fix: route Android Talk synthesis through the gateway (#50849)
This commit is contained in:
parent
47e412bd0b
commit
61965e500f
@ -45,6 +45,7 @@ Docs: https://docs.openclaw.ai
|
||||
- Plugins/context engines: expose `delegateCompactionToRuntime(...)` on the public plugin SDK, refactor the legacy engine to use the shared helper, and clarify `ownsCompaction` delegation semantics for non-owning engines. (#49061) Thanks @jalehman.
|
||||
- Plugins/MiniMax: add MiniMax-M2.7 and MiniMax-M2.7-highspeed models and update the default model from M2.5 to M2.7. (#49691) Thanks @liyuan97.
|
||||
- Plugins/Xiaomi: switch the bundled Xiaomi provider to the `/v1` OpenAI-compatible endpoint and add MiMo V2 Pro plus MiMo V2 Omni to the built-in catalog. (#49214) thanks @DJjjjhao.
|
||||
- Android/Talk: move Talk speech synthesis behind gateway `talk.speak`, keep Talk secrets on the gateway, and switch Android playback to final-response audio instead of device-local ElevenLabs streaming. (#50849)
|
||||
- Plugins/Matrix: add `allowBots` room policy so configured Matrix bot accounts can talk to each other, with optional mention-only gating. Thanks @gumadeiras.
|
||||
- Plugins/Matrix: add per-account `allowPrivateNetwork` opt-in for private/internal homeservers, while keeping public cleartext homeservers blocked. Thanks @gumadeiras.
|
||||
- Web tools/Tavily: add Tavily as a bundled web-search provider with dedicated `tavily_search` and `tavily_extract` tools, using canonical plugin-owned config under `plugins.entries.tavily.config.webSearch.*`. (#49200) thanks @lakshyaag-tavily.
|
||||
|
||||
Loading…
x
Reference in New Issue
Block a user