fix(llm): validate the /health body and identify OpenAI-compatible runners

[sosidudku1]

Closes #65, closes #66.

What actually happened in #65

KoboldCpp serves its web UI with HTTP 200 on every path, including /health. The external-URL probe treated any 200 as success, so it passed falsely, the chat route switched onto a server the llama.cpp client cannot drive, and the next call hung while the busy flag ate the keyboard. That is the permanent freeze the reporter described for http://localhost:5001. With /v1 appended the downstream call failed fast instead, which is why that variant unfroze after seconds. (The earlier theory in the issue thread blamed probe retries; the probe on this path already ran a single 8s attempt, the hang lived after the false pass.)

Change

1. A 200 on /health is no longer enough. The body must carry llama.cpp's JSON shape (a status string; ok and loading model both count). KoboldCpp's HTML now fails the probe instead of hijacking the route.
2. A second probe identifies OpenAI-compatible runners. When /health says no, {base}/v1/models is asked; a JSON answer with a data array marks the result kind: "openai-compat" (KoboldCpp, LM Studio, vLLM all match). The external llama.cpp route genuinely cannot drive these servers, so passing them through would only move the hang one step later.
3. The save path talks. probing <url> is emitted immediately (an 8s silent probe reads as a freeze), and an openai-compat answer produces an actionable message: add the server as a cloud provider, base URL included, which is the path that actually works for these runners today.

Testing

New llama-server-health.test.ts (the module had no tests): real llama /health accepted, loading model accepted, KoboldCpp-style HTML 200 rejected with a clear error, the /v1/models fallback identifying an OpenAI-compatible runner, network failure reporting unknown, and retry short-circuiting on first success.

All probe consumers pass unchanged: src/llm, src/tui/llm-health, src/http, src/runtime — 356 tests. tsc clean. Full suite shows the same 8 pre-existing failures as main.