* feat: add npm publishing support with @composio scope
Set up Changesets for version management, add publish metadata to all 20
packages under the @composio scope, create an unscoped wrapper package
(@composio/agent-orchestrator) for global install, and add a GitHub
Actions release workflow.
- Rename all packages from @agent-orchestrator/* to @composio/ao-*
- Add @composio/agent-orchestrator wrapper (bin shim → @composio/ao-cli)
- Add license, repository, homepage, bugs, files, engines to all packages
- Add .npmrc (access=public), MIT LICENSE file
- Add .changeset/ config with linked versioning for all packages
- Add .github/workflows/release.yml (changesets publish CI)
- Add changeset, version-packages, release scripts to root
Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
* fix: exclude private web package from release build
The release script now filters out @composio/ao-web, matching the
workflow's existing exclusion and preventing a Next.js build failure
from blocking npm publishing.
Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
---------
Co-authored-by: Claude Sonnet 4.5 <noreply@anthropic.com>
* fix: resolve dashboard GitHub API rate limiting and PR enrichment issues
This commit addresses critical dashboard performance and reliability issues:
**Core Issues Fixed:**
1. GitHub API rate exhaustion (~84 calls/refresh → ~7-10 calls/refresh)
2. Silent failures showing misleading PR data when rate-limited
3. Missing SessionStatus values ("done", "terminated")
4. Unnecessary enrichment of merged/closed PRs
5. No caching of API responses
**Key Changes:**
- Add "done" and "terminated" to SessionStatus type
- Update getAttentionLevel to correctly classify terminal sessions
- Skip PR enrichment for terminal sessions (merged, done, terminated)
- Implement 60-second TTL cache for PR enrichment data
- Handle rate limit errors gracefully with explicit "unavailable" messages
- Improve default values in basicPRToDashboard (no longer misleading)
- Add orchestrator terminal button to Dashboard header
**Test Coverage:**
- 54 new test cases across 3 test files
- Tests for cache behavior, attention level classification, and serialization
- All tests passing (cache: 9/9, types: 29/29, serialize: 16/16)
**Performance Impact:**
- 10× reduction in API calls (84 → 7-10 per refresh)
- 10× improvement in rate limit exhaustion time
- 60s cache prevents redundant API calls on page refresh
Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
* fix: address bugbot comments (cache leak, PR skip, CI alert)
Fixes three issues identified by bugbot:
1. **TTL cache memory leak (Medium)**: Cache only evicted expired entries
on get(), causing unread keys to accumulate indefinitely. Added periodic
cleanup via setInterval (runs every TTL period) with unref() to prevent
blocking process exit.
2. **PR skip condition never triggers (Low)**: Check for merged/closed PRs
was using sessions[i].pr.state which is always "open" (default from
basicPRToDashboard). Fixed by checking cache for merged/closed state
before enrichment, avoiding unnecessary API calls.
3. **SessionCard "0 CI check failing" bug**: When GitHub API fails,
ciStatus is "failing" but ciChecks is empty, showing nonsensical
"0 CI check failing" alert. Fixed to show "CI status unknown" instead
when failCount is 0.
**Tests Added:**
- Cache cleanup interval test (async real timer)
- SessionCard CI status unknown test (verifies no "0 failing" or "ask to fix")
Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
* fix: CRITICAL - fix field name mismatch in getCIChecks causing all checks to fail
Root cause of "CI failing" everywhere: scm-github plugin was requesting
non-existent fields from gh CLI, causing all checks to map to "failed".
**The Bug:**
- Requesting: `conclusion` and `detailsUrl` (don't exist in gh pr checks)
- Since `conclusion` was always undefined, every check hit the else clause
and was marked as "failed"
**The Fix:**
- Use correct field names: `state` (contains SUCCESS/FAILURE/PENDING directly)
and `link` (replaces detailsUrl)
- Parse `state` directly instead of looking for non-existent `conclusion`
- Map state values: SUCCESS → passed, FAILURE → failed, PENDING → pending, etc.
**Impact:**
This was the #1 bug causing false "CI failing" status everywhere, not rate
limiting. All PRs with passing CI were incorrectly shown as failing.
Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
* fix: update plugin-integration tests for getCIChecks field name changes
The getCIChecks fix changed field names from `conclusion`/`detailsUrl`
to `state`/`link`. Updated test mocks to match:
- Changed `conclusion: "SUCCESS"` → `state: "SUCCESS"`
- Changed `conclusion: "FAILURE"` → `state: "FAILURE"`
- Changed `detailsUrl` → `link`
Tests now pass with correct field names.
Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
* fix: update scm-github plugin tests for correct field names
Updated all test mocks to use correct gh pr checks field names:
- Changed `conclusion: "SUCCESS"/"FAILURE"/etc` → `state: "SUCCESS"/"FAILURE"/etc`
- Changed `detailsUrl` → `link`
- Removed redundant `state: "COMPLETED"` prefix (state contains result directly)
All 52 scm-github plugin tests now pass.
Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
* fix: apply cached data when skipping enrichment + improve rate-limit detection
Fixes two issues identified in bugbot comments:
1. **Cached terminal PR state never applied** (issue #2807979137):
- When skipping enrichment for merged/closed PRs, we now copy all cached
fields to the session before returning
- Previously the session kept default basicPRToDashboard() values (e.g.,
state: "open"), causing terminal PRs to render with stale data
2. **Rate-limit detection cannot trigger reliably** (issue #2807979141):
- Changed from "all failed" to "majority failed" detection (>= 50%)
- Some SCM methods (like getCISummary) return fallback values instead of
throwing, so allFailed was too strict
- Now detects rate limiting even when some methods return defaults
Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
* fix(web): apply partial enrichment data when rate-limited + fix type errors
Addresses bugbot comment #2807998258: Rate-limit detection should not
discard partial successful enrichment data.
**Changes:**
1. Remove early return when mostFailed - continue to apply any fulfilled results
2. Add rate-limit blocker message to mergeability after applying partial data
3. Fix cached data application - use correct field names (unresolvedThreads/unresolvedComments)
4. Add proper type casts for cached ciChecks status field
5. Fix tsconfig to exclude test files from type-checking (jest-dom type extensions
don't work with tsc, but tests run fine with vitest)
**Behavior change:**
- Before: 3+ failed API calls → skip enrichment entirely, show "API rate limited"
- After: 3+ failed API calls → apply any successful results + add blocker message
This allows partial data (e.g., PR state, title, passing CI checks) to be displayed
even when some API calls fail, providing better UX during rate limiting.
Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
* fix: apply cached data to terminal sessions + always cache partial enrichment
Addresses two new bugbot comments:
1. **Terminal sessions keep stale open PR state** (#2808037050):
- Problem: page.tsx returned early for terminal sessions before checking cache
- Result: Terminal sessions kept basicPRToDashboard() defaults (pr.state="open")
- Fix: Check cache FIRST, apply cached data, THEN skip enrichment for terminal sessions
2. **Partial rate-limit results are never cached** (#2808037054):
- Problem: Caching was gated by `if (!mostFailed)`, so partial data wasn't cached
- Result: During rate-limits, sessions repeatedly re-hit SCM APIs every refresh
- Fix: Always cache enrichment results (including partial data from rate-limited requests)
**Behavior changes:**
- Terminal sessions now show correct cached PR state (merged/closed) instead of "open"
- Partial enrichment data is cached for 60s, reducing API pressure during rate-limit periods
- Updated test expectations to reflect new caching behavior
Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
* fix: apply all cached fields + allow terminal sessions to enrich once
Addresses two new bugbot comments:
1. **Cached terminal data applied incompletely** (#2808048773):
- Problem: Only copied some fields (state, ciStatus, etc.) but omitted title, additions, deletions
- Fix: Added missing fields when applying cached data
2. **Terminal PRs remain permanently unenriched** (#2808048771):
- Problem: Terminal sessions with no cache never got enriched → kept stale defaults forever
- Fix: Removed the "skip enrichment for terminal with no cache" logic
- Behavior: Terminal sessions now enrich at least once (or when cache expires), then skip subsequent enrichments
**Behavior change:**
- Before: Terminal session without cache → skip enrichment forever → stale data
- After: Terminal session without cache → enrich once → cache for 60s → skip while cached
This ensures terminal sessions get accurate PR data at least once, while still avoiding
unnecessary API calls for sessions that already have fresh cached data.
Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
---------
Co-authored-by: Claude Sonnet 4.5 <noreply@anthropic.com>
getCISummary() was returning "failing" whenever getCIChecks() threw an
error, even for merged PRs where GitHub may not return check data.
This caused the dashboard to show "CI failing" for merged PRs.
Now checks PR state before fail-closing — merged/closed PRs return
"none" instead of "failing".
Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
* fix: wire dashboard to real session data with PR enrichment
- Parse owner/repo from GitHub PR URLs in session-manager for gh CLI calls
- Add static plugin imports in web services.ts (webpack can't resolve dynamic imports)
- Add PR enrichment to page.tsx server component with project matching fallback
- Add project matching fallback in API route for sessions without projectId
- Map bash "starting" status to "working" for backwards compatibility
- Add fallback runtime handle for bash-created sessions without runtimeHandle
- Add getPRSummary to SCM interface for fetching additions/deletions/title
- Implement getPRSummary in scm-github plugin
- Use getPRSummary in enrichSessionPR to populate PR diff stats
- Add plugin-tracker-github dependency to web package
Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
* fix: update send test for fallback runtime handle behavior
Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
* fix: register workspace-worktree plugin in web services
Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
---------
Co-authored-by: Claude Sonnet 4.5 <noreply@anthropic.com>
* feat: implement SCM and tracker plugins (github, linear)
Implement three plugin interfaces from packages/core/src/types.ts:
- scm-github: Full GitHub PR lifecycle via `gh` CLI — PR detection by
branch, state tracking, CI checks, reviews, review decision, pending
comments, automated bot comment detection (cursor[bot], codecov, etc.),
and merge readiness (CI + reviews + conflicts + draft).
