Merge branch 'worktree/ci-native-windows-20260808' into worktree/ci-native-windows-coverage-20260808
# Conflicts: # packages/subagent/subagent-codex/README.i18n.yaml # packages/subagent/subagent-codex/README.md # packages/subagent/subagent-codex/README.zh.md
This commit is contained in:
Tianyi Cui
@@ -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 .agents/notes/implemented/feature/2026-06-15-code-mode.md
|
||||
2026-06-15-code-mode.md: 8a6fa068a4c7fee6fbfd9e16757a0fae5efa0c8b
|
||||
2026-06-15-code-mode.zh.md: 00d4fd48b83e183d45423722bf223a63e305d5a4
|
||||
2026-06-15-code-mode.md: 5ad7be9506c2356f90050b86d85aa77f602946ce
|
||||
2026-06-15-code-mode.zh.md: 1902c6ba86b6b8d3fecd06c417347a9c082f67b4
|
||||
|
||||
@@ -30,7 +30,7 @@ This note owns Code Mode's presentation, composition, isolation, and settlement
|
||||
|
||||
**Wire tool list.** The registry contributes visible capabilities in `'native'`, only `run_code` in `'code'`, and both in `'both'`. The final `PromptAssembly.tools` list is logged in the request header. `run_code` is a reserved presentation transport outside registration and restriction layers; direct prompt providers and the assembly waterfall remain responsible for their own contributions.
|
||||
|
||||
**Interaction with `toolOrder`, stated up front:** a configured `systemPrompt.toolOrder` naming native capabilities rejects every assembly under `mode: 'code'`, because those names are outside that mode's wire-validation universe. This is correct behavior, not a bug: a deployment using Code Mode updates its order config or drops it.
|
||||
**Interaction with `toolOrder`:** a configured `systemPrompt.toolOrder` naming native capabilities rejects every assembly under `mode: 'code'`, because those names are outside that mode's wire-validation universe. This is correct behavior, not a bug: a deployment using Code Mode updates its order config or drops it.
|
||||
|
||||
**SDK prompt section.** In `'code'` and `'both'`, the lazy `tools:sdk` section in the tool-guidance order band renders the loaded runtime's language declarations plus fixed usage instructions for the scope's visible capabilities (TypeScript by default; the [language-dispatch note](2026-07-31-code-mode-language-dispatch.md) added Python and the `ctx.codeRuntime.language` renderer table). It shares lookup and execution visibility, excludes `run_code`, and sorts tools lexicographically for byte-stable output.
|
||||
|
||||
@@ -106,7 +106,7 @@ Deployments switching to `'code'` must update any native-only `toolOrder`. Assem
|
||||
|
||||
**Result elision / summarization over native tool-calling.** Addresses only the context-bloat half of the problem: trimming old `tool-result`s is cheap to add as a logged surface replacement under reconstructable requests, but still pays one model round-trip per call and cannot express loops, branches, or joins. Complementary, not competing; it can layer under Code Mode for residual native calls.
|
||||
|
||||
**Parallel native dispatch in the loop.** The other answer to round-trip cost at decision time; it was blocked on concurrency-safety metadata and offers no composition either way — it parallelizes calls the model already decided on in one step. Code Mode's queue decision kept the two compatible, and that is how it played out: the metadata landed as `isConcurrencySafe` (the [parallel tool-call note](2026-07-10-parallel-tool-call-execution.md)), and native rolling-pool dispatch and per-tool binding parallelism unlocked on the same classifier.
|
||||
**Parallel native dispatch in the loop.** The other answer to round-trip cost at decision time; it was blocked on concurrency-safety metadata and offers no composition either way — it parallelizes calls the model already decided on in one step. Code Mode's queue decision kept the two compatible, and both later shipped: the metadata as `isConcurrencySafe` (the [parallel tool-call note](2026-07-10-parallel-tool-call-execution.md)), and native rolling-pool dispatch plus per-tool binding parallelism on the same classifier.
|
||||
|
||||
**Always-exclusive (Cloudflare-faithful, no mode).** Rejected for this SDK's primary consumer: a coding agent's bread-and-butter single calls (`bash`, `read`, `edit`) are already ideal as native calls, and forcing every edit through a program taxes the common case. The mode config keeps the faithful form (`'code'`) one line away without imposing it.
|
||||
|
||||
|
||||
@@ -30,7 +30,7 @@ Cloudflare 的 [Code Mode](https://blog.cloudflare.com/code-mode/) 提出了一
|
||||
|
||||
**协议工具列表。** 注册表在 `'native'` 下贡献可见能力，在 `'code'` 下仅贡献 `run_code`，在 `'both'` 下两者都贡献。最终的 `PromptAssembly.tools` 列表记录在请求头中。`run_code` 是一个保留的呈现传输通道，位于注册和限制层之外；直接提示词提供方和组装 waterfall 仍各自负责自己的贡献。
|
||||
|
||||
**与 `toolOrder` 的交互，预先说明：** 如果配置的 `systemPrompt.toolOrder` 引用了原生能力名称，在 `mode: 'code'` 下会拒绝所有组装，因为那些名称不在该模式的协议校验范围内。这是正确行为而非 bug：使用 Code Mode 的部署需要更新其 order 配置或移除它。
|
||||
**与 `toolOrder` 的交互：** 如果配置的 `systemPrompt.toolOrder` 引用了原生能力名称，在 `mode: 'code'` 下会拒绝所有组装，因为那些名称不在该模式的协议校验范围内。这是正确行为而非 bug：使用 Code Mode 的部署需要更新其 order 配置或移除它。
|
||||
|
||||
**SDK 提示词段。** 在 `'code'` 和 `'both'` 下，tool-guidance order band 中的惰性 `tools:sdk` 段为当前 scope 的可见能力渲染所加载运行时语言的声明加固定的使用说明（默认 TypeScript；[语言分发 note](2026-07-31-code-mode-language-dispatch.md) 加入了 Python 与按 `ctx.codeRuntime.language` 选择的渲染器表）。它共享查找和执行可见性，排除 `run_code`，并按字典序排列工具以获得字节稳定的输出。
|
||||
|
||||
@@ -106,7 +106,7 @@ SDK 指示模型编写一个所加载运行时语言的异步函数体（默认
|
||||
|
||||
**在原生工具调用上做结果省略/摘要。** 仅解决问题中上下文膨胀这一半：裁剪旧 `tool-result` 作为可重建请求下的日志化表面替换成本低，但仍需每次调用一次模型往返，且无法表达循环、分支或汇合。互补而非竞争；它可以在 Code Mode 下为残余的原生调用分层。
|
||||
|
||||
**循环中的并行原生分发。** 决策当时对往返成本的另一个答案；它被并发安全元数据阻塞，且无论如何都不提供组合能力——它并行化的是模型在一步中已经决定的调用。Code Mode 的队列决策保持了两者兼容，后续也正是这样落地的：元数据以 `isConcurrencySafe` 的形式就绪（见[并行工具调用 note](2026-07-10-parallel-tool-call-execution.md)），原生 rolling-pool 分发与每工具绑定并行化基于同一个分类器一起解锁。
|
||||
**循环中的并行原生分发。** 决策当时对往返成本的另一个答案；它被并发安全元数据阻塞，且无论如何都不提供组合能力——它并行化的是模型在一步中已经决定的调用。Code Mode 的队列决策保持了两者兼容，两者后来都已交付：元数据即 `isConcurrencySafe`（见[并行工具调用 note](2026-07-10-parallel-tool-call-execution.md)），原生 rolling-pool 分发加每工具绑定并行化则基于同一个分类器。
|
||||
|
||||
**始终排他（忠于 Cloudflare，无模式）。** 否决，因为本 SDK 的主要消费方是编码 agent：其日常的单次调用（`bash`、`read`、`edit`）作为原生调用已经是最优的，强制每次编辑都通过程序会给常见场景增加负担。mode 配置让忠实形式（`'code'`）只需一行配置即可启用，而不强加于人。
|
||||
|
||||
|
||||
@@ -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 .agents/notes/implemented/feature/2026-06-17-filesystem-tool-schemas.md
|
||||
2026-06-17-filesystem-tool-schemas.md: b48f8e5d44913f2b6a2b7e1b19269c58e72efd1f
|
||||
2026-06-17-filesystem-tool-schemas.zh.md: ad4081d28950a4a2df4f5718038e2a4124bf70b5
|
||||
2026-06-17-filesystem-tool-schemas.md: ede7daee5c0f49a094df16861b107c8f528664fa
|
||||
2026-06-17-filesystem-tool-schemas.zh.md: 5ab19b82d6523bc81dd57c319252d998cc203911
|
||||
|
||||
@@ -8,17 +8,17 @@ English | [中文](2026-06-17-filesystem-tool-schemas.zh.md)
|
||||
|
||||
[The filesystem capability-seam Agent Note](../architecture/2026-06-17-filesystem-capability-seam.md) defines the filesystem capability seam (`ctx.fs`), the package split (`dsh-fs`, `dsh-fs-local`, `dsh-tool-fs`, plus the `dsh-fs-policy` policy plugin), and the observed-file/stale-version policy for read-before-write/edit checks — which the [split-fs-seam](../simplification/2026-06-26-fsspec-style-fs-seam.md) and [event-gate](../architecture/2026-06-26-file-context-as-event-gate.md) Agent Notes moved off `ctx.fs` into the `dsh-fs-policy` plugin on the `fs/*` event gate. The remaining decision for the first filesystem tool delivery is the model-facing schema surface: what arguments the model sees for `read`, `write`, and `edit`.
|
||||
|
||||
The schema should be small enough to implement in the first `dsh-tool-fs` pass, but stable enough that future local/remote/sandboxed filesystem backends do not require model-facing churn. It should also avoid importing every option from reference systems. Claude Code and OpenCode expose similar core file tools but differ in naming style and extra flags; this Agent Note chooses the minimal shared surface for the prototype.
|
||||
The schema must be small, yet stable enough that local/remote/sandboxed filesystem backends do not require model-facing churn, and must avoid importing every option from reference systems. Claude Code and OpenCode expose similar core file tools but differ in naming style and extra flags; this decision picks the minimal shared surface.
|
||||
|
||||
## Decision
|
||||
|
||||
`@deepseek-ai/dsh-tool-fs` exposes these three model-facing tools in the first filesystem suite:
|
||||
|
||||
| Tool | Our schema | Claude Code | OpenCode | Notes | Part of prototype |
|
||||
|---|---|---|---|---|---|
|
||||
| `read` | `read(file_path, offset?, limit?)` | `Read(file_path, offset?, limit?, pages?)` | `read(filePath, offset?, limit?)` | Files only; 1-indexed `offset`; no image/PDF/multimodal support in the first pass. | YES |
|
||||
| `write` | `write(file_path, content)` | `Write(file_path, content)` | `write(content, filePath)` | Creates or overwrites UTF-8 text. Under the default fs-policy, updates to existing files require a prior observation; new-file creates do not. | YES |
|
||||
| `edit` | `edit(file_path, old_string, new_string, replace_all?)` | `Edit(file_path, old_string, new_string, replace_all?)` | `edit(filePath, oldString, newString, replaceAll?)` | Literal string replacement; unique match required by default; under the default fs-policy requires a prior observation (any windowed read counts). | YES |
|
||||
| Tool | Our schema | Claude Code | OpenCode | Notes |
|
||||
|---|---|---|---|---|
|
||||
| `read` | `read(file_path, offset?, limit?)` | `Read(file_path, offset?, limit?, pages?)` | `read(filePath, offset?, limit?)` | Files only; 1-indexed `offset`; no image/PDF/multimodal support in the first pass. |
|
||||
| `write` | `write(file_path, content)` | `Write(file_path, content)` | `write(content, filePath)` | Creates or overwrites UTF-8 text. Under the default fs-policy, updates to existing files require a prior observation; new-file creates do not. |
|
||||
| `edit` | `edit(file_path, old_string, new_string, replace_all?)` | `Edit(file_path, old_string, new_string, replace_all?)` | `edit(filePath, oldString, newString, replaceAll?)` | Literal string replacement; unique match required by default; under the default fs-policy requires a prior observation (any windowed read counts). |
|
||||
|
||||
The schema uses snake_case field names (`file_path`, `old_string`, `new_string`, `replace_all`) to align with Claude Code and with existing DeepSeek Harness tool-schema examples. The Consumer package translates these model-facing names into `ctx.fs` calls and `fs/*` event dispatches.
|
||||
|
||||
|
||||
@@ -8,17 +8,17 @@ Status: implemented
|
||||
|
||||
[文件系统能力 seam Agent Note](../architecture/2026-06-17-filesystem-capability-seam.md) 定义了文件系统能力 seam（`ctx.fs`）、包拆分（`dsh-fs`、`dsh-fs-local`、`dsh-tool-fs`，加上 `dsh-fs-policy` 策略插件），以及针对 read-before-write/edit 检查的已观测文件／陈旧版本策略——[拆分文件系统 seam](../simplification/2026-06-26-fsspec-style-fs-seam.md)和[事件门控插件](../architecture/2026-06-26-file-context-as-event-gate.md) Agent Note 后来将其从 `ctx.fs` 移至 `dsh-fs-policy` 插件的 `fs/*` 事件门上。首次文件系统工具交付剩余的决策是面向模型的 schema 接口：模型在 `read`、`write` 和 `edit` 中看到哪些参数。
|
||||
|
||||
该 schema 应足够小，以便在 `dsh-tool-fs` 的首次实现中完成，但又足够稳定，使未来的本地/远程/沙箱文件系统后端不需要改动面向模型的接口。同时应避免从参考系统中照搬所有选项。Claude Code 和 OpenCode 暴露了类似的核心文件工具，但在命名风格和额外 flag 上有所不同；本 Agent Note 为原型选择最小的共有接口。
|
||||
该 schema 必须足够小，但又要足够稳定，使本地/远程/沙箱文件系统后端不需要改动面向模型的接口，并且必须避免从参考系统中照搬所有选项。Claude Code 和 OpenCode 暴露了类似的核心文件工具，但在命名风格和额外 flag 上有所不同；本决策选择最小的共有接口。
|
||||
|
||||
## 决策
|
||||
|
||||
`@deepseek-ai/dsh-tool-fs` 在首个文件系统工具套件中暴露以下三个面向模型的工具：
|
||||
|
||||
| 工具 | 我们的 schema | Claude Code | OpenCode | 说明 | 原型包含 |
|
||||
|---|---|---|---|---|---|
|
||||
| `read` | `read(file_path, offset?, limit?)` | `Read(file_path, offset?, limit?, pages?)` | `read(filePath, offset?, limit?)` | 仅文件；`offset` 从 1 开始；首版不支持图片、PDF 或多模态内容。 | 是 |
|
||||
| `write` | `write(file_path, content)` | `Write(file_path, content)` | `write(content, filePath)` | 创建或覆盖 UTF-8 文本。在默认 fs-policy 下，更新现有文件前必须先观测；创建新文件则不需要。 | 是 |
|
||||
| `edit` | `edit(file_path, old_string, new_string, replace_all?)` | `Edit(file_path, old_string, new_string, replace_all?)` | `edit(filePath, oldString, newString, replaceAll?)` | 字面字符串替换；默认要求唯一匹配；在默认 fs-policy 下必须先观测（任意窗口读取均算作观测）。 | 是 |
|
||||
| 工具 | 我们的 schema | Claude Code | OpenCode | 说明 |
|
||||
|---|---|---|---|---|
|
||||
| `read` | `read(file_path, offset?, limit?)` | `Read(file_path, offset?, limit?, pages?)` | `read(filePath, offset?, limit?)` | 仅文件；`offset` 从 1 开始；首版不支持图片、PDF 或多模态内容。 |
|
||||
| `write` | `write(file_path, content)` | `Write(file_path, content)` | `write(content, filePath)` | 创建或覆盖 UTF-8 文本。在默认 fs-policy 下，更新现有文件前必须先观测；创建新文件则不需要。 |
|
||||
| `edit` | `edit(file_path, old_string, new_string, replace_all?)` | `Edit(file_path, old_string, new_string, replace_all?)` | `edit(filePath, oldString, newString, replaceAll?)` | 字面字符串替换；默认要求唯一匹配；在默认 fs-policy 下必须先观测（任意窗口读取均算作观测）。 |
|
||||
|
||||
schema 使用 snake_case 字段名（`file_path`、`old_string`、`new_string`、`replace_all`），与 Claude Code 及现有 DeepSeek Harness 工具 schema 示例保持一致。Consumer 包将这些面向模型的名称转换为 `ctx.fs` 调用和 `fs/*` 事件分发。
|
||||
|
||||
|
||||
@@ -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 .agents/notes/implemented/feature/2026-06-18-compaction-capability-seam.md
|
||||
2026-06-18-compaction-capability-seam.md: 6357482600fabd0354325a19118ec245eee5d855
|
||||
2026-06-18-compaction-capability-seam.zh.md: a5c60c667734f119a8bd9d9b6a8fbc9c66155470
|
||||
2026-06-18-compaction-capability-seam.md: 83f224aef50eb02712ac095da0cabf552399a9a6
|
||||
2026-06-18-compaction-capability-seam.zh.md: 12cf2498535d77dcf1a718b841a751bccadfdf1c
|
||||
|
||||
@@ -31,7 +31,7 @@ This is not a coupling smell — it is the contract's domain. The "only cordis"
|
||||
|
||||
### Three abstract operations, algorithm in the backend
|
||||
|
||||
An earlier draft put the full algorithm (the retention walk, token-summing, text extraction) as concrete methods on the interface. That recouples the contract to one strategy: a backend that wants a different retention policy or event sequence would have to fight inherited concrete code. Making all three operations abstract puts every *how* decision in the backend and keeps the interface a statement of *what*. Token measurement is not a compaction hook at all; the singleton service lets multiple consumers share one per-session replay fold.
|
||||
Putting the full algorithm (the retention walk, token-summing, text extraction) as concrete methods on the interface recouples the contract to one strategy: a backend that wants a different retention policy or event sequence would have to fight inherited concrete code. Making all three operations abstract puts every *how* decision in the backend and keeps the interface a statement of *what*. Token measurement is not a compaction hook at all; the singleton service lets multiple consumers share one per-session replay fold.
|
||||
|
||||
`compactIfNeeded(agent, trigger, signal)` takes an explicit `'pressure' | 'context-overflow'` trigger and cancellation. It reads only the latest durable routed request; no header means no work, while any routed provider/model target uses the singleton estimator. `compactNow(agent, signal)` requires an idle agent and performs one useful balanced reduction even below pressure, returning `null` without writes when none exists. `compactRegion(start, end, agent, signal?)` uses `agent.session` as its single session identity and keeps an optional signal for explicit callers. The default summarizer resolves its target from explicit config, the latest logged routed target, then agent options, and records the provider/model pair after any `llm/stream` routing. It replays the routed request's prefix and appends the compaction directive as a trailing user message so the provider's warm KV cache is reused — see the [summary prefix-cache Agent Note](../bug-fix/2026-07-21-compaction-summary-prefix-cache-reuse.md). The result carries `llmStreamCall: true` because it consumed exactly one call through this context's LLM service; a subclass sets that marker only under the same condition, since retained `rawOutput` alone does not identify the call path. The call sets the provider-neutral `GenerateOptions.purpose` to `compaction`; adapters may map that purpose to model-hidden transport metadata, and the DeepSeek adapter sends `x-deepseek-harness-compact: 1`.
|
||||
|
||||
|
||||
@@ -31,7 +31,7 @@ Status: implemented
|
||||
|
||||
### 三个抽象操作，算法在后端
|
||||
|
||||
早期草案将完整算法（保留遍历、token 求和、文本提取）作为接口上的具体方法。这会将约定重新耦合到一种策略：想要不同保留策略或事件排序的后端必须与继承来的具体代码对抗。将三个操作都设为抽象，把所有*怎么做*的决策放在后端，并让接口保持为*做什么*的声明。token 测量根本不是压缩钩子；单例服务使多个消费方能够共享逐会话的回放折叠。
|
||||
将完整算法（保留遍历、token 求和、文本提取）作为接口上的具体方法，会将约定重新耦合到一种策略：想要不同保留策略或事件排序的后端必须与继承来的具体代码对抗。将三个操作都设为抽象，把所有*怎么做*的决策放在后端，并让接口保持为*做什么*的声明。token 测量根本不是压缩钩子；单例服务使多个消费方能够共享逐会话的回放折叠。
|
||||
|
||||
`compactIfNeeded(agent, trigger, signal)` 接受显式的 `'pressure' | 'context-overflow'` 触发原因与取消信号。它只读取最新的持久化已路由请求；没有 header 就不执行工作，任何已路由的提供方/模型目标都使用单例估算器。`compactNow(agent, signal)` 要求 agent 处于 idle，即使未达到压力也进行一次有效的平衡缩减；不存在这种范围时返回 `null`，且不写入任何内容。`compactRegion(start, end, agent, signal?)` 将 `agent.session` 作为唯一会话身份，并为显式调用方保留可选 signal。默认摘要器依次从显式配置、最新记录的已路由目标和 agent 选项解析目标，并在任何 `llm/stream` 路由后记录提供方/模型对。它回放已路由请求的前缀，并将压缩指令追加为尾部 user 消息，从而复用提供方的热 KV cache；见[摘要前缀缓存 Agent Note](../bug-fix/2026-07-21-compaction-summary-prefix-cache-reuse.md)。该结果携带 `llmStreamCall: true`，因为生成它时恰好通过此上下文的 LLM 服务发起了一次调用；只有满足相同条件时，子类才设置该标记，因为单有保留的 `rawOutput` 并不能判定调用路径。该调用将提供方无关的 `GenerateOptions.purpose` 设为 `compaction`；适配器可以将此用途映射为对模型隐藏的传输元数据，DeepSeek 适配器会发送 `x-deepseek-harness-compact: 1`。
|
||||
|
||||
|
||||
@@ -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 .agents/notes/implemented/feature/2026-06-21-subagent-capability-seam.md
|
||||
2026-06-21-subagent-capability-seam.md: 553411a0d8f989c883e3eea929669ccebcfe807b
|
||||
2026-06-21-subagent-capability-seam.zh.md: 5fa2bd62828e9afcb79647ec4821c2da1da041e7
|
||||
2026-06-21-subagent-capability-seam.md: 28ecf985db1289ce4f80570583eac6a051cd2c0b
|
||||
2026-06-21-subagent-capability-seam.zh.md: 5f349ddcacebe66c346976b822c9dcc65bda8d18
|
||||
|
||||
@@ -8,9 +8,9 @@ English | [中文](2026-06-21-subagent-capability-seam.zh.md)
|
||||
|
||||
## Problem
|
||||
|
||||
The harness has a long-deferred seam for **subagents** — an agent delegating work to another agent. The intent was sketched in the `Agent`/`AgentLoop` interfaces ([packages/core/agent/src/types.ts](../../../../packages/core/agent/src/types.ts), [packages/core/agent-loop/src/index.ts](../../../../packages/core/agent-loop/src/index.ts)): a creation option referencing a parent agent (fork = seed the child session with the parent's event log; spawn = fresh session), with the child returned as an `Agent` handle so steering and event subscription work uniformly. This Agent Note realizes that seam; the banner above lists what shipped.
|
||||
The harness has a long-deferred seam for **subagents** — an agent delegating work to another agent. The intent was sketched in the `Agent`/`AgentLoop` interfaces ([packages/core/agent/src/types.ts](../../../../packages/core/agent/src/types.ts), [packages/core/agent-loop/src/index.ts](../../../../packages/core/agent-loop/src/index.ts)): a creation option referencing a parent agent (fork = seed the child session with the parent's event log; spawn = fresh session), with the child returned as an `Agent` handle so steering and event subscription work uniformly.
|
||||
|
||||
The distinctive requirement — the one that shapes the whole design — is that **multiple subagent implementations must coexist at runtime**. A parent may want a cheap in-process child for a scoped subtask AND an isolated out-of-process child (over ACP) in the same session. The transports we foresee:
|
||||
The distinctive requirement — the one that shapes the whole design — is that **multiple subagent implementations must coexist at runtime**. A parent may want a cheap in-process child for a scoped subtask AND an isolated out-of-process child (over ACP) in the same session. The transports:
|
||||
|
||||
- **in-process** — a child concrete `Agent` on the same `Context` (the cheapest, and nearly free given the existing agent factory);
|
||||
- **ACP** — act as an ACP *client* driving another agent process (which can be another instance of ourselves);
|
||||
@@ -62,7 +62,7 @@ Each in-process subagent runs in its **own `Session`** (own id, `parentSession`
|
||||
|
||||
### Provider selection is config, not model-facing
|
||||
|
||||
`dsh-tool-subagent` binds to exactly one provider name (`Config.provider`); the model sees only `{ description, prompt }`. To expose more than one transport, load the tool plugin more than once, each bound to a different provider and a distinct `toolName` (the tool registry rejects a duplicate name). The *service* holds the multi-provider registry; the *tool* picks one — no provider/type parameter in the schema this cut.
|
||||
`dsh-tool-subagent` binds to exactly one provider name (`Config.provider`); the model sees only `{ description, prompt }`. To expose more than one transport, load the tool plugin more than once, each bound to a different provider and a distinct `toolName` (the tool registry rejects a duplicate name). The *service* holds the multi-provider registry; the *tool* picks one — the schema carries no provider/type parameter.
|
||||
|
||||
## Testing
|
||||
|
||||
@@ -72,5 +72,5 @@ Registry and tool tests replace only the nondeterministic child boundary with a
|
||||
|
||||
- **Recursion.** Without a bound, an in-process child can see the delegation tool and recurse. The in-process backends implement the optional absolute depth limit and scoped live-global `toolFilter`; ACP advertises both capabilities off and rejects such a request. The [subagent composition-controls Agent Note](2026-07-12-subagent-persona-tool-filter-and-depth.md) owns their exact semantics and security limits.
|
||||
- **Blocking the parent turn.** Foreground collection holds the parent's step open for the child's full duration. Background delegation uses the shared `ctx.tasks` runtime and generic `task_*` tools, the same collection mechanism as background bash; the subagent seam itself remains task-agnostic.
|
||||
- **Live progress.** This cut surfaces only lifecycle + final result; a per-chunk child→parent update stream is deferred with the background redesign.
|
||||
- **ACP client surface.** Proxying `fs`/`terminal` from the ACP child back to the parent (a shared-workspace mode) is future work; the first cut advertises neither, so the child self-serves in its own process.
|
||||
- **Live progress.** Only lifecycle + the final result surface; a per-chunk child→parent update stream is deferred with the background redesign.
|
||||
- **ACP client surface.** Proxying `fs`/`terminal` from the ACP child back to the parent (a shared-workspace mode) is future work; the backend advertises neither capability, so the child self-serves in its own process.
