* 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>
* 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>
* feat(agents): add droid adapter
Registers the droid harness, stacked on the agent platform. Includes its own activity deriver.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
* feat(agents): add amp adapter
Registers the amp harness, stacked on the agent platform.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
* feat(agents): add agy adapter
Registers the agy harness, stacked on the agent platform. Includes its own activity deriver.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
* feat(agents): add crush, aider, goose, auggie, continue, devin, cline, kiro, kilocode, vibe, pi, autohand adapters
Cherry-pick batch landing the remaining 12 yyovil adapter directories per
Discussion #148 recipe, on top of #145 (grok/cursor/qwen/copilot/kimi) and
the droid/amp/agy commits earlier on this branch. Each adapter is a
self-contained package under backend/internal/adapters/agent/<name>/;
registry.Constructors(), activitydispatch.Derivers (for adapters with
activity.go), and wiring_test.go are unified to register all 23 shipped
adapters in one place. No new migration: 0007_allow_implemented_harnesses
already widens the sessions.harness CHECK to cover every adapter.
* fix(agents/kilocode): return error from json.Marshal of permission config
Previously the marshal error was discarded and the function returned a
prefix carrying an empty KILO_CONFIG_CONTENT. An unrecoverable marshal
failure for the typed map should never happen in practice, but if it ever
did, Kilo would silently launch with default permissions regardless of
the requested mode. Surface it as "no prefix" so the caller's mode choice
can't be misrepresented.
---------
Co-authored-by: yyovil <itsyyovil@gmail.com>
Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
* feat(agents): add grok adapter
Registers the grok harness (xAI Grok CLI). grok installs Claude Code-compatible
hooks, so it reuses the claude-code activity deriver already in the platform.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
* feat(agents): add cursor adapter
Registers the cursor harness, stacked on the agent platform. Includes its own activity deriver.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
* feat(agents): add qwen adapter
Registers the qwen harness, stacked on the agent platform. Includes its own activity deriver.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
* feat(agents): add copilot adapter (#128)
* feat(agents): add copilot adapter
Registers the copilot harness, stacked on the agent platform. Includes its own activity deriver.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
* Update backend/internal/adapters/agent/copilot/hooks.go
Co-authored-by: greptile-apps[bot] <165735046+greptile-apps[bot]@users.noreply.github.com>
* fix(copilot): map permission-request to documented preToolUse event
Copilot CLI does not document a "permissionRequest" hook event. Per
https://docs.github.com/en/copilot/how-tos/copilot-cli/customize-copilot/use-hooks
the documented camelCase events are sessionStart, sessionEnd,
userPromptSubmitted, preToolUse, postToolUse, errorOccurred, agentStop.
Writing "permissionRequest" into .github/hooks/ao.json silently disables
that hook because Copilot does not recognize the key.
Remap AO's permission-request sub-command onto preToolUse (the closest
documented signal — fires before any tool invocation, including ones
that would prompt for approval) and add a tripwire test asserting the
JSON keys AO writes match the documented camelCase names.
Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
* chore(copilot): gofmt the new tripwire test
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: Harshit Singh Bhandari <dev@theharshitsingh.com>
Co-authored-by: greptile-apps[bot] <165735046+greptile-apps[bot]@users.noreply.github.com>
Co-authored-by: harshitsinghbhandari <24b4506@iitb.ac.in>
* feat(agents): add kimi adapter
Registers the kimi harness, stacked on the agent platform.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
* fix(agents/kimi): drop approval flags on -p and --session paths
Kimi rejects `--prompt` combined with `--yolo`/`--auto`/`--plan`, and
rejects `--yolo`/`--auto` combined with `--session`/`--continue`
(non-interactive and resumed sessions inherit the auto permission
policy). The previous mapping appended one of those flags before `-p`
on every launch and before `--session` on every restore, so every
non-interactive launch would fail at startup. The local binary
(v1.37.0) additionally has no `--auto` option at all, which would
fail even on otherwise-permissible paths.