- tracker-github: GitHub Issues tracker via `gh` CLI — issue CRUD,
completion check, branch naming (feat/issue-N), prompt generation,
list/filter/update/create with label and assignee support.
- tracker-linear: Linear issue tracker via GraphQL API (LINEAR_API_KEY) —
issue fetch, completion check, branch naming (feat/IDENTIFIER), prompt
generation, list with team/state/label filters, state transitions via
workflow state resolution, issue creation with teamId config.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* fix: address PR review — GraphQL injection, N+1 queries, timeouts, tests
- tracker-linear: use GraphQL variables in listIssues to prevent injection
- tracker-linear: add 30s HTTP timeout to linearQuery
- tracker-linear: fix issueUrl to use workspace slug from project config
- tracker-linear: add labels/assignee support to createIssue
- scm-github: rewrite getPendingComments to use GraphQL reviewThreads
with real isResolved status instead of hardcoding false
- scm-github: simplify getAutomatedComments to single API call (N+1 fix)
- scm-github: add 30s timeout to gh CLI calls
- scm-github: fix parseDate to return epoch instead of fabricating dates
- scm-github: add repo format validation in detectPR
- scm-github: fix getCISummary to not count all-skipped as passing
- tracker-github: add 30s timeout to gh CLI calls
- tracker-github: fix createIssue to not use unsupported --json flag
- Add comprehensive vitest tests for scm-github and tracker-github
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* fix: address Codex review — assignee lookup, GraphQL vars, status checks
Iteration 1 fixes (8 issues from Codex review):
- tracker-linear: remove invalid assigneeDisplayName, resolve assignee
by display name to ID via users query after creation
- tracker-linear: add HTTP status code check in linearQuery
- tracker-linear: throw on missing workflow state in updateIssue
- scm-github: use GraphQL variables ($owner, $name, $number) in
getPendingComments instead of string interpolation
- scm-github: guard against empty comment nodes in review threads
- scm-github: use mergeStateStatus in getMergeability (BEHIND, BLOCKED)
- tracker-github: default description to "" in createIssue
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* fix: address PR review + lint — error context, GraphQL vars, mergeability
- scm-github/tracker-github: wrap gh() errors with command context + cause
- scm-github: use GraphQL variables ($owner, $name, $number) in
getPendingComments to prevent injection
- scm-github: guard against empty review thread nodes
- scm-github: incorporate mergeStateStatus (BEHIND/BLOCKED) in getMergeability
- tracker-linear: add identifier vs UUID comment in updateIssue
- Fix ESLint preserve-caught-error violations
- Remove unused mockGhRaw in scm-github tests
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* fix: add pagination to getAutomatedComments and increase thread limit
- getAutomatedComments: add --paginate flag to REST API call to fetch
all review comments beyond the default 30-item first page
- getPendingComments: increase GraphQL reviewThreads limit from 100 to
250 (GitHub's max for connections)
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* fix: use per_page=100 instead of --paginate for JSON-safe pagination
Replace --paginate with -F per_page=100 in getAutomatedComments to
avoid concatenated JSON arrays that break JSON.parse on multi-page
responses. 100 is GitHub's max per_page value.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* fix: filter out resolved threads in getPendingComments
The method name implies it should only return unresolved/pending review
threads. The isResolved data was already fetched via GraphQL but was not
being filtered on, causing resolved threads to be included in results.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* test: add comprehensive tracker-linear test suite (53 tests)
Covers all Tracker interface methods: getIssue, isCompleted, issueUrl,
branchName, generatePrompt, listIssues, updateIssue, createIssue.
Mocks node:https request to simulate Linear GraphQL API responses.