|
||||
|
||||
@@ -8,9 +8,9 @@ Status: implemented
|
||||
|
||||
## 问题
|
||||
|
||||
harness 有一个长期搁置的 seam 用于 **subagent**：一个 agent 将工作委派给另一个 agent。这一意图在 `Agent`/`AgentLoop` 接口中已有草案（[packages/core/agent/src/types.ts](../../../../packages/core/agent/src/types.ts)、[packages/core/agent-loop/src/index.ts](../../../../packages/core/agent-loop/src/index.ts)）：一个创建选项引用父 agent（fork = 用父会话的事件日志初始化子会话；spawn = 全新会话），子 agent 以 `Agent` 句柄返回，使 steering（中途引导）和事件订阅可以统一工作。本 Agent Note 实现了这个 seam；上方横幅列出了已交付的内容。
|
||||
harness 有一个长期搁置的 seam 用于 **subagent**：一个 agent 将工作委派给另一个 agent。这一意图在 `Agent`/`AgentLoop` 接口中已有草案（[packages/core/agent/src/types.ts](../../../../packages/core/agent/src/types.ts)、[packages/core/agent-loop/src/index.ts](../../../../packages/core/agent-loop/src/index.ts)）：一个创建选项引用父 agent（fork = 用父会话的事件日志初始化子会话；spawn = 全新会话），子 agent 以 `Agent` 句柄返回，使 steering（中途引导）和事件订阅可以统一工作。
|
||||
|
||||
决定整体设计走向的核心需求是：**多种 subagent 实现必须在运行时共存**。一个父 agent 可能在同一个会话中既需要一个廉价的进程内子 agent 处理有限范围的子任务，又需要一个隔离的进程外子 agent（通过 ACP）。我们预见的传输方式：
|
||||
决定整体设计走向的核心需求是：**多种 subagent 实现必须在运行时共存**。一个父 agent 可能在同一个会话中既需要一个廉价的进程内子 agent 处理有限范围的子任务，又需要一个隔离的进程外子 agent（通过 ACP）。传输方式：
|
||||
|
||||
- **进程内**：在同一个 `Context` 上创建一个具体的子 `Agent`（最廉价，且鉴于现有 agent 工厂几乎零成本）；
|
||||
- **ACP**：作为 ACP *客户端*驱动另一个 agent 进程（可以是自身的另一个实例）；
|
||||
@@ -62,7 +62,7 @@ bash seam（[能力 seam](../architecture/2026-06-13-capability-seams.md)）在
|
||||
|
||||
### 提供方选择是配置，不面向模型
|
||||
|
||||
`dsh-tool-subagent` 绑定到恰好一个提供方名称（`Config.provider`）；模型只看到 `{ description, prompt }`。若要暴露多种传输方式，请多次加载该工具插件，每次绑定不同的提供方和不同的 `toolName`（工具注册表拒绝重名）。*服务*持有多提供方注册表；*工具*选择其中一个——本版 schema 中没有提供方/type 参数。
|
||||
`dsh-tool-subagent` 绑定到恰好一个提供方名称（`Config.provider`）；模型只看到 `{ description, prompt }`。若要暴露多种传输方式，请多次加载该工具插件，每次绑定不同的提供方和不同的 `toolName`（工具注册表拒绝重名）。*服务*持有多提供方注册表；*工具*选择其中一个——schema 中没有提供方/type 参数。
|
||||
|
||||
## 测试
|
||||
|
||||
@@ -72,5 +72,5 @@ bash seam（[能力 seam](../architecture/2026-06-13-capability-seams.md)）在
|
||||
|
||||
- **递归。** 如果不设限制，进程内子 agent 能看到委派工具并递归调用。进程内后端实现了可选的绝对深度限制和有作用域的实时全局 `toolFilter`；ACP 声明这两项能力为关闭状态，并拒绝此类请求。[subagent 组合控制 Agent Note](2026-07-12-subagent-persona-tool-filter-and-depth.md) 负责定义它们的确切语义和安全边界。
|
||||
- **阻塞父轮次。** 前台收集在子 agent 的整个持续时间内保持父 agent 的步骤打开。后台委派使用共享的 `ctx.tasks` 运行时与通用 `task_*` 工具，与后台 bash 共用同一套收集机制；subagent seam 本身仍不感知任务。
|
||||
- **实时进度。** 本版仅暴露生命周期事件与最终结果；逐分片的子→父更新流推迟到后台重新设计时一并处理。
|
||||
- **ACP 客户端接口。** 将 ACP 子 agent 的 `fs`/`terminal` 代理回父 agent（共享工作区模式）是后续工作；首版不声明这两项能力，子 agent 在自己的进程中自行服务。
|
||||
- **实时进度。** 仅暴露生命周期事件与最终结果；逐分片的子→父更新流推迟到后台重新设计时一并处理。
|
||||
- **ACP 客户端接口。** 将 ACP 子 agent 的 `fs`/`terminal` 代理回父 agent（共享工作区模式）是后续工作；该后端不声明这两项能力，子 agent 在自己的进程中自行服务。
|
||||
|
||||
@@ -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 .agents/notes/implemented/feature/2026-06-22-acp-subagent-backend.md
|
||||
2026-06-22-acp-subagent-backend.md: 211030a6ecc9b6f673174ba410415c7bd80818ef
|
||||
2026-06-22-acp-subagent-backend.zh.md: 2dde3d96329cc47d9c7cca08e1d25764c32f8ebe
|
||||
2026-06-22-acp-subagent-backend.md: 41a60bc8e73cbda1d382226acfbd9c0a4b146fa6
|
||||
2026-06-22-acp-subagent-backend.zh.md: 6aea991c2b4ab783b5f8c43ecb9529df07269d3f
|
||||
|
||||
@@ -18,7 +18,7 @@ Each `start` spawns a new child, runs exactly one ACP session (`initialize` →
|
||||
|
||||
### Minimal client stub
|
||||
|
||||
The client advertises NO optional capabilities (no `fs`, no `terminal`): the child self-serves file/terminal access in its own process. `session/update` notifications are consumed — the backend accumulates `agent_message_chunk` text as the result output and ignores the rest (thoughts, tool-call cards) in this cut, which surfaces only the child's final answer. `session/request_permission` is auto-answered by a configured policy (`reject` declines every prompt, `allow` approves via the first allow-shaped option) — the first cut surfaces no prompt to a human. Proxying `fs`/`terminal` back to the parent (a shared-workspace mode) remains future work, as the seam Agent Note noted.
|
||||
The client advertises NO optional capabilities (no `fs`, no `terminal`): the child self-serves file/terminal access in its own process. `session/update` notifications are consumed — the backend accumulates `agent_message_chunk` text as the result output and ignores the rest (thoughts, tool-call cards), so only the child's final answer surfaces. `session/request_permission` is auto-answered by a configured policy (`reject` declines every prompt, `allow` approves via the first allow-shaped option) — no prompt is surfaced to a human. Proxying `fs`/`terminal` back to the parent (a shared-workspace mode) remains future work, as the seam Agent Note noted.
|
||||
|
||||
### No start-time capabilities
|
||||
|
||||
|
||||
@@ -18,7 +18,7 @@ subagent seam（[seam Agent Note](2026-06-21-subagent-capability-seam.md)）的
|
||||
|
||||
### 最小化客户端桩
|
||||
|
||||
客户端不声明任何可选能力（无 `fs`、无 `terminal`）：子 agent 在自己的进程中自行处理文件/终端访问。`session/update` 通知被消费：后端将 `agent_message_chunk` 文本累积为结果输出，在本阶段忽略其余内容（思考、工具调用卡片），仅暴露子 agent 的最终回答。`session/request_permission` 由配置的策略自动应答（`reject` 拒绝所有提示，`allow` 通过第一个表示允许的选项批准）——本阶段不向人类暴露任何权限提示。将 `fs`/`terminal` 代理回父进程（共享工作区模式）仍为后续工作，如 seam Agent Note 所述。
|
||||
客户端不声明任何可选能力（无 `fs`、无 `terminal`）：子 agent 在自己的进程中自行处理文件/终端访问。`session/update` 通知被消费：后端将 `agent_message_chunk` 文本累积为结果输出，忽略其余内容（思考、工具调用卡片），因此仅暴露子 agent 的最终回答。`session/request_permission` 由配置的策略自动应答（`reject` 拒绝所有提示，`allow` 通过第一个表示允许的选项批准）——不向人类暴露任何权限提示。将 `fs`/`terminal` 代理回父进程（共享工作区模式）仍为后续工作，如 seam Agent Note 所述。
|
||||
|
||||
### 无启动时能力
|
||||
|
||||
|
||||
@@ -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 .agents/notes/implemented/feature/2026-06-29-todo-write-tool.md
|
||||
2026-06-29-todo-write-tool.md: c4cf64b7876bd8b80df80fe6fc27005715f96b5e
|
||||
2026-06-29-todo-write-tool.zh.md: 2e95cfc4b085b03a70a651c622ca87ad7efa1538
|
||||
2026-06-29-todo-write-tool.md: 74af8a66ea86a474533b9c53d6431f7e0026192c
|
||||
2026-06-29-todo-write-tool.zh.md: ec2b7c8d59d65a44018425de81aa410890d8c208
|
||||
|
||||
@@ -42,7 +42,7 @@ The schema enforces type/required/enum. Beyond that, `execute` rejects empty or
|
||||
|
||||
## Testing
|
||||
|
||||
Four tiers, designed up front:
|
||||
Four tiers:
|
||||
- **Unit** — the session event (append/snapshot-clone/last-write-wins/not-on-surface); the tool (schema shape, arg validation via the real `ctx.tools.execute`, value validation, the event append + replacement, no-agent rejection, `presentCall`, HMR-safety); and TUI folding.
|
||||
- **Real-Loader path** — the plugin run through `Loader.unwrapExports`, asserting the namespace export shape survives (it HAS `inject`, so a stray default would crash at load — postmortem/0001).
|
||||
- **Full-loop integration** — a scripted mock model calls `todo_write` through the real agent loop; the `todo/write` event lands and a second call replaces it.
|
||||
|
||||
@@ -42,7 +42,7 @@ schema 强制 type/required/enum。在此之上，`execute` 拒绝为空或重
|
||||
|
||||
## 测试
|
||||
|
||||
四个层级，预先设计：
|
||||
四个层级：
|
||||
- **单元测试**——会话事件（append/snapshot-clone/last-write-wins/not-on-surface）；工具（schema 形状、通过真实 `ctx.tools.execute` 的参数校验、值校验、事件追加与替换、非 agent 拒绝、`presentCall`、HMR（热模块替换）安全性）；以及 TUI 折叠。
|
||||
- **真实 Loader 路径**——插件通过 `Loader.unwrapExports` 运行，断言命名空间导出形状存活（它有 `inject`，因此一个意外的 default 导出会在加载时崩溃——事故复盘（postmortem）0001）。
|
||||
- **全循环集成**——一个脚本化的 mock 模型通过真实 agent loop（智能体循环）调用 `todo_write`；`todo/write` 事件落地，第二次调用替换它。
|
||||
|
||||
@@ -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 .agents/notes/implemented/feature/2026-06-30-hook-protocol-lib.md
|
||||
2026-06-30-hook-protocol-lib.md: 576a126e1022ac72265c476e03ef36aaf17f78b4
|
||||
2026-06-30-hook-protocol-lib.zh.md: f2554eaa378a26bf8254d86d458e0de5ce1aa4fd
|
||||
2026-06-30-hook-protocol-lib.md: e6938f88b2b587ef97c135d6482ae9ce0e3a94c1
|
||||
2026-06-30-hook-protocol-lib.zh.md: 4a4efae9a8950368d4db0309bc2c89a3f8c6d0d0
|
||||
|
||||
@@ -6,7 +6,7 @@ English | [中文](2026-06-30-hook-protocol-lib.zh.md)
|
||||
|
||||
## Problem
|
||||
|
||||
The hooks subsystem ships two bridge plugins: one that runs a user's existing Claude Code (CC) hooks, one for Codex hooks. Studying the reference implementations (`~/repos/refs/claude-code`, `~/repos/refs/codex`) surfaced a decisive fact: **Codex deliberately reimplements a SUBSET of the CC hook protocol.** Its engine reads the same `hooks.json`, uses the same matcher-group shape, the same exit-code/structured-stdout output contract, and the same command-hook execution model — Codex's source even names the engine after Claude's and comments where it "intentionally diverges." So the two bridges would otherwise duplicate the bulk of the protocol.
|
||||
The hooks subsystem ships two bridge plugins: one that runs a user's existing Claude Code (CC) hooks, one for Codex hooks. The reference implementations (`~/repos/refs/claude-code`, `~/repos/refs/codex`) show a decisive fact: **Codex deliberately reimplements a SUBSET of the CC hook protocol.** Its engine reads the same `hooks.json`, uses the same matcher-group shape, the same exit-code/structured-stdout output contract, and the same command-hook execution model — Codex's source even names the engine after Claude's and comments where it "intentionally diverges." So the two bridges would otherwise duplicate the bulk of the protocol.
|
||||
|
||||
This Agent Note introduces `@deepseek-ai/dsh-hook-protocol`, a **library** (not a plugin — it registers and injects nothing) holding the genuinely-identical primitives both bridges build on. The split between shared and per-dialect is the design's center of gravity.
|
||||
|
||||
|
||||
@@ -6,7 +6,7 @@ Status: implemented
|
||||
|
||||
## 问题
|
||||
|
||||
钩子子系统提供两个桥接插件：一个运行用户既有的 Claude Code（CC）钩子，另一个运行 Codex 钩子。研究参考实现（`~/repos/refs/claude-code`、`~/repos/refs/codex`）后发现一个决定性事实：**Codex 有意重新实现了 CC 钩子协议的一个子集。** 它的引擎读取相同的 `hooks.json`，使用相同的 matcher-group 形状、相同的 exit-code/structured-stdout 输出约定，以及相同的命令钩子执行模型。Codex 的源码甚至以 Claude 的引擎命名，并在注释中标注了「有意偏离」之处。因此，如果不做抽取，两个桥接插件将大量重复协议逻辑。
|
||||
钩子子系统提供两个桥接插件：一个运行用户既有的 Claude Code（CC）钩子，另一个运行 Codex 钩子。参考实现（`~/repos/refs/claude-code`、`~/repos/refs/codex`）表明一个决定性事实：**Codex 有意重新实现了 CC 钩子协议的一个子集。** 它的引擎读取相同的 `hooks.json`，使用相同的 matcher-group 形状、相同的 exit-code/structured-stdout 输出约定，以及相同的命令钩子执行模型。Codex 的源码甚至以 Claude 的引擎命名，并在注释中标注了「有意偏离」之处。因此，如果不做抽取，两个桥接插件将大量重复协议逻辑。
|
||||
|
||||
本 Agent Note 引入 `@deepseek-ai/dsh-hook-protocol`，一个**库**（不是插件——它不注册也不注入任何东西），持有两个桥接插件共同依赖的真正相同的原语。共享与方言专属之间的分界是本设计的重心。
|
||||
|
||||
|
||||
@@ -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 .agents/notes/implemented/feature/2026-06-30-session-store-fork-api.md
|
||||
2026-06-30-session-store-fork-api.md: 69ff85e1f137f4f263bf951af0a3f655411c606a
|
||||
2026-06-30-session-store-fork-api.zh.md: f354aaefbc16c6c3251da20de507602105a32296
|
||||
2026-06-30-session-store-fork-api.md: 85e748ba4e42919eac49cae583a08c72e0c3c0a0
|
||||
2026-06-30-session-store-fork-api.zh.md: f985c93085cbc2dbb1b8a768dac82a40025ea54d
|
||||
|
||||
@@ -36,7 +36,7 @@ The Host creates the child through the agent registry with the selected seed and
|
||||
|
||||
## Alternatives considered
|
||||
|
||||
**Separate `ctx.sessionFork` service.** This was the first implementation, but review showed it overfit the capability-seam pattern. The code had no swappable backend, no extra event surface, no independent ownership lifecycle, and no durable behavior beyond `ctx.sessions.create({ seed, meta })`. Keeping a separate package would make callers discover and install a second service just to perform policy around a session-store primitive.
|
||||
**Separate `ctx.sessionFork` service.** An earlier iteration shipped this as a separate service; it overfit the capability-seam pattern. The code had no swappable backend, no extra event surface, no independent ownership lifecycle, and no durable behavior beyond `ctx.sessions.create({ seed, meta })`. Keeping a separate package would make callers discover and install a second service just to perform policy around a session-store primitive.
|
||||
|
||||
**Two functions: `snapshot()` plus `fork()`.** This preserved a reusable seed/metadata computation, but the only supported consumer created a session immediately. It also made the surface feel more abstract than the concrete operation users need. A single `fork()` with an explicit `boundary` keeps the API direct while still supporting previous-point forks.
|
||||
|
||||
|
||||
@@ -36,7 +36,7 @@ Host 通过 agent（智能体）注册表，以选定的种子和谱系创建子
|
||||
|
||||
## 曾考虑的替代方案
|
||||
|
||||
**独立的 `ctx.sessionFork` 服务。** 这是最初的实现，但评审表明它过度套用了能力 seam 模式。代码没有可替换的后端、没有额外的事件面、没有独立的所有权生命周期，也没有超出 `ctx.sessions.create({ seed, meta })` 的持久化行为。保留独立包会迫使调用方为了在会话存储原语之上执行一层策略而去发现并安装第二个服务。
|
||||
**独立的 `ctx.sessionFork` 服务。** 较早的一版迭代曾把它作为独立服务交付；它过度套用了能力 seam 模式。代码没有可替换的后端、没有额外的事件面、没有独立的所有权生命周期，也没有超出 `ctx.sessions.create({ seed, meta })` 的持久化行为。保留独立包会迫使调用方为了在会话存储原语之上执行一层策略而去发现并安装第二个服务。
|
||||
|
||||
**两个函数：`snapshot()` 加 `fork()`。** 这保留了一个可复用的种子／元数据计算，但唯一支持的消费方会立即创建会话。它还使接口看起来比用户实际需要的具体操作更抽象。单一的 `fork()` 加显式 `boundary` 使 API 保持直接，同时仍支持对先前时间点的 fork。
|
||||
|
||||
|
||||
@@ -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 .agents/notes/implemented/feature/2026-07-05-dynamic-workflows.md
|
||||
2026-07-05-dynamic-workflows.md: 4dc8744f7505aeb84a14dbf5ad0cc8cb5783d234
|
||||
2026-07-05-dynamic-workflows.zh.md: 5d3f5b014ff4532050bb0afd5464f7ec5e91a323
|
||||
2026-07-05-dynamic-workflows.md: 3e491478286eb77b56872fcbbdd5ebb6b62a5545
|
||||
2026-07-05-dynamic-workflows.zh.md: 7888d83f981a96ac5eb31d5ca6f1f8d0b4930ec7
|
||||
|
||||
@@ -52,7 +52,7 @@ An output schema makes a schema-valid committed capture mandatory for successful
|
||||
|
||||
Worker-side logic runs through an in-process `MessageChannel` so V8 coverage measures it. Unit tests cover script helpers, fatal and nullable failures, JSON boundaries, caps, cancellation, child ownership, and structured output through real loops. A built-bin smoke runs the separately bundled `lib/worker.cjs` under plain Node, a with-key e2e drives real child agents, and model-facing workflow behavior is snapshot-covered through its owning example.
|
||||
|
||||
## Deferred (documented non-goals of this cut)
|
||||
## Deferred (documented non-goals)
|
||||
|
||||
- **Background collection** (start tool → run id → completion notice → collect), designed alongside bash/subagent background unification.
|
||||
- **Journaling + resume** (`resumeFromRunId`, cached agent() prefixes) — implementing it reintroduces CC's determinism bans as a script-contract tightening (scripts may read the clock today).
|
||||
|
||||
@@ -52,7 +52,7 @@ harness 可以将一个任务委派给一个子 agent（`dsh-tool-subagent`）
|
||||
|
||||
worker 侧逻辑通过进程内 `MessageChannel` 运行，使 V8 覆盖率能够度量它。单元测试覆盖脚本辅助函数、fatal 与 nullable 失败、JSON 边界、上限、取消、子 agent 所有权和通过真实循环的结构化输出。构建后二进制文件的冒烟测试在纯 Node 下运行单独打包的 `lib/worker.cjs`，带密钥的 e2e 驱动真实子 agent，面向模型的工作流行为通过其所属示例进行快照覆盖。
|
||||
|
||||
## 延迟（本轮明确的非目标）
|
||||
## 延迟（明确的非目标）
|
||||
|
||||
- **后台收集**（启动工具 → run id → 完成通知 → 收集），与 bash/subagent 后台统一一起设计。
|
||||
- **日志化 + 恢复**（`resumeFromRunId`、缓存的 agent() 前缀）：实现它会以脚本约定收紧的形式重新引入 CC 的确定性禁令（脚本目前可以读取时钟）。
|
||||
|
||||
@@ -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 .agents/notes/implemented/feature/2026-07-14-cross-family-fs-sandbox.md
|
||||
2026-07-14-cross-family-fs-sandbox.md: e8a59be345b52f7684c574134b37f48bc49843fc
|
||||
2026-07-14-cross-family-fs-sandbox.zh.md: 228e156688ce23c10ac42b2c96b3737f796d4524
|
||||
2026-07-14-cross-family-fs-sandbox.md: 1c734a583403d1c1c9ea132a1e089362a9de4707
|
||||
2026-07-14-cross-family-fs-sandbox.zh.md: fdde507e002ac8dac452bb0f783ba8915bfcc30f
|
||||
|
||||
@@ -49,7 +49,7 @@ The [`examples/acp-agent`](../../../../examples/acp-agent/cordis.yml) compositio
|
||||
|
||||
### The enforcement point: provider, not intent gate
|
||||
|
||||
The sandbox Agent Note's original cross-family sketch put fs enforcement on the `fs/write-intent`/`fs/edit-intent` events. This Agent Note enforces in the provider instead, on two mechanical facts: the intent slots are single-decision first-wins (occupied by `dsh-fs-policy`, whose contract names a second decider a misconfiguration), and the intent events are dispatched only by `dsh-tool-fs` — a direct `ctx.fs` caller (a cordis-mounted plugin, a custom tool) bypasses them, where provider-level enforcement covers every caller by construction. The sandbox Agent Note's deferred-phase wording is updated to match in the same change.
|
||||
The sandbox Agent Note's original cross-family sketch put fs enforcement on the `fs/write-intent`/`fs/edit-intent` events. This Agent Note enforces in the provider instead, on two mechanical facts: the intent slots are single-decision first-wins (occupied by `dsh-fs-policy`, whose contract names a second decider a misconfiguration), and the intent events are dispatched only by `dsh-tool-fs` — a direct `ctx.fs` caller (a cordis-mounted plugin, a custom tool) bypasses them, where provider-level enforcement covers every caller by construction.
|
||||
|
||||
### Out of scope
|
||||
|
||||
|
||||
@@ -49,7 +49,7 @@ Status: implemented
|
||||
|
||||
### 强制执行点：提供方，而非 intent gate
|
||||
|
||||
沙箱 Agent Note 最初的跨家族草图把 fs 强制执行放在 `fs/write-intent`/`fs/edit-intent` 事件上。本 Agent Note 改为在提供方中强制执行，基于两个机制性事实:intent 槽是单决策、先到先得(已被 `dsh-fs-policy` 占据,其约定称第二个决策者为配置错误),且 intent 事件只由 `dsh-tool-fs` 派发——一个直连 `ctx.fs` 的调用方(一个 cordis 挂载插件、一个自定义工具)会绕过它们,而提供方级强制执行按构造覆盖每一个调用方。沙箱 Agent Note 的暂缓阶段措辞在同一变更中被更新以匹配。
|
||||
沙箱 Agent Note 最初的跨家族草图把 fs 强制执行放在 `fs/write-intent`/`fs/edit-intent` 事件上。本 Agent Note 改为在提供方中强制执行，基于两个机制性事实:intent 槽是单决策、先到先得(已被 `dsh-fs-policy` 占据,其约定称第二个决策者为配置错误),且 intent 事件只由 `dsh-tool-fs` 派发——一个直连 `ctx.fs` 的调用方(一个 cordis 挂载插件、一个自定义工具)会绕过它们,而提供方级强制执行按构造覆盖每一个调用方。
|
||||
|
||||
### 范围之外
|
||||
|
||||
|
||||
@@ -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 .agents/notes/implemented/feature/2026-07-16-harness-level-loop.md
|
||||
2026-07-16-harness-level-loop.md: 2efcf64adf07152b544c82f5bbf3bd8e415cd64d
|
||||
2026-07-16-harness-level-loop.zh.md: 8b83ca4a7f957f304c093e4b3f4c462c6301d6bc
|
||||
2026-07-16-harness-level-loop.md: e84a5738a55988d3b968eac829d9daaf10d7e304
|
||||
2026-07-16-harness-level-loop.zh.md: d7cda56d66d4456ac5c3c7d55bb238e85fcacbc5
|
||||
|
||||
@@ -14,7 +14,7 @@ The repository therefore needs goal-based execution above the turn/step loop, bu
|
||||
|
||||
## Decision
|
||||
|
||||
This proposal is implemented in amended form as two explicit plugin policies over existing seams:
|
||||
Two explicit plugin policies over existing seams:
|
||||
|
||||
1. **Same-session goals** retain one durable objective in the current session and admit goal-attributed continuation turns only while live activation is armed.
|
||||
2. **Fresh-agent Ralph runs** execute a fixed foreground workflow whose rounds each spawn a new structured child with no conversation seed.
|
||||
|
||||
@@ -14,7 +14,7 @@ Status: implemented
|
||||
|
||||
## 决策
|
||||
|
||||
本提案以修订后的形式实现为构建在现有 seam 之上的两项显式插件策略：
|
||||
构建在现有 seam 之上的两项显式插件策略：
|
||||
|
||||
1. **同会话目标**在当前会话中保留一个持久目标，并且只在实时激活态已激活时接纳带目标归属的续行轮次。
|
||||
2. **全新 agent Ralph 运行**执行一个固定前台工作流，其中每个 Round 都生成一个不带对话种子的全新结构化子 agent。
|
||||
|
||||
@@ -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 .agents/notes/implemented/feature/2026-07-16-persistent-pty-sessions.md
|
||||
2026-07-16-persistent-pty-sessions.md: 5d45f5fd13099352d503bc3296e4f6b7b0c53bc8
|
||||
2026-07-16-persistent-pty-sessions.zh.md: a0b4150157110b64943a42ce4e3544342e1be788
|
||||
2026-07-16-persistent-pty-sessions.md: f27d799574e61d92123c9ca4e31c5c2a9d3229b4
|
||||
2026-07-16-persistent-pty-sessions.zh.md: 0c23619faf00794c2c4e7b3f85ef961faddd99e0
|
||||
|
||||
@@ -161,7 +161,6 @@ The package ships concise tool guidance explaining persistent state, owner isola
|
||||
- Real `node-pty` and PTY-consumer tests jointly exercise shell state, shared sandbox policy, environment scrubbing, raw-mode foreground `SIGINT`, a TERM-ignoring descendant, and immediate post-disposal quiescence on supported hosts.
|
||||
- A Loader-driven `cordis.yml` test mounts the real three-package composition. ACP and headless snapshots pin the six schemas, bounded results, and errors through opt-in overlays; TUI snapshots pin terminal and generic card presentation.
|
||||
- Package contracts, the architecture map, subsystem pages, generated catalogs, and the website API describe the same shipped surface.
|
||||
- The repository CI-equivalent sequence owns type, lint, coverage, snapshot, documentation, build, hygiene, demo, and built-entry verification.
|
||||
|
||||
## Consequences
|
||||
|
||||
|
||||
@@ -161,7 +161,6 @@ plugins:
|
||||
- 真实 `node-pty` 与 PTY 消费方测试共同在受支持宿主上覆盖 shell 状态、共享沙箱策略、环境清洗、raw mode 前台 `SIGINT`、忽略 `SIGTERM` 的后代进程，以及 dispose 返回后立即完全停稳。
|
||||
- Loader 驱动的 `cordis.yml` 测试挂载真实三包组合。ACP 与 headless 快照通过 opt-in overlay 固定 6 个 schema、有界结果和错误；TUI 快照固定 terminal 与 generic 卡片展示。
|
||||
- 包约定、架构图、子系统页面、生成目录和 website API 描述同一个已发布接口。
|
||||
- 仓库 CI 等价序列负责类型、lint、覆盖率、快照、文档、构建、hygiene、demo 和 built-entry 验证。
|
||||
|
||||
## 后果
|
||||
|
||||
|
||||
@@ -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 .agents/notes/implemented/feature/2026-07-20-dsh-cli-personal-config.md
|
||||
2026-07-20-dsh-cli-personal-config.md: c00432ba2b75cc42caf23e405c24acb33d839e7a
|
||||
2026-07-20-dsh-cli-personal-config.zh.md: 91d2c938b345a7f2233da1566ac6db5b934c3148
|
||||
2026-07-20-dsh-cli-personal-config.md: f5207c5ffbd963b9b7c4a7166fa9f17a460707a9
|
||||
2026-07-20-dsh-cli-personal-config.zh.md: 24478a4b4fd5878032bf80f5b30ab9e2008da785
|
||||
|
||||
@@ -30,7 +30,7 @@ The TUI and Web register the exact personal path through Cordis HMR after boot.
|
||||
|
||||
**A separate `bin/dsh` wrapper owning the `dsh` name.** Rejected because `apps/cli` is the single product CLI for default TUI, headless, and Web dispatch. Two competing entrypoints would collide in `$PATH` and product identity.
|
||||
|
||||
**A pi-style typed settings file (`defaultProvider`/`defaultModel`/`providers`).** Rejected by the user in favor of patch semantics: the personal file is a cordis overlay over the shipped default config, not a second config vocabulary to own and translate.
