Files

T

Дмитрий 975570e555 chore(brain): phase-1 flags + rollback re-verify — Phase 1 closed (task 7)

Phase 1 Task 7 closes Phase 1 of LLM-first router overhaul.

Live user-level state (NOT git-tracked):
- ~/.claude/runtime/skill-discipline-mode.json = {mode: 'off'} (new).
- ~/.claude/runtime/router-gate-mode.json = {mode: 'warn-only'} (unchanged).

Rollback re-verified after 6 destructive Phase 1 commits:
- node tools/test-rollback.mjs --dry-run -> OK.
- Tag brain-pre-llm-bootstrap intact (origin/main 9d4a30c3).
- Snapshots in docs/archive/llm-bootstrap-2026-05/ all present.

Phase 1 commits (7 tasks, 7 commits):
- dc7fd579 Task 1: Rollback infra + e2e proof.
- 3073e0cb Task 2: §12 hooks unwired, economy preserved.
- 03600acc Task 3: discipline-metrics KEEP.
- bca63fc6 Task 4: §12 archived + 4 tools mv + 2 consumers refactored.
- 712b4c63 Task 5: Pravila §17 + ADR-016.
- 6d72f5b6 Task 6: cross-ref version drift fix (minimal scope).
- (this commit) Task 7: phase-1 flag + rollback re-verify.

Final verification:
- npx vitest run tools/ : 539 passed (baseline preserved).
- C1 l1-watcher: 0 drift.
- C2 cross-ref-checker: 0 drift in 4 files.
- All 7 Phase 1 exit criteria met (TASKLOG.md Task 7 section).

Plan: docs/superpowers/plans/2026-05-25-llm-first-router-overhaul.md Task 7.

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

2026-05-25 14:28:24 +03:00

baselines

fix(baseline): correct dangling SHA reference (final review minor)

2026-05-24 07:32:20 +03:00

notes

chore: working tree cleanup pre-llm-first-router merge

2026-05-25 14:23:11 +03:00

.pii-counters.json

chore: working tree cleanup pre-llm-first-router merge

2026-05-25 14:23:11 +03:00

.read-counter.json

chore: working tree cleanup pre-llm-first-router merge

2026-05-25 14:23:11 +03:00

active-projects.md

docs(continuity): stage 3 follow-up закрыт — 3 fixes + STATUS regen

2026-05-24 16:01:41 +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

chore: working tree cleanup pre-llm-first-router merge

2026-05-25 14:23:11 +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): phase-1 flags + rollback re-verify — Phase 1 closed (task 7)

2026-05-25 14:28:24 +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.