* 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>
* fix: pause workers on model limits and stabilize session visibility
Detect model limit exhaustion, pause project worker operations until reset, and expose pause state in dashboard/API. Also harden killed-session cleanup and SSE session reconciliation so sessions do not appear ghost-active or disappear until reload.
* fix: satisfy lint in rate-limit pause probe
* fix: address bugbot feedback for pause handling
* fix(lifecycle): prevent infinite re-pause loop for duration-based rate limits
Duration-based rate limits (e.g., 'usage limit reached for N hours') were
causing infinite re-pause loops because they always calculate reset time as
Date.now() + duration, which extends the pause on every poll cycle if the
message remains in terminal output.
Now checks for existing active pause before setting a new one:
- Skips override if same session already has active pause
- Preserves longer pauses from other sessions
Fixes infinite loop described in PR #367 review comment.
* fix(core): export global pause constants to prevent duplication
Export GLOBAL_PAUSE_*_KEY constants and parsePauseUntil utility from
@composio/ao-core so web package can import them instead of hardcoding.
This prevents silent breakage if key values ever change - now there's
a single source of truth.
Addresses review comment on PR #367.
* fix(web): globalPause as first-class state in SSE event flow
globalPause is now part of the same reducer/event flow as sessions,
not derived from provider-specific output text in the UI.
Changes:
- useSessionEvents: manage globalPause alongside sessions in reducer state
- Dashboard: consume globalPause from hook instead of SSR-only prop
- types: re-export GlobalPauseState from shared lib (provider-agnostic contract)
- Tests: 15 new tests proving banner appears/disappears from state updates
alone, regardless of agent model/plugin (Claude Code, OpenCode, Codex)
Design requirements satisfied:
- First-class state in same reducer/event flow as sessions
- Key names sourced from shared core contract via export/import
- Provider-neutral: no Anthropic/OpenAI string coupling in control logic
- State-driven: banner visibility from reducer state updates via SSE
Addresses Bugbot finding: Dashboard pause banner never updates after
initial render (eba24a0b-9e4c-47e3-91c9-7d10be01e3cf)
* fix: remove unused import in test file
* fix(cli): consistent purge default for session kill and stop commands
The kill method's default changed from opt-in (=== true) to opt-out (!== false).
Both session kill and stop commands now use the same logic:
purgeOpenCode = opts.purgeSession === true ? true : opts.keepSession !== true
This ensures consistent behavior across all kill paths.
Adds --keep-session flag to both commands.
Adds regression tests for provider-agnostic behavior verified.
Addresses Bugbot finding: orchestrator start cleanup inconsistent
with new purge default (2bc2535f-b2d1-4f64-96d6-150f97ed8564)
* fix: capture exact OpenCode session ID from JSON stream to prevent orphan sessions
- Primary: Extract session_id from opencode run --format json step_start event
- Fallback: Title-based match with newest-first sorting for delayed visibility
- Core: Add atomic reserveSessionId check in spawnOrchestrator to prevent race conditions
- Prevents orphan sessions when multiple spawns use same title or delayed discovery
(cherry picked from commit 42cc0cfa1a)
* fix: capture OpenCode session id from stream output
(cherry picked from commit 42b3bf3ba6)
* fix: respawn orchestrators when stale metadata is left behind
(cherry picked from commit e519628017)
* fix: align respawn guard and opencode test expectation
* fix: remove unused helper from opencode launch path
* fix: remove unused function and align tests with session capture format
- Remove unused buildSessionLookupScript function from opencode agent
- Update integration tests to expect --format json flag in launch commands
- Fix assertions for exec opencode --session wrapper format
* fix: address Bugbot findings on PR #366
- Fix orphaned runtime leak when reuse strategy finds alive runtime but
get() returns null (now destroys the orphaned runtime)
- Restore session ID format validation in fallback script with
isValidId regex check
- Add regression tests for both fixes
* fix: address additional Bugbot findings on PR #366
- Add timestamp helper to fallback sort to avoid NaN from invalid dates
- Add session ID type/format validation to primary capture script
- Add tests for both robustness improvements
* fix: address bugbot follow-ups in send and opencode discovery
* fix(test): update stale integration test expectation for opencode bootstrap
The getLaunchCommand implementation now uses a robust bootstrap pattern
that captures the session ID between 'opencode run' and 'exec opencode --session'.
Updated test to check both parts separately instead of expecting a contiguous
string that no longer exists.
* fix: avoid NaN in sort comparator when both timestamps are missing
The comparator (b.updatedAt ?? -Infinity) - (a.updatedAt ?? -Infinity)
produces NaN when both timestamps are missing because -Infinity - (-Infinity)
is NaN in IEEE 754. A comparator returning NaN violates ECMA-262's
'consistent comparison function' requirement, making sort results
implementation-defined.
Fixed by adding equality check before subtraction:
- If both timestamps are equal (including both -Infinity), return 0
- Otherwise return the difference
* feat: add PR claim flow for agent sessions
* feat: support PR claim during spawn
* fix: address PR review feedback
* feat: add lifecycle worker automation
* fix: prevent duplicate messages on unconfirmed delivery and deduplicate review prompt
sendWithConfirmation now treats unconfirmed delivery as a soft success
since the message was already sent, preventing the dispatch hash from
staying stale and causing duplicate sends on the next poll cycle.
review-check command now sources its prompt from the lifecycle reaction
config instead of hardcoding it, keeping both paths aligned.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* fix: pass AO_CONFIG_PATH to spawned lifecycle worker and log duplicate-worker early exit
The spawned lifecycle worker now receives AO_CONFIG_PATH in its
environment so it finds the correct config regardless of CWD. Also
added a log message when exiting early due to an existing worker.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* fix: prevent lifecycle worker from clearing metadata on SCM fetch failures
SCM methods (getPendingComments, getAutomatedComments) silently returned []
on error, causing maybeDispatchReviewBacklog to treat fetch failures as
"no comments" and clear all tracking metadata every poll cycle. The worker
appeared to do nothing because it kept resetting its own state.
- SCM methods now propagate errors instead of returning []
- maybeDispatchReviewBacklog distinguishes null (fetch failed, skip) from
[] (confirmed empty, safe to clear)
- pollAll() logs errors instead of silently swallowing them
- Added heartbeat logging and stdout flush before process.exit
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* fix: add debug breadcrumbs when review comment fetch fails
Logs a console.debug message when getPendingComments or
getAutomatedComments fails, making it clear the lifecycle loop is
preserving metadata due to a fetch failure rather than genuinely
having no comments.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* fix: scope lifecycle worker polling to its project and add missing test
pollAll() now passes the worker's projectId to sessionManager.list(),
so each per-project lifecycle worker only polls its own sessions. This
prevents duplicate SCM API calls and race conditions in multi-project
configs.
Also fixed misleading test name and added a test verifying that
--no-dashboard alone still starts the lifecycle worker.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* fix: remove dead confirmation check and respect project-level reaction overrides
Removed the unreachable "could not be confirmed" guard from the retry
logic since sendWithConfirmation now returns silently on unconfirmed
delivery.
review-check now resolves the prompt per-session by checking
project-level reaction overrides before falling back to the global
config, matching lifecycle worker behavior.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* fix: close TOCTOU race in lifecycle worker spawn and unexport getRegistry
Write the child PID from the parent immediately after spawn, closing
the window where a concurrent ensureLifecycleWorker could pass the
"not running" check and spawn a duplicate worker.
Also removed the unnecessary export on getRegistry since it has no
external consumers.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* fix: always include ao base prompt on spawn
* fix: clear heartbeat on shutdown and add initial delay to confirmation loop
Clear the heartbeat interval in the shutdown handler to prevent it
firing during the stream-flush window after lifecycle.stop().
