15 Commits

Author SHA1 Message Date
YeonGyu-Kim
0eddd28a95 fix: skip ultrawork injection for plan-like agents (#1501)
Ultraworked with [Sisyphus](https://github.com/code-yeongyu/oh-my-opencode)

Co-authored-by: Sisyphus <clio-agent@sisyphuslabs.ai>
2026-02-07 19:52:47 +09:00
YeonGyu-Kim
f146aeff0f
refactor: major codebase cleanup - BDD comments, file splitting, bug fixes (#1350)
* style(tests): normalize BDD comments from '// #given' to '// given'

- Replace 4,668 Python-style BDD comments across 107 test files
- Patterns changed: // #given -> // given, // #when -> // when, // #then -> // then
- Also handles no-space variants: //#given -> // given

* fix(rules-injector): prefer output.metadata.filePath over output.title

- Extract file path resolution to dedicated output-path.ts module
- Prefer metadata.filePath which contains actual file path
- Fall back to output.title only when metadata unavailable
- Fixes issue where rules weren't injected when tool output title was a label

* feat(slashcommand): add optional user_message parameter

- Add user_message optional parameter for command arguments
- Model can now call: command='publish' user_message='patch'
- Improves error messages with clearer format guidance
- Helps LLMs understand correct parameter usage

* feat(hooks): restore compaction-context-injector hook

- Restore hook deleted in cbbc7bd0 for session compaction context
- Injects 7 mandatory sections: User Requests, Final Goal, Work Completed,
  Remaining Tasks, Active Working Context, MUST NOT Do, Agent Verification State
- Re-register in hooks/index.ts and main plugin entry

* refactor(background-agent): split manager.ts into focused modules

- Extract constants.ts for TTL values and internal types (52 lines)
- Extract state.ts for TaskStateManager class (204 lines)
- Extract spawner.ts for task creation logic (244 lines)
- Extract result-handler.ts for completion handling (265 lines)
- Reduce manager.ts from 1377 to 755 lines (45% reduction)
- Maintain backward compatible exports

* refactor(agents): split prometheus-prompt.ts into subdirectory

- Move 1196-line prometheus-prompt.ts to prometheus/ subdirectory
- Organize prompt sections into separate files for maintainability
- Update agents/index.ts exports

* refactor(delegate-task): split tools.ts into focused modules

- Extract categories.ts for category definitions and routing
- Extract executor.ts for task execution logic
- Extract helpers.ts for utility functions
- Extract prompt-builder.ts for prompt construction
- Reduce tools.ts complexity with cleaner separation of concerns

* refactor(builtin-skills): split skills.ts into individual skill files

- Move each skill to dedicated file in skills/ subdirectory
- Create barrel export for backward compatibility
- Improve maintainability with focused skill modules

* chore: update import paths and lockfile

- Update prometheus import path after refactor
- Update bun.lock

* fix(tests): complete BDD comment normalization

- Fix remaining #when/#then patterns missed by initial sed
- Affected: state.test.ts, events.test.ts

---------

Co-authored-by: justsisyphus <justsisyphus@users.noreply.github.com>
2026-02-01 16:47:50 +09:00
YeonGyu-Kim
96e7b39a83
fix: use _resetForTesting() consistently to prevent flaky tests (#1318)
- Replace setMainSession(undefined) with _resetForTesting() in keyword-detector tests
- Add _resetForTesting() to afterEach hooks for proper cleanup
- Un-skip the previously flaky mainSessionID test in state.test.ts

Fixes #848

Co-authored-by: 배지훈 <new0126@naver.com>
2026-01-31 16:34:07 +09:00
TheEpTic
01500f1ebe
Fix: prevent system-reminder tags from triggering mode keywords (#1155)
Automated system messages with <system-reminder> tags were incorrectly
triggering [search-mode], [analyze-mode], and other keyword modes when
they contained words like "search", "find", "explore", etc.

