Header «Версия» line lagged at 2.18 while §9 already carried v2.19
(factor-analysis extension) and v2.20 (phase 1.1) entries — pre-existing
drift from f7f37fb. Header now reflects actual latest version; v2.18
summary demoted to «v2.18 наследие». Full per-version detail stays in §9.
Через /claude-md-management:claude-md-improver (§5 п.10).
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Root cause (systematic-debugging): isRealUserPrompt treated skill-content
("Base directory for this skill:"), local-command output
(<local-command-stdout>), and interrupt markers as genuine prompts.
findTurnStart then anchored a turn on the synthetic message — the turn
slice missed the genuine prompt's UserPromptSubmit hook_additional_context
attachment → economy_level: null, wrong prompt_signal/task_classification.
Same cause made extractLastUserPromptText return skill content, so the
Stop-hook routing-gate false-positive-blocked autonomous §12 skill
invocations (detectMethodDirected saw the node name in skill text).
Fix: SYNTHETIC_PROMPT_MARKERS + isSyntheticPrompt — isRealUserPrompt
returns false for synthetic messages. One fix closes both the
economy_level capture gap and the 2nd routing-gate FP class.
160/160 tools tests GREEN (+3 new).
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Строка метрик начиналась с «+ 121 индекс» после переноса → markdownlint
MD004/MD032 (трактовал как list-item). Переформулирована через запятые.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Финальное code-review вскрыло CRITICAL: dedup-сверка findOnPortal и
manualQueueResolve матчат строки портала по {platform, signal_type,
unique_key}, но listProjects отдавал сырое тело rt-projects-load.
Сырая форма (verified из recon-снапшота 2026-05-19):
- ответ — конверт {projects:[443 строки], tags, users, ...}, НЕ голый массив
→ listProjects возвращал весь dict, findOnPortal итерировал по ключам
конверта (projects/tags/...) вместо строк проектов;
- строка проекта: {id, name:"B<n>_<key>", type:"hosts|calls|sms", content}
— без platform/signal_type/unique_key.
Фикс:
- SupplierPortalClient::listProjects — извлекает body['projects'].
- AjaxProjectChannel::listProjects — нормализует сырые строки в контракт
SupplierProjectChannel: platform <- префикс name "B<n>_", signal_type <-
type (hosts->site/calls->call/sms->sms), unique_key <- content. Сырые
поля сохранены. findOnPortal + manualQueueResolve матчат корректно.
- AjaxProjectChannelTest — тест нормализации против фактической формы
портала (не идеального мока); SupplierPortalClientRtProjectTest —
listProjects против конверта {projects}.
Также (code-review I1): findOnPortal catch — Log::warning проглоченного
исключения, иначе провал дедупа невидим (молчаливый дубль rt-проекта).
Code-review I2 (partial-unique индекс supplier_manual_sync_queue от
дубль-эскалаций при job-retry) и I3 (lockForUpdate в manualQueueResolve) —
follow-up до прод-релиза (эпик гейтится Б-1, не в проде).
Регрессия Pest 973/970/0 / 3 skipped.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Таблица pending-записей яруса 3 + кнопка «Отметить выполнено» с confirm-
диалогом, дёргает POST .../manual-queue/{id}/resolve. Реюз существующего
админ-экрана интеграции с поставщиком (после «Истории сверок»).
NB: spec в tests/Frontend/ (vitest include — tests/Frontend/**, не
resources/.../__tests__/ как указал план Step 11.1). loadManualQueue
defensive Array.isArray-guard — иначе onMounted в чужих spec'ах
(mockResolvedValue без queue-ключа) ловил undefined.length.
Spec §4.6. Task 11 of 12. Vitest 5/5 (2 новых + 3 существующих).
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
GET /api/admin/supplier-integration/manual-queue — pending список (limit 100).
POST /manual-queue/{id}/resolve — оператор пометил, что вручную создал проект
на портале; reconcile через channel->listProjects() по (platform, signal_type,
unique_key), 409 если не найден.
ОТКЛОНЕНИЕ ОТ plan Step 10.3: план писал portal external_id прямо в
projects.supplier_b*_project_id (FK на local supplier_projects.id) — FK
violation. Resolve делает firstOrCreate local supplier_projects row с
verified external_id, в FK пишет local id.
Routes — в группе saas-admin (web.php, EnsureSaasAdmin стаб). Task 10 of 12.
Tests 4/4 (index pending / exclude resolved / resolve match / resolve 409).
Spec §4.6.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Запас ~3 часа до портального дедлайна 21:00 — эскалация на ярус 2/3
(медленный браузер / ручной оператор) происходит в рабочее время.
RefreshSupplierSessionJob daily — на 15 мин раньше sync (17:45).
Hourly RefreshSupplierSessionJob — без изменений.
Spec §4.7. Task 9 of 12. Tests 2/2 (cron expression + timezone).
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Оба job'а инжектят SupplierProjectChannel (DI → FailoverProjectChannel)
вместо прямого SupplierPortalClient. Catch TierEscalatedException +
WindowDeferredException — эскалация/перенос пропускают элемент, не валят job.
SyncSupplierProjectJob (singular): handle переписан — find-or-create local
supplier_projects row, portal-create через channel. ОТКЛОНЕНИЕ ОТ plan Step 8.1:
план писал channel-результат (portal external_id) прямо в projects.supplier_b*_
project_id, но эта колонка — FK на supplier_projects.id (local), не portal id.
Сохранена семантика ensureSupplierProject — job создаёт local row с
supplier_external_id и пишет в FK local id. ensureSupplierProject удалён из
SupplierPortalClient (был единственный consumer — этот job).
SyncSupplierProjectsJob (plural): handle/syncOne принимают channel; create →
createProjectForLiderra, update → updateProjectForLiderra (context-project из
liderraProjects->first() для project_id в очереди яруса 3).
Tests: singular переписан под SupplierProjectChannel mock (6 tests, incl.
idempotency reuse); plural — handle(AjaxProjectChannel) для non-failover
ветки (Http::fake-контракт сохранён). Larastan отложен на T12 (worktree
quirk — гонится в основной копии). Регрессия Pest 966/963/0 / 3 skipped.
Spec §5. Task 8 of 12.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
create/update/list через headless Chromium по образцу refresh-session.js.
Селекторы зафиксированы из recon-снапшота rt-add-project-form.yml (Task 1).
stdin/stdout JSON, exit codes 0/1/2/3/4 (success/auth/selector/timeout/input).
Фикстурный тест против локального HTML — без живого портала. Runner —
встроенный node:test (app/playwright не использует @playwright/test, только
playwright core); skipLogin режим открывает фикстуру напрямую.
Spec §4.3. Task 6 of 12. Node-тесты 2/2.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
listProjects() матч по (platform, signal_type, unique_key) до create.
Защита от дубля при полу-успехе яруса 1 (create прошёл на портале, но
локальная запись не сохранилась → следующий запуск дублировал бы).
listProjects-сбой проглатывается — ярус-эскалация всё равно покроет.
Spec §4.4 шаг 2, §7. Task 5 of 12. Тесты 7/7 (19 assertions).
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Live discovery через Playwright MCP (Task 1):
- создан LIDPOTOK_TEST_DELETE_ME (B1+B2+B3) → 3 rt-проекта на портале;
- записаны сетевые запросы /admin/visit/rt-*;
- все три проекта удалены вручную, портал чист.
Endpoints (verified):
- POST /admin/visit/rt-project-save (create id:0, update id:N — same URL)
- POST /admin/visit/rt-project-delete (id строкой)
- GET /admin/visit/rt-projects-load?src=none
Все три — application/json. Конверт ответа:
- success: HTTP 200 + {status:OK, message, result, id?:string}
- error: HTTP 200 + {status:Error, message, result:null}
ID — строка (12721245), приводится к int (fits в int64).
Один save с B1+B2+B3 включёнными создаёт 3 rt-проекта — toPayload()
шлёт ровно один платформенный флаг (srcrt|srcbl|srcmt).
