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:
@@ -211,6 +211,36 @@ export class WorkspaceRepo {
|
||||
.executeTakeFirst();
|
||||
}
|
||||
|
||||
/**
|
||||
* Deep-merge a partial provider config into the fixed path
|
||||
* `settings.ai.provider`. Unlike `updateAiSettings` (single scalar key under
|
||||
* `settings.ai`), this stores a nested object. The path is constant — only the
|
||||
* provider value is parameterized (bound, not `sql.raw`) — so it cannot store
|
||||
* a secret and is safe from injection. Sibling `settings.ai.*` keys (search /
|
||||
* generative / chat / mcp / systemPrompt) and provider fields absent from the
|
||||
* partial are preserved via jsonb `||` merge.
|
||||
*/
|
||||
async updateAiProviderSettings(
|
||||
workspaceId: string,
|
||||
provider: Record<string, unknown>,
|
||||
trx?: KyselyTransaction,
|
||||
): Promise<Workspace> {
|
||||
const db = dbOrTx(this.db, trx);
|
||||
const providerJson = JSON.stringify(provider);
|
||||
return db
|
||||
.updateTable('workspaces')
|
||||
.set({
|
||||
settings: sql`COALESCE(settings, '{}'::jsonb)
|
||||
|| jsonb_build_object('ai', COALESCE(settings->'ai', '{}'::jsonb)
|
||||
|| jsonb_build_object('provider', COALESCE(settings->'ai'->'provider', '{}'::jsonb)
|
||||
|| ${providerJson}::jsonb))`,
|
||||
updatedAt: new Date(),
|
||||
})
|
||||
.where('id', '=', workspaceId)
|
||||
.returning(this.baseFields)
|
||||
.executeTakeFirst();
|
||||
}
|
||||
|
||||
async updateSharingSettings(
|
||||
workspaceId: string,
|
||||
prefKey: string,
|
||||
|
||||
Reference in New Issue
Block a user