Commit Graph

6 Commits

Author SHA1 Message Date
Mark Backman
86c2dd5cfc Remove processing metrics (ProcessingMetricsData)
Processing metrics were an early addition that predated a clear
understanding of what timing measurements matter in real-time pipelines.
They were inconsistently implemented across services, often broken, and
overlapped with the better-defined TTFB metric.

- Remove ProcessingMetricsData class and all start/stop_processing_metrics
  methods from FrameProcessorMetrics, FrameProcessor, and SentryMetrics
- Remove all processing metrics calls from 31 service files (LLM, TTS,
  STT, image, vision, realtime)
- Clean up empty _start_metrics() stubs left in STT services
- Remove processing metrics handling from RTVI, metrics log observer,
  pipeline task initial metrics, and strands agents framework
- Update tests and examples

Remaining metrics (TTFB, LLM token usage, TTS character usage, text
aggregation time) are well-defined and consistently implemented.
2026-02-26 18:20:49 -05:00
Luke Payyapilli
247f0bbcd3 Fix async generator cleanup to prevent uvloop crash on Python 3.12+ 2026-02-17 13:10:31 -05:00
Aleix Conchillo Flaqué
93f4402198 Update stream close test to match new _closing helper 2026-02-10 18:19:57 -08:00
Luke Payyapilli
55a3b10e70 fix(openai): close stream on cancellation to prevent socket leaks 2026-02-04 09:59:10 -05:00
Luke Payyapilli
433c1b9b92 add catch-all exception handler per review feedback 2026-01-29 09:07:06 -05:00
Luke Payyapilli
ff0eb6d286 fix: emit ErrorFrame on LLM completion timeout 2026-01-28 09:44:32 -05:00