Pulls in 2 main commits (#1487 orchestrator identity fix, #1238 gh CLI
tracer + scm/tracker migration Phase A1a) plus the auto-merged
follow-on changes from upstream.
Conflict resolutions:
- packages/core/src/session-manager.ts:
Took main's reorganized opencode-agents-md import + new
getOrchestratorSessionId import. Kept main's reformatted sessionCache
type and added the new ensureOrchestratorPromises Map.
- packages/core/src/agent-workspace-hooks.ts:
Took main's WRAPPER_VERSION = "0.6.0" (and matching test fixture).
- packages/core/src/__tests__/agent-workspace-hooks.test.ts:
Merged both sides' imports — kept branch's buildNodeWrapper +
node:path/join (still used in test body) and added main's
AO_METADATA_HELPER + GH_WRAPPER constant exports.
- packages/plugins/agent-codex/src/index.ts:
Dropped now-unused PREFERRED_GH_PATH import (env injection moved to
session-manager). Kept isWindows — needed by branch's new
formatLaunchCommand, resolveCodexBinaryWindows, and pre-existing
isProcessRunning code.
- packages/plugins/agent-codex/src/index.test.ts:
Took main's collapsed PATH/GH_PATH undefined assertions and no-op
setupWorkspaceHooks test — the agent no longer constructs PATH or
installs wrappers (session-manager owns those paths now). Removed
the orphaned wrapper-write tests. Kept branch's
describe.skipIf(win32) on the shell-wrapper-content block (those
tests verify Unix shell-script content that genuinely can't run on
PowerShell).
- packages/plugins/agent-aider/src/index.test.ts +
packages/plugins/agent-cursor/src/index.test.ts:
Took main's `expect(env["PATH"]).toBeUndefined()` — agents no
longer set PATH directly.
- packages/web/server/mux-websocket.ts:
Kept branch's Windows pipe handler branch and updated the inner
Unix `terminalManager.open(id, tmuxName)` call to main's new
signature with the optional tmuxName argument.
Verified: typecheck clean, lint 0 errors, full build (28 pkgs), tests
942/946 passing — the 4 failing tests in plugin-integration.test.ts
also fail on main itself (verified by running main's untouched test
file), so they're pre-existing flakes unrelated to this merge.
Three Windows-specific gaps that combined to make every Codex spawn fail
on PowerShell with "Unexpected token '-c' in expression or statement":
- formatLaunchCommand(): prepend `& ` to the joined launch string when
running on Windows. shellEscape quotes the resolved binary path
('C:\Users\...\codex.cmd'), and PowerShell parses a leading quoted
string as an expression — without the call operator the next flag
triggers a parser error before codex is ever invoked. bash treats
the same string as a normal command, so the prefix is Windows-only.
Applied at both getLaunchCommand and getRestoreCommand exits.
- resolveCodexBinary(): add a Windows branch using `where.exe` instead
of `which`. Prefers codex.cmd (npm shim) over codex.exe (Cargo build),
then falls back to %APPDATA%\npm\codex.{cmd,exe} and ~\.cargo\bin
for users whose PATH doesn't yet include the install dir. Lookup runs
with windowsHide:true so the search itself doesn't flash a console.
- sessionFileMatchesCwd(): compare paths via a canonical form
(forward slashes, lowercased drive letter) so Codex JSONL rollout
files can still be located when payload.cwd uses a different slash
direction or drive-letter case than the workspace path AO computes
via path.join. Without this, dashboard activity/cost stay empty
for Codex sessions on Windows.
* feat(core): add opt-in gh CLI tracer and migrate scm/tracker plugins
Introduces execGhObserved() in @aoagents/ao-core: a thin wrapper around
execFile("gh", ...) that writes a JSONL trace row to $AO_GH_TRACE_FILE
on both success and failure. Captures status line, HTTP status, ETag,
rate-limit headers, duration, stdout/stderr byte counts, exit code, and
signal. No-op when the env var is unset, so default behavior is
unchanged.
Migrates three call sites to the observer:
- scm-github/graphql-batch.ts — PR-list guard, commit-status guard,
GraphQL batch query
- scm-github/index.ts — gh() and ghInDir() helpers
- tracker-github/index.ts — internal gh() helper
This is Phase A1a of experiments/PLAN.md: tracer infrastructure +
migration. The full GhRunner contract (Promise<GhResult>,
GhRunnerError.ghResult on reject, body capture, redaction, 64 KB cap)
lands in A1b along with the scorecard baseline.
Also adds experiments/ reference docs: the v2.3 plan, the gh-CLI call
catalog, two ETag verification writeups, and a trace harness + summary
script.
