4 Commits
Author SHA1 Message Date
ducoterra 1374faf136 phase: 112_honesty_gate_weak_hits
Build and Push Containers / build-and-push-app (push) Successful in 2m15s
Build and Push Containers / build-and-push-db (push) Successful in 14s
**Phase 112 — final verification pass (all 4 tasks already complete in `complete/`):**

- Verified gate fix: `app/api/chat.py::plan_turn` — HIGH iff `best_cosine >= relevance_threshold` OR (`fts_hits > 0` AND `best_cosine >= lexical_support_floor`); `lexical_support_floor` (default 0.35, `BOR_LEXICAL_SUPPORT_FLOOR`, bounds-validated) in `app/config.py` + `.env.example`; A8 revision note (2026-09-14) in `.agents/PLAN.md`.
- Verified prompt contract: `app/rag/prompts.py` diff is docstring-only (dated owner-decision-iii entry); `tests/unit/test_prompt_lock.py` byte-pins PERSONA/TOOLS_SECTION/DEFLECT body (sha256+length).
- Verified README: L11 + L575 deflection copy refreshed; `grep "haven't done anything" README.md` → no hits; disclosed-answer behavior documented.
- Tests: `uv run pytest --cov=app --cov-report=term-missing` → **2378 passed, 99% coverage (>90%)**; includes Mongolia-quadrant unit pins (fts>0 + cosine<floor → LOW).
- E2E in isolation: `uv run pytest tests/e2e/test_honest_deflection.py -v --no-cov` → **4 passed** (out-of-KB question: `deflected=true`, `sources==[]`, 2–3 suggestions); regression `test_chat_rag.py` + `test_retrieval_quality.py` → **7 passed**.
- Lint/types: `uv run ruff check .` → clean; `uv run pyright` → 0 errors.

**Completion criteria:** weak-FTS→LOW unit-pinned ✅ · no false citations + 2–3 alternatives E2E ✅ · prompts byte-identical (test-pinned) + README matches ✅ · suite/coverage/e2e/lint all green ✅ · commit + phase move → left to harness (no `git commit` run, per rules; changes in working tree).

**Deviations:** none. Next pending phase: `113_source_chip_quality`.
2026-09-15 00:37:38 -04:00
ducoterra 17dd3bfac1 docs(plan): remove hardcoded phase/migration references to prevent staleness
Build and Push Containers / build-and-push-app (push) Successful in 14s
Build and Push Containers / build-and-push-db (push) Successful in 16s
Refactor §12 roadmap to point to ls commands and 00_phase.md files
instead of listing specific phase numbers and descriptions.

Remove ~20 phase-number references from anchors, revision notes,
tool surface, feedback, and sync sections — keep only the one
stable reference (phase 03 convention).

Replace migration ranges with 'ls alembic/versions/'.
Replace hardcoded retry values with 'configurable (defaults: ...)'.
Status header now points to §12 instead of listing counts.
2026-09-12 10:22:45 -04:00
ducoterra d4f38ad3ce add PLAN.md
Build and Push Containers / build-and-push-app (push) Successful in 39s
Build and Push Containers / build-and-push-db (push) Successful in 25s
2026-09-10 13:08:55 -04:00
ducoterra dac4a3eec0 docs(agent): restore master plan at .agents/PLAN.md with locked decisions through phase 92
Re-lands the master plan (removed from VCS in 281f355 as .agent/PLAN.md)
at .agents/PLAN.md — the path AGENTS.md and the codebase's PLAN §…
references use. Rebuilt from the original text plus every
owner-permitted revision recorded in the completed phases: A1–A17
anchors with the full revision log (auth, SSE thinking/tool/retry
events, agent tools, history, SPA shell), new A18–A20 (docs push,
deploy caching, security headers), current data model (11 tables),
locked persona + <tools> copy, current UI/UX contracts (46rem/92rem
column, theme tab, never-stale feedback, no autoscroll), the full
per-turn log line, and the phase 01–92 roadmap with the open TODO.md
items as next up.
2026-09-10 09:28:58 -04:00