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.
- openai provider: use .chat() (Chat Completions) instead of the default callable
(Responses API), which gateways reject on multi-turn -> 400.
- updateAiProviderSettings: assemble settings.ai.provider via jsonb_build_object
with ::text-cast bound params + jsonb_typeof self-heal (postgres.js was
double-encoding it into an array; the ::text cast avoids 'could not determine
data type of parameter').
- chat agent: drop the hard maxOutputTokens cap (truncated complex tool calls);
keep a tiny cap only on the test-connection ping.
- testConnection + chat stream: surface the real provider error (statusCode+message)
to logs and the UI instead of generic masks; never log the API key.
- chat UI: typing indicator, incremental streaming render, tool 'running' status, Stop.
Also bundled (prior uncommitted ai-chat work):
- history 'AI agent' provenance badge; vector RAG (pgvector image + page_embeddings
+ AI_QUEUE indexer + space-scoped semanticSearch); external MCP servers backend
(@ai-sdk/mcp client, SSRF IP-pinning, encrypted headers, admin CRUD/Test);
yjs duplicate-instance fix via pnpm patch (single CJS instance server-side).
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>
* Better trash
I recently lost a bunch of time editing and searching for pages that were actually in the Trash. Docmost intentionally tries to not link to Trashed pages, but the url of that Trashed page and any inbound links still work. This makes it clearer when a page you are interacting with is in the Trash.
- /trash
- Refactored banner into `trash-banner.tsx`
- Refactored "Restore" modal into `use-restore-page-modal.tsx`
- Page (when isDeleted)
- Add: `trash-banner.tsx`
- Add breadcrumbs: `Parent / Child / Page (Deleted)`
- Change: Deleted Pages are read-only
- Replace "Move to Trash" with "Restore" in page menu (invokes `use-restore-page-modal`)
I tried very hard to keep this simple and re-use existing translation strings wherever possible.
* cleanup
---------
Co-authored-by: Philipinho <16838612+Philipinho@users.noreply.github.com>
* Show actual history changes
* V2 - WIP
* feat: page history diff
* fix: exclude content from history listing
---------
Co-authored-by: Jason Norwood-Young <jason@10layer.com>
* add cursor pagination function
* support custom order modifier
* refactor returned object
* feat(db): migrate paginated endpoints to cursor-based pagination
* sync
* support hasPrevPage boolean
* feat(client): migrate pagination from offset to cursor-based
* support beforeCursor/prevCursor
* wrap search results in items array for API consistency
* feat: implement SSO group synchronization for SAML and OIDC
- Add group_sync column to auth_providers table
- Extract groups from SAML attributes (memberOf, groups, roles)
- Extract groups from OIDC claims (groups, roles)
- Implement case-insensitive group matching with auto-creation
- Sync user groups on each SSO login
- Ensure only one provider can have group sync enabled at a time
- Add group sync toggle to SAML and OIDC configuration forms
* rename column
- Add PostgreSQL unaccent and pg_trgm extensions
- Create immutable f_unaccent wrapper function for performance
- Update all search queries to use f_unaccent for accent-insensitive matching
- Add 1MB limit to tsvector content to prevent errors on large documents
- Update full-text search trigger to use f_unaccent
- Fix MultiSelect client-side filtering to show server results properly
