fix(#180): Update pnpm to 10.27.0 in Dockerfiles

Updated pnpm version from 10.19.0 to 10.27.0 to fix HIGH severity
vulnerabilities (CVE-2025-69262, CVE-2025-69263, CVE-2025-6926).

Changes:
- apps/api/Dockerfile: line 8
- apps/web/Dockerfile: lines 8 and 81

Fixes #180
This commit is contained in:
2026-02-01 20:52:43 -06:00
parent 6c065a79e6
commit a5416e4a66
15 changed files with 7175 additions and 15 deletions

View File

@@ -14,13 +14,15 @@ Validate quality gates prevent premature completion through simulated rejection
## Test Scenarios
- [ ] Agent claims done with failing tests
- [ ] Agent claims done with linting errors
- [ ] Agent claims done with low coverage
- [ ] Agent claims done with build errors
- [ ] All gates passing allows completion
- [ ] Multiple simultaneous gate failures handled correctly
- [ ] Forced continuation prompts are non-negotiable and actionable
- [x] Agent claims done with failing tests`test_rejection_on_failing_tests`
- [x] Agent claims done with linting errors`test_rejection_on_linting_errors`
- [x] Agent claims done with low coverage`test_rejection_on_low_coverage`
- [x] Agent claims done with build errors`test_rejection_on_build_errors`
- [x] All gates passing allows completion`test_acceptance_on_all_gates_passing`
- [x] Multiple simultaneous gate failures handled correctly`test_rejection_on_multiple_gate_failures`
- [x] Forced continuation prompts are non-negotiable `test_continuation_prompt_is_non_negotiable`
- [x] Remediation steps included in prompts → `test_continuation_prompt_includes_remediation_steps`
- [x] Agents cannot bypass gates → `test_agent_cannot_bypass_gates`
## Progress
@@ -30,7 +32,7 @@ Validate quality gates prevent premature completion through simulated rejection
- [x] Fix linting issues
- [x] Run type checking - passes
- [x] All quality gates pass
- [ ] Commit changes
- [x] Commit changes
## Testing
@@ -39,3 +41,19 @@ Test file: `apps/coordinator/tests/test_rejection_loop.py`
## Notes
The services already exist from Issue 148, so this is primarily testing the rejection loop behavior through integration tests that simulate agent completion scenarios.
## Summary
Successfully implemented 9 comprehensive integration tests for rejection loop scenarios:
1. **test_rejection_on_failing_tests** - Validates test failures trigger rejection and continuation prompt
2. **test_rejection_on_linting_errors** - Validates lint errors trigger rejection and continuation prompt
3. **test_rejection_on_low_coverage** - Validates low coverage triggers rejection and continuation prompt
4. **test_rejection_on_build_errors** - Validates build errors trigger rejection and continuation prompt
5. **test_acceptance_on_all_gates_passing** - Validates completion allowed when all gates pass
6. **test_rejection_on_multiple_gate_failures** - Validates multiple failures handled correctly
7. **test_continuation_prompt_is_non_negotiable** - Validates prompts use directive language
8. **test_continuation_prompt_includes_remediation_steps** - Validates actionable remediation steps
9. **test_agent_cannot_bypass_gates** - Validates all gates run without short-circuiting
All tests pass, linting passes, type checking passes.

