hangshuo652
|
bc1d56d1a4
|
feat: Phase 2 complete — 13 Phases of COBOL type classification and test benchmark
P0.6: gcov infrastructure
P1: extract_structure output expansion (11 new feature fields)
P2: Confusion group rule engine (8 pairs + contradiction + backtrack)
P3: 4-factor confidence calculation + quality gate update
P4: 33+2 COBOL program type test samples (22 files, 7 categories)
P5: parametrized/ test data generation engine
P6: japanese_data.py lookup tables
P7-10: Type-specific test suites (~159 parametrized tests)
P11: Full classification pipeline (classify_program) + orchestrator integration
P12: Documentation (module-interfaces, test-plan v3.0, coverage-matrix)
Architecture decisions:
- classification_pipeline/ merged to hina/pipeline/
- parametrized/ as independent module
- japanese_data.py as root-level file
- hina/__all__ only exports classify_program()
Co-Authored-By: Claude <noreply@anthropic.com>
|
2026-06-19 23:51:55 +08:00 |
|
hangshuo652
|
63b5284715
|
fix: _parse_llm_response now handles empty/invalid JSON gracefully
test: add gap coverage tests (hina_agent/JCL/quality gate edge cases)
|
2026-06-18 17:31:16 +08:00 |
|
hangshuo652
|
c93104e6bf
|
feat: Phase 3+4 - gcov support + enhanced report
|
2026-06-18 16:31:54 +08:00 |
|
hangshuo652
|
e2486db510
|
fix: 3 issues found during real COBOL validation
|
2026-06-18 16:26:44 +08:00 |
|
hangshuo652
|
de506d9c31
|
feat: Phase 2 - HINA Agent + Strategy Agent + classifier
|
2026-06-18 16:10:38 +08:00 |
|
hangshuo652
|
c021dfe01e
|
feat: Phase 1 - orchestrator quality gate loop + hina/gate + main CLI args
|
2026-06-18 16:02:38 +08:00 |
|
hangshuo652
|
097530b036
|
feat: Phase 1 - cobol_testgen API + quality fields + retry handler
|
2026-06-18 15:47:35 +08:00 |
|