* docs(experiments): add A1a validation status and A1b blockers
Record the five A1b pre-freeze blockers surfaced by Adil's 1,487-row
baseline and an independent drill run: graphql-batch missing -i,
extractOperation flag mis-bucketing, analyzer not segmenting burn by
reset window, CLI-subcommand opacity (GH_DEBUG=api stderr vs coarse
/rate_limit bracket — not equivalent), and sessionId/projectId not
threaded through plugin callsites. Note bare gh() helper cleanup as
known-open follow-up.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* fix(tracer): close A1b blockers 1-4 — graphql-batch visibility, operation naming, analyzer segmentation
- Add -i flag to executeBatchQuery in graphql-batch.ts and split HTTP
headers from JSON body before parsing, making all gh.api.graphql-batch
rows visible to status and rate-limit analysis (was 186 invisible rows)
- Fix extractOperation() in gh-trace.ts to walk past -* flags before
picking the operation segment, eliminating the gh.api.--method bucket
- Add per-reset-window burn segmentation to both analyzers so runs
straddling a reset boundary produce per-window deltas instead of a
single invalid cross-reset delta
- Add experiment scripts: analyze-trace.mjs (deep trace analysis) and
drill-tracer.mjs (standalone tracer exerciser)
- Document Gap 1 decision in PLAN.md: accept CLI subcommands as opaque
for A1, bracket A2 runs with /rate_limit snapshots for coarse burn
- Add progress timeline to PLAN.md showing A→B→C track dependencies
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* docs(experiments): add A2 baseline matrix runbook
Practical execution plan for the Phase A2 scenario x scale x topology
matrix: 7 priority cells, per-cell procedure, /rate_limit bracketing
for Gap 1 subcommand burn, output format for baseline.md, and the
scorecard that gates Track B.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* fix(tracer): guard stderr/stdout against undefined, bound operation cardinality
Addresses code review findings:
1. Guard Buffer.byteLength and parseIncludedHttpResponse against
undefined stderr/stdout — fixes 48 SCM test regressions where
mocked execFile paths don't populate stderr
2. extractOperation() now takes only the first path segment of REST
URLs (e.g. "repos" from "repos/acme/repo/pulls/123/...") to keep
operation bucket cardinality bounded and stable across runs
3. Fix A2 runbook /rate_limit snapshots to produce valid JSON using
jq's now|todate instead of appending raw timestamp
4. Add blocker 5 dependency to runbook prereqs and per-session cells
All 140 SCM tests pass (0 failures).
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* docs(experiments): add rate-limiting research artifacts
Baseline measurements, discussion notes, benchmark harness spec,
and updated master plan from two independent trace runs at 5-6 sessions.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* feat(experiments): add benchmark harness for GH rate-limit measurement
Three modes: setup (spawn sessions, wait for PRs), measure (trace API
calls over a fixed window, produce scorecard), report (recompute from
existing trace). Node.js stdlib only, shells out to ao CLI and gh CLI.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* fix(scm-github): handle 304 Not Modified in ETag guard catch blocks (B1)
`gh api -i` exits code 1 on HTTP 304 responses, causing the catch blocks
in checkPRListETag and checkCommitStatusETag to assume the resource changed
and trigger unnecessary GraphQL batch queries every poll cycle.
Fix: inspect stdout/stderr in the catch block for the 304 status line before
falling back to "assume changed". Also unifies the 304 detection regex to
handle HTTP/1.1, HTTP/2, and HTTP/2.0 status lines, and adds rateLimit
introspection to the batch GraphQL query.
Benchmark result (quiet-steady, 5 sessions, 15 min):
- GraphQL points/hr: 260/5,000 (5%) — down from 820–1,416 pre-fix
- ETag guard 304 rate: 100%
- GraphQL batch calls during measurement: 0
Also fixes the benchmark harness to create placeholder tmux sessions with a
claude symlink so the lifecycle actually polls sessions instead of
short-circuiting to "killed".
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* docs(experiments): update plan and notes with B1 benchmark results
B1 fix validated at 5, 10, and 20 sessions in quiet-steady state:
- 5 sessions: 260 GraphQL pts/hr (5% budget)
- 10 sessions: 640 pts/hr (13%)
- 20 sessions: 680 pts/hr (14%) — sub-linear scaling confirmed
- 50-session projection: ~800-1000 pts/hr (16-20%)
- ETag guard 304 rate: 100% at all scale points
- graphql-batch calls: 0 during measurement at all scale points
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* feat(core): log gh wrapper invocations for D1
* fix(core): preserve wrapper logging for dash-prefixed gh args
* feat(core): add gh wrapper cache for PR discovery and issue context (D4)
Add read-through caching to the ~/.ao/bin/gh wrapper, targeting the two
largest agent-side waste buckets identified in D4 analysis:
1. PR discovery (gh pr list --head): infinite TTL for positive results.
598 calls → ~10 per 10-session run (98% reduction).
2. Issue context (gh issue view): 300s TTL.
75 calls → ~20 per 10-session run (73% reduction).
The wrapper now caches successful read-only responses in
$AO_DATA_DIR/.ghcache/$AO_SESSION/ and serves them on subsequent
identical calls. Negative results (empty []) are never cached.
gh pr create populates the PR discovery cache immediately.
Also lifts PATH wrapper installation from individual agent plugins into
session-manager, making it universal for all agents including Claude Code:
- session-manager injects PATH + GH_PATH into every runtime.create()
- session-manager calls setupPathWrapperWorkspace() for all agents
- Removes duplicate buildAgentPath/setupPathWrapperWorkspace boilerplate
from codex, aider, opencode, and cursor plugins
Includes D4 implementation plans in experiments/.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* docs(experiments): add full capacity discovery (5→50 sessions) and CI churn results
Complete scaling curve measured: 50 sessions uses only ~28% of GraphQL
budget with 100% ETag guard hit rate at every scale. Poll cycle lag
identified as first bottleneck (66s at 50 sessions vs 30s target).
CI churn benchmark shows ETag invalidation is a latency problem, not
a rate-limit problem (+9% GraphQL, +4.4x p50 latency).
