snipe/api
pyr0ball 1bf95bba2a feat(llm): migrate query_translator to cf-orch task endpoint for cloud, keep LLMRouter for local (#54)
QueryTranslator now supports two backends chosen at startup:
- CF_ORCH_URL set: allocate via POST /api/inference/task (product=snipe,
  task=query_translation), call the allocated cf-text service, release the
  slot in a finally block to guarantee the VRAM lease is freed.
- CF_ORCH_URL absent: existing LLMRouter path unchanged (ollama/vllm/api keys).

Also moves httpx from dev-only to main dependencies (already used by mcp/server.py).
2026-05-13 15:22:09 -07:00
..
__init__.py feat(snipe): FastAPI layer, Playwright+Xvfb scraper, caching, tests 2026-03-25 20:09:30 -07:00
cloud_session.py refactor: replace hand-rolled JWT+Heimdall with cf-core CloudSessionFactory 2026-04-25 16:35:41 -07:00
ebay_webhook.py fix: authenticate eBay public key fetch + add webhook health endpoint 2026-04-18 22:20:29 -07:00
main.py feat(llm): migrate query_translator to cf-orch task endpoint for cloud, keep LLMRouter for local (#54) 2026-05-13 15:22:09 -07:00