luna/oh-my-opencode
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

refactor: migrate delegate_task to task tool with metadata fixes

Browse Source 
- Rename delegate_task tool to task across codebase (100 files)
- Update model references: claude-opus-4-6 → 4-5, gpt-5.3-codex → 5.2-codex
- Add tool-metadata-store to restore metadata overwritten by fromPlugin()
- Add session ID polling for BackgroundManager task sessions
- Await async ctx.metadata() calls in tool executors
- Add ses_ prefix guard to getMessageDir for performance
- Harden BackgroundManager with idle deferral and error handling
- Fix duplicate task key in sisyphus-junior test object literals
- Fix unawaited showOutputToUser in ast_grep_replace
- Fix background=true → run_in_background=true in ultrawork prompt
- Fix duplicate task/task references in docs and comments
This commit is contained in:
YeonGyu-Kim
2026-02-06 16:01:54 +09:00
parent f1c794e63e
commit a691a3ac0a
78 changed files with 1182 additions and 403 deletions
Download Patch File Download Diff File Expand all files Collapse all files
src/hooks/keyword-detector/ultrawork/default.ts
+22 -22
View File
@@ -2,7 +2,7 @@
* Default ultrawork message optimized for Claude series models.
*
* Key characteristics:
* - Natural tool-like usage of explore/librarian agents (background=true)
* - Natural tool-like usage of explore/librarian agents (run_in_background=true)
* - Parallel execution emphasized - fire agents and continue working
* - Simple workflow: EXPLORES → GATHER → PLAN → DELEGATE
*/
@@ -44,9 +44,9 @@ export const ULTRAWORK_DEFAULT_MESSAGE = `<ultrawork-mode>
**WHEN IN DOUBT:**
\`\`\`
delegate_task(subagent_type="explore", load_skills=[], prompt="Find [X] patterns in codebase", run_in_background=true)
delegate_task(subagent_type="librarian", load_skills=[], prompt="Find docs/examples for [Y]", run_in_background=true)
delegate_task(subagent_type="oracle", load_skills=[], prompt="Review my approach: [describe plan]", run_in_background=false)
task(subagent_type="explore", load_skills=[], prompt="Find [X] patterns in codebase", run_in_background=true)
task(subagent_type="librarian", load_skills=[], prompt="Find docs/examples for [Y]", run_in_background=true)
task(subagent_type="oracle", load_skills=[], prompt="Review my approach: [describe plan]", run_in_background=false)
\`\`\`
**ONLY AFTER YOU HAVE:**
@@ -104,7 +104,7 @@ TELL THE USER WHAT AGENTS YOU WILL LEVERAGE NOW TO SATISFY USER'S REQUEST.
| Architecture decision needed | MUST call plan agent |
\`\`\`
delegate_task(subagent_type="plan", prompt="<gathered context + user request>")
task(subagent_type="plan", prompt="<gathered context + user request>")
\`\`\`
**WHY PLAN AGENT IS MANDATORY:**
@@ -119,9 +119,9 @@ delegate_task(subagent_type="plan", prompt="<gathered context + user request>")
| Scenario | Action |
|----------|--------|
| Plan agent asks clarifying questions | \`delegate_task(session_id="{returned_session_id}", prompt="<your answer>")\` |
| Need to refine the plan | \`delegate_task(session_id="{returned_session_id}", prompt="Please adjust: <feedback>")\` |
| Plan needs more detail | \`delegate_task(session_id="{returned_session_id}", prompt="Add more detail to Task N")\` |
| Plan agent asks clarifying questions | \`task(session_id="{returned_session_id}", prompt="<your answer>")\` |
| Need to refine the plan | \`task(session_id="{returned_session_id}", prompt="Please adjust: <feedback>")\` |
| Plan needs more detail | \`task(session_id="{returned_session_id}", prompt="Add more detail to Task N")\` |
**WHY SESSION_ID IS CRITICAL:**
- Plan agent retains FULL conversation context
@@ -131,10 +131,10 @@ delegate_task(subagent_type="plan", prompt="<gathered context + user request>")
\`\`\`
// WRONG: Starting fresh loses all context
delegate_task(subagent_type="plan", prompt="Here's more info...")
task(subagent_type="plan", prompt="Here's more info...")
