Files

T

Дмитрий 963379c3d9 chore(brain-retro): #3 retro + map/dormancy hygiene (A1/A2/B1/D1)

Brain-retro #3 за весь май 2026 — 116 v2-эпизодов / 61 task_ref.
Здоровье: 0 observer_error, 1.7% correction-rate, 19 skill-инвокаций
(vs 6 в ретро #2 — рост в 3×).

Применены 4 кандидата по явному «делай» от заказчика:

A1. observer-classification-map.json: question → [] (был ["#60"])
    Разговорные RU-вопросы давали 17/40 false-positive промахов против context7.

A2. observer-classification-map.json: memory-sync → [] (был ["#33"])
    #33 claude-md-management — канал ТОЛЬКО для CLAUDE.md (Pravila §5 п.10),
    не для memory/*.md. Давало 8/40 false-positive.

B1. Tooling §4.8 #34 Sentry MCP — boundaries +DEFERRED
    Sentry instance не задеплоен (pending Б-1). Двойной сигнал
    extractor'а → .node-dormancy.json[#34] = true.

D1. memory/feedback_feature_via_writing_plans.md (user-memory вне git).

Effect: missed-activations 40 → 15 после очистки шума. Из 15 реально
значимы 2 эпизода (audit-journaling closure 116 tools без writing-plans;
SyncSupplierProjectJobTest planning без skill). Остальные 13 — шум
классификатора на правках своих документов.

+cspell-words.txt: 20 слов (9 секций Tooling + 11 из retro-note).

NB: docs/observer/episodes-2026-05.jsonl снят со staging — gitleaks
обнаружил 3× RU-phone leak (`ru-phone-unmasked` rule). Это сигнал что
observer PII-фильтр пропустил телефон в free-text record — отдельный
follow-up (PII фильтр Stop-хука).

Retro-отчёт: docs/observer/notes/2026-05-23-brain-retro.md.
STATUS.md перегенерирован.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

2026-05-23 12:09:55 +03:00

notes

chore(brain-retro): #3 retro + map/dormancy hygiene (A1/A2/B1/D1)

2026-05-23 12:09:55 +03:00

.read-counter.json

chore(brain-retro): #3 retro + map/dormancy hygiene (A1/A2/B1/D1)

2026-05-23 12:09:55 +03:00

dashboard-core.js

feat(brain): conflict three-layer panel (design / friction / correlation) +3 tests

2026-05-19 16:23:51 +03:00

dashboard.html

feat(brain): Forest polish + observer README entry for the dashboard

2026-05-19 16:23:52 +03:00

dashboard.js

feat(brain): conflict three-layer panel (design / friction / correlation) +3 tests

2026-05-19 16:23:51 +03:00

episodes-2026-05.jsonl

docs(pilot): backend supplier group-sync fix задеплоен (d3197095)

2026-05-22 18:19:53 +03:00

README.md

feat(brain): Forest polish + observer README entry for the dashboard

2026-05-19 16:23:52 +03:00

STATUS.md

chore(brain-retro): #3 retro + map/dormancy hygiene (A1/A2/B1/D1)

2026-05-23 12:09:55 +03:00

README.md

Observer infrastructure

Passive evidence-loop for the Лидерра «brain» per ADR-011.

Files

episodes-YYYY-MM.jsonl — append-only JSONL, one line per Stop-event. Schema v2 (schema_version: 2): the 5 mandatory fields + decision_provenance (who chose the node), environment (economy_level / model / post_compaction / session_turn / parallel_session), task_size, task_ref, prompt_signal, and an outcome that is unknown at write time (refined by /brain-retro). On an internal hook failure a minimal observer_error marker line is written instead of a silent skip. Written by tools/observer-stop-hook.mjs via tools/observer-transcript-parser.mjs.
notes/YYYY-MM-DD-<slug>.md — optional MD notes for sessions with qualitative history.
STATUS.md — auto-generated dashboard. Regenerated per-commit by tools/status-md-generator.mjs.
.read-counter.json — C3 observer-of-observer counter. Updated on Read of observer files.
dashboard.html + dashboard.js + dashboard-core.js — Brain Dashboard: visualises the episode log over the automation-graph topology (4 views — Карта / Разбор / Лента / Агрегат). Run npm run brain:dashboard, open the printed localhost URL. dashboard-core.js is pure logic, unit-tested in tools/brain-dashboard-core.test.mjs.

Lifecycle

Write: every Stop-event appends one JSONL line, parsed from the session transcript (Stop-hook).
Aggregate: /brain-retro skill reads JSONL each sprint, proposes regulatory candidates.
Surface: STATUS.md shows controllers + monthly stats.
Self-prune: C3 warns if 54 weeks pass without any read of observer files.

Routing-tag discipline

When the user dictates a specific method/node (e.g. «запусти discovery-interview»), Claude must emit one line in its response:

<!-- routing: provenance=user_directed_method node=<chosen> counterfactual=<node Claude would have chosen autonomously> -->

The Stop-hook routing-gate (tools/observer-routing-detector.mjs + routingGateDecision) detects a dictated method; if the tag is missing it returns decision: block, so the turn cannot end without the tag. The gate fires at most once per turn (stop_hook_active guard). This makes decision_provenance reliable — factor analysis can separate a router error from a user-dictated one.

Privacy

PII filter (phone numbers, emails, tokens) is applied before every write — see tools/observer-pii-filter.mjs. gitleaks pre-push also scans observer files as part of full-history sweep.

Don't

Don't edit episodes-*.jsonl manually — it's append-only.
Don't write outside docs/observer/notes/ for hand-curated notes.
Don't change .read-counter.json manually — it's maintained by hooks.

HK1 pre-check (Pravila ADR-010) — verified 2026-05-19

Before registering tools/observer-stop-hook.mjs on Stop event (Task B5), verified collision against 6-component economy/skill-discipline architecture:

User-level ~/.claude/settings.json already has Stop hook: agent-type Sonnet-4.6 economy compliance verifier (analyzes transcript for claim-without-evidence violations).
Project-level .claude/settings.json — Stop slot empty.

Result: no overwrite. observer-stop-hook will be added as command-type entry in project-level Stop array. Project + user scopes are independent slots in Claude Code 2.x — both run on the same Stop event without conflict. The agent verifier (user scope) and the JSONL appender (project scope) have non-overlapping responsibilities.