refactor(meet-kevin): switch LLM analyzer to OpenRouter via OpenAI SDK

User's Vault has openrouter_api_key but no direct sk-ant-* Anthropic key.
OpenRouter passes through Claude Sonnet 4.6 (~3% markup over Anthropic
list pricing) and matches the existing gpt_mini_endpoint pattern used
by recruiter-responder.

- Replace anthropic.AsyncAnthropic with openai.AsyncOpenAI + base_url
- Convert Anthropic tool-use API to OpenAI function-calling
- System prompt unchanged (analyst instructions are model-agnostic)
- Drop cache_control (not in OpenAI API); revisit later if cost matters
- Model slug: anthropic/claude-sonnet-4.5 (OpenRouter's current Claude tier)
- Pricing: $3.10/M input, $15.50/M output (OpenRouter pass-through)
- Config field anthropic_api_key -> openrouter_api_key
- pyproject extras: anthropic>=0.40 -> openai>=1.50

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>

services/meet_kevin_watcher/config.py

@@ -18,12 +18,12 @@ class MeetKevinWatcherConfig(BaseConfig):
 
     # LLM analysis settings
     meet_kevin_max_llm_retries: int = 3
-    meet_kevin_llm_model: str = "claude-sonnet-4-6"
+    meet_kevin_llm_model: str = "anthropic/claude-sonnet-4.5"
     meet_kevin_prompt_version: str = "v1"
     meet_kevin_daily_cost_cap_usd: float = 5.0
 
     # API credentials
-    anthropic_api_key: str = ""
+    openrouter_api_key: str = ""
 
     # Runtime settings
     meet_kevin_workdir: str = "/tmp/meet_kevin_captions"