Tom Houlé 5e717a06cd open_ai: Support fast mode in BYOK via the Responses API service_tier (#57412) ... Maps the existing `Speed::Fast` plumbing to OpenAI's `service_tier: "priority"`, which matches what "fast mode" in Codex does. Relevant docs [here](https://platform.openai.com/docs/api-reference/chat/create#chat-create-service_tier). Like for the existing Anthropic fast mode we have a `Model::supports_priority` method for the variants on https://openai.com/api-priority-processing. Pro, nano, and legacy gpt-4 are excluded; Custom defaults to false. This is gated to staff only for now (not in this diff, but the existing fast mode feature), until we have the mechanism to require confirmation before you enable fast mode. Release Notes: - Added support for Fast Mode (priority service tier) on the OpenAI API provider.		2026-05-27 09:17:23 +00:00
..
benches	Track additional metrics in settled (#52938)	2026-04-08 18:39:17 -04:00
license_examples	Reorganize edit prediction code and remove old experiments (#44187)	2025-12-04 15:56:57 -08:00
license_patterns	Reorganize edit prediction code and remove old experiments (#44187)	2025-12-04 15:56:57 -08:00
src	open_ai: Support fast mode in BYOK via the Responses API service_tier (#57412)	2026-05-27 09:17:23 +00:00
Cargo.toml	Move edit prediction metrics into shared crate (#53912)	2026-04-14 21:04:10 +03:00
LICENSE-GPL	Rename remaining mentions of "inline completion" to "edit prediction" (#35512)	2025-08-04 16:22:18 +00:00