Address review on #198 (interrupt agent / send now):
- sendNow now branches on the live useChat status (statusRef) instead of
the closure-captured isStreaming. A turn can finish between render and
click, where stop() is a no-op; arming flushOnAbortRef/interruptNextSendRef
against that no-op would strand the flags and leak into a later, unrelated
Stop (auto-sending a queued message the user did not ask to send).
- Correct the stale queue comment: onFinish DOES fire on Stop/disconnect/
error (its abort/disconnect/error branches leave the queue intact), and a
deliberate "Send now" flushes the promoted head via the abort branch.
i18n keys for "Send now"/"Interrupt and send now" were already registered in
en-US and ru-RU on this branch.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Add a "Send now" button to each queued AI-chat message that interrupts the
running agent and immediately resends that message, preserving the agent's
partial output and telling it on the next turn that it was interrupted.
Client:
- queue-helpers: new pure promoteToHead() (+ tests)
- chat-thread: sendNow() promotes the chosen message to the queue head and
aborts; onFinish flushes the promoted head on the intentional abort; a
one-shot `interrupted` flag rides that resend request; stale flags are
cleared at every turn start to defuse a clean-finish/click race leak
- "Send now" action icon + en-US/ru-RU translations
Server:
- AiChatStreamBody.interrupted flag; shouldInjectInterruptNote() gates on the
flag AND a genuinely-unfinished previous turn (aborted/streaming)
- buildSystemPrompt() appends INTERRUPT_NOTE inside the safety sandwich so the
model treats its previous, partial reply as incomplete
- prompt + service unit tests
Partial-output persistence already existed (onAbort -> 'aborted', findRecent
replays regardless of status); that path is unchanged.
Co-Authored-By: Claude Opus 4.8 <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>
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>
The "Copy chat" button was hidden during a brand-new chat's very first
turn: both the `canExport` gate and the `handleCopy` early-return required
an `activeChatId` AND persisted `messageRows`, neither of which exists yet
while the first turn is streaming or after it was interrupted before any
row was persisted.
Decouple the export gate from persisted state. ChatThread now reports a
reactive `onLiveContentChange(messages.length > 0)` signal (the live
snapshot lives in a non-reactive ref, so a separate reactive flag is
needed to re-render the button); the parent keeps it in `hasLiveContent`
and exports whenever there is anything on screen OR persisted. `handleCopy`
passes a `"unsaved"` placeholder chat id when none exists yet, and the
live-first builder serializes the on-screen thread WYSIWYG.
Builds on #160 (WYSIWYG export); covers the first-turn edge case that was
explicitly out of scope there.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
"Copy chat" built the Markdown from persisted rows plus a live tail that was
only included while isStreaming. When a turn was interrupted (dropped stream /
"Lost connection" banner) isStreaming flipped false, the live tail was dropped,
and the partial assistant reply visible on screen — whose row often never
persisted — vanished from the export, leaving only the user messages.
- buildChatMarkdown is now live-first: the on-screen `live` messages ARE the
document. Each is matched to a persisted row by id to enrich it with token
usage / error / timestamp; authoritative usage/error already on the live
message win over the row. When `live` is empty it falls back to the persisted
rows (old format preserved). Only the tail assistant is flagged "still
generating", and only when it is genuinely the streaming tail — so the
status==="submitted" window (tail is the user message) never mislabels the
previous, completed answer.
- The on-screen banner (classified error / dropped connection / manual stop) is
flattened to a string in ChatThread, mirrored into liveStateRef alongside the
messages/isStreaming snapshot, and appended at the end of the export.
- handleCopy maps the live messages and passes live/rows/isStreaming/banner.
Tests: chat-markdown rewritten for the live/enrichment/fallback/banner paths and
the submitted-window regression (26); full ai-chat suite green (186). tsc clean.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Review of #156 (Request changes) flagged the new CLIENT logic as untested. Extract
the decision logic from chat-thread.tsx into pure, unit-testable helpers and cover
both branches the reviewer called out:
- `roleLaunchMessage(role, default)` — the three-way handleRolePick behavior:
autoStart=false -> null (send nothing); autoStart=true + custom -> trimmed
message; autoStart=true + empty/null/whitespace -> default fallback.
