feat(llm): add Gemini CLI provider as primary; set qwen3.5:9b as default Ollama model

- Add GeminiCliProvider: shells out to `gemini -p` with --output-format json,
  injection-safe prompt passing, MCP server suppression via temp workdir,
  6-slot concurrency semaphore, 60s subprocess deadline
- Add --llm-provider, --llm-model, --llm-base-url CLI flags for per-call overrides
- Provider chain: Gemini CLI → OpenAI → Ollama → Anthropic
- Move LLM timing to dispatch layer (LLM: Xs on stderr)
- Default Ollama model: qwen3:8b → qwen3.5:9b (benchmark shows better schema extraction)
- Add noxa mcp subcommand
- Add docs/reports/llm-benchmark-2026-04-11.md (Gemini vs qwen3.5:4b vs qwen3.5:9b)
- Bump version 0.3.11 → 0.4.0

Co-authored-by: Claude <claude@anthropic.com>

.codex-plugin/plugin.json

@@ -0,0 +1,19 @@
+{
+  "name": "noxa",
+  "version": "0.4.0",
+  "description": "noxa CLI, MCP server, and skills for AI-assisted web extraction",
+  "author": {
+    "name": "jmagar"
+  },
+  "homepage": "https://noxa.io",
+  "repository": "https://github.com/jmagar/noxa",
+  "license": "AGPL-3.0",
+  "keywords": ["web", "extraction", "mcp", "ai"],
+  "skills": "./skills/",
+  "mcpServers": "./.mcp.json",
+  "interface": {
+    "displayName": "noxa",
+    "shortDescription": "AI-assisted web extraction",
+    "longDescription": "Bundle the noxa skill and MCP server for Codex workflows."
+  }
+}