|
||||
**A pi-style typed settings file (`defaultProvider`/`defaultModel`/`providers`).** Rejected in favor of patch semantics (product-owner decision): the personal file is a cordis overlay over the shipped default config, not a second config vocabulary to own and translate.
|
||||
|
||||
**A personal full `cordis.yml` that includes the requested config.** Rejected: the personal file would have to name the leaf config's path, which varies per checkout; patches invert the dependency so the bin keeps choosing the tree and the personal layer only amends it.
|
||||
|
||||
|
||||
@@ -30,7 +30,7 @@ TUI 和 Web 启动后通过 Cordis HMR（热模块替换）注册确切的个人
|
||||
|
||||
**另设一个 `bin/dsh` 包装脚本并由其占用 `dsh` 名称。** 否决，因为 `apps/cli` 是统一的产品 CLI，负责分发默认 TUI、无头和 Web 界面。两个相互竞争的入口会在 `$PATH` 和产品身份上冲突。
|
||||
|
||||
**pi 风格的类型化设置文件（`defaultProvider`/`defaultModel`/`providers`）。** 用户否决，选择补丁语义：个人文件是叠加在随仓库提供的默认配置之上的 cordis overlay，而不是需要另行拥有和翻译的第二套配置词汇。
|
||||
**pi 风格的类型化设置文件（`defaultProvider`/`defaultModel`/`providers`）。** 否决，选择补丁语义（产品负责人决策）：个人文件是叠加在随仓库提供的默认配置之上的 cordis overlay，而不是需要另行拥有和翻译的第二套配置词汇。
|
||||
|
||||
**个人完整 `cordis.yml` 去 include 请求的配置。** 否决：个人文件将不得不写死叶子配置的路径，而该路径随 checkout 变化；补丁反转了依赖方向，bin 仍然选择配置树，个人层只做修正。
|
||||
|
||||
|
||||
@@ -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 .agents/notes/implemented/feature/2026-07-23-session-telemetry-otel-revival.md
|
||||
2026-07-23-session-telemetry-otel-revival.md: e6a213af65451a2ae26a5eb685c1a0f6ab220869
|
||||
2026-07-23-session-telemetry-otel-revival.zh.md: b97840405bbde35f3b6b7f417b0615774fe43061
|
||||
2026-07-23-session-telemetry-otel-revival.md: 67ab0d28a168422a6b787a6088648746cd6079b6
|
||||
2026-07-23-session-telemetry-otel-revival.zh.md: d59dcd07e9879e1c7cafc7a104d4f2515596cab8
|
||||
|
||||
@@ -30,7 +30,7 @@ The boundary axiom holds: the harness's aspect ends at `emit()`. Batching, retry
|
||||
|
||||
**Full-log replay when no handoff cursor survived (re-export constructor seeds).** Shipped in the first revival round, then narrowed: adoption now replays from the session's construction boundary (`Session.firstLiveSeq`, the constructor-seed length — a fact the session already validated but did not expose; `header.seedLength` cannot serve, it is the durable fork-lineage value and a resumed session's constructor seed is its full stored log). A resumed session's history already shipped from the previous process under the same id, and a fork's inherited prefix already shipped in the parent's stream — re-exporting either re-billed every resume for its full history and doubled query-time counts on OTLP backends with no native ingest dedupe. Receivers stitch fork lineage via `session.parent_id` + `session.seed_length`. What the narrowing gives up, consistently with the at-most-once stance: a resume no longer backfills records the previous process failed to deliver (telemetry unmounted then, or queued at crash) — the full replay's only real benefit, bought at the common case's expense. A deployment that states a backfill requirement needs the deferred outbox above, not replay. The boundary also swallows the synthetic turn closers `SessionPersistence.load()` writes when repairing a crash-interrupted log (they sit below `firstLiveSeq` despite never existing in the previous process) — deliberate, not incidental: exporting a synthetic closer cannot complete the remote turn whose real tail records died in the crashed process's queue, it can only make an incomplete turn look closed. The wire stream stays faithful to what the crashed process actually shipped; receivers read a never-closed turn on a resumed stream as "the previous process died inside it" (the OTel README states the rule), and a later clean `shutdown` marker attests only to the resumed process's exit. Threading the pre-repair boundary through load/prepare so repairs export as live events would couple three packages to un-ship that signal.
|
||||
|
||||
**Forwarding the seam's turn-boundary `flush()` hint to the OTel provider's `forceFlush()`.** Shipped in the first revival round, then removed after three review rounds each found a new silent-loss path in the same wrapper state: a dispose racing an in-flight flush (the SDK's concurrent-flush guard makes shutdown's internal drain skip), overlapping hints displacing the retained promise, and the provider's fixed 30-second flush timeout rejecting while the processor still drains. Every path exists only because the forwarding made this backend the process's second flusher against undocumented SDK internals from the upstream experimental tree; with no `flush()` implemented, the batch processor is the only flusher, its `scheduledDelayMillis` (already deployment-tunable through the `processor` passthrough) governs export cadence, and `shutdown()`'s drain is complete by construction. Reinstate only if a deployment states a turn-boundary latency requirement `scheduledDelayMillis` cannot meet — and then by calling the retained `BatchLogRecordProcessor`'s own `forceFlush()`, never the provider's timeout-wrapped one.
|
||||
**Forwarding the seam's turn-boundary `flush()` hint to the OTel provider's `forceFlush()`.** Shipped in the first revival round, then removed: three distinct silent-loss paths shared the wrapper state — a dispose racing an in-flight flush (the SDK's concurrent-flush guard makes shutdown's internal drain skip), overlapping hints displacing the retained promise, and the provider's fixed 30-second flush timeout rejecting while the processor still drains. Every path exists only because the forwarding made this backend the process's second flusher against undocumented SDK internals from the upstream experimental tree; with no `flush()` implemented, the batch processor is the only flusher, its `scheduledDelayMillis` (already deployment-tunable through the `processor` passthrough) governs export cadence, and `shutdown()`'s drain is complete by construction. Reinstate only if a deployment states a turn-boundary latency requirement `scheduledDelayMillis` cannot meet — and then by calling the retained `BatchLogRecordProcessor`'s own `forceFlush()`, never the provider's timeout-wrapped one.
|
||||
|
||||
## Consequences
|
||||
|
||||
|
||||
@@ -30,7 +30,7 @@ Status: implemented
|
||||
|
||||
**handoff 游标未存活时全量回放日志（重新导出构造函数种子）。** 首轮复活曾交付此方案，其后收窄：接管操作现在从会话的构造边界起回放（`Session.firstLiveSeq`，即构造函数种子长度，这一事实会话早已校验过却未曾暴露；`header.seedLength` 不能胜任：它是持久保存的 fork 谱系（lineage）值，而恢复会话的构造函数种子是其完整的已存储日志）。恢复会话的历史已由上一个进程以同一 id 发出，fork 继承的前缀也已在父会话的流中发出；再次导出任何一者，都会让每次恢复为其完整历史重复付费，并在没有原生摄取去重的 OTLP 后端上使查询时的计数翻倍。接收端基于 `session.parent_id` + `session.seed_length` 拼接 fork 谱系。此次收窄放弃的内容与至多一次立场一致：恢复不再回填上一个进程未能投递的记录（彼时遥测未挂载，或崩溃时仍在队列中）——这本是全量回放唯一的真实收益，代价却由常见情形承担。提出回填要求的部署需要的是上文已推迟的 outbox，而不是回放。该边界同样吞掉 `SessionPersistence.load()` 修复被崩溃打断的日志时写入的合成轮次关闭事件（它们落在 `firstLiveSeq` 之前，尽管在上一个进程中从未存在过）。这是有意为之，而非附带效果：远端轮次的真实尾部记录已随崩溃进程的队列一同消亡，导出合成关闭事件无法补全该轮次，只会让一个未完成的轮次看起来已经关闭。导出的流忠实于崩溃进程实际发出的内容；接收端会把恢复后的流中一个从未关闭的轮次读作「上一个进程死在了该轮次之内」（OTel README 陈述了这条规则），其后干净的 `shutdown` 标记也只证明恢复后进程自身的退出。若为让修复以实时事件的身份导出而将修复前边界贯穿 load/prepare 传递，将使三个包相互耦合，只为抹除这一信号。
|
||||
|
||||
**将 seam 的轮次边界 `flush()` 提示转发到 OTel 提供方的 `forceFlush()`。** 首轮复活曾交付此转发，其后移除：三轮评审在同一份包装层状态中各发现一条新的静默丢失路径——dispose 与进行中的 flush 之间的竞态（SDK 的并发 flush 防护会令 shutdown 的内部排空被跳过）、相互重叠的提示顶掉留存的 promise、以及提供方固定的 30 秒 flush 超时在批处理器仍在排空时便 reject。这些路径存在的唯一原因，是该转发让这个后端成为进程内第二个执行 flush 的组件，面对的还是上游实验性（experimental）源码树中未见诸文档的 SDK 内部行为；不实现 `flush()` 时，批处理器就是唯一执行 flush 的组件，其 `scheduledDelayMillis`（已可由部署方经 `processor` passthrough 调优）决定导出节奏，`shutdown()` 的排空从构造上就是完整的。仅当某个部署提出 `scheduledDelayMillis` 无法满足的轮次边界延迟要求时才恢复此转发——且届时应调用留存的 `BatchLogRecordProcessor` 自身的 `forceFlush()`，绝不调用提供方那个带超时包装的版本。
|
||||
**将 seam 的轮次边界 `flush()` 提示转发到 OTel 提供方的 `forceFlush()`。** 首轮复活曾交付此转发，其后移除：三条不同的静默丢失路径共用同一份包装层状态——dispose 与进行中的 flush 之间的竞态（SDK 的并发 flush 防护会令 shutdown 的内部排空被跳过）、相互重叠的提示顶掉留存的 promise、以及提供方固定的 30 秒 flush 超时在批处理器仍在排空时便 reject。这些路径存在的唯一原因，是该转发让这个后端成为进程内第二个执行 flush 的组件，面对的还是上游实验性（experimental）源码树中未见诸文档的 SDK 内部行为；不实现 `flush()` 时，批处理器就是唯一执行 flush 的组件，其 `scheduledDelayMillis`（已可由部署方经 `processor` passthrough 调优）决定导出节奏，`shutdown()` 的排空从构造上就是完整的。仅当某个部署提出 `scheduledDelayMillis` 无法满足的轮次边界延迟要求时才恢复此转发——且届时应调用留存的 `BatchLogRecordProcessor` 自身的 `forceFlush()`，绝不调用提供方那个带超时包装的版本。
|
||||
|
||||
## 后果
|
||||
|
||||
|
||||
@@ -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 .agents/notes/implemented/feature/2026-07-25-session-list-browsing-and-manual-order.md
|
||||
2026-07-25-session-list-browsing-and-manual-order.md: bd04e7f74c8a4540d68e60ad68965e05de76bce9
|
||||
2026-07-25-session-list-browsing-and-manual-order.zh.md: 2bf778284aa551c75f1206ed08ca073e47b7a15d
|
||||
2026-07-25-session-list-browsing-and-manual-order.md: 323c0db16cc6b9e83155a3fb873ab94e4facd3a2
|
||||
2026-07-25-session-list-browsing-and-manual-order.zh.md: 85b2b319f03113480b3953c21940c123ba594ca8
|
||||
|
||||
@@ -44,7 +44,7 @@ ui-sidebar shrinks to the column-geometry shell: brand row, fold state machine,
|
||||
|
||||
**Optimistic reordering on drop** — client-first reordering needs failure rollback, one more entangled state in the object layer; local/LAN round-trips are millisecond-scale, so waiting for the host response is imperceptible. With a single order authority (trust the host completely), the frontend never invents an order.
|
||||
|
||||
**Keep the rename dialog in ui-sidebar (smallest change)** — that is the problem itself: workspace-domain dialogs scattered in a borrowed slot, with each addition (the Delete confirmation is coming) repeating the cross-package wiring. Review first considered moving only the rename modal; the ruling was to give the whole browsing region to ui-workspace and leave the shell geometry-only.
|
||||
**Keep the rename dialog in ui-sidebar (smallest change)** — that is the problem itself: workspace-domain dialogs scattered in a borrowed slot, with each addition (the Delete confirmation is coming) repeating the cross-package wiring. Moving only the rename modal would repeat that wiring on the next dialog; the whole browsing region goes to ui-workspace and the shell stays geometry-only.
|
||||
|
||||
**Nest sessions by fork lineage in WorkSpace mode** — nesting makes the current child visible only while its ancestors are expanded and limits in-group manual ordering to root nodes; `parentId` is lineage data, not a list-navigation structure. Flattening all sessions into peer rows lets each row be opened, searched, and ordered independently; In one list still disables drag because it has no workspace persistence carrier.
|
||||
|
||||
|
||||
@@ -44,7 +44,7 @@ ui-sidebar 缩为列几何壳:品牌行、折叠状态机、New Session、Settin
|
||||
|
||||
**drop 后乐观重排** —— client 先行重排需失败回滚,对象层多一块纠缠态;本地/局域网往返毫秒级,等 host 响应的简单方案肉眼无感。顺序权威单一化(完全信 host)后,前端永不发明顺序。
|
||||
|
||||
**rename 对话框留在 ui-sidebar(最小改动)** —— 正是问题本身:workspace 域的对话框散落在借来的坑里,每加一个(Delete 确认框将至)都重演跨包接线。评审中先议了「只挪 rename Modal」的中间态,最终裁定整个浏览区域归 ui-workspace,壳只留几何。
|
||||
**rename 对话框留在 ui-sidebar(最小改动)** —— 正是问题本身:workspace 域的对话框散落在借来的坑里,每加一个(Delete 确认框将至)都重演跨包接线。只挪 rename Modal 会在下一个对话框上重演这份接线;整个浏览区域归 ui-workspace,壳只留几何。
|
||||
|
||||
**WorkSpace 模式按 fork 谱系嵌套 session** —— 嵌套会让当前子会话依赖祖先展开态才能可见，也让组内手动序只能移动根节点；`parentId` 是 lineage 数据，不是列表导航结构。所有 session 拍平成同级行后，每行都可独立打开、搜索与排序；In one list 仍因没有 workspace 持久化载体而禁用拖拽。
|
||||
|
||||
|
||||
@@ -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 .agents/notes/implemented/feature/2026-07-26-code-dispatch-log-spill.md
|
||||
2026-07-26-code-dispatch-log-spill.md: 3892a4a5a21c03d97d1873c68e2228119010e5c5
|
||||
2026-07-26-code-dispatch-log-spill.zh.md: c98b29e491e059fe27eb5b1ccea1b9664dce4639
|
||||
2026-07-26-code-dispatch-log-spill.md: 19d37c7ec2dbe5192e4c7e7ecd26e5b7f1467606
|
||||
2026-07-26-code-dispatch-log-spill.zh.md: 8dd270278932011db9658f9e4d5c1a1b6fe707ec
|
||||
|
||||
@@ -4,7 +4,7 @@ Status: implemented
|
||||
|
||||
English | [中文](2026-07-26-code-dispatch-log-spill.zh.md)
|
||||
|
||||
> Scope: the fourth PR of the Code Mode UI stack — bounding the `tool/code-dispatch` event's content with the existing spill machinery. The [host foundation note](2026-07-26-code-dispatch-ui-foundation.md) accepted the unbounded log deliberately and named this PR as the payoff point; the [live-parallel note](2026-07-26-code-mode-live-parallel-dispatch.md) settled the event pair this shaping hooks into.
|
||||
> Scope: bounding the `tool/code-dispatch` event's content with the existing spill machinery. The [host foundation note](2026-07-26-code-dispatch-ui-foundation.md) accepted the unbounded log deliberately with this spill integration as the payoff point; the [live-parallel note](2026-07-26-code-mode-live-parallel-dispatch.md) settled the event pair this shaping hooks into.
|
||||
|
||||
## Problem
|
||||
|
||||
|
||||
@@ -4,7 +4,7 @@ Status: implemented
|
||||
|
||||
[English](2026-07-26-code-dispatch-log-spill.md) | 中文
|
||||
|
||||
> 范围：Code Mode UI 堆叠 PR（Pull Request）链的第四个 PR，即用既有的 spill 机制为 `tool/code-dispatch` 事件的内容施加边界。[宿主侧基础 Agent Note](2026-07-26-code-dispatch-ui-foundation.md)当初有意接受了不设上限的日志，并指明本 PR 就是兑现点；[实时并行 Agent Note](2026-07-26-code-mode-live-parallel-dispatch.md)敲定了本次整形所挂接的事件对。
|
||||
> 范围：用既有的 spill 机制为 `tool/code-dispatch` 事件的内容施加边界。[宿主侧基础 Agent Note](2026-07-26-code-dispatch-ui-foundation.md)当初有意接受了不设上限的日志，并以这次 spill 集成为兑现点；[实时并行 Agent Note](2026-07-26-code-mode-live-parallel-dispatch.md)敲定了本次整形所挂接的事件对。
|
||||
|
||||
## 问题
|
||||
|
||||
@@ -20,7 +20,7 @@ Status: implemented
|
||||
|
||||
## 曾考虑的替代方案
|
||||
|
||||
**在桥接层内部用普通上限施加边界（不做 spill）。** 否决：没有定位符的截断会丢失回放与 UI 可能需要的数据，还会重新引入本堆叠 PR 链已经移除的「截断摘要」降级渲染路径。
|
||||
**在桥接层内部用普通上限施加边界（不做 spill）。** 否决：没有定位符的截断会丢失回放与 UI 可能需要的数据，还会重新引入本堆叠 PR（Pull Request）链已经移除的「截断摘要」降级渲染路径。
|
||||
|
||||
**直接在桥接层内做 spill（从 code-mode.ts 调用 `ctx.spillStore`）。** 否决：注册表会因此对 spill 能力产生硬依赖；waterfall 则把策略留在所有其他 spill 决策所在的地方，既可组合也可禁用（省略 `maxInlineBytes` 依然意味着真正的 no-op）。
|
||||
|
||||
|
||||
@@ -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 .agents/notes/implemented/feature/2026-07-26-code-dispatch-ui-foundation.md
|
||||
2026-07-26-code-dispatch-ui-foundation.md: 1714472018a415114efed7ce189a3d82268dd8e3
|
||||
2026-07-26-code-dispatch-ui-foundation.zh.md: 8ede615bf15b99c5ecf9a8da427b571180921e54
|
||||
2026-07-26-code-dispatch-ui-foundation.md: 4115a1898de7d2cce01346c3f005fcd19c325f4c
|
||||
2026-07-26-code-dispatch-ui-foundation.zh.md: aeb57b93d781163dd0a4747ac03053c65deda1db
|
||||
|
||||
@@ -4,11 +4,11 @@ Status: implemented
|
||||
|
||||
English | [中文](2026-07-26-code-dispatch-ui-foundation.zh.md)
|
||||
|
||||
> Scope: the host-side contract changes that let a UI render a Code Mode turn with the same fidelity as native tool calls — the first PR of the Code Mode web-UI stack. The [Code Mode foundation](2026-06-15-code-mode.md) owns the transport design; this note owns the model-visible `description` parameter, the full-content `tool/code-dispatch` payload, and the temporary `DSH_TOOLS_MODE` enablement switch for the `dsh` config tree.
|
||||
> Scope: the host-side contract changes that let a UI render a Code Mode turn with the same fidelity as native tool calls — the foundation the other Code Mode UI notes build on. The [Code Mode foundation](2026-06-15-code-mode.md) owns the transport design; this note owns the model-visible `description` parameter, the full-content `tool/code-dispatch` payload, and the temporary `DSH_TOOLS_MODE` enablement switch for the `dsh` config tree.
|
||||
|
||||
## Problem
|
||||
|
||||
A `run_code` turn was opaque in every product surface. The call card's title was the raw program text — unreadable at row width, and unlike `bash` (whose required `description` labels the card while the command rides the expanded input) there was no model-authored label at all. The `tool/code-dispatch` event carried only a 200-char, cwd-normalized `resultSummary` of each sub-call, so no UI could ever show what a sub-call actually returned: the planned web conversation view renders sub-calls through the exact components that render native `tool/result` cards, and a bounded summary cannot feed a native-parity card. And the `dsh web` composition had no way to enable Code Mode at all — the `tools` row pinned the schema default and the runtime was absent from the tree.
|
||||
A `run_code` turn was opaque in every product surface. The call card's title was the raw program text — unreadable at row width, and unlike `bash` (whose required `description` labels the card while the command rides the expanded input) there was no model-authored label at all. The `tool/code-dispatch` event carried only a 200-char, cwd-normalized `resultSummary` of each sub-call, so no UI could ever show what a sub-call actually returned: the web conversation view ([chat sub-call rows](2026-07-26-code-mode-chat-subcall-rows.md)) renders sub-calls through the exact components that render native `tool/result` cards, and a bounded summary cannot feed a native-parity card. And the `dsh web` composition had no way to enable Code Mode at all — the `tools` row pinned the schema default and the runtime was absent from the tree.
|
||||
|
||||
## Decision
|
||||
|
||||
@@ -20,7 +20,7 @@ Three changes, one per obstacle:
|
||||
|
||||
## Alternatives considered
|
||||
|
||||
**Keep a bounded summary (raised cap, or a cap + `truncated` flag).** Rejected: the stack's settled requirement is that sub-call rows and details render *identically* to native calls; any cap forces a second, degraded render path plus truncation UI. The cost accepted instead: a program that reads a large file logs the rendered content verbatim on the dispatch event — uncapped, outside spill policy, growing the session log by the same bytes. Spill integration for the logged copy is deferred to a later PR of this stack (the projection exists; wiring it into the bridge is mechanical once the event shape settles with the start/end pair).
|
||||
**Keep a bounded summary (raised cap, or a cap + `truncated` flag).** Rejected: the stack's settled requirement is that sub-call rows and details render *identically* to native calls; any cap forces a second, degraded render path plus truncation UI. The cost accepted instead: a program that reads a large file logs the rendered content verbatim on the dispatch event — uncapped, outside spill policy, growing the session log by the same bytes. Spill integration for the logged copy shipped as [code-dispatch log spill](2026-07-26-code-dispatch-log-spill.md).
|
||||
|
||||
**A `--tools-mode` CLI flag or profile key.** Deferred, not rejected: the flag grammar suggests permanence, and the profile json is user config — both would harden a seam the per-session design intends to remove. An env var reads as the workaround it is.
|
||||
|
||||
@@ -28,4 +28,4 @@ Three changes, one per obstacle:
|
||||
|
||||
## Consequences
|
||||
|
||||
Session format keeps `SESSION_FORMAT_VERSION` 0 (pre-release churn does not bump; old logs with `resultSummary` simply carry an extra unread field and lack `content` — v0 makes no compatibility promise). Existing code-mode snapshot fixtures were re-recorded. Model-visible surface grew: the `run_code` schema (one required parameter) and every code-mode system prompt/tool-schema snapshot changed. The web UI stack (subsequent PRs) builds directly on the new event payload; live per-sub-call running state needs a dispatch start/end pair that will reshape this event again.
|
||||
Session format keeps `SESSION_FORMAT_VERSION` 0 (pre-release churn does not bump; old logs with `resultSummary` simply carry an extra unread field and lack `content` — v0 makes no compatibility promise). Existing code-mode snapshot fixtures were re-recorded. Model-visible surface grew: the `run_code` schema (one required parameter) and every code-mode system prompt/tool-schema snapshot changed. The web UI work builds directly on the new event payload; live per-sub-call running state reshaped this event into a dispatch start/end pair ([live parallel dispatch](2026-07-26-code-mode-live-parallel-dispatch.md)).
|
||||
|
||||
@@ -4,11 +4,11 @@ Status: implemented
|
||||
|
||||
[English](2026-07-26-code-dispatch-ui-foundation.md) | 中文
|
||||
|
||||
> 范围：让 UI 能以与原生工具调用相同的保真度渲染 Code Mode 轮次的宿主侧约定变更，即 Code Mode Web UI 堆叠 PR（Pull Request）链的第一个 PR。传输设计归 [Code Mode 基础](2026-06-15-code-mode.md)所有；模型可见的 `description` 参数、携带完整内容的 `tool/code-dispatch` 载荷，以及 `dsh` 配置树上临时的 `DSH_TOOLS_MODE` 启用开关，归本篇所有。
|
||||
> 范围：让 UI 能以与原生工具调用相同的保真度渲染 Code Mode 轮次的宿主侧约定变更，即其他 Code Mode UI Agent Note 赖以构建的基础。传输设计归 [Code Mode 基础](2026-06-15-code-mode.md)所有；模型可见的 `description` 参数、携带完整内容的 `tool/code-dispatch` 载荷，以及 `dsh` 配置树上临时的 `DSH_TOOLS_MODE` 启用开关，归本篇所有。
|
||||
|
||||
## 问题
|
||||
|
||||
`run_code` 轮次过去在每个产品界面上都不透明。调用卡片的标题就是原始程序文本，在行宽内无法阅读；而且不同于 `bash`（其必填的 `description` 用作卡片标签，命令本身放在展开后的输入里），`run_code` 完全没有模型撰写的标签。`tool/code-dispatch` 事件过去只携带每个子调用的 `resultSummary`（上限 200 字符、经 cwd 归一化），因此任何 UI 都无从展示子调用实际返回的内容：规划中的 Web 对话视图会用渲染原生 `tool/result` 卡片的同一批组件来渲染子调用，而有界摘要无法支撑一张与原生同等保真的卡片。同时，`dsh web` 组合此前根本无法启用 Code Mode：`tools` 行钉死在 schema 默认值上，配置树里也完全没有该运行时。
|
||||
`run_code` 轮次过去在每个产品界面上都不透明。调用卡片的标题就是原始程序文本，在行宽内无法阅读；而且不同于 `bash`（其必填的 `description` 用作卡片标签，命令本身放在展开后的输入里），`run_code` 完全没有模型撰写的标签。`tool/code-dispatch` 事件过去只携带每个子调用的 `resultSummary`（上限 200 字符、经 cwd 归一化），因此任何 UI 都无从展示子调用实际返回的内容：Web 对话视图（[chat 子调用行](2026-07-26-code-mode-chat-subcall-rows.md)）会用渲染原生 `tool/result` 卡片的同一批组件来渲染子调用，而有界摘要无法支撑一张与原生同等保真的卡片。同时，`dsh web` 组合此前根本无法启用 Code Mode：`tools` 行钉死在 schema 默认值上，配置树里也完全没有该运行时。
|
||||
|
||||
## 决策
|
||||
|
||||
@@ -20,7 +20,7 @@ Status: implemented
|
||||
|
||||
## 曾考虑的替代方案
|
||||
|
||||
**保留有界摘要（提高上限，或上限加 `truncated` 标志）。** 否决：本堆叠 PR 链已敲定的要求是，子调用的行与详情必须与原生调用渲染得*完全一致*；任何上限都会强制引入第二条降级的渲染路径，外加截断 UI。转而接受的代价是：读取大文件的程序会把渲染后的内容原样记录在分发事件上，不设上限、位于 spill 策略之外，并以同样的字节数增大会话日志。持久化副本的 spill 集成推迟到本链靠后的 PR（投影已经存在；待事件形状随 start/end 事件对一同定形，把它接入桥接层只是机械工作）。
|
||||
**保留有界摘要（提高上限，或上限加 `truncated` 标志）。** 否决：本堆叠 PR（Pull Request）链已敲定的要求是，子调用的行与详情必须与原生调用渲染得*完全一致*；任何上限都会强制引入第二条降级的渲染路径，外加截断 UI。转而接受的代价是：读取大文件的程序会把渲染后的内容原样记录在分发事件上，不设上限、位于 spill 策略之外，并以同样的字节数增大会话日志。持久化副本的 spill 集成已作为 [code-dispatch 日志 spill](2026-07-26-code-dispatch-log-spill.md) 交付。
|
||||
|
||||
**一个 `--tools-mode` CLI（命令行界面）标志或 profile 配置键。** 推迟，而非否决：标志语法暗示永久性，profile JSON 又是用户配置；两者都会固化这个 seam，而按会话选择的设计本就打算移除它。环境变量则如实呈现了它权宜之计的本质。
|
||||
|
||||
@@ -28,4 +28,4 @@ Status: implemented
|
||||
|
||||
## 后果
|
||||
|
||||
会话格式保持 `SESSION_FORMAT_VERSION` 为 0（预发布阶段的变动不递增版本号；携带 `resultSummary` 的旧日志只是多出一个不被读取的字段并缺少 `content`；v0 不作任何兼容性承诺）。既有的 Code Mode 快照 fixture（测试前置数据）已重新录制。模型可见表面扩大了：`run_code` 的 schema（新增一个必填参数）以及每一份 Code Mode 系统提示词／工具 schema 快照都发生了变化。Web UI 堆叠 PR 链（后续各 PR）直接构建在新的事件载荷之上；每个子调用的实时运行状态还需要一对分发 start/end 事件，这将再次重塑本事件的形状。
|
||||
会话格式保持 `SESSION_FORMAT_VERSION` 为 0（预发布阶段的变动不递增版本号；携带 `resultSummary` 的旧日志只是多出一个不被读取的字段并缺少 `content`；v0 不作任何兼容性承诺）。既有的 Code Mode 快照 fixture（测试前置数据）已重新录制。模型可见表面扩大了：`run_code` 的 schema（新增一个必填参数）以及每一份 Code Mode 系统提示词／工具 schema 快照都发生了变化。Web UI 工作直接构建在新的事件载荷之上；每个子调用的实时运行状态已把本事件重塑为一对分发 start/end 事件（[实时并行分发](2026-07-26-code-mode-live-parallel-dispatch.md)）。
|
||||
|
||||
@@ -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 .agents/notes/implemented/feature/2026-07-26-code-mode-chat-subcall-rows.md
|
||||
2026-07-26-code-mode-chat-subcall-rows.md: 40b4b8fd8c5cea8e9aea01731d7eceff692db188
|
||||
2026-07-26-code-mode-chat-subcall-rows.zh.md: 9981fded054f663dd539660ed2a2eca68a9d3138
|
||||
2026-07-26-code-mode-chat-subcall-rows.md: 4bf608c36de78818b3ab40c6798ee6eafabe99a1
|
||||
2026-07-26-code-mode-chat-subcall-rows.zh.md: 98680a90bf613ba2dd9b974a809ea5300400f9ea
|
||||
|
||||
@@ -29,4 +29,4 @@ With Code Mode enabled, the chat view showed one opaque `run_code` row: raw prog
|
||||
|
||||
## Consequences
|
||||
|
||||
Custom toolview registrations apply to sub-calls for free — and deliberately: there is no per-registration opt-out short of the component reading its own context, which no current consumer needs. Selection highlighting reaches nested rows through the same `selectedCallId` channel (group membership searches the whole tree). Trajectory/waterfall still render `run_code` as a single row — their sub-call spans are deferred to the PR that adds dispatch timing (start/end events), without which a waterfall span would be a lie. Fixture turn 64 (`?fixture`) plus the `code-mode-round` browser e2e (recorded real round, keyless replay) pin the full surface; the jsdom and Runtime suites pin slot dispatch, error states, recursive details resolution, history projection, and reference-stable path copying.
