Issue #193's tool-half has two open items. The shared, zod-agnostic tool-spec
registry (SHARED_TOOL_SPECS) for the identical tools is already merged
(f3fa15e7) and consumed by both layers, so that subset is done. The remaining
items are: (a) deriving the layer-3 hand-mirror `DocmostClientLike` from the
real client type, and (b) folding more tools into the registry. Both were
deferred as risky, and that deferral still holds (verified, see below) — so
this change ships the safest concrete increment instead of forcing the risk.
What this adds (behaviour-neutral, test-only + a doc comment):
- packages/mcp/test/unit/client-host-contract.test.mjs: pins the layer-3
contract from the ESM side, where the real DocmostClient is importable. It
asserts every method the in-app `DocmostClientLike` mirror declares exists as
a function on a real DocmostClient instance (constructor is side-effect-free).
A rename/removal in client.ts now fails this test instead of silently shipping
a runtime "x is not a function" into an agent tool call. Negative-case
verified (a bogus method name is detected).
- docmost-client.loader.ts: replaces the vague mirror comment with a pointer to
the guard test and a concrete, empirically-grounded staged plan for the full
type-derivation. Verified blockers kept it deferred: @docmost/mcp emits no
.d.ts (no `declaration`, no `types` export) and the server has no path mapping
for it, so there is no type to import today; and the real methods' inferred
CONCRETE return types conflict with the in-app adapter's loose
Record<string,unknown> + `as`-cast result handling (deriving the exact type
breaks the build / forces pervasive double-casts and full-surface test stubs).
Out of scope (noted in the issue): the PM<->Markdown converter unification.
Verified: server tsc clean; mcp tsc clean; mcp tests 369 pass (367 + 2 new);
ai-chat tools specs 51 pass. No behaviour change; committed mcp build untouched
(no mcp src changed).
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Additive test coverage across server, editor-ext, client and mcp.
#192 — AiChatService.stream integration (Section 3, against real Postgres):
- new apps/server/test/integration/ai-chat-stream.int-spec.ts drives the real
streamText through a seeded ai/test MockLanguageModelV3 and a real Node
ServerResponse, covering: onError persists an assistant error record
(status 'error' + partial answer + provider cause in metadata); external MCP
client closed exactly once on BOTH onFinish and onError; anti-tamper —
history is rebuilt from the DB transcript, not from body.messages.
#206 — red-team findings (most already fixed+tested in #212):
- mdrt-2 (UNFIXED, data loss): turndown.dataloss.test.ts documents that
pageBreak / transclusionReference / mention are silently dropped on Markdown
export (characterization + it.fails for the desired survive-export contract).
- persist-6 (UNFIXED, data loss): persistence-store.spec.ts adds an it.failing
documenting that a momentarily-empty live doc overwrites non-empty content
(left unfixed — a store-side empty-guard is a behaviour change).
#204 — test-strategy plan, highest-priority subset:
- Phase 1: mcp-clients.lease.spec.ts covers the external MCP client
lease/refcount/eviction lifecycle (leak / premature-close / double-close).
- Phase 2 data-integrity pure functions: editor-ext table-utils
(transpose/moveRow/convert round-trip) and math tokenizer false-positive
guard; client emoji-menu (+ it.fails for the unguarded localStorage
JSON.parse bug), sort-cells, normalizeTableColumnWidths; mcp htmlEmbed/
pageBreak markdown data-loss + footnote-diff; server export
getInternalLinkPageName extensionless-path bug — FIXED (small/clear) + tested.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
The agent-roles catalog source is no longer hardcoded in app code and no
longer supports a local filesystem directory. The provider now fetches only
from an http(s):// base URL read from AI_AGENT_ROLES_CATALOG_URL; an empty or
non-http value yields a 502 (catalog unavailable). The default URL is baked
into the Docker image at build time and set per branch in CI.
- provider: drop readLocal + node:fs/node:path; readRelative requires http(s)
and 502s otherwise; remote fetch/streaming-cap/SSRF guards unchanged.
- environment.service: keep AI_AGENT_ROLES_CATALOG_URL (default ''); comment
updated to reflect build-time injection, remote-only.
- Dockerfile: add ARG+ENV AI_AGENT_ROLES_CATALOG_URL in the installer stage.
- CI: develop.yml builds with the develop raw URL; release.yml (both build
steps) with the main raw URL.
- tests: replace local-fixture tests with remote-mock happy/malformed bundle
tests and a non-http => 502 case; path-traversal block uses an https source.
- docs: update .env.example, CHANGELOG (#222), agent-roles-catalog/README.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
ITEM 1: cover useImportAiRolesFromCatalogMutation onSuccess notifications.
Add import-from-catalog-message.test.tsx (twin of update-from-catalog-message)
asserting the always-shown summary (errors:[]) and the additional red
"Failed to import N role(s)" notification when result.errors is non-empty.
ITEM 2: pass redirect:'error' to the remote catalog fetch in fetchRemote so a
compromised-but-trusted upstream cannot 3xx the fetch into the internal network
(redirect-SSRF). Add provider specs asserting the option is passed and that a
redirect rejection maps to BadGatewayException.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
MUST-FIX
- isSourceUniqueViolation read the wrong error field: kysely-postgres-js
(postgres@3.4.8) puts the violated constraint on `constraint_name`, not
node-postgres' `.constraint`, so a concurrent same-slug+language import's
23505 was never recognized as a source-collision and surfaced a false
"name already exists" error. Now read `constraint_name` (with `.constraint`
as a fallback for other drivers). Fix the faked test fixture (it built the
error with the same wrong `.constraint` field, masking the bug): it now
uses `constraint_name`, so the test genuinely exercises the skip path and
FAILS against the unfixed code.
- Extract the catalog modal's role-state computation into a pure
`catalogRoleInstallState(role, workspaceRoles, language)` helper (mirrors
role-launch.ts) and cover it with vitest: import / installed / update /
same-slug-different-language.
