- stream_chat: add think=False parameter passed through to Ollama payload.
qwen3 models have thinking enabled by default; without this flag the model
spends minutes generating internal thinking tokens that stream_chat silently
discards, leaving the frontend spinner blank until the SSE connection times
out and the widget disappears.
- create_assist_buffer: orphan (overwrite) a still-running buffer instead of
raising. The old asyncio task holds a direct reference and completes
harmlessly against the stale buffer. New requests always win.
- assist_route: remove the 409 guard that blocked new requests when a previous
generation got stuck. create_assist_buffer now handles this transparently.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
- New NoteEmbedding model + migration 0014 stores float embeddings (JSONB)
- services/embeddings.py: get_embedding, upsert_note_embedding,
semantic_search_notes (cosine similarity), backfill_note_embeddings
- build_context() now tries semantic search first, falls back to keyword search;
accepts cached_note_ids to reuse last-turn notes and stabilise the system
prompt prefix for Ollama's KV cache
- generation_buffer.py: per-conversation note ID cache (get/set/clear)
- generation_task.py: passes cached IDs into build_context, updates cache
after each turn, and invalidates it after create_note/update_note/create_task
- app.py: pulls nomic-embed-text at startup and launches a background backfill
to embed all existing notes (30 s delay so Ollama has time to load the model)
- routes/notes.py + services/tools.py: fire-and-forget embedding update on
every note create or update via the API or LLM tool calls
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Before executing any write tool (create/update/delete), the backend now
pauses with an asyncio.Future and emits a tool_pending SSE event. The
frontend displays a ToolConfirmCard with Accept and Decline buttons.
Clicking Accept resolves the Future and proceeds; Decline records a
declined tool_call chip and falls through to regular streaming. Typing
single-word yes/no responses (e.g. "yes", "cancel") also works as
confirmation. 120s timeout auto-declines if no response.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
The assist flow previously tied the entire LLM generation to a single
POST request with no keepalives, causing NS_ERROR_NET_PARTIAL_TRANSFER
in Firefox when Hypercorn closed the connection during gaps between
chunks. This refactor decouples generation into a background task with
a buffer and a separate SSE stream — the same pattern used by chat.
- generation_buffer.py: Widen _buffers to support string keys, add
create/get/remove_assist_buffer() using "assist:{user_id}" keys,
fix cleanup log format for string keys
- generation_task.py: Add run_assist_generation() — lightweight
background task with no DB persistence or title generation
- notes.py: Replace single POST SSE route with POST /api/notes/assist
(returns 202) + GET /api/notes/assist/stream (SSE with 15s keepalives
and Last-Event-ID reconnection); 409 if already running
- useAssist.ts: Switch from apiStreamPost to apiPost + apiSSEStream
two-step pattern with named event mapping and stream handle cleanup
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
bvandeusen