Changes:
- Add removeSystemReminders() to strip <system-reminder> content before keyword detection
- Add hasSystemReminder() utility function
- Update keyword-detector to clean text before pattern matching
- Add comprehensive test coverage for system-reminder filtering

Fixes issue where automated system notifications caused agents to
incorrectly enter MAXIMUM SEARCH EFFORT mode.

Co-authored-by: TheEpTic <git@eptic.me>
2026-01-28 16:26:37 +09:00
justsisyphus
e47ab084fd fix(keyword-detector): skip ultrawork injection for planner agents
Ultraworked with [Sisyphus](https://github.com/code-yeongyu/oh-my-opencode)

Co-authored-by: Sisyphus <clio-agent@sisyphuslabs.ai>
2026-01-27 17:54:52 +09:00
justsisyphus
5c7eb02d5b
chore(test): sync agent name casing in tests (#1128)
Co-authored-by: justsisyphus <justsisyphus@users.noreply.github.com>
2026-01-26 12:10:30 +09:00
justsisyphus
0e18efc7e4 refactor(keyword-detector): change keyword injection from synthetic to direct message transform
- Replace collector.register() with direct output.parts[textIndex].text modification
- All keyword types (ultrawork, search, analyze) now prepend to user message text
- Message format: keyword message + '---' separator + original text
- Update tests to verify text transformation instead of collector registration
- All 18 tests pass
2026-01-23 01:53:59 +09:00
justsisyphus
fa9bf4590c fix(test): add _resetForTesting to all session state tests 2026-01-17 17:04:40 +09:00
justsisyphus
5ee8996a39 fix(keyword-detector): use session state for agent-specific ultrawork templates
Bug: When switching from Prometheus to Sisyphus, the Prometheus ultrawork
template was still injected because:
1. setSessionAgent() only sets on first call, ignoring subsequent updates
2. keyword-detector relied solely on input.agent which could be stale

Fix:
- Use updateSessionAgent() instead of setSessionAgent() in index.ts
- keyword-detector now uses getSessionAgent() as primary source, fallback to input.agent
- Added tests for agent switch scenario
2026-01-16 19:06:00 +09:00
Kenny
3801e42ccb fix: restore mock in keyword-detector tests 2026-01-14 09:32:05 -05:00
Kenny
9f040e020f
Merge branch 'dev' into fix/ulw-boundary-and-skill-mcp-args 2026-01-14 09:27:59 -05:00
popododo0720
5c4f4fc655 fix: ulw keyword word boundary and skill_mcp parseArguments object handling
- Add word boundary to ulw/ultrawork regex to prevent false matches on substrings like 'StatefulWidget' (fixes #779)
- Handle object type in parseArguments to prevent [object Object] JSON parse error (fixes #747)
- Add test cases for word boundary behavior
2026-01-14 21:36:32 +09:00
Jason Kölker
2b8853cbac
feat(config): add model variant support
Allow optional model variant config for agents and categories.
Propagate category variants into task model payloads so
category-driven runs inherit provider-specific variants.

Closes: #647
2026-01-13 04:37:51 +00:00
YeonGyu-Kim
ce5315fbd0 refactor(keyword-detector): decouple from claude-code-hooks via ContextCollector pipeline
- keyword-detector now registers keywords to ContextCollector
- context-injector consumes and injects via chat.message hook
- Removed keyword detection logic from claude-code-hooks
- Hook order: keyword-detector → context-injector → claude-code-hooks
- ultrawork now works even when claude-code-hooks is disabled
2026-01-11 12:06:16 +09:00
YeonGyu-Kim
b5c1cfb57f fix(keyword-detector): use mainSessionID for session check instead of unreliable API
The keyword-detector was using ctx.client.session.get() to check parentID for
determining subagent sessions, but this API didn't reliably return parentID.

This caused non-ultrawork keywords (search, analyze) to be injected in subagent
sessions when they should only work in main sessions.

Changed to use getMainSessionID() comparison, consistent with other hooks like
session-notification and todo-continuation-enforcer.

- Replace unreliable parentID API check with mainSessionID comparison
- Add comprehensive test coverage for session filtering behavior
- Remove unnecessary session.get API call
2026-01-07 03:00:28 +09:00