SUGGESTIONS
- Restore IAiRoleUpdateFromCatalogResult as a discriminated union mirroring
the server; narrow the consumer via `"reason" in result` (the boolean
discriminant does not narrow under strictNullChecks:false).
- README: add a "How it's served" section documenting AI_AGENT_ROLES_CATALOG_URL
(remote http(s) base / local path / empty => in-repo folder).
- check.mjs: drop the redundant `const key = slug` alias.
- Cover the reason->message mapping in useUpdateAiRoleFromCatalogMutation
(4 branches) via renderHook with a mocked service.
- Cover importFromCatalog "bundle not in index" => BadGateway.
- Cover updateFromCatalog "slug in index but missing in bundle file" =>
not-in-catalog.
ARCHITECTURE
- Extract the shared catalog read prefix: a private `loadBundleById`
(fetchIndex -> meta -> fetchBundle -> versionMap) reused by getCatalogBundle
and importFromCatalog, and a `catalogRoleContentFields` mapper shared by the
import insert and update patch. The three orchestrations and their distinct
write paths stay separate.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Item 1 (concurrency-safe import): add a partial UNIQUE index on
(workspace_id, source->>'slug', source->>'language') WHERE source IS NOT NULL
AND deleted_at IS NULL, so two concurrent imports of the same bundle can no
longer create duplicate roles for one catalog slug+language. The in-memory
installedKeys snapshot cannot see a sibling request's writes; the index is the
backstop. importFromCatalog now catches the 23505 from THIS index (keyed off
the constraint name) and treats it as "already installed" -> skip, batch
continues. A 23505 from the name-uniqueness index keeps its existing friendly
per-role error behavior (distinguished by constraint name; an indeterminate
23505 falls back to that path, so no regression).
Item 2 (single source validator): strengthen parseSource into THE single form
validator for the source jsonb column -> returns a fully-valid RoleSource | null
(slug/language non-empty strings, version a number). The service's weaker
roleSource is removed and both layers share the RoleSource type (defined in the
db entity.types module both already import AiAgentRole from, so no import
cycle). normalizeRow / the read path now only ever yield a valid RoleSource or
null; a malformed stored source normalizes to null (tolerated by the service).
Tests: parseSource null for {} / {slug:123} / {slug:'a'} / empty-string keys /
string version, typed value for a full valid shape; service test that a
source-uniqueness 23505 is skipped (not errored) and the batch continues.
Verified the partial index rejects a duplicate source-not-null row but allows
two source-NULL rows, and the migration up/down run cleanly.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
- CHANGELOG: document the importable multilingual agent-roles catalog under
[Unreleased] (browse/import/update, 4 new endpoints, source column, the new
AI_AGENT_ROLES_CATALOG_URL env var) (#222).
- Fix importFromCatalog docstring: a role is skipped only on source.slug AND
source.language; another language of the same slug still imports.
- Provider: map a timeout/abort (or any failure) during the response-BODY read
to a logged BadGatewayException, so a slow/dripping source yields a 502, not a
generic 500. Existing too-large BadGateway cases are rethrown as-is.
- Service: inject a Nest Logger and log the root cause (with workspaceId/
bundleId/slug) on a non-23505 insert error during import.
- Modal: hoist the duplicated i18n base-subtag into a single baseLang const.
- Tests: AbortError body-read -> BadGateway; null-body text() fallback (under
and over cap); invalid-JSON and malformed-index BadGateway; non-23505 import
error -> generic message + logged root cause.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
- Rename catalog-source migration 20260626T120000 -> T150000 so it sorts
after develop's latest migration (T140000-page-temporary-notes); the old
timestamp predated ai-chat-message-status/share-aliases and tripped
Kysely's #ensureMigrationsInOrder, aborting server boot.
- Provider: inject a Nest Logger and log the real cause (incl. response
status) in the parseJson / readLocal / fetchRemote catch blocks, and
propagate a useful cause into the BadGatewayException message; add a
shortError helper (robust to jest's realm-shifted Error-likes).
- Provider: replace the manual Uint8Array assembly with
Buffer.concat(chunks).toString('utf8'); keep the streaming size cap.
- Controller spec: add admin-gate coverage for the 4 catalog routes
(catalog/catalogBundle/import/updateFromCatalog) - non-admin Forbidden +
service untouched, admin delegates with the right args.
- Service spec: add getCatalog/getCatalogBundle tests covering the
localized() three-tier fallback, the sorted language union, the
missing-bundle BadGateway, and the role-version default.
- Provider spec: add remote fetch-rejects and non-ok (503) error branches.
- Service: drop the dead Date.now() tail in freeName (now an explicit
unreachable throw) and extract a shared isUniqueViolation() predicate.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Admins can browse a curated catalog of agent roles, import roles/bundles
into a workspace, and update an imported role when the catalog ships a
newer version.
Catalog: a set of JSON files (index.json manifest + bundles/<id>/<lang>.json)
served from a local folder (dev) or a remote http(s) base URL via
AI_AGENT_ROLES_CATALOG_URL. Seeded with the existing 7 RU roles (editorial +
research bundles) plus EN translations.
Server:
- migration: nullable jsonb `source` column on ai_agent_roles
({ slug, language, version }; null => manually created)
- catalog provider: remote fetch with timeout + streaming size cap, or local
read; ^[a-z0-9-]+$ segment guard against path-traversal/SSRF
- admin endpoints: catalog, catalog/bundle, import, update-from-catalog
- import/update match by slug+language; update preserves `enabled`
Client:
- catalog modal with language selector and Import/Installed/Update states
- "Import from catalog" button + empty-state CTA in the roles settings panel
- en-US/ru-RU strings
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Remove the separate, un-toggleable `settings.ai.generative` workspace flag
(and its write-side alias `generativeAi`) along with the dead "Ask AI"
generative editor menu, and re-gate the AI page-title generation on the
general AI chat flag (`settings.ai.chat`) — the same toggle that enables
the chat agent and the chat stream endpoint.