// CORRECT: Resume preserves everything
delegate_task(session_id="ses_abc123", prompt="Here's my answer to your question: ...")
task(session_id="ses_abc123", prompt="Here's my answer to your question: ...")
\`\`\`
**FAILURE TO CALL PLAN AGENT = INCOMPLETE WORK.**
@@ -147,23 +147,23 @@ delegate_task(session_id="ses_abc123", prompt="Here's my answer to your question
| Task Type | Action | Why |
|-----------|--------|-----|
| Codebase exploration | delegate_task(subagent_type="explore", run_in_background=true) | Parallel, context-efficient |
| Documentation lookup | delegate_task(subagent_type="librarian", run_in_background=true) | Specialized knowledge |
| Planning | delegate_task(subagent_type="plan") | Parallel task graph + structured TODO list |
| Hard problem (conventional) | delegate_task(subagent_type="oracle") | Architecture, debugging, complex logic |
| Hard problem (non-conventional) | delegate_task(category="artistry", load_skills=[...]) | Different approach needed |
| Implementation | delegate_task(category="...", load_skills=[...]) | Domain-optimized models |
| Codebase exploration | task(subagent_type="explore", run_in_background=true) | Parallel, context-efficient |
| Documentation lookup | task(subagent_type="librarian", run_in_background=true) | Specialized knowledge |
| Planning | task(subagent_type="plan") | Parallel task graph + structured TODO list |
| Hard problem (conventional) | task(subagent_type="oracle") | Architecture, debugging, complex logic |
| Hard problem (non-conventional) | task(category="artistry", load_skills=[...]) | Different approach needed |
| Implementation | task(category="...", load_skills=[...]) | Domain-optimized models |
**CATEGORY + SKILL DELEGATION:**
\`\`\`
// Frontend work
delegate_task(category="visual-engineering", load_skills=["frontend-ui-ux"])
task(category="visual-engineering", load_skills=["frontend-ui-ux"])
// Complex logic
delegate_task(category="ultrabrain", load_skills=["typescript-programmer"])
task(category="ultrabrain", load_skills=["typescript-programmer"])
// Quick fixes
delegate_task(category="quick", load_skills=["git-master"])
task(category="quick", load_skills=["git-master"])
\`\`\`
**YOU SHOULD ONLY DO IT YOURSELF WHEN:**
@@ -177,14 +177,14 @@ delegate_task(category="quick", load_skills=["git-master"])
## EXECUTION RULES
- **TODO**: Track EVERY step. Mark complete IMMEDIATELY after each.
- **PARALLEL**: Fire independent agent calls simultaneously via delegate_task(background=true) - NEVER wait sequentially.
- **BACKGROUND FIRST**: Use delegate_task for exploration/research agents (10+ concurrent if needed).
- **PARALLEL**: Fire independent agent calls simultaneously via task(run_in_background=true) - NEVER wait sequentially.
- **BACKGROUND FIRST**: Use task for exploration/research agents (10+ concurrent if needed).
- **VERIFY**: Re-read request after completion. Check ALL requirements met before reporting done.
- **DELEGATE**: Don't do everything yourself - orchestrate specialized agents for their strengths.
