feat(FN-3905): use merger session model for post-merge workflow steps
The merge implements post-merge model resolution, using the merger's own session model for executing post-merge prompt workflow steps instead of falling back to executor model defaults. Tests cover the resolution hierarchy, and documentation clarifies the precedence order for downstream consumers. Fusion-Task-Id: FN-3905
This commit is contained in:
@@ -280,8 +280,9 @@ Intentional exclusions from shared snapshots:
|
||||
- The Rooms tab in `packages/dashboard/app/components/ChatView.tsx` is wired through `useChatRooms` (`packages/dashboard/app/hooks/useChatRooms.ts`).
|
||||
- `useChatRooms` owns room list fetch/sort, active-room selection, member+message hydration, room creation/deletion, and room message sends.
|
||||
- The hook subscribes to `/api/events` and consumes `chat:room:created`, `chat:room:updated`, `chat:room:deleted`, `chat:room:member:added`, `chat:room:member:removed`, `chat:room:message:added`, `chat:room:message:updated`, and `chat:room:message:deleted` to keep UI state in sync.
|
||||
- Room messages persist through `POST /api/chat/rooms/:id/messages`; the route persists the user message first, then calls `ChatManager.sendRoomMessage(...)` to orchestrate room-member responders and persist assistant room replies with `chatStore.addRoomMessage(...)`.
|
||||
- Room messages persist through `POST /api/chat/rooms/:id/messages`; the route persists the user message first, then calls `ChatManager.sendRoomMessage(...)` to orchestrate room-member responders and persist assistant room replies with `chatStore.addRoomMessage(...)` (including `senderAgentId` for each responder).
|
||||
- `sendRoomMessage(...)` uses existing room-member + mention resolution rules: mentioned members are direct responders, non-mentioned members are ambient responders (capped by `ROOM_AMBIENT_MAX_RESPONDERS`), and non-member mentions are handled explicitly by the manager instead of silently disappearing.
|
||||
- Room-reply generation is now non-silent on failure: if a room has members but no active responders can be resolved, or all responder generations fail/return empty output, `sendRoomMessage(...)` throws `RoomReplyGenerationError` and the route surfaces HTTP 502 instead of returning a silent user-only success.
|
||||
- UI does not optimistically insert room messages; `useChatRooms.sendRoomMessage()` re-fetches authoritative room messages immediately after `POST /api/chat/rooms/:id/messages` so persisted assistant replies remain visible across SSE timing gaps, then continues applying `chat:room:message:*` events for live updates.
|
||||
- Mention UI in rooms keeps direct-chat behavior unchanged while adding room affordances:
|
||||
- `AgentMentionPopup` receives room membership context and shows members first with a `status-dot` member indicator (`aria-label="Room member"`).
|
||||
|
||||
@@ -114,6 +114,8 @@ Chat Rooms are project-scoped group conversations for multiple agents. They are
|
||||
- After a successful room send, the room composer is cleared (matching direct-chat composer behavior) so stale text is not left in the input.
|
||||
- On mobile, room threads use the same keyboard-aware thread anchoring as direct chat, keeping the composer pinned above the soft keyboard while typing.
|
||||
- The dashboard backend now orchestrates room responders on that POST: mentioned members are routed as direct responders, additional ambient members may reply (up to the room ambient responder cap), and each assistant reply is persisted with `senderAgentId` via `chatStore.addRoomMessage(...)`.
|
||||
- If room replies cannot be generated (for example no resolvable responders or all responders fail), the POST fails with an API error (HTTP 502) instead of silently returning only the user message.
|
||||
- If room responders cannot be resolved or all room-reply generations fail, the POST now returns an error instead of silently succeeding with only the user message, so failures are surfaced deterministically.
|
||||
- Room responder prompt construction now includes a bounded recent room transcript (role, sender label, timestamp, content) plus an explicit latest-user-message marker, so replies stay thread-aware without unbounded prompt growth.
|
||||
- The UI still avoids optimistic room echo; after `POST /api/chat/rooms/:id/messages`, it immediately re-fetches authoritative room messages to surface persisted user/assistant replies even if SSE delivery is delayed, and it continues to apply `chat:room:message:*` SSE updates for live fan-out.
|
||||
- Relationship summary: direct Chat runs one target (agent or model) per session; rooms are shared threads with multiple agent members and now use the same message contract as direct Chat; Quick Chat stays a floating single-target panel and does not host rooms.
|
||||
|
||||
@@ -530,6 +530,8 @@ When heartbeat has both (1) and (2-5), the runtime model is used as primary and
|
||||
3. Global `defaultProvider` + `defaultModelId`
|
||||
4. Automatic provider/model resolution
|
||||
|
||||
For post-merge prompt workflow steps, explicit step-level `modelProvider` + `modelId` overrides take precedence over the merger lane above.
|
||||
|
||||
### Title summarization model
|
||||
|
||||
Used for task title auto-summarization and (when enabled) AI merge commit summaries.
|
||||
|
||||
Reference in New Issue
Block a user