Move the sleep in sendWithConfirmation to before each check (including
the first), so the runtime has time to reflect the message before
the first confirmation attempt.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* fix: resolve lint errors in lifecycle and session manager
- Replace dynamic delete with object reconstruction in lifecycle-manager
- Add { cause } to re-thrown errors in session-manager for preserve-caught-error rule
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
* feat: add `ao start <url>` one-command project onboarding
When `ao start` receives a repo URL instead of a project ID, it now:
1. Parses the URL (supports GitHub, GitLab, Bitbucket — HTTPS and SSH)
2. Clones the repo (or reuses if already present with matching remote)
3. Auto-generates agent-orchestrator.yaml with sensible defaults:
- SCM/tracker plugins inferred from URL host
- Default branch detected from local refs
- Project type detected (language, package manager)
- Post-create install commands set based on package manager
4. Starts the orchestrator + dashboard as usual
New core module `config-generator.ts` handles URL parsing, SCM detection,
project info detection, and config generation. All logic is in core (not
CLI) for reusability. 36 unit tests cover URL parsing, SCM detection,
default branch detection, project info, config generation, and clone
target resolution.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* fix: address bugbot review feedback
1. Non-JS postCreate fix: Only set postCreate install commands for JS
package managers (pnpm/yarn/bun/npm). Rust/Go/Python projects no
longer get an incorrect "npm install" command.
2. Deduplicate startup logic: Extract shared `runStartup()` helper used
by both URL-mode and normal-mode start flows. Eliminates ~100 lines
of duplicated dashboard+orchestrator startup code.
3. SSH URL matching: Normalize SSH URLs to HTTPS format in
`isRepoAlreadyCloned()` so repos cloned via SSH
(git@github.com:owner/repo) are correctly detected as matching.
4. SCM/tracker always explicit: Always set scm and tracker fields in
generated config so `applyProjectDefaults()` doesn't silently
override with github defaults for non-GitHub repos.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* fix: sanitize repo names for project IDs and session prefixes
Address remaining bugbot comments:
- Add sanitizeProjectId() to handle dots/special chars in repo names
(e.g. "my.app" → "my-app" instead of failing Zod validation)
- Preserve original case for generateSessionPrefix() so CamelCase
detection works (e.g. "DevOS" → prefix "dos", not "dev")
- Strip invalid chars before prefix generation to prevent dots
leaking into sessionPrefix
Also update README and SETUP docs with `ao start <url>` quick
onboarding flow.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* feat: auto-open browser to orchestrator page on `ao start`
Opens the orchestrator session page (/sessions/{id}) instead of the
root dashboard, since the Kanban board is empty on first startup
with no worker sessions yet.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* fix: replace fixed 3s delay with port polling for browser open
Poll the dashboard port via TCP connection attempts (300ms intervals,
30s timeout) instead of a hardcoded setTimeout. Opens the browser only
once the server is actually accepting connections — deterministic
regardless of how long Next.js takes to compile.
Applied to both `ao start` and `ao dashboard` commands.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* test: add CLI tests for start/stop commands
12 new tests covering:
- Project resolution: single project, explicit arg, missing project,
multi-project ambiguity, empty config
- URL argument: reuse existing clone, git clone flow, existing config
detection, clone failure error handling
- Port polling: waitForPortAndOpen polls isPortAvailable before opening
browser (proves deterministic behavior vs fixed delay)
- Stop command: session kill + dashboard stop, graceful missing session
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* refactor: deduplicate waitForPortAndOpen into shared utility
Move waitForPortAndOpen to lib/web-dir.ts (alongside isPortAvailable)
so both start.ts and dashboard.ts share a single cancellation-aware
implementation. start.ts now uses AbortSignal like dashboard.ts —
polling stops immediately if the dashboard process exits early.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
* fix: use JSONL-based activity detection in lifecycle manager
Replace terminal-output-based detectActivity() with JSONL-based
getActivityState() as the primary activity detection in determineStatus().
Falls back to terminal parsing when getActivityState returns null.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* fix: address bugbot review comments on lifecycle JSONL detection
- Pass config.readyThresholdMs to getActivityState() for consistency
- Fix idle-but-running test to exercise fallback path (getActivityState → null)
- Deduplicate identical exited tests; replace duplicate with fallback-path test
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
- BUG-28: Verify no .tmp files left behind after writeMetadata/updateMetadata,
and rapid sequential writes produce correct final state
- BUG-29: Verify restoredAt roundtrips through writeMetadata/readMetadata,
persists in key=value file, and can be set via updateMetadata
- BUG-12: Verify computeStats counts active/idle/ready as working,
excludes exited and null activity
- BUG-13: Verify errored/needs_input/stuck sessions with activity=active
land in respond zone, not working
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
The session reconstruction path (readMetadataRaw → metadataToSession)
was not mapping the restoredAt field, so session.restoredAt was always
undefined after a server restart despite the value existing in the
metadata file.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
- BUG-28: Use atomic write-then-rename for metadata files to prevent
race condition data loss between concurrent TS and bash writers
- BUG-29: Read and write restoredAt field in metadata so it persists
across server restarts
- BUG-12: Count all non-exited sessions (idle, ready, active) as
"working" instead of only active ones
- BUG-13: Check status-based error conditions (errored, needs_input,
stuck) before activity-based checks in getAttentionLevel() so errored
sessions immediately appear in the Respond Kanban zone
Closes#238
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* fix: handle "invalid issue format" error for ad-hoc spawn
gh CLI returns "invalid issue format" when the issue argument is free-text
rather than a valid issue number/URL. This error was not matched by
isIssueNotFoundError, causing ad-hoc spawns to fail instead of gracefully
falling through to ad-hoc mode.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* fix: sanitize ad-hoc issue text into valid git branch names
When tracker lookup fails (ad-hoc mode), the raw free-text was used
directly as a branch name, causing git to reject it. Now:
- Only use tracker.branchName() when the issue was actually resolved
- Slugify ad-hoc text (lowercase, replace non-alphanumeric with hyphens,
trim, cap at 60 chars) to produce valid branch names
e.g. "fix the cold start issue" → feat/fix-the-cold-start-issue
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* fix: preserve casing for branch-safe issue IDs, only slugify free-text
The slug sanitization was lowercasing all issue IDs without a resolved
issue (e.g. INT-9999 → int-9999). Now only applies sanitization when
the issueId contains characters invalid for git branch names.
Adds tests for slug sanitization, casing preservation, truncation,
empty-slug fallback, and isIssueNotFoundError patterns.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* test: assert tracker.branchName not called for unresolved issues
Adds assertion to existing test that tracker.branchName is NOT called
when the issue wasn't found. Adds end-to-end test for "invalid issue
format" error flowing through spawn with free-text slugification.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* fix: reject '..' in branch-safe check, verify generatePrompt skipped
The isBranchSafe regex allowed '..' which is invalid in git refs.
