* feat(frontend): add live browser panel
* chore: format with prettier [skip ci]
* feat: preserve and auto-open browser previews
* fix: retry browser preview after session updates
* fix: wait for browser view before preview navigation
* fix: reopen preview after session switches
* fix: preserve browser views across session switches
* chore: format with prettier [skip ci]
* feat: add `ao preview` command to drive the session browser panel
Replaces the browser panel's auto-detect with an explicit, session-scoped
command. `ao preview [url]` runs inside a session (derives the target from
AO_SESSION_ID; rejects when unset or when the session is unknown):
- with a url, opens it verbatim (file://, http, https; no sanitization for now)
- with no url, autodetects index.html in the workspace as before
The resolved target is persisted as a new `previewUrl` session field and fans
out over the existing CDC /events stream (the sessions update trigger now fires
on preview_url and carries previewUrl in its payload). The desktop browser panel
reflects session.previewUrl: it opens, switches the center pane to the browser,
and navigates, re-navigating only when the target changes.
ponytail: file:// preview targets are accepted unsanitized; agent-trusted for now.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
* docs(cli): document the `ao preview` command
Add `ao preview` to the CLI command tables in README.md and docs/cli/README.md,
noting it resolves its session from AO_SESSION_ID and its no-arg autodetect vs
explicit-URL behavior.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
* chore: format with prettier [skip ci]
* fix(frontend): reveal `ao preview` in the inspector Browser tab, not the center pane
`ao preview` set session.previewUrl, and SessionView surfaced it by
popping the browser into the center pane, replacing the terminal. Reveal
it in the inspector rail's Browser tab instead (opening the rail if it is
collapsed); the manual pop-out button still expands it to the center.
Lifts the inspector's active tab to an optional controlled prop so
SessionView can drive it, and adds a regression test asserting the center
pane keeps the terminal while the rail switches to Browser.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
* docs: instruct agents to `ao preview` when showing frontend changes
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
---------
Co-authored-by: Vaibhaav <user@example.com>
Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
Co-authored-by: Harshit Singh Bhandari <dev@theharshitsingh.com>
Co-authored-by: Claude Opus 4.8 <noreply@anthropic.com>
* feat(session): support multiple PRs per session
A session can now own several pull requests (a root plus stacked
children) instead of being capped at one. The SQLite schema was already
1-session->many-PR (pr.url PK, session_id a plain FK), so this is a
behavioural change across the observe -> persist -> derive -> react
pipeline, not a migration.
- observe: the SCM observer discovers every open PR whose source branch
matches a session branch or descends from it ("branch/..." stacking),
attributing each to the owning session; the longest matching branch
wins so a child session claims its own stacked PRs.
- derive: session status is a worst-wins aggregate over all owned PRs,
with a stack model (B is a child of A iff B.target == A.source and A is
open) exposed via prs[] on every session read DTO.
- react: per-PR reactions; a stacked child blocked by an open parent is
exempt from the rebase/merge-conflict nudge (only the bottom of the
stack is eligible), and the session completes only when no PR is open
and at least one merged.
- tests: unit coverage across stack/status/observer/lifecycle, a
real-SQLite ListPRFactsForSession test for the stacked-PR read path,
and a functional end-to-end integration test driving the real store +
lifecycle + observer through attribution, completion, and stacked-child
nudge suppression.
Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
* fix(scm): ignore fork heads in PR attribution and persist discovered siblings before completion
Branch-prefix attribution now requires a discovered PR's head branch to live
in the project repo. A fork PR can reuse a session's branch name while its
commits live in the fork, so the previous code could auto-claim foreign work.
Carry head repo full_name from the REST list response and skip any PR whose
head repo is not the base repo.
discoverNewPRs also writes each newly discovered PR as an open baseline row
before the refresh/lifecycle pass runs. A session can own several PRs, and a
terminal observation triggers a completion check that reads all of the
session's PRs from the store. Without the early write, an open sibling found
in the same poll was not yet durable and the session could terminate while
that PR was still open.
Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
* fix(session): surface actionable signals from blocked stacked children; clarify worker prompt
Status aggregation previously dropped any open PR blocked by an open parent,
hiding actionable child signals (failing CI, draft, requested changes,
unresolved comments) behind the parent's status. A blocked child still cannot
merge, so its readiness signals (mergeable/approved/review-pending/open) stay
suppressed, but its problem signals now contribute to the worst-wins aggregate.
The all-blocked fallback is preserved so a session never goes dark.
The worker multi-PR prompt said independent PRs could branch off the base
branch as usual, which conflicts with branch-prefix attribution. Clarify that
a PR may target the base branch, but its source branch must stay under the
session branch namespace for AO to track it.
Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 4.7 <noreply@anthropic.com>
validateBranch returned an untyped error for a name rejected by
git check-ref-format, so toAPIError fell through to INTERNAL_ERROR 500.
Add a ports.ErrWorkspaceBranchInvalid sentinel (mirroring the not-fetched /
checked-out-elsewhere ones), wrap it in validateBranch, and map it to
INVALID_BRANCH (400). Completes the residual of #152 Bug 3, which typed the
not-fetched and checked-out-elsewhere cases but left the invalid-format case
collapsing to 500.
Closes#212
An unknown --harness was only caught at the agent-registry lookup deep in
Spawn, after the seed row and worktree were already created: the untyped
error collapsed to INTERNAL_ERROR 500 and left a terminated orphan row.
Validate the harness against the registry before any durable state is
created and return a typed ErrUnknownHarness mapped to UNKNOWN_HARNESS (400).
Sibling to #152 Bug 6 (unknown binary on PATH), which did not cover a harness
with no registered adapter.
Closes#210
* feat(frontend): rebuild Electron desktop UI as a React + Vite renderer
Replaces the skeleton Electron frontend with a full React 19 + TypeScript
renderer (Vite, electron-forge, contextBridge preload), plus the backend
additions it needs.
Renderer:
- TanStack Query + EventTransport (CDC SSE on /api/v1/events)
- TanStack Router file-system routing (hash history for the file:// origin)
- Tailwind + shadcn/ui, react-resizable-panels, Zustand UI state
- @xterm/xterm per-session PTY over /mux WebSocket + WebGL addon
- openapi-typescript + openapi-fetch types off openapi.yaml
- electron-forge packaging + update-electron-app auto-updater
- Vitest + RTL · Playwright
Backend:
- cors.go — allowlist-only CORS, handles Private Network Access preflight
for app:// renderer -> loopback daemon
- session.TerminalHandleID exposed in domain + OpenAPI spec
- project.Path added to OpenAPI spec, service, store, and tests
DESIGN.md documents the emdash-matched dark UI (tokens, blue accent, status
glyph spec, orchestrator-led layout).
Co-authored-by: Ashish Huddar <ashish.hudar@gmail.com>
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Entire-Checkpoint: b1e334c1e54a
* feat(terminal): port yyork's terminal rendering architecture
XtermTerminal becomes a self-contained, dependency-free renderer component
(yyork's xterm-terminal.tsx pattern):
- Nothing writes into the buffer at mount — status/empty-state is DOM chrome.
Fixes the startup crash (xterm Viewport.syncScrollArea reading renderer
dimensions on a zero-sized panel).
- Multi-trigger fit (rAF + 50/250ms settle + fonts.ready + ResizeObserver):
FitAddon must re-measure after monospace font metrics settle or it
over-counts columns. xterm only fires onResize on real grid changes, so
repeated fits don't spam the PTY.
- Unicode11 width (agent CLIs print emoji/wide glyphs), WCAG-AA minimum
contrast, WebGL→canvas renderer fallback, full ANSI-16 palette per DESIGN.md.
TerminalPane keeps ONE terminal instance across session switches — the
attachment effect re-points the mux and RIS-resets the screen instead of
remounting (a keyed remount drops the warm GPU surface mid-switch).
useTerminalSession: resize debounced 100ms trailing (one SIGWINCH per pane
drag, not dozens); the "Attaching…" writeln is gone (banner chrome covers it).
Test infra: vitest never loaded vite.renderer.config.ts after the forge split
(it only auto-discovers vite.config.*) so the whole suite ran without jsdom.
Point the test script at the config and type it via vitest/config. Fix
pre-existing type errors (notarytool field, maker-zip config, named
updateElectronApp import). 97/97 passing, typecheck clean.
Co-authored-by: Claude Fable 5 <noreply@anthropic.com>
Entire-Checkpoint: eb0f94fcf914
* fix(spawn): don't send base branch; surface real API errors
Two bugs found spawning a worker from the modal:
1. "Based on: main" sent branch:"main" in the POST, but git can't add a
second worktree on a branch already checked out (main lives in the repo
root) — the daemon returns 409 BRANCH_CHECKED_OUT_ELSEWHERE. The base
branch must be OMITTED so the daemon mints a fresh ao/<sessionId> off the
project default. Only a non-default branch (resume an existing session
branch) is sent through.
2. The daemon's error body is {error,code,message,requestId}; App.createTask
did String(error) on it → the modal showed "[object Object]". Add
apiErrorMessage() to unpack message/error from the structured body, with
Error/string fallbacks.
Co-authored-by: Claude Fable 5 <noreply@anthropic.com>
Entire-Checkpoint: d3e718d393cd
* feat(terminal): Nerd Font glyph support via --font-mono (yyork pattern)
The terminal now resolves its fontFamily from the --font-mono CSS token
(styles.css @theme), which leads with the Nerd Font family stack
(JetBrainsMono Nerd Font Mono first). Agent TUIs get powerline separators
and file-type icons; box-drawing stays renderer-rasterized.
Mirrors yyork exactly: no font is bundled — the stack names system-installed
Nerd Fonts and the browser picks the first present, falling back to plain
monospace (no icon glyphs) when none are installed.
Co-authored-by: Claude Fable 5 <noreply@anthropic.com>
Entire-Checkpoint: 28120fa527a7
* chore(frontend): set up shadcn/ui foundation
Prep for the route-parity port: build new screens from shadcn primitives.
- components.json: Tailwind v4, css=styles.css, cssVariables, lucide, "@/" aliases
- "@/" -> src/renderer alias in tsconfig (paths) + vite (resolve.alias)
- fill the shadcn token gaps in @theme (card-foreground, input, destructive,
destructive-foreground) mapped to existing emdash tokens so `shadcn add`
components render on-brand without touching the design system
- add Card primitive (first use: Phase 1 board)
Did NOT run `shadcn init` (it would overwrite styles.css and wipe the emdash
tokens); the @theme already maps shadcn semantic names onto emdash raw tokens.
Co-authored-by: Claude Fable 5 <noreply@anthropic.com>
Entire-Checkpoint: 9b9c8391e52c
* refactor(renderer): persistent _shell layout + per-route pages (projects vocab)
Phase 0 of the route-parity port. Replaces the single state-driven <App> with
real TanStack Router pages behind a persistent _shell layout, the foundation
every ported screen builds on.
- _shell.tsx: pathless layout owning the Sidebar + shared state (workspace
query, daemon status, spawn modal, create project/task, theme, shortcuts);
child routes render into <Outlet>. The daemon-status effect runs once here.
- Router owns selection: ui-store sheds view/selectedSession/selectedWorkspace
(now route params); keeps only theme/sidebar/workbenchTab. Sidebar/SideRail
navigate via router and read active state from useParams.
- Routes (projects vocabulary): / -> SessionsBoard (new board home, replacing
the orchestrator-terminal home), /projects/$projectId -> scoped board,
/projects/$projectId/sessions/$sessionId and /sessions/$sessionId ->
SessionView (Topbar + terminal + git rail).
- Terminal persistence: it lives on the session route, so session->session is
a param change (TanStack keeps the route mounted -> mux re-points, no
remount); leaving for the board unmounts it and the server ring replays on
return.
- shell-context.ts hands daemonStatus/openSpawn/create* to route content.
Removed the monolithic App.tsx (+ App.test.tsx, whose create/spawn coverage
moves to route/hook-level tests in Phase 5) and the old workspaces.* routes.
shadcn Card used for the board cards. typecheck clean, 91 tests pass.
Co-authored-by: Claude Fable 5 <noreply@anthropic.com>
Entire-Checkpoint: d10b22f0d841
* feat(board): attention-zone kanban home
Phase 1: SessionsBoard becomes the real kanban, porting agent-orchestrator's
getAttentionLevel state machine (packages/web/src/lib/types.ts) as a pure
function rebound to reverbcode's SessionStatus.
- attentionZone() buckets a session into urgency-ordered zones — merge (one
click to clear, leftmost) → action (needs-you: needs_input/ci_failed/
changes_requested, the collapsed respond+review) → pending (waiting on
reviewer/CI) → working → done (archive).
- Board renders a horizontal column per non-empty zone; cards navigate into
the session route. shadcn Card for cards. Styled to DESIGN.md (emdash
hairlines, status dots, accent), not agent-orchestrator's tokens.
- 13 zone-mapping unit tests. typecheck clean, 104 tests pass.
Co-authored-by: Claude Fable 5 <noreply@anthropic.com>
Entire-Checkpoint: d315acacf784
* feat(settings): project settings form (Phase 2)
/projects/$projectId/settings — a settings page on reverbcode's own
ProjectConfig shape (not agent-orchestrator's agent/runtime/tracker/scm,
which the Go daemon doesn't have). Reuses agent-orchestrator's form structure:
read-only identity card + editable config.
- Reads GET /api/v1/projects/{id} (config + identity), saves via
PUT /api/v1/projects/{id}/config. The PUT replaces the whole config, so the
form merges edited fields over what loaded (keeps env/symlinks/postCreate
it doesn't expose).
- Editable: defaultBranch, sessionPrefix, default worker/orchestrator agent,
model override. React Query for load + mutation with inline save state.
- shadcn select + label added; settings gear in the project board header.
typecheck clean, 104 tests pass.
Co-authored-by: Claude Fable 5 <noreply@anthropic.com>
Entire-Checkpoint: 0633ebde603b
* feat(session): PR inspector in the session rail (Phase 2)
Ports agent-orchestrator's SessionInspector onto reverbcode's SessionPRFacts
(GET /api/v1/sessions/{id}/pr -> {prs: SessionPRFacts[]}). Mounts above the
git rail on the session route; renders nothing when the session has no PR.
- Shows PR number + state badge, and CI / mergeability / review facts with
tone derived from the fact string (pass/fail/pending), plus an unresolved
review-comments flag.
- React Query, fetched only when the session has a PR.
Completes Phase 2 (project board reuse + settings + inspector).
typecheck clean, 104 tests pass.
Co-authored-by: Claude Fable 5 <noreply@anthropic.com>
Entire-Checkpoint: c75dadfd45b8
* feat(prs): pull-requests board (Phase 3)
/prs — a PR board ported from agent-orchestrator's PullRequestsPage. The Go
daemon has no PR-list endpoint, so rows are derived from session PR fields
(every session carries pullRequest), sorted open/draft above merged/closed.
- Per-row Merge (POST /prs/{number}/merge) and Resolve comments
(POST /prs/{number}/resolve-comments) mutations with inline result; clicking
a row opens the session (whose inspector has the full CI/review facts).
- shadcn Table; "Pull requests" + "Review" nav added to the sidebar footer.
- /review + /reviews routes added as placeholders (the reviews board needs a
daemon backend — Phase 4); /reviews redirects to /review.
typecheck clean, 104 tests pass.
Co-authored-by: Claude Fable 5 <noreply@anthropic.com>
Entire-Checkpoint: 3526d847c568
* feat(reviews): code-review API + dashboard (Phase 4)
The long pole: the Go daemon had no reviews surface, so /review needed a
backend. Adds one, mirroring agent-orchestrator's reviews feature.
Backend:
- internal/service/review: in-memory reviews Manager (Run + Finding types,
List/Execute/Send). Execution is not yet wired to a real review agent —
Execute records a pending run so the surface is live; agent-backed findings
+ persistence are a follow-up (documented in the package).
- ReviewsController (GET /reviews, POST /reviews/execute, POST /reviews/{id}/send),
wired through api.go + daemon.go (constructed, not nil — actually serves).
- genspec: reviewOperations() + tag + schemaNames; openapi.yaml + schema.ts
regenerated. apispec parity/drift tests pass, go build + go test green.
Frontend:
- ReviewDashboard reads GET /reviews, lists runs with status + findings, lets
you pick a worker and Run review (execute) and Send a run. Replaces the
placeholder /review route. shadcn Card/Badge/Select.
Verified live: GET /reviews -> 200, POST /reviews/execute -> created run.
typecheck clean, 104 frontend tests pass.
Co-authored-by: Claude Fable 5 <noreply@anthropic.com>
Entire-Checkpoint: ce16c62dfdb0
* chore(renderer): Phase 5 polish — route prefetch + restored spawn coverage
- Route loader: _shell prefetches the workspace list via
queryClient.ensureQueryData (parent loader runs before children), pairing
with defaultPreload: "intent" so a hovered nav target is warm on click.
workspaceQueryOptions exported so the loader and hook share one cache.
- Restored the spawn coverage dropped with App.test.tsx as a focused
SpawnWorkerModal test: the base-branch-omission regression guard (the 409
fix) + the empty-prompt gate.
Full parity surface green: 106 frontend tests, typecheck clean, backend
build + vet clean, all daemon endpoints 200.
Co-authored-by: Claude Fable 5 <noreply@anthropic.com>
Entire-Checkpoint: 284ae668ffea
* feat(board): match agent-orchestrator's board verbatim
Per explicit request to mirror agent-orchestrator's app exactly (overriding
DESIGN.md/emdash for this screen). Rebuilds SessionsBoard from its actual
source (Dashboard + AttentionZone + SessionCard + mc-board.css), using its
exact tokens and values:
- 4 equal-width columns (grid 1fr), left->right flow: Working -> Needs you ->
In review -> Ready to merge (SIMPLE_KANBAN_LEVELS), always rendered; "done"
archived to a separate strip, not a column.
- Per-column vertical glow gradient (status-tinted top fading at 130px) +
glow dots + uppercase tinted column titles; #0a0b0d base, #15171b cards.
- Topbar: project crumb + Coding/Reviews tabs + breathing "N working" pill +
bell + blue "New worker" primary. "Board" subhead + subtitle.
- Card: status badge (dot + label) · mono id, 2-line title, mono branch line,
hairline-topped PR footer ("no PR yet").
typecheck clean, 106 tests pass.
Co-authored-by: Claude Fable 5 <noreply@anthropic.com>
Entire-Checkpoint: 3569e49ba7d6
* feat(theme): clone agent-orchestrator's dark palette globally
Per the verbatim-clone directive (supersedes DESIGN.md/emdash). Remaps the
:root tokens to agent-orchestrator's exact values — #0a0b0d base, #15171b
card, #f4f5f7/#9ba1aa/#646a73 text, hairline white-alpha borders, #4d8dff
accent, orange/amber/green/red status — so every screen's base shifts at once.
Adds --color-working (orange) for the working status.
Co-authored-by: Claude Fable 5 <noreply@anthropic.com>
Entire-Checkpoint: d70096d7f30d
* feat(renderer): clone agent-orchestrator ProjectSidebar verbatim
Rebuild the sidebar to match agent-orchestrator's ProjectSidebar: #08090b
rail, "Reverb / Code" brand with dimmed separator + collapse button,
uppercase PROJECTS label, project disclosure rows (rotating chevron +
hover-revealed New worker action + session count), nested session rows
with a 6px breathing working-dot and mono session id, and a single
Settings menu footer (Pull requests / Reviews / Search / Project
settings) plus a daemon-health dot.
Adds a shadcn dropdown-menu primitive (radix-ui unified package, matching
the existing select/label convention) for the footer menu.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Entire-Checkpoint: c4e1827b6142
* feat(renderer): clone agent-orchestrator session topbar
Restyle the session header to match agent-orchestrator's SessionDetailHeader:
a "Kanban" back-to-board button + hairline divider, a stacked identity
(project / title over a mono branch line with a git-branch icon), and a
StatusBadge --pill (tinted bordered pill with a 6px dot that breathes while
the agent is working). Wire onOpenBoard from SessionView to navigate back to
the project board (or home).
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Entire-Checkpoint: dcd3e4880af5
* feat(renderer): unify board/review/PR/settings chrome verbatim
Extract the mc-board dashboard header (project crumb · Coding/Reviews tabs ·
"N working" breathing pill · bell · settings · New worker) and the 21px
subhead into a shared DashboardTopbar/DashboardSubhead, then apply it to the
review, PR, and settings screens so every dashboard surface shares one stable
agent-orchestrator top strip. SessionsBoard now consumes the shared chrome
instead of its inline copy; review/PR/settings drop their minimal h-11 headers
for the crumb+tabs+subhead treatment on the #0a0b0d base.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Entire-Checkpoint: 2801a9c5c0ba
* docs: record agent-orchestrator-verbatim design direction
Per explicit user decision (2026-06-10), the renderer clones the
agent-orchestrator web app verbatim, superseding the older "match emdash"
direction. Add a prominent banner at the top of DESIGN.md (reference files,
live palette, the cloned surfaces, shadcn-primitive guidance), mark the
Aesthetic Direction section as superseded, and retarget CLAUDE.md's QA rule so
future review flags divergence from agent-orchestrator instead of emdash.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Entire-Checkpoint: fe028f97d5d5
* feat(renderer): clone agent-orchestrator shell and inspector
Finish the agent-orchestrator-style renderer pass with shadcn sidebar chrome, titlebar navigation, resizable session inspector, orchestrator spawn affordances, and matching design tokens.
Co-authored-by: Cursor <cursoragent@cursor.com>
* chore: format with prettier [skip ci]
* fix: repair UI PR CI drift
Co-authored-by: Cursor <cursoragent@cursor.com>
* refactor(terminal): per-client zellij attach replaces shared PTY + replay ring
Each WebSocket client that opens a pane now gets its own `zellij attach`
PTY (attachment.go) instead of sharing one PTY whose output was replayed
from a bounded byte ring. Zellij answers every fresh attach with its full
init handshake (alt screen, SGR mouse tracking, bracketed paste) and a
faithful repaint — the ring replay lost exactly that handshake, leaving
late subscribers without mouse reporting (dead wheel scroll). The cost is
one zellij client process per open pane per connection, which the zellij
server is built for (yyork ships the same model).
ring.go and session.go (fan-out, replay buffer) are deleted; manager.go
now tracks per-client attachments with liveness gating, and pty_unix.go
answers every resize frame with an explicit SIGWINCH.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
* fix(renderer): re-assert settled terminal resize; align docs with per-client attach
After each debounced resize settles, send one follow-up resize frame with
the same grid (RESIZE_REASSERT_MS). xterm only fires onResize on actual
grid changes, so a resize update the zellij client loses (raced mid-attach
or coalesced during a drag) would otherwise desync the session layout from
the pane until the next real change. The backend answers every resize
frame with an explicit SIGWINCH, so the re-assert is a no-op when already
in sync.
Comments in the terminal hook/components now describe the per-client
attach model (fresh server-side `zellij attach` per open, no replay ring).
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
* feat(renderer): full-width shell topbar; retire per-view topbars and review dashboard
The shell now owns a single full-width ShellTopbar (status pill, history
arrows, notifications, kanban/inspector toggles) with the sidebar pinned
below it, replacing the per-view Topbar/DashboardTopbar pair; board pages
get a lightweight DashboardSubhead. The standalone review dashboard and
its /review(s) routes are removed — review state lives on the PR board.
Approved divergence from the AO reference (full-height sidebar) recorded
in DESIGN.md; macOS traffic lights re-centered on the 56px header row.
Also hardens the session view around rrp v4:
- inspector defaultSize re-derived per panel mount (orchestrator → worker
navigation kept SessionView mounted while the panel remounted), and the
imperative expand/collapse effect no longer races panel registration
- onResize writes gated on data-separator="active" so flex-grow
transition frames can't bounce the store (dead-looking toggle button)
- findProjectOrchestrator skips terminated orchestrators so the topbar
offers Spawn instead of attaching to a dead zellij session
- inspector resize handle gets a visible 1px divider at rest
- playwright specs for history arrows + inspector toggle; test-results/
gitignored
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
* docs: document Electron app dev quick start
Add an "Electron app (dev)" section: npm install + npm run dev under
frontend/, with the explicit heads-up that the app does not start the
daemon — it attaches over loopback to a daemon started via `ao start`
(plus npm run dev:web for renderer-only work in a browser).
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
* chore(fork): ignore local agent session dirs
Fork-only ignore entries (.entire/.claude/.gstack) — must not be included
in upstream PRs.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
* chore: format with prettier [skip ci]
* feat: align backend session lifecycle with workspace runtime updates
* refactor: replace spawn modal with shell-native worker controls
* chore: add shared daemon launch helper and docs updates
* chore: format with prettier [skip ci]
---------
Co-authored-by: Ashish Huddar <ashish.hudar@gmail.com>
Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Co-authored-by: Cursor <cursoragent@cursor.com>
Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
* fix(sessions): stop AO hook files from making every worktree permanently dirty
Agent adapters write hook files (.codex/hooks.json, .opencode/plugins/
ao-activity.ts, .claude/settings.local.json, ...) into fresh session
worktrees as untracked files. `git worktree remove` (deliberately run
without --force) refuses on any untracked file, so Workspace.Destroy
failed for every session of the 12 workspace-writing harnesses:
POST /sessions/{id}/kill returned an unlogged 500 INTERNAL_ERROR and
`ao session cleanup` reported 'Would clean N' then '0 sessions cleaned'
with no reason, leaking workspaces forever.
Three coordinated fixes, none of which force-deletes user/agent work:
- Root cause: every adapter now writes a sentinel-guarded, self-ignoring
.gitignore next to its hook files (hookutil.EnsureWorkspaceGitignore),
so AO's own files no longer count as dirt while anything an agent
drops — even in the same directory — still blocks teardown. A
registry-wide conformance test enforces the contract for all current
and future adapters. (Per-worktree .git/worktrees/<name>/info/exclude
was evaluated first but git does not honor it.)
- Typed refusal: gitworktree.Destroy classifies a still-dirty refusal as
ports.ErrWorkspaceDirty (git status probe). Kill maps it to success
with freed=false (session terminated, worktree preserved); Cleanup
reports it per-session as skipped-with-reason through the API
(CleanupSessionsResponse.skipped), and the CLI prints
'Skipped: <id> (workspace has uncommitted changes)' plus a summary.
- Observability: envelope.WriteError records the raw service error into
a request-scoped slot and the access log attaches it to 5xx lines, so
any remaining internal error is diagnosable server-side.
Worktrees created before this fix gain the .gitignore on restore (hook
install re-runs); their cleanup is otherwise reported as skipped instead
of erroring.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
* fix(cleanup): address Greptile P2s — surface dirty-probe failures, stop leaking raw errors
Two review findings on this PR:
- gitworktree.Destroy: when the isDirty probe itself failed, the error was
silently discarded and the refusal looked identical to "registered but not
dirty". The probe failure now rides the returned error (dirty probe: ...),
so it reaches the access log via the 5xx error capture.
- Cleanup skip reasons: a non-dirty teardown failure put the raw error —
including internal filesystem paths — into the public skipped[].reason
field. The public reason is now the fixed string "workspace teardown
failed"; the full cause goes to the daemon log (warn, with sessionID and
path). The dirty-refusal reason is unchanged.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
* fix(gitworktree): wrap the dirty-probe error with %w per errorlint
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
---------
Co-authored-by: Claude Fable 5 <noreply@anthropic.com>
* fix(cdc): emit pr_review_thread_resolved on replace polls (#152 bug 5)
writePRRows was DELETE-then-UPSERT on the Replace path, so every poll's
upserts hit the INSERT branch and the AFTER UPDATE trigger that emits
pr_review_thread_resolved never fired in production. Replaces the
blanket delete with a set-diff: upsert observed threads first (so
unchanged thread_ids go through ON CONFLICT DO UPDATE and fire the
UPDATE trigger when resolved flips), then delete orphans whose
thread_id is not in the observed set, all inside the existing tx.
Adds DeletePRReviewThread query (sqlc-generated form hand-edited; no
sqlc binary available locally — sqlc generate from backend/ produces an
identical file).
Tests: TestPRReviewThreadsCDC_EmitsResolvedOnReplacePoll (regression —
fails without fix) and TestPRReviewThreadsReplace_PrunesOrphansWithoutReinserting.
Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
* fix(observe): emit scm-disabled log on startup with no subjects (#152 bug 7)
checkCredentials lived only inside Poll, which short-circuits when
discoverSubjects is empty. On a fresh daemon with no tracked PRs the
documented "scm observer disabled: provider credentials unavailable"
warn was unreachable, leaving users with no signal that the SCM
observer was a no-op.
Calls checkCredentials once in Observer.loop before the first Poll.
The existing credentialsChecked guard preserves once-per-process
semantics; provider construction still uses SkipTokenPreflight so
daemon readiness doesn't block on gh.
Test: TestStart_LogsDisabledWarningWhenNoTokenAndNoSubjects with a
race-safe syncBuffer for capturing slog from the observer goroutine.
Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
* fix(api,spawn): typed errors + project/branch/binary preflight (#152 bugs 1-4,6)
Closes the long tail of opaque-500-and-orphan-row failures that
discussion #149's smoke walk surfaced. The common shape: spawn created
the session row before validating preconditions, and the underlying
errors weren't typed, so toAPIError defaulted to INTERNAL_ERROR.
Bug 1 (orphan row + opaque 500 on unknown projectId):
Service.Spawn / SpawnOrchestrator now call store.GetProject first and
return apierr.NotFound("PROJECT_NOT_FOUND", ...) before manager.Spawn,
eliminating the create-row-then-fail-workspace ordering.
Bug 2 (Restore opaque 500 on half-spawned/terminated session):
Manager.Restore gained the ErrIncompleteHandle guard that Kill has at
manager.go:189-193. toAPIError now maps both restore and kill to the
same SESSION_INCOMPLETE_HANDLE 409 envelope.
Bug 3 (--branch unfetched / checked-out-elsewhere → opaque 500):
gitworktree pre-checks listRecords for branch-in-other-worktree, falls
back to refs/tags on missing local/remote head, and emits two new port
sentinels (ErrWorkspaceBranchCheckedOutElsewhere,
ErrWorkspaceBranchNotFetched) mapped to BRANCH_CHECKED_OUT_ELSEWHERE
(409) and BRANCH_NOT_FETCHED (400).
Bug 4 (orphan terminated row on claim-pr rollback):
Adds Store.DeleteSession gated to seed-state rows only (preserves the
no-resurrection guarantee for live sessions), transactional change_log
cleanup, Manager.RollbackSpawn (delete-then-fallback-to-kill), a new
POST /sessions/{id}/rollback endpoint, and rewires
cli/spawn.rollbackSpawnedSession to use it. The exit-0 sub-symptom was
unreproducible from current source and is left unaddressed.
Bug 6 (agent binary not on PATH → silent idle session):
Drops the "return name, nil" anti-pattern from all 21 agent adapters
and returns the new ports.ErrAgentBinaryNotFound on exec.LookPath miss.
Manager.Spawn gained a validateAgentBinary pre-flight (with injectable
LookPath so tests don't need real binaries on PATH) that aborts before
runtime.Create. Mapped to AGENT_BINARY_NOT_FOUND (400). Integration
tests in internal/integration/ stub LookPath to /usr/bin/true.
Tests cover each bug end-to-end. OpenAPI regenerated for /rollback.
Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
* chore: gofmt + regen frontend schema.ts for /rollback
CI fixes for #153:
- gofmt/goimports on kilocode and kiro adapters that the bug 6 audit
left mis-grouped.
- openapi-typescript regen against the new /rollback endpoint added in
the Lane A commit.
Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
* fix(store): guard change_log delete behind seed probe + regen sqlc (#152, PR #153 review)
Addresses @greptile-apps P1 and P2 review feedback on PR #153.
P1 (CDC events deleted for live sessions in rollback fallback):
DeleteChangeLogForSession ran unconditionally inside the transaction
before DeleteSeedSession's seed-state predicates filtered the session
delete to a no-op. For a live session reaching DeleteSession (the
delete-then-kill fallback path inside RollbackSpawn), the seed delete
returned 0 rows but the session_created/session_updated CDC events
had already been purged. Now probes via a new SessionIsSeed query
first and short-circuits the whole tx — including the change_log
cleanup — when the row is not in seed state.
P2 (regen sqlc): installed sqlc 1.31.1 and ran `sqlc generate` from
backend/, replacing the hand-edited pr_review_threads.sql.go (and
producing minor format-only churn in models.go, pr.sql.go,
sessions.sql.go, changelog.sql.go).
