Reduces onboarding to `npm install -g @composio/ao && ao start`.
- Absorb init and add-project logic into `ao start` with auto-config
creation, environment detection, and project type detection
- Add single-instance tracking via running.json with already-running
interactive menu (human) and info+exit (agent)
- Add caller context detection (human/orchestrator/agent) via TTY and
AO_CALLER_TYPE env var
- Add plugin-based agent runtime detection — no hardcoded binary paths,
each plugin exports detect() and displayName
- Simplify `ao spawn` to just `ao spawn <issue>` with auto-detected
project (backward compat: `ao spawn <project> <issue>` still works)
- Set AO_CALLER_TYPE, AO_PROJECT_ID, AO_CONFIG_PATH, AO_PORT env vars
on all spawned sessions (worker, orchestrator, restore)
- Add `ao config-help` subcommand for config schema reference
- Deprecate `ao init` to thin wrapper, fully remove `ao add-project`
- Register/unregister in running.json on start/stop
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
- Publish @composio/ao-web dashboard as npm package (removed private flag,
added files field, production entry point, node-pty made optional)
- CLI auto-detects dev vs production mode for dashboard startup
- Use local next binary instead of npx in production start-all.ts
- findWebDir() throws with install-specific guidance instead of returning
broken path
- Fix CI-silent failure: setup.sh and ao-update.sh exit 1 on non-interactive
npm link failure
- Deduplicate detectDefaultBranch into shared cli/lib/git-utils.ts
- Add EACCES permission guidance to README.md and SETUP.md
- Move resolveProjectIdForSessionId to @composio/ao-core
- Update design doc with problems #8-13, changes #9-12, known limitations
section, and expanded test plan
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Every command now prints what to run next and from where:
- setup.sh → tells user to cd to project dir and run ao init
- ao init → tells user to run ao start (with directory context)
- ao add-project → tells user to run ao start and ao spawn
- ao start → tells user to run ao spawn <project> <issue>
Eliminates confusion about running commands in the wrong directory
(e.g., ao init inside agent-orchestrator instead of the project repo).
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
- npm link retry logic decision tree
- ao init auto vs interactive decision flow
- ao add-project 8-step pipeline diagram
- ao start port resolution flowchart
- Before/after horizontal bar chart for UX metrics
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Swap markdown design doc for a styled HTML version with dark theme,
before/after comparisons, impact metrics, and flow diagrams.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
- Add design doc covering all changes, UX impact, and new flow
- Update README: add ao init, ao add-project, ao start to Quick Start and CLI sections
- Remove --auto flag from README examples (now the default)
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
- `ao init` now auto-detects project with zero prompts by default
- Old 13-prompt wizard moved to `ao init --interactive`
- Removed dead `--smart` placeholder flag
- `ao start` auto-finds next free port if configured port is busy
instead of crashing with an error
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
- Fix npm link EACCES permission error in setup.sh, ao-update.sh, and ao-doctor.sh
by auto-retrying with sudo when interactive
- Add `ao add-project <path>` command that auto-detects git remote, default branch,
project type, and generates agent rules — appends to existing config in one step
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* fix(lifecycle): implement stuck detection using agent-stuck threshold
The agent-stuck reaction config supported a threshold field (e.g.
"10m"), but determineStatus() never returned "stuck" — there was no
code path that consumed the threshold or transitioned sessions based
on idle time. Sessions would stay parked at pr_open/working forever
even when the agent had been idle for hours.
Added idle-time check in determineStatus(): when getActivityState()
reports "idle" or "blocked" with a timestamp, compare the idle
duration against the agent-stuck.threshold config. If exceeded,
return "stuck" so the reaction system can fire notifications.
Also removed the priority !== "info" guard on transition
notifications, so all priority levels (including info) are routed
through notificationRouting. This lets the config control which
notifiers receive each priority level, rather than silently dropping
info-level transition events.
* fix(lifecycle): add post-PR stuck detection as safety net
The original stuck check in step 2 (before PR checks) can be bypassed
when getActivityState() returns null (session file not found, cache miss,
I/O failure). When this happens, the code falls through to the PR path
which returns 'pr_open' without ever checking idle duration.
