Andrew Simonson ee885b2390 Handle LLM rate limits gracefully — stop and resume rather than fail ...

- Add LLMRateLimitError to llm/base.py (provider-agnostic)
- GeminiLLMProvider raises it on 429/RESOURCE_EXHAUSTED responses
- Pipeline catches it, marks the run completed (not failed), and returns
  partial results — already-reviewed combos are saved, and re-running
  pass 4 resumes from where it left off

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

2026-02-18 22:36:13 -06:00

..

db

Display metric units in web UI, make seed idempotent, simplify code

2026-02-18 16:18:50 -06:00

engine

Handle LLM rate limits gracefully — stop and resume rather than fail

2026-02-18 22:36:13 -06:00

llm

Handle LLM rate limits gracefully — stop and resume rather than fail

2026-02-18 22:36:13 -06:00

models

Add async pipeline with progress monitoring, resumability, and result transparency

2026-02-18 15:30:52 -06:00

seed

Display metric units in web UI, make seed idempotent, simplify code

2026-02-18 16:18:50 -06:00

__init__.py

Add Flask web UI, Docker Compose, core engine + tests

2026-02-18 13:59:53 -06:00

__main__.py

Add Flask web UI, Docker Compose, core engine + tests

2026-02-18 13:59:53 -06:00

cli.py

Add pluggable LLM support with Gemini provider

2026-02-18 22:04:35 -06:00