2 Commits

Include renames

Author	SHA1	Message	Date
bvandeusenandClaude Sonnet 4.6	df4c52412d	Phase 22b: Parallel research fetching, streaming synthesis, intent optimizations ... 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>	2026-02-27 18:24:15 -05:00
bvandeusenandClaude Sonnet 4.6	590682a5d2	Phase 22: SearXNG web research pipeline + settings layout overhaul ... Research pipeline (research_topic tool): - New service: services/research.py — sub-query generation, SearXNG search, URL fetch, deduplication, and LLM synthesis into a note - 5 sub-queries × 3 pages = up to 15 sources, capped at 12 for synthesis - Synthesis uses num_ctx=16384 + max_tokens=8192 for long-form output - Prompt demands 2500+ words, 6+ topic-appropriate sections, detailed prose - 429 retry with backoff; 1s inter-query sleep; raw_decode JSON parsing search_web tool (new): - Lightweight single-query SearXNG search, results returned inline in chat - LLM answers conversationally in round 1; no note created - web_search result type with external links in ToolCallCard Infrastructure: - llm.py: generate_completion accepts num_ctx override - config.py: SEARXNG_URL + Config.searxng_enabled() - docker-compose: OLLAMA_NUM_PARALLEL=2, commented SEARXNG_URL example - intent.py: search_web and research_topic routing rules Settings UI: - 2-column grid layout (small sections pair up, complex span full width) - Search Test section: live SearXNG query with result preview - GET /api/settings/search?q= proxy endpoint - Research button (magnifier) in ChatView input toolbar → popover modal Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>	2026-02-27 15:21:38 -05:00