Commit Graph

951 Commits

Author SHA1 Message Date
YeonGyu-Kim 268c89c945 fix(background-agent): coalesce rapid-fire idle parent notifications
When many background tasks complete in rapid succession while the parent
session is idle, each completion fired its own promptAsync call, stacking
N consecutive `<system-reminder>` user messages with no assistant turn
between. Hyperplan + many parallel explore subagents made this very
visible to the user.

Route the idle-path through the existing pendingParentWakes queue with a
100ms debounce window. Notifications arriving during the debounce join
the same batch, the 150ms settle window also coalesces newcomers, and a
single batched prompt fires to the parent. Busy-path semantics are
unchanged (still 1s retry).

Prior attempts (1c05c60dc, ea55c385b, a337635e3) all coalesced only the
busy-defer path, leaving the idle-immediate-send path uncoalesced.
2026-05-14 18:52:28 +09:00
YeonGyu-Kim b9beea1039 feat(team-mode): drive immediate teardown and recreate-to-reshape loop
Reframe the skill's Lifecycle section so the lead treats teams as
ephemeral, one-per-phase units. The moment a phase ends or the shape
no longer fits, call team_delete and spawn a fresh team. Restructure
through delete-then-create, never in place.

Also fixes a misframing in old step 5: team_shutdown_request is a
per-session self-shutdown signal, not a 'wind down the team' command.
team_delete is what tears the whole team down.
2026-05-14 18:22:30 +09:00
YeonGyu-Kim 1e7a7600a2 docs(agents-md): regenerate hierarchical AGENTS.md knowledge base for v4.1.1
Refresh all AGENTS.md files to reflect codebase state at 5ffbe0e24 (was cd31d2a1a, 197 commits behind).

Key drift corrections across 45 modified + 1 new file:

Root AGENTS.md:
- TS file counts: 1967 -> 2034 in src/ (1337 source + 697 test)
- LOC: 278k -> 292k
- Barrel index.ts: 120 -> 122
- Hook tier composition: 52/59 -> 54/61 (base/with team-mode)
- Tool Guard hooks: 14 -> 16 (add fsync-skip-warning, bash-file-read-guard)
- Add boulder feature, agent-ordering schema, .agents/ directory, v4.1.1 release tag
- Add generated/ directory entry

src/AGENTS.md:
- Subsystem inventory: agents 96->102, hooks 570->581, tools 306->314,
  features 389->400, shared 258->278, cli 150->158, plugin 55->56
- LOC totals refreshed for every subsystem
- Schema files: 32 -> 30

src/hooks/AGENTS.md:
- Tier 2 (Tool Guard): 14 -> 16 hooks, add fsyncSkipWarning row
- Total: 52 base / 59 team-mode -> 54 base / 61 team-mode
- zauc-mocks count: 7 -> 5

src/features/AGENTS.md:
- background-agent: 47 -> 57 files, mention archive fallback
- opencode-skill-loader: 33 -> 30
- tmux-subagent: 34 -> 32

src/plugin/AGENTS.md:
- Tool Guard composer count: 14 -> 16
- Aggregator total: 43 -> 45

src/cli/AGENTS.md:
- Add new boulder subcommand (BoulderState inspector)
- Command count: 6 -> 7

NEW: src/features/boulder-state/AGENTS.md
- Document the new Boulder work tracking feature
- Schema v2 with BoulderState/BoulderWorkState/TaskSessionState
- Lifecycle, storage, integration points with atlas/ralph-loop hooks

All other AGENTS.md files: Generated date 2026-05-08 -> 2026-05-14.
2026-05-14 12:57:46 +09:00
YeonGyu-Kim ea55c385bb fix(background-agent): defer busy parent notifications 2026-05-14 00:45:36 +09:00
YeonGyu-Kim a337635e3b fix(background-agent): defer active parent wakes 2026-05-13 17:02:17 +09:00
YeonGyu-Kim 6035a551ad fix(background-agent): route session prompts by directory 2026-05-12 18:13:39 +09:00
YeonGyu-Kim d5fbada13d test: make unsafe test coercion explicit
Move test coercion out of a hidden global and require each test to import the helper so review tools and runtime scripts can see the unsafe boundary.

