diff --git a/.agents/notes/implemented/bug-fix/2026-07-20-code-mode-result-card-completeness.i18n.yaml b/.agents/notes/implemented/bug-fix/2026-07-20-code-mode-result-card-completeness.i18n.yaml index 73691b55d9..477e6c571c 100644 --- a/.agents/notes/implemented/bug-fix/2026-07-20-code-mode-result-card-completeness.i18n.yaml +++ b/.agents/notes/implemented/bug-fix/2026-07-20-code-mode-result-card-completeness.i18n.yaml @@ -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-result-card-completeness.md: 85942a564b7e4ff6768bedb040ae4371f48bb665 -2026-07-20-code-mode-result-card-completeness.zh.md: 3e71667de66e017176266fd7f5d82aeabf507c61 +2026-07-20-code-mode-result-card-completeness.md: 9f660c57af2004dff34aeb46a0c37381751163af +2026-07-20-code-mode-result-card-completeness.zh.md: 16149dc6e3d6a830c1bcb5feec2c355496ed3cc0 diff --git a/.agents/notes/implemented/bug-fix/2026-07-20-code-mode-result-card-completeness.md b/.agents/notes/implemented/bug-fix/2026-07-20-code-mode-result-card-completeness.md index 85942a564b..9f660c57af 100644 --- a/.agents/notes/implemented/bug-fix/2026-07-20-code-mode-result-card-completeness.md +++ b/.agents/notes/implemented/bug-fix/2026-07-20-code-mode-result-card-completeness.md @@ -14,13 +14,13 @@ Nested Code calls never owned cards, so producing metadata for the outer call so The canonical tool registry pipeline owns the final model-facing outer content. On success, the `run_code` output renderer renders captured logs followed by the return value or the explicit no-output marker. Runtime failures and pre-execution policy denials are normalized into error content by `ToolRegistry` without invoking that renderer. A post-execute block runs after successful rendering and replaces the result with error content; other post-execute policy and spill decisions may replace content before persistence. -`run_code.presentResult` now forwards the final `result.content` into one generic result card. It deliberately omits the title so the pending card retains the program text. The redundant logs-only `presentationMeta` projection is removed: `tool/result.content` is the durable, replayable, post-policy projection and the card's only result-content source. +`run_code` omits `presentResult`. The established generic result fallback keeps the pending program title and renders the raw final `tool/result.content`; that durable, replayable, post-policy projection is the card's only result-content source. The host API proxy therefore omits a separate result view instead of serializing the same content in both `event.data.content` and `view.view.content`. The redundant logs-only `presentationMeta` projection remains removed. Nested dispatch remains unchanged. Calls marked by `exec.parent` emit bounded `tool/code-dispatch` diagnostics but no `tool/call` or `tool/result` surface cards, so one outer `run_code` invocation still produces exactly one card. ## Testing -Presenter unit coverage pins logs-only, result-only, logs-plus-result, no-output, and spilled-result content. A separate integration-shaped unit drives a real runtime failure through the canonical registry result before presenting it. The successful cases prove stale metadata cannot replace final content; the failure case guards complete forwarding without claiming it reproduced the original metadata-triggered defect. +Tool unit coverage drives logs-only, result-only, logs-plus-result, no-output, spilled-result, and failure outcomes through the canonical registry, then pins the durable content and absence of a result presenter. A host-mux regression uses a call-only presenter to prove the result frame carries raw content exactly once and no view. These cases prove stale metadata cannot replace final content without making the host duplicate that content. The keyless ACP and TUI Code Mode snapshots execute one outer program that performs two nested bash calls, logs `captured output`, and returns `CODE_ONE+CODE_TWO`. Both surfaces show one completed outer card containing both lines and no nested cards. @@ -30,8 +30,10 @@ The keyless ACP and TUI Code Mode snapshots execute one outer program that perfo **Merge presenter metadata with `result.content`.