- `shouldResetRolePicked(chatId, roleId, flag)` — the #149 render-phase reset; the
regression test asserts the stuck-flag case (New chat after an autoStart=false
pick -> cards return) that the pre-fix code never handled, and that a still-bound
role keeps the cards hidden.
chat-thread.tsx now calls these helpers (behavior unchanged). 9 new pure tests.
Also folded the review's cosmetic suggestion: `x ? x : null` -> `x || null` in
ai-agent-roles.repo.ts (identical for string|null|undefined).
Client tsc clean; role-launch + role-cards green; repo spec green.
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>
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>
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>
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 turn that ends without a clean finish now shows a neutral marker, so an
interrupted answer is visible instead of trailing off silently. Errors keep
their existing red banner; this covers the aborted case.
- chat-stopped-notice.tsx: new neutral (gray) notice component
- chat-thread.tsx: live marker driven by useChat onFinish flags — distinguishes
a manual Stop (isAbort) from a dropped connection (isDisconnect); cleared when
the next turn streams; flushNext still runs only on a clean finish
- message-item.tsx: per-message marker in reopened history for finishReason
'aborted' with no error (combined wording, since the server can't tell a
manual Stop from a dropped connection)
- ai-chat.types.ts: add metadata.finishReason; rowToUiMessage now carries it
- en-US: three new strings
Frontend only — the server already persists partial work and finishReason and
replays it to the model on the next turn (continue, not restart).
The "Copy chat" export read only persisted DB rows (messageRows), so an
assistant reply that was still streaming — and the user message that
triggered it — were absent from the export until the turn finished and
the messages query was refetched.
ChatThread now mirrors its live useChat snapshot ({ messages,
isStreaming }) into a parent-owned ref; the effect clears the ref on
unmount so a thread switch can't leak its tail into the next chat.
AiChatWindow.handleCopy computes the not-yet-persisted live tail
(messages whose id is absent from messageRows, only while streaming) and
passes it to buildChatMarkdown as `pending`. buildChatMarkdown appends
pending messages after the persisted rows (continuing the heading
numbering), flags the streaming assistant message with an
"still being generated" note, and reuses an extracted renderMessageParts
helper so persisted and pending rendering stay identical.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
The AI chat error Alert stranded the warning icon in the top-left while
the detail text hung indented under the heading, wrapping to 3 narrow
lines with empty space below. Switch to a "full-width detail" layout
(icon + bold heading on the first row, detail spanning full width below)
and extract the markup, previously duplicated in ChatThread and
MessageItem, into a single shared ChatErrorAlert component.
- add apps/client/src/features/ai-chat/components/chat-error-alert.tsx
- use it for the live stream error in chat-thread.tsx (mb="xs")
- use it for the persisted history error in message-item.tsx (mt={4})
- heading/icon use the adaptive --mantine-color-red-light-color so the
banner stays correct in dark mode
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Previously a message composed while the AI agent was streaming a reply was
silently dropped (the composer early-returned on isStreaming). Now such
messages are queued FIFO and sent automatically once the current turn
finishes cleanly.
- chat-input: submit() enqueues while streaming (via new onQueue prop) and
sends otherwise; during streaming show a queue Send button (when text is
present) alongside the Stop button; the textarea stays usable.
- chat-thread: per-conversation queue in local state (mirrored in a ref);
flush the next message in onFinish ONLY on a clean finish - ai@6 useChat
fires onFinish from a finally on Stop/disconnect/error too, where the queue
must be preserved. Pending messages render as removable chips above the
composer. Queue is cleared on chat switch (parent remount) and survives
in-place new-chat id adoption.
- queue-helpers: pure FIFO helpers (enqueue/dequeue/removeQueuedById) + tests.
- i18n: add en-US/ru-RU keys (Queue message, Remove queued message,
Send when the agent finishes).
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
A brand-new chat's first turn streamed and finished successfully, but the
whole assistant response vanished from the UI. On finish the window adopts
the server-created chat id, which changed the <ChatThread> key and remounted
it — discarding the live useChat store (the full answer) and re-seeding from
not-yet-persisted history, so only the user message remained.
- chat-thread: pin the useChat store id to a per-mount value so adopting the
chatId prop no longer recreates the store and wipes the live turn.
- ai-chat-window: derive the thread mount key via setState-during-render and
move the live-thread marker in lockstep with the adopted id, so in-place
adoption keeps the same mounted thread while real chat switches still
remount and re-seed; gate the history loader to a freshly opened chat.
