fix(cli): close litellm async clients after each compile/index (CLOSE-WAIT/FD leak)

[cnndabbler]

Problem

add_single_file compiles each document in a fresh asyncio.run() event loop. LiteLLM caches its async (aiohttp) clients per event loop, so when each loop ends the previous doc's clients are abandoned without being closed. Their HTTP connections sit in CLOSE-WAIT and accumulate sockets/file descriptors across a long ingest.

Observed on a 165-document ingest against a remote API: the process held 200+ sockets in CLOSE-WAIT, climbing per doc. (On a box with a low ulimit -n this would eventually exhaust FDs and start failing compilations.)

Fix

Add a best-effort _close_litellm_async_clients() (calls litellm's own close_litellm_async_clients(), never raises) and invoke it in try/finally around the three async entry points in add_single_file:

• index_long_document(...)
• asyncio.run(compile_long_doc(...))
• asyncio.run(compile_short_doc(...))

So cached clients are closed after each doc whether it succeeds or fails.

Verification

Added a doc end-to-end after the change: CLOSE-WAIT returns to ~0 after each doc instead of accumulating. Updated test_add_short_doc_runs_compiler (the compile path now drives asyncio.run for both the compile and the cleanup, so it asserts the compile_short_doc coroutine was run rather than that asyncio.run was called exactly once).

Relation to #44

#44 carried this same intent but is now ~23 commits behind main and conflicts with the current indexer.py/cli.py. This is a minimal reimplementation on current main, so it supersedes #44.