Add pluggable LLM support with Gemini provider

- Add LLMProvider registry (llm/registry.py) that builds a provider from
  env vars (LLM_PROVIDER, GEMINI_API_KEY, GEMINI_MODEL)
- Add GeminiLLMProvider using the google-genai SDK
- Wire build_llm_provider() into CLI and web pipeline route (replacing llm=None)
- Wrap pass 2 and pass 4 LLM calls in per-combo try/except so API errors
  skip individual combos rather than aborting the whole run
- Add gemini optional dep to pyproject.toml; Dockerfile installs [web,gemini]
- Document env vars in .env.example and README
- Lower requires-python to >=3.10 to match installed system Python

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

src/physcom_web/routes/pipeline.py

@@ -42,9 +42,10 @@ def _run_pipeline_in_background(
             conn.close()
             return
 
+        from physcom.llm.registry import build_llm_provider
         resolver = ConstraintResolver()
         scorer = Scorer(domain)
-        pipeline = Pipeline(repo, resolver, scorer, llm=None)
+        pipeline = Pipeline(repo, resolver, scorer, llm=build_llm_provider())
 
         pipeline.run(
             domain, dim_list,