gitmost/packages/mcp/node_modules/@hocuspocus/provider at main - gitmost - vvzvlad@gitea

vvzvlad/gitmost

Files

vvzvlad a4b7919753 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).

2026-06-17 04:28:29 +03:00

Symbolic link

1 line

185 B

Plaintext

Raw Permalink Blame History

../../../../node_modules/.pnpm/@hocuspocus+provider@3.4.4_y-protocols@1.0.6_yjs@13.6.30_patch_hash=1ceeb66dba1f86545c9_bc01a253a9579de2451e72d099c2c9d7/node_modules/@hocuspocus/provider