Commit Graph

7 Commits

Author SHA1 Message Date
YeonGyu-Kim 1833fdb74a fix(call-omo-agent): add finally cleanup for sync executor session Sets
Sync call_omo_agent leaked entries in global activeSessionMessages
and activeSessionToolResults Sets when execution threw errors,
since cleanup only ran on success path.

- Wrap session Set operations in try/finally blocks
- Ensure Set.delete() runs regardless of success/failure
- Add guard against double-cleanup

Tests: 2 pass, 14 expects
2026-03-12 01:37:02 +09:00
YeonGyu-Kim d2526878b6 Count sync subagent spawns against descendant limits 2026-03-11 20:50:11 +09:00
YeonGyu-Kim 3a0af4d2ce fix: align sync fallback chain, fix model-fallback test determinism
- Hoist resolveFallbackChainForCallOmoAgent before sync/background branch
  so sync executor also receives the fallback chain
- Add fallbackChain parameter to sync-executor with setSessionFallbackChain
- Mock connected-providers-cache in event.model-fallback tests for
  deterministic behavior (no dependency on local cache files)
- Update test expectations to account for no-op fallback skip when
  normalized current model matches first fallback entry
- Add cache spy isolation for subagent-resolver fallback_models tests
2026-03-09 13:11:03 +09:00
YeonGyu-Kim 15bfd4e963 fix(tools/call-omo-agent): replace as any with SessionWithPromptAsync type
Add SessionWithPromptAsync local type for promptAsync access

Remove as any cast from session.promptAsync call

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

Co-authored-by: Sisyphus <clio-agent@sisyphuslabs.ai>
2026-02-23 02:42:37 +09:00
YeonGyu-Kim c8dc03d75d refactor(call-omo-agent): inject executeSync dependencies for tests 2026-02-14 22:06:23 +09:00
YeonGyu-Kim d16073aa59 refactor: remove redundant subagent-question-blocker hook
Replace PreToolUse hook-based question tool blocking with the existing
tools parameter approach (tools: { question: false }) which physically
removes the tool from the LLM's toolset before inference.

The hook was redundant because every session.prompt() call already passes
question: false via the tools parameter. OpenCode converts this to a
PermissionNext deny rule and deletes the tool from the toolset, preventing
the LLM from even seeing it. The hook only fired after the LLM already
called the tool, wasting tokens.

Changes:
- Remove subagent-question-blocker hook invocation from PreToolUse chain
- Remove hook registration from create-session-hooks.ts
- Delete src/hooks/subagent-question-blocker/ directory (dead code)
- Remove hook from HookNameSchema and barrel export
- Fix sync-executor.ts missing question: false in tools parameter
- Add regression tests for both the removal and the tools parameter
2026-02-13 14:55:46 +09:00
YeonGyu-Kim 146ad3e2d9 refactor(tools/call-omo-agent): split tools.ts into focused modules under 200 LOC
- Extract getMessageDir to message-dir.ts
- Extract executeBackground to background-executor.ts
- Extract session creation logic to session-creator.ts
- Extract polling logic to completion-poller.ts
- Extract message processing to message-processor.ts
- Create sync-executor.ts to orchestrate sync execution
- Add ToolContextWithMetadata type to types.ts
- tools.ts now <200 LOC and focused on tool definition
2026-02-08 17:37:44 +09:00