openclaw/docs/providers/openai
Sarah Fortune 4c40118d65
feat(agentsapi): preserve native output and tool history (#156182)
* feat(agentsapi): project native output and reconcile saved history

* fix(agentsapi): retain observed usage after accounting read failures

ClawSweeper: "Retain observed usage when the final REST read fails"
https://github.com/openclaw/openclaw/pull/156182#issuecomment-5789452458

Merge final REST usage with observed usage by admitted turn ID. Canonical
records replace matching contributions, while omitted turns keep observed
usage and repeated accounting does not double count them.

* test(agentsapi): cover projection usage and authoritative session receipts

* refactor(agentsapi): keep projection implementation helpers module-local

* test(agentsapi): use the projection factory and preserve fixture types

---------

Co-authored-by: Sarah Fortune <sarah.fortune@gmail.com>
2026-09-23 21:18:27 -07:00
..
advanced.md fix: prevent premature context overflow after compaction (#149462) 2026-09-15 20:34:31 -07:00
azure.md
coverage-and-cost.md
image-and-video.md feat(openai): support GPT Image 2.5 variants (#143068) 2026-09-09 20:47:22 +09:00
models.md feat(openai): support GPT-6 Sol and Luna (#155967) 2026-09-22 22:11:33 +00:00
runtimes.md feat(agentsapi): preserve native output and tool history (#156182) 2026-09-23 21:18:27 -07:00
setup.md fix: skip official setup approvals and default to Astra (#145646) 2026-09-12 00:34:25 -07:00
voice-and-speech.md feat(voice): share GPT Live across meetings and calls (#146546) 2026-09-12 17:06:51 -07:00