Commit Graph

925 Commits

Author SHA1 Message Date
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
YeonGyu-Kim 503df29195 fix(team-mode): register spawned sessions early 2026-05-06 14:20:50 +09:00
YeonGyu-Kim cb819307ff fix(team-mode): stop tmux freeze when many teammates spawn
Drop the per-pane select-pane title shuffle and the cyan border styling that leaked to window scope, then switch from main-vertical to tiled when there are 4 or more teammates so each pane keeps a usable height for the opencode TUI.

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

Co-authored-by: Sisyphus <clio-agent@sisyphuslabs.ai>
2026-05-06 14:20:50 +09:00
YeonGyu-Kim e6cd50cc15 fix(team-mode): preserve tmux focus during layout
Ultraworked with [Sisyphus](https://github.com/code-yeongyu/oh-my-openagent)

Co-authored-by: Sisyphus <clio-agent@sisyphuslabs.ai>
2026-05-06 14:20:50 +09:00
YeonGyu-Kim 8f48277e6c fix(builtin-commands): pin hyperplan roster contract
Ultraworked with [Sisyphus](https://github.com/code-yeongyu/oh-my-openagent)

Co-authored-by: Sisyphus <clio-agent@sisyphuslabs.ai>
2026-05-06 14:20:50 +09:00
YeonGyu-Kim ca8732f8fe fix(team-mode): reject incomplete hyperplan teams
Ultraworked with [Sisyphus](https://github.com/code-yeongyu/oh-my-openagent)

Co-authored-by: Sisyphus <clio-agent@sisyphuslabs.ai>
2026-05-06 14:20:50 +09:00
YeonGyu-Kim d737f2e214 test(background-agent): remove forbidden assertions in manager tests
Ultraworked with [Sisyphus](https://github.com/code-yeongyu/oh-my-openagent)

Co-authored-by: Sisyphus <clio-agent@sisyphuslabs.ai>
2026-05-06 14:20:50 +09:00
YeonGyu-Kim c90be7f9a6 feat(team-mode): align member and lead prompts with Claude Code free-code reference
Bring the team member addendum and the team-mode skill in line with the
Claude Code experimental Agent Teams reference (../free-code) on the
behavioral framing the LLM needs, while keeping every omo-specific
constraint (TeamRunId param, lead-only tool blocklist, eligibility
registry, sisyphus-junior routing) intact.

Member addendum (src/features/team-mode/member-guidance.ts) — adopt
free-code teammatePromptAddendum.ts wisdom that was missing:

- "User interacts primarily with the team lead" — members no longer try
  to address the user directly; they coordinate via task system + DMs.
- Stronger emphasis that plain assistant text is invisible to the team;
  team_send_message is mandatory, not optional.
- Broadcast (`to: "*"`) called out explicitly with "sparingly" guidance
  and the lead-only constraint.
- "Idle is normal" section: idle ≠ done, idle teammates can still
  receive messages, the lead must not treat idle as an error.
- "Communication rules" section forbidding structured JSON status
  messages and forbidding terminal tools as a peer-inspection backdoor;
  always reference teammates by NAME, not session ID.
- Auto-delivery framing: messages arrive as new turns, no manual inbox
  polling, no need to quote a teammate's message back to the lead.

Team-mode skill (src/features/builtin-skills/skills/team-mode.ts) —
adopt free-code TeamCreateTool/prompt.ts sections that were missing:

- Task ownership: any agent can set/change `owner` via team_task_update.
- Automatic message delivery: <peer_message ...> envelope flow.
- Teammate idle state: idle is the expected post-turn state; peer DM
  summaries surface in the lead's idle notification.
- Discovering team members: team_status + ~/.omo/teams/ config; refer by
  name, never raw session IDs.
- Task list coordination: claim by ID order (lowest first), check after
  every completion, escalate blocking deadlocks to the lead.
- Communication rules: same anti-patterns as the member addendum, scoped
  for the lead's awareness (no JSON status, no terminal peer-inspection,
  no delegate-task from inside members).

Test (create.test.ts) updated to track the renamed section header
("Lead-only tools you must NOT call") and to lock the new free-code
parity assertions ("user interacts primarily with the team lead",
"Idle is normal", "structured JSON status messages").

All other contract tests (team-mode skill keyword/section tests,
member parser, runtime tests) untouched and still passing.

Generated with assistance of [OhMyOpenCode](https://github.com/code-yeongyu/oh-my-opencode).
2026-05-06 14:20:50 +09:00
YeonGyu-Kim d8f89b6965 fix(team-mode): preserve per-category model for kind:"category" members
The shared resolveCategoryExecution path treats `agents.sisyphus-junior.model`
(plugin config) as a higher-precedence override than the category default. That
ranking is correct for plain `task(category=...)` delegations - it lets users
pin sisyphus-junior to their preferred general model - but in team-mode it
collapses every kind:"category" member onto the same model.

