Coder/deepseek-harness
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

docs: sync bilingual pairs and static gates with the message-machine refactor

Browse Source 
The branch edited the English side of 17 doc pairs without their Chinese
counterparts. Bring every .zh.md up to date (loop.ts references now point
at agent.ts, send/steer/inject unification, context/message folded into
user/message, HookContext replaced by UserMessageData in tool decision
blocks, plan/skill delivery moved to agent/step) and re-record the pairing
hashes. Deduplicate type-equiv.manifest.json entries duplicated by the
master merge and drop entries for symbols the refactor removed. Complete
the missing JSDoc on extractSnapshotSpillPaths.
This commit is contained in:
_Kerman
2026-07-26 11:48:06 +08:00
parent 3df3a0dc00
commit 8432c68b6a
35 changed files with 215 additions and 532 deletions
Download Patch File Download Diff File Expand all files Collapse all files

17
docs/core-data-structures/tools.zh.md
View File

@@ -215,7 +215,9 @@ interface ToolRunContext extends ToolExecution {
* the agent loop. Contexts retain their individual source and metadata and
* are emitted in call order.
*/
deferContext(context: HookContext): void
deferContext(context: UserMessageData): void
/** Mark a successful final result as terminal for the current agent turn. */
concludeTurn(): void
}
```
@@ -292,7 +294,9 @@ interface ToolExecutionSuccess {
readonly content: ContentBlock[]
readonly error?: never
readonly meta?: JsonValue
readonly additionalContexts?: HookContext[]
readonly additionalContexts?: UserMessageData[]
/** The agent loop stops after committing this successful result batch. */
readonly concludesTurn?: true
}
```
@@ -304,7 +308,8 @@ interface ToolExecutionFailure {
readonly value?: never
readonly content: ContentBlock[]
readonly meta?: JsonValue
readonly additionalContexts?: HookContext[]
readonly additionalContexts?: UserMessageData[]
readonly concludesTurn?: never
}
```
@@ -340,9 +345,9 @@ type PreToolDecision =
* next request, or block by turning corrective feedback into an error result.
*/
type PostToolDecision =
| { kind: 'accept'; content?: ContentBlock[]; value?: never; additionalContexts?: HookContext[] }
| { kind: 'accept'; value: JsonValue; content?: never; additionalContexts?: HookContext[] }
| { kind: 'block'; feedback: ContentBlock[]; additionalContexts?: HookContext[] }
| { kind: 'accept'; content?: ContentBlock[]; value?: never; additionalContexts?: UserMessageData[] }
| { kind: 'accept'; value: JsonValue; content?: never; additionalContexts?: UserMessageData[] }
| { kind: 'block'; feedback: ContentBlock[]; additionalContexts?: UserMessageData[] }
```
调用 `next()` 获取默认决策，或直接返回一个决策以短路。前置策略可以 deny 或 ask；只有 `allowed-once` 才继续执行，而未授权、缺少审批通道或服务、或无 agent 的请求都会变为拒绝。Guard 仍可施加最终拒绝。参数不可被改写，因为历史记录、审计、UI 和执行必须保持一致。