fix(ai-chat): OpenAI Chat Completions for multi-turn + provider settings, stream UX & errors" -m "Live-stand fixes (OpenRouter / OpenAI-compatible):

- 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).

package.json

@@ -95,7 +95,8 @@
   "packageManager": "pnpm@10.4.0",
   "pnpm": {
     "patchedDependencies": {
-      "scimmy@1.3.5": "patches/scimmy@1.3.5.patch"
+      "scimmy@1.3.5": "patches/scimmy@1.3.5.patch",
+      "yjs@13.6.30": "patches/yjs@13.6.30.patch"
     },
     "overrides": {
       "prosemirror-changeset": "2.4.0",
@@ -133,8 +134,8 @@
       "axios": "1.16.0",
       "langsmith": "0.7.0",
       "follow-redirects": "1.16.0",
-      "protobufjs":  "7.5.8",
-      "ip-address":  "10.1.1"
+      "protobufjs": "7.5.8",
+      "ip-address": "10.1.1"
     },
     "neverBuiltDependencies": []
   }