- cancel a pending adoption on New chat / explicit chat selection.
- log the raw stream error to the browser console for debugging.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
The AI chat error banner always showed a generic "Something went wrong"
with no reason. The server already forwards the provider cause into the
stream (e.g. "Cannot connect to API: read ECONNRESET"), but the client
hid it behind a static heading.
- describeChatError now returns { title, detail }: a short heading naming
the cause category plus a one-line explanation.
- Add classifyProviderError: maps connection reset, timeout, rate limit,
context-window overflow, quota and auth failures to clear categories;
the 403/503 gating responses are preserved; unknown errors fall back to
the verbatim provider text.
- Match HTTP status codes only as the leading token and textual signatures
only against the message head (before "| response body:"), so a number
or phrase in the response-body snippet never mislabels the cause.
- Use the new {title, detail} in all three banners: chat-thread,
share-ai-widget and the persisted-error banner in message-item.
- Cover the classifier with 20 unit tests (categories + regressions).
Rework the new-chat role-card empty state:
- Remove the "Universal assistant" card; universal assistant is now the
implicit default the user gets by typing without picking a card.
- Show each role's description on its card (under the emoji and name).
- Clicking a card immediately starts the chat: it binds the role to the
new chat and sends the default opening prompt "Take a look at the
current document" (one click, no separate select step). roleIdRef is
set synchronously before sendMessage so the create request carries the
role.
- Show the current role's name in the window header badge and as the
assistant's display name (transcript label + "… is typing…"), falling
back to "AI agent" for a role-less chat. selectChat resets the picked
role so it cannot leak into an unrelated existing chat.
- Add the "Take a look at the current document" i18n key (en-US, ru-RU).
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Replace the new-chat <Select label="Agent role"> picker with colored role
cards rendered as the empty-state of a brand-new chat (centered in the window),
per docs/backlog/ai-chat-role-cards-empty-state.md. Clicking a card selects that
identity; sending without a pick falls back to the Universal assistant; the
cards disappear once the chat is non-empty. Purely client-side — the existing
selectedAiRoleIdAtom + roleId request wiring (server role fixation on chat
creation) is unchanged.
- new RoleCards rendered through the existing emptyState prop chain
(AiChatWindow -> ChatThread -> MessageList); MessageList already supported it.
- Universal assistant card (gray, value null, default-selected) + one card per
enabled role, color cycled from a 10-name Mantine palette via the pure
roleCardColor() helper; theme-aware CSS vars (light/-light-color/-filled).
- each card is an UnstyledButton with aria-pressed for a11y + testability.
- tests: role-card-color (palette cycling, negative-safe) + role-cards.test.tsx
(render, emoji/name, selection highlight, click -> onSelect). 9 tests green,
client tsc clean.
Verified live in-browser: cards (not a Select) show for a new chat; selecting
Пират binds the chat to that role end-to-end (badge + pirate reply); no pick =>
Universal; cards vanish after the first message.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Behaviour change (split out of the test commit per review).
In AI SDK v6 the useChat `onFinish` callback does NOT fire when the stream
errors. A brand-new chat whose very first turn fails would therefore never run
the post-turn path: the chat list was not invalidated and the client never
adopted the server-created chat id — so the failed chat only appeared in
history after a manual refresh (the server already creates the row and stores
the error message). Running the same `onTurnFinished()` handler on `onError`
makes the failed chat show up immediately. The error itself is still surfaced
to the user via the existing `error` state.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Reusable, workspace-shared agent roles for the built-in AI chat. A role is
a named persona (system-prompt instructions) + optional model override; a
chat is bound to a role at creation and applies it every turn.
Backend:
- migration 20260620T120000: ai_agent_roles table + ai_chats.role_id
(FK ON DELETE SET NULL); hand-merged types into db.d.ts/entity.types.ts
(db.d.ts is hand-curated here, full codegen would clobber it).
- core/ai-chat/roles: CRUD module. list = any workspace member; create/
update/delete = admin (Manage Settings ability, like ai-settings/mcp).
All repo queries scoped by workspace_id; soft-delete (deleted_at).
- buildSystemPrompt gains roleInstructions: role REPLACES the persona base
(admin prompt / DEFAULT_PROMPT) but SAFETY_FRAMEWORK + context are always
still appended.
- stream(): role resolved from ai_chats.role_id for existing chats (never
the request body -> no per-turn role swap); body.roleId only on creation.
Disabled (enabled=false) and soft-deleted roles fall back to universal.
- getChatModel(workspaceId, override): role model_config can swap model id /
driver; a driver without configured creds throws 503 with a clear message
naming the driver+role, resolved BEFORE response hijack.
Client:
- new-chat role picker (enabled roles only, default Universal assistant),
roleId sent only on the first message; role badge (emoji+name) in the chat
header and conversation list; admin Agent-roles management section in
Settings -> AI (add/edit/delete, MCP-form pattern).
Tests: ai-chat.prompt.spec (role layering + safety always present, incl.
jailbreak); ai.service.spec (override on unconfigured driver -> 503).
Implements docs/ai-agent-roles-plan.md.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Surfacing the stream error via useChat().error alone was not enough: on a
brand-new chat the errored turn still fires onFinish -> onTurnFinished, which
adopts the freshly-created chat id and changes the <ChatThread> key, remounting
it with a fresh useChat whose transient `error` is gone. The thread re-seeds
from persisted history, where the assistant row has empty parts and the error
lives only in metadata.error — which was never rendered. Result: an empty
"AI agent" row and no visible error.
- Render the persisted metadata.error inline in MessageItem, so the error
survives the remount and is also shown in reopened chat history.
- Carry metadata.error onto the rebuilt UIMessage in rowToUiMessage.
- Extract the error formatter into utils/error-message.ts (describeChatError)
and reuse it for both the live Alert and the persisted error.
- Add metadata.error to the IAiChatMessageRow type.
Client-only; the server already persists metadata.error. No new i18n keys.
The AI chat UI previously collapsed every non-403/503 failure into a
generic "could not respond" message, hiding real provider errors such as
OpenRouter HTTP 402 "requires more credits". The backend already forwards
the real "<status>: <message>" via pipeUIMessageStreamToResponse onError,
so the fix is client-side.
- describeError now returns the provider message verbatim for any error
that is not one of our own gating responses, so 402 (credits), 429
(rate limit) and similar causes are visible to the user.
- Match gating responses by the NestJS JSON "statusCode" field instead of
loose substring/word checks, so a provider message that merely contains
"403"/"503"/"disabled" is no longer misclassified and hidden.
- Add a providerDetail() helper that filters empty text and the opaque
"An error occurred." / "Internal server error" placeholders, falling
back to the generic message only then.
No backend changes; no new i18n keys.
so the v6 hook stops re-creating its store every render on a new chat
(which wiped the optimistic user message + streamed deltas, so nothing
showed until the turn finished). Also send X-Accel-Buffering:no + flushHeaders.
- context: client sends the currently-open page {id,title}; the system prompt
tells the agent which page 'this page' refers to (it reads it via its
CASL-scoped getPage tool; id is prompt-context only, no server-side fetch).
- embeddings: make page_embeddings.embedding dimension-agnostic (drop the
HNSW index + ALTER to vector), remove the hard 1536 guard, filter search by
model_dimensions — so 3072-dim (and any) models index instead of being
skipped. Seq-scan <=> search (wiki scale); existing pages reindex on next edit.
- Add reversible write tools to the per-user agent toolset (page create/update/
move/soft-delete; comment reply + resolve), exposed under the user's JWT and
enforced by Docmost CASL; no permanent/force delete (D3).
- Non-spoofable agent provenance: sign actor/aiChatId into the access and collab
tokens (TokenService), propagate via jwt.strategy onto the request, and set
pages.last_updated_source/last_updated_ai_chat_id on REST create/update/move and
comments.created_source/resolved_source/ai_chat_id.
- packages/mcp: add an optional getCollabToken provider (content-edit provenance)
and guard against empty tokens; service-account /mcp path unchanged.
Frontend:
- Admin 'AI / Models' settings section: provider/model/embedding/base URL, a
write-only API key field, system prompt, and Test connection.
- AI chat panel (useChat + DefaultChatTransport): conversation list, streamed
messages, tool-call action log and page citations; header entry point gated on
settings.ai.chat.
Compile-verified (server nest build + client tsc/vite); not yet live-tested.
Known gaps: history 'AI agent' badge (C3), vector RAG (D), external MCP (E);
chat tool-card citation links pending a fix.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
