Коммит 2. Каждое ручное зеркало получает настоящий гард/деривацию/parity-тест
вместо комментария «mirror this»:
- ROUTING_PROSE → ОБРАТНЫЙ гард (server-instructions.ts): прямой уже покрыт
генерируемым <tool_inventory> (каждый зарегистрированный тул в списке); теперь
`unregisteredProseToolMentions` краснеет, если проза ссылается на
несуществующий/переименованный тул (camelCase-токены прозы ⊆ реестр, минус
явный список не-тул-терминов PROSE_NON_TOOL_TERMS). Раньше мёртвая ссылка в
прозе не краснела. Мутационный тест: `getPageContentz` ловится.
- LABELS экспорта чата (chat-markdown.util.ts) → parity-тест: каждый ключ-ярлык
обязан быть реальным in-app тулом (иначе переименованный тул молча
сваливается на generic «Ran tool <name>»), и оба языка (en/ru) размечают
ОДИН набор тулов.
- зонд comment-signal ×2 (оба хоста) → общий `createListCommentsProbe` в
packages/mcp: index.ts и ai-chat-tools.service.ts (через loader) строят
tracker.probe из ОДНОЙ фабрики — тела больше не могут разойтись (например,
один считает resolved-комментарии, другой нет). Проброшен через loader-границу
как опциональный (отсутствует на устаревшем билде → сигнал выключен).
- countAnchorMatches (comment-anchor.ts) → делегирует решение
exact-wins/strip-fallback единственному резолверу resolveAnchorSelection
вместо параллельной копии; поведение идентично (rawCanAnchor ⟺ rawCount>0),
parity-тест по корпусу краснеет при расхождении count↔resolve.
- normalize+sha256 ×2 (gen-registry-stamp.mjs + docmost-client.loader.ts):
зеркало УЖЕ закрыто cross-impl parity-тестом (CROSS_IMPL_TREE/EXPECTED
проверяется с обеих сторон) — критерий issue «либо parity-тест» уже выполнен;
извлечение общего модуля через границу пакета/билд-шага регрессионно-опасно
для load-bearing integrity-проверки (#486), поэтому оставлено как есть.
Тесты: mcp node --test unit+mock зелёные (844); затронутые server-specs
(chat-markdown, comment-signal-inapp, loader, service, tiers, contract, cap)
зелёные (351).
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
F1: pc.title (untrusted cross-user page title) was interpolated raw into the
markdown export heading. Reusing escapeAttr alone (the prompt sink's XML-attribute
sanitizer, strips < > ") is insufficient here because the sink is MARKDOWN: link
/image syntax survives, so a title like  or [phish](http://evil)
injects a remote image / clickable link into the downloaded .md disguised as a
trusted system annotation. Add markdownHeadingSafe() = escapeAttr() + backslash-
escape [ and ] (disables both [text](url) and ; a bare (url) is inert).
F2: cover the title branch — a title that collapses to empty via escapeAttr falls
to the bare heading (no ("")), and a link/image-injection title is neutralized
(non-vacuous vs the escapeAttr-only version).
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
The #274 page_changed marker lived only in the ephemeral system prompt, so the
diff the agent saw was invisible in the chat export/history, and the note was
too weak — the agent still overwrote the user's manual edits with a full-page
replace.
- Persist the diff the agent saw as metadata.pageChanged on the assistant row
(flushAssistant), threaded into all five flush call sites in stream(). Model
replay (rowToUiMessage/rowParts) reads only metadata.parts, so the sibling
never re-injects the note into the model context on later turns.
- Render the persisted diff as a labelled block (en/ru) before the message body
in the server-side Markdown export (chat-markdown.util.ts).
- Strengthen PAGE_CHANGED_NOTE: mandate a fresh getPage re-read and targeted
edits (editPageText/patchNode/insertNode/deleteNode) instead of a whole-page
replace, and never revert or overwrite the user's edits.