Why: the `generative` flag had no UI toggle (its switch was already removed,
leaving orphaned i18n strings), so the title-generation button was
unreachable on self-hosted. The "Ask AI" menu was dead — its atom was never
rendered. Consolidating onto the AI chat flag makes the title button follow
the one AI switch users actually have.
Changes:
- server: title-gen endpoint gate generative -> chat (ai-chat.controller.ts);
remove generativeAi from update DTO and workspace service (update block,
delete line, cloud default now { ai: { chat: true } }); fix repo comment;
migrate generate-page-title spec assertions generative -> chat.
- client: title-gen gate -> settings.ai.chat (full-editor.tsx); remove the
dead Ask AI button + showAiMenu wiring from bubble-menu; remove AskAiGroup
usage/import and commented block from fixed-toolbar; delete ask-ai-group.tsx;
remove showAiMenuAtom; drop generative/generativeAi from workspace types.
- i18n: remove 3 orphaned generative-AI keys from all 12 locales.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
On opening the floating AI-chat window from the header on a document page,
auto-open the LAST chat bound to that document. Binding reuses the existing
ai_chats.page_id (no migration): the bound chat is the requesting user's
most-recent non-deleted chat created on that page, so a new chat on the page
becomes the bound one for free. Resolution happens only on a genuine
closed -> open transition; the provenance badge deep-link is untouched.
Server: AiChatRepo.findLatestByPage + POST /ai-chat/bound-chat (BoundChatDto),
both read-only and owner/workspace-scoped.
Client: getBoundChat service + useOpenAiChatForCurrentPage hook wired into the
app-header entry point (fail-soft to a fresh chat; draft/role cleared only on a
real switch).
Tests: repo scoping/ordering, controller wiring, and hook behavior.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
- Register the new AI-chat keys "Send now" and "Interrupt and send now" in
both en-US and ru-RU catalogs so the UI never renders mixed-language
tooltip/aria-label (i18n policy).
- Make INTERRUPT_NOTE module-private (drop the unused re-export), matching the
module's private DEFAULT_PROMPT/SAFETY_FRAMEWORK siblings.
- Reset interruptNextSendRef in the flush-on-abort branch when nothing is
actually sent, so a stuck one-shot interrupt flag cannot tag the next
unrelated send; flushNext now reports whether it sent.
- Add a CHANGELOG [Unreleased]/Added entry for #198.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
The per-turn model conversation was rebuilt via findRecent(chatId, ws, 50),
a sliding window that dropped the beginning of any chat longer than ~50 stored
rows. Switch streamChat to the existing findAllByChat, which loads the full
non-deleted transcript chronologically with a 5000-row memory-safety backstop
(keeps the newest rows + logs a warning on overflow) — a safety net, not a
conversational limit. Remove the now-unused findRecent method and update the
comments/log text that referenced it (findAllByChat now feeds both the Markdown
export and the model history).
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Add an AI button in the page byline that generates a note's title from the
live editor content (including unsaved edits) and applies it immediately.
Server: one-shot, non-streaming POST /ai-chat/generate-page-title mirroring
the chat generateTitle path — gated by settings.ai.generative, throttled via
AI_CHAT_THROTTLER, resolves the workspace chat model and returns { title }.
The endpoint never touches the page; the client applies the title through the
existing /pages/update route (which enforces edit permission).
Client: ai-chat-service.generatePageTitle, a useGeneratePageTitle hook that
converts the editor HTML to markdown, calls the endpoint, applies the title
via updateTitle + updatePageData, reflects it in the unfocused title editor,
and broadcasts the UpdateEvent (mirroring TitleEditor.saveTitle). A sparkles
button (GenerateTitleGroup) renders next to dictation, edit-mode + flag gated.
Tests: pure cleanGeneratedTitle helper + controller gate/delegation/error-map.
i18n: en-US + ru-RU strings.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Add a "send now" button to queued AI-chat messages: it interrupts the
running agent and immediately sends that message, while the agent's
partial output at interruption is kept in history and the next turn is
marked as a user interrupt.
Client:
- queue-helpers: pure `promoteToHead` to move a queued message to the head.
- chat-thread: `sendNow` (promote head + abort + flush-on-abort), one-shot
`flushOnAbortRef`/`interruptNextSendRef`, `interrupted` flag in the
request body, and the "send now" ActionIcon in the queued list.
Server:
- `interrupted` on AiChatStreamBody; pure `isInterruptResume` confirms the
client hint against persisted history (prev assistant turn aborted/
streaming) before honouring it.
- prompt: INTERRUPT_NOTE injected in the context section only on a
confirmed interrupt-resume turn so the model treats the partial answer
above as incomplete.
Tests: promoteToHead, chat-thread send-now (abort + resend + one-shot
interrupt flag + non-streaming immediate send), isInterruptResume, and
the prompt interrupt-note injection.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
onFinish always receives a totalUsage object, so the `?? {}` guard and
optional chaining were dead. Extract the field-level extraction into a
recordTurnUsage method (totalTokens, else input+output) and unit-test that
recordShareTokens receives the summed value when totalTokens is absent and the
authoritative total when present.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
The anonymous public-share assistant only capped the COUNT of requests
(100/hour/workspace), not their cost. One accepted turn runs the agent loop
up to stepCountIs(5), re-sending the whole client-held transcript as input on
every step, while maxOutputTokens caps only the output; the request window is
hourly with no daily ceiling, so a steady stream at the cap sustains ~24x its
count per day. Counting requests therefore does not bound the owner's LLM bill
(red-team finding #5).
Add a second cost contour: a cluster-wide, sliding-window per-workspace TOKEN
budget over a rolling day. It is checked read-only BEFORE a turn streams (429,
no request slot consumed, nothing spent) and the turn's real usage
(totalUsage: input re-sent per step + output, summed across all steps) is
recorded once it finishes via streamText onFinish. Fails closed on the check
(deny when Redis can't prove we're under budget); best-effort on the record.
Env-overridable via SHARE_AI_WORKSPACE_TOKEN_BUDGET_PER_DAY (default 1M/day).
