): remove the freshly-created file when write or close fails
The O_EXCL switch creates the inbox file before writing its body; if
WriteString or Close then fails, the empty/partial .md was left on disk and
the agent's next inbox scan would pick up a truncated ghost message. Remove
the file on those error paths. O_EXCL guarantees the file did not exist before
this call, so the cleanup can only delete our own partial write, never a
legitimate earlier message.
Addresses greptile review on PR #83.
Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
* fix(messenger): reduce ao send to live pane delivery
* fix(send): preserve messages and map lookup errors
* fix(send): reject terminated sessions
* Add `ao spawn` and `ao project add`; resolve project repos for worktrees
Make a registered project spawnable end-to-end from the CLI:
- DB-backed RepoResolver: the daemon resolves a project's on-disk repo
path from the projects table (replacing the empty StaticRepoResolver
that failed every lookup), so a session's worktree is cut from the
right repo.
- session_manager defaults an empty spawn branch to ao/<session-id> — a
fresh, unique branch per session, since gitworktree can't reuse a
branch already checked out elsewhere (e.g. main).
- `ao project add --path <repo>`: register a local git repo (POST /api/v1/projects).
- `ao spawn --project <id> [--harness] [--branch] [--prompt] [--issue]`:
spawn a worker session (POST /api/v1/sessions); harness defaults to the
daemon's AO_AGENT.
- Shared postJSON daemon client (reads the run-file for the port, surfaces
the API error envelope).
Stacked on #65, which lands the agent-adapter + session-manager wiring
this depends on.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
* Address Copilot review on #77
- `ao spawn` no longer prints a branch the sessions API doesn't return
(session metadata is json:"-"), so the output is no longer misleading.
- Unregistered/archived/no-path projects now surface a 400
PROJECT_NOT_RESOLVABLE with an actionable message instead of a generic
500: a new sessionmanager.ErrProjectNotResolvable sentinel the resolver
wraps and writeSessionError maps.
- postJSON reuses the injected Deps.HTTPClient (cloned, with a longer
timeout) instead of a fresh client, keeping HTTP behaviour stubbable.
- postJSON treats a stale run-file (dead PID) as "not running" via
ProcessAlive, matching its docstring.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
* Assert the project-not-resolvable sentinel in the resolver test
Greptile review: harden TestProjectRepoResolver to verify the unregistered
-project error wraps ErrProjectNotResolvable, so a future regression in the
sentinel wrapping (which the HTTP 400 mapping relies on) is caught.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
* Fix ao spawn 500 on long session ids (zellij socket-path overflow)
Root cause: the daemon built the zellij runtime with an empty SocketDir,
so zellij fell back to its $TMPDIR-based default (long on macOS). That
left almost none of the ~103-byte unix-socket-path budget for the session
name, so a long session id (e.g. "aoagents-agent-orchestrator-1", derived
from a long project id) was rejected by zellij with "session name must be
less than 0 characters". runtime.Create failed, the spawn 500'd, and the
worktree was rolled back (leaving an orphan ao/ branch).
- New zellij.DefaultSocketDir(): a short, stable per-user socket dir
(/tmp/ao-zellij-<uid>); the daemon uses it (and MkdirAll's it).
- ao spawn's attach hint now prefixes ZELLIJ_SOCKET_DIR so it stays
copy-pasteable against the daemon's socket dir.
- Regression test guards that the socket dir leaves >= 48 bytes for the
session name within the 103-byte limit.
Verified: ao spawn against a long-id project now succeeds (session live,
worktree created) where it previously 500'd.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
* test(cli): guard CLI/daemon DTO drift with an e2e round-trip
The CLI keeps its own request structs (spawnRequest, addProjectRequest)
separate from the daemon's canonical DTOs (controllers.SpawnSessionRequest,
project.AddInput). Nothing verified the JSON field names agreed, so a renamed
tag on either side would compile but break at runtime.