Fix: extract isIdleBeyondThreshold() helper and call it in three places:
1. Step 2: before PR checks (fast path, catches most cases)
2. Step 4b: after PR checks return 'pr_open' (safety net)
3. Step 5: after all checks, for agents that finish without a PR
This ensures stuck detection fires even when the JSONL activity detection
fails to return idle state. Sessions can no longer get permanently stuck
at 'pr_open' when the agent has been idle beyond the threshold.
Also removes the debug console.error calls from the previous commit.
* fix(lifecycle): treat reviewDecision 'none' as approved for merge readiness
PRs with no required reviewers never reached 'mergeable' status because
getReviewDecision returned 'none', which was not handled. The lifecycle
poll fell through to 'review_pending' or the default, so merge.ready
never fired and the approved-and-green reaction never triggered.
Also: skip stuck short-circuit when session has an open PR so merge
readiness checks in step 4 can still run. Without this, idle agents
with open PRs get stuck status and never transition to mergeable.
Closes composio#0 (internal fix)
* fix(opencode): classify activity state from session timestamps
* test(lifecycle): cover opencode idle-threshold stuck transition
* fix(lifecycle): preserve global stuck threshold with project overrides
* fix(lifecycle): run PR auto-detection before stuck transitions
---------
Co-authored-by: Harsh <harshb012@gmail.com>
* perf: coalesce dashboard session refreshes
Batch membership-driven refreshes behind a short cadence and keep low-frequency steady-state refreshes so pause and PR data stay current without hammering /api/sessions during SSE churn.
Ultraworked with [Sisyphus](https://github.com/code-yeongyu/oh-my-opencode)
Co-authored-by: Sisyphus <clio-agent@sisyphuslabs.ai>
* perf: memoize dashboard session views
Keep unchanged zones and cards cold during same-membership SSE updates by stabilizing dashboard callbacks, caching project groupings, and memoizing the session view tree with a render-cadence regression test.
Ultraworked with [Sisyphus](https://github.com/code-yeongyu/oh-my-opencode)
Co-authored-by: Sisyphus <clio-agent@sisyphuslabs.ai>
* fix: prevent stale refresh scheduling after project switch
Abort in-flight refreshes and ignore late completions from disposed effects so old project fetches cannot re-arm timers or reset the new project state.
Ultraworked with [Sisyphus](https://github.com/code-yeongyu/oh-my-opencode)
Co-authored-by: Sisyphus <clio-agent@sisyphuslabs.ai>
---------
Co-authored-by: Sisyphus <clio-agent@sisyphuslabs.ai>
* docs: add CONTRIBUTING.md, expand development guide, fix broken CLAUDE.md links
- Add CONTRIBUTING.md covering bug reports, dev setup, plugin development, PR process
- Expand docs/DEVELOPMENT.md into a comprehensive architecture + conventions reference
(architecture overview, plugin pattern with full example, spawn flow, TypeScript and
shell command conventions, key design decisions, common dev tasks)
- Update README.md docs table to reference docs/DEVELOPMENT.md instead of gitignored CLAUDE.md
- Fix broken CLAUDE.md links in SETUP.md to point to docs/DEVELOPMENT.md
CLAUDE.md is gitignored (personal agent config) so links to it were always broken.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
* docs: document ao update workflow and fix guide links
---------
Co-authored-by: Claude Sonnet 4.6 <noreply@anthropic.com>
Co-authored-by: Harsh <harshb012@gmail.com>
Treat persisted tmuxName as metadata-derived runtime identity when runtimeHandle is missing so active sessions are not misclassified as exited/unknown across agents.
* fix: gate fresh session sends on interactive readiness
Wait for spawning tmux-backed sessions to settle before injecting input, and use OpenCode session timestamps to confirm delivery without relying on pane churn alone.
Ultraworked with [Sisyphus](https://github.com/code-yeongyu/oh-my-opencode)
Co-authored-by: Sisyphus <clio-agent@sisyphuslabs.ai>
* fix: satisfy lint in opencode send regression helper
Remove unnecessary escaping in generated shell snippets used by the new OpenCode confirmation tests so CI lint passes cleanly.
Ultraworked with [Sisyphus](https://github.com/code-yeongyu/oh-my-opencode)
Co-authored-by: Sisyphus <clio-agent@sisyphuslabs.ai>
* fix: avoid false opencode delivery confirmation
Only treat OpenCode timestamp confirmation as delivered when updatedAt advances beyond a known baseline, and add regression coverage for transient baseline visibility.