Tests state mapping, error handling, assignee/label resolution, and
GraphQL variable injection.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* fix: address 6 bugbot review comments on PR #4
- GraphQL reviewThreads(first: 250) → first: 100 (GitHub max)
- noConflicts false when mergeable is UNKNOWN (not just CONFLICTING)
- updateIssue now handles labels and assignee (not just state/comment)
- Add res.on("error") handler in linearQuery to prevent crashes
- createIssue returns only actually-applied labels, not all requested
- Tests added/updated for all fixes (144 total across 3 plugins)
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* fix: make Linear updateIssue labels additive to match GitHub behavior
Linear's issueUpdate replaces all labels, while GitHub's --add-label is
additive. Now fetches existing label IDs first and merges with new ones
before sending to issueUpdate, ensuring consistent behavior across both
tracker implementations.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* fix: default listIssues to open state in tracker-linear
When no state filter is specified, tracker-github defaults to "open"
but tracker-linear was returning all issues. Now defaults to excluding
completed/canceled issues, matching tracker-github behavior.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* feat: add Composio SDK support to tracker-linear
Allow users with a COMPOSIO_API_KEY to use the Linear tracker without
a separate LINEAR_API_KEY. The plugin auto-detects which key is available
and routes through either the direct Linear GraphQL API or Composio's
LINEAR_RUN_QUERY_OR_MUTATION tool. All existing queries and response
parsing are reused via a GraphQLTransport abstraction.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* fix: address 2 bugbot review comments on PR #4
1. getCIChecks now throws on error instead of silently returning [],
preventing a fail-open where CI appears healthy when we can't fetch
check status. getCISummary catches the error and returns "failing".
2. Handle GitHub's UNSTABLE mergeStateStatus (required checks failing)
as a merge blocker in getMergeability.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* fix: prevent unhandled promise rejection in Composio timeout race
When the timeout wins Promise.race in the Composio transport, the
resultPromise is left without a rejection handler. If the SDK call
later rejects, it becomes an unhandled promise rejection that crashes
Node.js 20+ with --unhandled-rejections=throw.
Attach no-op .catch() to both resultPromise and timeoutPromise before
the race so whichever promise loses has its rejection silently handled.
Also adds plugin integration tests (core -> real plugins -> mocked gh CLI).
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* fix: chain error cause in getCIChecks and fix core build
- getCIChecks catch now preserves the original error via { cause: err }
instead of discarding it, matching the pattern used by the gh() helper
- Add tsconfig.build.json to core that excludes __tests__/ from build
compilation, preventing TS5055 errors from circular workspace deps
(integration tests import plugin packages that depend back on core)
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* fix: remove circular devDeps, address bugbot comments
- Remove plugin devDependencies from core/package.json that created a
circular dependency (core -> plugins -> core), breaking CI build order
- Document in_progress state as intentional no-op in tracker-github
updateIssue (GitHub Issues only supports open/closed)
- Remove @composio/core optional peerDependency from tracker-linear;
the dynamic import() already handles the missing package gracefully,
and the peer dep was pulling composio + transitive deps into lockfile
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* feat: add real integration test for tracker-linear against Linear API
Creates a test that exercises the full tracker-linear plugin lifecycle
against the real Linear API — createIssue, getIssue, isCompleted,
listIssues, updateIssue (comment, close, reopen), generatePrompt,
branchName, issueUrl. Each run creates a throwaway test issue and
trashes it in cleanup. Skipped when LINEAR_API_KEY is not set.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* ci: pass LINEAR_API_KEY and LINEAR_TEAM_ID to integration tests
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* feat: support both LINEAR_API_KEY and COMPOSIO_API_KEY in integration test
The tracker-linear integration test now runs with either credential:
- LINEAR_API_KEY: direct Linear API (full cleanup via trash)
- COMPOSIO_API_KEY: via Composio SDK (cleanup falls back to closing)
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* fix: don't pass COMPOSIO_API_KEY to CI integration tests
When both LINEAR_API_KEY and COMPOSIO_API_KEY are set, the plugin
prefers the Composio transport which requires @composio/core SDK.
The SDK isn't installed in CI, so use the direct LINEAR_API_KEY
transport which has no extra dependencies.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* fix: use import.meta.url in vitest config, default createIssue description
- Replace __dirname with import.meta.url-derived dirname in ESM config
- Default createIssue description to "" for defensive safety
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* fix: map CANCELLED and ACTION_REQUIRED CI conclusions to failed
Terminal check conclusions (CANCELLED, ACTION_REQUIRED) were falling
through to "pending", causing the lifecycle manager to wait forever.
Also changed the default else branch to "failed" (fail-closed).
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
Phase 0 complete. Establishes:
- pnpm workspace with 18 packages (core, cli, web, 15 plugins)
- Complete type definitions in packages/core/src/types.ts defining
all 8 plugin slot interfaces (Runtime, Agent, Workspace, Tracker,
SCM, Notifier, Terminal) + core service interfaces
- YAML config loader with Zod validation and sensible defaults
- Plugin registry with built-in discovery
- CLAUDE.md with conventions for spawned agents
All agents can now branch from main and implement their assigned
packages against the interfaces defined in types.ts.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
prateek