|
|
9b1a1c0b8a
|
feat(#145): Build assignment algorithm
Implement intelligent agent assignment algorithm that selects the optimal
agent for each issue based on context capacity, difficulty, and cost.
Algorithm:
1. Filter agents that meet context capacity (50% rule - agent needs 2x context)
2. Filter agents that can handle difficulty level
3. Sort by cost (prefer self-hosted when capable)
4. Return cheapest qualifying agent
Features:
- NoCapableAgentError raised when no agent can handle requirements
- Difficulty mapping: easy/low->LOW, medium->MEDIUM, hard/high->HIGH
- Self-hosted preference (GLM, minimax cost=0)
- Comprehensive test coverage (100%, 23 tests)
Test scenarios:
- Assignment for low/medium/high difficulty issues
- Context capacity filtering (50% rule enforcement)
- Cost optimization logic (prefers self-hosted)
- Error handling for impossible assignments
- Edge cases (zero context, negative context, invalid difficulty)
Quality gates:
- All 23 tests passing
- 100% code coverage (exceeds 85% requirement)
- Lint: passing (ruff)
- Type check: passing (mypy)
Refs #145
Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
|
2026-02-01 18:07:58 -06:00 |
|