Ultraworked with [Sisyphus](https://github.com/code-yeongyu/oh-my-openagent)

Co-authored-by: Sisyphus <clio-agent@sisyphuslabs.ai>
2026-05-12 15:51:31 +09:00
YeonGyu-Kim 11b3638493 test(features): remove unsafe test assertions
Ultraworked with [Sisyphus](https://github.com/code-yeongyu/oh-my-openagent)

Co-authored-by: Sisyphus <clio-agent@sisyphuslabs.ai>
2026-05-12 15:41:17 +09:00
YeonGyu-Kim 07797e1975 fix(background-agent): preserve direct all-complete replies 2026-05-12 15:28:35 +09:00
YeonGyu-Kim d82f6a6024 fix(background-agent): refresh stale todo state 2026-05-12 13:28:40 +09:00
YeonGyu-Kim 8e07ef642e fix(mcp-oauth): use fixed localhost base for callback URL parsing
Cubic AI reviewer flagged the use of the untrusted Host header as the
URL base in startCallbackServer. The server only binds to 127.0.0.1,
so hardcoding "http://127.0.0.1" as the URL base is robust against
malformed or manipulated Host values and matches upstream behavior
prior to the node:http refactor.
2026-05-12 12:54:24 +09:00
YeonGyu-Kim 22c7e4eb8e refactor(mcp-oauth): replace Bun.serve with node:http in callback-server
The OAuth callback server was using Bun.serve, which would crash if
mcp-oauth code paths ever entered the plugin bundle. Switch to
node:http.createServer with the same WHATWG behavior:

- Binds to 127.0.0.1, preserves 200/400/404 status codes
- Translates fetch(Request)→Response to (req, res) callback style
- Clears OAuth timeout on success/error/missing-param paths
- Replaces server.stop(true) with server.close() for shutdown

Functional behavior and response bodies unchanged.
2026-05-12 12:46:50 +09:00
YeonGyu-Kim 0aafe20a85 refactor: route raw Bun.file/write/hash/which/spawn through runtime shims
Eliminates 19 unguarded `Bun.*` runtime call sites in the plugin bundle
that crashed with `ReferenceError: Bun is not defined` under Electron.

Per-tool-call hot paths (executed on every Read/Edit):
- src/tools/hashline-edit/hash-computation.ts: Bun.hash.xxHash32 → bunHashXxh32
- src/tools/hashline-edit/hashline-edit-executor.ts: 8 sites via bunFile/bunWrite
- src/hooks/hashline-read-enhancer/hook.ts: Bun.file → bunFile
- src/hooks/hashline-edit-diff-enhancer/hook.ts: 2 sites via bunFile

Plugin-load paths:
- src/hooks/claude-code-hooks/config.ts and config-loader.ts: Bun.file → bunFile
- src/features/claude-code-mcp-loader/loader.ts: Bun.file → bunFile
- src/features/claude-code-plugin-loader/mcp-server-loader.ts: Bun.file → bunFile
- src/features/team-mode/deps.ts: Bun.spawn → spawn shim
- src/hooks/session-notification-utils.ts: Bun.which → bunWhich, also drops
  the bare `declare const Bun` ambient declaration
- src/shared/binary-downloader.ts: Bun.write → bunWrite

Pure mechanical API swaps. No control-flow or signature changes.
2026-05-12 12:46:50 +09:00
YeonGyu-Kim 4da48555ee fix(plugin): normalize event session ids
Handle OpenCode session events that carry the session ID under properties.info.id or properties.info.sessionID so background tasks and continuation hooks do not miss idle/error/delete events.

Add regression coverage for nested session.idle events completing background tasks and waking continuation hooks.
2026-05-12 12:32:26 +09:00
YeonGyu-Kim 1c05c60dcc fix(background-agent): replace system-reminder wake with queued notifications 2026-05-11 18:55:36 +09:00
YeonGyu-Kim 90f0971f4f fix(background-agent): handle idle status events 2026-05-11 18:06:22 +09:00
YeonGyu-Kim dd5f77562a fix(boulder-state): missing plan file no longer reports isComplete=true 2026-05-11 14:25:35 +09:00
YeonGyu-Kim ce2f3af001 fix(boulder-state): make completeBoulder idempotent on already-completed works 2026-05-11 14:25:06 +09:00
YeonGyu-Kim fb2f696b47 docs(start-work): document multi-work resume flow in agent template
Ultraworked with [Sisyphus](https://github.com/code-yeongyu/oh-my-openagent)

Co-authored-by: Sisyphus <clio-agent@sisyphuslabs.ai>
2026-05-11 13:41:06 +09:00
YeonGyu-Kim 42db7078af feat(boulder-state): add formatDurationHuman utility
Ultraworked with [Sisyphus](https://github.com/code-yeongyu/oh-my-openagent)