|
||||
Custom toolview registrations apply to sub-calls for free — and deliberately: there is no per-registration opt-out short of the component reading its own context, which no current consumer needs. Selection highlighting reaches nested rows through the same `selectedCallId` channel (group membership searches the whole tree). Trajectory/waterfall now draw sub-call spans from the dispatch timing pair ([live parallel dispatch](2026-07-26-code-mode-live-parallel-dispatch.md)); without that timing a waterfall span would be a lie. Fixture turn 64 (`?fixture`) plus the `code-mode-round` browser e2e (recorded real round, keyless replay) pin the full surface; the jsdom and Runtime suites pin slot dispatch, error states, recursive details resolution, history projection, and reference-stable path copying.
|
||||
|
||||
@@ -29,4 +29,4 @@ Status: implemented
|
||||
|
||||
## 后果
|
||||
|
||||
自定义 toolview 注册免费适用于子调用——而且是刻意为之：不存在按注册粒度的退出机制，唯一的出路是组件自行读取自身上下文，而当前没有任何消费方需要这么做。选中高亮经由同一条 `selectedCallId` 通道到达嵌套行（分组归属会搜索整棵树）。trajectory/waterfall 仍把 `run_code` 渲染为单独一行——它们的子调用 span 推迟到增加分发计时（start/end 事件）的那个 PR；缺少计时，waterfall 上的 span 就是在撒谎。fixture（测试前置数据）的轮次 64（`?fixture`），加上 `code-mode-round` 浏览器 e2e（录制的真实轮次、无密钥回放），共同锁定整个界面；jsdom 与运行时测试套件则锁定 slot 分发、错误状态、递归详情解析、历史投影与引用稳定的路径复制。
|
||||
自定义 toolview 注册免费适用于子调用——而且是刻意为之：不存在按注册粒度的退出机制，唯一的出路是组件自行读取自身上下文，而当前没有任何消费方需要这么做。选中高亮经由同一条 `selectedCallId` 通道到达嵌套行（分组归属会搜索整棵树）。trajectory/waterfall 现在依据分发计时事件对（[实时并行分发](2026-07-26-code-mode-live-parallel-dispatch.md)）绘制子调用 span；缺少计时，waterfall 上的 span 就是在撒谎。fixture（测试前置数据）的轮次 64（`?fixture`），加上 `code-mode-round` 浏览器 e2e（录制的真实轮次、无密钥回放），共同锁定整个界面；jsdom 与运行时测试套件则锁定 slot 分发、错误状态、递归详情解析、历史投影与引用稳定的路径复制。
|
||||
|
||||
@@ -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 .agents/notes/implemented/feature/2026-07-26-code-mode-live-parallel-dispatch.md
|
||||
2026-07-26-code-mode-live-parallel-dispatch.md: e85d1f99f58f1aae28091cd8875ee87a6df5a1e7
|
||||
2026-07-26-code-mode-live-parallel-dispatch.zh.md: c7f91f570e20e27aade0e8f47606d31b1d8ae7eb
|
||||
2026-07-26-code-mode-live-parallel-dispatch.md: 998152ee43d93e5190062cb632e20a3123cda4f9
|
||||
2026-07-26-code-mode-live-parallel-dispatch.zh.md: ac9b06cf1f2c197d4a8ea1dd69c8fb0840878097
|
||||
|
||||
@@ -4,11 +4,11 @@ Status: implemented
|
||||
|
||||
English | [中文](2026-07-26-code-mode-live-parallel-dispatch.zh.md)
|
||||
|
||||
> Scope: the third PR of the Code Mode UI stack — the `tool/code-dispatch-start` event, per-sub-call running state in the web chat, and the bridge's scheduler reusing the native concurrency contract. Builds on the [host foundation](2026-07-26-code-dispatch-ui-foundation.md) and [chat sub-call rows](2026-07-26-code-mode-chat-subcall-rows.md); the native contract itself is owned by the [parallel tool-call note](2026-07-10-parallel-tool-call-execution.md).
|
||||
> Scope: the `tool/code-dispatch-start` event, per-sub-call running state in the web chat, and the bridge's scheduler reusing the native concurrency contract. Builds on the [host foundation](2026-07-26-code-dispatch-ui-foundation.md) and [chat sub-call rows](2026-07-26-code-mode-chat-subcall-rows.md); the native contract itself is owned by the [parallel tool-call note](2026-07-10-parallel-tool-call-execution.md).
|
||||
|
||||
## Problem
|
||||
|
||||
Two gaps remained after the first two PRs. Sub-call rows appeared only when each dispatch *settled* — while one ran, the UI showed nothing for it, so a slow sub-call read as a stalled parent. And the bridge serialized every binding call ("even `Promise.all` executes one at a time"), a placeholder from before tools carried concurrency metadata: `isConcurrencySafe` now exists, the loop scheduler already runs native siblings in bounded pools, and a Code Mode program awaiting three independent reads paid 3× the latency the native path would.
|
||||
Two gaps remained after the host foundation and chat sub-call rows shipped. Sub-call rows appeared only when each dispatch *settled* — while one ran, the UI showed nothing for it, so a slow sub-call read as a stalled parent. And the bridge serialized every binding call ("even `Promise.all` executes one at a time"), a placeholder from before tools carried concurrency metadata: `isConcurrencySafe` now exists, the loop scheduler already runs native siblings in bounded pools, and a Code Mode program awaiting three independent reads paid 3× the latency the native path would.
|
||||
|
||||
## Decision
|
||||
|
||||
@@ -29,4 +29,4 @@ Two gaps remained after the first two PRs. Sub-call rows appeared only when each
|
||||
|
||||
## Consequences
|
||||
|
||||
Programs get native-grade latency for independent reads with no new model-side API — `Promise.all` simply works better, and prompt guidance changed accordingly. The web UI shows per-sub-call running rings live (fixture emits start/settle pairs; jsdom pins the running shape; the runtime spec pins in-place settlement, out-of-order completion, and callTime pairing). PR6 (trajectory/waterfall spans) can now draw truthful spans from the pair's timing. The spill PR (next) inherits the settle event as its single bounding point.
|
||||
Programs get native-grade latency for independent reads with no new model-side API — `Promise.all` simply works better, and prompt guidance changed accordingly. The web UI shows per-sub-call running rings live (fixture emits start/settle pairs; jsdom pins the running shape; the runtime spec pins in-place settlement, out-of-order completion, and callTime pairing). Trajectory/waterfall sub-call spans draw truthful timing from the pair. Spill bounding ([code-dispatch log spill](2026-07-26-code-dispatch-log-spill.md)) inherits the settle event as its single bounding point.
|
||||
|
||||
@@ -4,11 +4,11 @@ Status: implemented
|
||||
|
||||
[English](2026-07-26-code-mode-live-parallel-dispatch.md) | 中文
|
||||
|
||||
> 范围：Code Mode UI 堆叠 PR（Pull Request）链的第三个 PR，涵盖 `tool/code-dispatch-start` 事件、Web chat 中每个子调用的运行状态，以及桥接层调度器对原生并发约定的复用。构建在[宿主侧基础](2026-07-26-code-dispatch-ui-foundation.md)与 [chat 子调用行](2026-07-26-code-mode-chat-subcall-rows.md)之上；原生约定本身归[并行工具调用 Agent Note](2026-07-10-parallel-tool-call-execution.md) 所有。
|
||||
> 范围：`tool/code-dispatch-start` 事件、Web chat 中每个子调用的运行状态，以及桥接层调度器对原生并发约定的复用。构建在[宿主侧基础](2026-07-26-code-dispatch-ui-foundation.md)与 [chat 子调用行](2026-07-26-code-mode-chat-subcall-rows.md)之上；原生约定本身归[并行工具调用 Agent Note](2026-07-10-parallel-tool-call-execution.md) 所有。
|
||||
|
||||
## 问题
|
||||
|
||||
前两个 PR 之后仍留有两个缺口。子调用行过去只在每次分发*结算*后才出现：某次分发运行期间，UI 对它毫无展示，于是一个慢的子调用看上去就像父调用卡住了。而桥接层过去把每一次绑定调用都串行化（「即使 `Promise.all` 也一次只执行一个」），这是工具尚未携带并发元数据时留下的占位实现：如今 `isConcurrencySafe` 已经存在，agent loop（智能体循环）调度器早已在有界并发池中运行原生兄弟调用，而一个等待三个独立读取的 Code Mode 程序，付出的延迟却是原生路径的 3 倍。
|
||||
宿主侧基础与 chat 子调用行交付之后仍留有两个缺口。子调用行过去只在每次分发*结算*后才出现：某次分发运行期间，UI 对它毫无展示，于是一个慢的子调用看上去就像父调用卡住了。而桥接层过去把每一次绑定调用都串行化（「即使 `Promise.all` 也一次只执行一个」），这是工具尚未携带并发元数据时留下的占位实现：如今 `isConcurrencySafe` 已经存在，agent loop（智能体循环）调度器早已在有界并发池中运行原生兄弟调用，而一个等待三个独立读取的 Code Mode 程序，付出的延迟却是原生路径的 3 倍。
|
||||
|
||||
## 决策
|
||||
|
||||
@@ -29,4 +29,4 @@ Status: implemented
|
||||
|
||||
## 后果
|
||||
|
||||
程序不需要任何新的模型侧 API，独立读取就获得了原生级的延迟：`Promise.all` 直接变得更好用，提示词指引也随之修改。Web UI 实时显示每个子调用的运行指示环：fixture（测试前置数据）发出成对的 start/settle 事件；jsdom 锁定运行中形状；运行时测试锁定原位结算、乱序完成与 callTime 配对。PR6（trajectory/waterfall 的 span）现在可以依据这对事件的计时绘制如实的 span。spill PR（下一个）则继承结算事件，作为自己唯一施加边界的位置。
|
||||
程序不需要任何新的模型侧 API，独立读取就获得了原生级的延迟：`Promise.all` 直接变得更好用，提示词指引也随之修改。Web UI 实时显示每个子调用的运行指示环：fixture（测试前置数据）发出成对的 start/settle 事件；jsdom 锁定运行中形状；运行时测试锁定原位结算、乱序完成与 callTime 配对。trajectory/waterfall 的子调用 span 从这对事件取得如实的计时。spill 边界施加（[code-dispatch 日志 spill](2026-07-26-code-dispatch-log-spill.md)）则继承结算事件，作为自己唯一施加边界的位置。
|
||||
|
||||
@@ -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 .agents/notes/implemented/feature/2026-07-26-todo-parallel-in-progress.md
|
||||
2026-07-26-todo-parallel-in-progress.md: 8d047f33ab1aebd8c0de2a0a5e90e7efb1b28154
|
||||
2026-07-26-todo-parallel-in-progress.zh.md: ebd4b1567eba637493956993b43b1ec56df14c39
|
||||
2026-07-26-todo-parallel-in-progress.md: 5664960ce94dfac60d89cb363ea62459dd51f59e
|
||||
2026-07-26-todo-parallel-in-progress.zh.md: f346f89fcae5e8607c5608bbf7541ada0bae4593
|
||||
|
||||
@@ -33,11 +33,11 @@ The durable-log invariant deliberately does NOT follow the flag. A log written w
|
||||
|
||||
- **Keep the cap and add an explicit parallel opt-in flag** — an extra argument on every call to serve the common case; the flag would be noise for sequential work and still unverifiable.
|
||||
- **Cap active items at a configured maximum** — any fixed number is arbitrary. This is why the config field is a boolean policy switch and not a count: "may several tasks be active" is a property of the deployment, while "at most N" invents a threshold nothing can justify.
|
||||
- **Hardcode the parallel policy** — the first revision of this branch did, which is what made `allowParallelInProgress` necessary: a deployment running strictly sequential agents had no way back to the discipline it wanted.
|
||||
- **Hardcode the parallel policy** — the first revision of this change did, which is what made `allowParallelInProgress` necessary: a deployment running strictly sequential agents had no way back to the discipline it wanted.
|
||||
|
||||
## The display surfaces are part of the change
|
||||
|
||||
Lifting the cap makes a list shape reachable that no renderer had ever received, so this branch stacks on the [web todo display](2026-07-23-web-todo-display.md) rather than landing beside it: both change `tool-todo`, and the GUI is where a parallel plan becomes visible. Two web sites derived their one-line summary with `todos.find(t => t.status === 'in_progress')` — the collapsed plan-strip header and the `todo_write` row — and under the old cap that `find` was total, since at most one item could match. With several active it silently dropped every active item but the first: a four-item plan with three running tasks collapsed to the name of one, and the row read `1/4 已完成 · <one task>` while two others were in flight. The expanded list was always correct (it maps every item), which is why neither PR's tests caught it — only the collapsed header and the row lost information. The panel redesign replaced the collapsed header's named hint with `·`-joined per-status counts (localized, `1 completed · 2 in progress · 1 pending`, zero-count segments omitted), which reports parallel work correctly and needs no name to truncate; the row is the one site this branch still had to fix.
|
||||
Lifting the cap makes a list shape reachable that no renderer had ever received, so this change builds on the [web todo display](2026-07-23-web-todo-display.md) rather than landing beside it: both change `tool-todo`, and the GUI is where a parallel plan becomes visible. Two web sites derived their one-line summary with `todos.find(t => t.status === 'in_progress')` — the collapsed plan-strip header and the `todo_write` row — and under the old cap that `find` was total, since at most one item could match. With several active it silently dropped every active item but the first: a four-item plan with three running tasks collapsed to the name of one, and the row read `1/4 已完成 · <one task>` while two others were in flight. The expanded list was always correct (it maps every item), which is why neither change's tests caught it — only the collapsed header and the row lost information. The panel redesign replaced the collapsed header's named hint with `·`-joined per-status counts (localized, `1 completed · 2 in progress · 1 pending`, zero-count segments omitted), which reports parallel work correctly and needs no name to truncate; the row is the one site this change still had to fix.
|
||||
|
||||
The row takes `planSummary` in `toolviews/plan-summary.ts`. It names the first active item and counts the rest, so the row reports how many tasks are running instead of implying one. Naming every active item was rejected: the row is a single line, and an unbounded join would overflow it — the count degrades predictably where a list does not. The derivation sits inside the toolviews domain rather than in `contract/`, the inter-domain face: the panel computes its own counts inline and shares nothing with the row, so a contract module would declare a sharing relationship that no longer exists.
|
||||
|
||||
@@ -47,8 +47,8 @@ The row takes `planSummary` in `toolviews/plan-summary.ts`. It names the first a
|
||||
|
||||
## Deferred
|
||||
|
||||
Two review findings are recorded here rather than fixed on this branch. The `summarySuffix` span carries no accessible name, so a screen reader reads the count without its noun (`… 实现 fixture 样本 +1`); naming it introduces localized copy with its own test contract, which belongs to an accessibility pass over the whole `ToolRow` summary line rather than to one row. And when the *first* active item's content is unusable — missing, mistyped, or blank once trimmed — the row drops the active clause and the count with it, so a parallel plan renders as bare counts; skipping forward to the first usable active item was rejected because call args are an explicitly unvalidated boundary where model order is the only ordering the row can honour, and dropping the unusable clause alone keeps the `done`/`total` counts, which are trustworthy regardless.
|
||||
Two known gaps are deferred. The `summarySuffix` span carries no accessible name, so a screen reader reads the count without its noun (`… 实现 fixture 样本 +1`); naming it introduces localized copy with its own test contract, which belongs to an accessibility pass over the whole `ToolRow` summary line rather than to one row. And when the *first* active item's content is unusable — missing, mistyped, or blank once trimmed — the row drops the active clause and the count with it, so a parallel plan renders as bare counts; skipping forward to the first usable active item was rejected because call args are an explicitly unvalidated boundary where model order is the only ordering the row can honour, and dropping the unusable clause alone keeps the `done`/`total` counts, which are trustworthy regardless.
|
||||
|
||||
## Consequences
|
||||
|
||||
A todo list can now faithfully mirror parallel execution, and every surface renders several active markers at once: the plan strip's header counts the active items, and the row needed the derivation above. A composition that sets `allowParallelInProgress: true` no longer rejects a formerly-invalid snapshot shape; one that sets `false` keeps the old rejection, and the durable-log invariant accepts both. The model-facing description changed, which re-recorded the tool-catalog page and every snapshot sidecar carrying the todo schema. No count is recorded here: the set grows with every pinning scenario that lands, and the two point-in-time censuses this note previously carried were both stale within days. The operative rule is that a branch changing the tool description must refresh whichever sidecars landed after it branched — including the numbered `tool-schemas.<n>.expected.json` files pinning a subagent class, whose schemas the parent scenario does not cover — and `pnpm run test:snapshot:refresh` does it keylessly over the whole corpus. The web fixture's todo sample now runs two items `in_progress`, so both fixture-driven surfaces render a parallel plan. `packages/client/ui-conversation/tests/todo-panel.spec.tsx` pins the row summary and the plan strip over src, the ACP `todo-write` scenario records a three-todo plan with two active, and `apps/web/tests/todo-row.snapshot.ts` pins both surfaces in the assembled application — booted from the built `packages/client/*/lib/client.js` bundles, so it is the one place the keyed registration and the bundled wiring are under test. That last file records `summary`, `suffix`, and the strip's header as separate fields, so folding the `+N` count back into the summary string changes the expected output even though the concatenated text would read the same.
|
||||
A todo list can now faithfully mirror parallel execution, and every surface renders several active markers at once: the plan strip's header counts the active items, and the row needed the derivation above. A composition that sets `allowParallelInProgress: true` no longer rejects a formerly-invalid snapshot shape; one that sets `false` keeps the old rejection, and the durable-log invariant accepts both. The model-facing description changed, which re-recorded the tool-catalog page and every snapshot sidecar carrying the todo schema. No count is recorded here: the set grows with every pinning scenario that lands. The operative rule is that a branch changing the tool description must refresh whichever sidecars landed after it branched — including the numbered `tool-schemas.<n>.expected.json` files pinning a subagent class, whose schemas the parent scenario does not cover — and `pnpm run test:snapshot:refresh` does it keylessly over the whole corpus. The web fixture's todo sample now runs two items `in_progress`, so both fixture-driven surfaces render a parallel plan. `packages/client/ui-conversation/tests/todo-panel.spec.tsx` pins the row summary and the plan strip over src, the ACP `todo-write` scenario records a three-todo plan with two active, and `apps/web/tests/todo-row.snapshot.ts` pins both surfaces in the assembled application — booted from the built `packages/client/*/lib/client.js` bundles, so it is the one place the keyed registration and the bundled wiring are under test. That last file records `summary`, `suffix`, and the strip's header as separate fields, so folding the `+N` count back into the summary string changes the expected output even though the concatenated text would read the same.
|
||||
|
||||
@@ -33,11 +33,11 @@ Status: implemented
|
||||
|
||||
- **保留上限并增加一个显式的并行 opt-in 标志**——为服务常见场景而给每次调用增加一个额外参数；这个标志对顺序工作而言只是噪声，而且仍然无法验证。
|
||||
- **把活跃条目限制在一个可配置的上限内**——任何固定数字都是任意的。这正是该配置字段是布尔策略开关而非数量的原因：「是否允许多个任务同时活跃」是部署的属性，而「最多 N 个」凭空发明了一个无从论证的阈值。
|
||||
- **把并行策略硬编码**——本分支的第一版就是如此，这也是 `allowParallelInProgress` 之所以必要的原因：运行严格顺序 agent 的部署没有任何办法回到它想要的纪律。
|
||||
- **把并行策略硬编码**——本变更的第一版就是如此，这也是 `allowParallelInProgress` 之所以必要的原因：运行严格顺序 agent 的部署没有任何办法回到它想要的纪律。
|
||||
|
||||
## 展示面是本次改动的一部分
|
||||
|
||||
解除上限使一种此前任何渲染器都不曾收到的列表形状变得可达，因此本分支 stack（栈叠）在 [web todo 展示](2026-07-23-web-todo-display.md)之上，而不是与之并行落地：两者都改 `tool-todo`，而 GUI 正是并行计划变得可见的地方。web 有两处用 `todos.find(t => t.status === 'in_progress')` 推导单行摘要——折叠态的计划横条表头与 `todo_write` 工具行——在旧上限下这个 `find` 是完备的，因为最多只能有一个条目匹配。一旦有多个活跃项，它会静默丢掉除第一个之外的全部活跃条目：一个四条目、三个任务在跑的计划折叠后只显示其中一个的名字，工具行读作 `1/4 已完成 · <一个任务>`，而另外两个仍在进行。展开态的列表始终正确（它遍历每个条目），这也是两个 PR（Pull Request）的测试都没抓到它的原因——只有折叠表头与工具行丢失了信息。面板重做把折叠表头的具名提示换成以 `·` 连接的各状态计数（本地化后形如 `1 已完成 · 2 进行中 · 1 待处理`，计数为零的段落省略），它能正确报告并行工作，且不需要任何可被截断的名字；工具行才是本分支仍需修的那一处。
|
||||
解除上限使一种此前任何渲染器都不曾收到的列表形状变得可达，因此本变更构建在 [web todo 展示](2026-07-23-web-todo-display.md)之上，而不是与之并行落地：两者都改 `tool-todo`，而 GUI 正是并行计划变得可见的地方。web 有两处用 `todos.find(t => t.status === 'in_progress')` 推导单行摘要——折叠态的计划横条表头与 `todo_write` 工具行——在旧上限下这个 `find` 是完备的，因为最多只能有一个条目匹配。一旦有多个活跃项，它会静默丢掉除第一个之外的全部活跃条目：一个四条目、三个任务在跑的计划折叠后只显示其中一个的名字，工具行读作 `1/4 已完成 · <一个任务>`，而另外两个仍在进行。展开态的列表始终正确（它遍历每个条目），这也是两个变更的测试都没抓到它的原因——只有折叠表头与工具行丢失了信息。面板重做把折叠表头的具名提示换成以 `·` 连接的各状态计数（本地化后形如 `1 已完成 · 2 进行中 · 1 待处理`，计数为零的段落省略），它能正确报告并行工作，且不需要任何可被截断的名字；工具行才是本变更仍需修的那一处。
|
||||
|
||||
工具行改用 `toolviews/plan-summary.ts` 中的 `planSummary`。它给出第一个活跃条目，并计数其余活跃项，因此工具行报告的是有多少任务在跑，而不是暗示只有一个。列出全部活跃条目被否决了：工具行是单行，无上界的拼接会溢出——在列表做不到的地方，计数能够可预测地降级。该推导放在 toolviews 域内而非 `contract/`（域间共享面）：面板自行内联计算其计数，与工具行不共享任何东西，因此放进 contract 会声明一种已不存在的共享关系。
|
||||
|
||||
@@ -47,8 +47,8 @@ Status: implemented
|
||||
|
||||
## 暂缓项
|
||||
|
||||
两条 review 结论在此记录而非在本分支修复。`summarySuffix` 这个 span 没有无障碍名称，屏幕阅读器读出的数量缺少它所修饰的名词（`… 实现 fixture 样本 +1`）；为它命名会引入带自身测试约定的本地化文案，这属于对整条 `ToolRow` 摘要行做的无障碍专项，而不属于某一行。以及，当*第一个*活跃条目的 content 不可用时——缺失、类型不对、或 trim 后为空——行会连同数量一起丢掉活跃子句，于是并行计划渲染成裸计数；向后跳到第一个可用活跃条目的方案被否决，因为调用 args 是一处明确未经校验的边界，模型给出的顺序是该行唯一能遵循的顺序，而只丢掉不可用的那个子句可以保住 `done`/`total` 计数——这两个数无论如何都是可信的。
|
||||
两个已知缺口暂缓处理。`summarySuffix` 这个 span 没有无障碍名称，屏幕阅读器读出的数量缺少它所修饰的名词（`… 实现 fixture 样本 +1`）；为它命名会引入带自身测试约定的本地化文案，这属于对整条 `ToolRow` 摘要行做的无障碍专项，而不属于某一行。以及，当*第一个*活跃条目的 content 不可用时——缺失、类型不对、或 trim 后为空——行会连同数量一起丢掉活跃子句，于是并行计划渲染成裸计数；向后跳到第一个可用活跃条目的方案被否决，因为调用 args 是一处明确未经校验的边界，模型给出的顺序是该行唯一能遵循的顺序，而只丢掉不可用的那个子句可以保住 `done`/`total` 计数——这两个数无论如何都是可信的。
|
||||
|
||||
## 后果
|
||||
|
||||
现在 todo 列表可以忠实反映并行执行，并且每个展示面都能一次渲染多个活跃标记：计划横条的表头会计数活跃条目，工具行则需要上述推导。设置 `allowParallelInProgress: true` 的组合不再拒绝一种此前无效的快照形状；设置为 `false` 的组合仍保留旧的拒绝行为，而持久日志不变式两者都接受。面向模型的描述发生了变化，这重新记录了 tool-catalog 页面以及每个带有 todo schema 的快照伴随文件。此处不记录数量：该集合会随每个新落地的 pin 场景增长，而本 Agent Note 先前记过的两次时点统计都在几天内失实。有效规则是：改动工具描述的分支必须刷新它分叉之后落地的那些伴随文件——包括固定 subagent 类工具的编号文件 `tool-schemas.<n>.expected.json`，其 schema 不被父场景覆盖——`pnpm run test:snapshot:refresh` 可以无 key 地对整个语料完成刷新。web fixture（测试前置数据）的 todo 样本现在有两个条目处于 `in_progress`，因此两个由 fixture 驱动的展示面渲染的都是并行计划。`packages/client/ui-conversation/tests/todo-panel.spec.tsx` 在 src 上固定工具行摘要与计划横条，ACP（Agent Client Protocol）`todo-write` 场景录制的是三条目、两个活跃的计划，而 `apps/web/tests/todo-row.snapshot.ts` 在组装后的应用中固定这两个面——它从构建产物 `packages/client/*/lib/client.js` 启动，因此是唯一覆盖 keyed 注册与打包接线的地方。该文件把 `summary`、`suffix` 与横条表头记录为独立字段，因此即便拼接后的文本读起来一样，把 `+N` 计数折回摘要字符串也会改变预期输出。
|
||||
现在 todo 列表可以忠实反映并行执行，并且每个展示面都能一次渲染多个活跃标记：计划横条的表头会计数活跃条目，工具行则需要上述推导。设置 `allowParallelInProgress: true` 的组合不再拒绝一种此前无效的快照形状；设置为 `false` 的组合仍保留旧的拒绝行为，而持久日志不变式两者都接受。面向模型的描述发生了变化，这重新记录了 tool-catalog 页面以及每个带有 todo schema 的快照伴随文件。此处不记录数量：该集合会随每个新落地的 pin 场景增长。有效规则是：改动工具描述的分支必须刷新它分叉之后落地的那些伴随文件——包括固定 subagent 类工具的编号文件 `tool-schemas.<n>.expected.json`，其 schema 不被父场景覆盖——`pnpm run test:snapshot:refresh` 可以无 key 地对整个语料完成刷新。web fixture（测试前置数据）的 todo 样本现在有两个条目处于 `in_progress`，因此两个由 fixture 驱动的展示面渲染的都是并行计划。`packages/client/ui-conversation/tests/todo-panel.spec.tsx` 在 src 上固定工具行摘要与计划横条，ACP（Agent Client Protocol）`todo-write` 场景录制的是三条目、两个活跃的计划，而 `apps/web/tests/todo-row.snapshot.ts` 在组装后的应用中固定这两个面——它从构建产物 `packages/client/*/lib/client.js` 启动，因此是唯一覆盖 keyed 注册与打包接线的地方。该文件把 `summary`、`suffix` 与横条表头记录为独立字段，因此即便拼接后的文本读起来一样，把 `+N` 计数折回摘要字符串也会改变预期输出。
|
||||
|
||||
@@ -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 .agents/notes/implemented/feature/2026-07-28-continuable-subagent-conversations.md
|
||||
2026-07-28-continuable-subagent-conversations.md: 991b89599d7f300c79928e568833a2cd488f5a4e
|
||||
2026-07-28-continuable-subagent-conversations.zh.md: a7d282c4fadd943ad9250e01de5d379a776a32a0
|
||||
2026-07-28-continuable-subagent-conversations.md: 8408cf27003c011e140c3f426d81f3ba5af76b06
|
||||
2026-07-28-continuable-subagent-conversations.zh.md: e6f7bcc7d4f70edb8cbbe1ac88b9bdd7ac2e11a5
|
||||
|
||||
@@ -105,7 +105,7 @@ When the authenticated parent is itself a continuation-managed Activation, start
|
||||
|
||||
Child release occurs only after the child Agent is quiescent, every child of that child is disposed, the best-effort final session flush settles, and the child's `AgentHandle` completes disposal. The manager awaits `ctx.sessions.flush(child.session)` but does not interpret its participation boolean: an arbitrary listener cannot prove that the selected persistence backend stored the state. A rejection is logged without preventing handle disposal or ownership release, because retaining a child would permanently pin its ancestors in `waiting`. If the child is owned, the manager then resolves the live parent through `SessionHeader.parentSession` and removes the child Session id from its `ownedChildren`. Manager teardown uses the same child-first order.
