pashpashpash
02fe0d8978
Keep OpenAI Codex migrations on automatic runtime routing ( #79238 )
...
* fix: keep migrated openai codex routes automatic
* scope runtime policy to providers and models
* fix runtime policy surfaces
* fix ci runtime policy checks
* fix doctor stale session runtime pins
2026-05-08 16:05:35 +09:00
Peter Steinberger
b75e5c50bf
docs: document OpenAI realtime voices
2026-05-08 01:07:46 +01:00
Peter Steinberger
63ec912786
fix(openai): use GA realtime bridge for gpt-realtime-2
...
Summary:
- switch OpenAI realtime voice default to gpt-realtime-2
- migrate backend OpenAI WebSocket bridge to the GA session shape and drop the beta header
- keep Azure deployment realtime bridges on the deployment-compatible shape
- extend live Talk smoke coverage and align npm Telegram package-runtime assertions
Verification:
- pnpm test extensions/openai/realtime-voice-provider.test.ts src/gateway/protocol/index.test.ts src/gateway/talk-handoff.test.ts extensions/google-meet/index.test.ts -- --reporter=dot
- pnpm test test/scripts/npm-telegram-live.test.ts -- --reporter=dot
- pnpm check:docs
- env OPENCLAW_TESTBOX=0 pnpm check:changed
- OPENCLAW_REALTIME_OPENAI_MODEL=gpt-realtime-2 node --import tsx scripts/dev/realtime-talk-live-smoke.ts
2026-05-08 00:47:25 +01:00
pashpashpash
1c33990108
Route OpenAI agents through Codex by default ( #78899 )
...
* route openai agent runs through codex
* fix: load codex plugin for implicit openai runtime
* fix: preserve explicit OpenAI PI Codex auth routing
* fix: show codex auth for openai model listing
* fix: map codex auth into configured openai list rows
* fix: preserve explicit openai pi auth routes
* docs: keep openai model route examples canonical
* fix: clean openai codex test fixtures
* fix: scope codex auth status fallback
* fix: repair current ci boundary drift
2026-05-07 19:46:49 +09:00
Vincent Koc
f2b01bb7b1
feat(openai): add chat-latest model override
...
Add openai/chat-latest as an explicit direct API-key OpenAI model override, document the moving alias, and normalize unsupported Responses text verbosity for that model.
2026-05-07 03:09:16 -07:00
pashpashpash
3a901b5e95
Revert "Install Codex plugin on OpenAI model selection ( #78799 )" ( #78878 )
...
This reverts commit c8f3fecad6
2026-05-07 18:13:59 +09:00
pashpashpash
c8f3fecad6
Install Codex plugin on OpenAI model selection ( #78799 )
...
* route openai agent runs through codex
* fix: load codex plugin for implicit openai runtime
* docs: credit openai codex auth fix
* fix(agents): respect custom openai runtime routing
* fix(agents): install codex plugin on openai selection
* fix(agents): preserve OpenAI Codex auth switching
* fix(ci): restore channel contract runner expression
---------
Co-authored-by: Vincent Koc <vincentkoc@ieee.org >
2026-05-07 01:57:34 -07:00
Peter Steinberger
11a0b1248d
docs: clarify Codex OAuth hotfix recovery
2026-05-06 19:01:41 +01:00
Peter Steinberger
5cf55ed3f1
fix(openai): suppress stale Codex OAuth models
2026-05-06 09:38:07 +01:00
pashpashpash
8f4eaa9c00
Stop heartbeat tool turns from asking for HEARTBEAT_OK ( #76338 )
...
* fix heartbeat tool prompt sentinel
* fix: remove agent runtime fallback config
2026-05-03 13:46:26 +09:00
pashpashpash
8adbee3a68
docs: fix codex strict json examples ( #75916 )
2026-05-02 15:30:34 +09:00
pashpashpash
9fb90f3d29
docs: clarify Codex subscription runtime ( #75910 )
2026-05-02 11:33:20 +09:00
Peter Steinberger
5e3265b09b
feat: support openai tts extra body
2026-05-01 22:57:35 +01:00
Peter Steinberger
3766bbb674
fix(models): restore codex mini oauth route
2026-04-30 14:43:39 +01:00
Peter Steinberger
dc6031197b
fix(models): hide unsupported codex mini route
2026-04-28 06:43:51 +01:00
pashpashpash
401ae38f13
fix(codex): keep env fallback local to stdio app-server
2026-04-28 00:46:15 +01:00
Peter Steinberger
5f15bea6ce
fix(codex): bootstrap app-server auth fallback
2026-04-28 00:46:15 +01:00
Peter Steinberger
93bbbe5e37
feat: add browser realtime talk transports
2026-04-27 14:22:32 +01:00
Peter Steinberger
775ed36c16
feat(memory): support asymmetric embedding input types
2026-04-27 11:25:40 +01:00
Peter Steinberger
5b9be2cdb1
fix: migrate agent runtime config
2026-04-26 08:12:44 +01:00
Peter Steinberger
6d4f65c9d4
docs: clarify codex runtime routing
2026-04-26 04:38:39 +01:00
Peter Steinberger
6336ed4166
fix: gate codex acp route hints
2026-04-26 04:36:26 +01:00
Peter Steinberger
ed5276f9b9
fix(providers): keep vllm nemotron replies visible
2026-04-26 03:54:20 +01:00
Peter Steinberger
e4bfc8066e
fix(openai): extend Azure image timeout
...
