trading/services/meet_kevin_watcher
Viktor Barzin ed2195d879 feat(meet-kevin): throttle inter-video LLM calls (30s) to stay under Anthropic RPM
First production run hit Anthropic's per-account rate_limit_error (429) trying
to burn through 16 backfill videos in seconds. The SDK's built-in retry can't
recover because the rate limit window resets slower than the 3 retry attempts.

Added meet_kevin_inter_video_sleep_seconds (default 30s) to PipelineDeps and
main's _process_pending_videos loop. 16 backfill videos now take ~8 min (16 * 30s
sleeps + ~30s per LLM call) instead of bursting into the rate limit.
2026-05-22 20:25:19 +00:00
..
__init__.py feat: scaffold meet_kevin_watcher service + config 2026-05-21 19:33:04 +00:00
caption_extractor.py feat(meet-kevin): caption extractor via yt-dlp 2026-05-21 19:40:52 +00:00
config.py feat(meet-kevin): throttle inter-video LLM calls (30s) to stay under Anthropic RPM 2026-05-22 20:25:19 +00:00
llm_analyzer.py refactor(meet-kevin): switch LLM back to native Anthropic SDK with OAuth bearer 2026-05-22 19:24:40 +00:00
main.py feat(meet-kevin): throttle inter-video LLM calls (30s) to stay under Anthropic RPM 2026-05-22 20:25:19 +00:00
pipeline.py feat(meet-kevin): throttle inter-video LLM calls (30s) to stay under Anthropic RPM 2026-05-22 20:25:19 +00:00
rss_poller.py feat(meet-kevin): RSS poller for YouTube uploads 2026-05-21 19:36:22 +00:00