conductor(plan): code_path_audit_20260607 v2 - 14 phases, 85+ tasks, 91 tests
Worker-ready plan for the v2 implementation. 14 phases: 0. Setup (8 tasks: state.toml, empty files, fixture dirs) 1. Data model (11 tasks: 5 enums + 9 supporting dataclasses + AggregateProfile) 2. PCG (6 tasks: skeleton + P1/P2/P3 AST passes + build_pcg()) 3. MemoryDim classifier (5 tasks: 2 dicts + override loader + file heuristic + classifier) 4. APD (8 tasks: 4 thresholds + 4 pattern detectors + dominant_pattern + detect_access_pattern) 5. CFE (4 tasks: 6 caller sets + override loader + estimate_call_frequency) 6. Decomposition cost (9 tasks: 6 constants + per_call_cost + frequency_multiplier + componentize + unify + recommended + rationale + compute) 7. Cross-audit integration (7 tasks: read_input_json + 6 input contracts + 3-tier mapping + 2 coverage + aggregate + run_all) 8. v2 DSL (5 tasks: arity table + to_dsl_v2 + to_markdown + to_tree + parse_dsl_v2) 9. run_audit + CLI + MCP (7 tasks: 2 aggregate constants + synthesize + run_audit + render_rollups + CLI + MCP tool) 10. Integration tests (6 tasks: synthetic src/ + 4 function files + 6 JSON fixtures + 7 tests) 11. Live_gui E2E (2 tasks: 2 opt-in tests) 12. Meta-audit + extension + styleguide (4 tasks: 3 implementations) 13. End-of-track report (5 tasks: 1 run + 6 verifications + 1 report + 1 tracks.md update + 1 final verification) Total: 91 tests (84 unit + 7 integration; 2 live_gui opt-in). 13 per-aggregate profiles (10 real + 3 candidate). 4 top-level rollups (summary, cross_audit_summary, decomposition_matrix, candidates). 5 follow-up tracks recorded. No new pip dependencies. No modifications to existing src/*.py files (read-only on the 65 existing files). No modifications to the 5 existing audit scripts (consume their JSON). Self-review: spec coverage (all sections covered), placeholder scan (no TBDs), type consistency (no name mismatches). 5006 lines. spec_v2.md is 460 lines. Total v2 spec+plan: 5466 lines.
This commit is contained in:
