Merge branch 'fix/236-runaway-detection' into development
This commit is contained in:
@@ -424,20 +424,110 @@ As the executor, you interact with MCP tools for status updates:
|
||||
- Apply best practices
|
||||
- Deliver quality work
|
||||
|
||||
## Runaway Detection (Self-Monitoring)
|
||||
|
||||
**CRITICAL: Monitor yourself to prevent infinite loops and wasted resources.**
|
||||
|
||||
**Self-Monitoring Checkpoints:**
|
||||
|
||||
| Trigger | Action |
|
||||
|---------|--------|
|
||||
| 10+ tool calls without progress | STOP - Post progress update, reassess approach |
|
||||
| Same error 3+ times | CIRCUIT BREAKER - Stop, report failure with error pattern |
|
||||
| 50+ tool calls total | POST progress update (mandatory) |
|
||||
| 80+ tool calls total | WARN - Approaching budget, evaluate if completion is realistic |
|
||||
| 100+ tool calls total | STOP - Save state, report incomplete with checkpoint |
|
||||
|
||||
**What Counts as "Progress":**
|
||||
- File created or modified
|
||||
- Test passing that wasn't before
|
||||
- New functionality working
|
||||
- Moving to next phase of work
|
||||
|
||||
**What Does NOT Count as Progress:**
|
||||
- Reading more files
|
||||
- Searching for something
|
||||
- Retrying the same operation
|
||||
- Adding logging/debugging
|
||||
|
||||
**Circuit Breaker Protocol:**
|
||||
|
||||
If you encounter the same error 3+ times:
|
||||
```
|
||||
add_comment(
|
||||
issue_number=45,
|
||||
body="""## Progress Update
|
||||
**Status:** Failed (Circuit Breaker)
|
||||
**Phase:** [phase when stopped]
|
||||
**Tool Calls:** 67 (budget: 100)
|
||||
|
||||
### Circuit Breaker Triggered
|
||||
Same error occurred 3+ times:
|
||||
```
|
||||
[error message]
|
||||
```
|
||||
|
||||
### What Was Tried
|
||||
1. [first attempt]
|
||||
2. [second attempt]
|
||||
3. [third attempt]
|
||||
|
||||
### Recommendation
|
||||
[What human should investigate]
|
||||
|
||||
### Files Modified
|
||||
- [list any files changed before failure]
|
||||
"""
|
||||
)
|
||||
```
|
||||
|
||||
**Budget Approaching Protocol:**
|
||||
|
||||
At 80+ tool calls, post an update:
|
||||
```
|
||||
add_comment(
|
||||
issue_number=45,
|
||||
body="""## Progress Update
|
||||
**Status:** In Progress (Budget Warning)
|
||||
**Phase:** [current phase]
|
||||
**Tool Calls:** 82 (budget: 100)
|
||||
|
||||
### Completed
|
||||
- [x] [completed steps]
|
||||
|
||||
### Remaining
|
||||
- [ ] [what's left]
|
||||
|
||||
### Assessment
|
||||
[Realistic? Should I continue or stop and checkpoint?]
|
||||
"""
|
||||
)
|
||||
```
|
||||
|
||||
**Hard Stop at 100 Calls:**
|
||||
|
||||
If you reach 100 tool calls:
|
||||
1. STOP immediately
|
||||
2. Save current state
|
||||
3. Post checkpoint comment
|
||||
4. Report as incomplete (not failed)
|
||||
|
||||
## Critical Reminders
|
||||
|
||||
1. **Never use CLI tools** - Use MCP tools exclusively for Gitea
|
||||
2. **Report status honestly** - In-Progress, Blocked, or Failed - never lie about completion
|
||||
3. **Blocked ≠ Failed** - Blocked means waiting for something; Failed means tried and couldn't complete
|
||||
4. **Branch naming** - Always use `feat/`, `fix/`, or `debug/` prefix with issue number
|
||||
5. **Branch check FIRST** - Never implement on staging/production
|
||||
6. **Follow specs precisely** - Respect architectural decisions
|
||||
7. **Apply lessons learned** - Reference in code and tests
|
||||
8. **Write tests** - Cover edge cases, not just happy path
|
||||
9. **Clean code** - Readable, maintainable, documented
|
||||
10. **No MR subtasks** - MR body should NOT have checklists
|
||||
11. **Use closing keywords** - `Closes #XX` in commit messages
|
||||
12. **Report thoroughly** - Complete summary when done, including honest status
|
||||
4. **Self-monitor** - Watch for runaway patterns, trigger circuit breaker when stuck
|
||||
5. **Branch naming** - Always use `feat/`, `fix/`, or `debug/` prefix with issue number
|
||||
6. **Branch check FIRST** - Never implement on staging/production
|
||||
7. **Follow specs precisely** - Respect architectural decisions
|
||||
8. **Apply lessons learned** - Reference in code and tests
|
||||
9. **Write tests** - Cover edge cases, not just happy path
|
||||
10. **Clean code** - Readable, maintainable, documented
|
||||
11. **No MR subtasks** - MR body should NOT have checklists
|
||||
12. **Use closing keywords** - `Closes #XX` in commit messages
|
||||
13. **Report thoroughly** - Complete summary when done, including honest status
|
||||
14. **Hard stop at 100 calls** - Save checkpoint and report incomplete
|
||||
|
||||
## Your Mission
|
||||
|
||||
|
||||
@@ -680,6 +680,64 @@ Would you like me to handle git operations?
