davsclaus opened a new pull request, #26162: URL: https://github.com/apache/camel/pull/26162
## Summary Builds on the work from #26145 (atiaomar1978-hub) with additional features folded in from the now-closed #26144. ### Core (from #26145 — Omar Atie) - **`OllamaDoctorSupport`** — shared probe for local Ollama at `localhost:11434` and `camel infra run ollama` PID files; lists pulled models via `/api/tags` - **`camel doctor`** — new Ollama row showing running state and model names - **TUI doctor popup** — Ollama row with model count; Ollama status threaded into `checkAiProvider` so only one HTTP probe is made per open - **`LlmClient.endpointUrl()`** — exposes resolved endpoint after auto-detection - Tests: `OllamaDoctorSupportTest`, `DoctorTest`, `DoctorPopupOllamaTest` ### Added in this PR - **`LlmClient`**: `LLM_BASE_URL` / `OPENAI_BASE_URL` env vars redirect `LLM_API_KEY` to any OpenAI-compatible server (LM Studio, vLLM, llama.cpp, GPT4All, …) - **`OllamaDoctorSupport`**: `isSmallModel()` / `allModelsSmall()` helpers; TUI shows ⚠ and an upgrade hint when all pulled models are <14B (too small for reliable tool calling in F8) - **`AiPanel`**: renders a guided setup page (Ollama install steps, ≥14B model table, cloud-provider table, OpenAI-compatible server section) instead of a bare error when no LLM provider is reachable - **Docs** (`camel-jbang-ai.adoc`, `camel-jbang-tui.adoc`): native Ollama install, ≥14B model requirements, tool-calling warning, OpenAI-compatible server section ## Test plan - [ ] `camel doctor` with Ollama running — shows model list - [ ] `camel doctor` with Ollama not running — shows optional hint - [ ] TUI Doctor popup with Ollama running + large model — green OK - [ ] TUI Doctor popup with only small models (e.g. `:8b`) — shows WARN + upgrade hint - [ ] TUI F8 with no provider — setup guide renders with install instructions - [ ] `LLM_API_KEY=x LLM_BASE_URL=http://localhost:1234 camel ask` — routes to custom server Jira: https://issues.apache.org/jira/browse/CAMEL-24631 _Claude Code on behalf of davsclaus_ -- This is an automated message from the Apache Git Service. To respond to the message, please log on to GitHub and use the URL above to go to the specific comment. To unsubscribe, e-mail: [email protected] For queries about this service, please contact Infrastructure at: [email protected]