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
In-app AI-chat tools used bare zod schemas, so when the model dropped a
required arg (typically pageId) in a parallel/batch tool call, the AI SDK
forwarded zod's raw "expected string, received undefined" text to the model
— not actionable. Add a centralized modelFriendlyInput(shape) wrapper that
keeps the exact JSON Schema contract (required/description/constraints via
z.toJSONSchema draft-7) but replaces the raw zod text with a message naming
each missing/invalid parameter and reminding the model not to drop ids like
pageId in parallel batches. No value is guessed/backfilled (cf. #159).
Applied to every in-app tool: the sharedTool() builder and all inline
inputSchema in ai-chat-tools.service.ts, plus public-share-chat-tools.service.ts.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
The floating chat window's header badge flipped meaning — a live per-turn token
counter while streaming, the persisted context size at rest — so it "reset to 1"
on each prompt and conflated two different numbers. Replace it with a stable
"current / max" context badge (e.g. `572 / 200k`). The live "Thinking · N tokens"
inside the chat body stays; only the duplicate live counter is removed from the
header.
Max comes from a new admin setting "Context window (tokens)". The server resolves
it and attaches `maxContextTokens` to the completed assistant turn's metadata
(next to contextTokens), so the badge needs no client-side model resolution and
this survives public shares / per-role models.
Server:
- ai.types: chatContextWindow on AiProviderSettings + PROVIDER_SETTINGS_KEYS +
ResolvedAiConfig + MaskedAiSettings.
- workspace.repo: chatContextWindow in AI_PROVIDER_SETTINGS_ALLOWED (parity).
- update-ai-settings.dto: @IsInt @Min(0) chatContextWindow.
- ai-settings.service: coerce the ::text-stored value to a positive int in
resolve()/getMasked().
- ai-chat.service: flushAssistant writes metadata.maxContextTokens (>0); the
completed turn passes resolved.chatContextWindow.
Client:
- ai-chat.types: maxContextTokens on the message-row metadata.
- ai-chat-window: read maxContextTokens; render "current [/ max]"; drop the
liveTurnTokens state/branch and the onLiveTurnTokens prop; new tooltip.
- chat-thread: remove the live-turn-token throttle effect and plumbing.
- count-stream-tokens: drop the now-dead liveTurnTokens()/types; keep
estimateTokens.
- settings: chatContextWindow on IAiSettings(+Update) + a NumberInput in the AI
provider settings form.
i18n: add the badge/settings keys (en, ru); remove the two now-unused keys.
Tests: flushAssistant maxContextTokens, DTO validation, trim token tests.
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>
15-point review of the persistent-history PR. Architecture decisions: crash
recovery = recency threshold; tool-label duplication = leave as-is.
Must-fix:
1. Boot-sweep bounded by recency. sweepStreaming now also requires
`updatedAt < now() - SWEEP_STREAMING_STALE_MS` (10 min), so a fresh replica's
startup sweep can't abort a turn another replica is actively streaming
(multi-instance deploy). Int-spec: a FRESH 'streaming' row is NOT swept, a
STALE one IS.
2. Restore export during the FIRST streaming turn of a new chat (#174). The
server chatId is now adopted EARLY (in-place, on the start-chunk metadata) via
a new `onServerChatId` callback wired through use-chat-session → chat-thread,
so `activeChatId` is set at turn start and the Copy button is live mid-first-
turn (canExport = !!activeChatId). Hook tests for early/in-place/no-op adopt.
3. Cover finalizeAssistant's fallback-insert branch: extracted pure
`planFinalizeAssistant(assistantId)` (update when id present, insert when the
upfront insert failed) + a dispatch harness test for both arms.
Tests: onModuleInit lifecycle spec (sweep called; throw → resolves + warns);
int-spec updatedAt assertion → toBeGreaterThan.
Cleanups: cap findAllByChat at 5000 rows; upfront-insert-failure log carries
chatId+workspaceId; removed the now-dead buildPartialAssistantRecord (only the
spec consumed it; shapes still pinned by the flushAssistant suite); controller
passes `lang: dto.lang` (normalizeLang handles undefined); dropped a no-op
`?? undefined` in errorOf; documented the content-column semantics change
(concatenated step text, UI renders from metadata.parts); CHANGELOG [Unreleased]
entry (#183, #174); reworded the stale LABELS parity comment.
Verified: server build + 323 ai-chat unit + 5 integration; client tsc + 160
ai-chat unit; prettier clean.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
8-point multi-aspect review of the batch PR; security/regressions were clean.
1. Lease leak: the #180 reorder moved `toolsFor` (which leases external MCP
clients, refCount+1) ahead of buildSystemPrompt + forUser, but the only
release (closeExternalClients) was bound to the streamText callbacks. A throw
in between leaked the lease (refCount stuck, undici sockets held until
restart). Define closeExternalClients right after the lease and wrap
buildSystemPrompt+forUser in try/catch that closes-then-rethrows.
2. Cover the patch_node/delete_node dup-id refusal (#159#6): extract the guard
into a pure `assertUnambiguousMatch` (node-ops) and unit-test 0/1/>1.
3. Regress the body-before-title order (#159#10): mock-HTTP test (collab fails
fast against a server with no WS upgrade) asserts /pages/update (title) is
NEVER posted when the body write fails — for updatePage AND updatePageJson.
4. CHANGELOG [Unreleased]: #180, #168 (Added); #163 (Fixed).
5. Add the missing en-US i18n keys (Back to references / {{label}}).
6. Drop the duplicate content/empty/blank cases in ai-chat.prompt.spec.ts (they
repeat the buildMcpToolingBlock unit tests); keep only sandwich placement +
both-safety-copies.
7. CI Postgres pg16 -> pg18 (match docker-compose).
8. jsonb decode seam: shared `parseJsonbValue(value, guard)` in database/utils.ts
holds the legacy double-encoding self-heal in one place; parseToolAllowlist /
parseModelConfig keep only a type-guard.
