Peter Steinberger
07a7d596ff
feat(providers): add Qwen 3.6 Flash and Gemini 3.1 Live ( #102791 )
...
* feat(providers): add current Qwen and Gemini Live models
* fix(google): align live thinking enum type
* fix(google): align live thinking enum type
2026-07-09 13:37:16 +01:00
Vincent Koc
6e6d1aac4c
test(openai): add focused realtime live smoke
2026-07-06 23:22:33 -07:00
Vincent Koc
c43e020f47
feat(openai): default realtime voice to gpt-realtime-2.1
2026-07-06 23:22:33 -07:00
Peter Steinberger
e643828af6
perf: defer realtime smoke live imports ( #100002 )
2026-07-04 11:52:30 -04:00
Vincent Koc
4575734f59
fix(test): guard realtime perf cli args
2026-06-20 02:34:06 +02:00
Vincent Koc
d97574aae6
fix(dev): bound realtime SDP answer reads
...
Keep the OpenAI Realtime WebRTC smoke's SDP offer request in the browser fetch path while moving the browser-side SDP answer reader into a testable helper. Reject unsafe decimal Content-Length values before acquiring a body reader and preserve streamed byte limiting for responses without a safe declared length.
Proof: direct bounded-reader repro rejects unsafe content-length before getReader and cancels the body; node --check --experimental-strip-types scripts/dev/realtime-talk-live-smoke.ts; node --check --experimental-strip-types test/scripts/dev-tooling-safety.test.ts; git diff --check origin/main...HEAD; autoreview clean overall 0.84; exact-head release gate succeeded at https://github.com/openclaw/openclaw/actions/runs/27848673438 .
2026-06-20 05:22:56 +08:00
Peter Steinberger
b8d08f0cfd
docs: document repository scripts
2026-06-04 20:52:50 -04:00
Peter Steinberger
27dde7a4d6
chore(lint): enable stricter error rules
2026-06-01 01:12:21 +01:00
Peter Steinberger
304e2c83c0
chore(lint): enable stricter oxlint rules
2026-05-31 18:59:02 +01:00
Vincent Koc
6fd8cfd5bb
refactor: share script bounded response reader
2026-05-29 23:02:03 +02:00
Vincent Koc
21bcc0e942
fix(scripts): cap realtime smoke responses
2026-05-29 18:14:59 +02:00
Vincent Koc
e2cebe88ca
fix(dev): bound realtime smoke HTTP waits
2026-05-27 13:46:42 +02:00
Peter Steinberger
4e84229e82
fix: infer realtime smoke dev server type
2026-05-26 21:55:57 +01:00
Vincent Koc
00fc2950d9
chore(scripts): harden dev tooling diagnostics
2026-05-17 17:04:18 +08:00
Colin
7a2a31dede
feat: add realtime voice OAuth controls
2026-05-10 00:13:23 -04:00
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
Peter Steinberger
93bbbe5e37
feat: add browser realtime talk transports
2026-04-27 14:22:32 +01:00
