docs: fix 8 spec review issues in Fable MCP design

- Add migration down_revision = "0026"
- Document create_conversation service + route changes for conversation_type
- Document SSE wire format (endpoints, event schema, termination event)
- Add retention sweep exclusion for mcp conversation type
- Rename type→content_type in search, document is_task mapping
- Clarify API keys cannot access admin-protected routes
- Document POST /api/chat/conversations accepting conversation_type body field
- Add delete_milestone to milestones tool list

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
This commit is contained in:
2026-03-23 20:03:53 -04:00
parent f9973e22f1
commit e54d172487
+51 -19
View File
@@ -28,6 +28,8 @@ All existing Fable routes use session-based authentication (`session["user_id"]`
### Database
New table `api_keys` via migration `0027_add_api_keys.py`:
- `down_revision = "0026"` (the briefing tables migration)
- `revision = "0027"`
| Column | Type | Notes |
|--------|------|-------|
@@ -54,9 +56,11 @@ Full keys are generated as `fmcp_<32 random url-safe chars>`, returned once at c
Session auth is untouched — no regression risk for the web UI.
**Admin routes and API keys:** Routes decorated with `admin_required` check `user.role == "admin"` after auth resolves. API keys authenticate as the key owner — so a write-scoped key for a non-admin user will fail admin-protected routes with 403 (role check, not scope check). This is intentional: API keys cannot elevate privilege beyond the user's role.
### Routes (`/api/api-keys`)
New blueprint `api_keys_bp`:
New blueprint `api_keys_bp`, registered in `app.py`:
- `GET /api/api-keys` — list caller's keys (prefix, name, scope, last_used_at, created_at — never the hash or full key)
- `POST /api/api-keys` — create key; body: `{name, scope}`. Returns full key in response **once only**
@@ -73,9 +77,14 @@ New "API Keys" tab in `SettingsView.vue` (added to `VALID_TABS`):
### New Search Endpoint
`GET /api/search?q=<query>&type=note|task|all&limit=N`
`GET /api/search?q=<query>&content_type=note|task|all&limit=N`
Calls the existing `semantic_search_notes()` service (already in `services/embeddings.py`). Returns:
Calls the existing `semantic_search_notes()` service (already in `services/embeddings.py`). The `content_type` parameter maps to the service's `is_task` argument:
- `content_type=note``is_task=False`
- `content_type=task``is_task=True`
- `content_type=all` (default) → `is_task=None`
Returns:
```json
{
@@ -88,6 +97,37 @@ Calls the existing `semantic_search_notes()` service (already in `services/embed
This endpoint is needed by the MCP's `search.py` tool module. It reuses existing infrastructure with no new ML work.
### Conversation Type: `"mcp"`
A new conversation type `"mcp"` is added alongside `"chat"` and `"briefing"`. This requires changes in two places in the main app:
**`services/chat.py`** — `create_conversation(user_id, title, model)` gains an optional `conversation_type: str = "chat"` parameter, passed through to the `Conversation` constructor.
**`routes/chat.py`** — `POST /api/chat/conversations` accepts an optional `conversation_type` body field (defaults to `"chat"`), passed to `create_conversation`. `GET /api/chat/conversations` continues to default-filter to `conversation_type="chat"` (excluding `"mcp"` and `"briefing"`); pass `?type=mcp` to retrieve MCP conversations.
**Retention:** `cleanup_old_conversations` in `routes/chat.py` currently deletes conversations regardless of type. It must be updated to exclude `conversation_type="mcp"` from the sweep, so MCP audit-trail conversations are not automatically pruned.
MCP conversations:
- Are created with a caller-supplied name (e.g., `"MCP Session 2026-03-23"`) or auto-named
- Are excluded from the default chat list
- Are accessible via `GET /api/chat/conversations?type=mcp` for inspection
- Appear in the Fable UI if explicitly navigated to, providing an audit trail of MCP-driven interactions
### Chat SSE Wire Format
The MCP's `chat.py` tool must consume the existing SSE stream. The relevant endpoints and event schema:
- **Create conversation:** `POST /api/chat/conversations``{id, title, ...}`
- **Post message + start generation:** `POST /api/chat/conversations/:id/messages``{message_id, ...}`; then connect to:
- **Stream:** `GET /api/chat/conversations/:id/stream` (SSE)
SSE event format (each line is `data: <json>`):
- `{"type": "token", "content": "..."}` — streaming token
- `{"type": "tool_call", "name": "...", "result": {...}}` — tool fired
- `{"type": "done", "content": "...", "tools_used": [...]}` — generation complete; this is the termination event
The MCP tool reads tokens until it receives `type: "done"`, then returns `response` (full content) and `tools_used` (list of tool names).
---
## Sub-project 2: Fable MCP Server
@@ -109,12 +149,13 @@ fable-mcp/
client.py # FableClient: async httpx wrapper, env var config, FableAPIError
tools/
__init__.py
notes.py # list_notes, get_note, create_note, update_note, delete_note, search_notes
notes.py # list_notes, get_note, create_note, update_note, delete_note
tasks.py # list_tasks, get_task, create_task, update_task, delete_task,
# patch_task_status, add_task_log
projects.py # list_projects, get_project, create_project, update_project,
# delete_project, get_project_summary
milestones.py # list_milestones, get_milestone, create_milestone, update_milestone
milestones.py # list_milestones, get_milestone, create_milestone,
# update_milestone, delete_milestone
search.py # semantic_search — calls GET /api/search
chat.py # send_message — creates/continues conversation, returns response
```
@@ -172,17 +213,18 @@ Each module imports `_client` from `client.py` and defines tools as `async def`
- `get_milestone(project_id, milestone_id)`
- `create_milestone(project_id, title, description, order_index)`
- `update_milestone(project_id, milestone_id, title, description, status, order_index)`
- `delete_milestone(project_id, milestone_id)`
**`search.py`** tools:
- `semantic_search(query, type, limit)`calls `GET /api/search`, returns ranked results with similarity scores
- `semantic_search(query, content_type, limit)``content_type` is `"note"`, `"task"`, or `"all"` (avoids shadowing Python's `type` builtin). Calls `GET /api/search`, returns ranked results with similarity scores.
**`chat.py`** tools:
- `send_message(message, conversation_name)`:
- Looks up or creates a Fable conversation with the given name and type `"mcp"`
- Looks up or creates a Fable conversation with the given name and `conversation_type="mcp"`
- Posts the message via `POST /api/chat/conversations/:id/messages`
- Polls the SSE stream until generation completes
- Consumes SSE stream from `GET /api/chat/conversations/:id/stream` until `type: "done"`
- Returns: `{response: str, tools_used: [str], conversation_id: int}`
- MCP conversations use type `"mcp"` and are excluded from the normal chat UI list
- MCP conversations are excluded from the normal chat UI list
### Error Handling
@@ -212,16 +254,6 @@ Claude Code spawns the process over stdio automatically. No Docker, no daemon.
---
## Conversation Type: `"mcp"`
A new conversation type `"mcp"` is added alongside `"chat"` and `"briefing"`. Conversations of this type:
- Are created with a caller-supplied name (e.g., `"MCP Session 2026-03-23"`) or auto-named
- Are excluded from `GET /api/chat/conversations` (the main chat list) by default
- Are accessible via `GET /api/chat/conversations?type=mcp` if inspection is needed
- Appear in the Fable UI if explicitly navigated to, providing an audit trail of MCP-driven interactions
---
## Build & Repo Plan
1. Implement and test within `fabledassistant/fable-mcp/`