SupplierPortalClient:
- docblock переписан под verified контракт
- listProjects: путь /admin/visit/rt-projects-load + ?src=none query
- saveProject: путь /admin/visit/rt-project-save, asJson, парсинг id
- updateProject: тот же endpoint что save, id:N в body
- deleteProject: путь /admin/visit/rt-project-delete, asJson, id строкой
- new assertStatusOk() — HTTP 200 + status:Error → SupplierClientException
- toPayload(): полный Vuex-payload с маппингом DTO → portal:
- platform B1/B2/B3 → srcrt/srcbl/srcmt (single-true)
- signalType site/call/sms → type:hosts/calls/sms
- workdays int[] → string[]
- status active/paused → bool
- + tag:_lidpotok, name/content из uniqueKey, defaults для show/depth/etc
Tests:
- new: tests/Feature/Supplier/SupplierPortalClientRtProjectTest.php (7 tests,
contract: save+update+delete+list + 2 status:Error error-paths + B2/calls
mapping)
- Sync/Cleanup/Unit тесты обновлены под новый URL + envelope shape.
Закрывает spec §1 honest-caveat «placeholder, не верифицирован»
и журнал решений запись 9. Регрессия: Pest 944/941/0 failed / 3 skipped
/ 2768 assertions / 59.2s.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
buildFactorMatrix already buckets decision_provenance.kind dynamically
(brain-retro-analyzer.mjs:112) — no production change needed. Test
pins that user_chose_from_options is counted on the provenance axis.
12/12 brain-retro tests GREEN.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
When episode is user_chose_from_options, routing-gate does NOT block —
collaborative-choice from Claude-offered options doesn't require a
routing-tag (detector is deterministic). 18/18 stop-hook tests GREEN.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
detectChoiceProvenance runs BEFORE parseRoutingTag; if last assistant
turn offered options and user prompt references one, decision_provenance
becomes user_chose_from_options. Otherwise falls back to existing
routing-tag / autonomous logic.
3 new parser tests GREEN; all existing tests still GREEN (43/43).
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Pure module — extracts options (numbered/lettered/bullets/AskUserQuestion)
from last assistant message, detects user reference (position-based +
substring), returns decision_provenance for the 3rd kind.
23/23 tests GREEN.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Adds 3rd decision_provenance kind for collaborative-choice case
(user picks one of options Claude offered). Distinct from
user_directed_method: counterfactual = Claude's recommended option,
not "what Claude would have done autonomously". Routing-gate does
NOT block this kind — collaborative choice from Claude-designed
choice-space.
Trigger: 19.05.2026 live false-positives — "1 экономия 0%",
"в делаем", "делай 2" classified as user_directed_method.
§11 + 8 subsections; 7-attribute decision_provenance schema;
new tools/observer-choice-detector.mjs (pure module); parser
+routing-gate +/brain-retro extensions.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Pure deterministic Layer-4 aggregation module (spec §6) for the /brain-retro
skill. Exports: dedupeEpisodes, inferOutcome, groupEpisodesToTasks,
findCausalChains, buildFactorMatrix, analyze. Read-only — never writes JSONL.
11/11 tests green. CLI smoke: 10 real episodes → valid JSON with all 5 keys.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Русская проектная лексика для плана резерва канала миграции проектов
(docs/superpowers/plans/2026-05-19-supplier-project-channel-failover.md).
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
12-task plan implementing the spec
docs/superpowers/specs/2026-05-19-observer-factor-analysis-design.md
in 4 layers (schema v2 + capture + enforcement + analysis) plus
normative sync. Each task has TDD steps with full code.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Design for making the brain governance observer rich enough for real
factor analysis. Surfaced during a discussion with the owner: the
observer is "paper-complete" but episodes lack the data factor analysis
needs — the outcome is a hardcoded "success", there is no decision
provenance (who chose the node — Claude autonomously, or the owner
forcing a method), no environment factors, no task grouping.
4-layer architecture:
- Layer 1 — episode schema v2: decision_provenance (+ counterfactual),
environment block, task_size, real outcome enum, task_ref.
- Layer 2 — capture: deterministic transcript parsing for all factors +
a one-line routing tag (owner-forced-method only).
- Layer 3 — two-sided enforcement: 3a routing-gate (Stop-hook blocks the
turn until the tag is present — unbypassable by Claude); 3b observer
self-discipline (silent failures become recorded observer_error
markers; coverage + registration verified by a controller).
- Layer 4 — analysis: /brain-retro infers real outcome from the next
episode's opening prompt, groups episodes into tasks, correlates
causal chains, builds the factor matrix.
Scope: everything except an independent agent-judge — that, plus
confusion_marker as a real judgment and real-time friction flags, is
phase 2 (separate spec).
Brainstormed via superpowers:brainstorming. Next: writing-plans.
Refs: ADR-011, spec 2026-05-19-brain-governance-design.md, Pravila §16.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
The committed STATUS.md was stale (generated 2026-05-19T03:49, before
the C1/C2 strict-mode fixes and before the post-commit hook existed):
it showed C1/C2 🔴 and "0 episodes". Regenerated via the now-installed
post-commit hook (C4 status-md job) — C1/C2/C3/C4 all ✅, 5 episodes.
Context: `.git/hooks/post-commit` was never installed, so the C4
status-md job (lefthook post-commit) never ran automatically. Fixed
locally via `lefthook install --force` (installs pre-commit/post-commit/
pre-push). The hook files live in `.git/` and are not version-tracked —
re-run `lefthook install` after clone if hooks go missing.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
The Stop-hook was writing empty-shell episodes (task_id "unknown-<ts>",
node_chosen "unknown", events []). Root cause: buildEpisodeFromContext
read fields from the Stop-event stdin that Claude Code never sends
(primary_rationale, node_chosen, ...) and the session field name was
wrong (ctx.sessionId camelCase vs Claude Code's session_id). The hook
never read transcript_path — the only real source of session data.
New tools/observer-transcript-parser.mjs — pure parseTranscript(text,
fallbackSessionId):
- Scopes to the last turn (from the last real user prompt to EOF) —
one episode == one prompt→response cycle. A tool_result-carrier user
message is not treated as a turn boundary.
- Extracts task_id (real sessionId), timestamps (real duration),
skill_invoked events, a tool_summary event with per-tool counts,
error events (tool_result is_error), node_chosen (first skill, else
"direct"), hard_floor (invoked when a superpowers:* skill is used),
path_type (regulated/improvised), task_classification (keyword
heuristic on the prompt).
- Reasoning fields triggers_matched/candidates_considered/
boundaries_applied stay [] — not recoverable from a transcript;
their capture is a separate ADR-011 follow-up.
observer-stop-hook.mjs: reads ctx.transcript_path + ctx.session_id
(camelCase fallback kept), readFileSync best-effort, delegates to
parseTranscript. No transcript → graceful fallback to ctx defaults.
Episode schema (5 mandatory + 7-field primary_rationale) unchanged —
no normative change. Stop-event is never blocked (exit 0 on any error).
TDD: 17 parseTranscript tests + 1 buildEpisodeFromContext transcript
test. Full tools Vitest 70/70 GREEN. CLI smoke against a real 575-entry
transcript: episode populated — real task_id, ~6.5 min duration,
tool_summary {Bash:5,Read:5,Grep:1,Edit:9,Write:1}, error event.
Refs: ADR-011 brain governance §6.2 (observer evidence loop).
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Removes the `missingInSettings` reverse check ("plugin documented in
Tooling but disabled in settings.json"). It was broken by design:
Tooling Прил. Н lists tools by human/group name ("Frontend Design
plugin", "Trail of Bits Skills") while settings.json keys are machine
IDs (`name@marketplace`) — the two namespaces never compare. The
`/#\d+\s+([\w-]+(?:@[\w-]+)?)/` scan also captured the first plain word
after "#NN" ("#1 PostgreSQL MCP" → "PostgreSQL"), so every run emitted
~190 lines of WARN noise.
ADR-011 §6.1 specifies only the settings→Tooling direction (the L1
pattern "plugin enabled without Tooling formalization"). That is the
FAIL path and is unchanged. detectDrift now returns `{ missingInTooling }`
only. CLI output is a clean single line on success.
Closes the cosmetic issue flagged in bffdaa9.
TDD: reverse-check test replaced with `not.toHaveProperty
('missingInSettings')`; 12/12 GREEN. Smoke: node tools/l1-watcher.mjs
-> exit 0, "OK — 0 drift" (no WARN block).
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Removes the `|| true` WARN-only guard from pre-commit jobs 11
(l1-watcher) and 12 (cross-ref-checker). Both controllers now block
the commit on real drift.
Safe to flip now that the false-positive sources are closed:
- C1: tools/.l1-watcher-aliases.txt resolves the 9 name@source drifts
(Frontend Design plugin, Trail of Bits Skills group).
- C2: link-anchored detection + history-block scope-cut removes the
~150 «наследие»/arrow-transition false positives.
Verified on the current tree: node tools/l1-watcher.mjs -> exit 0,
node tools/cross-ref-checker.mjs -> exit 0. Comment blocks and
fail_text updated to describe strict behaviour and the alias escape
hatch.
Refs: ADR-011 brain governance §6.1 / §6.2.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Closes the ~150 false drifts that prevented strict mode. The old regex
`\b(Name)\s+v(\d+\.\d+)` swept the whole file head and matched every
historical version mention, plus the FROM-side of arrow transitions
("v1.30→v1.31"). Real current-vs-header drift in the repo: zero.
Two-tier detection:
- Primary LINK_REF_RE: a markdown-link to a normative file followed by
the first bold version — "[..](docs/Tooling_v8_3.md) (**Прил. Н
v2.17**". Link anchor makes it immune to history-block noise. This is
how CLAUDE.md §0 cross-refs table is written, so CLAUDE.md is fully
validated. Runs on the whole file.
- Fallback CROSS_REF_RE: plain "Name vX.Y" mention, scoped to the text
*before* the first history block. Pravila/Tooling/PSR_v1 have no
markdown-link cross-refs, so the fallback covers them — but their
shapki list past releases, so the scan stops at the first history
marker (`**vN.M наследие**` / `**Что изменилось в vN.M относительно**`
/ `**vN.M** — `). dedupe-by-target keeps the first ref per target.
Regex hardening:
- `\b` after the version forbids backtracking to a partial capture
(so "v1.30→" never collapses to a spurious "v1.3" match).
- `(?!\s*→)` negative lookahead drops the FROM-side of transitions.
TDD: 8 new tests (link-based, "Прил. Н" prefix, multi-file table,
dedupe, two arrow shapes, three history-marker shapes, link-beats-
fallback). 18/18 GREEN.
Smoke: node tools/cross-ref-checker.mjs -> exit 0, "OK — 0 drift in
4 files" (Pravila/CLAUDE.md/Tooling/PSR_v1; MEMORY.md is outside the
repo by design — existsSync-skipped).
Refs: ADR-011 brain governance §6.2 (C2 cross-ref consistency detector).
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Closes the 9 pre-existing name@source drifts that prevented strict mode:
settings.json lists each marketplace plugin by machine name (e.g.
"frontend-design@claude-plugins-official"), while Tooling Прил. Н
describes them under a human/group name (e.g. "Frontend Design plugin",
"Trail of Bits Skills" — single row #39 for 8 sub-plugins).
Mechanism:
- tools/.l1-watcher-aliases.txt — settings_name=tooling_substring map.
- detectDrift(settings, tooling, aliases): direct match first, then
alias-substring fallback. Settings name considered formalized if
Tooling text includes either the name itself or aliases[name].
- parseAliases(raw) exported — line-based KV parser with #-comments
and split-on-first-= semantics (values may contain "=").
TDD: 6 new tests (3 detectDrift + 4 parseAliases). 12/12 GREEN.
Smoke: node tools/l1-watcher.mjs -> exit 0, "OK — 0 drift".
Known cosmetic baseline issue (pre-existing, not introduced here):
the missingInSettings WARN list is noisy — regex
/#\d+\s+([\w-]+(?:@[\w-]+)?)/g captures the first \w+ after "#NN"
even when it is a plain word (e.g. "#1 PostgreSQL MCP" -> "PostgreSQL"),
producing ~190 WARN entries. WARN is non-blocking, so strict mode flip
in Phase 3 is unaffected; a follow-up filter on names containing "@"
would silence this without behavioural change.
Refs: ADR-011 brain governance §6.1 (C1 L1-watcher detector for the
"plugin in settings.json without Tooling formalization" L1 pattern).
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Дмитрий