|
||||
|
||||
Ownership is retained until the child Activation is disposed. A later refinement may release a request-scoped lease earlier, but it would require an exact turn-completion correlation that this Task-free proposal deliberately does not add.
|
||||
Ownership is retained until the child Activation is disposed. A later refinement may release a request-scoped lease earlier, but it would require an exact turn-completion correlation that this Task-free design deliberately does not add.
|
||||
|
||||
Top-level teardown is host-owned rather than represented as another Activation. Manager unload invokes its internal manager-wide drain to close admission synchronously, await every admitted materialization through publication or rollback, stop the stable live forest, and release it child-first. A host that owns selected top-level Agents uses `drainContinuableDescendants(parents)`: exact Agent identities close admission only below those roots until each leaves the registry, while unrelated forests and manager-wide admission remain live; the manager stops their visible descendants before its first await, waits only materializations admitted below those roots, and releases only the selected branches. Every materialized start and live delivery rechecks caller cancellation, the applicable draining scope, Activation disposal, and exact parent authority in the same synchronous span as inbox submission, so teardown or parent replacement that wins before acceptance prevents delivery to the closing handle. Only after the applicable drain settles may the host dispose its top-level Agents; only manager-wide drain precedes manager-scope disposal.
|
||||
|
||||
@@ -149,7 +149,7 @@ It adds no host-user continuation, subagent steering operation, durable mailbox,
|
||||
|
||||
## Alternatives considered
|
||||
|
||||
**Keep Task-backed Activations.** Tasks provide generic status, result collection, and cancellation, but using them for conversation delivery creates a second queue and duplicates turn ownership. The proposal gives up those generic Task controls so the Agent inbox remains the only execution order.
|
||||
**Keep Task-backed Activations.** Tasks provide generic status, result collection, and cancellation, but using them for conversation delivery creates a second queue and duplicates turn ownership. This design gives up those generic Task controls so the Agent inbox remains the only execution order.
|
||||
|
||||
**Create one Activation per `next-turn`.** This restores independent result and cancellation boundaries, but it requires a manager FIFO beside the Agent inbox and makes a retained Agent cross artificial Activation boundaries. One Activation per residency epoch is smaller and follows the `AgentHandle` lifetime directly.
|
||||
|
||||
|
||||
@@ -105,7 +105,7 @@ Agent inbox 是唯一队列。每条继续执行消息都使用 `Agent.followup(
|
||||
|
||||
只有在 child Agent 完全停稳、该 child 持有的每个 child 都已 dispose、best-effort 的最终会话 flush 结算且 child 的 `AgentHandle` 完成 dispose 后，系统才释放 child。管理器会等待 `ctx.sessions.flush(child.session)`，但不解释其参与布尔值：任意 listener 都无法证明所选持久化后端已存储该状态。rejection 会被记录，但不会阻止 handle dispose 或释放所有权，因为保留 child 会让其祖先永久固定在 `waiting`。如果 child 归 parent 所有，管理器随后会通过 `SessionHeader.parentSession` 解析在线 parent，并从其 `ownedChildren` 中移除 child 会话 id。管理器拆卸使用相同的 child-first 顺序。
|
||||
|
||||
系统会一直保留所有权，直至 child 激活完成 dispose。后续改进可以更早释放限定到请求的 lease，但这需要精确关联轮次完成，而本 Task-free 提案特意不增加该机制。
|
||||
系统会一直保留所有权，直至 child 激活完成 dispose。后续改进可以更早释放限定到请求的 lease，但这需要精确关联轮次完成，而本 Task-free 设计特意不增加该机制。
|
||||
|
||||
顶层拆卸由宿主负责，而不表示为另一次激活。管理器卸载会调用其内部的管理器全局 drain，同步关闭准入，等待每个已获准的物化过程完成发布或回滚，停止稳定的在线森林，并按 child-first 顺序释放。拥有选定顶层 Agent 的宿主使用 `drainContinuableDescendants(parents)`：确切的 Agent 身份只关闭这些根之下的准入，直到每个身份离开注册表，而无关森林和管理器全局准入保持在线；管理器会在第一次 await 之前停止其可见后代，只等待这些根之下已获准的物化过程，并且只释放选定分支。每个已物化的 start 和在线投递都会在与 inbox 提交相同的同步区间内重新检查调用方取消、适用的 draining 作用域、Activation dispose 和确切的 parent 权限，因此只要拆卸或 parent 替换先于接受发生，就会阻止向正在关闭的 handle 投递。只有适用的 drain 结算后，宿主才能 dispose 自己的顶层 Agent；只有管理器全局 drain 会先于管理器作用域 dispose。
|
||||
|
||||
@@ -149,7 +149,7 @@ activation-owner 作用域之所以存在，是因为普通 Cordis owner effect
|
||||
|
||||
## 曾考虑的替代方案
|
||||
|
||||
**保留由 Task 支撑的激活。** Task 可以提供通用状态、结果收集和取消，但使用 Task 投递会话会产生第二条队列，并重复轮次所有权。本提案放弃这些通用 Task 控制，让 Agent inbox 成为唯一执行顺序。
|
||||
**保留由 Task 支撑的激活。** Task 可以提供通用状态、结果收集和取消，但使用 Task 投递会话会产生第二条队列，并重复轮次所有权。本设计放弃这些通用 Task 控制，让 Agent inbox 成为唯一执行顺序。
|
||||
|
||||
**每个 `next-turn` 创建一次激活。** 这会恢复独立的结果与取消边界，但需要在 Agent inbox 旁维护管理器 FIFO，还会使所保留的 Agent 跨越人为划分的激活边界。每个驻留周期对应一次激活更小，也直接跟随 `AgentHandle` 生命周期。
|
||||
|
||||
|
||||
@@ -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 .agents/notes/implemented/feature/2026-07-28-todo-plan-clears-on-next-turn.md
|
||||
2026-07-28-todo-plan-clears-on-next-turn.md: 8a2808f5023a0800fbbeb65c5e28b3495e051dbc
|
||||
2026-07-28-todo-plan-clears-on-next-turn.zh.md: c96485ec2d5b0faea0682624cde9a7569cd2e227
|
||||
2026-07-28-todo-plan-clears-on-next-turn.md: 55a0d4f307bef5cd04add0baae220ea763772ee9
|
||||
2026-07-28-todo-plan-clears-on-next-turn.zh.md: e881884443b06b780c12d348c7ecca4a88801b73
|
||||
|
||||
@@ -18,7 +18,7 @@ The standing plan is the latest `todo/write` that is not followed by a later `tu
|
||||
|
||||
### TUI live path
|
||||
|
||||
The TUI `renderEvent` switch still clears its local plan panel on `turn/start` and replaces it on `todo/write` (TUI is not yet a projection carrier). The rebuild path resets the panel before replaying the log so cold resume converges on the same rule.
|
||||
The former TUI's `renderEvent` switch cleared its local plan panel on `turn/start` and replaced it on `todo/write`, with its rebuild path resetting the panel before replay so cold resume converged on the same rule; that package has since been removed ([remove TUI package](../simplification/2026-08-04-remove-tui-package.md)).
|
||||
|
||||
## Alternatives considered
|
||||
|
||||
|
||||
@@ -18,7 +18,7 @@ Status: implemented
|
||||
|
||||
### TUI 实时路径
|
||||
|
||||
TUI 的 `renderEvent` 分支仍在 `turn/start` 清空本地计划面板、在 `todo/write` 替换之（TUI 尚非投影载体）。重建路径在回放日志前重置面板，使冷恢复收敛到同一规则。
|
||||
原 TUI 的 `renderEvent` 分支曾在 `turn/start` 清空本地计划面板、在 `todo/write` 替换之，其重建路径在回放前重置面板，使冷恢复收敛到同一规则；该包其后已被移除（[移除 TUI 包](../simplification/2026-08-04-remove-tui-package.md)）。
|
||||
|
||||
## 考虑过的替代方案
|
||||
|
||||
|
||||
@@ -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 .agents/notes/implemented/feature/2026-07-28-web-terminal-card.md
|
||||
2026-07-28-web-terminal-card.md: 0338fa1cdb4a19177bddd4181661173bf75492b0
|
||||
2026-07-28-web-terminal-card.zh.md: f9dc686cfbf817fe5a1c15b8d5a94e3f8ab2adee
|
||||
2026-07-28-web-terminal-card.md: 84e5cdb786944b014fd3a687cfefad6768174006
|
||||
2026-07-28-web-terminal-card.zh.md: 58c236bda9c45e13fda0f965f84af24b3c831bb4
|
||||
|
||||
@@ -20,7 +20,7 @@ The component's contract:
|
||||
- **One run-state dot for the call, on the first row.** `StateDot` in three of its four states: the chase while running, red for the exit status that also renders the pill, green for a clean settle — the same indicator a tool row's leading icon uses, so a row and its own card cannot disagree about one command. The dot exists because the first question a reader has about a shell command is whether it is still running, and without it that had to be inferred from the absence of output — which a settled command producing no output also looks like. It sits out of flow in a gutter the card reserves as its OWN left padding, so it neither indents its command nor depends on the command's text metrics to line up. The reservation is padding rather than margin because every render site rewrites `margin` wholesale to set its own indent, which silently cancelled a margin-based gutter and let a container clip the dot. Exactly one dot, whatever the line count: the exit status the view carries is the whole call's, and bash reports no per-command status, so a dot per line would assert of a line that succeeded inside a failing call that the line itself failed. The single visually hidden text label carries the same scope, since `StateDot` is `aria-hidden` and one label per row would read to assistive technology as several distinct outcomes.
|
||||
- **No soft wrapping.** Output lines are `white-space: pre` inside a horizontally scrolling box. Column alignment survives; a long line scrolls instead of folding.
|
||||
- **Height cap with an expand control.** Output longer than `DEFAULT_TERMINAL_MAX_LINES` (16) lines shows `ceil(max/2)` head lines plus the remaining tail lines, with a button in between that reports the hidden count and expands. The count is of parsed lines after the trailing output terminator is dropped, so an N-line output ending in a newline is N lines. The split arithmetic preserves the former TUI transcript's collapsed-card behavior, so the established head/tail selection stays stable.
|
||||
- **ANSI color.** `anser` splits the SGR runs; `ui-primitives/src/ansi.ts` resolves each run into an inline style rendered as React spans. A foreground-only run maps the basic 16 colors onto `--dsw-*` theme tokens so authored color stays legible under both themes; a run that paints its own background keeps anser's literal rgb for both so its intended contrast survives, as do 256-palette, truecolor, and the two basic colors this design system has no token for. Sequences that carry no color (OSC strings, non-CSI escapes, inert C0 controls) are stripped before parsing so they never reach the DOM as literal characters. Cursor movements resolve before that strip, into a per-line column buffer rather than by string surgery, because carriage return and backspace only MOVE the cursor — neither erases anything, so what a reader sees is whatever each column last had written to it. `100%` then a carriage return and `OK` shows `OK0%`, since the redraw is shorter than the frame beneath it; a trailing `abc` plus a backspace still shows `abc`, since nothing overwrote the `c`; `abc` plus two backspaces and `XY` shows `aXY`. Each of these was checked against a real terminal, because the earlier truncate-and-delete approximations looked right and were not. SGR state is stamped per column as a terminal stores it per cell, so a partial overwrite keeps each surviving character's own color: red `bad`, three backspaces, then `ok` shows `okd` with the `d` still red. A CSI sequence occupies no column and changes only the state later writes are stamped with, which is also why a carriage return does not reset color, and why SGR state threads from one line to the next rather than closing at each newline. Erase-in-line is part of the same replay, because `\r\x1b[K` is the single idiom every spinner and progress bar writes — modelling the `\r` alone left the previous frame's tail standing, which is text the terminal never showed. Only `m` accumulates into a cell's style; a cursor or erase sequence must not, or the state string grows per redraw and emits boundaries anser has to discard. SGR is held per cell as a NORMALIZED record (foreground, background, attribute set), not as the sequence history: accumulating raw sequences made every state boundary re-emit the whole chain, so output that switches color without a full reset emitted O(n^2) characters — 3200 such cells produced 25 MB and a `RangeError` well under bash's own output cap. The record also lets the attribute closers every chalk-based tool writes (`39`, `49`, `22`, `24`, …) actually close their attribute, and each boundary emits one canonical sequence for the state it opens. A run also has to CLOSE: the replay converges to the state the scan ended in, not the last written cell's, because a reset after the final write changes no cell yet ends the run — without that a line finishing in `\x1b[0m` leaked its color onto every later line. The cursor advances by terminal columns, so a tab reaches the next 8-column stop, a wide character takes two (its spacer blanking rather than closing the gap once the lead cell is overwritten), and a combining mark takes none. Width follows emoji PRESENTATION rather than the U+2600-U+27BF block: `\u2713`, the check every progress line writes, is one column, so treating the block as wide misaligned exactly the output this card exists for. Writing over either half of a wide pair blanks the other, since a terminal cannot leave one cell of a two-cell glyph standing: `a\tb` then a redraw of `XY` shows `XY b`, since a two-character redraw cannot reach column 8.
|
||||
- **ANSI color.** `anser` splits the SGR runs; `ui-primitives/src/ansi.ts` resolves each run into an inline style rendered as React spans. A foreground-only run maps the basic 16 colors onto `--dsw-*` theme tokens so authored color stays legible under both themes; a run that paints its own background keeps anser's literal rgb for both so its intended contrast survives, as do 256-palette, truecolor, and the two basic colors this design system has no token for. Sequences that carry no color (OSC strings, non-CSI escapes, inert C0 controls) are stripped before parsing so they never reach the DOM as literal characters. Cursor movements resolve before that strip, into a per-line column buffer rather than by string surgery, because carriage return and backspace only MOVE the cursor — neither erases anything, so what a reader sees is whatever each column last had written to it. `100%` then a carriage return and `OK` shows `OK0%`, since the redraw is shorter than the frame beneath it; a trailing `abc` plus a backspace still shows `abc`, since nothing overwrote the `c`; `abc` plus two backspaces and `XY` shows `aXY`. These semantics match a real terminal; truncate-and-delete approximations look right and are not. SGR state is stamped per column as a terminal stores it per cell, so a partial overwrite keeps each surviving character's own color: red `bad`, three backspaces, then `ok` shows `okd` with the `d` still red. A CSI sequence occupies no column and changes only the state later writes are stamped with, which is also why a carriage return does not reset color, and why SGR state threads from one line to the next rather than closing at each newline. Erase-in-line is part of the same replay, because `\r\x1b[K` is the single idiom every spinner and progress bar writes — modelling the `\r` alone left the previous frame's tail standing, which is text the terminal never showed. Only `m` accumulates into a cell's style; a cursor or erase sequence must not, or the state string grows per redraw and emits boundaries anser has to discard. SGR is held per cell as a NORMALIZED record (foreground, background, attribute set), not as the sequence history: accumulating raw sequences made every state boundary re-emit the whole chain, so output that switches color without a full reset emitted O(n^2) characters — 3200 such cells produced 25 MB and a `RangeError` well under bash's own output cap. The record also lets the attribute closers every chalk-based tool writes (`39`, `49`, `22`, `24`, …) actually close their attribute, and each boundary emits one canonical sequence for the state it opens. A run also has to CLOSE: the replay converges to the state the scan ended in, not the last written cell's, because a reset after the final write changes no cell yet ends the run — without that a line finishing in `\x1b[0m` leaked its color onto every later line. The cursor advances by terminal columns, so a tab reaches the next 8-column stop, a wide character takes two (its spacer blanking rather than closing the gap once the lead cell is overwritten), and a combining mark takes none. Width follows emoji PRESENTATION rather than the U+2600-U+27BF block: `\u2713`, the check every progress line writes, is one column, so treating the block as wide misaligned exactly the output this card exists for. Writing over either half of a wide pair blanks the other, since a terminal cannot leave one cell of a two-cell glyph standing: `a\tb` then a redraw of `XY` shows `XY b`, since a two-character redraw cannot reach column 8.
|
||||
- **Exit status and copy.** A non-zero exit code or a signal renders a status pill, matching the exit-status distinction the bash tool's own renderer draws; a clean exit renders none, and settled empty output renders a dimmed placeholder — judged on the parsed lines the card renders, not on the raw text, since output that is only escapes or control bytes survives a `trim()` yet parses to nothing visible and would otherwise draw blank rows plus a copy control for invisible bytes. The copy control copies the raw output text, not the rendered tree, so the prompt line and the pill stay out of the clipboard.
|
||||
|
||||
Geometry, radius, and fonts mirror `CodeBlock`, so a terminal card and a fenced code block match visually; `white-space: pre` plus horizontal scroll is the deliberate divergence. The clipboard write both components need moved out of `CodeBlock` into a package-internal `src/clipboard.ts`, unexported so it stays an implementation detail of the two blocks.
|
||||
@@ -41,7 +41,7 @@ One premise of that split has since weakened: [tool rows stopped being details-p
|
||||
|
||||
**Reuse `CodeBlock` with a `console` language instead of a new primitive.** Rejected: `CodeBlock` soft-wraps, which is the defect being fixed, and it has no exit status, no cwd prompt line, no height cap, and no ANSI handling. Adding four terminal-specific concerns to the shared code-fence component would impose them on every markdown fence. The two components share their geometry and font tokens instead, which is the only part where one implementation is correct for both.
|
||||
|
||||
**Hand-roll the SGR parser.** Rejected: an SGR parser is exactly the surface [prefer maintained dependencies over hand-rolling](../process/2026-07-26-dependencies-over-hand-rolling.md) says not to own — its edge cases (256-palette and truecolor forms, `reverse`, multi-parameter runs, unterminated sequences) each fail on output nobody produces in a test, so a hand-rolled version stays subtly wrong for a long time. Stated honestly against that policy's bar: `anser` does **not** delete existing owned code. It is a capability addition, which that note distinguishes from a net-deletion simplification; the health and boundary-fit halves of the bar are what it clears. What stays hand-rolled is the part `anser` does not cover: the theme-token color mapping, the non-CSI sanitizing, the carriage-return redraw, and the per-line span folding the height cap slices.
|
||||
**Hand-roll the SGR parser.** Rejected: an SGR parser is exactly the surface [prefer maintained dependencies over hand-rolling](../process/2026-07-26-dependencies-over-hand-rolling.md) says not to own — its edge cases (256-palette and truecolor forms, `reverse`, multi-parameter runs, unterminated sequences) each fail on output nobody produces in a test, so a hand-rolled version stays subtly wrong for a long time. Against that policy's bar: `anser` does **not** delete existing owned code. It is a capability addition, which that note distinguishes from a net-deletion simplification; the health and boundary-fit halves of the bar are what it clears. What stays hand-rolled is the part `anser` does not cover: the theme-token color mapping, the non-CSI sanitizing, the carriage-return redraw, and the per-line span folding the height cap slices.
|
||||
|
||||
## Consequences
|
||||
|
||||
@@ -59,7 +59,7 @@ Inline rendering is licensed for the terminal intent alone. A future intent that
|
||||
|
||||
`packages/client/ui-tool/tests/terminal-card.spec.tsx` pins the wiring at every render site: `terminalCardModel`'s derivation and each of its null arms, the result title replacing the pending one, the cwd resolving against the session workspace across all four of its cases, the panel resetting the card's expand state when the selection changes, the chat row's expand-gated body against the panel's full-height one, `BashRow`'s resident card and its agreement with its own summary row's state dot, and the panel's Output section including the run_code sub-dispatch and the out-of-window head. That file is written against no gate pressure — `packages/client/ui-tool/src/*` sits on the coverage `exclude` list in `vitest.config.ts`, so a coverage run over this package measures none of these files.
|
||||
|
||||
`apps/web/tests/terminal-card.snapshot.ts` pins the assembled application over the built client bundles: the same render intent at both conversation render sites and in both chat-row shapes, because a bash call reaches a resident card only through the keyed `BashRow` registration and every other terminal-declaring tool name lands on the render-site fallback row, whose body is expand-gated. Fixture turn 65 was named `bash` and turn 60 left as `fx-bash` so one fixture covers both shapes, and turn 60's command was made two lines so the built-bundle snapshot pins the per-line prompt and its single dot (`dotsPerPromptRow: [1, 0]`). That terminal turn is ordered BEFORE the todo turn on purpose: the standing plan retires at the next `turn/start`, so appending it after would have emptied the dock's plan strip and taken the todo surfaces' own coverage with it; that turn also carries what turn 60's two prompt rows cannot — SGR runs resolved to `--dsw-*` tokens, output past the chat cap, a nested cwd, and a non-zero exit authored beside the sample. The sample's body deliberately carries NO `[exit code: N]` line: the real bash presenter consumes that marker out of the body precisely because the card shows the exit as its own pill, so leaving it in would pin a frame showing the exit twice — one the product path cannot produce.
|
||||
`apps/web/tests/terminal-card.snapshot.ts` pins the assembled application over the built client bundles: the same render intent at both conversation render sites and in both chat-row shapes, because a bash call reaches a resident card only through the keyed `BashRow` registration and every other terminal-declaring tool name lands on the render-site fallback row, whose body is expand-gated. Fixture turn 65 is named `bash` and turn 60 stays `fx-bash` so one fixture covers both shapes, and turn 60's command is two lines so the built-bundle snapshot pins the per-line prompt and its single dot (`dotsPerPromptRow: [1, 0]`). That terminal turn is ordered BEFORE the todo turn on purpose: the standing plan retires at the next `turn/start`, so appending it after would have emptied the dock's plan strip and taken the todo surfaces' own coverage with it; that turn also carries what turn 60's two prompt rows cannot — SGR runs resolved to `--dsw-*` tokens, output past the chat cap, a nested cwd, and a non-zero exit authored beside the sample. The sample's body deliberately carries NO `[exit code: N]` line: the real bash presenter consumes that marker out of the body precisely because the card shows the exit as its own pill, so leaving it in would pin a frame showing the exit twice — one the product path cannot produce.
|
||||
|
||||
`apps/web/tests/navigation-panes.e2e.ts` adds the real-browser scenario over its existing `echo NAVIGATION_OK` bash call, asserting what jsdom cannot compute: squeezing the output pane below its content width leaves the line at one row and gives the pane horizontal overflow, the run-state dot resolves to the green success token rather than to a literal color (a `--dsw-*` var has no computed value at all without the real theme stylesheet) and sits inside the card box yet left of the prompt label, which is the invariant the gutter padding owns, and the copy control reaches the page's own async Clipboard API rather than the `execCommand` fallback. Its `terminal-card.expected.md` golden records the resolved workspace in the prompt row, which is what a bash call with no `workdir` must show instead of a bare `$`.
