 Sven Geboers
|
efb3a8fbd2
|
fix: agent-native audit — parameterize thresholds, add CRUD tests, tool discovery
Audit fixes for agent-native architecture gaps:
- agent_tools/content.py: parameterize healthy_threshold in check_embedding_quality
- agent_tools/__init__.py: add __all__ exports and list_tools() runtime discovery
- agent_tools/database.py: add CRUD primitives (create_motion, update_motion, delete_report)
plus query_embeddings, query_similar_motions, query_compass_positions
- tests/agent_tools/test_database_tools.py: add CRUD tool tests
- tests/agent_tools/test_content_tools.py: add parameterized threshold test
- tests/agent_tools/test_package.py: test list_tools() and package imports
Tests: 245 passed, 3 skipped
|
4 weeks ago |
|
Sven Geboers
|
8af27bbf04
|
feat: implement agent-native architecture (U1-U6)
Implements the agent-native architecture plan (docs/plans/2026-05-01-002-agent-native-architecture-plan.md):
- U1: Database query primitives (agent_tools/database.py)
- query_motions, query_votes, query_svd_vectors, query_party_positions, query_pipeline_status
- U2: Pipeline control primitives (agent_tools/pipeline.py)
- pipeline_run_stage, pipeline_run_full, pipeline_check_health, pipeline_get_logs, pipeline_validate_output
- U3: Analysis & report generation (agent_tools/analysis.py, reports.py)
- analyze_party_shift, analyze_axis_stability, validate_svd_labels, generate_report
- U4: Content validation primitives (agent_tools/content.py)
- validate_motion_coverage, validate_layman_explanations, suggest_svd_label, check_embedding_quality
- U5: System prompt & context injection (SYSTEM_PROMPT.md, context.py, context.md)
- U6: Parity verification tests (tests/agent_tools/test_parity.py)
Tests: 238 passed, 2 skipped
AGENTS.md updated to surface agent_tools/
|
4 weeks ago |