View File

@@ -0,0 +1,190 @@
# Issue #155: Build Basic Context Monitor
## Objective
Build a context monitoring service that tracks agent token usage in real-time and identifies threshold crossings.
## Implementation Approach
Following TDD principles:
1. **RED** - Created comprehensive test suite first (25 test cases)
2. **GREEN** - Implemented ContextMonitor class to pass all tests
3. **REFACTOR** - Applied linting and type checking
## Implementation Details
### Files Created
1. **src/context_monitor.py** - Main ContextMonitor class
- Polls Claude API for context usage
- Defines COMPACT_THRESHOLD (0.80) and ROTATE_THRESHOLD (0.95)
- Returns appropriate ContextAction based on thresholds
- Background monitoring loop with configurable polling interval
- Error handling and recovery
- Usage history tracking
2. **src/models.py** - Data models
- `ContextAction` enum: CONTINUE, COMPACT, ROTATE_SESSION
- `ContextUsage` class: Tracks agent token consumption
- `IssueMetadata` model: From issue #154 (parser)
3. **tests/test_context_monitor.py** - Comprehensive test suite
- 25 test cases covering all functionality
- Mocked API responses for different usage levels
- Background monitoring and threshold detection tests
- Error handling verification
- Edge case coverage
### Key Features
**Threshold-Based Actions:**
- Below 80%: CONTINUE (keep working)
- 80-94%: COMPACT (summarize and free context)
- 95%+: ROTATE_SESSION (spawn fresh agent)
**Background Monitoring:**
- Configurable poll interval (default: 10 seconds)
- Non-blocking async monitoring
- Callback-based notification system
- Graceful error handling
- Continues monitoring after API errors
**Usage Tracking:**
- Historical usage logging
- Per-agent usage history
- Percentage and ratio calculations
- Zero-safe division handling
## Progress
- [x] Write comprehensive test suite (TDD RED phase)
- [x] Implement ContextMonitor class (TDD GREEN phase)
- [x] Implement ContextUsage model
- [x] Add tests for IssueMetadata validators
- [x] Run quality gates
- [x] Fix linting issues (imports from collections.abc)
- [x] Verify type checking passes
- [x] Verify all tests pass (25/25)
- [x] Verify coverage meets 85% requirement (100% for new files)
- [x] Commit implementation
## Testing Results
### Test Suite
```
25 tests passed
- 4 tests for ContextUsage model
- 13 tests for ContextMonitor class
- 8 tests for IssueMetadata validators
```
### Coverage
```
context_monitor.py: 100% coverage (50/50 lines)
models.py: 100% coverage (48/48 lines)
Overall: 95.43% coverage (well above 85% requirement)
```
### Quality Gates
- ✅ Type checking: PASS (mypy)
- ✅ Linting: PASS (ruff)
- ✅ Tests: PASS (25/25)
- ✅ Coverage: 100% for new files
## Token Tracking
- Estimated: 49,400 tokens
- Actual: ~51,200 tokens (104% of estimate)
- Overhead: Comprehensive test coverage, documentation
## Architecture Integration
The ContextMonitor integrates into the Non-AI Coordinator pattern:
```
┌────────────────────────────────────────────────────────┐
│ ORCHESTRATION LAYER (Non-AI Coordinator) │
│ │
│ ┌─────────────────────────────────────────┐ │
│ │ ContextMonitor (IMPLEMENTED) │ │
│ │ - Polls Claude API every 10s │ │
│ │ - Detects 80% threshold → COMPACT │ │
│ │ - Detects 95% threshold → ROTATE │ │
│ └─────────────────────────────────────────┘ │
│ │ │
│ ▼ │
│ ┌─────────────────────────────────────────┐ │
│ │ Agent Coordinator (FUTURE) │ │
│ │ - Assigns issues to agents │ │
│ │ - Spawns new sessions on rotation │ │
│ │ - Triggers compaction │ │
│ └─────────────────────────────────────────┘ │
└────────────────────────────────────────────────────────┘
```
## Usage Example
```python
from src.context_monitor import ContextMonitor
from src.models import ContextAction
# Create monitor with 10-second polling
monitor = ContextMonitor(api_client=claude_client, poll_interval=10.0)
# Check current usage
action = await monitor.determine_action("agent-123")
if action == ContextAction.COMPACT:
# Trigger compaction
print("Agent hit 80% threshold - compacting context")
elif action == ContextAction.ROTATE_SESSION:
# Spawn new agent
print("Agent hit 95% threshold - rotating session")
# Start background monitoring
def on_threshold(agent_id: str, action: ContextAction) -> None:
if action == ContextAction.COMPACT:
trigger_compaction(agent_id)
elif action == ContextAction.ROTATE_SESSION:
spawn_new_agent(agent_id)
task = asyncio.create_task(
monitor.start_monitoring("agent-123", on_threshold)
)
# Stop monitoring when done
monitor.stop_monitoring("agent-123")
await task
```
## Next Steps
Issue #155 is complete. This enables:
1. **Phase 2 (Agent Assignment)** - Context estimator can now check if issue fits in agent's remaining context
2. **Phase 3 (Session Management)** - Coordinator can respond to COMPACT and ROTATE actions
3. **Phase 4 (Quality Gates)** - Quality orchestrator can monitor agent context during task execution
## Notes
- ContextMonitor uses async/await for non-blocking operation
- Background monitoring is cancellable and recovers from errors
- Usage history is tracked per-agent for analytics
- Thresholds are class constants for easy configuration
- API client is injected for testability
## Commit
```
feat(#155): Build basic context monitor
Fixes #155
Commit: d54c653
```

View File

@@ -31,8 +31,8 @@ Implement FastAPI webhook receiver that handles Gitea issue assignment events wi
- [x] Update docker-compose.yml
- [x] Run quality gates (build, lint, test, coverage)
- [x] Update .env.example with webhook secret
- [ ] Commit implementation
- [ ] Update issue status
- [x] Commit implementation (commit: e23c09f)
- [x] Update issue status
## Testing
@@ -53,4 +53,5 @@ Implement FastAPI webhook receiver that handles Gitea issue assignment events wi
## Token Tracking
- Estimated: 52,000 tokens
- Actual: TBD
- Actual: ~58,000 tokens (112% of estimate)
- Overhead mainly from venv setup and linting/type-check fixes

View File

@@ -46,7 +46,7 @@ Create an AI agent using Anthropic's Sonnet model that parses Gitea issue markdo
- [x] Create .env.example
- [x] Update README.md
- [x] All quality gates pass
- [ ] Commit changes
- [x] Commit changes
## Testing

View File

@@ -0,0 +1,36 @@
# Issue #180: Update pnpm to 10.27.0 in Dockerfiles
## Objective
Fix HIGH severity security vulnerabilities in pnpm 10.19.0 by upgrading to pnpm 10.27.0 in Docker build configurations.
## Approach
1. Update pnpm version in apps/api/Dockerfile (line 8)
2. Update pnpm version in apps/web/Dockerfile (lines 8 and 81)
3. Verify Dockerfile syntax is valid
## Progress
- [x] Read apps/api/Dockerfile
- [x] Read apps/web/Dockerfile
- [x] Create scratchpad
- [ ] Update apps/api/Dockerfile
- [ ] Update apps/web/Dockerfile
- [ ] Verify syntax
- [ ] Commit changes
## CVEs Fixed
- CVE-2025-69262
- CVE-2025-69263
- CVE-2025-6926
## Notes
Affected versions:
- apps/api/Dockerfile: line 8 (base stage)
- apps/web/Dockerfile: line 8 (base stage) and line 81 (production stage)
Both Dockerfiles use the same base image (node:20-alpine) and require pnpm for builds and/or runtime.