OpenAI Codex provider by hannesrudolph · Pull Request #8281 · RooCodeInc/Roo-Code

feat(codex): align validation with optional auth.json path; docs mapping; SSE parser cleanup

hannesrudolph

committed

feat(i18n): add optional auth.json path for ChatGPT Codex in multiple languages

hannesrudolph

committed

feat: integrate override prompt for dynamic instructions in Codex responses

hannesrudolph

committed

feat(openai-native-codex): remove service tier logic; stop forcing minimal effort; add request timeout; improve auth.json error guidance; update ChatGPT link; clear reasoningEffort on model change\…

hannesrudolph

committed

i18n(openai-native-codex): localize provider errors; document immutable Codex system prompt and override rationale\n\n- Add i18n keys under common.errors.openaiNativeCodex and use t() in handler\n-…

hannesrudolph

committed

feat(i18n): add OpenAI Native Codex OAuth error messages in multiple languages

hannesrudolph

committed

fix(codex): improve oauth error guidance and correct comment on default reasoning effort

hannesrudolph

committed

feat(codex): add codex-mini-latest model (fast reasoning, tuned from o4-mini) with pricing and caps

hannesrudolph

committed

refactor(openai-native-codex): address @daniel-lxs review — remove unused const, strengthen typing for message transform and auth.json parsing, extract helpers for testability

hannesrudolph

committed

fix(codex): address @daniel-lxs review — i18n settings, auth.json size guard, remove previous_response_id, avoid as-any reasoning mutation

hannesrudolph

committed

Add OAuth file size error messages and update settings localization for Codex

hannesrudolph

committed

fix(codex): remove unused lastServiceTier property from OpenAiNativeCodexHandler

hannesrudolph

committed

sync: openai-native-codex typing fix for lastServiceTier

hannesrudolph

committed

refactor(codex): remove unused service_tier handling

hannesrudolph

committed

Revert "refactor(codex): remove unused service_tier handling"

hannesrudolph

committed

codex: drop unused lastServiceTier assignments

hannesrudolph

committed

fix(codex): address review feedback and lint errors

hannesrudolph

committed

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

Uh oh!

OpenAI Codex provider#8281

OpenAI Codex provider#8281
hannesrudolph wants to merge 17 commits intomainfrom
feat/openai-native-codex-polish

Commits on Jan 10, 2026

feat(codex): align validation with optional auth.json path; docs mapping; SSE parser cleanup

feat(i18n): add optional auth.json path for ChatGPT Codex in multiple languages

feat: integrate override prompt for dynamic instructions in Codex responses

feat(openai-native-codex): remove service tier logic; stop forcing minimal effort; add request timeout; improve auth.json error guidance; update ChatGPT link; clear reasoningEffort on model change\…

i18n(openai-native-codex): localize provider errors; document immutable Codex system prompt and override rationale\n\n- Add i18n keys under common.errors.openaiNativeCodex and use t() in handler\n-…

feat(i18n): add OpenAI Native Codex OAuth error messages in multiple languages

fix(codex): improve oauth error guidance and correct comment on default reasoning effort

feat(codex): add codex-mini-latest model (fast reasoning, tuned from o4-mini) with pricing and caps

refactor(openai-native-codex): address @daniel-lxs review — remove unused const, strengthen typing for message transform and auth.json parsing, extract helpers for testability

fix(codex): address @daniel-lxs review — i18n settings, auth.json size guard, remove previous_response_id, avoid as-any reasoning mutation

Add OAuth file size error messages and update settings localization for Codex

fix(codex): remove unused lastServiceTier property from OpenAiNativeCodexHandler

sync: openai-native-codex typing fix for lastServiceTier

refactor(codex): remove unused service_tier handling

Revert "refactor(codex): remove unused service_tier handling"

codex: drop unused lastServiceTier assignments

fix(codex): address review feedback and lint errors