Ultraworked with [Sisyphus](https://github.com/code-yeongyu/oh-my-opencode)
Co-authored-by: Sisyphus <clio-agent@sisyphuslabs.ai>
---------
Co-authored-by: Sisyphus <clio-agent@sisyphuslabs.ai>
* feat: add end-to-end observability across core, web, and terminal
Instrument lifecycle/API/websocket flows with correlation-aware metrics and operator health surfaces so the system can self-diagnose and escalate failures.
* fix: realign session restore set and unblock claim PR typecheck
* fix(web): restore project-filtered sessions route after main merge
* fix(core): remove unused orchestrator import to unblock lint
* fix(core): always record lifecycle poll failures and remove dead review branches
* fix(web): harden websocket metrics and reuse SSE observers
* fix(web): preserve primary session API errors when services bootstrap fails
* fix(web): use full orchestrator config type in SSE observer helper
* fix(web): restore project-scoped SSE and guard observability error paths
* fix(web): address remaining Bugbot review gaps
* fix(web): align SSE project attribution and share session project resolver
* fix(web): require request arg for SSE route and align tests
* fix(web): record websocket error disconnects as failures
* fix(web): use path alias for session project resolver import
* fix(web): include active connection count in disconnect metrics
* fix: skip PR auto-detection for orchestrator sessions
Orchestrator sessions sit on the base branch (e.g. master) and should
never own a PR. When the lifecycle worker ran detectPR for these
sessions, any PR whose head branch matched master (e.g. a master->prod
deploy PR) would get incorrectly attached and keep re-attaching after
manual cleanup.
Add a role=orchestrator check to the PR auto-detection guard so
orchestrator sessions are skipped entirely.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* fix: add session ID suffix fallback for orchestrator PR auto-detection skip
Pre-existing orchestrator sessions spawned before the role metadata field
was added lack role=orchestrator. Mirror the session-manager pattern by
also checking session.id.endsWith("-orchestrator") as a fallback.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
Treat the all-projects dashboard as a project overview surface with per-project metrics and orchestrator access, while keeping the detailed kanban lanes for single-project workflows.
Drop the lifecycle manager's local orchestrator predicate so the final remaining core polling path follows the same shared detection logic as session cleanup, web filters, and CLI status.
Scan every orchestrator for active pause metadata instead of stopping at the first control session, so pause banners stay visible even when metadata-role orchestrators appear before the paused orchestrator in session listings.
Use one project-matching rule across the sessions API and SSR dashboard paths, and keep global pause derived from the full session set even when the API request is scoped to a single project.
Keep the SSR dashboard page using unified project filtering while clearing orchestrator links and pause state whenever enrichment fails, so error paths cannot render stale state beside an empty session list.
Use the same project matching logic for dashboard orchestrators and workers, and switch the client detail page to the lightweight core types entry so the canonical orchestrator helper stays shared without pulling server-only modules into the browser bundle.
Carry legacy project ownership through recovery, drop the redundant dashboard worker filter, and remove the now-unused orchestrator helper so the PR branch stays aligned with the shared per-project orchestration contract.
Use the core orchestrator detector in web filtering paths so SSE snapshots, backlog polling, and pause state all treat metadata-role orchestrators consistently with the dashboard and sessions API.
Keep the orchestrator detail page keyed on stable project-scoped values so zone-count polling does not recreate its callback on every session fetch and hammer the sessions API.
Preserve the legacy project fallback in the shared session loader and keep the sessions route filtering by project after the clean branch cherry-pick, so the final PR branch matches the verified multi-project behavior.
Keep orchestrator control sessions visible in CLI status without counting them as worker sessions, and preserve explicit roles in JSON output for multi-project tooling.
Render every project's orchestrator explicitly and keep orchestrator detail pages scoped to their own project so multi-project dashboards show the right control session.
Expose orchestrator links per project and keep them out of worker session stats so dashboard consumers stop collapsing multi-project state into one global orchestrator.
Recover the owning project from the sessions directory and archived metadata so older session files still resolve to the correct project and reuse the right orchestrator mapping.
* feat(core): add scm webhook contract
Defines a provider-agnostic SCM webhook contract in core types and
config so SCM plugins can verify and normalize inbound webhook events
without reshaping project config later.
* feat(scm): trigger lifecycle checks from github webhooks
Adds GitHub webhook verification and event parsing, exposes a web
webhook endpoint, and routes matching PR/branch events through the
existing lifecycle manager so CI and review reactions update immediately.
