Дмитрий
2b7a71c5b6
План из spec v2.2 — 22 задачи (Task 0 pre-flight + 8 phase-1 + 8 phase-2 + 6 phase-3) в bite-sized TDD-формате. Phase 1 (foundation+archive): tag + archive scaffold + inventory hooks + discipline-metrics decision + test-rollback.mjs (TDD) + archive §12/routing- docs/memory + §17+ADR-016 + cross-refs §12→§17 + flags+ROLLBACK.md. Phase 2 (classifier): router-config + nodes.yaml capabilities + prefilter 3 группы/manual-override/anchor (TDD) + Sonnet 4.6 classifier+памятка (TDD) + missed-activations на nodes.yaml (TDD) + embedding (TDD) + §17 gate (TDD, D1 continuation-not-exempt) + prehook inheritance+cost (TDD) + parser v4.0 + C1/C2 adapters + warmup hook + flags flip. Phase 3 (evidence loop): Stop-hook execution_trace+chain_gaps+inheritance- copy (TDD) + self_assessment (TDD) + reviewer subagent verify + direct-API fallback handler + sanity-generator + brain-retro v2 procedure + self- retrospect skill + analyzer v4 + status-md cost sections + schema v4.3 + final flags + rollback dry-run verification. Self-review: spec coverage (8 слоёв + §17 + 16 находок v2.2), 0 placeholders (кроме намеренного model-ID резолва Task 0/9), type consistency проверена. Реализация — после Биллинга v2 Спек C. Фаза 4 (distillation) — отдельный план через ~6 месяцев. НЕ исполняется сейчас (per user). Co-Authored-By: Claude Opus 4.7 (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.