Verified: server build + 124 unit + 15 integration; mcp 311; prettier clean.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
The client sends the "current page" as { id, title } in the request body and the
server echoed BOTH verbatim into the system prompt context and the
getCurrentPage tool. id and title are independently attacker/desync-controllable
(two tabs, stale navigation), so openPage.id could point at page B while
openPage.title said "Page A" — the model then reported "updated Page A" while it
actually edited page B (CASL still allowed it; the user has access). Red-team
finding #4.
Resolve the open page ONCE against the DB via a new `resolveOpenPageContext`:
workspace-scoped lookup + access check, returning the AUTHORITATIVE { id, title }
(title from the DB row, never the client) or null (fail-closed) for a missing /
foreign / inaccessible page. That validated value now feeds the system prompt,
the getCurrentPage tool, AND the new-chat history origin (which previously did
this validation inline, for the id only — now shared, and the title is fixed
too).
Tests: resolveOpenPageContext covers no-id, not-found, foreign-workspace,
Forbidden, non-Forbidden-fault (fail-closed), the DB-title-wins-over-client case,
and null-title coercion.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Admins can now give each EXTERNAL MCP server a free-text instruction ("how/
when to use this server's tools") that the agent receives in its SYSTEM
PROMPT next to the tool descriptions — porting the built-in SERVER_INSTRUCTIONS
idea to admin-configured servers. Trusted, admin-authored text (like a system
prompt); NON-secret, so unlike headersEnc it IS returned in views/forms.
- Migration: nullable `instructions text` on ai_mcp_servers (old rows = null =
no guidance). Table type + repo insert/update (blank/whitespace -> null via
blankToNull). DTO `@MaxLength(4000)`. Service threads it through
McpServerView/toView.
- mcp-clients: `McpServerInstruction { serverName, toolPrefix, instructions }`
threaded through the toolset/cache/lease. Guidance is built ONLY for a server
that actually connected AND contributed >=1 callable tool (the allowlist may
filter all of them out) AND has non-blank text — so a guide never appears for
tools the agent cannot call. Cached with the toolset, so an edit is picked up
next turn via the existing CRUD cache invalidation.
- System prompt: `buildMcpToolingBlock` renders an <mcp_tooling> block INSIDE
the safety sandwich (after context, before the trailing SAFETY_FRAMEWORK) so
it informs tool choice but cannot override the rules; each section is headed
by the server's `prefix_*` namespace. Empty/blank -> block omitted. The
caller (ai-chat.service) now builds the external toolset BEFORE the prompt and
passes external.instructions; client-handle lifecycle (close-once) unchanged.
- Client: instructions field in types + a Textarea (autosize, maxLength 4000)
in the MCP-server form with a namespace-prefix hint; i18n (en/ru).
Tests across every layer (prompt block placement + both SAFETY copies; view
blank->null; buildEntry includes guidance only for connected+>=1-tool+non-blank;
DTO MaxLength; repo + integration round-trip; service wiring). Delegated impl
reviewed (APPROVE); applied the import-type follow-up.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
PR #172 fixed the jsonb double-encoding for `tool_allowlist` but the same
class of bug, and the same re-derived workaround, remained elsewhere.
1. model_config (agent roles): jsonbObject still used the buggy `::jsonb`
bind, so `ai_agent_roles.model_config` round-tripped as a jsonb STRING
SCALAR. The read-path `typeof === 'object'` check then failed and the
model override was SILENTLY dropped (role fell back to the default model).
Fixed to `::text::jsonb` and added `parseModelConfig` + `normalizeRow` so
every read self-heals already-corrupted rows (no migration).
2. Centralized the write workaround as `jsonbBind()` in database/utils.ts —
one implementation with one explanation of the quirk — replacing the
per-repo `jsonbArray` (mcp) and `jsonbObject` (roles).
3. Integration coverage (the fix is a DB round-trip a unit test cannot see;
the read-side parser MASKS a write regression): new
ai-mcp-server-repo.int-spec asserts `jsonb_typeof(tool_allowlist)='array'`
after insert + heals a seeded string-scalar row; ai-agent-roles-repo
int-spec gains the same for `model_config` (`'object'` + heal).
4. Updated the stale `ai-mcp-servers.types.ts` comment (the driver returns a
JSON string for legacy rows; the repo normalizes every read).
5. Fail-open logging: a corrupt tool_allowlist degrades to "no restriction"
(agent gets ALL tools) — normalizeRow now warns (server id only, never
contents) so the silent widening leaves a trace.
6. Simplified parseToolAllowlist (normalize the string once, then a single
array-of-strings check) — identical behaviour, all 12 cases still pass.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Review caught a real race: onStepFinish fires `updateStreaming()` fire-and-
forget (not awaited), so the FINAL step's streaming UPDATE and the terminal
`finalizeAssistant` UPDATE run as two concurrent statements on different pool
connections — commit order is not guaranteed. If the late streaming update
lands AFTER finalize, the completed row is clobbered back to status='streaming'
with no usage/finishReason, and the next startup sweep then mis-marks the
finished turn 'aborted'. Green unit/integration tests don't reproduce a
cross-connection race.
Fix: scope the per-step update with `onlyIfStreaming` → SQL `WHERE
status='streaming'`. Once finalize has set a terminal status the late update
matches zero rows and no-ops, regardless of commit order; finalize runs
unguarded so it always wins. A cheap `if (finalized) return` short-circuit
avoids most wasted queries, but the SQL guard is the authoritative fix (the
flag can be set after a query is already in flight).
Integration test: finalize to 'completed', then a late onlyIfStreaming update
is a no-op — status/content/usage preserved.
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>
External MCP tools (web search, crawl) had no per-call timeout: a hung
tool call was only broken by the 15-min transport silence timeout shared
with the chat provider, and a server that kept the socket warm but never
returned could spin until the user cancelled.
Add two independent, composing bounds for external MCP traffic (the chat
provider path is unchanged):
- Silence 5 min: buildPinnedDispatcher now overrides headersTimeout/
bodyTimeout with mcpStreamTimeoutMs() (AI_MCP_STREAM_TIMEOUT_MS,
default 300000) on the external-MCP dispatcher only, so a byte-silent
upstream is severed in ~5 min instead of 15.