|
||||
|
||||
|
||||
@@ -20,7 +20,7 @@ Web client 却对它视而不见。`packages/client/ui-tool/src/client/tool/mode
|
||||
- **整次调用一枚运行状态点，位于第一行。** 它是 `StateDot` 四种状态中的三种：运行期间为追逐动画，与渲染状态徽章相同的退出状态为红色，干净落定为绿色——与工具行行首图标使用同一个指示器，因此一行与其自身的卡片不可能对同一条命令产生分歧。该状态点存在的理由是：读者对一条 shell 命令的第一个问题就是它是否仍在运行；没有它时，这一点只能从「没有输出」推断，而一条落定后无输出的命令看起来也一样。它以脱离文档流的方式落在卡片以**自身左内边距**预留的落区里，因此既不会缩进其命令，也不依赖命令自身的文本度量来与之对齐。该预留用 padding 而非 margin，是因为每个渲染点都会整条重写 `margin` 来设定自己的缩进——那会静默取消基于 margin 的落区，并让容器把状态点裁掉。无论有多少行，都只有一枚：视图携带的退出状态属于整次调用，而 bash 不报告逐条命令的状态，因此每行一枚状态点就等于在断言——一条在失败调用中其实成功了的命令行自身失败了。那一处视觉隐藏的文本标签具有相同的作用域，因为 `StateDot` 是 `aria-hidden`，而每行一个标签会被辅助技术读成好几个各自独立的结果。
|
||||
- **不软换行。** 输出行使用 `white-space: pre`，置于横向滚动的容器内。列对齐得以保留；长行滚动，而非折行。
|
||||
- **高度上限与展开控件。** 输出超过 `DEFAULT_TERMINAL_MAX_LINES`（16）行时，显示 `ceil(max/2)` 行首部加余下的尾部行数，中间是一个按钮，报告被隐藏的行数并可展开。计数针对的是剥除输出末尾终止符之后解析出的行，因此以换行结尾的 N 行输出就是 N 行。切分算法保留原 TUI transcript 折叠卡片的行为，因此既有的首尾选择保持稳定。
|
||||
- **ANSI 颜色。** `anser` 切分 SGR 分段；`ui-primitives/src/ansi.ts` 把每段解析为内联样式，渲染成 React span。只设前景色的分段把基本 16 色映射到 `--dsw-*` 主题 token，使作者指定的颜色在两种主题下都可读；自行绘制背景的分段则前后景都保留 anser 给出的字面 rgb，以保住它意图中的对比度，256 色板、truecolor 以及本设计系统没有对应 token 的两种基本色同样如此。不承载颜色的转义序列（OSC 串、非 CSI 转义、无显示意义的 C0 控制符）在解析前被剥除，因此绝不会以字面字符抵达 DOM。光标移动在该剥除之前先行结算，且落在逐行的列缓冲里而不是靠字符串手术，因为回车与退格**只移动**光标——两者都不擦除任何东西，所以读者看到的就是每一列最后被写入的内容。`100%` 后接回车再接 `OK` 显示为 `OK0%`，因为这次重绘比它下面的帧更短；末尾 `abc` 加一个退格仍显示 `abc`，因为没有任何东西覆盖过那个 `c`；`abc` 加两个退格再接 `XY` 显示 `aXY`。这些用例都对照真实终端核实过，因为先前「截断加删除」的近似看起来是对的，实际并不对。SGR 状态按列打戳，与终端按单元格存储颜色的方式一致，因此部分覆盖会保留每个存活字符自身的颜色：红色 `bad`、三个退格、再写 `ok`，显示为 `okd` 且那个 `d` 仍是红的。CSI 序列不占列，只改变后续写入被打上的状态——这也正是回车不会重置颜色的原因，以及 SGR 状态会从一行延续到下一行、而不是在每个换行处关闭的原因。行内擦除属于同一次重放，因为 `\r\x1b[K` 是每个 spinner 与进度条都会写的同一个惯用法——只建模 `\r` 会让上一帧的尾巴留在原处，那是终端从未显示过的文本。只有 `m` 会累加进单元格样式；光标或擦除序列不能累加，否则状态串会随每次重绘线性增长，并发出 anser 只能丢弃的边界。SGR 按单元格以**归一化记录**保存（前景、背景、属性集合），而不是序列历史：累积原始序列会让每个状态边界重新发射整条链，因此不做完整 reset 的换色输出会发射 O(n^2) 个字符——3200 个这样的单元格产生 25 MB 并最终 `RangeError`，远低于 bash 自身的输出上限。该记录也让所有 chalk 系工具写出的属性闭合码（`39`、`49`、`22`、`24` 等）真正闭合其属性，且每个边界只为它开启的状态发射一条规范序列。一个分段也必须**收束**：重放收敛到扫描结束时的状态，而不是最后一个被写入单元格的状态——因为最后一次写入之后的 reset 不改变任何单元格，却结束了该分段；没有这一步，以 `\x1b[0m` 结尾的行会把颜色泄漏到其后所有行。光标按终端列推进，因此制表符前进到下一个 8 列制表位、宽字符占两列（其续列在首列被覆盖后变为空白而非合拢），组合标记不占列。宽度依据 emoji **presentation** 而非 U+2600–U+27BF 整个区块：`\u2713`——每条进度行都会写的对勾——只占一列，把该区块整体当作双宽恰好会错位这张卡片赖以存在的那类输出。写入宽字符对的任一半都会把另一半清成空白，因为终端无法让一个双格字形只留下一格：`a\tb` 之后用 `XY` 重绘显示为 `XY b`，因为两个字符的重绘到不了第 8 列。
|
||||
- **ANSI 颜色。** `anser` 切分 SGR 分段；`ui-primitives/src/ansi.ts` 把每段解析为内联样式，渲染成 React span。只设前景色的分段把基本 16 色映射到 `--dsw-*` 主题 token，使作者指定的颜色在两种主题下都可读；自行绘制背景的分段则前后景都保留 anser 给出的字面 rgb，以保住它意图中的对比度，256 色板、truecolor 以及本设计系统没有对应 token 的两种基本色同样如此。不承载颜色的转义序列（OSC 串、非 CSI 转义、无显示意义的 C0 控制符）在解析前被剥除，因此绝不会以字面字符抵达 DOM。光标移动在该剥除之前先行结算，且落在逐行的列缓冲里而不是靠字符串手术，因为回车与退格**只移动**光标——两者都不擦除任何东西，所以读者看到的就是每一列最后被写入的内容。`100%` 后接回车再接 `OK` 显示为 `OK0%`，因为这次重绘比它下面的帧更短；末尾 `abc` 加一个退格仍显示 `abc`，因为没有任何东西覆盖过那个 `c`；`abc` 加两个退格再接 `XY` 显示 `aXY`。这些语义与真实终端一致；「截断加删除」的近似看起来是对的，实际并不对。SGR 状态按列打戳，与终端按单元格存储颜色的方式一致，因此部分覆盖会保留每个存活字符自身的颜色：红色 `bad`、三个退格、再写 `ok`，显示为 `okd` 且那个 `d` 仍是红的。CSI 序列不占列，只改变后续写入被打上的状态——这也正是回车不会重置颜色的原因，以及 SGR 状态会从一行延续到下一行、而不是在每个换行处关闭的原因。行内擦除属于同一次重放，因为 `\r\x1b[K` 是每个 spinner 与进度条都会写的同一个惯用法——只建模 `\r` 会让上一帧的尾巴留在原处，那是终端从未显示过的文本。只有 `m` 会累加进单元格样式；光标或擦除序列不能累加，否则状态串会随每次重绘线性增长，并发出 anser 只能丢弃的边界。SGR 按单元格以**归一化记录**保存（前景、背景、属性集合），而不是序列历史：累积原始序列会让每个状态边界重新发射整条链，因此不做完整 reset 的换色输出会发射 O(n^2) 个字符——3200 个这样的单元格产生 25 MB 并最终 `RangeError`，远低于 bash 自身的输出上限。该记录也让所有 chalk 系工具写出的属性闭合码（`39`、`49`、`22`、`24` 等）真正闭合其属性，且每个边界只为它开启的状态发射一条规范序列。一个分段也必须**收束**：重放收敛到扫描结束时的状态，而不是最后一个被写入单元格的状态——因为最后一次写入之后的 reset 不改变任何单元格，却结束了该分段；没有这一步，以 `\x1b[0m` 结尾的行会把颜色泄漏到其后所有行。光标按终端列推进，因此制表符前进到下一个 8 列制表位、宽字符占两列（其续列在首列被覆盖后变为空白而非合拢），组合标记不占列。宽度依据 emoji **presentation** 而非 U+2600–U+27BF 整个区块：`\u2713`——每条进度行都会写的对勾——只占一列，把该区块整体当作双宽恰好会错位这张卡片赖以存在的那类输出。写入宽字符对的任一半都会把另一半清成空白，因为终端无法让一个双格字形只留下一格：`a\tb` 之后用 `XY` 重绘显示为 `XY b`，因为两个字符的重绘到不了第 8 列。
|
||||
- **退出状态与复制。** 非零退出码或信号渲染一枚状态徽章，与 bash 工具自身渲染器所作的退出状态区分一致；干净退出不渲染徽章，落定后的空输出渲染一处变暗的占位文字——该判定读的是卡片实际渲染的解析行，而非原始文本，因为只含转义或控制字节的输出能通过 `trim()` 却解析不出任何可见内容，否则就会画出一片空行外加一个把不可见字节写进剪贴板的复制控件。复制控件复制的是原始输出文本而非渲染后的树，因此提示符行与徽章不会进入剪贴板。
|
||||
|
||||
几何尺寸、圆角与字体沿用 `CodeBlock`，因此终端卡片与围栏代码块在视觉上一致；`white-space: pre` 加横向滚动是有意的分歧。两个组件都需要的剪贴板写入从 `CodeBlock` 中提取到包内部的 `src/clipboard.ts`，不对外导出，因此它仍是这两个块的实现细节。
|
||||
@@ -41,7 +41,7 @@ Web client 却对它视而不见。`packages/client/ui-tool/src/client/tool/mode
|
||||
|
||||
**复用 `CodeBlock` 并传入 `console` 语言，而不新建组件。** 已否决：`CodeBlock` 会软换行，而软换行正是本次要修的缺陷，且它没有退出状态、没有 cwd 提示符行、没有高度上限、也不处理 ANSI。把四项终端专属关注点加进共享的代码围栏组件，等于把它们强加给每一个 markdown 围栏。两个组件改为共享几何与字体 token，那是唯一一处「一套实现对两者都正确」的部分。
|
||||
|
||||
**手写 SGR 解析器。** 已否决：SGR 解析器恰是[优先采用维护良好的依赖而非手写](../process/2026-07-26-dependencies-over-hand-rolling.md)所指明不该自持的那类实现——它的边界情形（256 色板与 truecolor 形式、`reverse`、多参数分段、未终止的序列）各自只在没人会写进测试的输出上失效，因此手写版本会在很长时间内一直微妙地出错。对照那条策略的门槛如实陈述：`anser` **并未**删除任何既有自持代码。它是一次能力增补，而那条 Agent Note 把这与净删除式的简化区分开来；它清过的是健康度与边界契合这两半门槛。`anser` 未覆盖而仍由我们手写的部分是：主题 token 的颜色映射、非 CSI 序列的剥除、回车重绘，以及供高度上限切片的逐行 span 折叠。
|
||||
**手写 SGR 解析器。** 已否决：SGR 解析器恰是[优先采用维护良好的依赖而非手写](../process/2026-07-26-dependencies-over-hand-rolling.md)所指明不该自持的那类实现——它的边界情形（256 色板与 truecolor 形式、`reverse`、多参数分段、未终止的序列）各自只在没人会写进测试的输出上失效，因此手写版本会在很长时间内一直微妙地出错。对照那条策略的门槛：`anser` **并未**删除任何既有自持代码。它是一次能力增补，而那条 Agent Note 把这与净删除式的简化区分开来；它清过的是健康度与边界契合这两半门槛。`anser` 未覆盖而仍由我们手写的部分是：主题 token 的颜色映射、非 CSI 序列的剥除、回车重绘，以及供高度上限切片的逐行 span 折叠。
|
||||
|
||||
## Consequences
|
||||
|
||||
@@ -59,7 +59,7 @@ Web client 却对它视而不见。`packages/client/ui-tool/src/client/tool/mode
|
||||
|
||||
`packages/client/ui-tool/tests/terminal-card.spec.tsx` 固定每个渲染点上的接线：`terminalCardModel` 的推导及其每一处 null 分支、结果标题替换待定标题、cwd 针对会话 workspace 解析的全部四种情形、切换选中调用时面板重置卡片展开态、对话行受展开控制的输出体与面板的全高输出体的对比、`BashRow` 的常驻卡片及其与自身摘要行状态点的一致性，以及面板 Output 区段（含 run_code 子派发与超出窗口的调用头）。该文件在没有门禁压力的情况下写成——`packages/client/ui-tool/src/*` 位于 `vitest.config.ts` 的覆盖率 `exclude` 列表中，因此覆盖率运行不会统计其中任何文件。
|
||||
|
||||
`apps/web/tests/terminal-card.snapshot.ts` 在构建后的客户端产物上固定组装完整的应用：同一渲染意图在两个对话渲染点、以及两种对话行形态下的表现——因为 bash 调用只有经由带键的 `BashRow` 注册才得到常驻卡片，而其他任何声明 terminal 的工具名都落到渲染点兜底行上，其输出体受展开控制。fixture 第 65 轮改名为 `bash`、第 60 轮保留 `fx-bash`，于是一份 fixture 覆盖两种形态，并把第 60 轮的命令改为两行，使构建产物快照钉住逐行提示区及其单枚状态点（`dotsPerPromptRow: [1, 0]`）。该终端轮有意排在 todo 轮**之前**：站立计划会在下一次 `turn/start` 时退役，若追加在其后就会让 dock 的计划条变空，并连带毁掉 todo 表面自身的覆盖；该轮还承载第 60 轮两个提示行无法覆盖的部分——解析到 `--dsw-*` token 的 SGR 分段、超出对话上限的输出、嵌套 cwd，以及在样本旁另行标注的非零退出码。样本正文有意**不含** `[exit code: N]` 行：真实的 bash presenter 正是因为卡片以徽章单独呈现退出状态，才把该标记从正文中消费掉；若保留它，钉住的将是一帧把退出状态显示两次的画面——而产品路径产不出这一帧。
|
||||
`apps/web/tests/terminal-card.snapshot.ts` 在构建后的客户端产物上固定组装完整的应用：同一渲染意图在两个对话渲染点、以及两种对话行形态下的表现——因为 bash 调用只有经由带键的 `BashRow` 注册才得到常驻卡片，而其他任何声明 terminal 的工具名都落到渲染点兜底行上，其输出体受展开控制。fixture 第 65 轮名为 `bash`、第 60 轮保持 `fx-bash`，于是一份 fixture 覆盖两种形态，而第 60 轮的命令为两行，使构建产物快照钉住逐行提示区及其单枚状态点（`dotsPerPromptRow: [1, 0]`）。该终端轮有意排在 todo 轮**之前**：站立计划会在下一次 `turn/start` 时退役，若追加在其后就会让 dock 的计划条变空，并连带毁掉 todo 表面自身的覆盖；该轮还承载第 60 轮两个提示行无法覆盖的部分——解析到 `--dsw-*` token 的 SGR 分段、超出对话上限的输出、嵌套 cwd，以及在样本旁另行标注的非零退出码。样本正文有意**不含** `[exit code: N]` 行：真实的 bash presenter 正是因为卡片以徽章单独呈现退出状态，才把该标记从正文中消费掉；若保留它，钉住的将是一帧把退出状态显示两次的画面——而产品路径产不出这一帧。
|
||||
|
||||
`apps/web/tests/navigation-panes.e2e.ts` 在其既有的 `echo NAVIGATION_OK` bash 调用上新增真实浏览器场景，断言 jsdom 无法计算的部分：把输出面板挤压到窄于内容宽度后，行仍保持单行且面板产生横向溢出；运行状态点解析为绿色的 success token，而不是字面颜色（没有真实主题样式表时，`--dsw-*` 变量根本不产生计算值），且它位于卡片盒之内、提示标签之左——这正是那道 gutter 内边距所拥有的不变量；复制控件走的是页面自身的异步 Clipboard API，而非 `execCommand` 兜底路径。其 `terminal-card.expected.md` 基准记录了提示行中已解析的 workspace——这正是不带 `workdir` 的 bash 调用应当显示的内容，而非一个裸 `$`。
|
||||
|
||||
|
||||
@@ -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 .agents/notes/implemented/feature/2026-07-29-ask-question-web-presentation.md
|
||||
2026-07-29-ask-question-web-presentation.md: 11471bba08b723620b83af0e14e64a759d11c520
|
||||
2026-07-29-ask-question-web-presentation.zh.md: 6957d34fa5d3769340be9798998e59496e4b7f44
|
||||
2026-07-29-ask-question-web-presentation.md: a622a128a6b3ad1b1041dd8a0ae418c805655d1a
|
||||
2026-07-29-ask-question-web-presentation.zh.md: 5a43ba4f469565769234d7a13230e3edabfebf4f
|
||||
|
||||
@@ -12,7 +12,7 @@ Separately, the composer visuals had drifted from the current design: an expand-
|
||||
|
||||
## Decision
|
||||
|
||||
A pending question owns exactly two surfaces: the composer takeover collects the answers, and a dedicated `ask_user_question` toolview row in the transcript names the interaction outcome. The row registers into the keyed `tool.call.toolview` hole exactly like `todo_write` and composes the shared `ToolRow` (chrome, running sweep, leading expansion). Its summary is the interaction verdict rather than args: `waiting` while running, `N/M answered` from the result JSON once settled (a skipped answer — empty `selected`, no `custom` — stays out of the count), `cancelled` for `ASK_CANCELLED`, and `interrupted` with the shared amber stopped semantics for `ASK_ABORTED`. Malformed or truncated results fall back to the generic summary. `PendingCard` narrows to `PendingWait<'approval'>` and `ChatView` filters the pending list to approval waits, so the placeholder card now exists only for the approval takeover still on the roadmap.
|
||||
A pending question owns exactly two surfaces: the composer takeover collects the answers, and a dedicated `ask_user_question` toolview row in the transcript names the interaction outcome. The row registers into the keyed `tool.call.toolview` hole exactly like `todo_write` and composes the shared `ToolRow` (chrome, running sweep, leading expansion). Its summary is the interaction verdict rather than args: `waiting` while running, `N/M answered` from the result JSON once settled (a skipped answer — empty `selected`, no `custom` — stays out of the count), `cancelled` for `ASK_CANCELLED`, and `interrupted` with the shared amber stopped semantics for `ASK_ABORTED`. Malformed or truncated results fall back to the generic summary. `PendingCard` narrowed to `PendingWait<'approval'>` and `ChatView` filtered the pending list to approval waits, leaving the placeholder card to approvals alone; the approval composer takeover ([web permission and approval](2026-07-23-web-permission-and-approval.md)) has since removed it entirely.
|
||||
|
||||
The composer redesign moves paging into the footer next to the actions, renders multi-select options with explicit checkboxes, keeps single-select numbered rows, and replaces the expand-to-open custom entry with an always-visible custom input row (textarea for optionless questions). The `parseQuestionTitle` multi-select suffix convention is deleted; `multi_select` is already structured metadata, so the title renders verbatim.
|
||||
|
||||
@@ -36,7 +36,7 @@ Two adjacent fixes ride along. All generic toolview leading icons (and the hover
|
||||
|
||||
`ask_user_question` and `todo_write` now demonstrate the intended toolview pattern: compose `ToolRow`, summarize from call args or result JSON with shape-checked fallbacks, and register through the keyed slot. The bespoke `todo-row.module.css` is gone.
|
||||
|
||||
The row verdict strings are the one remaining hardcoded-English surface of the question flow; localizing them is deferred follow-up. `PendingCard` remains a visible-but-not-answerable approval placeholder until the approval composer takeover ships.
|
||||
The row verdict strings are the one remaining hardcoded-English surface of the question flow; localizing them is deferred follow-up. The approval composer takeover shipped ([web permission and approval](2026-07-23-web-permission-and-approval.md), height-capped per the [approval-panel note](../bug-fix/2026-07-30-approval-panel-command-cap.md)), and `PendingCard` no longer exists.
|
||||
|
||||
`ui-question` gains a `dsh-client-locale` dependency and an inject face where it previously had none; its contract (`QuestionComposerInjected`) lives with the consumer in `contract/slots.ts`.
|
||||
|
||||
|
||||
@@ -12,7 +12,7 @@ Web GUI 已经可以通过 `QuestionComposer` 的输入区接管收集回答，
|
||||
|
||||
## 决定
|
||||
|
||||
一个待回答的问题恰好拥有两个界面：输入区接管收集回答，会话记录中一个专门的 `ask_user_question` toolview 行陈述交互结果。该行与 `todo_write` 完全一样注册进带 key 的 `tool.call.toolview` 槽位，并复用共享的 `ToolRow`（外观、运行扫光、前导展开）。其摘要是交互裁决而非参数：运行中显示 `waiting`，结算后从结果 JSON 得出 `N/M answered`（被跳过的回答 —— `selected` 为空且无 `custom` —— 不计入），`ASK_CANCELLED` 显示 `cancelled`，`ASK_ABORTED` 显示 `interrupted` 并沿用共享的琥珀色 stopped 语义。畸形或截断的结果回退到通用摘要。`PendingCard` 收窄为 `PendingWait<'approval'>`，`ChatView` 将待处理列表过滤为仅审批等待，占位卡片从此只服务于仍在路线图上的审批接管。
|
||||
一个待回答的问题恰好拥有两个界面：输入区接管收集回答，会话记录中一个专门的 `ask_user_question` toolview 行陈述交互结果。该行与 `todo_write` 完全一样注册进带 key 的 `tool.call.toolview` 槽位，并复用共享的 `ToolRow`（外观、运行扫光、前导展开）。其摘要是交互裁决而非参数：运行中显示 `waiting`，结算后从结果 JSON 得出 `N/M answered`（被跳过的回答 —— `selected` 为空且无 `custom` —— 不计入），`ASK_CANCELLED` 显示 `cancelled`，`ASK_ABORTED` 显示 `interrupted` 并沿用共享的琥珀色 stopped 语义。畸形或截断的结果回退到通用摘要。`PendingCard` 曾收窄为 `PendingWait<'approval'>`，`ChatView` 曾将待处理列表过滤为仅审批等待，使占位卡片只服务于审批；其后审批输入区接管（[Web 权限与审批](2026-07-23-web-permission-and-approval.md)）已将它彻底移除。
|
||||
|
||||
输入区重设计将分页移到底部操作区旁，多选选项渲染显式复选框，单选保留编号行，并用始终可见的自定义输入行取代展开式自定义入口（无选项问题用多行文本框）。删除 `parseQuestionTitle` 的多选后缀约定；`multi_select` 已是结构化元数据，标题原样渲染。
|
||||
|
||||
@@ -36,7 +36,7 @@ Web GUI 已经可以通过 `QuestionComposer` 的输入区接管收集回答，
|
||||
|
||||
`ask_user_question` 与 `todo_write` 现在共同示范预期的 toolview 模式：复用 `ToolRow`、从调用参数或结果 JSON 做带形状校验回退的摘要、通过带 key 的槽位注册。专用的 `todo-row.module.css` 已删除。
|
||||
|
||||
行内裁决字符串是问题流程仅剩的硬编码英文面；将其本地化是推迟的后续工作。在审批输入区接管交付之前，`PendingCard` 仍是可见但不可操作的审批占位。
|
||||
行内裁决字符串是问题流程仅剩的硬编码英文面；将其本地化是推迟的后续工作。审批输入区接管已交付（[Web 权限与审批](2026-07-23-web-permission-and-approval.md)，并按[审批面板 Agent Note](../bug-fix/2026-07-30-approval-panel-command-cap.md)施加高度上限），`PendingCard` 已不复存在。
|
||||
|
||||
`ui-question` 新增 `dsh-client-locale` 依赖和此前没有的 inject face；其约定（`QuestionComposerInjected`）与消费者一起放在 `contract/slots.ts`。
|
||||
|
||||
|
||||
@@ -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 .agents/notes/implemented/feature/2026-07-30-queued-manual-compaction.md
|
||||
2026-07-30-queued-manual-compaction.md: 94afdd84dfe573ee2b60eb3dbfdae2dd5b6beb1e
|
||||
2026-07-30-queued-manual-compaction.zh.md: bd120050e621d1bfa3a677578e429f939b9c17d1
|
||||
2026-07-30-queued-manual-compaction.md: 3aa4e17bd673417569990090abec0ec29427665a
|
||||
2026-07-30-queued-manual-compaction.zh.md: 0763d6d127d158fa3b91b52aaa9b28ddf78e839f
|
||||
|
||||
@@ -12,7 +12,7 @@ The human command arrives between turns and must summarize asynchronously. A pro
|
||||
|
||||
Compaction also needs one mutual-exclusion fact shared by manual, pressure, overflow, and explicit-range entry points. A process-local flag alone cannot explain a crash-recovered log, while a summarize-first transaction leaves no durable evidence during the expensive interval. Conversely, treating marker pairs as exclusive containers would forbid valid idle injection even though injection is explicitly non-waking and immediate between turns.
|
||||
|
||||
This note extends the [compaction capability seam](2026-06-18-compaction-capability-seam.md), the [session end-seed boundary](../architecture/2026-07-30-session-end-seed-log-boundary.md), and the [removal of synthetic log-only turns](../simplification/2026-07-28-remove-synthetic-log-only-turns.md). The supersession audit found partial overlap only: each remains active and owns its broader decision.
|
||||
This note extends the [compaction capability seam](2026-06-18-compaction-capability-seam.md), the [session end-seed boundary](../architecture/2026-07-30-session-end-seed-log-boundary.md), and the [removal of synthetic log-only turns](../simplification/2026-07-28-remove-synthetic-log-only-turns.md). Each remains active and owns its broader decision; the overlap is partial only.
|
||||
|
||||
## Decision
|
||||
|
||||
|
||||
@@ -12,7 +12,7 @@ Status: implemented
|
||||
|
||||
手动、压力、溢出和显式范围入口点还需要共享同一项互斥事实。仅使用进程本地标志无法解释一份崩溃恢复后的日志，而先摘要再记录的事务在开销较大的等待期间不会留下持久证据。反过来，把标记对视为排他容器又会禁止有效的空闲注入，尽管注入按定义不会唤醒，并且会在轮次之间立即执行。
|
||||
|
||||
本 Agent Note 扩展[压缩能力 seam](2026-06-18-compaction-capability-seam.md)、[会话 end-seed 边界](../architecture/2026-07-30-session-end-seed-log-boundary.md)和[移除纯日志事件的合成轮次](../simplification/2026-07-28-remove-synthetic-log-only-turns.md)。取代关系审计只发现部分重叠：三者均保持活动状态，并拥有各自更广泛的决策。
|
||||
本 Agent Note 扩展[压缩能力 seam](2026-06-18-compaction-capability-seam.md)、[会话 end-seed 边界](../architecture/2026-07-30-session-end-seed-log-boundary.md)和[移除纯日志事件的合成轮次](../simplification/2026-07-28-remove-synthetic-log-only-turns.md)。三者均保持活动状态，并拥有各自更广泛的决策；重叠仅是部分的。
|
||||
|
||||
## 决策
|
||||
|
||||
|
||||
@@ -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 .agents/notes/implemented/feature/2026-07-30-search-render-card.md
|
||||
2026-07-30-search-render-card.md: 29544cb703f3ab048f4e7702935887ecf05179bf
|
||||
2026-07-30-search-render-card.zh.md: 01ffe25522c462a26e781f9bd455711331e58445
|
||||
2026-07-30-search-render-card.md: 585609bd059dbd9aa8283547fa8a4b223f7bdd99
|
||||
2026-07-30-search-render-card.zh.md: a129b024fcbe067025e9bcd6cfd6aeeb5400347a
|
||||
|
||||
@@ -18,7 +18,7 @@ The discriminant is `shape`, not `kind`, deliberately: the same presentation mod
|
||||
|
||||
One view with two shapes rather than two cards, because both tools are the same visual object — a search result — and a web consumer switches on one `card` value, then on `shape` for the row layout. The discriminated `shape` keeps each variant's fields non-optional (a matches view always has `files`, a paths view always has `paths`) instead of a single interface where every shape-specific field is optional.
|
||||
|
||||
The view carries **no** result text. An earlier revision attached the model-facing `result.content` to the view; that was a no-op because consumer fallbacks already read the raw `tool/result` content, and it serialized the whole search text a second time into the persisted view. The view is the structured shape only; a UI without a search card falls back to the raw result content.
|
||||
The view carries **no** result text. Attaching the model-facing `result.content` would be a no-op — consumer fallbacks already read the raw `tool/result` content — and would serialize the whole search text a second time into the persisted view. The view is the structured shape only; a UI without a search card falls back to the raw result content.
|
||||
|
||||
The card tag is result-time only. A search call stays a `GenericCallView` (`kind: 'search'`): the pending state has no matches or paths to show, so there is nothing a `SearchCallView` would carry that the generic title does not. This is the asymmetry with the terminal card, whose call view carries the command, cwd, and description that exist before execution; a search's structured content exists only after `execute`.
|
||||
|
||||
@@ -30,7 +30,7 @@ The card tag is result-time only. A search call stays a `GenericCallView` (`kind
|
||||
|
||||
The `SearchMeta` member shapes are object-literal `type` aliases, not the `SearchFileMatches`/`SearchLineMatch` interfaces the view exposes, because only a type alias is assignable to the `JsonValue` index signature `presentationMeta` returns; the two are structurally identical, so the projected value still reads back as a `SearchResultView`.
|
||||
|
||||
A consumer without a dedicated `search` arm falls back to the same generic body and reads the model-facing text from the raw result. Because the search view carries no `content` of its own and grep/glob returned a generic card before this PR, that fallback stays byte-identical to the pre-search-card path. The frontend that renders the structured `files`/`paths` shape is independent of this backend contract and its two producers.
|
||||
A consumer without a dedicated `search` arm falls back to the same generic body and reads the model-facing text from the raw result. Because the search view carries no `content` of its own and grep/glob previously returned a generic card, that fallback stays byte-identical to the pre-search-card path. The frontend that renders the structured `files`/`paths` shape is independent of this backend contract and its two producers.