Also asserts that tracker.generatePrompt is not called when the
issue wasn't resolved, and adds a test for the '..' edge case.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* fix: trim dashes after truncation, not before
Bugbot correctly noted that .slice(0, 60) after dash-trim can
reintroduce a trailing dash. Reorder so trim runs after slice.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
Co-authored-by: Prateek <karnalprateek@gmail.com>
* docs: add demo video and article links to README
Add tweet screenshot for the video demo prominently after the intro,
and link to the full article thread. Replaces the TODO placeholder.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* docs: use article screenshot for README article link
Replace text-only article link with clickable screenshot showing
the article title, preview image, and engagement stats.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* docs: replace demo video screenshot with higher quality version
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* Default dangerouslySkipPermissions to true for autonomous agent operation
Spawned agents need to run CLI commands without permission prompts. Changed
the agentConfig.permissions schema default from undefined to "skip" so
--dangerously-skip-permissions is included by default. The orchestrator
session is hardcoded to "skip" regardless of config since it must always
run ao CLI commands autonomously.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* Default agentConfig to {} so permissions default propagates
When agentConfig is absent from YAML, .optional() leaves it undefined,
so project.agentConfig?.permissions evaluates to undefined instead of
"skip". Change to .default({}) so Zod always constructs the object and
applies the inner permissions default.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
* fix: skip orchestrator sessions during cleanup
The cleanup command could kill the orchestrator's own tmux session
(named {prefix}-orchestrator) because it has no PR or issue, making
it eligible for the "dead runtime" cleanup heuristic.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* fix: add role metadata for orchestrator session identification
Store role=orchestrator in metadata during spawnOrchestrator() and
check it in cleanup() for explicit identification. Keeps the name
fallback (endsWith -orchestrator) for pre-existing sessions.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* fix: preserve role in restore path, add integration test
- restore() now preserves the role field when recreating metadata
from archive (previously dropped, breaking role-based detection)
- Add integration test: orchestrator skipped while sibling session
with same closed issue gets killed (verifies real tracker plugin)
- Verified: both unit and integration tests fail without the guard
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* fix: persist role field in metadata, isolate role test from name fallback
Bugbot caught two real issues:
- writeMetadata() and readMetadata() never serialized the role field,
so role=orchestrator was silently dropped on disk
- The role-based test used "app-orchestrator" as session name, so the
name fallback caught it — role check was never actually exercised
Fix: add role to metadata read/write, rename test session to "app-99"
so only the role metadata path can protect it.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
* fix: keep Claude Code interactive after initial prompt
Claude Code's -p flag runs in one-shot mode (exits after responding),
which prevents follow-up messages via `ao send`. Instead, launch Claude
interactively and deliver the initial prompt post-launch via
runtime.sendMessage().
Adds `promptDelivery` property to the Agent interface so each agent
plugin can declare whether prompts should be inlined in the launch
command or sent after the agent starts.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* fix: make post-launch prompt delivery non-fatal and add test coverage
- Move sendMessage call outside the try/catch that destroys the session.
A prompt delivery failure should not kill a running agent — user can
retry with `ao send`.
- Add tests: no-prompt + post-launch agent, sendMessage failure resilience,
5s delay verification, systemPrompt/systemPromptFile alongside omitted -p.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* test: add integration test for prompt delivery (proves bug and fix)
Two real-Claude integration tests that contrast:
1. `-p` mode: Claude exits after responding (the bug)
2. Interactive + sendMessage: Claude stays alive, follow-up works (the fix)
Runs in CI with ANTHROPIC_API_KEY. Skips when prerequisites missing.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* fix(test): skip interactive test without auth, improve TUI readiness detection
The integration test failed in CI because interactive Claude requires
full login auth (not just ANTHROPIC_API_KEY). Skip the interactive suite
when `claude auth status` reports not logged in.
Also fix local flakiness: replace blind 5s sleep with polling for
Claude's TUI prompt character (❯) before sending the first message,
and increase scrollback capture from 200 to 500 lines.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* fix(test): skip interactive test in CI, fix TUI readiness detection
The interactive test ran in CI despite hasInteractiveAuth() — Claude
reports logged in when ANTHROPIC_API_KEY is set, but interactive mode
requires OAuth. Use `!process.env.CI` as the skip condition instead.
Also fix waitForTuiReady false positive: the OAuth screen's
"Paste code here if prompted >" matched the `>` regex. Now checks
the last non-empty line for Claude's specific ❯ prompt character,
and bails early if the OAuth/login screen is detected.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
readMetadata() was not returning the `agent` field even though
writeMetadata() persisted it. This meant typed consumers got
undefined for session.agent while raw readers worked fine.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
When --agent override is used at spawn time, the agent name was not stored
in session metadata. The lifecycle manager and session enrichment always
resolved the agent from project config defaults, causing mismatched process
detection (e.g. looking for "claude" instead of "codex") and incorrect
"killed" status on the first poll cycle.
- Add `agent` field to SessionMetadata type and writeMetadata
- Store `plugins.agent.name` in metadata during spawn
- Pass stored agent name to resolvePlugins in list/get/restore paths
- Read `session.metadata["agent"]` in lifecycle manager's determineStatus
- Add tests for metadata persistence with and without override
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
- Session manager: agent override uses correct agent, unknown agent throws, default used without override
- CLI spawn: --agent flag passthrough with and without issue ID
- Plugin registry: multiple agent plugins registered via loadBuiltins importFn
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Allows starting sessions with a different agent without changing config:
ao spawn ao --agent codex
ao spawn ao --agent codex INT-1234
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
The static file is fully superseded by the auto-generated orchestrator
prompt in packages/core/src/orchestrator-prompt.ts, which gets injected
dynamically via `ao start`. Also clean up stale references in comments
and architecture docs.
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
* docs: add design research artifacts — briefs, token reference, screenshots
Comprehensive design research package for the ao dashboard, session
detail page, and orchestrator terminal. Produced via competitive analysis
of 14 products (Linear, Vercel, Railway, Fly.io, Inngest, WandB, LangSmith,
Supabase, and more) + Playwright CSS extraction from live sites + full
codebase audit.
Artifacts:
- docs/design/design-brief.md Main design brief (v2, Playwright-updated)
- docs/design/session-detail-design-brief.md /sessions/[id] design spec
- docs/design/orchestrator-terminal-design-brief.md Orchestrator page spec
- docs/design/token-reference.css Drop-in CSS replacement for globals.css
- docs/design/competitive-analysis-raw.md Raw research notes, all 14 sites
- docs/design/design-brief-v1.md Original text-only brief (pre-Playwright)
- docs/design/README.md Index + research methods summary
- docs/design/screenshots/linear-homepage.png Playwright-captured screenshot
- docs/design/screenshots/railway-homepage.png Playwright-captured screenshot
Key findings:
- Linear CSS token values verified via Playwright (body bg #08090A, accent
#7070FF, Berkeley Mono monospace, type scale, radius, transitions)
- Recommended palette: #0C0C11 base (blue-cast dark vs current GitHub #0d1117)
- Highest-impact change: load Inter Variable via next/font/google
- Orchestrator terminal needs visual differentiation (violet accent, status strip)
- token-reference.css is ready to drop into packages/web/src/app/globals.css
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
* feat(web): redesign dashboard, session detail, and orchestrator terminal
Implements a cohesive dense dark-mode design system across all three main views.
