docs(code-mode): align result presentation contract

2026-07-21 21:10:45 +08:00
parent a13c316d2f
commit 60a88114c2
4 changed files with 5 additions and 5 deletions
@@ -42,7 +42,7 @@ Under `'code'` and `'both'` the registry owns `run_code` as a reserved presentat

 1. **Build bindings.** One run-scoped signal follows outer cancellation and is aborted whenever the run settles. Each visible tool binding snapshots lossless-JSON arguments, waits on the serialization queue, executes with a deterministic call id and the outer token as `parent`, defers returned contexts through the outer execution, and logs `tool/code-dispatch`. Success returns the tool's final canonical JSON value; failure becomes the program-visible `ToolCallError`. Every sub-call retains its own immutable execution identity and traverses the full tool pipeline.
 2. **Runs the program**: `ctx.codeRuntime.run({ program: args.code, bindings: [{ global: 'tools', functions }], signal: runController.signal })`. The runtime receives the run-scoped signal, not only the caller's outer signal, so any way the outer run settles also aborts work inside the runtime.
-3. **Settle after quiescence.** When the runtime settles, the bridge aborts outstanding work and drains the dispatch queue before returning. Success returns captured output and presentation metadata. A runtime failure becomes `CodeRunFailedError`; backend rejection uses the registry's normal error boundary. Both produce structured error results, and no sub-call can append after `run_code` settles.
+3. **Settle after quiescence.** When the runtime settles, the bridge aborts outstanding work and drains the dispatch queue before returning. Success returns captured logs and the completion value as canonical output; the registry renders that value into durable `tool/result.content`, which the result card reads directly. A runtime failure becomes `CodeRunFailedError`; backend rejection uses the registry's normal error boundary. Both produce structured error results, and no sub-call can append after `run_code` settles.

 **Sub-call contexts are deferred through the parent.** Injecting inside `run_code` would break parent call/result adjacency, so `ToolRunContext.deferContext()` collects every sub-result `additionalContexts` entry in dispatch order. The registry carries that array even when the program later throws, and the loop appends each entry only after the outer result and every sibling result in the step. An outer post-execute block discards tool-deferred entries and exposes only contexts explicitly attached by the blocking decision.

@@ -2,5 +2,5 @@
 # side as of the last confirmed-consistent state. Both languages carry equal authority;
 # after editing either side, bring the other along and re-record with:
 #   pnpm run verify-translation-pairing --write
-2026-07-20-code-mode-typed-tool-returns.md: 1beecbc9e5f61ac5dce50aeba508ce75cb0ce507
-2026-07-20-code-mode-typed-tool-returns.zh.md: 0dbad69f6b8120e0904f026961b004855d23f3ab
+2026-07-20-code-mode-typed-tool-returns.md: a8503f7a57c0a34624b6e923185078307ece6c68
+2026-07-20-code-mode-typed-tool-returns.zh.md: f2a65286d3eb89ad80920a11dfd14d784d878d35
@@ -75,7 +75,7 @@ Dynamic Cordis mounting follows the same rule: `cordis_mount` returns `{ id, plu

 Nested dispatch keeps the existing bounded `tool/code-dispatch.resultSummary` for diagnostics but does not persist canonical values. `tool/result` continues to persist only rendered content, error, and optional metadata. This is deliberately not a session-format change, so `SESSION_FORMAT_VERSION` remains unchanged and replay cannot recreate intermediate program values.

-The opaque `exec.parent` token marks nested calls. Presentation metadata and generic or tool-owned spill projections skip those calls because they have no direct result card and their canonical values never enter context. The outer `run_code` call alone computes presentation metadata, produces one card, and may spill its final post-policy presentation.
+The opaque `exec.parent` token marks nested calls. Presentation metadata and generic or tool-owned spill projections skip those calls because they have no direct result card and their canonical values never enter context. The outer `run_code` call alone produces one card and may spill its final post-policy presentation; its presenter reads durable `tool/result.content` directly instead of persisting a presentation-metadata copy.

 ## Testing

@@ -75,7 +75,7 @@ worker 暴露的是真正用于 `tools` 绑定失败的 `ToolCallError` 构造

 嵌套分发会为诊断保留既有的有界 `tool/code-dispatch.resultSummary`，但不会持久化规范值。`tool/result` 继续只持久化渲染后的内容、错误和可选元数据。这并非会话格式变更，因此 `SESSION_FORMAT_VERSION` 保持不变，回放也无法重建程序的中间值。

-不透明的 `exec.parent` token 用于标识嵌套调用。由于这些调用没有直接对应的结果卡片，而且其规范值永远不会进入上下文，展示元数据以及通用或工具自有的输出落盘投影都会跳过它们。只有外层 `run_code` 调用会计算展示元数据、生成一张卡片，并且可能将 post-policy 处理后的最终展示写入落盘文件。
+不透明的 `exec.parent` token 用于标识嵌套调用。由于这些调用没有直接对应的结果卡片，而且其规范值永远不会进入上下文，展示元数据以及通用或工具自有的输出落盘投影都会跳过它们。只有外层 `run_code` 调用会生成一张卡片，并且可能将 post-policy 处理后的最终展示写入落盘文件；它的展示逻辑直接读取持久化的 `tool/result.content`，而不是持久化一份展示元数据副本。

 ## 测试