The regen surfaced two issues:
1. GetPR / ListPRsBySession had their return types hand-changed to
gen.PR by the previous PR; sqlc actually emits GetPRRow /
ListPRsBySessionRow when queries enumerate columns. Fixed by
collapsing those two queries to `SELECT * FROM pr` so sqlc returns
gen.PR (which is what the store's prRowFromGen converter expects),
and pr.last_nudge_signature now lands in the result alongside the
existing 37 columns.
2. sqlc 1.31.1's SQLite parser silently strips trailing `?`
placeholders and string literals from DELETE statements (reproduced
with sqlc.arg, IFNULL, rowid subquery, and second-predicate
workarounds — all eaten). DeleteSeedSession and
DeleteChangeLogForSession both tripped it. They are now run as
plain tx.ExecContext calls inside Store.DeleteSession, inside the
same write transaction as SessionIsSeed; both queries are removed
from the queries/ directory and the workaround context is
documented inline in queries/sessions.sql and queries/changelog.sql
to keep future contributors from re-adding them.
Verified: go build ./... clean, go test -race ./... 1097/1097 pass.
* refactor(backend): LLD maintainability fixes in controllers/service layers
Addresses the high + medium severity findings from the LLD review of
backend/internal/httpd and backend/internal/service (#95):
1. Controllers no longer import internal/session_manager. Session sentinel
errors are now *domain.ServiceError values carrying their own HTTP mapping,
so the controller translates them with one generic errors.As — no
cross-package sentinel imports.
2. One error pattern across services: project.Error is now an alias of the
shared domain.ServiceError, and session_manager sentinels use it too. A
single writeServiceError replaces the per-resource error switches.
3. Clean-orchestrator business logic moved out of the controller into
session.Service.SpawnOrchestrator(ctx, projectID, clean).
4. isGitRepo no longer treats case-different paths as equal on case-sensitive
filesystems; case-insensitive compare is gated to darwin/windows via samePath.
5. Project repo check sits behind an injectable GitChecker, so the service is
testable without a real git binary.
6. httpd exports only the production constructors (NewWithDeps,
NewRouterWithControl); the 3 test-only wrappers are removed and the
"router with empty deps" convenience moved to an unexported test helper.
Closes#95
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
* refactor(backend): standardize service errors on internal/httpd/errors
Replace the domain.ServiceError approach with a REST-API-scoped error package
and a single envelope renderer, per review feedback:
- Add internal/httpd/errors (package errors, aliased apierr): one structured
Error type with semantic Kinds (Internal/Invalid/NotFound/Conflict) and
constructors. Imports nothing, so any layer can depend on it.
- envelope.WriteError is now the single path from a service error to the wire
APIError, and the only place a Kind becomes an HTTP status/word. The
per-resource writeProjectError/writeSessionError translators are gone.
- Delete domain/errors.go (keeps domain pure of HTTP-flavored kinds) and
service/project/errors.go (no per-service error files); services build
errors inline via apierr constructors.
- session_manager sentinels are apierr.Error values (pointer identity still
works with errors.Is).
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
* revert(backend): drop GitChecker seam and isGitRepo case-sensitivity change
Defer findings #4 (isGitRepo case-sensitivity) and #5 (GitChecker seam) out
of this PR. Restores the original exec-based isGitRepo and the New(store)
constructor; removes git.go, git_test.go, and the test-only export shims. The
error-standardization and other findings are unaffected.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
* refactor(session): translate engine errors to API errors at the facade
The session_manager is the internal command engine and must not depend on the
REST API error vocabulary. Revert its sentinels to plain errors.New values and
move the engine→API translation into the service/session facade (toAPIError),
which is the correct boundary. Controllers still see apierr.Error and never
import the engine; the engine no longer imports internal/httpd/errors.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
* docs(session): tighten error comments to state what the code does
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
* style(envelope): make KindInternal an explicit case in httpStatus
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
* refactor(apierr): rename package, test SpawnOrchestrator, parity fixes
Address review feedback on PR #96:
- Rename internal/httpd/errors → internal/httpd/apierr (package apierr) so
importers no longer alias around the stdlib errors package.
- Add a commander seam to session.Service and unit-test the relocated
clean-orchestrator rule: clean=true kills all active orchestrators before
spawning; clean=false spawns without kills.
- project.Add: wrap the UpsertProject store error in apierr.Internal for parity
with its sibling paths (was a raw 500).
- Document that KindInternal is iota's zero value, so a zero-value Error
defaults to 500.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 4.8 <noreply@anthropic.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>
Vaibhaav Tiwari
Adil Shaikh
Laxman
Pritom Mazumdar
Khushi Diwan
yyovil
Ashish Huddar
Harshit Singh Bhandari
neversettle