- New color token palette: #0c0c11 base, #141419 surface, #1c1c25 elevated
- Accent blue #5b7ef8, status semantics (ready/error/attention/working/idle/done)
- Violet accent #a371f7 reserved for orchestrator
- Inter Variable + JetBrains Mono loaded via next/font with CSS variables
- activity-pulse keyframe for live agent dots
- AttentionZone header: dot + label + flex divider + count pill + chevron
- Sessions laid out in responsive 1→2→3 column grid
- Solid green merge button (translateY hover), no confirm() dialog
- Breadcrumb nav: ← Agent Orchestrator / {session-id} [orchestrator badge]
- CSS 8×8px activity dot with pulse animation replaces emoji labels
- Merge-ready state: green-bordered banner with checkmark icon
- Orchestrator sessions show zone counts strip (merge/respond/review counts)
- xterm.js dark theme (#0a0a0f bg, #d4d4d8 fg, full 16-color ANSI palette)
- variant prop: "agent" (blue cursor) vs "orchestrator" (violet cursor)
- Dynamic height prop instead of fixed 600px; fullscreen toggle with SVG icons
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
* refactor(web): strip rainbow stats, clean header, IBM Plex Sans typography
- Replace Inter with IBM Plex Sans (technical tool aesthetic, distinctive numerics)
- Replace 4-color big-number stats bar with a single compact inline status line
in the header: "35 sessions · 1 working · 9 PRs" — no decorative colors
- Remove the two-tone "Agent (blue) Orchestrator (white)" title — just "Orchestrator"
- Remove ClientTimestamp (useless) — replaced by orchestrator nav link
- Zone headers: colored dot only (semantic), neutral uppercase label, plain count
— removes the rainbow-colored label text that read as a widget template
- Add subtle radial gradient glow at top of page for depth
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
* feat(web): kanban layout, amber accent, full-width, bigger stats
- Switch accent from blue (#5b7ef8) to amber/gold (#d18616) throughout
- Replace grid layout with horizontal Kanban columns for active zones
(merge, respond, review, pending, working), Done stays full-width below
- Remove max-w-[1100px] constraint — full viewport width
- Header stats numbers 20px bold (was 12px), orchestrator link is now a
visible bordered button
- AttentionZone gains variant="column" for Kanban mode (compact header
with count pill, vertical card stack)
- Update all hardcoded rgba(91,126,248,...) in SessionCard to amber
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
* fix(web): layout, alert sizing, column order, button feel
- Kanban column order: working→pending→review→respond→merge
(left = in progress, right = ready to ship)
- Columns use flex-1 min-w-[200px] to fill available width
instead of fixed 260px leaving half the page empty
- Alert badges: inline-flex wrapper prevents stretching to full
row width when wrapping
- Terminal button: add bg-subtle fill so it reads as a button
- PR number (#91): remove opaque pill background, now plain
amber text link — clearly a hyperlink
- Merge PR button: pt-0.5 spacer above the action area
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
* fix(web): don't cache rate-limited partial PR data
When GitHub rate limits fire, enrichSessionPR was caching the
bad partial data (0 additions, CI failing) for 60 seconds, causing
the dashboard to show incorrect data for the full TTL window.
- Skip cache write when majority of API calls failed
- Downgrade console.error → console.warn (this is handled/expected)
The next page refresh will retry live API calls, so data recovers
as soon as the rate limit window resets.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
* feat(web): graceful GitHub API rate limit handling in UI
When the GitHub plugin hits rate limits, the dashboard now:
- Shows a single amber banner: "GitHub API rate limited — PR data
(CI status, review state, sizes) may be stale. Will retry on
next refresh."
- Hides CI badge, review decision, and size pill on PR cards
(they'd show wrong values: +0 -0 XS, CI failing)
- Shows a subtle "⚠ PR data rate limited" note on affected cards
instead of misleading alert badges
- Skips CI/review/conflict-based attention zone classification
for rate-limited PRs (prevents sessions moving to Review due
to phantom "CI failing" from the fallback value)
- Doesn't cache partial rate-limited data so next refresh retries
live API calls as soon as the rate limit window resets
What still works when rate limited:
- Session ID, title, branch, PR number/link
- Session activity status (working/spawning/etc.)
- Merge button if mergeability was already cached
- Restore/terminate/send actions
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
* feat(web): dashboard redesign — glassmorphism, Kanban, rate-limit handling, perf fix
Design:
- Kanban layout: active zones as flex columns (working→pending→review→respond→merge),
Done as full-width grid below
- GitHub dark color palette (main's tokens) with glassmorphic card surfaces
(rgba bg + backdrop-blur) and subtle blue/violet body gradient
- Activity state shown as labeled pill (● active / ● idle etc.) instead of bare dot
- Session card: title on its own row, larger font, inline-flex alert badges (no stretch)
- PR number rendered as plain accent link, not a blue pill badge
- Terminal button has background fill to feel like a button
- Info circle icon replaces alarming warning triangle for rate-limit indicators
- "1 working" → "1 active" in header stats
- PR table constrained to max-w-[900px] and centered
- Orchestrator session no longer uses purple accent
Rate limiting:
- isPRRateLimited() helper; getAttentionLevel() skips PR classification when limited
- Rate-limited banner in Dashboard; suppressed CI/size/review badges in PRStatus
- SessionCard shows subtle "PR data rate limited" indicator; getAlerts() returns []
- serialize.ts: rate-limited enrichment results cached for 5 min (not 60s) to stop
retrying 168 failing API calls every minute
Performance:
- page.tsx: 4s hard timeout on PR enrichment — serves stale data fast instead of
blocking SSR for 75s under rate limiting
- cache.ts: TTLCache.set() accepts optional ttl override for per-entry control
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
* fix: suppress stale size/CI/review in PR table when rate limited
PRTableRow now shows "—" for size, CI, and review columns when GitHub
API is rate limited, matching the card view which already hides these.
Prevents misleading "+0 -0 XS" size and "needs review" labels from the
default fallback values.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
* feat: 3D card effect with depth shadow and top-edge shine
Cards now clearly pop against the dark background:
- Solid gradient bg (rgba(28,36,47) → rgba(18,23,31)) instead of
near-invisible rgba(22,27,34,0.8) surface
- Layered box-shadow: contact shadow + diffuse depth + inset top highlight
that simulates light hitting the card's top edge (the "shine")
- Hover: card lifts 2px with deeper shadow
- Merge-ready: green-tinted bg with green ambient glow + stronger lift on hover
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
* fix: restore text legibility inside session cards
The darker solid card gradient made muted/secondary text nearly
invisible — #484f58 (text-muted) had only ~2:1 contrast on the
new card bg. Override the color tokens locally within .session-card
to GitHub's established dark-mode legibility values:
--color-text-muted: #484f58 → #656d76 (3.8:1 on card bg)
--color-text-secondary: #7d8590 → #8b949e (6.2:1 on card bg)
--color-text-tertiary: #484f58 → #656d76
Scoped to .session-card so the rest of the UI is unchanged.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
* fix: address bugbot comments — fonts, review zone, ActivityDot, orchestrator btn
- layout.tsx: add IBM Plex Sans weight 700 (was missing, font-bold falling
back to 600)
- DirectTerminal.tsx: use "IBM Plex Mono" instead of unloaded "JetBrains Mono"
- SessionDetail.tsx: add review zone to OrchestratorStatusStrip (was omitted,
sessions with CI failures were invisible in the strip)
- ActivityDot.tsx: extract shared component, remove duplicate implementations
in SessionCard.tsx and SessionDetail.tsx
- Dashboard.tsx: redesign orchestrator button with 3D glass style matching
card aesthetic (blue-tinted bg, depth shadow, hover lift)
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
* fix(web): lint — eqeqeq, duplicate import, unused var
- ActivityDot.tsx: != → !== (eqeqeq rule)
- PRStatus.tsx: merge duplicate @/lib/types imports into one
- SessionCard.tsx: remove unused activityIcon import
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
* feat(web): elevate session detail + orchestrator page design
- Nav: glass backdrop-blur effect with chevron back link
- Header: detail-card 3D treatment with left-border accent keyed to activity color
- Meta chips: bordered pill style with subtle bg instead of flat text
- Status tag: pill badge for status instead of plain text
- PR card: detail-card 3D treatment, border-color reflects PR state
- PR merged badge: purple pill instead of gray text
- Unresolved count: red pill badge in section header
- Blockers section: renamed "Issues" → "Blockers"
- Terminal section: colored bar indicator instead of plain label
- Orchestrator status strip: total agent count + per-zone colored pills
- globals.css: add .nav-glass and .detail-card classes
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
* fix(web): fetchZoneCounts parses body.sessions, delayed 2s to avoid contention
The /api/sessions endpoint returns `{ sessions: [...] }` not a bare array.
fetchZoneCounts was treating the whole response object as an array, so
zone counts were always zero on the orchestrator detail page.
