docs: add model source plan changelog · openclaw/openclaw@7f316b9
shakkernerd
·
2026-04-27
·
via Recent Commits to openclaw:main
| Original file line number | Diff line number | Diff line change |
|---|
@@ -9,6 +9,7 @@ Docs: https://docs.openclaw.ai
|
9 | 9 | ### Changes |
10 | 10 | |
11 | 11 | - Control UI/Talk: add a generic browser realtime transport contract, Google Live browser Talk sessions with constrained ephemeral tokens, and a Gateway relay for backend-only realtime voice plugins. Thanks @VACInc. |
| 12 | +- CLI/models: route provider-filtered model listing through an explicit source plan so user config, installed manifest rows, Provider Index previews, and scoped runtime fallbacks keep a stable authority order without adding another catalog cache. Thanks @shakkernerd. |
12 | 13 | - Providers: add Cerebras as a bundled plugin with onboarding, static model catalog, docs, and manifest-owned endpoint metadata. |
13 | 14 | - Memory/OpenAI-compatible: add optional `memorySearch.inputType`, `queryInputType`, and `documentInputType` config for asymmetric embedding endpoints, including direct query embeddings and provider batch indexing. Carries forward #63313 and #60727. Thanks @HOYALIM and @prospect1314521. |
14 | 15 | - Ollama/memory: add model-specific retrieval query prefixes for `nomic-embed-text`, `qwen3-embedding`, and `mxbai-embed-large` memory-search queries while leaving document batches unchanged. Carries forward #45013. Thanks @laolin5564. |
|
此内容由惯性聚合(RSS阅读器)自动聚合整理，仅供阅读参考。 原文来自 — 版权归原作者所有。