- Total per-call 15 min: wrapToolWithCallTimeout wraps each external
tool's execute with a fresh AbortController + timer composed with the
turn signal via AbortSignal.any (AI_MCP_CALL_TIMEOUT_MS, default
900000). It RACES the call against the abort signal because
@ai-sdk/mcp does not settle its in-flight promise on abort, so a
warm-but-stuck call would otherwise hang forever.
On timeout the call surfaces as a tool-error and the agent loop recovers.
Add tests (incl. a never-settling real-client-style stub) and document
both env vars in .env.example.
The /api/ai-chat/stream and public-share streaming paths piped streamText
output to the client socket via pipeUIMessageStreamToResponse, whose only
reader is that socket. On a client disconnect (pervasive Safari/proxy
ECONNRESET), backpressure stalled the stream: the controller aborted the
turn but nothing drained it, so streamText's onFinish/onError/onAbort never
fired. Cleanup (close leased MCP clients, persist partial) never ran and the
whole per-turn object graph (history, per-request toolset closures, captured
steps, SDK buffers) stayed rooted — accumulating across turns until the
default ~2GB heap saturated and the process crashed with
"Ineffective mark-compacts near heap limit - JavaScript heap out of memory".
Add the AI SDK v6 documented remedy: fire-and-forget
`result.consumeStream({ onError })` right after streamText(), which removes
backpressure and drains the stream independently of the client socket so the
terminal callbacks always fire and the turn's memory is released even when the
client has gone away. Applied to both the authenticated and public-share
stream services.
Also add `--heapsnapshot-near-heap-limit=2` to the prod start script so any
residual leak dumps a heap snapshot near OOM for diagnosis (no effect on
normal operation). Heap size stays ops-tunable via NODE_OPTIONS.
- apps/server/src/core/ai-chat/ai-chat.service.ts
- apps/server/src/core/ai-chat/public-share-chat.service.ts
- apps/server/package.json
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Long research turns failed mid-task with "Lost connection to the AI provider".
Node's global fetch (undici) defaults BOTH headersTimeout and bodyTimeout to
300_000ms, and the chat provider + the external-MCP dispatcher both ran on it
with no override, so:
- the z.ai chat stream dropped when a late step's huge accumulated context
pushed the model's time-to-first-token past 5 min (the model reasons
server-side with NO streamed reasoning, so the connection is silent until the
first answer token — reproduced: even a trivial glm-5.2 query has a ~4-8s
first-chunk gap; a long run reaches 400k+-token steps), or a reasoning model
paused >5 min between chunks (bodyTimeout);
- the crawl4ai SSE transport, held open across the whole turn, dropped when it
idled >5 min between tool calls.
Fix: a dedicated undici dispatcher whose stream timeouts are raised to a
generous-but-FINITE silence timeout (default 15 min, AI_STREAM_TIMEOUT_MS) on
each path. NOT disabled (0): that would let a genuinely hung provider — with the
client still connected — hang forever, since the turn's abortSignal only fires on
client disconnect. The timeout bounds SILENCE (time-to-first-byte and the gap
BETWEEN chunks), NOT total turn duration, so an arbitrarily long turn that keeps
streaming is never cut; only a stream quiet for >15 min is treated as a hang.
- ai-streaming-fetch.ts: createStreamingFetch() + streamTimeoutMs() /
streamingDispatcherOptions() (the shared, configurable timeout).
- ai.service: the chat provider fetch is createStreamingFetch(), wrapped by the
existing passive ECONNRESET telemetry (createDiagnosticFetch gained an
optional baseFetch) so the telemetry observes the SAME transport.
- mcp-clients: the SSRF-pinned Agent uses streamingDispatcherOptions().
Investigation: reproduced the transport mechanism against the real z.ai endpoint
(a 1ms headersTimeout throws UND_ERR_HEADERS_TIMEOUT — the exact drop) and ran
the actual research agent to a ~428k-token context. Verified the fixed path
streams cleanly live (glm-5.2 turns finish; telemetry confirms the streaming
fetch is in use).
Tests: ai-streaming-fetch.spec (default 15m + env override + invalid fallback +
both-timeouts + streams a delayed response); ai-http-diagnostics + ai/mcp specs
green. server tsc clean.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Investigate the Safari-only "Lost connection to the AI provider" mid-stream
disconnect (Chrome unaffected). Pure instrumentation, no behavior change:
the 15s heartbeat interval and all stream callbacks are unchanged.
- sse-resilience.ts: startSseHeartbeat() gains an optional onBeat hook fired
after each successfully written ping (beat counter).
- ai-chat.service.ts: track stream start, first-chunk latency, model-silent
gap and heartbeat count; log them on finish/error/abort to classify the
drop (idle-gap vs hard wall-clock cap vs slow first chunk).
- ai-chat.controller.ts: append elapsed-since-request to the disconnect warn.
All blocks tagged "DIAGNOSTIC ... temporary" for easy removal once the Safari
failure mode is identified.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Tokens were only counted post-hoc (onFinish) and the header badge updated only on
chat open/switch; reasoning wasn't requested or shown. Now a counter ticks LIVE
during generation and surfaces reasoning ("thinking") tokens separately, like
Claude Code's `Thinking… · N tokens`.
Architecture (AI SDK v6): no provider gives exact per-token usage mid-stream, so
the live number is a cheap client estimate (chars/≈4) reconciled to AUTHORITATIVE
provider usage at step boundaries and turn end. The useChat per-delta re-render is
the existing realtime engine.
- server: `chatStreamMetadata` now also forwards usage on `finish-step` + `finish`;
`sendReasoning: true`; persisted `metadata.usage` carries `reasoningTokens`
(normalized from `outputTokenDetails` or the deprecated field).
- client: pure `count-stream-tokens` (estimateTokens / liveTurnTokens, prefers
authoritative usage else estimate); `Thinking… · N tokens` in the typing
indicator; collapsible "Thinking" reasoning block; throttled (~8 Hz) live
turn-token header badge; `reasoningTokens` in types + Markdown export.