Co-authored-by: Sisyphus <clio-agent@sisyphuslabs.ai>
2026-05-11 13:35:59 +09:00
YeonGyu-Kim 5d823b5078 feat(boulder-state): add task timer + completion helpers
Ultraworked with [Sisyphus](https://github.com/code-yeongyu/oh-my-openagent)

Co-authored-by: Sisyphus <clio-agent@sisyphuslabs.ai>
2026-05-11 13:30:29 +09:00
YeonGyu-Kim 9f500743d1 feat(boulder-state): add session-aware multi-work storage helpers
Ultraworked with [Sisyphus](https://github.com/code-yeongyu/oh-my-openagent)

Co-authored-by: Sisyphus <clio-agent@sisyphuslabs.ai>
2026-05-11 13:28:58 +09:00
YeonGyu-Kim 246e0dca80 feat(boulder-state): add BoulderWorkState and timing fields to types
Ultraworked with [Sisyphus](https://github.com/code-yeongyu/oh-my-openagent)

Co-authored-by: Sisyphus <clio-agent@sisyphuslabs.ai>
2026-05-11 13:24:28 +09:00
YeonGyu-Kim bd4db2acfd Merge pull request #3938 from code-yeongyu/fix/delegate-bg-completion-message
fix(background-agent): retry deferred parent wake
2026-05-11 12:43:38 +09:00
YeonGyu-Kim a5cc498433 fix(background-agent): retry deferred parent wake 2026-05-11 12:38:04 +09:00
YeonGyu-Kim 59209f0659 fix(team-mode): track session-created team runs 2026-05-11 12:37:20 +09:00
YeonGyu-Kim eb6605a87f fix(background-agent): preserve non-sensitive timing in archived tasks
Carry queuedAt and startedAt in sanitized archive snapshots so post-cleanup task output duration remains accurate without retaining prompt content.

Ultraworked with [Sisyphus](https://github.com/code-yeongyu/oh-my-openagent)

Co-authored-by: Sisyphus <clio-agent@sisyphuslabs.ai>
2026-05-11 08:53:44 +09:00
YeonGyu-Kim a4ce0b63b6 fix(background-agent): redact archived prompts and cap fallback archive
Store only sanitized completed-task snapshots in archive to avoid retaining sensitive prompts after cleanup.

Ultraworked with [Sisyphus](https://github.com/code-yeongyu/oh-my-openagent)

Co-authored-by: Sisyphus <clio-agent@sisyphuslabs.ai>
2026-05-11 08:47:39 +09:00
YeonGyu-Kim 6fd1ec3ea8 test(background-agent): align cancel cleanup assertions with archive fallback 2026-05-10 15:05:31 +09:00
YeonGyu-Kim dbaea82b73 fix(background-agent): retain completed tasks via archive fallback after cleanup
MessageAbortedError/worker shutdown could race with scheduled removeTask, leaving background_output's manager.getTask returning 'Task not found' even though the task had completed cleanly.

Fix: add completedTaskArchive (max 500, FIFO eviction). On removeTask, archive non-running/pending tasks with sessionId. getTask falls back to archive on active-map miss. addTask clears stale archive entries on re-registration.

Fixes #3895
2026-05-10 14:56:28 +09:00
YeonGyu-Kim 862a2df0db fix(delegate-task): pause timeouts for active sessions 2026-05-10 13:52:22 +09:00
YeonGyu-Kim 5a4127cc8a fix(background-agent): defer busy parent wake 2026-05-10 13:40:41 +09:00
YeonGyu-Kim d801c88888 fix(team-mode): preserve member context on retry 2026-05-10 13:11:52 +09:00
YeonGyu-Kim b36389ef2c fix(team-mode): keep member communication tools visible 2026-05-10 12:54:16 +09:00
YeonGyu-Kim 1bb36314bd feat(tmux-subagent): add event handlers for session lifecycle 2026-05-08 17:44:19 +09:00
YeonGyu-Kim c69d6bd964 fix(team-mode): tolerate EPERM during fsync in atomicWrite and acquireLock
Replaces direct fileHandle.sync() calls in acquireLock and atomicWrite
with tolerantFsync. Users on iCloud Drive / OneDrive / Desktop sync
folders were hitting 'EPERM: operation not permitted, fsync' during
team_create, which propagated up and aborted the entire team_create
flow even though the actual write+rename had succeeded.

