prosolis 583616f9d0 llm: route every LLM caller through a shared backend client ...

Replaces the per-plugin Ollama HTTP calls with internal/llm, which picks a
backend from the environment (vLLM or Ollama) behind one Chat interface, plus
internal/plugin/llm_client.go as the plugin-facing wrapper.

Startup now logs llm_backend/llm_endpoint/llm_model instead of the two
OLLAMA_* vars, which no longer describe where inference actually goes.

These files were already running in prod from the vLLM migration but had never
been committed; this is that live state, byte-for-byte.

2026-07-26 10:16:33 -07:00

..

llm.go

llm: route every LLM caller through a shared backend client

2026-07-26 10:16:33 -07:00

ollama.go

llm: route every LLM caller through a shared backend client

2026-07-26 10:16:33 -07:00

ping.go

llm: route every LLM caller through a shared backend client

2026-07-26 10:16:33 -07:00

vllm.go

llm: route every LLM caller through a shared backend client

2026-07-26 10:16:33 -07:00