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>

pyproject.toml

@@ -6,7 +6,7 @@ build-backend = "setuptools.build_meta"
 name = "physcom"
 version = "0.1.0"
 description = "Physical Combinatorics — innovation via attribute mixing"
-requires-python = ">=3.11"
+requires-python = ">=3.10"
 dependencies = [
     "click>=8.1",
 ]
@@ -18,6 +18,9 @@ dev = [
 web = [
     "flask>=3.0",
 ]
+gemini = [
+    "google-genai>=1.0",
+]
 
 [project.scripts]
 physcom = "physcom.cli:main"
@@ -26,5 +29,8 @@ physcom-web = "physcom_web.app:run"
 [tool.setuptools.packages.find]
 where = ["src"]
 
+[tool.setuptools.package-data]
+physcom_web = ["templates/**/*.html", "static/**/*"]
+
 [tool.pytest.ini_options]
 testpaths = ["tests"]