Files
portal/docs/observer
Дмитрий c6f9dc2d76 feat(brain): Pravila §17 (universal skill-coverage) + ADR-016 (phase 1 task 5)
Phase 1 Task 5 of LLM-first router overhaul. §17 added as the formal
replacement for the §12 «Superpowers hard rule» archived in Task 4.

Pravila changes:
- Header v1.40 -> v1.41 (25.05.2026) + changelog entry.
- §17 «Universal skill-coverage rule» added (6 subsections):
  - §17.1 default-deny on non-conversation tasks.
  - §17.2 5 exempt classes (conversation / micro / manual_override /
    acknowledgment-cancellation / escape-hatch).
  - §17.3 Continuation НЕ exempt (D1).
  - §17.4 Enforcement via router-tool-gate.mjs + runtime mode-flag
    (off / warn-only / enforce; default Phase 2 = warn-only).
  - §17.5 Status (not hard-rule under §9, mechanical hook).
  - §17.6 Link to §16.4 missed-activation.

ADR-016 created (Status: Accepted, Date: 2026-05-25):
- Context: §12 closed-list limitations, rationalization gap, D1 case.
- Decision: §12 archived, §17 introduced.
- Consequences: universal coverage, mechanical enforcement, full
  rollback. Cost ~$320-1370/mo bootstrap (accepted).
- Boundaries: 10 scenarios mapped.
- Enforcement: hook chain + adr-judge + brain-retro + STATUS.md C5.

No code changes — normative-text + new ADR file only. Test impact zero.

Plan: docs/superpowers/plans/2026-05-25-llm-first-router-overhaul.md Task 5.
Spec: docs/superpowers/specs/2026-05-24-llm-first-router-overhaul-design.md §6.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-05-25 14:28:24 +03:00
..

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

  1. Write: every Stop-event appends one JSONL line, parsed from the session transcript (Stop-hook).
  2. Aggregate: /brain-retro skill reads JSONL each sprint, proposes regulatory candidates.
  3. Surface: STATUS.md shows controllers + monthly stats.
  4. 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.