Review fixes folded in:
- v6 `finish-step.usage` is PER-STEP, not cumulative — the server now ACCUMULATES
a running sum (new pure `accumulateStepUsage`) and sends the cumulative, which
converges to `finish.totalUsage`, so the live counter never jumps DOWN on a
multi-step agent turn.
- reasoning double-count: the authoritative turn-total is attributed to a block
ONLY for a single-reasoning-part (one-step) turn; multi-step blocks each show
their own estimate (the authoritative total stays in the header).
- no "0" badge flash at turn start (require live > 0, else show context size).
- comment refreshed (finish-step trigger).
Tests: server `accumulateStepUsage` + updated `chatStreamMetadata` (34 in the
suite); client pure-fn tests. Both tsc clean; 162 client ai-chat + the ai-chat
server suite pass.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Agent role cards always auto-sent a hardcoded "Take a look at the current
document" on pick. Make it configurable per role:
- autoStart (bool, default true): whether picking the role auto-sends a message.
- launchMessage (nullable text): the text sent on auto-start; empty -> the
built-in default. autoStart=false -> bind the role and send nothing (the user
types the first message, which still carries the roleId).
Existing roles default to autoStart=true / launchMessage=null => identical old
behavior.
Full-stack:
- migration 20260624T120000 adds `auto_start boolean NOT NULL DEFAULT true` +
`launch_message text` (additive; down drops both); db.d.ts updated by hand.
- DTO: autoStart (@IsBoolean) + launchMessage (trim @Transform, @MaxLength 2000).
- repo/service: thread + normalize (undefined=unchanged, ""=>null, autoStart??true).
Both fields exposed in the picker-view for ordinary members (they decide
whether/what to auto-send); instructions/modelConfig stay ADMIN-ONLY.
- client: IAiRole types, role form (Switch + Textarea, re-hydrated on edit),
handleRolePick branches on autoStart; i18n en-US + ru-RU.
Review follow-ups folded in: reset the `rolePickedNoSend` flag when the thread
returns to an empty role-less state (the "New chat after autoStart=false pick"
stuck-UI bug — render-phase one-shot reset); made create/update launchMessage
normalization symmetric (raw value, server normalizes ""→null).
Server: 68 role tests pass, tsc clean. Client: tsc clean, role tests pass.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
The custom undici RetryAgent + aiFetch transport added for issue #140
did not actually heal mid-stream provider drops: undici's retry path is
a Range-based download-resume that SSE/chat-completions endpoints cannot
satisfy, so a reset after the first byte only swapped ECONNRESET for a
"server does not support the range header" error. Its only real effect
was reconnecting a poisoned keep-alive socket before the first byte, and
PR #141 on top of it turned the 60s headers timeout into deterministic
~61s failures (plus CONTENT_LENGTH_MISMATCH from retrying a POST body
after a timeout abort). The root cause is the z.ai coding endpoint, not
our transport.
Remove the whole layer and return all AI provider calls to Node's
default global fetch.
- delete integrations/ai/ai-http.ts and its spec
- ai.service.ts: drop the aiFetch import, the AI_BYPASS_RESILIENT_FETCH
diagnostic toggle, and fetch:aiFetch from every chat/embedding/STT
factory; raw STT call back to global fetch
- ai-chat.controller.ts: drop the stream-timing START log + startedAt
- ai-chat.service.ts: drop the first-chunk/FINISHED/ERROR timing logs
- .env.example: drop AI_BYPASS_RESILIENT_FETCH
Reverts: 1af5d34a, 7c308728, b7abb7ea, 35fc58ea, d6cd2754, 6efb8656.
Preserved (not part of the rollback): client-disconnect abort, title
generation in onFinish, partial-answer persistence, Safari SSE heartbeat.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
A new-chat turn fired the chat stream (streamText) and title generation
(generateText) concurrently to the same z.ai coding endpoint. That plan
stalls one of two concurrent requests, so the chat stream black-holed for
~300s (undici headers timeout) and the turn hung forever in every browser;
the AI SDK then retried 3x. Server logs showed two concurrent POSTs to
/chat/completions per turn — one 200 in ~8s, the other "fetch failed after
301209ms". Bypassing the custom undici transport did not help, confirming
the cause is the concurrency, not the transport.
Move generateTitle from before the response pipe into onFinish, so it runs
solo AFTER the stream's provider call completes. A first turn that errors or
aborts no longer auto-titles (fallback "Untitled chat" already handles a
null title) — acceptable, and it removes the request that was stalling.
Addresses the 2nd PR #138 review (test debt + the Variant-B architecture ask).
The new→persisted chat id lifecycle (mount key, both adoption paths, the
history-load latch, the render-phase reconciler, onTurnFinished) is moved out of
the 768-line window into a new useChatSession hook driven by a pure
threadSessionReducer (reconcile/adopt), so adopt-vs-switch is one explicit
dispatch point and the scattering the review flagged is gone (window: 768→~620).
Tests (the blockers):
- use-chat-session.test.tsx — hook-level locks incl. the #137 regression
(adopts the authoritative streamed id 'A', NOT chats.items[0]='B' — fails on
the old heuristic), the error-path fallback (arm/adopt/ambiguous/add+delete),
the disarm-on-reconcile lock (a fallback armed then switched away must not be
adopted by a late refetch), in-place-adopt-keeps-key vs external-switch-remount,
and the waitingForHistory latch.
- extractServerChatId (reading message.metadata.chatId) and newlyAddedChatIds
extracted as pure helpers with unit tests; threadSessionReducer tested.
Cleanups: single canonical #137 explanation in adopt-chat-id.ts (other sites
reference it); fallback effect computes the set diff once; invalidate callbacks
memoized; redundant invariant tests folded.
Behavior preserved — re-verified live (z.ai glm-5.2): new-chat adopt + 2nd turn
in the same row, no mid-conversation remount, two-tab race leak-free, switch to
an existing chat reseeds full history, reload restores history.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
The streaming chat turn hangs in all browsers while the non-streaming test
endpoint works — both use the same model/transport (createOpenAI + aiFetch),
so the suspect is the streaming path / custom undici RetryAgent transport.
