§6 drifted from the implemented brain-retro analyzer after Phase 1.2/1.3:
- factor matrix now lists 9 axes (session_turn + parallel_session were
captured in the episode schema §3 but missing from the §6 matrix);
- outcome inference documents 'blocked' (error events > retry events) and
notes 'failure' as deferred to the phase-2 agent-judge.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
P0.1b: inferOutcome emits 'blocked' when a turn had more error than retry
events (an unrecovered tool failure) — previously the enum value was dead.
P0.1c: 'failure' documented as deferred to the phase-2 agent-judge. It is a
judgment (work wrong AND never corrected), not deterministically recoverable
from a transcript; a wrong-then-corrected turn surfaces as 'rework'.
P1.1: analyze() drops v1 episodes (no schema_version 2) — they lack
environment/prompt_signal/decision_provenance and polluted the factor
matrix. Reports v1SkippedCount.
P2.1: session_turn (bucketed early/mid/late) and parallel_session added to
FACTOR_FNS — closes the schema↔matrix mismatch (both were captured in the
episode but absent from the factor axes).
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
P0.2: count session_turn from the last compaction. The transcript file
accumulates duplicated context-rebuild snapshots (quirk #101), so counting
real prompts from i=0 inflated it and made it non-monotonic. Now counts
"real prompts since the last compaction" — monotonic by construction.
P0.1a: widen the correction prompt_signal regex (не работает / сломал /
опять / откати / revert / still not / wrong / ...). The old regex was too
narrow, so rework outcomes were invisible to the factor analysis.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Task 4 live-smoke выявил: единственный .el-switch формы — include/exclude
регионов (regions_reverse), НЕ статус active/paused. Старый код кликал его
по dto.active → ошибочно ставил regions_reverse. Статус — дефолт портала
(active), UI-switch для него нет → switch-блок удалён.
recon-doc 2026-05-19-rt-project-form-locators.md: +секция Live-smoke
(domain-формат валидируется, multi-source save = N проектов, switch = regions,
type/tab re-render); row 6 исправлен.
Найдено при Task 4 live-smoke form-канала:
- type-select и вкладка «Список» кликались безусловно → re-click уже-активного
значения ремоунтит Element UI tab-pane (textarea детачится). Теперь кликаем
только при реальной смене значения + waitForTimeout после смены типа.
- defensive: проверка непустого textarea после fill content.
- diag: на status!=OK дамп фактически отправленного rt-project-save body в stderr.
- fillForm rewritten to label-for locators (.el-form-item:has([for="..."])) from recon 2026-05-19
- createOp: external_id from page.waitForResponse('rt-project-save') body, not DOM
- updateOp: same save endpoint intercept; row found by data-id or text
- listOp: Vuex state strategy 1, DOM scrape strategy 2, empty array fallback
- Known gaps (JSDoc + stderr warnings): workdays not in add-project form (portal default);
regions require id->name mapping (skipped in Tier-2 MVP, logged to stderr)
- Test: HTTP fixture server serves rt-form-element-ui.html + handles /admin/visit/rt-project-save
- Fixture: .v-dialog--active wrapper + 10 .el-form-item (label[for=...]) + type-select popup in body
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Browser smoke (Playwright) revealed that rewriting path internally without
changing the response URL left the browser's base URL as /, breaking
relative <script src="dashboard.js"> and ../automation-graph-data.js
references. 302 redirect makes the browser settle on /docs/observer/,
which resolves the relative paths correctly. All 4 views verified clean
(0 console errors). Screenshots: brain-dashboard-{map,replay,feed,aggregate}-view.png.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Worktree has no app/node_modules — vitest not run here; final regression
deferred to main-checkout post parallel-session release. Logic is a 7-line
pure filter; tests cover empty filter, classification, errors-only.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
The config's include `../tools/*.test.mjs` resolves relative to its
own dir (app/), not cwd. Baseline verified 2026-05-19 from app/:
11 files, 169 tests passing, 0 failures.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Standalone HTML dashboard that visualises the observer episode log over
the automation-graph topology — 4 views (map / task-replay / session
feed / aggregate), graph as shared canvas, 3-phase build order.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Логин-страница уже в состоянии networkidle → waitForLoadState резолвился
мгновенно (до пост-логин редиректа), скрипт хватал PHPSESSID
неаутентифицированной логин-страницы. CSV-сверка 11:00 (19.05) упала
"load-reports returned non-array response" — портал отдал HTTP 200
+ HTML логин-страницы вместо JSON-массива отчётов.
После клика submit:
- waitForFunction опрашивает исчезновение #loginform-username из DOM
(переживает навигацию);
- guard exit 1, если форма осталась — отклонённый логин больше не
маскируется под «успех» (exit 0).
Verified: 2× RefreshSupplierSessionJob → валидная сессия (load-reports
JSON-массив из 39 отчётов); CsvReconcileJob id=7 status=ok.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
core.autocrlf=true rewrites .mjs to CRLF in the working tree on
checkout/rebase. vitest fails to load CRLF .mjs files with imports
(SyntaxError: Invalid or unexpected token, no location) — node --check
and esbuild tolerate it, only vitest's transform breaks. `*.mjs text
eol=lf` pins LF in the working tree regardless of autocrlf.
See memory quirk #100. Repo blobs were already LF — no content change.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
#1 — detectAskUserQuestionChoice: when a turn contains an AskUserQuestion
whose answer exactly matches an offered option label, classify as
user_chose_from_options. The answered entry carries a structured
toolUseResult (questions[].options[].label + answers map). A custom
"Other" free-text answer is NOT a pick — falls through. Wired into
parseTranscript after the text-list detector.
#3 — parallel_session: dropped broad word matches (параллельн /
"parallel session") that false-fired on any casual mention. Now only
strong collision evidence (foreign git index / чужой staged /
index.lock / another git process). Best-effort per spec R2 — prefer
false-negative over false-positive.
169/169 tools tests GREEN (+9 new).
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
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 831573d. 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>
Дмитрий