Commit Graph

17 Commits

Author SHA1 Message Date
YeonGyu-Kim d5dfaaa3ad fix(delegate-task): remove kimi from unstable agent detection, harden callID resolution for metadata store
- Remove kimi from auto-detected unstable agents in category-resolver (only gemini/minimax remain)
- Add resolveCallID() to safely resolve callID/callId/call_id variants from tool context
- Use resolveCallID across all 5 delegate task execution paths (sync, background, unstable, continuations)
- Update writing category test to verify kimi runs sync when kimi provider is available
- Add atlas metadata preservation tests confirming tool-execute-after does not clobber metadata

Co-authored-by: factory-droid[bot] <138933559+factory-droid[bot]@users.noreply.github.com>
2026-04-05 15:30:36 +09:00
Ryan Dielhenn 571dfe23a4 add bool value: tdd to sisyphus_agent config 2026-03-28 09:34:58 -07:00
YeonGyu-Kim 984464470c fix(task): preserve restricted agent tools in sync continuation
Restore sync continuation to apply agent tool restrictions after permissive defaults so resumed explore and librarian sessions cannot regain nested delegation. Add regression tests for resumed restricted agents while keeping plan-family continuation behavior intact.

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

Co-authored-by: Sisyphus <clio-agent@sisyphuslabs.ai>
2026-03-24 23:54:29 +09:00
YeonGyu-Kim 20b185b59f fix(task): append plan delegation prompt requirements
Ultraworked with [Sisyphus](https://github.com/code-yeongyu/oh-my-opencode)

Co-authored-by: Sisyphus <clio-agent@sisyphuslabs.ai>
2026-03-06 22:56:51 +09:00
YeonGyu-Kim d6b0e564bf feat(delegate-task): unify TUI metadata by adding model field to all 5 executor paths 2026-03-04 18:31:19 +09:00
Lynricsy d09cf56e15 feat(delegate-task): ⚙️ make sync subagent timeout configurable via syncPollTimeoutMs
Allow users to set `background_task.syncPollTimeoutMs` in config to override
the default 10-minute sync subagent timeout. Affects sync task, sync continuation,
and unstable agent task paths. Minimum value: 60000ms (1 minute).

Co-authored-by: Wine Fox <fox@ling.plus>
2026-02-27 16:17:39 +08:00
YeonGyu-Kim 1a6810535c refactor: create normalizeSDKResponse helper and replace scattered patterns across 37 files 2026-02-16 18:20:19 +09:00
YeonGyu-Kim c9c02e0525 refactor(shared): consolidate 13+ getMessageDir copies into single shared function 2026-02-16 16:13:39 +09:00
YeonGyu-Kim f20e1aa0d0 feat: store tool restrictions in session-tools-store at prompt-send sites
Call setSessionTools(sessionID, tools) before every prompt dispatch so
the tools object is captured and available for later retrieval when
background tasks complete.
2026-02-14 14:58:25 +09:00
YeonGyu-Kim 95aa7595f8 feat: include subagent in task_metadata when resuming sessions
When delegate-task resumes a session via session_id, the response
task_metadata now includes a subagent field identifying which agent
was running in the resumed session. This allows the parent agent to
know what type of subagent it is continuing.

- sync-continuation: uses resumeAgent extracted from session messages
- background-continuation: uses task.agent from BackgroundTask object
- Gracefully omits subagent when agent info is unavailable
2026-02-12 19:09:15 +09:00
YeonGyu-Kim 087ce06055 refactor(delegate-task): inject sync task deps for test isolation 2026-02-10 22:54:30 +09:00
YeonGyu-Kim 2b87719c83 docs: document intentional design decisions in atlas, todo-continuation, and delegation hooks 2026-02-10 22:00:54 +09:00
YeonGyu-Kim 231e790a0c fix(sync-continuation): improve error handling and toast cleanup
- Add proper error handling in executeSyncContinuation with try-catch blocks
- Ensure toast cleanup happens in all error paths via finally block
- Add anchorMessageCount tracking for accurate result fetching after continuation
- Improve fetchSyncResult to filter messages after anchor point
- Add silent failure detection when no new response is generated
2026-02-10 22:00:54 +09:00
YeonGyu-Kim 11f587194f fix(delegation): replace message-count-stability polling with native finish-based completion detection
Sync task completion was fragile — detecting premature stability during
brief idle periods between tool calls. Now mirrors opencode's native
SessionPrompt.loop() logic: checks assistant finish reason is terminal
(not tool-calls/unknown) and assistant.id > user.id.

Also switches sync prompt sender from blocking HTTP (promptSync) to
async fire-and-forget (promptAsync) to avoid JSON parse errors in ACP.
2026-02-09 15:37:19 +09:00
YeonGyu-Kim c9be2e1696 refactor: extract model selection logic from delegate-task into focused modules
- Create available-models.ts for model availability checking
- Create model-selection.ts for category-to-model resolution logic
- Update category-resolver, subagent-resolver, and sync modules to import
  from new focused modules instead of monolithic sources
2026-02-08 18:03:15 +09:00
YeonGyu-Kim f3f6ba47fe merge: integrate origin/dev into modular-enforcement branch
Resolves all merge conflicts, preserving our split module structure
while integrating all dev changes:
- Custom agent summaries support (parseRegisteredAgentSummaries)
- Background notification queue (enqueueNotificationForParent)
- Atlas shared git-worktree module (collectGitDiffStats, formatFileChanges)
- Ralph-loop withTimeout + DEFAULT_API_TIMEOUT=5000
- Session recovery assistant_prefill_unsupported error type
- Atlas agentOverrides forwarding
- Config handler plan model demotion (buildPlanDemoteConfig)
- Delegate-task agentOverrides, promptSyncWithModelSuggestionRetry, variant
- LSP init timeout + stale init detection
- isPlanFamily function + task-continuation-enforcer hook
- Handoff command
2026-02-08 17:34:47 +09:00
YeonGyu-Kim 29155ec7bc refactor: wave 1 - extract leaf modules, rename catch-all files, split index.ts hooks
- Split 25+ index.ts files into hook.ts + extracted modules
- Rename all catch-all utils.ts/helpers.ts to domain-specific names
- Split src/tools/lsp/ into ~15 focused modules
- Split src/tools/delegate-task/ into ~18 focused modules
- Separate shared types from implementation
- 155 files changed, 60+ new files created
- All typecheck clean, 61 tests pass
2026-02-08 13:57:26 +09:00