customer-support-api / inference.py

Commit History

  1. fix: normalize [END] score to (0,1) range — divide by 4.8 max score, clamp to (0.001, 0.999)

    9f3a7c5
  2. fix: wrap LLM call in try/except with fallback responses to prevent inference.py crash

    49f7113

  1. fix: rewrite inference.py to use LiteLLM proxy via API_BASE_URL/API_KEY env vars

    000a6e7
  2. fix: add [START]/[STEP]/[END] structured output blocks to inference.py for Phase 2 validator

    0261b11
  3. FastAPI OpenEnv server

    a77725d