Commit Graph

16 Commits

Author SHA1 Message Date
Дмитрий 4a4fb625d2 docs(pilot): Этап 3 slepok-routing-protection выкачен на боевой liderra.ru
GitHub Actions run 26575476127, merge commit 8b818144, PR #27.
R-03 (frozen filter в LeadRouter + LedgerService reject) + R-13 (paused_at
sync на freeze/unfreeze) live на проде.

+ cspell-words: чарж, чарже, сматчить, тригернёт (domain jargon)
2026-05-28 15:53:11 +03:00
Дмитрий 81cbd8c1c2 feat(brain-retro #7): C1+C2+C3+C4 router-discipline fixes
retro #7 (docs/observer/notes/2026-05-27-brain-retro-7.md) surfaced 4
candidates against 23 turns since retro #6. All four implemented TDD.

C1 — translit slang vocabulary in router-classifier-regex-fallback.mjs.
TASK_TYPE_KEYWORDS += deploy bucket (push / запушь / выкат);
memory-sync += обнови мозг / эталон / пилот / memory dump.

C2 — short_ambiguous_block in router-tool-gate.mjs + router-prehook.mjs.
prehook persists prompt_length; gate blocks Edit/Write/MultiEdit/Bash
when task_type in {ambiguous, unknown} AND prompt_length <= 30 AND
skill not invoked AND no direct_justified tag.

C3 — self-assessment timeout 30s to 50s in observer-self-assessment-api.mjs.
Windows TLS handshake + Sonnet latency exceeded 30s. Stop-hook has 60s
budget; 50s leaves headroom. DEFAULT_TIMEOUT_MS exported for tests.

C4 — Reviewer findings block in status-md-generator.mjs. New helper
computeReviewerFindingsBlock surfaces 51 actionable findings without
running /brain-retro. Detects batch-reviewed via
outcome_reviewed_source=direct_api_batch. MD012 guard test added.

C5 (gitleaks-before-push) intentionally skipped — pre-push hook already
blocks at server side.

Tests: 956/956 root tools, 0 regressions. LEFTHOOK=0 used per quirk #111.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-05-27 06:46:55 +03:00
Дмитрий 0789367742 chore(observer): runtime drift — counters + episodes-2026-05
ремонт инфраструктуры: runtime-данные observer Stop-хуков, накопленные за параллельные сессии 26.05.2026. Auto-generated, не требуют регрессии.

- .pii-counters.json: WIN_USER_PATH 97 → 107
- episodes-2026-05.jsonl: append-only events from observer-stop-hook

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
2026-05-26 20:26:10 +03:00
Дмитрий 9b7de8bf8c chore(observer): runtime + STATUS.md refresh after G/H/A1/A2 fixes + settings.json hook order
Hygiene commit after consolidated brain-retro #6 follow-up. Captures live
runtime state where the fixes are now visibly working:

  - STATUS.md regen reflects 917-test sentinel pass.
  - episodes-2026-05.jsonl: +50 lines from this session's turns, including
    state with source: llm + non-empty task_cost (A1 live evidence).
  - pii-counters.json: counter increments from PII filter scans during retro.
  - settings.json: linter-normalized hook order (no semantic change).
  - .gitleaksignore: prior staged hash entry from parallel session.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-05-26 20:04:38 +03:00
Дмитрий 8f9ffc387d chore(observer): brain-retro #6 — full reviewer pass (316/316), digital analysis
Period 2026-05-24T00:00Z..2026-05-26T13:18Z (~61h, 317 episodes).
Processed 132 unreviewed episodes via brain-retro-batch-reviewer.mjs
(Opus 4.7 / ProxyAPI, 293.6s, 0 errors). Coverage 100% (316/316), up from
91% in retro #5.