|
||||
|
||||
## Alternatives considered
|
||||
|
||||
@@ -40,7 +40,7 @@ A consumer without a dedicated `search` arm falls back to the same generic body
|
||||
|
||||
**Attach the model-facing text as the view's `content`.** Rejected: a no-op for every current consumer and a second serialization of the whole search text into the persisted view. The view is the structured shape; text fallback reads the raw result content.
|
||||
|
||||
**A meta channel on `PostToolDecision` so `dsh-spill-policy` bounds `meta` like it bounds `content`.** Rejected for this PR: it changes the core tool decision contract and the spill-policy plugin for one tool's payload. The projection bounding its own `meta` at a config byte cap is self-contained and keeps the seam unchanged.
|
||||
**A meta channel on `PostToolDecision` so `dsh-spill-policy` bounds `meta` like it bounds `content`.** Rejected here: it changes the core tool decision contract and the spill-policy plugin for one tool's payload. The projection bounding its own `meta` at a config byte cap is self-contained and keeps the seam unchanged.
|
||||
|
||||
**A call-time `SearchCallView` mirroring the terminal card's both-sides symmetry.** Rejected: a search call has no matches or paths before `execute`, so the view would carry only the title the `GenericCallView` already carries.
|
||||
|
||||
|
||||
@@ -18,7 +18,7 @@ Status: implemented
|
||||
|
||||
用一个带两种形状的视图而非两张卡片，因为两个工具是同一个视觉对象 —— 一个搜索结果 —— web 消费方先在一个 `card` 值上分支，再在 `shape` 上分支决定行布局。判别式 `shape` 让每个变体的字段保持非可选（matches 视图总有 `files`，paths 视图总有 `paths`），而不是一个所有形状相关字段都可选的单一接口。
|
||||
|
||||
该视图**不**携带结果文本。早期版本曾把面向模型的 `result.content` 附到视图上；但消费方的回退路径本就读取原始 `tool/result` 内容，因此这不会产生效果，却会把整段搜索文本又序列化进持久化视图一遍。视图只承载结构化形状；无 search 卡片的 UI 回退到原始结果内容。
|
||||
该视图**不**携带结果文本。把面向模型的 `result.content` 附到视图上不会产生效果——消费方的回退路径本就读取原始 `tool/result` 内容——却会把整段搜索文本又序列化进持久化视图一遍。视图只承载结构化形状；无 search 卡片的 UI 回退到原始结果内容。
|
||||
|
||||
卡片标签只在结果时存在。搜索调用保持为 `GenericCallView`（`kind: 'search'`）：pending 状态没有匹配或路径可展示，所以 `SearchCallView` 能携带的东西不会比 generic 标题更多。这是与 terminal 卡片的不对称之处 —— terminal 的调用视图携带执行前就存在的命令、cwd、description；搜索的结构化内容只在 `execute` 之后才存在。
|
||||
|
||||
@@ -30,7 +30,7 @@ Status: implemented
|
||||
|
||||
`SearchMeta` 的成员形状是对象字面量 `type` 别名，而非视图暴露的 `SearchFileMatches`/`SearchLineMatch` 接口，因为只有 type 别名可赋给 `presentationMeta` 返回的 `JsonValue` 索引签名；两者结构等价，所以投影值仍读回为 `SearchResultView`。
|
||||
|
||||
没有专用 `search` 分支的消费方会回退到同一个 generic body，并从原始结果中读取面向模型的文本。因为搜索视图不带自己的 `content`，而本 PR 之前 grep/glob 返回的是 generic 卡片，所以该回退与引入 search 卡片之前的路径逐字节一致。渲染结构化 `files`/`paths` 形状的前端独立于这个后端约定及其两个生产者。
|
||||
没有专用 `search` 分支的消费方会回退到同一个 generic body，并从原始结果中读取面向模型的文本。因为搜索视图不带自己的 `content`，而 grep/glob 此前返回的是 generic 卡片，所以该回退与引入 search 卡片之前的路径逐字节一致。渲染结构化 `files`/`paths` 形状的前端独立于这个后端约定及其两个生产者。
|
||||
|
||||
## 考虑过的备选
|
||||
|
||||
@@ -40,7 +40,7 @@ Status: implemented
|
||||
|
||||
**把面向模型的文本作为视图的 `content` 附上。** 否决：对每个当前消费方是 no-op，且把整段搜索文本第二次序列化进持久化视图。视图是结构化形状；文本回退读原始结果内容。
|
||||
|
||||
**在 `PostToolDecision` 上加 meta 通道，让 `dsh-spill-policy` 像约束 `content` 那样约束 `meta`。** 本 PR 否决：它为一个工具的载荷改动核心工具决策约定与 spill-policy 插件。投影在配置字节上限处约束自己的 `meta` 是自包含的，且保持 seam 不变。
|
||||
**在 `PostToolDecision` 上加 meta 通道，让 `dsh-spill-policy` 像约束 `content` 那样约束 `meta`。** 此处否决：它为一个工具的载荷改动核心工具决策约定与 spill-policy 插件。投影在配置字节上限处约束自己的 `meta` 是自包含的，且保持 seam 不变。
|
||||
|
||||
**镜像 terminal 卡片双侧对称的调用时 `SearchCallView`。** 否决：搜索调用在 `execute` 前没有匹配或路径，视图只会携带 `GenericCallView` 已有的标题。
|
||||
|
||||
@@ -56,6 +56,6 @@ Status: implemented
|
||||
|
||||
## 相关
|
||||
|
||||
- [工具调用呈现的带标签渲染意图联合](../architecture/2026-07-02-tool-render-intent-union.md) —— 本 PR 用 `search` 结果标签扩展的 `card` 标签词汇。
|
||||
- [工具调用呈现的带标签渲染意图联合](../architecture/2026-07-02-tool-render-intent-union.md) —— 本变更用 `search` 结果标签扩展的 `card` 标签词汇。
|
||||
- [Canonical 工具输出约定](../architecture/2026-07-20-canonical-tool-output-contract.md) —— 本投影所乘的 value/render/`presentationMeta` 划分；结构化值留在执行本地，卡片乘 `meta`。
|
||||
- [Web terminal 卡片](2026-07-28-web-terminal-card.md) —— 本 PR 在后端镜像的先例：工具把结果投影进 `presentationMeta` 与一个 `presentResult` 视图；搜索卡片的 web 消费方是与之类比的后续。
|
||||
- [Web terminal 卡片](2026-07-28-web-terminal-card.md) —— 本变更在后端镜像的先例：工具把结果投影进 `presentationMeta` 与一个 `presentResult` 视图；搜索卡片的 web 消费方是与之类比的后续。
|
||||
|
||||
@@ -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 .agents/notes/implemented/feature/2026-07-30-web-diff-card.md
|
||||
2026-07-30-web-diff-card.md: b078da8d0e688d705683599467bd98b5c6a0be48
|
||||
2026-07-30-web-diff-card.zh.md: 901331907ed9052541aaee0d4fe70531b030d0f9
|
||||
2026-07-30-web-diff-card.md: d8b0cf32e42af45e16e6f7059c873c384d4a9229
|
||||
2026-07-30-web-diff-card.zh.md: 51df03c3f8b79cd8415a15bd30e92e3c152f335e
|
||||
|
||||
@@ -32,7 +32,7 @@ The chat row renders the diff resident under its path-link summary, capped at `C
|
||||
|
||||
**A side-by-side (two-column) diff.** Rejected for now by the owner: it is denser but does not fit the narrow chat row, and the goal was parity with the TUI's single-column unified form. A two-column mode in the details panel is a later props change, not a redesign.
|
||||
|
||||
**Git-style line-number gutters.** The `FileDiff` contract carries only `{ path, oldText, newText }` — `structuredPatch`'s hunk start lines are dropped in `diff.ts`, so no line number reaches the client. Rendering a numbered gutter needs a backend contract change (carry `oldStart`/`newStart`) and a matching TUI upgrade to stay consistent; deferred so this PR stays a pure Web consumer of the existing contract.
|
||||
**Git-style line-number gutters.** The `FileDiff` contract carries only `{ path, oldText, newText }` — `structuredPatch`'s hunk start lines are dropped in `diff.ts`, so no line number reaches the client. Rendering a numbered gutter needs a backend contract change (carry `oldStart`/`newStart`) and a matching TUI upgrade to stay consistent; deferred so this change stays a pure Web consumer of the existing contract.
|
||||
|
||||
**Reuse `CodeBlock`.** Rejected for the same reason the terminal card was: `CodeBlock` soft-wraps and has no per-line `+`/`-` role, no path headers, and no footer. The two share geometry and font tokens, which is the only part where one implementation is correct for both.
|
||||
|
||||
|
||||
@@ -32,7 +32,7 @@ chat 行把 diff 常驻渲染在路径链接摘要之下，上限 `CHAT_DIFF_MAX
|
||||
|
||||
**并排（双栏）diff。** owner 目前拒绝：它更密但不适合狭窄的 chat 行，目标是与 TUI 单栏统一形式对齐。详情面板里的双栏模式是后续的 props 改动，不是重设计。
|
||||
|
||||
**git 式行号槽。** `FileDiff` 约定只携带 `{ path, oldText, newText }` —— `structuredPatch` 的 hunk 起始行在 `diff.ts` 里被丢弃，所以没有行号抵达客户端。渲染行号槽需要后端约定改动（携带 `oldStart`/`newStart`）并同步升级 TUI 以保持一致；推迟，使本 PR（Pull Request）保持为对既有约定的纯 Web 消费。
|
||||
**git 式行号槽。** `FileDiff` 约定只携带 `{ path, oldText, newText }` —— `structuredPatch` 的 hunk 起始行在 `diff.ts` 里被丢弃，所以没有行号抵达客户端。渲染行号槽需要后端约定改动（携带 `oldStart`/`newStart`）并同步升级 TUI 以保持一致；推迟，使本变更保持为对既有约定的纯 Web 消费。
|
||||
|
||||
**复用 `CodeBlock`。** 因与 terminal 卡片相同的理由拒绝：`CodeBlock` 会折行，且没有每行 `+`/`-` 角色、没有路径头、没有页脚。两者共享几何与字体 token，那是唯一一处一个实现对两者都正确的部分。
|
||||
|
||||
|
||||
@@ -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 .agents/notes/implemented/feature/2026-07-30-web-read-card-frontend.md
|
||||
2026-07-30-web-read-card-frontend.md: e659645066b706f35709fead4c11023eb4fe9554
|
||||
2026-07-30-web-read-card-frontend.zh.md: ac3972ace7458b8a751b4cc342bbdb3e2b0a7a9e
|
||||
2026-07-30-web-read-card-frontend.md: 1d9b6d7fa0c8b5391d175a53507db88a84234b91
|
||||
2026-07-30-web-read-card-frontend.zh.md: 2678d50e851e4b3a079f59c7db6ec08ecc5c4aed
|
||||
|
||||
@@ -18,11 +18,11 @@ The [read backend](2026-07-30-web-read-card.md) added a fourth render-intent car
|
||||
|
||||
The chat row renders the card **resident** under the summary line, capped at `CHAT_READ_MAX_LINES` (8, half the primitive's default), the same posture `BashRow` gives a terminal card — the block's internal expander keeps a long read from taking over the message flow. Two render sites carry it: the keyed `ReadRow` (registered under `read` through `ctx.slots.inject`, exactly as the bash sample) whose summary is the file path as an openable host link, and `GenericToolCard`'s fallback for a read-declaring tool without its own keyed row (e.g. `web_fetch`, which classifies to the `read` variant). The details panel renders the same card at the primitive's own full-height cap (16), because the panel is the single-call reading surface.
|
||||
|
||||
Whole-row collapse/expand (defaulting every tool call to collapsed) is a separate later change that will flip every resident card at once; this note's card is resident, matching the terminal card it sits beside.
|
||||
Whole-row collapse/expand (defaulting every tool call to collapsed) is owned by the [unified expand-and-inspect note](2026-07-30-web-tool-row-unified-expand-and-inspect.md), which flipped every resident card at once; this note's card is resident, matching the terminal card it sits beside.
|
||||
|
||||
**Read-card grammars load lazily; only the boot three stay eager.** `highlight.ts` is a platform seed `ui-primitives` loads on every Web boot, and its warm-up unconditionally builds the shiki singleton. The read card's `langFromPath` hints span the full source/config/markup extension set (python, rust, yaml, html, …); registering all of them eagerly would add ~1.6 MB of grammar modules to the boot chunk and their synchronous init to every session, including sessions that never open a read card. So only the three grammars every session already renders — TypeScript, shell, JSON (the markdown-fence and `run_code` languages) — load at boot. Each read-card extension grammar sits behind a dynamic `import()` in `LAZY_GRAMMARS`, keyed by the grammar id its aliases resolve to. On the first `highlightLines`/`highlightToHtml` call for a lazy language, `ensureGrammar` starts the import (once) and returns not-ready, so the card renders plain that frame; when the import resolves it registers the grammar with `loadLanguageSync`, bumps a load counter, and notifies subscribers. `ReadBlock` and `CodeBlock` subscribe through `useSyncExternalStore(subscribeGrammarLoaded, grammarLoadCount)`, so the card re-renders with highlighting the moment the grammar is ready. An unknown/absent language still returns undefined synchronously (plain, never an error).
|
||||
|
||||
**The empty-window copy control is hidden, matching `TerminalBlock`.** A successful read of an empty file returns `lines: []`, `totalLines: 0`, and `presentResult` still projects `card: 'read'`, so the empty-window branch is reachable — the read card is not, as an earlier draft assumed, unreachable for an empty result. `ReadBlock` therefore hides the copy control when `lines` is empty, exactly as `TerminalBlock` hides copy on empty output, so the button can never wipe the clipboard with an empty string.
|
||||
**The empty-window copy control is hidden, matching `TerminalBlock`.** A successful read of an empty file returns `lines: []`, `totalLines: 0`, and `presentResult` still projects `card: 'read'`, so the empty-window branch is reachable. `ReadBlock` therefore hides the copy control when `lines` is empty, exactly as `TerminalBlock` hides copy on empty output, so the button can never wipe the clipboard with an empty string.
|
||||
|
||||
## Alternatives considered
|
||||
|
||||
|
||||
@@ -18,11 +18,11 @@ Status: implemented
|
||||
|
||||
聊天行把卡片**常驻**渲染在摘要行之下，上限 `CHAT_READ_MAX_LINES`（8，是 primitive 默认值的一半），与 `BashRow` 对终端卡片的姿态相同 —— block 的内部展开器让长读取不会占据整个消息流。两个渲染点承载它：keyed `ReadRow`（经 `ctx.slots.inject` 以 `read` 键注册，与 bash 样例完全一致），其摘要是作为可打开的宿主链接的文件路径；以及 `GenericToolCard` 对没有自己 keyed 行的读取声明工具（例如归到 `read` 变体的 `web_fetch`）的回退。详情面板以 primitive 自己的全高上限（16）渲染同一张卡片，因为面板是单次调用的阅读界面。
|
||||
|
||||
整行折叠/展开（把每个工具调用默认折叠）是一个单独的后续改动，它会一次性翻转每张常驻卡片；本 note 的卡片是常驻的，与它旁边的终端卡片一致。
|
||||
整行折叠/展开（把每个工具调用默认折叠）归[统一展开与检视 note](2026-07-30-web-tool-row-unified-expand-and-inspect.md)所有，它已一次性翻转每张常驻卡片；本 note 的卡片是常驻的，与它旁边的终端卡片一致。
|
||||
|
||||
**读取卡片的语法按需 lazy 加载，只有 boot 三种保持 eager。** `highlight.ts` 是 `ui-primitives` 在每次 Web 启动都加载的平台 seed，其预热会无条件构建 shiki 单例。读取卡片的 `langFromPath` 提示覆盖完整的源码/配置/标记扩展集（python、rust、yaml、html……）；把它们全部 eager 注册会给启动 chunk 增加约 1.6 MB 的语法模块、并把它们的同步初始化摊给每个会话，包括从不打开读取卡片的会话。因此只有每个会话本就渲染的三种语法 —— TypeScript、shell、JSON（markdown 围栏与 `run_code` 语言）—— 在 boot 时加载。每种读取卡片扩展语法置于 `LAZY_GRAMMARS` 中一个动态 `import()` 之后，以其别名解析到的语法 id 为键。对某个 lazy 语言首次调用 `highlightLines`/`highlightToHtml` 时，`ensureGrammar` 启动 import（仅一次）并返回未就绪，于是卡片该帧渲染纯文本；import 解析后用 `loadLanguageSync` 注册该语法、递增一个加载计数、并通知订阅者。`ReadBlock` 与 `CodeBlock` 通过 `useSyncExternalStore(subscribeGrammarLoaded, grammarLoadCount)` 订阅，因此语法就绪的那一刻卡片就重渲染带上高亮。未知/缺省语言仍同步返回 undefined（纯文本，绝不报错）。
|
||||
|
||||
**空窗口的复制控件被隐藏，与 `TerminalBlock` 对齐。** 成功读取一个空文件会返回 `lines: []`、`totalLines: 0`，且 `presentResult` 仍投出 `card: 'read'`，因此空窗口分支是可达的 —— 读取卡片并非如早前草稿所假设的对空结果不可达。故 `ReadBlock` 在 `lines` 为空时隐藏复制控件，正如 `TerminalBlock` 对空输出隐藏复制，使按钮绝不会用空字符串清空剪贴板。
|
||||
**空窗口的复制控件被隐藏，与 `TerminalBlock` 对齐。** 成功读取一个空文件会返回 `lines: []`、`totalLines: 0`，且 `presentResult` 仍投出 `card: 'read'`，因此空窗口分支是可达的。故 `ReadBlock` 在 `lines` 为空时隐藏复制控件，正如 `TerminalBlock` 对空输出隐藏复制，使按钮绝不会用空字符串清空剪贴板。
|
||||
|
||||
## Alternatives considered
|
||||
|
||||
|
||||
@@ -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 .agents/notes/implemented/feature/2026-07-30-web-read-card.md
|
||||
2026-07-30-web-read-card.md: 26d1634b6be86666980e65f842de51c868c26efd
|
||||
2026-07-30-web-read-card.zh.md: c48cd56b7f919d5ceb702f890ee18a2a735da347
|
||||
2026-07-30-web-read-card.md: 8ed170e3bbe63cdee85f0ee8440ab1d975c6ff0a
|
||||
2026-07-30-web-read-card.zh.md: 68ab9a118e946f397b69691a02a55d1c43ee41b1
|
||||
|
||||
@@ -16,7 +16,7 @@ Add a fourth `card` tag, `read`, to the [render-intent union](../architecture/20
|
||||
|
||||
The read tool projects the structured window through `output.presentationMeta`, the same persisted channel write/edit use for their applied-diff hunks ([canonical tool output contract](../architecture/2026-07-20-canonical-tool-output-contract.md)). `presentationMeta` runs once for a top-level surface call, returns `{ path, offset, lines, totalLines, lang? }` as JSON the session validates and stores on the result's `meta`, and `presentResult` narrows that meta back into the `ReadResultView` on both live and replay paths. `offset` (the 1-based first line the window requested) rides along because a byte cap below the first selected line yields an empty `lines` array with a positive `totalLines`; without the persisted `offset` a replayed card of such a window could not report where it starts or where a continuation resumes, and the last-line and re-parse fallbacks are both lossy. Without this channel the line array and total would be unreachable: the raw output object is not on the wire, and re-parsing the `N: text` text is lossy and fragile against the truncation footer.
|
||||
|
||||
`presentResult` returns `undefined` — the generic fallback — whenever the meta is absent or malformed (`readMetaFromMeta` narrows it defensively, so a replay of an older logged result never throws), whenever the result is an error, and whenever the single text block is not the read envelope. A pre-card logged result — a valid read envelope with no persisted `meta`, recorded before this card existed — takes that same `undefined` path deliberately: the client falls back to the raw `result.content`, so it shows the enveloped `<path>/<type>/<content>` text rather than the envelope-stripped generic card the old presenter returned. This is the accepted degradation under the [pre-release stance](../../../../AGENTS.md#pre-release-stance-foundation-over-blast-radius): reject the old on-disk format rather than add an envelope-stripping compatibility branch, since this PR re-records every published fixture and the session format promises no backward compatibility. On the success path `presentResult` carries `content` (the envelope-stripped text) alongside the structured fields, so a UI without the read capability renders the file text through its generic/default card arm. The former TUI established the need for this fallback: its non-exhaustive result switch read `view.content`, while a separate dim-Markdown gate also had to admit `card: 'read'`. That frontend has since been removed, but the content fallback remains part of the view contract for any consumer without a structured read card.
|
||||
`presentResult` returns `undefined` — the generic fallback — whenever the meta is absent or malformed (`readMetaFromMeta` narrows it defensively, so a replay of an older logged result never throws), whenever the result is an error, and whenever the single text block is not the read envelope. A pre-card logged result — a valid read envelope with no persisted `meta`, recorded before this card existed — takes that same `undefined` path deliberately: the client falls back to the raw `result.content`, so it shows the enveloped `<path>/<type>/<content>` text rather than the envelope-stripped generic card the old presenter returned. This is the accepted degradation under the [pre-release stance](../../../../AGENTS.md#pre-release-stance-foundation-over-blast-radius): reject the old on-disk format rather than add an envelope-stripping compatibility branch, since this change re-records every published fixture and the session format promises no backward compatibility. On the success path `presentResult` carries `content` (the envelope-stripped text) alongside the structured fields, so a UI without the read capability renders the file text through its generic/default card arm. The former TUI established the need for this fallback: its non-exhaustive result switch read `view.content`, while a separate dim-Markdown gate also had to admit `card: 'read'`. That frontend has since been removed, but the content fallback remains part of the view contract for any consumer without a structured read card.
|
||||
|
||||
### Language hint derivation
|
||||
|
||||
@@ -40,7 +40,7 @@ The read tool now computes `presentationMeta` for every top-level read, a small
|
||||
|
||||
## Testing
|
||||
|
||||
`packages/fs/tool-fs/tests/read-render.spec.ts` unit-tests `langFromPath` (known extensions case-insensitively, extension read after the last segment and last dot, and the `undefined` cases: dotfile, extensionless, trailing dot, unknown) and `readMetaFromMeta` (a well-formed narrow with and without `lang`, and every rejection: non-object, array, missing or wrong-typed `path`/`totalLines`/`lines`, a malformed line entry, a non-string `lang`, and — because the function narrows the opaque persisted `meta` boundary — the semantically invalid paths a well-typed replayed JSON can still carry: an `offset` that is not a 1-based integer, a first line `number` below `offset`, a line `number` that is not a 1-based integer (`0`, `1.5`, `NaN`, `Infinity`), a `totalLines` that is not a non-negative integer (`-1`, `1.5`, `NaN`), and lines whose numbers duplicate, decrease, or exceed `totalLines`; it also narrows an empty window at a positive `offset` (a byte cap below the first selected line). `packages/fs/tool-fs/tests/tools.spec.ts` pins the tool wiring: `execute` attaches the structured window (with and without a `lang` hint) as `meta`, `presentResult` narrows it into a `card: 'read'` view carrying the envelope-stripped `content`, and the decline paths (error result, non-single-text content, malformed envelope with valid meta, and valid envelope with absent or malformed meta) all fall back to `undefined`. Both changed source files hold per-file 100% coverage. This PR carries the snapshot evidence for the persisted meta and the extended union, not for a new rendered view: the re-recorded ACP session fixtures (`fs-read`, `fs-read-window`, `fs-edit`, `fs-policy-reject`, `fs-write-overwrite`, `parallel-tool-calls`, `workspace-context`, `workspace-edit`) pin the persisted read `meta` (with `{{cwd}}`-tokenized paths), and `cordis-inspect-jsdoc` pins the four-member `ToolResultView` union. The then-current terminal snapshot also pinned that a consumer's generic dim-Markdown fallback stayed byte-identical; the structured card's own assembled-application transcript belonged to its consuming frontend change.
|
||||
`packages/fs/tool-fs/tests/read-render.spec.ts` unit-tests `langFromPath` (known extensions case-insensitively, extension read after the last segment and last dot, and the `undefined` cases: dotfile, extensionless, trailing dot, unknown) and `readMetaFromMeta` (a well-formed narrow with and without `lang`, and every rejection: non-object, array, missing or wrong-typed `path`/`totalLines`/`lines`, a malformed line entry, a non-string `lang`, and — because the function narrows the opaque persisted `meta` boundary — the semantically invalid paths a well-typed replayed JSON can still carry: an `offset` that is not a 1-based integer, a first line `number` below `offset`, a line `number` that is not a 1-based integer (`0`, `1.5`, `NaN`, `Infinity`), a `totalLines` that is not a non-negative integer (`-1`, `1.5`, `NaN`), and lines whose numbers duplicate, decrease, or exceed `totalLines`; it also narrows an empty window at a positive `offset` (a byte cap below the first selected line). `packages/fs/tool-fs/tests/tools.spec.ts` pins the tool wiring: `execute` attaches the structured window (with and without a `lang` hint) as `meta`, `presentResult` narrows it into a `card: 'read'` view carrying the envelope-stripped `content`, and the decline paths (error result, non-single-text content, malformed envelope with valid meta, and valid envelope with absent or malformed meta) all fall back to `undefined`. Both changed source files hold per-file 100% coverage. This change carries the snapshot evidence for the persisted meta and the extended union, not for a new rendered view: the re-recorded ACP session fixtures (`fs-read`, `fs-read-window`, `fs-edit`, `fs-policy-reject`, `fs-write-overwrite`, `parallel-tool-calls`, `workspace-context`, `workspace-edit`) pin the persisted read `meta` (with `{{cwd}}`-tokenized paths), and `cordis-inspect-jsdoc` pins the four-member `ToolResultView` union. The then-current terminal snapshot also pinned that a consumer's generic dim-Markdown fallback stayed byte-identical; the structured card's own assembled-application transcript belonged to its consuming frontend change.
