refactor(llm-server): serve chat models only - #2336
Open
wqymi wants to merge 1 commit into
Open
Conversation
Drops the /v1/audio/* routes, the speech-only protocol and provider plumbing behind them, and the voice_design/voice_clone model capabilities.
wqymi
force-pushed
the
feat/llm-server-drop-audio
branch
from
September 4, 2026 16:49
9e6ac5d to
86c83c7
Compare
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Summary
mimo llm-server只服务 chat 模型。/v1上只剩GET /models与POST /chat/completions。移除的部分:
POST /v1/audio/speech、POST /v1/audio/transcriptions两条路由,以及它们背后的音频 over-chat 传输层(llm-server/audio-chat.ts)与语音请求协议。llm-server issue --capability与llm-server/capability.ts。issue现在只有--model(可重复,不给即全部配置的模型),JSON 输出相应少了capability/model/alternatives*。getSpeech、speech 模型缓存、SpeechUnsupportedError、isSpeechModel/isTranscriptionModel,以及modelKind/ModelKind与模型能力voiceDesign/voiceClone、配置字段voice_design/voice_clone。openapi.json与 JS SDK 类型已重生。chat 侧的多模态音频输入(
input_audiocontent part)保留——那是对话模型的输入形态。TUI 语音输入不受影响,它直连配置的 ASR 供应商,从不经过这条表面。顺带的整理:
system.test.ts的模板守卫改为断言结构标记加一条绝对家目录路径正则;删掉deep-research技能里引用未随仓库发行脚本的一节;TUI fixture 用/tmp路径;AGENTS.md补一条示例值约定。Verification
bun typecheck（packages/opencode）通过bun test test/llm-server test/provider test/cli test/config test/server test/session/system.test.ts：1197 pass / 4 skip