Findings:
  - rework 10.4% (33/316), stable vs retro #5 (11.4%)
  - 132 episodes (41.6%) with gap «recommended, picked direct» — but
    60-70% turned out to be silent regex-fallback false-positives (fixed
    in follow-up commit).
  - rework by group: skill_used 12.0% | direct_no_rec 2.5% |
    direct_ignored_rec 22.7% — delta 20.2 п.п.
  - user_chose_from_options: 0% rework / 0% blocked on 55 episodes —
    brainstorm-pattern is the strongest quality mechanism.
  - 85% episodes без self_assessment — owner подтвердил «бежал слишком
    быстро без остановки» (material signal).

Artefacts:
  - docs/observer/notes/2026-05-26-brain-retro-6.md (25KB)
  - docs/observer/sanity-checks/2026-05-26-brain-retro-6.json
  - STATUS.md regen (C5 488 episodes, missed_activations=21)
  - read-counter + self-retrospect-counter bumped (519 since last)

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-05-26 17:28:26 +03:00
Дмитрий 5215842304 chore(observer): episodes + pii-counter refresh after webmaster brainstorm session 26.05 вечер — К1+К2 финализированы в memory; К3-К7 пауза до фикса baseline-бага LeadRouter snapshot (см. spec 2026-05-26-slepok-routing-protection). Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> 2026-05-26 15:53:16 +03:00
Дмитрий 659f2b0757 feat(brain-retro): retro #5 — first reviewer pass (184/202) + batch-reviewer tool
Brain-retro #5 за период 2026-05-24T13:18Z .. 2026-05-26T05:09Z (202 эпизода).
Первый ненулевой reviewer-pass в истории brain-governance (раньше 0/414).

Key findings:
  • 184 episodes reviewed via Opus 4.7 ProxyAPI, 18 errors (~$9 cost)
  • outcome_reviewed: success 24.5% / soft_success 64.1% / rework 11.4%
  • node_quality: correct 30% / disputable 59% / wrong_node 9% / over+under 1.6%
  • 93.5% no_self_assessment — confirms self-assessment bug fixed in 752d80af
  • Top ignored nodes (wrong_node): #19 Superpowers (5), #18 Pest (3),
    #33 claude-md-management (2), #25 Semgrep (2)
  • Discipline regressed in long session: regulated 19% → 4.5%

Artifacts:
  • tools/brain-retro-batch-reviewer.mjs (new) — direct API batch driver
    for retros >50 episodes (canonical Task() spawn impractical at scale).
  • docs/observer/notes/2026-05-26-brain-retro.md (new) — full retro note
    with 4 candidates A/B/C/D for owner review.
  • docs/observer/sanity-checks/2026-05-26.json (new) — sanity Q&A.
  • docs/observer/episodes-2026-05.jsonl — 184 episodes mutated with
    review.* / outcome_reviewed / outcome_reviewed_source fields.
  • docs/observer/STATUS.md — refreshed.
  • docs/observer/.pii-counters.json / .read-counter.json / .self-retrospect-counter.json
    — bumped by procedure.

Spec: brain-retro skill .claude/skills/brain-retro/SKILL.md.
2026-05-26 10:49:28 +03:00
Дмитрий 633435e990 chore(observer): session episodes — Phase 4 follow-up testing
Append-only journal capture during the factor-analysis bug-surface session.
Episodes contain live tests of the LLM classifier retry logic (10/10 LLM
success rate post-retry) and the prefilter Layer 1 gate on short prompts.

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
2026-05-25 16:15:24 +03:00
Дмитрий 26999ca597 chore: working tree cleanup pre-llm-first-router merge
Три группы накопившихся auto-правок (НЕ ручные):

1. markdownlint --fix auto-format (~25 .md в docs/superpowers/, docs/security/marketing-vet.md, docs/adr/015, docs/deploy/lkomega-runbook): MD031/MD032 (blank lines around fence/list) + MD004 (bullet markers `+`→`-`). Содержательных текстовых правок 3: ADR-015 bullet, sprint5d-cleanup bullet, router-discipline trailing space.

2. lefthook 2.1.6 → 2.1.8 (package.json + lock): patch-bump, авто-резолвил npm.

3. Observer runtime (docs/observer/): episodes-2026-05.jsonl +420 строк (текущая активность мозга), STATUS.md regen, .pii-counters / .read-counter тики, +2026-05-24-brain-retro.md note.

