LlamaIndex-Event-Handler

You are adding Execlave (an AI agent governance platform) to an existing Python project that uses LlamaIndex. Do not rewrite existing indexes, retrievers, or query engines — only attach instrumentation. Rules you MUST follow:1. Install the correct extra: `pip install 'execlave-sdk[llamaindex]'`. Add it to requirements.txt / pyproject.toml.2. Read `EXECLAVE_API_KEY` from environment variables. Never hardcode keys. Add it to `.env.example`.3. Create exactly ONE Execlave client per process and reuse it: `exe = Execlave(api_key=os.environ["EXECLAVE_API_KEY"])`.4. Register the handler ONCE at app start, not per request:   ```   from llama_index.core.instrumentation import get_dispatcher   from execlave.integrations.llamaindex import ExeclaveLlamaIndexHandler   handler = ExeclaveLlamaIndexHandler(exe, agent_id="<stable-kebab-id>")   get_dispatcher().add_event_handler(handler)   ```5. `agent_id` is a stable kebab-case string identifying this app in the Execlave dashboard.6. Wrap `query_engine.query()` / `agent.chat()` in try/except for `execlave.errors.PolicyBlockedError`. On block, return a structured 4xx response containing `exc.violations`. Do NOT swallow the error.7. Do NOT call `exe.enforce_policy` manually — the handler runs enforcement on `QueryStartEvent` and `AgentToolCallEvent`.8. On process shutdown (ASGI lifespan / SIGTERM handler), call `exe.flush()`. Deliverables:- One diff per file. Touch only app bootstrap and the entry-point that runs queries.- Add `EXECLAVE_API_KEY` and optional `EXECLAVE_BASE_URL` to `.env.example`. Reference: https://www.execlave.com/docs/integrations/llamaindexAPI reference: https://www.execlave.com/docs/sdk-reference