Ollama reloaded the chat model mid-message because plan/summary/router
calls sent divergent runner options (no num_ctx/num_batch) and omitted
keep_alive — the main cause of perceived slowness.
- share one keep-alive httpx.AsyncClient for all Ollama calls
- unify runner options (runner_options) + keep_alive on every model
call, embeddings included
- drop the blocking LLM routing fallback (pure lexical heuristic)
- run RAG recall + plan + code-model pick in parallel inside the SSE
stream, after the start event
- RAG cosine scoring off the event loop; cache /api/tags 30s and
nvidia-smi 5s; frontend polls 2s->5s, warm poll backoff, dedup
config fetch
feat: working session menu in TopBar (switch/create/rename/delete)
feat: workspace file deletion (DELETE /api/files + UI trash buttons)
docs: recommended Ollama env vars (KEEP_ALIVE, MAX_LOADED_MODELS...)
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
UI : reskin complet vers un theme neo-brutaliste clair (bordures noires 3px,
ombres dures, accent orange, polices Press Start 2P + DM Mono).
- tailwind.config / index.css / index.html : palette, polices, ombres, scrollbars
- TopBar, ActivityBar, LeftPanel, ChatPanel, PreviewPanel, SettingsView,
ToolCard, ModelSelector, Icon : restyle complet
Chat : panneau « Raisonnement » repliable et redimensionnable affichant le
thinking de l'agent en direct (diffuse depuis le backend, persiste dans meta).
Robustesse Ollama : les echecs de generation de parseur d'outils
(« Unable to generate parser for this template ») declenchent desormais le
repli automatique en conversation simple sans outils, au lieu d'un 400.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
MichaelandClaude Opus 4.8