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* docs(experiments): record real-agent catastrophe and Track D handoff
5-real-agent run on todo-app exhausted GraphQL bucket in 31 min (~9572 pts/hr,
~37x quiet-steady at the same session count). AO polling consumed ~10 calls;
the rest came from agents themselves via the metadata-only ~/.ao/bin/gh
wrapper, which has no tracing. Captures findings, adds Track D (agent-side
gh consumption) plus B5 (migrate remaining bare gh callsites to
execGhObserved), and includes the runbook + benchmark scripts Adil will
build on for the cross-machine reproduction.
* feat(core): add cache-hit/miss tracing to gh wrapper (D4)
The wrapper trace now logs a cacheResult entry for every cacheable
command: hit, miss-stored, miss-negative, or miss-error. This makes
benchmark runs conclusive — you can count cache hits vs real gh calls
directly from the JSONL trace instead of inferring from rate-limit
deltas.
Bump wrapper version to 0.4.1.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* feat(scm-github): replace repo-scoped Guard 1 with PR-scoped ETag checks (D4)
Guard 1 now checks GET /repos/{owner}/{repo}/pulls/{number} per PR
instead of GET /repos/{owner}/{repo}/pulls?... per repo. This means:
- Only changed PRs flow into the GraphQL batch
- Unchanged PRs are served directly from the enrichment cache
- shouldRefreshPREnrichment returns a refresh plan (prsToRefresh +
cachedResults) instead of a boolean
When 1 of 10 PRs changes, the old guard refreshed all 10 via GraphQL.
Now only the 1 changed PR is fetched; the other 9 are served from cache
at zero GraphQL cost.
Trade-off: more REST guard calls (1 per PR instead of 1 per repo), but
304 responses cost zero rate limit points.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* Forward AO_AGENT_GH_TRACE to session runtimes
* revert: remove PR-scoped ETag guards (Change 3)
Reverts 25ae6013. The per-PR Guard 1 added more REST calls (1 per PR
instead of 1 per repo) without meaningful GraphQL savings at 10-session
scale. Core REST delta went from 16 to 142 while GraphQL rate stayed
flat. The repo-scoped guard is sufficient for current workloads.
Preserves the subsequent 6fc64f4f commit (AO_AGENT_GH_TRACE forwarding).
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* fix(core): use real gh binary in execGhObserved, bypass wrapper
execGhObserved() was calling bare "gh" which resolved to ~/.ao/bin/gh
(the wrapper) when that directory was in PATH. This caused:
- AO-side gh calls going through the agent wrapper
- All trace rows with aoSession=null polluting the agent trace
- Cache functions silently failing (no AO_SESSION in AO process)
Now strips ~/.ao/bin from PATH and resolves the real gh binary
(e.g. /opt/homebrew/bin/gh) at startup. Cached after first resolution.
AO process → execGhObserved → real gh → AO_GH_TRACE_FILE
Agent process → ~/.ao/bin/gh wrapper → AO_AGENT_GH_TRACE + cache
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* fix(core): harden gh wrapper caching and agent-side tracing
Cache correctness:
- Include --json fields in cache key (prevents stale partial responses)
- Only cache stdout, not stderr (prevents warning contamination)
- Fix trailing newline inconsistency in PR discovery cache
- Support --key=value arg syntax for all cached flags
- Remove PR create cache pre-population (hardcoded fields, no JSON escaping)
- Log miss-write-failed when ao_cache_write fails (previously silent)
Agent trace improvements:
- Add operation field to invocation rows (gh.pr.list, gh.issue.view, etc.)
- Add durationMs, exitCode, ok to cache outcome rows
- Log passthrough for all non-cached code paths (pr/create, default case)
- Replace exec with child process in default case to enable post-call tracing
Bump wrapper version to 0.6.0.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* fix(runtime-tmux): re-export PATH after shell init to survive macOS path_helper
macOS zsh runs path_helper during shell startup which resets PATH,
wiping entries set via tmux new-session -e. This caused ~/.ao/bin
to be lost, so the gh/git wrappers were never intercepting agent
calls — no caching, no tracing, no metadata auto-updates.
Fix: send `export PATH=...` via send-keys after the shell has
initialized but before the launch command, ensuring PATH sticks.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* fix(runtime-tmux): use launch script for PATH re-export instead of send-keys
The previous send-keys approach sent 1000+ literal keystrokes for the
PATH value, which broke terminal input buffers and caused stuck quote
prompts. Instead, include the PATH export in the launch script file
which is executed directly — no terminal buffer issues.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* docs(experiments): add AO-side gh rate-limit trace report
5-session, 15-minute trace analysis with full call breakdown,
ETag guard effectiveness, anomaly investigation, and ranked
reduction opportunities.
Key findings:
- GraphQL at 41%/hr with 5 sessions (bottleneck at ~12 sessions)
- 47% of calls are individual REST fallbacks that batch should cover
- Review thread GraphQL calls (55/15min) can be folded into batch
- detectPR() and guard failures are working as designed
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* docs(experiments): add AO rate-limit reduction plan with Step 1
Step 1: Remove individual REST fallback from determineStatus().
110 calls (65 pr view + 45 pr checks) eliminated per 15-min window.
Batch enrichment covers all PRs every 30s — fallback is unnecessary
insurance for an event that never occurred in real traces.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* experiments(m2): drop agent-trace gate for claude-code
Claude Code uses native PostToolUse hooks (.claude/settings.json), bypassing
the ~/.ao/bin/gh PATH wrapper, so AO_AGENT_GH_TRACE stays empty even when
Claude makes gh calls. The previous smoke gate required AGENT_ROWS>0 and
aborted every claude-code M2 batch at smoke.
