dc6031197b
fix(models): hide unsupported codex mini route
2026-04-28 06:43:51 +01:00
2ff7eb36cf
fix(models): expose codex runtime context caps
2026-04-25 07:38:31 +01:00
713807b55d
fix: harden openai auth and reasoning replay
2026-04-25 03:10:24 +01:00
33c0cd1378
fix: improve codex model discovery
2026-04-24 08:17:01 +01:00
79066f5cab
fix(openai): synthesize codex gpt-5.5 oauth model
2026-04-24 01:49:00 +01:00
f04a3dced0
build: update Pi model dependencies
2026-04-24 01:24:46 +01:00
ff56a9d41b
test(openai): prefer canonical GPT refs
2026-04-23 20:47:39 +01:00
cd5bc2fc93
test(openai): cover GPT-5.5 defaults
2026-04-23 20:19:15 +01:00
2c25e1d58d
fix(openai): align auth picker copy metadata
2026-04-23 05:06:16 +01:00
edea0cba7a
fix(openai): align auth picker labels for API key vs Codex OAuth
...
Lock regression coverage for current OpenAI API key, Codex browser login, and Codex device pairing auth picker labels.\n\nThanks @tmlxrd.
2026-04-23 04:48:55 +01:00
1e8564cb13
fix(auth-profiles): repair stale codex oauth profiles
2026-04-23 04:03:47 +01:00
6f6fa5c90b
Remove Codex CLI auth import
2026-04-22 19:27:52 -07:00
da86ce7887
feat(openai): add codex device-code auth and fix login options in menu ( #69557 )
...
Merged via squash.
Prepared head SHA: 4918ed69f125068+vincentkoc@users.noreply.github.com >
Co-authored-by: BunsDev <68980965+BunsDev@users.noreply.github.com >
Reviewed-by: @BunsDev
2026-04-22 02:47:20 -05:00
c197b3fef4
fix(openai-codex): normalize legacy copilot transport
2026-04-21 08:03:31 +01:00
97534372f8
fix(openai-codex): normalize completions transport drift
2026-04-21 07:58:25 +01:00
8a2d7f2541
fix(openai-codex): use /backend-api/codex/ base URL
...
OpenAI removed the /backend-api/responses alias on chatgpt.com server-side.
The OpenAI SDK appends /responses to the configured baseUrl, so OpenClaw's
current baseUrl ("https://chatgpt.com/backend-api ") now resolves to
/backend-api/responses and hits a Cloudflare HTML 403 block page. The
provider's 403+HTML error classifier then surfaces this as an auth-scope
failure, triggering fruitless OAuth re-login loops for every GPT-5.4
sub-agent call.
- Point OPENAI_CODEX_BASE_URL at https://chatgpt.com/backend-api/codex
(both the catalog constant and the sibling local constant in the provider).
- Extend isOpenAICodexBaseUrl to accept the new /codex segment while keeping
the legacy path recognized so pre-existing user configs and persisted
model metadata still round-trip through the normalizer correctly.
- Add positive-case test coverage for the new base URL; update existing
normalization tests whose expected canonical output now includes /codex.
Verified with live curl using the exact OAuth access token stored by
OpenClaw: the /codex/responses path returns HTTP 200 with streaming SSE,
while the old /responses alias returns HTTP 403 HTML regardless of auth
headers. Scoped tests (base-url, openai-codex-provider, transport-policy,
openai-provider, index) pass; pnpm tsgo and pnpm build are clean.
2026-04-21 03:19:58 +01:00
4ea6e426cd
test: share openai codex model fixtures
2026-04-20 18:11:35 +01:00
2fc429dfbf
fix: keep codex oauth bridge extension-owned ( #68284 ) (thanks @vincentkoc)
2026-04-18 21:27:27 +01:00
b2ca265f11
test(openai): align codex import profile expectation
2026-04-18 21:27:27 +01:00
a018257487
fix(auth): harden codex oauth bridge security
2026-04-18 21:27:27 +01:00
859eb06662
refactor(auth): route codex runtimes through canonical oauth
2026-04-18 21:27:27 +01:00
90801ba400
fix(openai-codex): normalize stale transport metadata in resolution and discovery ( #67635 )
...
Merged via squash.
Supersedes:
- #66969 by @saamuelng601-pixel
- #67159 by @hclsys
Co-authored-by: saamuelng601-pixel <274746699+saamuelng601-pixel@users.noreply.github.com >
Co-authored-by: hclsys <7755017+hclsys@users.noreply.github.com >
2026-04-16 14:30:05 +03:00
5a5ca6d62c
feat(codex): add gpt-5.4-pro forward compat ( #66453 )
...
* feat(openai-codex): add gpt-5.4-pro forward-compat #63404
* feat(openai-codex): add gpt-5.4-pro forward-compat #63404
* openai-codex: use patch.cost when forward-compat falls back to normalizeModelCompat
* feat(codex): add gpt-5.4-pro forward compat
* fix(codex): reuse gpt-5.4 fallback for gpt-5.4-pro
---------
Co-authored-by: jepson-liu <jepsonliu@gmail.com >
2026-04-14 11:05:24 +01:00
b90d4ea3d7
fix(codex): canonicalize the gpt-5.4-codex alias ( #66438 )
...
* fix(codex): canonicalize the gpt-5.4-codex alias
* Update CHANGELOG.md
2026-04-14 09:56:58 +01:00
41243529fb
refactor(providers): centralize provider model policy
2026-04-04 06:16:48 +01:00
585b1c9413
fix(ci): repair openai codex provider test syntax
2026-04-04 04:27:02 +01:00
a23ab9b906
refactor: move voice-call realtime providers into extensions
2026-04-04 12:07:23 +09:00
6b3ff0dd4f
feat(openai): add codex gpt-5.4-mini support
2026-04-04 11:51:57 +09:00
f8a3840a42
fix(ci): restore contextTokens runtime typing
2026-04-04 02:00:19 +01:00
58d2b9dd46
fix: add runtime model contextTokens caps
2026-04-04 09:36:53 +09:00
f7285e0a9e
test: speed up extension suites
2026-03-31 02:25:02 +01:00
ef1784d264
refactor: move bundled plugin policy into manifests
2026-03-27 16:40:27 +00:00
17203d0af9
fix: stabilize codex oauth refresh tests
2026-03-27 04:44:43 +00:00
Peter Steinberger