Non-streaming generate_completion was the only LLM entry point that
didn't default num_ctx — stream_chat and stream_chat_with_tools both
fall back to Config.OLLAMA_NUM_CTX (16384). When a caller omitted the
argument, Ollama silently used the model's default window (~4k on
qwen3) and truncated the prompt.
That footgun was masked by fallback paths in the research pipeline:
_generate_outline's prompt carries ~12 sources × 2000 chars (~6k
tokens) of source material plus a system prompt, so the prompt got
chopped, the model never saw the sources, JSON parsing failed twice,
and run_research_pipeline dropped into the single-note "monolith"
fallback (research.py:251). The user reported chat 215 producing such
a monolith note for a multi-source research topic.
Two-layer fix:
- Default num_ctx to Config.OLLAMA_NUM_CTX inside generate_completion,
matching the streaming entry points. Any current or future caller
that forgets the argument stops silently losing input.
- Pin num_ctx=16384 explicitly in _generate_outline and
_generate_executive_summary with comments pointing at the failure
mode, so a refactor of the generate_completion default can't
silently regress the research pipeline.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Research pipeline now produces an index note with:
- Executive summary (2-3 paragraphs synthesized from sections)
- Clickable links to each section note (/notes/{id})
- Section notes have parent_id pointing to the index
Also improves outline resilience: lowered minimum sections from 3
to 2, retries once on failure before falling back to monolithic note.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Replaces the single monolithic research note with topic-driven section notes
plus an index note. Two new LLM calls: _generate_outline (JSON outline, 3-8
sections) and _synthesize_section (300-600 word focused note per section,
parallelised via asyncio.gather). Public signature of run_research_pipeline
unchanged; falls back to single-note synthesis on outline failure or if all
sections fail.
Also extracts _build_sources_block helper and adds full test suite.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
run_research_pipeline now accepts project_id; generation_task.py passes
workspace_project_id when the tool is called from a workspace context.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
The separate intent model (OLLAMA_INTENT_MODEL / qwen2.5:7b) is removed
from every part of the system. All classification now uses the primary model.
Changes:
- config.py: remove OLLAMA_INTENT_MODEL
- intent.py: remove classify_intent() and all supporting infrastructure
(_SYSTEM_PROMPT_TEMPLATE, _RESEARCH_PREFIX, _PRIOR_WORK_REFS); file now
only contains the quick-capture classifier
- quick_capture.py: classify_capture_intent() now called with Config.OLLAMA_MODEL
- generation_task.py: remove intent_model_setting DB lookup and get_setting import;
history summarization and research pipeline use the primary model directly
- research.py: remove intent_model parameter from run_research_pipeline() and
_generate_sub_queries(); both use the model param throughout
- routes/settings.py: remove intent_model from model-key validation and response
- app.py: remove intent model pre-warming at startup
- SettingsView.vue: remove Intent Model selector and related refs/state
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
- Remove all 6 CalDAV todo tools (create/list/update/complete/delete/search_todos)
from tools.py definitions, imports, execute_tool branches, intent routing rules,
generation_task labels/actions, and llm.py system prompt hints. CalDAV event
tools remain. Todo functions still exist in caldav.py but are no longer exposed.
- Quick-capture now uses a dedicated classify_capture_intent() with a focused
_CAPTURE_SYSTEM_PROMPT that always routes to a tool (never null). Tool set
expanded: create_note/task/event + update_note + research_topic.
- research_topic in quick-capture calls run_research_pipeline() directly (no SSE
buffer). run_research_pipeline() now accepts buf=None; all buf.append_event
calls are guarded so status events are skipped when no buffer is provided.
- Fallback note now always sets body=text (was empty for texts ≤80 chars).
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Images found via SearXNG are fetched server-side, stored on disk, and
served from /api/images/<id> — the user's browser never contacts the
original image host. Original URLs are preserved for citation.
New files:
- alembic/versions/0016_add_image_cache.py — image_cache table
- src/fabledassistant/models/image_cache.py — SQLAlchemy model
- src/fabledassistant/services/images.py — fetch/store/serve logic
- src/fabledassistant/routes/images.py — GET /api/images/<id>
Modified:
- config.py: IMAGE_CACHE_DIR (/data/images), IMAGE_MAX_BYTES (5 MB)
- research.py: _search_searxng_images() — SearXNG categories=images
- tools.py: _IMAGE_TOOLS def + search_images branch in execute_tool
- intent.py: search_images routing rule (explicit visual language only)
- app.py: register images_bp
- docker-compose.yml: image_cache named volume mounted at /data/images
- ToolCallCard.vue: "image_search" label
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
research.py:
- Parallelize all 5 SearXNG queries concurrently (200ms stagger via asyncio.gather)
- Parallelize all URL fetches in parallel (asyncio.gather) — up to 15 URLs at once
instead of sequential fetches; biggest performance win (was O(n) × 15s, now ~15s flat)
- _synthesize_note accepts buf: when provided uses stream_chat (num_ctx=16384,
num_predict=8192) to emit tokens into the chat buffer in real time so users see
the note being written; falls back to generate_completion when buf=None
- Added \n\n---\n\n separator before "Research complete!" to cleanly mark boundary
after streamed synthesis content
intent.py:
- classify_intent passes num_ctx=4096 to generate_completion — reduces VRAM pressure
and prefill time for the intent model call on every single request
generation_task.py:
- _INTENT_TRIGGER_WORDS frozenset (~50 action/object/date words) + _should_skip_intent()
skips intent classification for short messages (≤10 words) with no trigger words;
saves 400-800ms model call for conversational replies ("thanks", "okay", etc.)
- Added \n\n---\n\n separator before research "done" text in research_topic branch
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
bvandeusen