Цель — разблокировать merge feat/llm-first-router → main (этап 0 плана постановки в боевой). Содержание ветки не трогает.
2026-05-25 14:23:11 +03:00
Дмитрий dd0ac43052 chore(observer): commit live router-classification episodes (stage 3 warn-only)
Эпизоды реальных сессий после hotfix — сторож пишет state + классификацию
на каждый промпт (verified: UUID-session state files). Данные для brain-retro
warn-only ревью.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-05-24 11:40:05 +03:00
Дмитрий b8adeeb9fd docs(stage2): commit plan + observer evidence from this session
План этапа 2 (8 тасков subagent-driven) + эпизоды наблюдателя
текущей сессии разработки + PII-counters file.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-05-24 07:50:05 +03:00
Дмитрий 11822e3803 fix(observer): RU_PHONE regex catches bare 7XXXXXXXXXX (DO-PII-1)
Bug: gitleaks (rule `ru-phone-unmasked`) caught `79135191264` in 3 lines
of docs/observer/episodes-2026-05.jsonl during brain-retro #3 push
(963379c3). Stop-hook PII-filter was not masking bare-format Russian
phone numbers (without the `+` prefix).

Root cause:
  const RU_PHONE = /\+7\d{10}/g;   // requires literal '+7'

Free-text observer episodes captured phone `79135191264` in field-value
context (`call client 79135191264` / `phone 79135191264 in payload`),
slipping past the existing filter.

Fix:
  const RU_PHONE = /(?:\+7|\b7)\d{10}/g;

The `\b7` branch catches bare format with a word-boundary on the left,
avoiding false-positives inside long digit sequences (timestamps, IDs,
hashes). False-positive guard verified via test:
  'id 1796133619135191264999 not a phone' → unchanged.

TDD cycle:
  - RED: 3 new tests + 1 sanitizeWithCount test (4 fails on bare phone)
  - GREEN: regex extended, 24/24 file tests pass, 373/373 full tools
    suite GREEN (0 regressions across 18 files).

Cleanup: applied sanitize() to docs/observer/episodes-2026-05.jsonl;
11 lines touched (3 phone-leak lines + 8 with other PII patterns).
gitleaks now finds 0 leaks in the file.

Pravila §5.2 (no PII in commits) + 152-FZ (phone is regulated PD).
Closes DO-PII-1 (see memory observer-pii-leak-2026-05-23).

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-05-23 12:26:24 +03:00
Дмитрий 16ac37aba9 docs(pilot): backend supplier group-sync fix задеплоен (d3197095)
Обновлены два места в ПИЛОТ.md:
- «Снимок снят» (line 11) — упоминание выкатки supplier group-sync fix.
- §2 «Развёрнутый прикладной код» (line 31) — детальный отчёт о
  фиксе, деплое и ре-тесте на проде. Зафиксировано что осталось
  не сделано (16 осиротевших + csv_reconcile spam, UI #4-#7,
  финальная чистка qa-tenant'ов).

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
2026-05-22 18:19:53 +03:00
Дмитрий 233f9984fc chore(observer): backfill chain_ref on live May episodes (working branch) 2026-05-21 06:19:51 +03:00
Дмитрий 9e1a07aad3 chore(observer): remove 5 empty unknown-* episode stubs + commit session episodes
unknown-<ts>, empty events, fake outcome:success) — zero information.
Removed; remaining episodes carry real data. One-time cleanup of
pre-extension garbage — append-only stays the operational rule.
STATUS.md regenerated by C4.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-05-19 13:40:37 +03:00
Дмитрий 910c2d0e37 feat(observer): docs/observer/ scaffolding — README + STATUS + counter + JSONL seed
Empty infrastructure per ADR-011 + Pravila §16.2. Hook + generators
wire up in subsequent tasks (B2 PII filter, B3 Stop-hook, B5 register
in settings.json, C4 STATUS generator).

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-05-19 06:07:42 +03:00