- limit-finder.sh: add REQUIRE_AGENT_TRACE env + --no-require-agent-trace flag,
gate the AGENT_ROWS integrity check behind it.
- m2-ab-run.sh: bump SMOKE_DURATION to 420s; auto-pass --no-require-agent-trace
when AGENT=claude-code; simplify smoke_check to gate only on AO_ROWS>0
(B1 lives in AO-side scm-github, measured by AO trace).
Follow-up tracked as task #39: instrument Claude's hook/tool path or document
that AO_AGENT_GH_TRACE does not cover Claude Code.
* feat(tracker-github): cache issue reads in-process (5 min TTL)
The lifecycle worker polls getIssue/isCompleted repeatedly for the same
issue across a session. Trace data from a 5-session tier-5 bench run
showed the same (repo, issue) pair fetched 64+ times with >97% duplicate
rate — ~744 of 4,059 AO gh calls in 10 minutes were redundant issue views.
Adds an in-process Map<string, CachedIssue> per createGitHubTracker()
instance, keyed by `${repo}#${id}`, TTL 5 min, bounded to 500 entries
(LRU evict-oldest on overflow).
- getIssue: read-through cache, populate on miss
- isCompleted: routes through getIssue (was a separate narrow gh call)
- updateIssue: invalidate the entry before mutating
- createIssue: unchanged, naturally populates via the existing getIssue
- Failures are not cached
Cache lives inside createGitHubTracker so each create() returns an
isolated cache (test isolation comes for free).
Expected reduction: ~744 → ~15 gh issue view calls per tier-5 run.
Tests: 41 existing + 10 new cache tests, all passing.
* feat(scm-github): cache 5 gh pr view callsites with per-method TTLs
The lifecycle worker repeatedly polls each PR for state, summary, reviews,
and review decision. Trace data showed gh pr view was the single largest
AO-side endpoint at 1,280 calls per 5-session tier-5 run with >97% duplicate
rate (e.g. PR #184 polled 86× for --json state alone in 11.5 minutes).
Adds an in-process per-instance cache inside createGitHubSCM(), keyed by
${owner}/${repo}#${prKey}:${method} so different field-sets stay isolated.
Per-method TTLs balance reduction against staleness on decision-influencing
fields:
- resolvePR: 60s (identity metadata only)
- getPRState: 5s
- getPRSummary: 5s (includes state)
- getReviews: 5s
- getReviewDecision: 5s
assignPRToCurrentUser, mergePR, and closePR each invalidate the entire PR
cache for that PR after the mutation, so AO never sees stale state from its
own writes. Failures are not cached.
getCIChecksFromStatusRollup and getMergeability are intentionally NOT cached
here — those need ETag-based revalidation, not blind TTL, and will land
separately.
Expected reduction: ~1,165 of ~1,280 gh pr view calls per tier-5 run.
Tests: 73 existing + 12 new cache tests, all 153 passing.
* feat(scm-github): cache CI checks, mergeability, pending comments, detectPR
Completes the AO-side hot-read caching alongside the prior PR view cache.
All use 5s TTL per the approved policy for decision-influencing fields —
well under one lifecycle poll cycle so state transitions are still seen
next pass.
- getCIChecks (gh pr checks): 5s TTL
- getMergeability (composite pr view + CI + state): 5s TTL on the composite
- getPendingComments (gh api graphql review threads): 5s TTL —
ETag doesn't help on GraphQL per Experiment 2
- detectPR (gh pr list --head BRANCH): 5s TTL, POSITIVE-ONLY.
Empty results are never cached so a freshly created PR is discovered
on the very next poll. The branch-keyed cache entry is invalidated
by mergePR/closePR alongside the number-keyed entries.
Combined with the prior PR view cache, covers the top 6 AO-side gh
operation categories that accounted for ~85% of calls in tier-5 traces.
Tests: 85 existing + 9 new cache tests, all 162 passing.
* experiments(m2): parse REPO from yaml before using it in banner
m2-ab-run.sh referenced $REPO in the header banner before parsing it,
causing 'unbound variable' abort under 'set -u'. Parse it right after
CONFIG_FILE is set.
* test(core): mock full Issue shape in plugin-integration cleanup tests
After tracker-github routed isCompleted() through getIssue() to share
the issue cache, these mocks needed the full Issue shape (number, title,
body, url, state, stateReason, labels, assignees) instead of the narrow
{state} shape that worked when isCompleted made its own --json state call.
* perf(scm-github): tune cache TTLs based on trace replay
Replayed feat run1 + main run2 tier-5 traces (4059 + 1748 rows, 38 min, 5
sessions each) against the shipped cache logic. Three TTLs were materially
under-tuned for the actual lifecycle poll cadence:
- detectPR: 5s → 30s (was 0.5% hit rate; per-branch poll cadence
is ~90s, so 5s caught nothing. 30s catches
intra-cycle bursts when multiple sessions
share a branch. Positive-only stays.)
- getReviewDecision: 5s → 10s (within "10-30s TTL or ETag" policy)
- getPendingComments: 5s → 10s (same policy class)
All three are still well under one poll cycle; freshness contract unchanged
in practice. Other TTLs (5s on state/CI/mergeability, 60s on resolvePR,
5min on issue) hit the targets they were set for and stay as-is.
Replay results before/after:
- feat run1: 53.7% → 57.8% reduction (2179 → 2345 hits of 4059 calls)
- main run2: 47.4% → 52.6% reduction
- Net: ~55% AO-side gh calls eliminated across both traces
Adds experiments/cache-replay.mjs — a counterfactual replay tool that
walks an execGhObserved JSONL trace and simulates per-method cache hits
with the shipped TTLs. Useful as a regression check when tweaking cache
policy.