Hyperplan was the visible victim: skeptic/validator/researcher/architect/creative
are routed through sisyphus-junior with five distinct categories
(unspecified-low / unspecified-high / deep / ultrabrain / artistry). With any
sisyphus-junior model configured, all five resolved to that single override
model instead of their category defaults, defeating the multi-model adversarial
debate.

Strip the override at the team-mode boundary in resolveMember rather than
changing resolveCategoryExecution itself, so:
- delegate-task callers keep the existing override semantics (3 regression
  tests at tools.test.ts:2832, 2958, 3020 stay green)
- per-category user overrides (`categories[X].model`) and explicit fallback
  chains continue to apply
- only the `kind:"category"` team-mode path opts out of the global override

Lock the contract with a regression test in resolve-member.test.ts.

Generated with assistance of [OhMyOpenCode](https://github.com/code-yeongyu/oh-my-opencode).
2026-05-06 14:20:50 +09:00
YeonGyu-Kim 09fe4ca3dd fix(hyperplan): align keyword detector and command template with mandatory plan handoff
Update both injection paths to reflect the 7-phase workflow with the
mandatory plan agent handoff in step 7. The keyword detector now lists
all 8 enumerated steps including the explicit "do not write the plan
yourself" guidance, and the /hyperplan command template references the
7-phase workflow count.

Generated with assistance of [OhMyOpenCode](https://github.com/code-yeongyu/oh-my-opencode).
2026-05-06 14:20:50 +09:00
YeonGyu-Kim 5af41606be feat(builtin-commands): register hyperplan builtin command
Ultraworked with [Sisyphus](https://github.com/code-yeongyu/oh-my-openagent)

Co-authored-by: Sisyphus <clio-agent@sisyphuslabs.ai>
2026-05-06 14:20:50 +09:00
YeonGyu-Kim a75a24df77 feat(builtin-commands): add hyperplan command template
Ultraworked with [Sisyphus](https://github.com/code-yeongyu/oh-my-openagent)

Co-authored-by: Sisyphus <clio-agent@sisyphuslabs.ai>
2026-05-06 14:20:50 +09:00
YeonGyu-Kim 592308de1e feat(builtin-commands): add hyperplan to command name type
Ultraworked with [Sisyphus](https://github.com/code-yeongyu/oh-my-openagent)

Co-authored-by: Sisyphus <clio-agent@sisyphuslabs.ai>
2026-05-06 14:20:50 +09:00
YeonGyu-Kim b54922deab fix(team-mode): forbid delegate-task in member guidance
Ultraworked with [Sisyphus](https://github.com/code-yeongyu/oh-my-openagent)

Co-authored-by: Sisyphus <clio-agent@sisyphuslabs.ai>
2026-05-06 14:19:40 +09:00
YeonGyu-Kim 4d448778f3 fix(team-mode): reject empty team_create lead session override
Ultraworked with [Sisyphus](https://github.com/code-yeongyu/oh-my-openagent)

Co-authored-by: Sisyphus <clio-agent@sisyphuslabs.ai>
2026-05-06 14:19:40 +09:00
YeonGyu-Kim d7d956468c docs: add AGENTS.md for team-mode and tmux-subagent features 2026-05-06 14:19:39 +09:00
YeonGyu-Kim 855c848b99 feat(opencode-skill-loader): adapt skill resolution and discovery for team-mode 2026-05-06 14:19:39 +09:00
YeonGyu-Kim 7fbefa4cfe feat(claude-code-loader): adapt plugin discovery for team-mode 2026-05-06 14:19:39 +09:00
YeonGyu-Kim 15a0e10450 feat(background-agent): adapt task poller for team-mode work distribution 2026-05-06 14:19:39 +09:00
YeonGyu-Kim 00a6647021 feat(background-agent): adapt idle event handler for team-mode sessions 2026-05-06 14:19:39 +09:00
YeonGyu-Kim a0d122b1e6 feat(background-agent): integrate team-mode into background manager 2026-05-06 14:19:39 +09:00
YeonGyu-Kim 417a368af8 feat(background-agent): extend types for team-mode background tasks 2026-05-06 14:19:39 +09:00
YeonGyu-Kim 2e6bb3413e feat(builtin-commands): adapt commands and templates for team-mode 2026-05-06 14:19:39 +09:00
YeonGyu-Kim 844dcd4e83 feat(builtin-skills): register team-mode skill in exports 2026-05-06 14:19:39 +09:00
YeonGyu-Kim c9fdb04240 feat(builtin-skills): add team-mode skill implementation with tests 2026-05-06 14:19:39 +09:00
YeonGyu-Kim d3c020c4f9 feat(team-mode): export team-tools barrel 2026-05-06 14:19:39 +09:00
YeonGyu-Kim f2555feadb feat(team-mode): add team tasks tools with tests 2026-05-06 14:19:39 +09:00