Trip planner

Greg Pomerantz af63297297 mock: wire the local LLM backend (llama.cpp Qwen3.8-27B-UD3-Q5-dual) ... server.js: /llm-status probe + /llm-chat proxy to the local llama.cpp OpenAI-compatible server (192.168.3.7:1234, model ctx 131072, 2 parallel sessions). Model name, base URL and token budget pinned server-side (LLM_BASE/LLM_MODEL/LLM_MAX_TOKENS env to override); non-streaming, since the hidden thinking text shares max_tokens with the visible answer. app.js: checkLLM() alongside checkRouter(); free-form chat now goes to the model with a compact live plan snapshot (bookings, stays, per-day stops with times) as system context. Deterministic UI intents (discovery drawer, time nudges, swaps) stay local — the LLM proposes, the UI commits. Canned-reply fallback when the server is down or the model is not loaded; status badge now reads e.g. 'online · router · llm'.		2026-09-09 10:19:39 -04:00
mock	mock: wire the local LLM backend (llama.cpp Qwen3.8-27B-UD3-Q5-dual)	2026-09-09 10:19:39 -04:00
router	multi-trip mock + Colombia trip with a real walking router	2026-09-09 09:44:29 -04:00
.gitignore	multi-trip mock + Colombia trip with a real walking router	2026-09-09 09:44:29 -04:00
DESIGN.md	maps project: design, survey, mock app, and route-aware planning backend	2026-09-06 00:05:17 -04:00
SURVEY.md	maps project: design, survey, mock app, and route-aware planning backend	2026-09-06 00:05:17 -04:00