** Rejected because the rendered content already contains the logs; merging would duplicate them and require brittle deduplication. +**Forward `result.content` through a generic result presenter.** Rejected because the durable event already carries that content and ACP/TUI already have a generic raw-content fallback. The host mux serializes a tool-owned result view beside the event, so forwarding would duplicate an unspilled result of up to 64 MiB in one frame merely to recreate the fallback. + **Create one card per nested dispatch.** Rejected because intermediate values are intentionally execution-local and never model-facing. Multiple cards would expose an implementation trace instead of the single Code Mode operation the model and user invoked. ## Consequences -ACP and TUI now display the same complete content the model receives and replay persists, including post-policy spill previews. New `run_code` results no longer carry the optional logs metadata, but this requires no session-format bump: existing records remain valid because the presenter ignores that field and reads their durable rendered content. +ACP and TUI display the same complete content the model receives and replay persists, including post-policy spill previews, through their generic result fallback. The host API retains the pending program title without duplicating the raw result in a separate view payload. New `run_code` results no longer carry the optional logs metadata, but this requires no session-format bump: existing records remain valid because presentation reads their durable rendered content. diff --git a/.agents/notes/implemented/bug-fix/2026-07-20-code-mode-result-card-completeness.zh.md b/.agents/notes/implemented/bug-fix/2026-07-20-code-mode-result-card-completeness.zh.md index 3e71667de6..16149dc6e3 100644 --- a/.agents/notes/implemented/bug-fix/2026-07-20-code-mode-result-card-completeness.zh.md +++ b/.agents/notes/implemented/bug-fix/2026-07-20-code-mode-result-card-completeness.zh.md @@ -14,13 +14,13 @@ Status: implemented 规范的工具注册表流水线负责最终面向模型的外层内容。成功时，`run_code` 输出渲染器先渲染已捕获的日志，然后渲染返回值或显式的无输出标记。运行时失败和执行前策略拒绝由 `ToolRegistry` 归一化为错误内容，过程中不会调用该渲染器。Post-execute 阻断发生在成功渲染之后，并把结果替换为错误内容；其他 post-execute 策略与输出落盘决策可以在持久化之前替换内容。 -`run_code.presentResult` 会把最终的 `result.content` 转交给一张通用结果卡片。它有意省略标题，使待完成卡片保留程序文本。多余的仅含日志的 `presentationMeta` 投影被移除：`tool/result.content` 是持久、可回放且经过 post-policy 处理的投影，也是卡片中结果内容的唯一来源。 +`run_code` 不提供 `presentResult`。既有的通用结果回退机制会保留待完成的程序标题，并渲染原始的最终 `tool/result.content`；这一持久、可回放且经过 post-policy 处理的投影是卡片中结果内容的唯一来源。宿主 API 代理因此不提供单独的结果视图，而不会在 `event.data.content` 与 `view.view.content` 中重复序列化同一内容。冗余的仅含日志的 `presentationMeta` 投影继续保持移除状态。 嵌套分发保持不变。带有 `exec.parent` 标记的调用会发出有界的 `tool/code-dispatch` 诊断，但不会生成与 `tool/call` 或 `tool/result` 对应的界面卡片，因此一次外层 `run_code` 调用仍然只会生成一张卡片。 ## 测试 -展示逻辑的单元测试覆盖仅有日志、仅有结果、日志与结果并存、无输出和结果落盘时的内容。另一个具有集成测试形态的单元测试会触发真实的运行时失败，先让它经过规范注册表形成结果，再交给展示逻辑。成功场景证明陈旧元数据无法替换最终内容；失败场景则保护内容的完整转发，同时不声称它复现了最初由元数据触发的缺陷。 +工具单元测试通过规范注册表覆盖仅有日志、仅有结果、日志与结果并存、无输出、结果落盘和失败的结果，然后固定持久内容以及结果展示器不存在这一事实。宿主 mux 回归测试使用仅有调用的展示器，证明结果帧恰好携带一次原始内容，且不含视图。这些案例证明陈旧元数据无法替换最终内容，同时不会让宿主重复该内容。 无密钥的 ACP 与 TUI Code Mode 快照会执行一个外层程序：程序进行两次嵌套 bash 调用，记录 `captured output`，并返回 `CODE_ONE+CODE_TWO`。两个界面都只显示一张完成态外层卡片，其中包含这两行内容，且没有嵌套卡片。 @@ -30,8 +30,10 @@ Status: implemented **把展示元数据与 `result.content` 合并：**不予采纳。渲染内容已经包含日志；合并会造成重复，还需要依赖脆弱的去重逻辑。 +**通过通用结果展示器转发 `result.content`：**不予采纳。持久事件已经携带该内容，ACP 和 TUI 也已有通用的原始内容回退机制。宿主 mux 会在事件旁序列化工具拥有的结果视图，因此转发仅仅是为了重建该回退机制，却会在一个帧中重复未落盘、最大可达 64 MiB 的结果。 + **为每次嵌套分发创建一张卡片：**不予采纳。中间值有意只存在于执行期间，永远不面向模型。多张卡片会暴露实现轨迹，而不是模型与用户调用的单次 Code Mode 操作。 ## 影响 -ACP 和 TUI 会显示模型接收、回放持久化的同一份完整内容，其中包括 post-policy 输出落盘预览。新的 `run_code` 结果不再携带可选的日志元数据，但无需提升会话格式版本：展示逻辑会忽略该字段并读取记录中持久化的渲染内容，因此现有记录仍然有效。 +ACP 和 TUI 通过通用结果回退机制显示与模型接收及回放持久化相同的完整内容，其中包括 post-policy 输出落盘预览。宿主 API 保留待完成的程序标题，同时不在单独的视图负载中重复原始结果。新的 `run_code` 结果不再携带可选的日志元数据，但无需提升会话格式版本：现有记录仍然有效，因为展示逻辑会读取其中持久化的渲染内容。