Reported on Discord (omo 4.0.0, opencode desktop 1.14.41, project on
synced Desktop). atomicity is preserved by the temp-file rename; only
the durability hint is now best-effort on filesystems that disallow
fsync.
2026-05-08 14:09:16 +09:00
YeonGyu-Kim c7d6a4a2ce fix: remove dead-code files accidentally resurrected by previous commit
The previous commit (2dfa6336f) used 'git add -A' which swept up files that
prior commits had intentionally deleted but were still present untracked in
the local workspace. This commit re-deletes them to match the upstream intent.

Files removed (each was previously deleted in the cited commit):

- drafts/gpt-5-5/{README,deep,hephaestus,oracle,sisyphus-junior,sisyphus}.md
  (deleted in 40ded422c chore(drafts): remove stale gpt-5.5 prompt drafts)
- src/plugin-dispose.{ts,test.ts}
  (deleted in e2f5c0d36 refactor(plugin): remove orphaned createPluginDispose)
- src/features/tmux-subagent/{cleanup,session-created-handler,session-deleted-handler}.ts
  (deleted in 7a7926f22 chore(tmux-subagent): remove dead event-handler modules)
- src/tools/delegate-task/{model-string-parser,resolve-call-id,resolve-call-id.test}.ts
  (model-string-parser deleted in db056346d; resolve-call-id was scratch)
- src/__debug-test.test.ts (debug scratch never intended for git)

Typecheck + model-requirements tests still pass. The legitimate metis +
AGENTS.md edits from the previous commit remain on dev.
2026-05-08 13:08:16 +09:00
YeonGyu-Kim 2dfa6336f5 fix(metis): switch primary model to claude-sonnet-4-6 + correct AGENTS.md inaccuracies
Source code change:
- src/shared/model-requirements.ts: prepend claude-sonnet-4-6 to metis fallback
  chain so Sonnet becomes the default. Opus 4.7 max remains as the immediate
  fallback for callers who want extra reasoning.
- src/shared/model-requirements.test.ts: update assertion to expect Sonnet
  primary + Opus secondary.

AGENTS.md accuracy fixes (verified against source):
- Agent modes: Sisyphus/Hephaestus are 'primary' (not 'all'); Sisyphus-Junior
  is 'subagent' (not 'all'). Confirmed via 'const MODE: AgentMode = ...' in
  each agent file. Also clarified Prometheus has no agentSources factory and
  is built via buildPrometheusAgentConfig.
- Sisyphus fallback chain: corrected order to kimi-k2.6 → k2p5 → kimi-k2.5
  → gpt-5.5 medium → glm-5 → big-pickle (was missing kimi-k2.5).
- Librarian/Explore: added missing minimax-m2.7 step between -highspeed and
  claude-haiku-4-5.
- Metis chain: removed fictitious gemini-3.1-pro entry.
- Sisyphus-Junior chain: spelled out the actual fallback (was 'user-configurable').
- Temperatures: Sisyphus/Hephaestus do not set explicit temperature (model
  default); Sisyphus-Junior is 0.1 via SISYPHUS_JUNIOR_DEFAULTS.
- Quick category default: gpt-5.4-mini (not gpt-5.4-mini-fast).

Team-mode corrections:
- Eligibility registry has 3 verdicts: eligible (sisyphus, atlas, sisyphus-junior),
  conditional (hephaestus — needs D-36 teammate permission), hard-reject
  (oracle, librarian, explore, multimodal-looker, metis, momus, prometheus).
- Schema has 11 fields, not 4: added max_messages_per_run, max_wall_clock_minutes,
  max_member_turns, base_dir, message_payload_max_bytes, recipient_unread_max_bytes,
  mailbox_poll_interval_ms.
- Hooks: 'team-session-events' is 4 sub-handlers in src/plugin/event.ts
  (team-idle-wake-hint, team-lead-orphan-handler, team-member-error-handler,
  team-member-status-handler), not a single Continuation-tier hook.
- Tier counts now show base + team-mode: ToolGuard 14/15, Transform 5/7.
- Total: 52 base hooks, 59 with team-mode.