- ai-http.ts: wrap aiFetch with per-request timing logs (start, ms-to-headers
on success, elapsed ms + cause on failure). Chat at info, embeddings at
debug. Only host+path logged.
- ai-chat.controller.ts / ai-chat.service.ts: log turn START, first-chunk
latency, FINISHED duration, and elapsed ms on disconnect/error/abort.
- ai.service.ts: AI_BYPASS_RESILIENT_FETCH=true makes the CHAT model omit
fetch:aiFetch and use the default global fetch — isolates transport vs
request-shape. Chat-only; embeddings/STT untouched; reversible via env.
- .env.example: document the flag.
No timeout/retry change. tsc clean; ai-chat + ai suites pass (292).
Addresses the PR #138 review.
Blocker 1 — duplicate chat row: a brand-new chat whose first turn errors BEFORE
the SSE 'start' chunk never receives the authoritative chatId, so metadata
adoption can't run; a retry then sent chatId:null and the server inserted a
SECOND chat row, orphaning the first turn. Keep metadata adoption as the primary
path (resolveAdoptedChatId) and add a bounded, unambiguous fallback: on a
new-chat finish with no server id, snapshot the known chat ids and, once the
list refetch lands, adopt the SINGLE newly-appeared id (pickNewlyCreatedChatId).
Zero or >1 new ids (e.g. two tabs racing) → no adoption — no items[0] guessing,
so #137 stays fixed. The wait-for-refetch guard compares set membership (robust
to a concurrent delete), and the diff dedupes so a repeated id from a paginated
list never reads as ambiguous.
Blocker 2 — tests: new adopt-chat-id.test.ts covers both pure helpers (adopt
decision + newly-created-id diff incl. dedupe/reorder); the server
messageMetadata callback is extracted to chatStreamStartMetadata and unit-tested
(start -> {chatId}, otherwise undefined).
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Safari/WebKit dropped the AI chat answer stream mid-turn ("Load failed",
shown as "Lost connection to the server") while Chrome/Firefox were fine.
Two Safari-specific causes: (1) during model think/tool gaps the UI-message
SSE stream emits no bytes and WebKit aborts a non-progressing fetch far more
aggressively than Chrome; (2) the AI SDK sets a hop-by-hop `Connection:
keep-alive` header which is illegal on HTTP/2 — Chrome/Firefox ignore it,
Safari rejects the whole response. Earlier commits only improved the error
text, never the drop itself.
Add apps/server/src/core/ai-chat/sse-resilience.ts with two helpers wired into
both stream paths (authenticated + public share):
- startSseHeartbeat: writes a `: ping` SSE comment every 15s (ignored by the
client's EventSourceParserStream) so bytes keep flowing; unref'd timer,
guarded writes, auto-clear on finish/close.
- stripStreamingHopByHopHeaders: wraps writeHead once to drop Connection/
Keep-Alive before the head is sent, so they can never leak into an HTTP/2
response.
Add sse-resilience.spec.ts (7 tests). tsc + eslint clean.
A brand-new chat (activeChatId === null) had no way to learn the id of the row
the server created: the SSE stream never returned it, so the client adopted the
NEWEST chat in the per-user list (chats.items[0]). With two tabs open, a second
tab creating a chat at ~the same time made its row the newest, so the first tab
adopted the wrong id — its later turns persisted into the other chat and the
agent rebuilt history from it (commands leaked between chats), while the live UI
still showed the original conversation. (#137)
The server now attaches the authoritative chatId to the streamed assistant
message via the AI SDK messageMetadata on the 'start' part, so it reaches the
client on the first chunk. The client reads message.metadata.chatId in useChat's
onFinish and adopts that id in place (no remount, so the live turn and the
thread's chatIdRef follow the real id and the next turn targets the right chat).
The chats.items[0] guess and the adoptNewChat ref are removed.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
A provider error (e.g. read ECONNRESET) routed the turn through the
streamText onError callback, which persisted an EMPTY assistant record
(buildErrorAssistantRecord -> text:'', parts:[]). The answer text already
streamed to and shown by the client was therefore lost from the persisted
row, the chat export, and reopened history — leaving only the error line.
The AI SDK v6 onError callback receives only { error } (no steps/text),
and the visible final answer streams in the last, not-yet-finished step,
so it is absent from every finished step.text. Accumulate it ourselves:
onChunk folds each 'text-delta' into inProgressText; onStepFinish moves a
finished step into capturedSteps and resets inProgressText. onError and
onAbort now persist the partial answer (finished steps' text + tool parts
via assistantParts, then the in-progress text appended last) through a new
shared pure helper buildPartialAssistantRecord, recording the cause in
metadata.error on the error path. Replaces buildErrorAssistantRecord; its
empty-turn shape is preserved when nothing streamed.
Complementary to the resilient-fetch reconnect: that reduces how often a
turn dies; this preserves what was produced when it dies anyway.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Each chat row in the AI-chat history now shows a dimmed second line with
how long ago the chat was created and the document it was created in
("N ago / <document>", or "No document" when started outside a page).
Server:
- New migration: nullable ai_chats.page_id (FK pages.id, ON DELETE SET NULL).
- Capture the origin page at chat creation from the client-supplied openPage,
but validate it first: it must be a real page in the same workspace that the
user may read (PageAccessService.validateCanView), else null. This keeps the
"openPage.id is attacker-controllable but harmless" invariant - preventing a
cross-workspace/cross-space page-title leak and a post-hijack FK crash.
- findByCreator left-joins pages (scoped by workspace, defense-in-depth) and
returns pageTitle.
Client:
- IAiChat gains pageId/pageTitle; ConversationList renders a ChatMetaLine
(useTimeAgo + origin document) as a dimmed second line.
- Add i18n key "No document" (en-US, ru-RU).
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
claude code agent 227
vvzvlad