feat(ai-chat): per-user AI agent backend — LLM config, read-only agent, provenance schema
WIP checkpoint of the gitmost AI-chat backend (plan stages A + B1 + B3a). The agent acts under the requesting user's JWT (Docmost CASL enforces page access); the external service-account /mcp endpoint is untouched. LLM provider config (A2-A4): - integrations/crypto: AES-256-GCM SecretBoxService (key derived from APP_SECRET, per-record salt/iv; clear error on rotation instead of crashing). - ai_provider_credentials table/repo/types: encrypted API key stored outside workspace settings/baseFields, write-only (never returned by any endpoint). - integrations/ai: per-workspace AI SDK v6 provider driver (openai/gemini/ollama), admin-gated GET(masked)/PATCH(write-only key)/Test endpoints; settings.ai.provider holds non-secret config incl. systemPrompt. Removed unused AI_* env getters (DB is the single source of truth). Chat module (A1, A5-A8): - ai_chats/ai_chat_messages repos (workspace-scoped, soft-delete, tsv never selected). - core/ai-chat: CRUD + POST /ai-chat/stream (Fastify hijack + AI SDK v6 pipeUIMessageStreamToResponse, abort on disconnect, persist user/assistant msgs). - Agent loop: streamText + stepCountIs(8); read tools searchPages/getPage via a per-request DocmostClient over loopback REST under the user's minted access token. - Gate settings.ai.chat (+ 503 when provider unconfigured); buildSystemPrompt with a non-removable safety/anti-prompt-injection framework. Per-user rate limit. Per-user auth (B1): - @docmost/mcp DocmostClient gains an additive getToken variant (carry a user JWT, re-fetch on 401) and exports DocmostClient; the email/password service-account path (external /mcp, stdio) is unchanged. Agent-edit provenance backbone (B3a): - Migration: pages/page_history (last_updated_source, last_updated_ai_chat_id) and comments (created_source, ai_chat_id, resolved_source). - Signed actor/aiChatId claim in the collab token; onAuthenticate propagates it, onStoreDocument writes it with a sticky agent marker, saveHistory copies it. Migrations auto-run on boot (additive). Write tools, frontend, RAG and external MCP servers are not in this checkpoint. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
This commit is contained in:
@@ -20,6 +20,11 @@ export type JwtCollabPayload = {
|
||||
sub: string;
|
||||
workspaceId: string;
|
||||
type: 'collab';
|
||||
// Optional agent-edit provenance, signed into the collab token. Absent for
|
||||
// the human collab path (treated as 'user'); set only when the internal agent
|
||||
// mints a provenance collab token (§6.6 / §15 C2).
|
||||
actor?: 'user' | 'agent';
|
||||
aiChatId?: string;
|
||||
};
|
||||
|
||||
export type JwtExchangePayload = {
|
||||
|
||||
@@ -42,7 +42,13 @@ export class TokenService {
|
||||
return this.jwtService.sign(payload);
|
||||
}
|
||||
|
||||
async generateCollabToken(user: User, workspaceId: string): Promise<string> {
|
||||
async generateCollabToken(
|
||||
user: User,
|
||||
workspaceId: string,
|
||||
// Optional agent-edit provenance. When omitted (the human collab path), the
|
||||
// token carries no actor/aiChatId and is treated as 'user' downstream.
|
||||
provenance?: { actor: 'agent'; aiChatId: string },
|
||||
): Promise<string> {
|
||||
if (isUserDisabled(user)) {
|
||||
throw new ForbiddenException();
|
||||
}
|
||||
@@ -51,6 +57,9 @@ export class TokenService {
|
||||
sub: user.id,
|
||||
workspaceId,
|
||||
type: JwtType.COLLAB,
|
||||
...(provenance
|
||||
? { actor: provenance.actor, aiChatId: provenance.aiChatId }
|
||||
: {}),
|
||||
};
|
||||
const expiresIn = '24h';
|
||||
return this.jwtService.sign(payload, { expiresIn });
|
||||
|
||||
Reference in New Issue
Block a user