Also delays the initial fetchZoneCounts call by 2s so it doesn't contend
with the session fetch on page load (both hit /api/sessions which is slow
when GitHub enrichment is running).
Also includes: Playwright kill-Chrome-for-Testing tip in CLAUDE.md,
toned-down detail-card shadow in globals.css.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
* perf+test(web): cache-first PR enrichment, skip exited sessions, fix component tests
Performance improvements:
- enrichSessionPR() now accepts cacheOnly option and returns boolean
- /api/sessions/[id]: serve from cache immediately, only block on first load
- /api/sessions: skip PR enrichment for EXITED sessions (no longer changing)
- cache: increase default TTL from 60s to 5 minutes
Test fixes (match redesigned SessionCard + AttentionZone):
- "restore session" (header) → "restore"; expanded panel still shows "restore session"
- "merge PR #N" → "Merge PR #N" (capital M)
- "CI status unknown" → "CI unknown"
- "ask to fix CI" / "ask to fix CI" → "ask to fix"
- "terminate session" → "terminate"
- Zone labels: RESPOND/WORKING/DONE → Respond/Working/Done (CSS uppercase is visual only)
- "working" zone no longer collapsed by default; collapse tests now use "done" zone
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
* feat(core): ActivityDetection with timestamp propagation
- Add ActivityDetection interface { state, timestamp? } to types.ts
- Agent getActivityState() returns ActivityDetection | null instead of
ActivityState | null, allowing timestamp from JSONL mtime to propagate
- session-manager updates session.lastActivityAt when detected.timestamp
is more recent — fixes "active 22h ago" showing stale timestamps
- Update all agent plugins (claude-code, aider, codex, opencode) to
return ActivityDetection objects
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
* fix(web): dismissible rate limit banner + 60min rate-limit cache TTL
- Add X dismiss button to GitHub API rate limit banner in Dashboard.tsx
so it can be closed during demos
- Extend rate-limited PR cache TTL from 5min to 60min — GitHub GraphQL
rate limits reset hourly, no point retrying every 5 minutes
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
* fix(web): address Cursor Bugbot review comments on PR #125
- Dashboard StatusLine: active sessions count now uses var(--color-status-working)
(blue) instead of neutral text color, matching the design system semantics
- SessionCard: isReadyToMerge now guards against rate-limited state — a card
with stale cached mergeability data won't show green merge-ready styling
- DirectTerminal: add `variant` to useEffect dependency array (was missing,
causing stale cursor/selection colors if variant changed after mount)
- agent-aider: include `timestamp: chatMtime` in all ActivityDetection returns,
matching the pattern used by agent-claude-code (enables accurate lastActivityAt)
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
* fix(ci): resolve lint, typecheck, and test failures
Lint:
- Remove unused parseJsonlFile function (superseded by parseJsonlFileTail)
- Remove dead lastLogModified stat() call in getSessionInfo (field was
removed from AgentSessionInfo but the filesystem read was left behind)
Typecheck + Tests (ActivityDetection):
- session-manager.test.ts: update mocks to return { state: "active" } /
{ state: "idle" } instead of bare strings — getActivityState() returns
ActivityDetection | null, not ActivityState | null
- integration tests (aider, claude-code, codex, opencode): update imports
from ActivityState → ActivityDetection, variable types, comparisons
(activityState?.state !== "exited"), and assertions (?.state).toBe()
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
* fix: parseJsonlFileTail uses readFile for small files; enrich exited sessions with PRs
- parseJsonlFileTail now calls stat() then readFile() for files smaller than
maxBytes, falling back to open()/handle.read() only for large files. This
fixes the test infrastructure (which mocks readFile but not open) and also
fixes a scope bug where `offset` was declared inside an inner try block but
referenced outside both try blocks.
- Math.max(0, NaN) returns NaN not 0, so size must default to 0 when stat
returns a mock without a size field: `const { size = 0 } = await stat(...)`.
- Update activity-detection.test.ts: getActivityState() now returns
ActivityDetection objects, so tests use (await ...)?.state comparisons.
- Remove stale lastLogModified test (field was removed from AgentSessionInfo).
- Remove EXITED skip guard from api/sessions/route.ts: exited sessions can
still have open, merge-ready PRs that need enrichment on the dashboard.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
* fix: comprehensive code review fixes — tests, timestamps, UI correctness
Address gaps identified in code review of the ActivityDetection PR:
Core / Session Manager:
- Add `timestamp` to all `{ state: "exited" }` returns in all 4 agent plugins
(claude-code, aider, codex, opencode) using consistent `exitedAt = new Date()` pattern
- Add 2 new session-manager tests: timestamp propagation when detection timestamp
is newer, and no-downgrade when detection timestamp is older
- Fix `parseJsonlFileTail` lint error: remove useless `= 0` initializer (value was
always overwritten before use; catch block returns early)
Web package — tests:
- Fix 3 `api-routes.test.ts` failures: `sessionsGET()` needs a Request object since
the route reads `request.url` for `?active=true` query param
- Fix `serialize.test.ts` rate-limit test: spy on `console.warn` (what the code uses)
not `console.error`
- Add 5 `ActivityDot` component tests covering all activity states, unknown states,
null activity, and dotOnly mode
Web package — UI correctness:
- Fix `relativeTime()` in SessionDetail to guard against invalid/empty ISO strings
- Fix timer Map leak: add `timersRef.current.clear()` in cleanup effect after forEach
- Add `encodeURIComponent` to sessionId in message fetch URL
Server — race condition fix:
- Guard `activeSessions.delete` in pty.onExit, ws.on("close"), and ws.on("error")
against stale handlers deleting a newly-registered session with the same ID.
Fixes flaky integration test where afterEach's pty.kill() fired asynchronously
after the next test had already set up a new session with the same session ID.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
* fix(web): narrow PREnrichmentData types to eliminate unsafe casts in serialize
PREnrichmentData.ciStatus and .reviewDecision were typed as string,
requiring unsafe `as` casts when reading from cache into DashboardPR.
Narrow them to the same literal union types used by DashboardPR, making
the casts unnecessary. Also narrow ciChecks[].status to match CoreCICheck.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
---------
Co-authored-by: Claude Sonnet 4.6 <noreply@anthropic.com>
* feat: session title fallback chain — PR title → summary → issue title → branch
Sessions without PRs now always show a meaningful title on the dashboard
instead of just the status text. The fallback chain is:
1. PR title (already worked)
2. Agent summary (now fetched from JSONL via getSessionInfo())
3. Issue title (now fetched via tracker.getIssue())
4. Humanized branch name (e.g., "feat/infer-project-id" → "Infer Project ID")
Key changes:
- Enrich agent summaries by calling getSessionInfo() for sessions
without summaries (local file I/O, not API calls)
- Enrich issue titles via tracker.getIssue() with 5-min TTL cache
- Add humanizeBranch() utility for last-resort branch name display
- Add issueTitle field to DashboardSession type
- Show issue title in expanded detail panel
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* fix: extract humanizeBranch to separate module to avoid client-side timer leaks
Moves humanizeBranch() from serialize.ts to format.ts — a pure utility
module with no side effects. This prevents the client bundle from pulling
in TTLCache instantiations (which create setInterval timers) when
SessionCard.tsx imports the function.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* fix: remove dead re-export of humanizeBranch from serialize.ts
No consumer imports humanizeBranch from serialize — SessionCard imports
directly from format.ts. The re-export was unused surface area.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* fix: add missing first-project fallback in summary enrichment block
Matches the pattern used by all other enrichment blocks in page.tsx
(issue labels, issue titles, PR enrichment) which fall back to the
first configured project when projectId and sessionPrefix both miss.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* feat: smarter title heuristic — skip prompt excerpts, prefer issue titles
The agent summary fallback from extractSummary() often returns truncated
spawn prompts ("You are working on GitHub issue #42: Add auth...") which
make poor titles. The new heuristic detects these prompt excerpts and
prefers the issue title when available.