Doc cascade for the Metis change:
- docs/guide/orchestration.md, agent-model-matching.md, installation.md
- docs/reference/configuration.md, features.md
2026-05-08 13:06:34 +09:00
YeonGyu-Kim 838b5ae216 docs(agents): refresh hierarchical AGENTS.md with team-mode coverage
Update root + 43 directory-level AGENTS.md files to reflect current state:
- Root AGENTS.md rewritten with accurate counts (1967 TS files, 1304 source +
  663 test, 278k LOC, 120 barrel index.ts), 7-step init flow, 5-tier hook
  composition, and full Team Mode section (12 team_* tools, eligibility,
  storage layout, config gate)
- src/AGENTS.md adds team-mode init step, current per-subdir file/LOC table
- src/tools/AGENTS.md documents conditional gates (team-mode +12, task
  system +4, hashline +1, interactive_bash +1, look_at +1) with always-on
  baseline of 20
- src/hooks/AGENTS.md splits into 5 tiers + 4 conditional team-mode hooks
- src/features/team-mode/AGENTS.md surfaces 12 tools, eligible agents,
  spawn-race-safe invariants, and integration points
- src/features/builtin-skills/AGENTS.md tracks 10 skills incl. team-mode
- src/agents/AGENTS.md, src/plugin/AGENTS.md, src/config/AGENTS.md updated
  for team-mode awareness, accurate counts, and current schema field list
- All other AGENTS.md files refreshed to 2026-05-08 generation date
2026-05-08 12:08:42 +09:00
YeonGyu-Kim ee938aa097 fix full-suite isolation regressions 2026-05-07 18:36:03 +09:00
YeonGyu-Kim 7bd863b214 Merge pull request #3813 from code-yeongyu/fix/agent-name-backslash-sanitize
fix(agent): sanitize backslash/quote from agent name
2026-05-06 18:14:39 +09:00
YeonGyu-Kim d9ef03f1a5 test(agent): guard queueItem assertion against empty queue race 2026-05-06 17:50:11 +09:00
YeonGyu-Kim 25d183fbe8 fix(agent): sanitize backslash/quote from agent name in launch() and background-executor
Agent names like \hephaestus\ cause 'Agent not found' errors because
sanitizeSubagentType() was only called in subagent-resolver.ts but not
in the direct manager.launch() path or background-executor.ts.

- manager.ts: strip leading/trailing backslash/quote chars from input.agent
  before validation so \hephaestus\ → hephaestus
- background-executor.ts: call sanitizeSubagentType(args.subagent_type)
  instead of passing raw value to manager.launch()
- agent-display-names.ts: reuse sanitizeSubagentType in stripAgentListSortPrefix
- Add unit tests for all three fix points

Fixes: sessions dying with 'Agent not found: \hephaestus\'
2026-05-06 17:41:41 +09:00
YeonGyu-Kim 89c959955a fix(team-mode): gate tmux layout cleanup by config
Ultraworked with [Sisyphus](https://github.com/code-yeongyu/oh-my-openagent)

Co-authored-by: Sisyphus <clio-agent@sisyphuslabs.ai>
2026-05-06 17:36:03 +09:00
YeonGyu-Kim b4791c85ca fix(team-mode): keep tmux visualization in caller window
Ultraworked with [Sisyphus](https://github.com/code-yeongyu/oh-my-openagent)

Co-authored-by: Sisyphus <clio-agent@sisyphuslabs.ai>
2026-05-06 17:36:03 +09:00
YeonGyu-Kim 675f7880fe fix(team-mode): resolve caller tmux window target
Ultraworked with [Sisyphus](https://github.com/code-yeongyu/oh-my-openagent)

Co-authored-by: Sisyphus <clio-agent@sisyphuslabs.ai>
2026-05-06 17:36:03 +09:00
YeonGyu-Kim 7ac1109611 Merge pull request #3636 from lucasyounger/codex/fix-3629-worktree-plan-path
fix(boulder): resolve continuation progress from worktree plan
2026-05-06 17:15:21 +09:00
YeonGyu-Kim d1a7c8f17a Merge pull request #3096 from s2mr/fix/git-master-language-agnostic-support
docs(git-master): make language handling generic (incl. Japanese examples)
2026-05-06 16:40:56 +09:00
YeonGyu-Kim 3749656a2b Merge pull request #3784 from matchai/chore/remove-redundant-env-restore
test: remove redundant local env restoration
2026-05-06 15:44:54 +09:00
YeonGyu-Kim 2d37df48c1 refactor(team-mode): use dedicated focus and grid windows for team layout
Replace in-window pane splitting with two purpose-built windows
(focus: main-vertical, grid: tiled) created off the target session,
so leader pane is never disturbed and layouts no longer collapse
under teammate count.

🤖 Generated with assistance of [OhMyOpenCode](https://github.com/code-yeongyu/oh-my-opencode)
2026-05-06 14:20:50 +09:00