zero/internal/providers/openai at fix/undo-command - zero

Twigpine/zero

0 Fork 0

mirror of https://github.com/Twigpine/zero.git synced 2026-11-11 13:11:30 -10:00

Files

T

History

Vasanth T 60dc84e7a3 perf(openai): optimized turn session — background prewarm and prefix telemetry (PR8) (#723 )

* trace(perf): add provider prewarm span and prefix-stability counters

* feat(openai): optimized turn session with prewarm and prefix telemetry

* feat(providers): gate optimized OpenAI turn sessions behind env flag

* feat(cli): wire optimized turn sessions into headless exec

* docs(readme): document the optimized OpenAI turn-session toggle

* fix(openai): include tool descriptions in prefix digest, harden gate and test bounds

* fix(openai): isolate prewarm tracing, skip non-reusable transports, fingerprint wire order and cache key

* test(openai): pin keep-alive transports in probe-expecting tests

* feat(providers): preserve resolved capabilities on switched-model fallback sessions

2026-07-18 14:24:50 +05:30

codex_responses.go

fix(providerio): bound heartbeat-but-no-output streams so they can't hang forever (#347 )

2026-06-30 22:19:52 +05:30

codex_terminal_test.go

providers: surface non-normal terminal turns instead of silent empty completions (#263 )

2026-06-20 22:21:12 +05:30

codex_test.go

fix: stream Codex reasoning + drop swarm agents on their own completion (#345 )

2026-06-30 21:21:30 +05:30

codex.go

feat(oauth): Hugging Face + ChatGPT Codex as first-class built-in OAuth presets (#245 )