Updated fallback chain:
PR title → quality summary → issue title → any summary → humanized branch → status
Changes:
- Add looksLikePromptExcerpt() to detect spawn prompt patterns
- Add getSessionTitle() to encapsulate the smart fallback logic
- Expand humanizeBranch() with more prefix patterns (release, hotfix, etc.)
- SessionCard now uses getSessionTitle() instead of inline ?? chain
- Add 25 unit tests covering all functions and edge cases
- Fix missing issueTitle field in serialize.test.ts fixture
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* refactor: extract shared resolveProject() to eliminate duplication
Moves resolveProject() from route.ts into serialize.ts as a shared
export. Both page.tsx and route.ts now use the same function instead
of duplicating the 3-step project resolution logic (projectId →
sessionPrefix → first project fallback) inline.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* feat: replace looksLikePromptExcerpt heuristic with summaryIsFallback metadata
Instead of fragile string matching to detect truncated spawn prompts,
the agent plugin now sets summaryIsFallback: true when the summary is
a first-message fallback rather than a real agent-generated summary.
- Add summaryIsFallback to AgentSessionInfo (core/types.ts)
- extractSummary() returns { summary, isFallback } in claude-code plugin
- Add summaryIsFallback to DashboardSession, propagate in serialize.ts
- Replace looksLikePromptExcerpt() with !session.summaryIsFallback
- Fix .js extension in format.ts import (review feedback)
- Add thorough tests for all layers of propagation
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
* test: add resolveProject and enrichSessionIssueTitle coverage
- resolveProject: 5 tests covering direct match, prefix fallback,
first-project fallback, empty projects, and priority ordering
- enrichSessionIssueTitle: 7 tests covering enrichment, # prefix
stripping, Linear-style labels, skip conditions, error handling,
and cross-call caching
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
* refactor: extract shared enrichSessionsMetadata, fix session detail route
- Extract duplicated enrichment orchestration (issue labels, agent
summaries, issue titles) from page.tsx and route.ts into a single
enrichSessionsMetadata() function in serialize.ts
- Fix /api/sessions/[id] route: was missing agent summary and issue
title enrichment, and had hand-rolled project resolution instead of
using resolveProject() (also missing the first-project fallback)
- Optimize: resolve projects once per session instead of 3x
- Add 8 tests for enrichSessionsMetadata covering full pipeline, skip
conditions, missing plugins, no-tracker config, multiple sessions,
and default agent fallback
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
* fix: remove dead getAgent and getTracker exports from services.ts
These helpers became unused when enrichSessionsMetadata was extracted
to serialize.ts with inline registry.get() calls (to avoid coupling
serialize.ts to services.ts and pulling plugin packages into webpack).
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
All docs now mention that the dashboard port (default 3000) is
configurable via `port:` in agent-orchestrator.yaml. Fixes incorrect
port 9847 references in SETUP.md, adds multi-project port guidance,
and documents terminal port auto-detection.
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
* feat: make terminal server ports configurable to fix multi-dashboard EADDRINUSE
When multiple ao dashboards run simultaneously (e.g., ao on port 3000,
integrator on port 3002), both try to start terminal WebSocket servers
on hardcoded ports 3001/3003, causing EADDRINUSE. Add terminalPort and
directTerminalPort to config schema so each instance can use unique ports.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* fix: use optional() instead of default() for terminal port schema
Zod .default() always fills in the value, making config.terminalPort
never undefined and the env var fallback in buildDashboardEnv dead code.
Switch to .optional() so the priority chain works correctly:
config value > TERMINAL_PORT env var > hardcoded default.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* fix: move terminal server defaults from 3001/3003 to 14800/14801
The 3000-3009 range is the most contested in dev tooling (Next.js
auto-increments, BrowserSync, Grafana, Rails, Express all default to
3000+). Port 14800-14899 has zero IANA registrations, zero known dev
tool conflicts, and is safely below OS ephemeral ranges.
Updated all hardcoded fallbacks, .env.local.example, docker-compose
port mappings, and documentation.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* feat: auto-detect available terminal ports for zero-config multi-dashboard
When no terminal ports are configured (no config, no env vars),
buildDashboardEnv now probes for an available port pair starting at
14800. The second `ao start` automatically gets 14802/14803 (or the
next free pair), eliminating EADDRINUSE without any user configuration.
Port detection scans in steps of 2 to keep the pair consecutive.
Explicit config/env values bypass auto-detection entirely.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* fix: update onboarding test to use new default terminal port (14801)
The onboarding integration test had port 3003 hardcoded for the
WebSocket health check. Updated to read from DIRECT_TERMINAL_PORT
env var with 14801 as the default, matching the new port defaults.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
* fix: restore archived sessions that were killed/cleaned up
restore() only searched active metadata files, so sessions that had
been killed (and archived to the archive/ subdirectory) could not be
restored. Now restore() falls back to the archive directory, picks the
latest archived version, and recreates the active metadata file before
proceeding.
- Add readArchivedMetadataRaw() to metadata.ts
- Update restore() to search archive as fallback
- Add 4 unit tests for readArchivedMetadataRaw
- Add 2 integration tests for archive restore in session-manager
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* fix: prevent archive prefix collision for underscore-containing session IDs
readArchivedMetadataRaw used startsWith(sessionId + "_") which would
cause "app" to false-match archive files belonging to "app_v2". Now
verifies the character after the prefix is a digit (start of ISO
timestamp) to disambiguate.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
Two bugbot follow-ups from PR #104:
1. Destroy old runtime handle before creating new one in restore().
When an agent crashes, the tmux session survives. Creating a new
tmux session with the same name fails. Now we destroy the old
handle first (best-effort, non-blocking).
2. Wrap git clone in try-catch in workspace-clone restore(). On clone
failure (network error, disk full), clean up the partial directory
so future restore attempts aren't blocked.
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
* feat: implement session restore for crashed/exited agents
Add true in-place session restore: same session ID, same worktree, same
metadata — optionally resuming the Claude Code conversation via --resume.
Core changes:
- Add TERMINAL_STATUSES, TERMINAL_ACTIVITIES, NON_RESTORABLE_STATUSES sets
and isTerminalSession/isRestorable helpers to types.ts
- Add SessionNotRestorableError and WorkspaceMissingError error classes
- Add restore() to SessionManager with 9-step flow: find metadata →
validate restorability → check/recreate workspace → get restore or
launch command → create runtime → update metadata
- Add restoredAt field to Session and SessionMetadata
Plugin extensions:
- workspace-worktree: exists() + restore() (git worktree prune + re-add)
- workspace-clone: exists() + restore() (git clone + checkout)
- scm-github: branchExists() via git rev-parse
- agent-claude-code: getRestoreCommand() finds latest JSONL session file
and builds claude --resume command
CLI + Web:
- Add `ao session restore <id>` subcommand
- Web restore API route uses sessionManager.restore() instead of spawn()
- SessionCard uses centralized TERMINAL_STATUSES/TERMINAL_ACTIVITIES
- Web types re-export core constants with sync tests
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* fix: add "merged" to TERMINAL_STATUSES
The old inline isTerminal check included "merged" but when refactored
to use the TERMINAL_STATUSES set, "merged" was omitted. This caused
merged sessions (whose activity is not "exited") to incorrectly show
the "terminal" link and "terminate session" button.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* fix: enrich runtime state before restore check, remove dead branchExists
- Add enrichSessionWithRuntimeState() call before isRestorable() in
restore() so crashed sessions (status "working", agent exited) are
correctly detected as terminal and eligible for restore.