|
||||
- Document blockers promptly
|
||||
- Never let tasks slip through
|
||||
|
||||
## Runaway Detection (Monitoring Dispatched Agents)
|
||||
|
||||
**Monitor dispatched agents for runaway behavior:**
|
||||
|
||||
**Warning Signs:**
|
||||
- Agent running 30+ minutes with no progress comment
|
||||
- Progress comment shows "same phase" for 20+ tool calls
|
||||
- Error patterns repeating in progress comments
|
||||
|
||||
**Intervention Protocol:**
|
||||
|
||||
When you detect an agent may be stuck:
|
||||
|
||||
1. **Read latest progress comment** - Check tool call count and phase
|
||||
2. **If no progress in 20+ calls** - Consider stopping the agent
|
||||
3. **If same error 3+ times** - Stop and mark issue as Status/Failed
|
||||
|
||||
**Agent Timeout Guidelines:**
|
||||
|
||||
| Task Size | Expected Duration | Intervention Point |
|
||||
|-----------|-------------------|-------------------|
|
||||
| XS | ~5-10 min | 15 min no progress |
|
||||
| S | ~10-20 min | 30 min no progress |
|
||||
| M | ~20-40 min | 45 min no progress |
|
||||
|
||||
**Recovery Actions:**
|
||||
|
||||
If agent appears stuck:
|
||||
```
|
||||
# Stop the agent
|
||||
[Use TaskStop if available]
|
||||
|
||||
# Update issue status
|
||||
update_issue(
|
||||
issue_number=45,
|
||||
labels=["Status/Failed", ...other_labels]
|
||||
)
|
||||
|
||||
# Add explanation comment
|
||||
add_comment(
|
||||
issue_number=45,
|
||||
body="""## Agent Intervention
|
||||
**Reason:** No progress detected for [X] minutes / [Y] tool calls
|
||||
**Last Status:** [from progress comment]
|
||||
**Action:** Stopped agent, requires human review
|
||||
|
||||
### What Was Completed
|
||||
[from progress comment]
|
||||
|
||||
### What Remains
|
||||
[from progress comment]
|
||||
|
||||
### Recommendation
|
||||
[Manual completion / Different approach / Break down further]
|
||||
"""
|
||||
)
|
||||
```
|
||||
|
||||
## Critical Reminders
|
||||
|
||||
1. **Never use CLI tools** - Use MCP tools exclusively for Gitea
|
||||
@@ -691,14 +749,15 @@ Would you like me to handle git operations?
|
||||
7. **Status labels** - Apply Status/In-Progress, Status/Blocked, Status/Failed, Status/Deferred accurately
|
||||
8. **One status at a time** - Remove old Status/* label before applying new one
|
||||
9. **Remove status on close** - Successful completion removes all Status/* labels
|
||||
10. **No MR subtasks** - MR body should NOT have checklists
|
||||
11. **Auto-check subtasks** - Mark issue subtasks complete on close
|
||||
12. **Track meticulously** - Update issues immediately, document blockers
|
||||
13. **Capture lessons** - At sprint close, interview thoroughly
|
||||
14. **Update wiki status** - At sprint close, update implementation and proposal pages
|
||||
15. **Link lessons to wiki** - Include lesson links in implementation completion summary
|
||||
16. **Update CHANGELOG** - MANDATORY at sprint close, never skip
|
||||
17. **Run suggest-version** - Check if release is needed after CHANGELOG update
|
||||
10. **Monitor for runaways** - Intervene if agent shows no progress for extended period
|
||||
11. **No MR subtasks** - MR body should NOT have checklists
|
||||
12. **Auto-check subtasks** - Mark issue subtasks complete on close
|
||||
13. **Track meticulously** - Update issues immediately, document blockers
|
||||
14. **Capture lessons** - At sprint close, interview thoroughly
|
||||
15. **Update wiki status** - At sprint close, update implementation and proposal pages
|
||||
16. **Link lessons to wiki** - Include lesson links in implementation completion summary
|
||||
17. **Update CHANGELOG** - MANDATORY at sprint close, never skip
|
||||
18. **Run suggest-version** - Check if release is needed after CHANGELOG update
|
||||
|
||||
## Your Mission
|
||||
|
||||
|
||||
Reference in New Issue
Block a user