Tests: 162/162 passing.
* docs(experiments): add cache freshness check runbook
Seven-step manual runbook to validate the cache TTL contract doesn't
cause workflow lag. Covers each cached method with:
- exact gh CLI trigger command
- what to observe in the dashboard / lifecycle log
- pass/fail threshold (TTL + 30s poll cycle)
Companion to experiments/cache-replay.mjs — replay measures how much
we saved, runbook measures whether we lost anything in the process.
* docs(experiments): add Step 2 — consolidate review comment fetching
Single GraphQL call replaces GraphQL + REST for review comments.
Include comment data in agent reaction message to eliminate
agent-side gh read calls. Update future steps.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* docs(experiments): add duplicate API traffic analysis
Three independent sources hit GitHub API for the same PRs:
1. Dashboard serialize.ts — individual REST calls, no batch, no cache
2. CLI lifecycle manager — batch + guards
3. Web lifecycle manager — same batch + guards, 3s offset
~50% of all API traffic is pure duplication. Dashboard and dual
lifecycle managers are the root causes.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* docs(experiments): add full cache architecture to duplicate traffic analysis
Three independent cache layers across two processes with zero shared
state. Web process creates its own plugin registry, SCM plugin, lifecycle
manager, and dashboard cache — all hitting GitHub independently.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* docs(experiments): add shared PR enrichment plan
Persist batch enrichment + review comments to session metadata files.
Dashboard reads from disk instead of making its own GitHub API calls.
Remove web's duplicate lifecycle manager.
Eliminates ~268 calls / 15 min (58% of all traffic). Dashboard data
gets fresher (30s vs 5min). Single writer (CLI lifecycle), web only reads.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* docs(experiments): update Step 1 — remove all three fallback paths
Remove fallback in determineStatus(), maybeDispatchCIFailureDetails(),
and maybeDispatchMergeConflicts(). All three follow the same pattern:
batch cache hit → use it, cache miss → skip (wait 30s for next batch).
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* docs(experiments): promote Step 3 (remove dead reviews field) + detail Step 5 (issue caching)
Step 3: Remove reviews(last: 5) from batch query — fetched but never
consumed, reduces GraphQL complexity on every batch call.
Step 5: Persist issue data to session metadata at spawn — eliminates
27 gh issue view calls per 15 min (both processes re-fetch independently).
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* feat(core): remove individual REST fallback from lifecycle polling
Remove fallback paths in determineStatus(), maybeDispatchCIFailureDetails(),
and maybeDispatchMergeConflicts() that made individual REST calls when the
batch enrichment cache missed. The batch runs every 30s — a cache miss
means the data arrives on the next cycle, not that it's lost.
Also add populatePREnrichmentCache() call to check() so single-session
checks also use the batch path.
Eliminates ~110 individual pr view/pr checks calls per 15-min window
(24% of all AO-side traffic).
* feat(core): consolidate review comment fetching into single GraphQL call
Add getReviewThreads() to SCM interface — returns all review threads
(human + bot) with isBot flag from a single GraphQL query. Lifecycle
manager splits locally for separate reaction pipelines.
- Eliminates the REST getAutomatedComments() call (40 calls / 15 min)
- Reaction messages now include inline comment data (file, line, author,
body, URL) so agents don't need to re-fetch via gh api
- Default config messages updated to not tell agents to call gh
- getAutomatedComments kept as optional for backward compatibility
* perf(scm-github): remove unused reviews(last: 5) from batch query
The batch query fetched reviews with author, state, submittedAt but
the data was never consumed — only used in a validation check.
The reviewDecision scalar field provides everything AO needs.
Reduces GraphQL complexity cost on every batch call.
* docs(experiments): add post-optimization trace report (Steps 1-3)
5-session, 17-minute trace after removing REST fallback, consolidating
review comments, and removing dead reviews field.
Results: GraphQL 35%/hr (was 41%), REST <1% (was 3%), automated
comment REST calls eliminated. 54% of remaining traffic is redundant
(duplicate lifecycle manager + dashboard individual calls).
* docs(experiments): add trace file gist link to post-optimization report
* feat(core,web): shared PR enrichment — dashboard reads from metadata
CLI lifecycle manager now persists batch enrichment data and review
comments to session metadata files (prEnrichment + prReviewComments
keys). The web dashboard reads from metadata instead of calling
GitHub API.
Changes:
- lifecycle-manager: add persistPREnrichmentToMetadata() after poll,
write prReviewComments in maybeDispatchReviewBacklog()
- serialize: replace enrichSessionPR (6 API calls) with metadata read
- services: stop web lifecycle polling (keep for webhook checks)
- cache: remove prCache (no longer needed)
- routes: remove timeout wrappers and cacheOnly pattern
Eliminates ~237 calls / 15 min (54% of all AO-side traffic).
Dashboard data freshness improves from 5min to 30s.
* fix(web): remove unused beforeEach import in serialize test
* docs(experiments): add final trace report — 56% GraphQL reduction achieved
5-session, 24-min trace after all optimizations including shared
enrichment. GraphQL 905/hr (was 2,072), REST 5/hr (was 168).
Single lifecycle manager confirmed. Dashboard API calls eliminated.
Max sessions before budget exhaustion: ~27 (was ~12).