Closes #71705
2026-04-25 23:34:18 +01:00
Peter Steinberger
75d64cd4b8
feat: expose generic image background option
2026-04-25 20:21:46 +01:00
Peter Steinberger
b66f01bdca
fix: expose transparent image infer options
2026-04-25 19:58:41 +01:00
Peter Steinberger
de0097a23c
fix: support transparent OpenAI image generation
2026-04-25 19:28:56 +01:00
Peter Steinberger
768bbc7cc0
docs: update OpenAI GPT-5.5 API guidance
2026-04-25 18:14:10 +01:00
pashpashpash
6cfe810402
Refresh the Codex runtime docs
...
Refresh the Codex runtime docs and cross-link the Codex harness, OpenAI provider, agent runtime, plugin hook, ACP agent, and status pages.
2026-04-24 20:30:33 -07:00
Peter Steinberger
49f72b332f
fix: harden openai-compatible completions payloads
2026-04-25 03:29:26 +01:00
Vincent Koc
aa27e27f36
fix(models): normalize provider runtime selection ( #71259 )
...
* fix(models): normalize provider runtime selection
* fix(models): reverse codex-only runtime migration
* fix(models): default runtime selection to pi
* fix(status): label model runtime clearly
* fix(status): align pi runtime label
* fix(plugins): align tool result middleware runtime naming
* fix(models): validate runtime overrides
2026-04-24 16:56:49 -07:00
Peter Steinberger
b2352c3e24
docs: improve 2026.4.23 release docs
2026-04-24 17:55:03 +01:00
Peter Steinberger
6c509d8d4b
docs: clarify codex plugin auto-enable boundary
2026-04-24 06:38:54 +01:00
Peter Steinberger
04066d246a
feat: add browser realtime talk
2026-04-24 03:33:36 +01:00
Peter Steinberger
3aa3551491
test: cover OpenAI server compaction docs
2026-04-24 03:15:47 +01:00
Peter Steinberger
d16b879334
fix: allow private OpenAI image endpoints
2026-04-24 00:36:00 +01:00
Peter Steinberger
14c4143723
docs: clarify OpenAI GPT-5.5 auth routes
2026-04-23 23:49:17 +01:00
Peter Steinberger
38f157a148
fix(openai): prefer configured Codex OAuth for images
2026-04-23 22:49:37 +01:00
Peter Steinberger
ddcc39de91
fix(openai): reuse Codex OAuth for OpenAI images
2026-04-23 22:06:36 +01:00
Peter Steinberger
8af3d91668
docs(openai): clarify codex oauth image generation
2026-04-23 21:47:33 +01:00
Peter Steinberger
c84a2f5244
feat(openai): add codex oauth image generation
2026-04-23 21:34:24 +01:00
Peter Steinberger
bb63f3c26b
docs: document embedded harness status indicator
2026-04-23 21:17:20 +01:00
Peter Steinberger
f6336c5521
fix(openai): retire removed Codex Spark model
2026-04-23 21:16:46 +01:00
Vincent Koc
4a2cd533ac
docs: remove duplicate H1 where frontmatter title already sets it
2026-04-23 13:11:14 -07:00
Peter Steinberger
a8173276bf
docs(openai): canonicalize GPT model refs
2026-04-23 20:47:38 +01:00
Peter Steinberger
89051c6bf6
docs(openai): document GPT-5.5 defaults
2026-04-23 20:19:15 +01:00
Peter Steinberger
e9405318b4
fix(openai): default realtime voice to gpt-realtime-1.5
2026-04-23 19:39:24 +01:00
Peter Steinberger
79d8ce730a
docs: fix OpenAI provider compaction reference
2026-04-23 17:53:36 +01:00
Vincent Koc
b3ca4e088e
docs(providers): openai — drop stray anchor tag, consolidate trailing azure notes
2026-04-23 09:48:48 -07:00
Otto Deng
bc01cbb8a2
docs(providers/openai): document Azure OpenAI endpoint usage for image generation ( #70501 )
...
Verified:
- pnpm lint:docs
- Resolved bot review comments around Azure docs scope and accuracy
2026-04-23 07:48:54 -05:00