- Remove dead branchExists from SCM interface and scm-github plugin
(defined but never called anywhere in the codebase).
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* fix: allow restore of crashed working sessions
Remove "working" from NON_RESTORABLE_STATUSES. The isTerminalSession()
gate already prevents restoring truly active sessions (activity is not
"exited"). This fix allows crashed agents (status "working", activity
"exited") to be restored, aligning core behavior with the UI which
already shows the restore button for this case.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* fix: distinguish missing branch from missing restore support
Split the compound condition so workspace restore gives an accurate
error message when branch metadata is null ("branch metadata is
missing") vs when the workspace plugin lacks a restore method.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
* feat: first-class orchestrator session + file-based system prompt
Make the orchestrator a first-class managed session that flows through
the same SessionManager pipeline as worker sessions, and fix a blocking
bug where long system prompts get truncated by tmux/zsh.
Changes:
- Add OrchestratorSpawnConfig type and spawnOrchestrator() to
SessionManager interface
- Implement spawnOrchestrator() in session-manager.ts: proper
hash-based tmuxName, runtimeHandle, plugin lifecycle — no workspace
creation (uses project.path directly)
- Refactor `ao start` to use SessionManager.spawnOrchestrator()
instead of manual tmux calls + metadata writes (~80 lines removed)
- Refactor `ao stop` to use SessionManager.kill() instead of manual
tmux kill + metadata delete
- Update `ao init` next steps: guide users to `ao start` before
`ao spawn`
- Add systemPromptFile to AgentLaunchConfig for file-based system
prompts (avoids tmux truncation of 2000+ char inline prompts)
- Update agent-claude-code, agent-codex, agent-aider plugins to use
shell command substitution "$(cat '/path')" when systemPromptFile
is set
- Update runtime-tmux create() to use load-buffer/paste-buffer for
launch commands >200 chars
- Add 8 tests for spawnOrchestrator
- Fix SessionManager mock in 8 test files (add spawnOrchestrator)
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* fix: use hash-based tmux name in orchestrator attach hint
The tmux attach hint after `ao start` printed the user-facing session
ID (e.g. app-orchestrator) instead of the hash-based tmux session name
(e.g. a3b4c5d6e7f8-app-orchestrator), causing "session not found"
errors. Now captures the runtimeHandle.id from spawnOrchestrator's
return value for the correct tmux target.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
1. No-issue spawn: use session/{sessionId} branch instead of defaultBranch
to avoid git worktree conflicts with the main repo's checked-out branch.
2. Plugin resolution: accept importFn parameter in loadBuiltins/loadFromConfig
so CLI can pass its own import() context for pnpm strict resolution. Added
all plugin packages as CLI workspace dependencies.
3. Ad-hoc issue IDs: gracefully handle IssueNotFoundError by continuing
without tracker context instead of throwing. Non-issue errors (auth,
network) still fail fast.
Co-authored-by: Claude Sonnet 4.6 <noreply@anthropic.com>
* fix: config discovery, activity detection, and metadata port storage
- findConfigFile() checks AO_CONFIG_PATH env var (resolved to absolute path)
- loadConfig() delegates to findConfigFile() for consistent validation
- Pure Node.js readLastJsonlEntry (no external tail binary), safe for
multi-byte UTF-8 at chunk boundaries
- Added "ready" activity state to agent plugins
- Store dashboardPort, terminalWsPort, directTerminalWsPort in session
metadata so ao stop targets the correct processes
- Zod schema port default aligned with TypeScript interface
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* fix: dashboard config discovery + CLI service layer refactoring
- Config discovery via AO_CONFIG_PATH env var
- Auto port detection with PortManager
- Activity detection with ready state, pure Node.js readLastLine
- 5 CLI services: ConfigService, PortManager, DashboardManager, MetadataService, ProcessManager
- Store all service ports in metadata for ao stop
- Set NEXT_PUBLIC_ env vars for frontend terminal components
- Multi-byte UTF-8 safe readLastJsonlEntry
- Tests for all new services and utils
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* fix: address bugbot review comments (port fallback + systemPrompt)
1. Align port fallback to 3000 everywhere (matching Zod schema default):
- start.ts: config.port ?? 3000
- dashboard.ts: config.port ?? 3000
- types.ts JSDoc: "defaults to 3000"
- orchestrator-prompt.ts: already correct at 3000
2. Add --append-system-prompt to Claude Code plugin's getLaunchCommand
so orchestrator context is actually passed to the Claude agent.
Previously systemPrompt was generated but silently dropped.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* fix: remove dead ConfigService mock from status test
The vi.mock for ConfigService.js referenced a deleted module.
Config mocking is already handled by the @composio/ao-core mock.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* fix: extract shared buildDashboardEnv to eliminate duplication
Dashboard env construction (AO_CONFIG_PATH, PORT, NEXT_PUBLIC_*) was
duplicated between start.ts and dashboard.ts. Extracted into
buildDashboardEnv() in web-dir.ts (already shared by both commands).
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
* refactor: delegate CLI commands to core SessionManager
Replace direct tmux/metadata manipulation in CLI commands with calls to
core's SessionManager (spawn, list, kill, cleanup, send). This removes
~700 lines of reimplemented session logic and makes the CLI a thin layer
over the core service.
- Add create-session-manager.ts factory (cached PluginRegistry + SM)
- spawn: delegate to sm.spawn() instead of manual worktree/tmux setup
- session ls/kill/cleanup: delegate to sm.list()/kill()/cleanup()
- status: use sm.list() for session discovery and activity from Session
- send: resolve tmux target from session.runtimeHandle
- review-check: use sm.list() for session discovery
- dashboard/start: add --rebuild flag for stale .next cache cleanup
- Update all tests to mock create-session-manager.js
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* test: add regression tests for spawn delegation and dashboard stale cache
- spawn.test.ts: verify spawn delegates to sm.spawn() with correct args,
shows hash-based tmux name in attach hint (regression for flat-naming bug)
- dashboard.test.ts: verify stale .next cache detection patterns match the
actual error (Cannot find module vendor-chunks/xterm@5.3.0.js) and that
rebuildDashboard cleans .next directory
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* fix: ao dashboard --rebuild properly kills and restarts running server
Before: --rebuild deleted .next under the running dev server, leaving it
in a broken state (500s, missing chunks). Couldn't recover without manual
intervention.
Now: --rebuild detects the running dashboard via lsof, kills it, cleans
.next, then starts a fresh dev server on the same port. Works correctly
from any worktree since findWebDir resolves to the same web package.
- Add findRunningDashboardPid/findProcessWebDir/waitForPortFree utilities
- Split cleanNextCache from rebuildDashboard (cache-only vs full rebuild)
- Update tests for new dashboard-rebuild exports
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* fix: address bugbot review comments on PR #88
1. Cleanup dry-run now delegates to sm.cleanup({dryRun: true}) instead
of checking local status fields — ensures dry-run uses same live
checks (PR state, runtime alive) as actual cleanup.
2. Remove module-level mutable config in status.ts — pass config as
parameter to gatherSessionInfo() to avoid stale state bugs.
3. Batch-spawn duplicate detection uses sm.list() instead of broken
findSessionForIssue() which relied on flat tmux naming incompatible
with hash-based architecture.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
* chore: remove dead exports getPluginRegistry and rebuildDashboard
Both functions were exported but never imported outside test mocks.
Clean up test mocks and unused imports accordingly.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
* fix: deduplicate config/session lookups in send, hoist sm.list() in batch-spawn
1. Send command: merge resolveTmuxTarget() and resolveAgentForSession()
into a single resolveSessionContext() that loads config and calls
sm.get() once instead of twice.