Drive `ao spawn` and `ao project add` through the real httpd router and
controllers (fakes only at the service layer) over a real loopback round trip
via postJSON, asserting each field decodes into the right SpawnConfig/AddInput
field. Runs in the normal test lane (no extra ports/processes).
Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
* fix(cli,daemon): address review findings on ao spawn
- spawn: print the sanitised zellij session name (zellij.SessionName) in the
attach hint; a long/non-conforming session id is registered under a different
name, so the raw id sent users to a missing session.
- client: surface the daemon error envelope's requestId so a failed command can
be correlated with daemon logs.
- daemon: don't swallow the zellij socket-dir MkdirAll error — log it, since a
failure otherwise surfaces later as an opaque socket-bind error on every spawn.
- project: reject an embedded ".." in a project id up front; it passed the id
pattern but yielded an invalid branch (ao/a..b-1) and an opaque 500 at spawn.
Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Co-authored-by: harshitsinghbhandari <24b4506@iitb.ac.in>
* feat(plugin): add agents plugin (first iteration)
Faithful copy of the agents plugin implementation from yyovil/better-ao
(internal/plugin/ -> backend/internal/plugin/) plus its PRD
(prds/plugins/agents/PRD.md), as a first-iteration proposal for review.
Imports are left at their original github.com/yyovil/better-ao/... paths and
are NOT yet reconciled to this repo's module; see PR description for the
integration deltas (module path, missing internal/utils dependency).
Co-authored-by: Claude <noreply@anthropic.com>
* Move agent adapters under backend adapters
* Keep daemon ports and session out of adapter move
* Remove Better-AO naming from flake
* Keep flake as dev shell only
* Use goimports for local formatting
* Wire session manager to per-session agent adapters
Move the Agent port into internal/ports and have the claude-code and
codex adapters implement it directly, alongside their workspace-local
activity hooks and a manifest-keyed adapter registry. Rename
RuntimeConfig.LaunchCommand to Argv and update the tmux and zellij
runtimes to match.
The session Manager now resolves a real agent adapter per session via a
new ports.AgentResolver: from cfg.Harness on Spawn and the stored harness
on Restore, so one daemon runs claude-code and codex sessions side by
side. The daemon backs the resolver with the registry; AO_AGENT selects
the default harness (default claude-code), validated at startup. Removes
the temporary noopAgent stub.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
* docs(agent): point the agent contract at internal/ports/agent.go
The Agent interface moved from internal/adapters/agent to internal/ports;
update the PRD's Goal and Agent Contract sections (and the SessionInfo
references) to match the code.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
* Wire the session service into the daemon
daemon.Run now builds the controller-facing session service — a session
manager over the zellij runtime, a gitworktree workspace, the shared
store + LCM, and the per-session agent resolver (AO_AGENT default,
validated at startup) — and mounts it at httpd APIDeps.Sessions, so the
session REST routes are backed by a real service. startLifecycle moves
ahead of the HTTP server so both share one LCM.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
* Address Greptile review: complete the live spawn path
- Spawn and Restore now install workspace-local activity hooks
(GetAgentHooks) and run the adapter's optional PreLaunch step before
launch, via a shared prepareWorkspace helper. PreLaunch is how Claude
Code records workspace trust, so its interactive "trust this folder?"
dialog can't hang the headless pane; the spawned env now also carries
AO_DATA_DIR so the installed hook commands find the store.
- claudecode and codex hook/config writes are now atomic (temp + rename)
instead of os.WriteFile, so a crash mid-write can't leave a partial
file the agent fails to parse.
- ensureWorkspaceTrusted serializes its read-modify-write under a package
mutex, so concurrent spawns to different workspaces don't drop each
other's ~/.claude.json trust entries.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
* test(ports): pin MetadataKeyAgentSessionID to domain.SessionMetadata json tag
The equality between ports.MetadataKeyAgentSessionID and the json tag on
domain.SessionMetadata.AgentSessionID is a hand-maintained invariant; this
test fails loudly if either side drifts.
Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
* refactor(adapters): use ports.MetadataKeyAgentSessionID in claudecode + codex
The native session id metadata key is defined in ports for cross-package
consumption; drop the duplicated literals in each adapter so the constant
has one home.
Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
* test(codex): cover ensureCodexHooksFeatureEnabled TOML edge cases
The helper is a string editor over config.toml; pin its content
transformation for missing/empty files, existing [features] blocks,
the no-op case, and the legacy codex_hooks=true migration paths.
Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
* docs(adapters): document Registry concurrency contract
Registry registration runs at daemon boot before any goroutine calls Get,
so the underlying map needs no lock; pin that contract in the doc comment
so a future change doesn't quietly introduce a race.
Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
* style(codex): gofmt codex_test.go after constant rename
The previous commit (7c5b2a9) replaced codexAgentSessionIDMetadataKey with
ports.MetadataKeyAgentSessionID inside a map literal; the longer key threw
off gofmt's column alignment on the adjacent codexTitleMetadataKey /
codexSummaryMetadataKey lines. Caught by agent-ci's Check formatting step.
Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
Co-authored-by: harshitsinghbhandari <dev@theharshitsingh.com>
Introduces backend/.golangci.yml (27 linters across correctness, dead-code/
boilerplate, style, and security), wires it into CI as a blocking job, and
fixes every finding so the tree starts at zero.
Config:
- 27 linters: errcheck, govet, staticcheck, errorlint, bodyclose,
sqlclosecheck, rowserrcheck, nilerr, makezero, unused, unparam, unconvert,
wastedassign, copyloopvar, prealloc, dupl, revive (incl. exported-symbol doc
comments), gocritic, misspell, usestdlibvars, predeclared, nakedret, gosec, …
- Tuned for signal over noise: govet/shadow and gocritic hugeParam/rangeValCopy/
unnamedResult disabled (idiomatic-Go false positives); sqlc-generated code and
tests get scoped exclusions; gosec G304 excluded (paths are config/run-file/
worktree-derived, not user input); nilerr excluded in cli/status.go (probe
failures are the reported status, not a command error).
CI:
- New blocking lint job (golangci-lint-action, latest binary for Go-version
compatibility).
- go-version now read from go.mod (was pinned 1.22 while go.mod declares 1.25).
Cleanup to reach zero (no behavior change):
- errcheck: wrap deferred/inline Close()/Remove()/Rollback() with `_ =`.
- gosec: tighten dir/file perms (0755->0750, 0644->0600).
- unparam: drop always-nil error return from startLifecycle; drop unused
shellPath param (zellij PowerShell) and always-500 fallbackStatus param
(writeProjectError).
- gocritic: regexp \d, s != "", switch->if, combined appends.
- revive: doc comments on all exported symbols; rename project.ProjectRow ->
project.Row (stutter); rename `max` locals shadowing the builtin.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Each PR-child table (pr / pr_checks / pr_comment) had three near-identical
structs — gen.* (generated), sqlite.*Row, and ports.* — with wiring.Adapter
copying field-by-field between them. Collapse to one shared definition per
table in domain (PRRow / PRCheckRow / PRComment), used by both the PRWriter
port and the sqlite store; gen.* stays sealed inside the storage layer.
- *sqlite.Store now satisfies ports.SessionStore + ports.PRWriter directly,
so the entire wiring.Adapter package is deleted (lifecycle.New(store, store)).
- The bool PR state <-> single state column, int<->int64, and enum-default
translation now lives only at the gen<->domain boundary in pr_store.go.
- WritePRObservation renamed WritePR to match the port; the integration test
and composition root drop their adapter copies.
Net -280 lines, behaviour unchanged. go test -race ./... green.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Anirudh Sharma
Harshit Singh Bhandari
neversettle
Adil Shaikh
Laxman
Khushi Diwan
Ashish Huddar
yyovil
prateek
Dhruv Sharma