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

refactor: prune core tool and prompt surface

Browse Source
This commit is contained in:
Tianyi Cui
2026-07-14 02:54:30 +08:00
parent a0359bc4a9
commit 0236a12324
21 changed files with 50 additions and 139 deletions
Download Patch File Download Diff File Expand all files Collapse all files

3
docs/core-data-structures/tools.md
View File

@@ -137,7 +137,6 @@ type ToolGuard = (execution: Readonly<ToolExecution>) => string | undefined
```ts type-equiv
interface ToolExecutionResult {
callId: CallId
content: ContentBlock[]
isError: boolean
/**
@@ -167,6 +166,8 @@ interface ToolExecutionResult {
}
```
The result carries only the outcome. Call identity remains on the immutable `ToolExecution` that accompanies it through every hook and on the durable `tool/call` / `tool/result` session events, so wrappers cannot create a second, disagreeing identity.
The registry materializes and freezes the final accepted result immediately before `tools/result`. Its content, structured error, additional context, and presentation metadata must round-trip losslessly through JSON; an invalid outcome becomes a JSON-safe `isError` result, so the observed live outcome is safe for the later durable `tool/result` append.
Each interception waterfall returns a typed **Decision** (the idiom shared with the `agent/*` seams). `tools/pre-execute` listeners receive `(exec, next)` and return a `PreToolDecision`; `tools/execute` wrappers return a `ToolExecutionResult`; `tools/post-execute` listeners receive `(exec, result, next)` and return a `PostToolDecision`: