Дмитрий
ae3f841cee
loadFloorEscapes (единственный ВЫДАЮЩИЙ читатель floor_escape) теперь key-gated
проверяет подпись: ключ есть → оставить только валидно-подписанные (форж/
неподписанный/битый отброшены); нет ключа (truthy) → принять все (как сегодня,
content-floor backstop).
- Рефактор: generic loadRecords → floor_escape-специфичный readFloorEscapeRecordsAt,
возвращает ПОЛНЫЕ записи {type,action,ts,sig} (не stripped) для верификации.
Единственный вызыватель — loadFloorEscapes (loadConsumed читает другой файл).
- loadFloorEscapes(sessionId, now, {keyImpl, fsImpl, runtimeDir}) — 3-й опц.
аргумент, обратно-совместим (8 потребителей зовут loadFloorEscapes(sess)).
- ОТКЛОНЕНИЕ от дословного кода плана (одобрено владельцем): быстрый путь —
пропусков нет → [] БЕЗ резолва ключа. Поведение §3/§6 идентично, но keychain-
subprocess не дёргается на каждый tool-use в массовом пустом случае
(loadFloorEscapes — gate hot-path; 5 из 8 потребителей keychain не читали).
TDD: 6 новых тестов — 4 key-gated (signed принят / forged+tampered отброшены /
ключ null → все / '' falsy → все / окно 5 мин), 2 на быстрый путь (нет записей /
нет файла → [] без вызова ключа). Регрессия существующего escape-grant GREEN
(26 тестов). Суммарно 32 GREEN по затронутым файлам.
План: docs/superpowers/plans/2026-06-10-floor-escape-signing.md (Task 3)
Прод-код инертен до провижининга ключа (Фаза 8). Гейт закрытия — следующим шагом.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
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 anoutcomethat isunknownat write time (refined by/brain-retro). On an internal hook failure a minimalobserver_errormarker line is written instead of a silent skip. Written bytools/observer-stop-hook.mjsviatools/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 bytools/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). Runnpm run brain:dashboard, open the printed localhost URL.dashboard-core.jsis pure logic, unit-tested intools/brain-dashboard-core.test.mjs.
Lifecycle
- Write: every Stop-event appends one JSONL line, parsed from the session transcript (Stop-hook).
- Aggregate:
/brain-retroskill reads JSONL each sprint, proposes regulatory candidates. - Surface:
STATUS.mdshows 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-*.jsonlmanually — it's append-only. - Don't write outside
docs/observer/notes/for hand-curated notes. - Don't change
.read-counter.jsonmanually — 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.jsonalready 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.