- GetLaunchCommand: emit approval flags only on the interactive path
(no prompt). The `-p <prompt>` path is now bare.
- GetRestoreCommand: never emit approval flags; resumed sessions
inherit the original session's approval settings.
- Tests assert no approval/plan flag leaks onto either path for any
PermissionMode, and keep the interactive mapping unchanged.
Refs: https://moonshotai.github.io/kimi-code/en/reference/kimi-command.html
* fix(agents/qwen): sync hook settings temp file
* fix(agents/grok): delegate hook cleanup lifecycle
---------
Co-authored-by: yyovil <itsyyovil@gmail.com>
Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Co-authored-by: greptile-apps[bot] <165735046+greptile-apps[bot]@users.noreply.github.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>
* refactor(project): manager talks to the sqlite store; drop the in-memory store
The project Manager now runs only against the durable backend store: remove the
process-local MemoryStore (and NewMemoryManager), and require a real Store. The
daemon already wires the sqlite store; tests now build a real temp-dir sqlite
store instead of the mock.
- Move Row + the Store port to project/store.go. The Store interface stays
because it is the dependency-inversion port that lets the manager reach the
backend without an import cycle (storage imports project.Row), not an extra
mock layer — there is no longer any in-memory implementation.
- NewManager requires a non-nil Store (no in-memory fallback).
- Add project/manager_test.go: List/Add/Get/Remove happy paths +
PATH_REQUIRED/NOT_A_GIT_REPO/PATH_ALREADY_REGISTERED/ID_ALREADY_REGISTERED,
PROJECT_NOT_FOUND/INVALID_PROJECT_ID, and UpdateConfig — all against a real
sqlite store (the service-logic tests #47 lacked).
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
* refactor(project): trim routes, consolidate package, add code-first OpenAPI
- Remove POST /reload, PATCH /{id}, POST /{id}/repair routes and their
Manager methods (Reload, UpdateConfig, Repair) and DTOs (ReloadResult,
UpdateConfigInput) — not needed at this stage
- Merge Manager interface into manager.go; delete project.go (single-impl
split served no purpose)
- Remove dead notImplemented helper from errors.go
- Port PR #59 code-first OpenAPI generation: controllers/dto.go named
response types, specgen/build.go (4 routes), parity + drift tests,
cmd/genspec, go generate wiring; regenerate openapi.yaml
- Add swaggest deps; add YAML() method to apispec.Spec
Co-Authored-By: Claude Haiku 4.5 <noreply@anthropic.com>
* fix(project): address PR review comments
- t.Skipf → t.Fatalf in gitRepo helper: git failures now hard-fail
instead of silently skipping manager tests on a misconfigured runner
- FindProjectByPath: add AND archived_at IS NULL so archived paths don't
permanently block re-registration (update queries/projects.sql and
generated gen/projects.sql.go)
- Add TestManager_ReaddAfterRemove to lock the fix
Co-Authored-By: Claude Haiku 4.5 <noreply@anthropic.com>
* fixed lint and fmt
* addressed greptile comments
* Apply suggestions from code review
Co-authored-by: greptile-apps[bot] <165735046+greptile-apps[bot]@users.noreply.github.com>
* project tests fix
* project_tests fix
* fix: Linting and formatting fix
* refactor: move project manager into service layer (#68)
* refactor: split service package by resource (#68)
* fix: ignore archived project id conflicts (#68)
* refactor: move pr manager into service layer (#68)
---------
Co-authored-by: Claude Opus 4.8 <noreply@anthropic.com>
Co-authored-by: greptile-apps[bot] <165735046+greptile-apps[bot]@users.noreply.github.com>
Co-authored-by: itrytoohard <ayetrytoohard@gmail.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>
Harshit Singh Bhandari
Adil Shaikh
Laxman
neversettle
yyovil
prateek
Dhruv Sharma