* docs(experiments): add REST budget breakdown to final report
* fix(core): use storageKey for getSessionsDir in persistPREnrichmentToMetadata
* fix(test): use OpenCodeSessionManager type in plugin-integration tests
* fix(test): update bugbot-comments and auto-cleanup tests for new review API
* fix(web): fix syntax error and missing import from rebase
* docs(experiments): add complete rate-limiting change log and update final report numbers
* fix(web): fix tmux session resolution for legacy wrapped storageKeys
* fix(web): pass tmuxName directly to terminal server instead of reverse-resolving
* perf(core): gate detectPR behind Guard 1 ETag — skip when PR list unchanged
* perf(core): always run Guard 1 for all repos, dedup issue views, include threadId in review messages
* feat(core): add Guard 3 (review ETag), enrich review data with summaries, dedup issue views, gate detectPR for all repos
* fix(web): reuse cached tmuxSessionId on re-open, add 15-session trace report and comparison docs
* perf(scm-github): reduce contexts to first:10, add -i to review GraphQL for rate limit tracing
* feat(core): merge CI details into transition, enrich merge conflict message, reduce batch contexts, add graphqlCost tracing
* chore(experiments): remove working artifacts, keep final reports and reference docs
* chore: remove experiments directory
* refactor: remove getAutomatedComments from SCM interface and all implementations
* fix: address all PR review comments
- gh-trace: make binary resolution async via fs.access (no event loop
blocking, no shell injection), cache mkdir for trace writes, async
fire-and-forget appendFile, document 10MB maxBuffer rationale
- lifecycle-manager: log detectPR failures via observer instead of
silent catch, add getPRState fallback for terminal states
(merged/closed) when batch enrichment cache misses
- scm-gitlab: implement getReviewThreads with bot+human threads and
isBot flag, fixing silent feature regression after
getAutomatedComments removal
- scm-github: clear reviewThreadsCache in invalidatePRCache, document
first:11 CI checks cost budget
- runtime-tmux: use printf+JSON.stringify for PATH export to prevent
shell injection from single quotes
- agent-workspace-hooks: add cache timestamp sanity check, include
--repo in cache keys to prevent cross-repo collisions
- services: document dashboard dependency on CLI polling
- tests: update gh binary path assertions for resolved paths
* fix: address all 17 PR review comments
- gh-trace: use path.delimiter, cache-only-on-success, last HTTP status
line, await writes with warn-once, redact secrets, gate JSON.parse
- agent-workspace-hooks: validate cache keys, redact wrapper trace args,
sha256 cache keys to prevent collisions, 120s TTL ceiling
- session-manager: skip PATH wrappers for claude-code (native hooks)
- types: add deprecation JSDoc for getReviewThreads
- graphql-batch: clear Guard 3 in clearETagCache, re-read ETag on 304,
switch Guard 2 to check-runs endpoint, drop per_page=1 from Guard 3
- Add gh-trace unit tests for extractOperation, redactArgs, parseHttp
---------
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
Co-authored-by: adil <adil.business4064@gmail.com>
Co-authored-by: iamasx <adilshaikh4064@gmail.com>
- platform.ts: add windowsHide:true to pwsh/powershell/taskkill/netstat
spawns so AO no longer flashes a console window for each subprocess.
- script-runner.ts: auto-detect Git Bash at the common install paths on
Windows when AO_BASH_PATH is unset; tighter error if neither auto-detect
nor override succeeds. WSL bash intentionally excluded — invoking it
from Windows-native Node mixes Linux paths with Windows cwd and
silently breaks repo scripts. Also adds windowsHide:true to the spawn.
- web/services.ts: register @aoagents/ao-plugin-runtime-process so the
dashboard can spawn sessions on projects using runtime: process
(the Windows default per getDefaultRuntime).
- pty-client.ts: chunk ptyHostSendMessage into 512-char frames with a
15ms gap so large prompts (~3-4KB+) are no longer truncated by
ConPTY's input buffer. Cross-platform safe; Unix PTYs absorb chunks
at full speed. Trailing Enter still sent as a separate frame after
the existing 300ms pause.
- Mock test helpers updated to handle the (cmd, args, options, callback)
arity introduced by passing windowsHide; new test covers Git Bash
auto-detection.
Resolve tmux-utils.ts conflict: rewrite resolvePipePath to read
runtimeHandle.data.pipePath from on-disk session metadata instead of
recomputing a hash from AO_CONFIG_PATH. Mirrors the storageKey
disambiguation pattern upstream introduced for resolveTmuxSession in
PR #1488 (eca3001c). Recomputing the hash drifted from the runtime's
deriveStorageKey on Windows (raw backslash paths vs POSIX-normalized),
so the dashboard's named-pipe relay was connecting to the wrong path
and falling back to ENOENT while ao session attach worked fine.
Also normalize path separators in 6 upstream resolveTmuxSession tests
that hard-coded Unix forward slashes in their exists() mocks; on
Windows path.join produces backslashes and the assertions never
matched.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
runtime-process:
- Reserve the per-instance processes-map slot before the platform split
so the Windows ConPTY branch participates in duplicate-create detection
and getMetrics/getAttachInfo bookkeeping. Previously, Windows returned
a handle without storing it, so duplicate session IDs were silently
accepted and getMetrics always reported 0 uptime.
- Add 500ms graceful-exit poll before SIGKILLing the pty-host on destroy
so node-pty can dispose its ConPTY handle. Skipping this orphaned the
conpty_console_list_agent helper and triggered Windows Error Reporting
dialogs (0x800700e8) on real runs, not just tests.
