Skip to content

Commit 8e6c61d

Browse files
JuliaEdomclaude
andcommitted
docs: mark Codex #7 done, #8/#10 won't-fix
#7 closed via a7c617f (transitions use fresh original_match). #8 (_hashable float bucketing) and #10 (cache fill race) won't-fix: both verified latent (0 reachability), and proposed fixes add real cost (O(n²) comparisons, diskcache locks) for non-existent scenarios. Will reopen if real repro emerges. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
1 parent a7c617f commit 8e6c61d

1 file changed

Lines changed: 4 additions & 4 deletions

File tree

‎docs/NEXT_SESSION.md‎

Lines changed: 4 additions & 4 deletions
Original file line numberDiff line numberDiff line change
@@ -16,9 +16,9 @@
1616

1717
| # | Severity | Scope | Estimate |
1818
|---|---|---|---|
19-
| Codex #7 | P2 latent | `scripts/rescore_arcwise.py:82` stale `rec["match"]` — verified 0/200 disagreements on v29, transitions output unchanged if fixed | 30min, deferred |
20-
| Codex #8 | P2 latent | `execution_accuracy.py` `_hashable` float bucketing — verified 0 set-mismatch in v22-v30 baselines | 1h, deferred |
21-
| Codex #10 | P2 latent | `cache.py:88` cache miss/fill race — fires только при parallel workers (not currently used) | 1h, deferred |
19+
| ~~Codex #7~~ | **Done 2026-05-26 EOD-7** (`a7c617f`) | `scripts/rescore_arcwise.py` transitions теперь используют fresh `out_entry["original_match"]` вместо stored `rec["match"]`. Canonical v29 transitions (gained=7 / lost=91) не изменились — 0/200 disagreements verified. Future-proofing only. | 30min |
20+
| Codex #8 | P2 latent | `execution_accuracy.py` `_hashable` float bucketing — verified 0 set-mismatch in v22-v31 baselines. **Will NOT fix:** замена на O(n²) pair-wise tolerance match замедлит comparisons на больших result sets без observable benefit. Document как "won't fix" если не возникнет реальный repro. | won't fix |
21+
| Codex #10 | P2 latent | `cache.py:88` cache miss/fill race — fires только при parallel workers (not currently used). **Will NOT fix:** добавляет complexity (per-key diskcache locks) для несуществующего scenario. Если parallel workers потребуются — пересмотреть. | won't fix |
2222

2323
**Past 94.0% (gated к юзеру):** requires paid OR top-up / fine-tune / metric pivot. Residue 12 qids — large majority BIRD-annotation-quirks (unanimous fail через 3-model reasoning sweeps EOD-2 + EOD-4). Saturation подтверждена.
2424

@@ -218,7 +218,7 @@ fetch). Local heterogeneous CSC lever остаётся parked.
218218
| ~~Kimi P1.3~~ | **Done 2026-05-26 EOD-7** (`a7c1d81`) | `app/streamlit_app.py` 1184 → 200 lines split: `i18n.py`/`theme.py`/`samples.py`/`bootstrap.py` + `components/{output,show_working,schema_explorer,welcome}.py`. `pyproject.toml` ruff `src` расширен `["src","tests","app"]`. Local Streamlit + Playwright E2E подтвердил EN 94.0% / RU 94,0% / schema explorer render OK. Zero behavior change, 357 pytest pass. | 1.5h |
219219
| ~~Kimi P1.4~~ | **Done 2026-05-26** | `src/nl_sql/agent/nodes/_support.py` 483 lines → `_support.py` (public API, 184 lines) + `_text_utils.py` (JSON parsing, 53 lines) + `_hints.py` (schema appendices, 302 lines). Zero behavior change, 355 pytest pass, ruff + mypy strict clean. | 1h |
220220
| ~~Kimi P1.6~~ | **Done 2026-05-26 EOD-7** (`4207df0`) | API coverage **58% → 89%**. Extracted `Singletons` NamedTuple + `get_singletons()` FastAPI Depends-factory. `/readyz`, `/databases`, `/ask` теперь принимают `Singletons = Depends(get_singletons)`; production callers idiomatic через `@lru_cache(maxsize=1)` на `_make_singletons` (zero behavior change). New `tests/api/test_api_routes_mocked.py` (13 tests) покрывает /readyz healthy/empty/raises пути, /databases auth + schema-exception, /ask unknown-db / canned-result / error-kind / confidence-buckets + rate-limit 60→61st 429. | 1.5h |
221-
| Codex #7 | P2 latent | `scripts/rescore_arcwise.py:82` transition buckets используют stale `rec["match"]` вместо recomputed `out_entry["original_match"]` (line 141 overwrite). **Reachability verified 2026-05-26: 0/200 stale-vs-fresh disagreements в `eval/reports/2026-05-24/v29-arcwise-rescored.json`** — bug latent, transitions counts (7 gained / 91 lost) honest. Fix = 1-line swap, no observable change в output. | 30min, deferred |
221+
| ~~Codex #7~~ | **Done 2026-05-26 EOD-7** (`a7c617f`) | `scripts/rescore_arcwise.py` transitions teперь через fresh `out_entry["original_match"]` вместо stored `rec["match"]`. Canonical v29 transitions (gained=7 / lost=91) не изменились — 0/200 disagreements. Future-proofing. | 30min |
222222
| Codex #8 | P2 latent | `execution_accuracy.py:209-221` `_hashable` bucketing через `round(v / 1e-6)` может развести два tolerance-equivalent rows (diff ~9e-7, banker's rounding edge) в разные buckets → set-mode false negative. **Reachability verified 2026-05-26: 0 set-mismatch records в v22-v30 baselines (200 records each); 8 set-mismatch в demo runs 2026-05-11, все honest column-count diff не float-bucket.** Fix = replace `_hashable` с pair-wise tolerance match (O(n²)). | 1h, deferred |
223223
| ~~Codex #9~~ | **false positive 2026-05-26** | `cache.py:77` cache key omits `req.json_mode`. **Не достижимо в текущем коде:** `src/nl_sql/llm/providers/groq.py:44` force-set'ит `json_mode=True` через `req.model_copy` на каждом Groq call; Mistral codestral игнорирует поле (`base.py:21` docstring). Per (provider, model) пара `json_mode` имеет константное значение → collision impossible. Не трогать (попытка fix landed 2026-05-26, reverted после Codex+Kimi independent review). | closed |
224224
| Codex #10 | P2 latent | `cache.py:88` cache miss/fill race без lock — parallel eval workers могут race, duplicate paid calls, last-writer-wins. **Reachability: текущий eval pipeline serial per qid (см. `runner.py::_run_one`). Latent до момента запуска parallel workers.** Fix = per-key diskcache lock или atomic memoization (`Cache.add` semantic). | 1h, deferred |

0 commit comments

Comments
 (0)