Adam Perry @ OpenAI 39a99a6c36 Report clock failures again after recovery (#46006) ...

## Why

With `NonfatalClockReadErrors` enabled, a clock failure after a successful read could be suppressed if an earlier failure had already been reported in the same turn and context window. This left the model without a fresh notice that the clock was unavailable again.

## What changed

Clear `last_clock_failure` after a successful clock read so a subsequent outage produces a new notice while consecutive failures remain deduplicated.

## Testing

Add a regression test that scripts two failures, a successful read, and another failure within one turn. It verifies that the consecutive failures share one notice, recovery delivers a time reminder, and the later failure adds a new notice.

GitOrigin-RevId: f2a9c4d7b63f2e8408a47b1803b0bc4577f23f32

2026-09-16 18:54:45 +00:00

..

common

Route Guardian requests through /responses with identifying headers (#45736)

2026-09-15 17:09:11 +00:00

remote_env_windows

Apply remote platform semantics to exec safety checks (#42113)

2026-09-01 18:24:56 +00:00

suite

Report clock failures again after recovery (#46006)

2026-09-16 18:54:45 +00:00

all.rs

[codex] Use expect in integration tests (#28441)

2026-06-15 21:53:47 -07:00

responses_headers.rs

Add workspace routing support for Responses requests (#45812)

2026-09-16 00:20:40 +00:00