- pty-host: install SIGTERM/SIGINT/SIGHUP/SIGBREAK/beforeExit handlers
that drive the same shutdown sequence (kill pty, drop clients, close
pipe, exit after 50ms grace), and route MSG_KILL_REQ through the same
path. Previously MSG_KILL_REQ only called pty.kill() and left the host
process lingering.
- Add windowsHide:true to the pty-host child spawn so node-pty's helper
console window stays hidden on errors.
workspace-worktree: normalize paths to a comparable POSIX form
(backslash→slash, lowercase drive letter) when matching git worktree
list --porcelain output against project directories. git emits
forward-slash paths on Windows; path.join produces native backslashes
— the comparison failed and list() returned empty.
agent-opencode: guard tmux/ps usage with isWindows() in isProcessRunning
so process-runtime sessions on Windows take the PID-signal path instead
of attempting Unix-only commands.
cli/start: detect Windows local paths in isLocalPath (drive letter
prefix, UNC path, .\, ..\) so spawn arguments like C:\... aren't
mistaken for project names.
integration test: replace cat + /tmp with platform-native echo (findstr
"x*" on Windows, cat on Unix) and os.tmpdir(); the original used
Unix-only tooling and would never run on Windows.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
* feat: add zsh completion for ao (#1371)
Add a generated zsh completion command and dynamic completion backend so ao can tab-complete projects and session IDs without relying on jq or brittle text parsing. Document standard zsh and Oh My Zsh install paths, and cover the new flow with CLI tests.
* fix(cli): address copilot completion review feedback for PR 1374
* fix completion and harden local workflow parsing
* Update packages/cli/src/lib/completion.ts
Co-authored-by: greptile-apps[bot] <165735046+greptile-apps[bot]@users.noreply.github.com>
* fix completion regressions and agent-ci review feedback
---------
Co-authored-by: greptile-apps[bot] <165735046+greptile-apps[bot]@users.noreply.github.com>
The shared gh wrapper now extracts PR URLs with a regex instead of embedding a literal github URL, so the old codex assertion was stale and broke CI on PR #1300.
Represent missing activity probes as first-class signal states so lifecycle inference only treats valid idle evidence as proof. This prevents false stuck transitions, keeps API/UI lifecycle truth aligned, and makes root monorepo verification deterministic by serializing recursive build and typecheck.
Token sources in streamCodexSessionData are precedence-ordered via `continue`.
`total_token_usage` is a cumulative snapshot (overwrite) while the others are
per-turn deltas (accumulate) — document this so a future reader doesn't "fix"
the asymmetry and break cumulative totals.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
- Use ?? instead of || for ownerRepo fallback (semantically correct for
null-to-undefined conversion)
- Extract requireRepo() result into a local variable in tracker-gitlab's
updateIssue and issueUrl to avoid redundant validation calls
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
- Make `repo` field optional in ProjectConfig and Zod schema so projects
without a detected GitHub remote can still load and run
- Remove placeholder `repo: "owner/repo"` from autoCreateConfig() and
addProjectToConfig() — omit the field entirely when no remote is found
- Always use actual workingDir for `path` instead of unreliable `~/<projectId>`
fallback for non-git directories
- Add null guards for `project.repo` across SCM plugins, tracker plugins,
lifecycle manager, webhooks, and prompt builders to prevent crashes when
repo is not configured
Closes#1154
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Resolved conflict in orchestrator-prompt.ts — kept "runtime session"
wording (Windows-aware) and took main's additions for prompt-driven
session naming and freeform --prompt spawning docs.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
- session.ts/status.ts: use session.lastActivityAt on Windows (no tmux)
- session-manager.ts: stabilize ConPTY output before sending post-launch prompt
to prevent prompts being swallowed during agent startup splash screen
- pty-client.ts: split message + Enter into two writes (300ms gap) to match
tmux send-keys behavior; fix isAlive to return true while pipe is connectable
regardless of whether the agent process inside has exited
- pty-host.ts: keep named pipe server alive after agent exits (mirrors tmux
session persistence) so clients can still attach and view scrollback
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Use a single StringDecoder across reads so multi-byte UTF-8 sequences
that straddle the 8KB chunk boundary buffer correctly instead of
producing U+FFFD replacement characters that break JSON.parse.
Also fix the test mock: makeFakeFileHandle now advances an internal
cursor and returns bytesRead: 0 at EOF. The prior mock copied from
offset 0 every call, which would infinite-loop readJsonlPrefixLines
for any line larger than the 8192-byte chunk size.
Add a regression test using 3,000 CJK characters (9,000 bytes of
payload) to exercise the chunk boundary path.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Real Codex sessions emit records like
`{"type":"event_msg","payload":{"type":"error",...}}` and
`{"type":"event_msg","payload":{"type":"approval_request",...}}`.
readLastJsonlEntry only exposed the top-level `type`, so the codex
plugin's activity switch matched `event_msg` and decayed to ready/idle,
never surfacing `blocked` or `waiting_input`. The approval_request/error
branches were dead code for payload-wrapped sessions, which is the exact
format this PR series is migrating to.
- readLastJsonlEntry now returns payloadType alongside lastType.
- Codex getActivityState prefers payloadType when present and classifies
task_started/agent_reasoning as active, task_complete as ready, and
the approval/error variants as waiting_input/blocked.
- New tests cover the payload-wrapped approval_request, exec_approval_request,
error, task_started, and task_complete cases end-to-end.
- Core utils gains coverage for payloadType extraction and null fallbacks.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* chore: release 0.2.5
Realign main with npm registry after off-branch publish of 0.2.3/0.2.4.