Tests: prompt, export and service specs updated; 114 pass, tsc clean.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Approve-with-comments re-review; no blockers. All 7 actionable points (8 is a
forward-looking architecture note — recommendation A, keep as-is):
1. chat-markdown.util spec: restore parity coverage of the removed client spec —
tool error state (+ errorText), unknown-tool fallback (`Ran tool <name>` en /
`Выполнил инструмент <name>` ru), and the circular-output stringify catch.
2. findAllByChat row cap is now testable (injectable limit) + an int-spec proves
truncation on a modest volume.
3. Stability: the per-step durability updates are SERIALIZED via a promise chain
(stepUpdateChain) so they commit in step order — onlyIfStreaming already
closed the finalize race, this closes inter-step ordering.
4. findAllByChat keeps the NEWEST messages on truncation (order DESC + reverse,
like findRecent) and logs a warning with chatId, instead of silently dropping
the newest tail.
5. The LABELS parity comment already references the real path (tool-parts.tsx /
toolLabelKey) — confirmed accurate.
6. Removed the redundant 'off-by-one boundary' test (strict subset of the two
adjacent prepareAgentStep cases).
7. Extracted the terminal-finalize dispatch into a shared `applyFinalize`, used
by BOTH the service's finalizeAssistant and its test — the test now exercises
the real path, not a copy, so a production drift fails it.
Verified: server build + 325 ai-chat unit + 6 integration; prettier clean.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
The chat lived in inconsistent paradigms (in-memory stream + client export vs.
DB-as-context), which made export flaky and lost the assistant answer if the
process died mid-turn. Make the DB the single source of truth.
A. STEP-GRANULAR DURABILITY (server)
- ai_chat_messages gains a nullable `status` column (migration; NULL = legacy =
completed). The assistant row is now INSERTED UPFRONT as `status:'streaming'`
and UPDATEd on every onStepFinish with all finished steps (text + tool calls +
tool RESULTS), then finalized once to completed/error/aborted on the terminal
callback. So a process death mid-turn keeps every finished step; a startup
sweep (OnModuleInit → sweepStreaming) flips any dangling 'streaming' row to
'aborted'. The write path no longer depends on a live socket.
- Pure exported `flushAssistant(steps, inProgressText, status, extra?)` builds
the persist payload (metadata.parts byte-identical to the old builder), so a
future background worker can call the same path. AiChatMessageRepo gains
`update`, `sweepStreaming`, and `findAllByChat`.
- consumeStream drain, external-MCP client close-once, SSE heartbeat preserved.
B. SERVER-SIDE EXPORT
- New pure `chat-markdown.util.ts` renders Markdown from DB rows ONLY (server
port of the client builder). Because A persists the in-progress row, the
export now includes an interrupted turn up to its last finished step (flagged
"still generating"). `POST /ai-chat/export` (owner-gated via assertOwnedChat,
workspace-scoped) returns it; `lang` accepts a full client locale tag
('en-US'/'ru-RU') and is normalized server-side (normalizeLang) — a strict
@IsIn(['en','ru']) DTO rejected the real client's i18n.language with a 400,
caught in real-browser testing.
- Client: handleCopy calls the endpoint; `canExport = !!activeChatId`. The whole
liveThreadRef/liveStateRef/onLiveContentChange/hasLiveContent hybrid (and the
client chat-markdown util + test) is removed — the server is now authoritative.
Tests: flushAssistant unit (status shapes + parts parity), chat-markdown.util
unit (incl. legacy NULL-status + interrupted note + ru + normalizeLang locale
tags), controller export wiring + owner-gate, integration update/sweepStreaming.
Verified: server build + 318 ai-chat unit + 3 integration; client tsc + 157
ai-chat unit; and END-TO-END in a real browser — a chat turn persists mid-stream
and the Copy button exports the DB-sourced markdown (showing the in-progress
row), HTTP 200 after the locale fix.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
agent_coder
agent_coder
claude_code