## WORKFLOW
1. Analyze the request and identify required capabilities
2. Spawn exploration/librarian agents via delegate_task(background=true) in PARALLEL (10+ if needed)
2. Spawn exploration/librarian agents via task(run_in_background=true) in PARALLEL (10+ if needed)
3. Use Plan agent with gathered context to create detailed work breakdown
4. Execute with continuous verification against original requirements
src/hooks/keyword-detector/ultrawork/gpt5.2.ts
+7 -7
View File
@@ -73,11 +73,11 @@ Use these when they provide clear value based on the decision framework above:
| Resource | When to Use | How to Use |
|----------|-------------|------------|
| explore agent | Need codebase patterns you don't have | \`delegate_task(subagent_type="explore", run_in_background=true, ...)\` |
| librarian agent | External library docs, OSS examples | \`delegate_task(subagent_type="librarian", run_in_background=true, ...)\` |
| oracle agent | Stuck on architecture/debugging after 2+ attempts | \`delegate_task(subagent_type="oracle", ...)\` |
| plan agent | Complex multi-step with dependencies (5+ steps) | \`delegate_task(subagent_type="plan", ...)\` |
| delegate_task category | Specialized work matching a category | \`delegate_task(category="...", load_skills=[...])\` |
| explore agent | Need codebase patterns you don't have | \`task(subagent_type="explore", run_in_background=true, ...)\` |
| librarian agent | External library docs, OSS examples | \`task(subagent_type="librarian", run_in_background=true, ...)\` |
| oracle agent | Stuck on architecture/debugging after 2+ attempts | \`task(subagent_type="oracle", ...)\` |
| plan agent | Complex multi-step with dependencies (5+ steps) | \`task(subagent_type="plan", ...)\` |
| task category | Specialized work matching a category | \`task(category="...", load_skills=[...])\` |
<tool_usage_rules>
- Prefer tools over internal knowledge for fresh or user-specific data
@@ -97,8 +97,8 @@ Use these when they provide clear value based on the decision framework above:
**ALWAYS run both tracks in parallel:**
\`\`\`
// Fire background agents for deep exploration
delegate_task(subagent_type="explore", load_skills=[], prompt="Find X patterns...", run_in_background=true)
delegate_task(subagent_type="librarian", load_skills=[], prompt="Find docs for Y...", run_in_background=true)
task(subagent_type="explore", load_skills=[], prompt="Find X patterns...", run_in_background=true)
task(subagent_type="librarian", load_skills=[], prompt="Find docs for Y...", run_in_background=true)
// WHILE THEY RUN - use direct tools for immediate context
grep(pattern="relevant_pattern", path="src/")
src/hooks/keyword-detector/ultrawork/planner.ts
+7 -7
View File
@@ -14,7 +14,7 @@ You ARE the planner. You ARE NOT an implementer. You DO NOT write code. You DO N
| Write/Edit | \`.sisyphus/**/*.md\` ONLY | Everything else |
| Read | All files | - |
| Bash | Research commands only | Implementation commands |
| delegate_task | explore, librarian | - |
| task | explore, librarian | - |
**IF YOU TRY TO WRITE/EDIT OUTSIDE \`.sisyphus/\`:**
- System will BLOCK your action
@@ -38,9 +38,9 @@ You ARE the planner. Your job: create bulletproof work plans.
### Research Protocol
1. **Fire parallel background agents** for comprehensive context:
\`\`\`
delegate_task(agent="explore", prompt="Find existing patterns for [topic] in codebase", background=true)
delegate_task(agent="explore", prompt="Find test infrastructure and conventions", background=true)
delegate_task(agent="librarian", prompt="Find official docs and best practices for [technology]", background=true)
task(agent="explore", prompt="Find existing patterns for [topic] in codebase", background=true)
task(agent="explore", prompt="Find test infrastructure and conventions", background=true)
task(agent="librarian", prompt="Find official docs and best practices for [technology]", background=true)
\`\`\`
2. **Wait for results** before planning - rushed plans fail
3. **Synthesize findings** into informed requirements
@@ -117,9 +117,9 @@ Each TODO item MUST include:
| Wave | Tasks | Dispatch Command |
|------|-------|------------------|
| 1 | 1, 4 | \`delegate_task(category="...", load_skills=[...], run_in_background=false)\` × 2 |
| 2 | 2, 3, 5 | \`delegate_task(...)\` × 3 after Wave 1 completes |
| 3 | 6 | \`delegate_task(...)\` final integration |
| 1 | 1, 4 | \`task(category="...", load_skills=[...], run_in_background=false)\` × 2 |
| 2 | 2, 3, 5 | \`task(...)\` × 3 after Wave 1 completes |
| 3 | 6 | \`task(...)\` final integration |
**WHY PARALLEL TASK GRAPH IS MANDATORY:**
- Orchestrator (Sisyphus) executes tasks in parallel waves