Bump all 21 linked packages to 0.2.5 and cherry-pick the startup-grace-period
fix for #989 (was in 5e4244a8 but never merged to main).
Also sync non-linked plugin versions (notifier-discord, notifier-openclaw,
scm-gitlab, tracker-gitlab) to their current npm versions.
* Revert "chore: release 0.2.5"
This reverts commit eb17f32834.
* chore: bump all package versions to 0.2.5, remove release workflow
- Bump all 25 packages to 0.2.5 to realign with npm registry
- Update package-version test to expect 0.2.5
- Remove stale .changeset/linear-spawn-branch-name.md
- Delete .github/workflows/release.yml (changesets-based NPM publish)
---------
Co-authored-by: Prateek <karnalprateek@gmail.com>
Co-authored-by: AO Bot <ao-bot@composio.dev>
- Fix CI diff coverage and review feedback
- Fix test reliability for session attach, stop, and Windows attach
- Add coverage for session attach binary protocol and edge cases
- Clean up stdin listener + add resolvePipePath tests
- Address review comments + coverage for pipe relay
- Make 80 failing tests pass on Windows (cross-platform mocks, path assertions)
- Fix production code: execFile shell option for .cmd, isPathInside separator,
openclaw binary detection via `where` on Windows
- Add platform-aware test assertions for shell escaping, PATH handling, hooks
- Add signal forwarding comment for Windows dashboard process
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
- session.ts: restore isOrchestratorSession from core (checks both name
and metadata role) instead of name-only isOrchestratorSessionName
- session.ts: remove unused allSessionPrefixes after merge conflict
- start.test.ts: update stop command tests for sm.list() flow
- toClaudeProjectPath: remove speculative space replacement, keep only
verified chars (/ : .) — addresses review comment about Unix breakage
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
- cli/session: add Windows ao session attach via named pipe relay with
raw stdin mode and Ctrl+\ to detach; skip getTmuxActivity on Windows
- cli/start: fix ao stop looking for "tr-orchestrator" instead of the
actual numbered session (e.g. tr-orchestrator-5) — also fixes Linux
- agent-claude-code: fix toClaudeProjectPath dropping Windows drive colon
(C:\→C- not C) breaking JSONL lookup; ignore stale JSONL entries from
previous sessions in reused worktrees
- pty-client: use \r (carriage return) instead of \n for PTY Enter key
Addresses blockers W13 (partial), W14.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Windows equivalent of the tmux daemon. Per-session detached pty-host.js
process owns a ConPTY (via node-pty), listens on a named pipe
(\.\pipe\ao-pty-{hash}-{sessionId}), and relays terminal I/O to any
connected client.
- runtime-process: spawn pty-host on Windows, route sendMessage/getOutput/
isAlive/destroy through named pipe protocol
- mux-websocket: named pipe relay for dashboard terminal (skip TerminalManager
on Windows), resolvePipePath via generateConfigHash (instant, no pipe scan)
- direct-terminal-ws: use real mux server on Windows instead of placeholder
- tmux-utils: findTmux returns null on Windows, resolvePipePath added
- orchestrator-prompt: runtime-agnostic language
- opencode: fix isProcessRunning tmux-before-guard bug (W29)
Addresses blockers W01-W12, W23, W24, W28, W29, W33-W35.
Unix behavior completely unchanged.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Fix shell injection vulnerability when combining systemPromptFile with
prompt. The prompt could contain shell metacharacters ($(), backticks)
that would be executed inside the double-quoted string.
Now uses the exact same pattern as OpenCode:
"$(cat 'file'; printf '\n\n'; printf %s 'prompt')"
The shellEscape wraps prompt in single quotes (no shell expansion),
and printf %s outputs it literally without interpretation.
Co-Authored-By: Claude <noreply@anthropic.com>
Use $(cat file) shell substitution instead of inlining file content
to avoid tmux truncation for large system prompt files (2000+ chars).
This matches the pattern used by Claude Code, Aider, and OpenCode.
- Replace readFileSync with $(cat) in getLaunchCommand
- Remove unused readFileSync import
- Update tests to verify shell substitution behavior
Co-Authored-By: Claude <noreply@anthropic.com>
1. Add symlink check for .cursor directory in extractCursorSummary
to match getCursorSessionMtime behavior (prevents path traversal)
2. Add vitest alias for @aoagents/ao-plugin-agent-cursor in CLI tests
(fixes missing module resolution in tests)
3. Add lstatSync check before readFileSync in getLaunchCommand
to reject symlinked systemPromptFile paths (security hardening)
4. Add test coverage for symlink rejection behavior
Co-Authored-By: Claude <noreply@anthropic.com>
- Resolve @composio → @aoagents package renaming conflicts
- Add cursor agent to BUILTIN_PLUGINS in plugin-registry.ts
- Add cursor agent to AGENT_PLUGINS in detect-agent.ts
- Add cursor agent import and registration in plugins.ts
- Add cursor agent dependency and import in web services.ts
- Update cursor plugin package naming to @aoagents/ao-plugin-agent-cursor
- Add cursor agent to changeset linked group
- Fix test imports to use new @aoagents package naming
Co-Authored-By: Claude <noreply@anthropic.com>
Priyanshu Choudhary
Dhruv Sharma
yyovil
Ashish Huddar
harshitsinghbhandari
Harshit Singh Bhandari
Adil Shaikh
adil
yyovil
i-trytoohard
Gautam Tayal