* fix(scm): verify github signatures with raw webhook bytes
Preserves the original webhook bytes alongside the decoded payload so
GitHub HMAC verification uses the exact request body while the route
continues to drive lifecycle checks through the existing manager.
* fix(web): wire scm webhook route into main branch services
Restores the main-branch service and route-test wiring while keeping the
new webhook route coverage and scoped lifecycle helper in place.
* fix(webhooks): use singleton lifecycle manager and fail closed on scm API errors
Reuses the existing services lifecycle manager for webhook-triggered checks
so reactions and state transitions don't replay from a fresh instance, and
restores fail-closed behavior for GitHub review comment fetch failures.
* fix(webhooks): tighten project matching and restore scm compatibility methods
Prevents repository-less webhook events from matching all projects, restores
GitHub SCM PR utility methods and CI status rollup fallback, and adds tests
covering the compatibility paths and safer project matching behavior.
* fix(webhooks): pre-check content length and continue on parse errors
Adds an early content-length guard against configured maxBodyBytes before
reading the body and changes candidate parse failures to fail-forward so
one malformed payload path does not abort other valid candidate handling.
* fix(scm-github): parse review-comment timestamps from comment payload
Use comment.updated_at/created_at for pull_request_review_comment webhook
timestamps so normalized events retain temporal data for comment events.
* fix(webhooks): apply early size guard only when all candidates are bounded
Uses the broadest candidate limit for pre-read content-length checks and
skips early rejection when any matching project has no configured limit,
while retaining per-candidate verification limits.
* fix(webhooks): normalize repo matching and skip terminal sessions
Match webhook repository names case-insensitively against configured project
repos and avoid lifecycle checks for terminal sessions when resolving
webhook-affected sessions.
* fix(webhooks): fail forward when lifecycle checks throw
* fix(scm-github): parse push webhook branch and sha
* refactor(scm-github): dedupe cli exec helper wrappers
* fix(scm-github): tighten exec helper type and comment timestamps
* fix(scm-github): prefer head_commit timestamp for push events
* fix(webhooks): tighten repository parsing and helper visibility
* fix(scm-github): ignore non-head refs for push branch
* chore: trigger bugbot rerun
* feat(scm-gitlab): add webhook verification and event parsing
* fix(webhooks): share parser utils and handle check_run branch
* fix(webhooks): ignore gitlab tag refs in ci branch mapping
* fix(scm-gitlab): harden token and tag ref handling
* chore(scm-gitlab): update webhook helpers around bugbot threads
* feat(web): add project-based dashboard architecture
- Add project query parameter to API routes
- Filter sessions by project in both SSR and SSE
- Update useSessionEvents hook to accept project param
- Update Dashboard and pass project to hook
- Add unit tests for project filtering
- Add architecture spec document
Implements project-based architecture as defined in docs/specs/project-based-dashboard-architecture.md:
- GET /api/sessions?project=X returns sessions for project X
- GET /api/events?project=X streams only sessions for project X
- Dashboard uses project filter from config
- SSE URL includes project param when provided
- Project matching uses projectId and sessionPrefix
- Full backward compatibility maintained (no param = all sessions)
* fix: remove duplicate export default in page.tsx
* fix(web): clean project-scoped dashboard verification
* fix(web): scope dashboard using project id
* fix(web): address Bugbot findings in project-scoped dashboard
- Consolidate triplicated matchesProject into shared lib/project-utils.ts
- Fix Dashboard to receive both projectId (for SSE filtering) and projectName (for display)
- Remove inline matchesProject definitions from page.tsx, sessions/route.ts, events/route.ts
* fix(web): resolve Bugbot issues in project-scoped dashboard
- Add ?project=all query param support in SSR page to show all sessions
(previously getPrimaryProjectId() always returned non-empty, making
else branches unreachable)
- Exclude orchestrator sessions from SSE stream to match SSR/API behavior
(orchestrator sessions get their own button, not a card)
- Add tests for SSE stream orchestrator exclusion and project filtering
Addresses Bugbot issues:
- #2903595986: Dead else branches when project filter always applied
- #2903595995: SSE stream includes orchestrator sessions unlike SSR/API
* feat(web): add project navigation sidebar
Add visible left sidebar with project navigation for multi-project setups:
- ProjectSidebar component with active state styling
- /api/projects endpoint to fetch configured projects
- getAllProjects() helper in project-name.ts
- Sidebar appears only when 2+ projects configured
- Click navigation updates ?project= query param
- Active project highlighted with accent color
Tests:
- ProjectSidebar component tests (8 tests)
- API routes tests with proper mocking
- All 386 web tests passing
Manual test steps:
1. Configure 2+ projects in agent-orchestrator.yaml
2. Start dashboard - sidebar should appear on left
3. Click different projects - URL updates, sessions filter
4. Click "All Projects" - shows all sessions across projects
5. Active project highlighted in sidebar
* fix(web): remove duplicate import in test file
* fix(web): consolidate ProjectInfo type to shared source
Remove duplicated ProjectInfo interface definitions from Dashboard.tsx and
ProjectSidebar.tsx. Both now import the type from @/lib/project-name where it is exported as the single source of truth.
