mirror of
https://github.com/deepseek-ai/deepseek-harness
synced 2026-08-15 21:04:50 +00:00
refactor: narrow web image input v1
This commit is contained in:
@@ -122,7 +122,7 @@ interface ContentBlockMap {
|
||||
}
|
||||
```
|
||||
|
||||
各块接口(完整字段见源码):`TextBlock`(`text`)、`ReasoningBlock`(thinking,区别于可见文本)、`ImageBlock`(一个持久的[图像附件](attachment.md),外加可选的替代文本)、`ToolCallBlock`(`id: CallId`、`name`、原始 JSON `arguments`),以及 `ToolResultBlock`(`toolCallId`、嵌套 `content: ContentBlock[]`、`isError?`)。`ContentBlock = ContentBlockMap[ContentBlockType]`。仅当适配器、UI、压缩和持久回放路径均支持某种新模态时,才将其纳入可合并扩展的 map。
|
||||
各块接口(完整字段见源码):`TextBlock`(`text`)、`ReasoningBlock`(thinking,区别于可见文本)、`ImageBlock`(一个持久的[图像附件](attachment.md))、`ToolCallBlock`(`id: CallId`、`name`、原始 JSON `arguments`),以及 `ToolResultBlock`(`toolCallId`、嵌套 `content: ContentBlock[]`、`isError?`)。`ContentBlock = ContentBlockMap[ContentBlockType]`。仅当适配器、UI、压缩和持久回放路径均支持某种新模态时,才将其纳入可合并扩展的 map。
|
||||
|
||||
源码:[`packages/llm/llm/src/message.ts`](../../packages/llm/llm/src/message.ts)
|
||||
|
||||
@@ -212,8 +212,6 @@ interface LlmModelInfo {
|
||||
description?: string
|
||||
/** Accepted request modalities; absent means unknown, while an explicit omission is negative capability. */
|
||||
inputModalities?: readonly ModelModality[]
|
||||
/** Structured response modalities; absent means unknown, while an explicit omission is negative capability. */
|
||||
outputModalities?: readonly ModelModality[]
|
||||
}
|
||||
```
|
||||
|
||||
|
||||
Reference in New Issue
Block a user