2. Batch-spawn: move sm.list() call before the loop and build a Map for
O(1) duplicate lookups, avoiding repeated metadata reads + runtime
enrichment on every iteration.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
* chore: remove unused project parameter from spawnSession
After delegating to sm.spawn(), the ProjectConfig parameter is no
longer referenced — sm.spawn() resolves it internally from the
projectId. Remove the parameter and simplify both callers.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
* fix: handle process.kill race, waitForPortFree timeout, dry-run errors
1. Wrap process.kill() in try-catch to handle ESRCH when the target
process exits between detection and kill (race condition).
2. waitForPortFree() now throws on timeout instead of silently
returning, preventing the dashboard from starting on a busy port.
3. Dry-run cleanup now displays errors from PR/issue checks, matching
the non-dry-run branch behavior.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
* fix: hoist session manager in cleanup, skip dead sessions in batch-spawn
1. Hoist getSessionManager() before the dry-run if/else in cleanup
since both branches create the same instance.
2. Batch-spawn duplicate detection now excludes dead/killed/exited
sessions so crashed sessions don't block respawning the same issue.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
* fix: lsof flags, dry-run error guard, remove unused --regenerate
1. Fix lsof flag from -Fn to -Ffn so findProcessWebDir() actually
gets the file descriptor field needed to match "fcwd" markers.
2. Dry-run cleanup now guards "no sessions" message with both
killed.length === 0 AND errors.length === 0, matching the
non-dry-run branch behavior.
3. Remove unused --regenerate CLI option from ao start (defined
but never referenced in the action body).
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
* fix: cache registry promise and cap stderr buffer
- Cache the Promise instead of the resolved PluginRegistry to prevent
concurrent callers from racing past the null check and creating
multiple registries before loadFromConfig completes.
- Cap stderrChunks to 100 entries since only early startup errors
(stale build detection) are checked — unbounded growth wastes memory
for long-running dashboard processes.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
* fix: decouple activity detection from runtimeHandle
Activity detection reads JSONL files on disk — it only needs
workspacePath, not a runtime handle. Gating on runtimeHandle caused
sessions created by external scripts to always show "unknown".
Two fixes:
1. enrichSessionWithRuntimeState now runs activity detection
independently of runtime handle presence
2. list() and get() construct a fallback handle from session ID
when runtimeHandle is missing in metadata (same pattern
sendMessage already uses)
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* fix: don't let fabricated runtime handles override session status
Bugbot correctly identified that constructing a fallback runtimeHandle
for sessions without one causes isAlive() → false → status = "killed",
clobbering meaningful statuses like "pr_open". Track whether the handle
came from metadata and only run liveness checks on real handles.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* refactor: extract ensureHandleAndEnrich to deduplicate list/get
Bugbot flagged the identical fallback handle construction in list() and
get(). Extracted into ensureHandleAndEnrich() so the logic lives in one
place.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
* feat: overhaul orchestrator prompt with comprehensive CLI reference
The generated CLAUDE.orchestrator.md now teaches the orchestrator agent
everything it needs out of the box: identity/role, complete CLI reference
for every `ao` command with flags/options, behavioral guidelines (do/don't),
session lifecycle, workflows, and anti-patterns.
- Rewrite generateOrchestratorPrompt() with detailed CLI docs
- Add "Never Do" section (no legacy scripts, no raw tmux, no coding)
- Add session lifecycle ASCII diagram adapted to project config
- Document ao send flags (--no-wait, --timeout, -f) and mechanics
- Update static CLAUDE.orchestrator.md to use ao CLI exclusively
- Add 35 unit tests for orchestrator prompt generation
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* refactor: move orchestrator prompt injection into Agent plugin interface
The orchestrator prompt was being injected by directly writing
CLAUDE.local.md and CLAUDE.orchestrator.md in start.ts — Claude Code-
specific logic that doesn't work for other agents (Codex, Aider, OpenCode).
- Add `injectSystemPrompt()` to the Agent interface in types.ts
- Implement in agent-claude-code: writes CLAUDE.{name}.md + @import
- Implement in agent-codex/opencode: writes AGENTS.md
- Implement in agent-aider: writes .aider.conventions.md
- Remove ensureOrchestratorPrompt/ensureOrchestratorImport from start.ts
- start.ts now calls agent.injectSystemPrompt() (agent-agnostic)
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* refactor: pass orchestrator prompt via CLI flags instead of file injection
Replace the file-based injectSystemPrompt() approach with native agent CLI
flags. Each agent plugin now handles systemPrompt in getLaunchCommand():
- Claude Code: --append-system-prompt
- Codex: --system-prompt
- Aider: --system-prompt
- OpenCode: no flag yet (ignored)
This removes the need to write CLAUDE.orchestrator.md / CLAUDE.local.md /
AGENTS.md files, making the implementation truly agent-agnostic. Also removes
the unused --regenerate flag from `ao start`.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
* fix: activity detection — fix path encoding, use tail -1 for JSONL
Two tightly coupled infrastructure fixes:
- Fix toClaudeProjectPath(): leading `/` becomes `-` (not stripped),
matching Claude Code's actual project directory naming convention.
- Replace manual 4KB buffer read in readLastJsonlEntry() with
`tail -1` + JSON.parse — handles any file size, any line length,
and eliminates the truncated-line edge case entirely.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* feat: add "ready" state, return null when unknown, remove dead code
Behavioral changes to activity detection:
- Add "ready" to ActivityState — separates "alive at prompt" from
"idle/stale". Configurable via readyThresholdMs (default 5 min).
- Agent plugins return null when they can't determine activity
(no workspace, no JSONL, no per-session tracking). Session manager
preserves existing activity instead of overwriting with a guess.
- Remove isProcessing() from Agent interface — zero callers in
production code, fully superseded by getActivityState().
- Remove extractLastMessageType() from claude-code — the field it
populated (lastMessageType) was only consumed by the old inline
CLI mapping, which is now replaced by plugin delegation.
- CLI status delegates to agent.getActivityState() (single source
of truth) with metadata fallback when plugin returns null.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* test: comprehensive activity detection coverage
- activity-detection.test.ts: 42+ tests covering path encoding,
getActivityState edge cases (exited/null/fallback), real Claude Code
JSONL types, agent interface spec types, staleness thresholds,
JSONL file selection, and realistic session sequences.
- status.test.ts: plugin delegation tests — verifies CLI uses
agent.getActivityState() as single source of truth, passes
readyThresholdMs from config, falls back to metadata on null/throw.
- Integration tests: updated type expectations for null returns from
codex, opencode, and aider; added "ready" to valid state lists.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* fix: flaky Linear integration test + missing ready label in SessionDetail
Linear API has eventual consistency — updateIssue state changes don't
propagate instantly. Poll with retries instead of asserting immediately.
Also adds "ready" entry to SessionDetail activityLabel map (was missing,
causing fallback to dim/unstyled rendering).
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* fix: pure Node.js readLastJsonlEntry, use pollUntilEqual for Linear test
Replace `tail -1` with pure Node.js implementation that reads backwards
from end of file in 4KB chunks. No external binary dependency — works
on any platform.
Fix flaky Linear integration test by using the existing pollUntilEqual
helper instead of an inline retry loop. Linear API has eventual
consistency; pollUntilEqual retries for up to 5s with 500ms intervals.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* fix: use tail -1 for readLastJsonlEntry, add real-data integration test
Replace over-engineered pure Node.js backward-reading implementation with
simple `tail -1` via execFile. The codebase already shells out to tmux,
git, and ps everywhere — tail is no different.
Add integration test that validates toClaudeProjectPath() and
readLastJsonlEntry() against real ~/.claude/projects/ data on disk.
No API key needed — just requires Claude to have been run once.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
prateek
Harsh Batheja
Jayesh Sharma
Harsh
suraj_markup
suraj-markup
Karan Vaidya