This addresses Bugbot issue #2906835895: Triplicated ProjectInfo type instead of shared import.
* fix(web): integrate globalPause state from main
* fix(web): consolidate duplicate @/lib/types import
* feat(web): add project-based dashboard architecture
- Add project query parameter to API routes
- Filter sessions by project in both SSR and SSE
- Update useSessionEvents hook to accept project param
- Update Dashboard and pass project to hook
- Add unit tests for project filtering
- Add architecture spec document
Implements project-based architecture as defined in docs/specs/project-based-dashboard-architecture.md:
- GET /api/sessions?project=X returns sessions for project X
- GET /api/events?project=X streams only sessions for project X
- Dashboard uses project filter from config
- SSE URL includes project param when provided
- Project matching uses projectId and sessionPrefix
- Full backward compatibility maintained (no param = all sessions)
* fix: remove duplicate export default in page.tsx
* fix(web): clean project-scoped dashboard verification
* fix(web): scope dashboard using project id
* fix(web): address Bugbot findings in project-scoped dashboard
- Consolidate triplicated matchesProject into shared lib/project-utils.ts
- Fix Dashboard to receive both projectId (for SSE filtering) and projectName (for display)
- Remove inline matchesProject definitions from page.tsx, sessions/route.ts, events/route.ts
* fix(web): resolve Bugbot issues in project-scoped dashboard
- Add ?project=all query param support in SSR page to show all sessions
(previously getPrimaryProjectId() always returned non-empty, making
else branches unreachable)
- Exclude orchestrator sessions from SSE stream to match SSR/API behavior
(orchestrator sessions get their own button, not a card)
- Add tests for SSE stream orchestrator exclusion and project filtering
Addresses Bugbot issues:
- #2903595986: Dead else branches when project filter always applied
- #2903595995: SSE stream includes orchestrator sessions unlike SSR/API
* feat(web): add project navigation sidebar
Add visible left sidebar with project navigation for multi-project setups:
- ProjectSidebar component with active state styling
- /api/projects endpoint to fetch configured projects
- getAllProjects() helper in project-name.ts
- Sidebar appears only when 2+ projects configured
- Click navigation updates ?project= query param
- Active project highlighted with accent color
Tests:
- ProjectSidebar component tests (8 tests)
- API routes tests with proper mocking
- All 386 web tests passing
Manual test steps:
1. Configure 2+ projects in agent-orchestrator.yaml
2. Start dashboard - sidebar should appear on left
3. Click different projects - URL updates, sessions filter
4. Click "All Projects" - shows all sessions across projects
5. Active project highlighted in sidebar
* fix(web): remove duplicate import in test file
* fix(web): consolidate ProjectInfo type to shared source
Remove duplicated ProjectInfo interface definitions from Dashboard.tsx and
ProjectSidebar.tsx. Both now import the type from @/lib/project-name where it is exported as the single source of truth.
This addresses Bugbot issue #2906835895: Triplicated ProjectInfo type instead of shared import.
* fix(web): integrate globalPause state from main
* fix(web): consolidate duplicate @/lib/types import
* fix(web): restore global pause state and membership refresh
* fix(web): satisfy lint in project-scoped page defaults
* fix(web): remove dead global pause reducer action
Ultraworked with [Sisyphus](https://github.com/code-yeongyu/oh-my-opencode)
Co-authored-by: Sisyphus <clio-agent@sisyphuslabs.ai>
* fix(web): restore global pause resume time
Ultraworked with [Sisyphus](https://github.com/code-yeongyu/oh-my-opencode)
Co-authored-by: Sisyphus <clio-agent@sisyphuslabs.ai>
* chore(web): retrigger bugbot after thread reset
* refactor(web): centralize project session filtering helpers
* fix(web): reset pause banner dismissal on new pause
* fix(web): remove useless orchestrator assignment
* fix(web): derive header stats from live session state
* fix(web): restore project name in dashboard header
* fix(web): restore backlog poller startup in events stream
* refactor(web): keep project-utils helpers internal
* chore: retrigger bugbot evaluation
* chore: retrigger stuck bugbot check
* fix: address latest bugbot findings for dashboard events
* test(web): add dashboard bugbot regression coverage
* refactor(web): simplify projectId selection in dashboard props
* fix(web): derive selected project name from project filter
* refactor(web): initialize dashboard defaults before service load
* fix(web): satisfy lint in dashboard page error path
* fix: preserve PR number in recovery and dedupe validation utilities
Bugbot #2908822306: Use parsePrFromUrl utility to correctly extract
PR number from URL instead of defaulting to 0. Applied to both
recovery/actions.ts and session-manager.ts for consistency.
Bugbot #2908822310: Extract safeJsonParse and validateStatus to
shared utils/validation.ts to eliminate duplication between
recovery/validator.ts and session-manager.ts.
Clean rebuild from origin/main with only recovery-specific changes.
* fix: add PR number fallback and remove unused import
Bugbot #2908822306: Add fallback regex to extract PR number from URL
ending when full GitHub URL pattern doesn't match (e.g., non-GitHub URLs).
Bugbot #2908822310: Remove unused SessionStatus import from session-manager.ts
(now imported from utils/validation.ts).
Tests: 406 passed, typecheck clean.
* fix(core): harden recovery action selection and escalation
* fix(core): preserve recovered agent summary metadata
* fix(core): reuse canonical PR type in URL parser
Avoid shadowing the core PRInfo type in the recovery URL parser while keeping the non-GitHub trailing-number fallback covered by tests.
* fix(core): align recovery metadata and session reconstruction
Persist restored timestamps under the canonical metadata key, share
session reconstruction logic between recovery and session loading, and
log the real escalation reason when recovery aborts on retry limits.
* fix(core): keep dry-run escalation reasons accurate
Use the assessment's actual escalation reason in dry-run results so preview output matches real execution behavior for partial-session escalations.
* fix(core): dedupe recovery scanning and honor custom log path
Reuse metadata listing rules in scanner to avoid duplicated session ID filters,
and preserve user-supplied recovery logPath in recovery manager APIs.
* fix(core): align dry-run recovery behavior with real actions
Compute recovery escalation decisions before dry-run returns and route
single-session dry runs through executeAction so action-specific fields
(reason/manual-intervention) are preserved.
* fix(core): derive dry-run recovery report from action execution
Run dry-run recovery classification through executeAction so report actions
match real execution logic, including max-attempt escalation decisions.
* feat: wire lifecycle manager, backlog auto-claim, and dashboard overhaul
- Start LifecycleManager in dashboard server (30s polling) so reactions
actually fire: CI failures, review comments, merge conflicts are now
auto-forwarded to agents
- Add backlog auto-claim poller (60s interval) that watches for issues
labeled `agent:backlog` and auto-spawns agent sessions up to max
concurrent limit (5)
- Add tabbed dashboard UI: Board (kanban), Backlog (issue queue), PRs
- Add issue creation form in dashboard — creates GitHub issues with
`agent:backlog` label for immediate agent pickup
- Add API routes: /api/backlog, /api/issues, /api/setup-labels
- Pass notifier config through plugin registry (slack webhook fix)
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* feat: add task decomposition layer (classify → decompose → recurse)
Adds LLM-driven recursive task decomposition upstream of session spawning.
Complex issues are broken into atomic subtasks before agents start working.
Each agent receives lineage context (where it fits in the hierarchy) and
sibling awareness (what parallel agents are doing).
Core changes:
- New decomposer module (core/src/decomposer.ts) — classify, decompose,
plan tree, lineage formatting, using Claude API
- Extended SessionSpawnConfig with lineage/siblings fields
- Prompt builder Layer 4: decomposition context (hierarchy + siblings)
- ProjectConfig.decomposer config section with Zod validation
- Tracker plugin: added removeLabels support for label management
CLI:
- `ao spawn <project> <issue> --decompose` flag
- `--max-depth <n>` option for decomposition depth
- Spawns multiple sessions with lineage context for composite tasks
Backlog poller:
- Respects project.decomposer.enabled for auto-decomposition
- Posts plan as issue comment when requireApproval=true
- Auto-spawns subtasks with lineage when requireApproval=false
Config example:
projects:
my-app:
decomposer:
enabled: true
maxDepth: 3
requireApproval: true
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* feat: add verification gate — issues stay open until human confirms fix
PR merge no longer auto-closes GitHub issues. Instead:
1. On PR merge: issue labeled `merged-unverified`, stays open
2. Human checks staging, then runs `ao verify <issue>` to close
3. Or `ao verify <issue> --fail` to flag verification failure
Changes:
- services.ts: labelIssuesForVerification() replaces closeIssuesForMergedSessions()
- New CLI command: `ao verify` (verify/fail/list modes)
- New API route: GET/POST /api/verify
- Dashboard: new Verify tab with one-click verify/fail buttons
- ao status: shows count of issues awaiting verification
- Idle session detection + auto-nudge reaction
- Use TERMINAL_STATUSES in batch-spawn dedup check
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* fix: rename decomposerConfig to avoid variable shadowing
Addresses Bugbot medium severity issue where inner variable
shadowed outer from getServices().
* fix: update pnpm-lock.yaml for new @anthropic-ai/sdk dependency
* fix: resolve remaining merge conflicts and syntax errors
- Remove leftover conflict markers in types.ts
- Remove orphaned code in services.ts
- Fix semicolon to comma in config.ts
- Remove unused import in verify.ts
* fix: address final Bugbot issues
- requireApproval path now exits early with continue to prevent
fall-through to in-progress label and session spawned comment
- remove packages/core/package-lock.json (pnpm workspace should only
use root pnpm-lock.yaml)
* fix: idle sessions now transition back to working
When agent resumes activity after being idle, the status correctly
transitions to 'working' instead of remaining stuck in 'idle' state.
* fix(backlog): remove agent:backlog label when claiming issues
When claiming issues from the backlog, the poller now removes the
agent:backlog label in addition to adding agent:in-progress. This
prevents duplicate work if all spawned sessions reach terminal status
and the poller rediscovers the issue.
* fix(test): use Set for TERMINAL_STATUSES mock
The mock for TERMINAL_STATUSES was an array, but the real export is a
ReadonlySet. Changed to use a Set so tests with non-empty sessions won't
crash when calling .has().
* fix(web): resolve backlog/dashboard regressions after branch sync
* fix(web): align dashboard events hook and SSE test mocks
* fix(notifier-openclaw): apply exponential delay from retry index
* fix(integration-tests): align openclaw retry delay expectation
* fix(web): keep dashboard header stats in sync
* fix(openclaw): keep first retry at base delay
---------
Co-authored-by: Agent <agent@example.com>
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
Co-authored-by: Harsh <harsh@Ubuntu-24-Forrest.lan>
Co-authored-by: Harsh <harsh@example.com>
* fix(core): enforce single-owner PR claim consolidation
* refactor: remove dead `takeover` option from claimPR
Since PR consolidation is now automatic (single-owner enforcement),
the `--takeover` flag became dead code. Users passing it got no
error but it had zero effect.
This commit:
- Removes takeover from ClaimPROptions interface
- Removes --takeover flag from spawn and session CLI commands
- Updates orchestrator-prompt.ts examples
- Updates tests to reflect automatic consolidation
Tests: ao-core 403 passing, ao-cli 189 passing (spawn+session)
* fix: remove stale --takeover from Quick Start example
Remove remaining --takeover reference in orchestrator prompt Quick Start section.
* feat(core): document and test asymmetric PR ownership model
- Add JSDoc to claimPR documenting RULE A (exclusive PR->Agent) and
RULE B (Agent->Many PRs) ownership contract
- Add tests for:
- Same session claiming multiple PRs sequentially (RULE B)
- Idempotent re-claim by same owner
- Stale/dead prior owner handoff
- Exclusive PR ownership enforcement (RULE A)
139 tests passing
---------
Co-authored-by: Harsh <harsh@Ubuntu-24-Forrest.lan>
suraj-markup
Joakim Sigvardt
Harsh Batheja
Andrés Kaminker
Jayesh Sharma
Harsh
prateek