|
||||
|
||||
## Related
|
||||
|
||||
|
||||
@@ -16,7 +16,7 @@ Status: implemented
|
||||
|
||||
read 工具通过 `output.presentationMeta` 投影结构化窗口，这与 write/edit 用来投影其应用 diff hunk 的持久化通道相同（[规范化工具输出约定](../architecture/2026-07-20-canonical-tool-output-contract.md)）。`presentationMeta` 对一次顶层 surface 调用运行一次，返回 `{ path, offset, lines, totalLines, lang? }` 作为会话校验并存储在结果 `meta` 上的 JSON，`presentResult` 在 live 和回放路径上都把该 meta 收窄回 `ReadResultView`。`offset`（窗口请求的 1-based 起始行）一并携带，是因为当字节上限低于首个选中行时，窗口会返回空的 `lines` 数组而 `totalLines` 为正；没有持久化的 `offset`，这类窗口的回放 card 就无法报告它从哪行开始、或续读应从哪行继续，而末行推断与文本重解析两种兜底都有损。没有这个通道，行数组和总数就无法触及：原始输出对象不在线上，而重新解析 `N: text` 文本既有损又对截断脚注脆弱。
|
||||
|
||||
`presentResult` 在以下情况返回 `undefined`——即 generic 回退：meta 缺失或畸形（`readMetaFromMeta` 防御性收窄它，因此回放旧的已记录结果永不抛错）、结果是错误、以及单个文本块不是 read 信封。本 card 出现之前记录的结果——信封合法但无持久化 `meta`——有意走同一条 `undefined` 路径：客户端回退到原始 `result.content`，因此显示带 `<path>/<type>/<content>` 信封的原文，而非旧展示器返回的剥信封 generic card。这是 [pre-release 立场](../../../../AGENTS.md#pre-release-stance-foundation-over-blast-radius)下接受的降级：拒绝旧的磁盘格式，而非加一个剥信封的兼容分支——本 PR 已重录全部已发布 fixtures，且 session 格式不承诺向后兼容。在成功路径上，`presentResult` 在结构化字段之外携带 `content`（剥信封后的文本），因此不具备 read 能力的 UI 会通过自己的 generic/default card 分支渲染文件文本。原 TUI 证明了这条回退的必要性：它的非穷尽结果 switch 读取 `view.content`，而另一道 dim-Markdown 门控也必须接纳 `card: 'read'`。该前端随后被移除，但对任何没有结构化 read 卡片的消费方而言，content 回退仍是视图约定的一部分。
|
||||
`presentResult` 在以下情况返回 `undefined`——即 generic 回退：meta 缺失或畸形（`readMetaFromMeta` 防御性收窄它，因此回放旧的已记录结果永不抛错）、结果是错误、以及单个文本块不是 read 信封。本 card 出现之前记录的结果——信封合法但无持久化 `meta`——有意走同一条 `undefined` 路径：客户端回退到原始 `result.content`，因此显示带 `<path>/<type>/<content>` 信封的原文，而非旧展示器返回的剥信封 generic card。这是 [pre-release 立场](../../../../AGENTS.md#pre-release-stance-foundation-over-blast-radius)下接受的降级：拒绝旧的磁盘格式，而非加一个剥信封的兼容分支——本变更已重录全部已发布 fixtures，且 session 格式不承诺向后兼容。在成功路径上，`presentResult` 在结构化字段之外携带 `content`（剥信封后的文本），因此不具备 read 能力的 UI 会通过自己的 generic/default card 分支渲染文件文本。原 TUI 证明了这条回退的必要性：它的非穷尽结果 switch 读取 `view.content`，而另一道 dim-Markdown 门控也必须接纳 `card: 'read'`。该前端随后被移除，但对任何没有结构化 read 卡片的消费方而言，content 回退仍是视图约定的一部分。
|
||||
|
||||
### 语言提示推导
|
||||
|
||||
@@ -40,7 +40,7 @@ read 工具现在为每次顶层 read 计算 `presentationMeta`，这是对已
|
||||
|
||||
## Testing
|
||||
|
||||
`packages/fs/tool-fs/tests/read-render.spec.ts` 单测 `langFromPath`（已知扩展名的大小写不敏感、扩展名在最后一段与最后一个点之后读取、以及 `undefined` 各情况：dotfile、无扩展名、结尾的点、未知）与 `readMetaFromMeta`（含与不含 `lang` 的良构收窄，以及每种拒绝：非对象、数组、缺失或类型错误的 `path`/`totalLines`/`lines`、畸形行项、非字符串 `lang`，以及——因为该函数收窄持久化的 opaque `meta` 边界——良构类型的回放 JSON 仍可能携带的语义无效路径：不是 1-based 整数的 `offset`、小于 `offset` 的首行 `number`、不是 1-based 整数的行 `number`（`0`、`1.5`、`NaN`、`Infinity`）、不是非负整数的 `totalLines`（`-1`、`1.5`、`NaN`）、以及行号重复、递减或超过 `totalLines` 的情况；并且收窄正 `offset` 处的空窗口（字节上限低于首个选中行））。`packages/fs/tool-fs/tests/tools.spec.ts` 固定工具接线：`execute` 把结构化窗口（含与不含 `lang` 提示）作为 `meta` 附上、`presentResult` 把它收窄为携带剥信封 `content` 的 `card: 'read'` 视图、以及各拒绝路径（错误结果、非单文本内容、meta 有效但信封畸形、信封有效但 meta 缺失或畸形）都回退到 `undefined`。两个改动的源文件保持逐文件 100% 覆盖率。本 PR 携带的是持久化 meta 与扩展后联合类型的快照证据，而非新渲染视图的证据：重录的 ACP session fixtures（`fs-read`、`fs-read-window`、`fs-edit`、`fs-policy-reject`、`fs-write-overwrite`、`parallel-tool-calls`、`workspace-context`、`workspace-edit`）钉住持久化的读取 `meta`（含 `{{cwd}}` 令牌化路径），`cordis-inspect-jsdoc` 钉住四成员的 `ToolResultView` 联合类型。当时的终端快照还钉住了消费方的 generic dim-Markdown 回退保持逐字节一致；结构化卡片自身的组装应用 transcript 则属于消费它的前端变更。
|
||||
`packages/fs/tool-fs/tests/read-render.spec.ts` 单测 `langFromPath`（已知扩展名的大小写不敏感、扩展名在最后一段与最后一个点之后读取、以及 `undefined` 各情况：dotfile、无扩展名、结尾的点、未知）与 `readMetaFromMeta`（含与不含 `lang` 的良构收窄，以及每种拒绝：非对象、数组、缺失或类型错误的 `path`/`totalLines`/`lines`、畸形行项、非字符串 `lang`，以及——因为该函数收窄持久化的 opaque `meta` 边界——良构类型的回放 JSON 仍可能携带的语义无效路径：不是 1-based 整数的 `offset`、小于 `offset` 的首行 `number`、不是 1-based 整数的行 `number`（`0`、`1.5`、`NaN`、`Infinity`）、不是非负整数的 `totalLines`（`-1`、`1.5`、`NaN`）、以及行号重复、递减或超过 `totalLines` 的情况；并且收窄正 `offset` 处的空窗口（字节上限低于首个选中行））。`packages/fs/tool-fs/tests/tools.spec.ts` 固定工具接线：`execute` 把结构化窗口（含与不含 `lang` 提示）作为 `meta` 附上、`presentResult` 把它收窄为携带剥信封 `content` 的 `card: 'read'` 视图、以及各拒绝路径（错误结果、非单文本内容、meta 有效但信封畸形、信封有效但 meta 缺失或畸形）都回退到 `undefined`。两个改动的源文件保持逐文件 100% 覆盖率。本变更携带的是持久化 meta 与扩展后联合类型的快照证据，而非新渲染视图的证据：重录的 ACP session fixtures（`fs-read`、`fs-read-window`、`fs-edit`、`fs-policy-reject`、`fs-write-overwrite`、`parallel-tool-calls`、`workspace-context`、`workspace-edit`）钉住持久化的读取 `meta`（含 `{{cwd}}` 令牌化路径），`cordis-inspect-jsdoc` 钉住四成员的 `ToolResultView` 联合类型。当时的终端快照还钉住了消费方的 generic dim-Markdown 回退保持逐字节一致；结构化卡片自身的组装应用 transcript 则属于消费它的前端变更。
|
||||
|
||||
## Related
|
||||
|
||||
|
||||
@@ -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 .agents/notes/implemented/feature/2026-07-30-web-result-card-frontend.md
|
||||
2026-07-30-web-result-card-frontend.md: 0f3e46cda1aeeb0f526f839a9071f09058810b86
|
||||
2026-07-30-web-result-card-frontend.zh.md: d9802099f7d2300b4a4c88556103d0c014aaebee
|
||||
2026-07-30-web-result-card-frontend.md: c048c4f93f72e4a1da5c6426497e9274d65ac266
|
||||
2026-07-30-web-result-card-frontend.zh.md: a7090818dc023f857e01e43773adccfba585cc55
|
||||
|
||||
@@ -24,13 +24,13 @@ The card is **resident** under the summary row in the chat rows, the same reside
|
||||
|
||||
`WebBlock` reads only the web view's fields, so it stays a pure function of what the render intent carries — no session lookups, replay-safe like the presenters that produce the view, and unlike the terminal card it needs no cwd resolution because a web view carries no path. A UI without the `web` capability (the TUI) still gets the contract's fallback `content`; nothing about the tools' result shape changed. `MarkdownText` is reused for the answer, so the answer's own untrusted-link handling and GFM rendering come for free.
|
||||
|
||||
A separate later PR unifies the whole-row collapse/expand interaction and will flip every resident card (terminal, diff, web) to expand-gated at once; this card follows the current resident convention rather than pre-empting that change.
|
||||
The whole-row collapse/expand interaction shared by every resident card (terminal, diff, web) is owned by the [unified expand-and-inspect note](2026-07-30-web-tool-row-unified-expand-and-inspect.md); this card follows the resident convention rather than pre-empting that interaction.
|
||||
|
||||
## Alternatives considered
|
||||
|
||||
**Two components, one per kind.** Rejected: the two shapes share their card chrome, their safe-link handling, and their truncation indicator, and the contract already expresses their difference as a `kind` discriminant under one `card` tag; two components would duplicate the shared surface and split the safe-link logic.
|
||||
|
||||
**Reparse the model-facing render text instead of consuming the structured view.** Rejected for the same reason the contract note gives: `web_search`'s render collapses each source's fields into one free-text line labelled by title OR hostname, so reparsing cannot recover `{url, title?, snippet?, publishedAt?}`. The structured `resultView` is the only faithful source, which is why the backend PR added it.
|
||||
**Reparse the model-facing render text instead of consuming the structured view.** Rejected for the same reason the contract note gives: `web_search`'s render collapses each source's fields into one free-text line labelled by title OR hostname, so reparsing cannot recover `{url, title?, snippet?, publishedAt?}`. The structured `resultView` is the only faithful source, which is why the backend contract adds it.
|
||||
|
||||
**Render plain anchors without the protocol allowlist.** Rejected: the URL is model-authored and unverified at this presentation boundary, so an unfiltered href would let a `javascript:` URL execute on click. The allowlist is the http(s) subset of MarkdownText's (which also permits `mailto:`), so untrusted retrieval links behave identically wherever they render.
|
||||
|
||||
@@ -44,7 +44,7 @@ The fixture (`packages/client/connection/src/client/fixture.ts`) adds turns 66 (
|
||||
|
||||
## Related
|
||||
|
||||
- [Web result card](2026-07-30-web-result-card.md) — the backend PR that added the `card: 'web'` result arm and made the two tools emit it; this is its deferred frontend consumer.
|
||||
- [Web result card](2026-07-30-web-result-card.md) — the backend contract that added the `card: 'web'` result arm and made the two tools emit it; this note owns its frontend consumer.
|
||||
- [Web search source card scrolls instead of collapsing](2026-08-03-web-search-source-scroll.md) — replaces this note's source-list head/tail collapse with a fixed-height scroll container and removes `CHAT_WEB_MAX_SOURCES` and the primitive's own source cap; every other decision here still holds.
|
||||
- [Web terminal card](2026-07-28-web-terminal-card.md) — the precedent this mirrors: a `ui-primitives` block, a single card-model derivation, keyed and fallback chat rows, and a details-panel arm, for the `terminal` render intent.
|
||||
- [Tagged render-intent union for tool-call presentation](../architecture/2026-07-02-tool-render-intent-union.md) — the `card`-tagged vocabulary; the Web client is now a full consumer of the `web` arm.
|
||||
|
||||
@@ -24,13 +24,13 @@ Status: implemented
|
||||
|
||||
`WebBlock` 只读 web view 的字段,因此它是渲染意图所携带内容的纯函数 —— 无会话查找,与产出该视图的 presenter 一样回放安全,且不同于终端卡片它不需要 cwd 解析,因为 web view 不携带路径。没有 `web` 能力的 UI（TUI）仍得到约定的回退 `content`;工具的 result 形状没有任何改变。answer 复用 `MarkdownText`,因此 answer 自身的不受信任链接处理与 GFM 渲染免费获得。
|
||||
|
||||
一条独立的后续 PR 会统一整行折叠/展开交互,并把每张常驻卡片（terminal、diff、web）一次性翻成 expand-gated;本卡片遵循当前的常驻约定,而非抢先做那次改动。
|
||||
每张常驻卡片（terminal、diff、web）共用的整行折叠/展开交互归[统一展开与检视 note](2026-07-30-web-tool-row-unified-expand-and-inspect.md)所有;本卡片遵循常驻约定,而非抢先做那套交互。
|
||||
|
||||
## Alternatives considered
|
||||
|
||||
**两个组件,每种 kind 一个。** 拒绝:两种形状共享卡片外框、安全链接处理、截断提示,而约定已经把它们的差异表达为一个 `card` 标签下的 `kind` 判别;两个组件会重复共享表面并拆分安全链接逻辑。
|
||||
|
||||
**重解析模型可见的渲染文本,而非消费结构化视图。** 因约定笔记给出的同一理由拒绝:`web_search` 的渲染把每个 source 的字段压缩成一行自由文本、以标题或主机名为标签,所以重解析无法恢复 `{url, title?, snippet?, publishedAt?}`。结构化的 `resultView` 是唯一忠实来源,这正是后端 PR 添加它的原因。
|
||||
**重解析模型可见的渲染文本,而非消费结构化视图。** 因约定笔记给出的同一理由拒绝:`web_search` 的渲染把每个 source 的字段压缩成一行自由文本、以标题或主机名为标签,所以重解析无法恢复 `{url, title?, snippet?, publishedAt?}`。结构化的 `resultView` 是唯一忠实来源,这正是后端约定添加它的原因。
|
||||
|
||||
**不加协议 allowlist 直接渲染裸锚点。** 拒绝:URL 在此展示边界处是模型创作、未经验证的,所以未过滤的 href 会让 `javascript:` URL 在点击时执行。该 allowlist 是 MarkdownText allowlist（它还允许 `mailto:`）的 http(s) 子集,因此不受信任的检索链接无论在何处渲染都行为相同。
|
||||
|
||||
@@ -44,7 +44,7 @@ fixture（`packages/client/connection/src/client/fixture.ts`）添加 turn 66（
|
||||
|
||||
## Related
|
||||
|
||||
- [Web result card](2026-07-30-web-result-card.md) —— 添加 `card: 'web'` result 支路并让两个工具发出它的后端 PR;本条是它推迟的前端消费者。
|
||||
- [Web result card](2026-07-30-web-result-card.md) —— 添加 `card: 'web'` result 支路并让两个工具发出它的后端契约;其前端消费方归本 note 所有。
|
||||
- [Web search 来源卡片改为滚动而非折叠](2026-08-03-web-search-source-scroll.md) —— 用定高滚动容器替换本笔记的 source 列表头/尾折叠,并移除 `CHAT_WEB_MAX_SOURCES` 与原语自身的 source 上限;本笔记的其余决策依然成立。
|
||||
- [Web terminal card](2026-07-28-web-terminal-card.md) —— 本条所镜像的先例:一个 `ui-primitives` block、一处 card-model 派生、键控与兜底 chat 行、以及一个详情面板支路,用于 `terminal` 渲染意图。
|
||||
- [工具调用呈现的标签化 render-intent union](../architecture/2026-07-02-tool-render-intent-union.md) —— `card` 标签词汇;Web 客户端现在是 `web` 支路的完整消费者。
|
||||
|
||||
@@ -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 .agents/notes/implemented/feature/2026-07-30-web-result-card.md
|
||||
2026-07-30-web-result-card.md: 838b13a7f3240c753e5cd1af6909389055c6352d
|
||||
2026-07-30-web-result-card.zh.md: 36ab372864e5cd848b999ee759e73658271b8f90
|
||||
2026-07-30-web-result-card.md: 591471d219295019d28b9eeaf2e57f6d2115d380
|
||||
2026-07-30-web-result-card.zh.md: b84cdc69c132f7764874f14adac92918ba60f86e
|
||||
|
||||
@@ -22,7 +22,7 @@ Neither result view carries a `content` copy. A UI that does not render the stru
|
||||
|
||||
## Consequences
|
||||
|
||||
The frontend consumer was a separate later PR: this producer change adds the contract arm and makes the two tools emit it, with no client-side rendering. Its one observable change is that the `web_search`/`web_fetch` `tool/result` events persist a `data.meta` payload (the `web-fetch` keyless snapshot was refreshed accordingly); model-facing render text and generic fallback content stay unchanged. The assembled-application transcript snapshot that exercises a `web` card belongs to the consumer change that renders it. Any `ToolResultView` consumer that switches exhaustively must add a `web` arm; a non-exhaustive consumer may use the raw-result fallback. `apiproxy`'s session schema already accepts any `card` string (`packages/host/apiproxy/src/api/sessions.schema.ts`), so the new view crosses the wire without a schema change.
|
||||
The frontend consumer is owned by the [web result card frontend note](2026-07-30-web-result-card-frontend.md): this producer change adds the contract arm and makes the two tools emit it, with no client-side rendering. Its one observable change is that the `web_search`/`web_fetch` `tool/result` events persist a `data.meta` payload (the `web-fetch` keyless snapshot was refreshed accordingly); model-facing render text and generic fallback content stay unchanged. The assembled-application transcript snapshot that exercises a `web` card belongs to the consumer change that renders it. Any `ToolResultView` consumer that switches exhaustively must add a `web` arm; a non-exhaustive consumer may use the raw-result fallback. `apiproxy`'s session schema already accepts any `card` string (`packages/host/apiproxy/src/api/sessions.schema.ts`), so the new view crosses the wire without a schema change.
|
||||
|
||||
A future web tool that wants this card declares `presentResult` returning a `card: 'web'` view with its own `kind`; adding a third `kind` is a union edit plus the frontend's branch, not a new card tag.
|
||||
|
||||
@@ -41,4 +41,4 @@ A future web tool that wants this card declares `presentResult` returning a `car
|
||||
## Related
|
||||
|
||||
- [Tagged render-intent union for tool-call presentation](../architecture/2026-07-02-tool-render-intent-union.md) — the `card`-tagged vocabulary this extends with the `web` arm.
|
||||
- [Web terminal card](2026-07-28-web-terminal-card.md) — the precedent that carried the bash `terminal` render intent to the browser; the web frontend consumer of this arm is its analogue, deferred to a later PR.
|
||||
- [Web terminal card](2026-07-28-web-terminal-card.md) — the precedent that carried the bash `terminal` render intent to the browser; the [web result card frontend](2026-07-30-web-result-card-frontend.md) is its analogue for this arm.
|
||||
|
||||
@@ -22,7 +22,7 @@ Status: implemented
|
||||
|
||||
## Consequences
|
||||
|
||||
前端消费方由后续独立 PR 交付：本次生产者变更新增约定分支并让两个工具发出它，不含客户端渲染。其唯一可观察的变化是 `web_search`/`web_fetch` 的 `tool/result` 事件持久化一个 `data.meta` 载荷（`web-fetch` keyless 快照当时随之刷新）；面向模型的 render 文本与 generic 回退内容保持不变。渲染 `web` 卡片的组装应用 transcript 快照属于渲染它的消费方变更。任何做穷尽 switch 的 `ToolResultView` 消费方都必须新增一个 `web` 分支；非穷尽消费方可以使用原始结果回退。`apiproxy` 的会话 schema 已接受任意 `card` 字符串（`packages/host/apiproxy/src/api/sessions.schema.ts`），因此新视图无需 schema 变更即可跨 wire。
|
||||
前端消费方归 [Web result card 前端 note](2026-07-30-web-result-card-frontend.md) 所有：本次生产者变更新增约定分支并让两个工具发出它，不含客户端渲染。其唯一可观察的变化是 `web_search`/`web_fetch` 的 `tool/result` 事件持久化一个 `data.meta` 载荷（`web-fetch` keyless 快照当时随之刷新）；面向模型的 render 文本与 generic 回退内容保持不变。渲染 `web` 卡片的组装应用 transcript 快照属于渲染它的消费方变更。任何做穷尽 switch 的 `ToolResultView` 消费方都必须新增一个 `web` 分支；非穷尽消费方可以使用原始结果回退。`apiproxy` 的会话 schema 已接受任意 `card` 字符串（`packages/host/apiproxy/src/api/sessions.schema.ts`），因此新视图无需 schema 变更即可跨 wire。
|
||||
|
||||
未来想用此卡片的 web 工具，声明一个返回带自有 `kind` 的 `card: 'web'` 视图的 `presentResult`；新增第三个 `kind` 是一次联合类型编辑加前端的分岔，而非一个新的 card 标签。
|
||||
|
||||
@@ -41,4 +41,4 @@ Status: implemented
|
||||
## Related
|
||||
|
||||
- [标签化的工具调用渲染意图联合类型](../architecture/2026-07-02-tool-render-intent-union.md) —— 本卡片以 `web` 分支扩展的 `card` 标签词汇表。
|
||||
- [Web terminal card](2026-07-28-web-terminal-card.md) —— 把 bash `terminal` 渲染意图带到浏览器的先例；本分支的 web 前端消费者是它的对应物，推迟到后续 PR。
|
||||
- [Web terminal card](2026-07-28-web-terminal-card.md) —— 把 bash `terminal` 渲染意图带到浏览器的先例；[Web result card 前端](2026-07-30-web-result-card-frontend.md)是它在这一支上的对应物。
|
||||
|
||||
@@ -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 .agents/notes/implemented/feature/2026-07-30-web-search-card.md
|
||||
2026-07-30-web-search-card.md: e0be857df69dfd46b6e936c775c6bae1476c26dc
|
||||
2026-07-30-web-search-card.zh.md: 784afb0dd36f20c3a0e203d5595c46c8040d82ff
|
||||
2026-07-30-web-search-card.md: 23c89585770151551526223454e98d18716d1a44
|
||||
2026-07-30-web-search-card.zh.md: f92bd9f9231d947d4c70e283b462294c030e3f33
|
||||
|
||||
@@ -8,7 +8,7 @@ English | [中文](2026-07-30-web-search-card.zh.md)
|
||||
|
||||
The `grep` and `glob` tools declare a result-time `card: 'search'` render intent ([search render card](2026-07-30-search-render-card.md)): a `SearchMatchesResultView` (`shape: 'matches'`) carrying grep's matches grouped by file, or a `SearchPathsResultView` (`shape: 'paths'`) carrying glob's flat path list, both with a `truncated`/`total` capping signal. That view already reaches the browser — host, connection, and runtime deliver it onto `ConversationSnapshot` as `resultView` — but the Web client ignored it: every non-terminal, non-diff tool result fell through to the generic card, which renders the model-facing text. A web frontend that wants an expandable per-file group of matches, or a scannable path list, had only the pre-formatted text.
|
||||
|
||||
This is the follow-up the search render card note names: that PR was the backend contract and its two producers; this PR is the web consumer.
|
||||
This is the follow-up the search render card note names: that note owns the backend contract and its two producers; this note owns the web consumer.
|
||||
|
||||
## Decision
|
||||
|
||||
@@ -34,7 +34,7 @@ Geometry, radius, and fonts mirror `CodeBlock` and `TerminalBlock`, so a search
|
||||
|
||||
Three sites consume the derivation, mirroring the terminal card's placement exactly:
|
||||
|
||||
- **The keyed `SearchRow`** (`toolviews/search-row.tsx`) registers ONE component under both `grep` and `glob` in the `tool.call.toolview` keyed hole, and renders the card RESIDENT under the summary row, capped at `CHAT_SEARCH_MAX_LINES` (8) — the same posture `BashRow` takes for its terminal card. Both tool names get the same row because the derived `kind` decides the shape, so a second component would duplicate it. A capped result's recovery footer sits below the card. Because the keyed row owns this render slot, a settled call with no search card — an errored search (grep/glob emit no result view on error), a successful nested `run_code` sub-dispatch (the backend computes no `presentationMeta`, so `resultView` is null), or a legacy generic result — would otherwise show only its summary with its content lost; the row surfaces that model-facing text as a fallback body, keyed on `search === null && settled` rather than on the error state alone. (This resident posture matches the current terminal/diff cards; a separate later PR unifies the whole-row collapse/expand interaction and flips all resident cards at once — out of scope here.)
|
||||
- **The keyed `SearchRow`** (`toolviews/search-row.tsx`) registers ONE component under both `grep` and `glob` in the `tool.call.toolview` keyed hole, and renders the card RESIDENT under the summary row, capped at `CHAT_SEARCH_MAX_LINES` (8) — the same posture `BashRow` takes for its terminal card. Both tool names get the same row because the derived `kind` decides the shape, so a second component would duplicate it. A capped result's recovery footer sits below the card. Because the keyed row owns this render slot, a settled call with no search card — an errored search (grep/glob emit no result view on error), a successful nested `run_code` sub-dispatch (the backend computes no `presentationMeta`, so `resultView` is null), or a legacy generic result — would otherwise show only its summary with its content lost; the row surfaces that model-facing text as a fallback body, keyed on `search === null && settled` rather than on the error state alone. (This resident posture matches the terminal/diff cards; the [unified expand-and-inspect note](2026-07-30-web-tool-row-unified-expand-and-inspect.md) owns the whole-row collapse/expand interaction that flipped all resident cards at once.)
|
||||
- **The generic fallback** (`chat/GenericToolCard` → `chat/ToolRow`) threads the derived model as an expand-gated body, the same arm `terminal` uses: a `grep`/`glob` result with no keyed row (none in the shipped app, since both are registered) still renders its card, with the recovery footer, behind the row's expand toggle.
|
||||
- **The details panel** (`skeleton/DetailsPanel`) renders the card at the primitive's own full height in the Output section, with the recovery footer below it, keeping the JSON Input section.
|
||||
|
||||
|
||||
@@ -8,7 +8,7 @@ Status: implemented
|
||||
|
||||
`grep` 与 `glob` 工具声明了一个仅在结果阶段存在的 `card: 'search'` render intent（[search render card](2026-07-30-search-render-card.md)）：`SearchMatchesResultView`（`shape: 'matches'`）携带 grep 按文件分组的匹配，或 `SearchPathsResultView`（`shape: 'paths'`）携带 glob 的扁平路径列表，两者都带 `truncated`/`total` 截断信号。该视图已经到达浏览器 —— host、connection、runtime 把它作为 `resultView` 投递到 `ConversationSnapshot` 上 —— 但 Web 客户端忽略了它：每个非终端、非 diff 的工具结果都落到 generic 卡片，渲染面向模型的文本。想把搜索结果渲染成可展开的按文件匹配分组、或可扫读的路径列表的 web 前端，只有那段预格式化文本。
|
||||
|
||||
这正是 search render card note 指名的后续：那个 PR 是后端约定和它的两个生产者，本 PR 是 web 消费者。
|
||||
这正是 search render card note 指名的后续：后端约定和它的两个生产者归那篇 note 所有，web 消费方归本 note 所有。
|
||||
|
||||
## Decision
|
||||
|
||||
@@ -34,7 +34,7 @@ Status: implemented
|
||||
|
||||
三个渲染点消费该推导，与终端卡片的落位完全一致：
|
||||
|
||||
- **keyed `SearchRow`**（`toolviews/search-row.tsx`）把一个组件同时注册到 `tool.call.toolview` keyed hole 的 `grep` 与 `glob` 键下，并把卡片作为常驻（resident）渲染在摘要行下方，上限为 `CHAT_SEARCH_MAX_LINES`（8）—— 与 `BashRow` 对其终端卡片采取的姿态相同。两个工具名共用同一行，因为推导出的 `kind` 决定形态，第二个组件只会重复它。被截断结果的恢复脚注画在卡片下方。因为 keyed 行占据了这个渲染槽，一个没有搜索卡片的已结算调用 —— 出错的搜索（grep/glob 出错时不产出结果视图）、成功的嵌套 `run_code` 子派发（后端不为其计算 `presentationMeta`，故 `resultView` 为 null）、或旧日志的 generic 结果 —— 否则只会显示摘要而丢失内容；该行把这段面向模型的文本作为 fallback body 暴露出来，判据是 `search === null && 已结算`，而非仅凭错误状态。（该常驻姿态与当前的 terminal/diff 卡片一致；一个单独的后续 PR 会统一整行折叠/展开交互并一次性翻转所有常驻卡片 —— 不在本 PR 范围内。）
|
||||
- **keyed `SearchRow`**（`toolviews/search-row.tsx`）把一个组件同时注册到 `tool.call.toolview` keyed hole 的 `grep` 与 `glob` 键下，并把卡片作为常驻（resident）渲染在摘要行下方，上限为 `CHAT_SEARCH_MAX_LINES`（8）—— 与 `BashRow` 对其终端卡片采取的姿态相同。两个工具名共用同一行，因为推导出的 `kind` 决定形态，第二个组件只会重复它。被截断结果的恢复脚注画在卡片下方。因为 keyed 行占据了这个渲染槽，一个没有搜索卡片的已结算调用 —— 出错的搜索（grep/glob 出错时不产出结果视图）、成功的嵌套 `run_code` 子派发（后端不为其计算 `presentationMeta`，故 `resultView` 为 null）、或旧日志的 generic 结果 —— 否则只会显示摘要而丢失内容；该行把这段面向模型的文本作为 fallback body 暴露出来，判据是 `search === null && 已结算`，而非仅凭错误状态。（该常驻姿态与 terminal/diff 卡片一致；一次性翻转了所有常驻卡片的整行折叠/展开交互归[统一展开与检视 note](2026-07-30-web-tool-row-unified-expand-and-inspect.md)所有。）
|
||||
- **generic fallback**（`chat/GenericToolCard` → `chat/ToolRow`）把推导出的 model 作为展开门控的 body 传入，与 `terminal` 用的是同一分支：没有 keyed 行的 `grep`/`glob` 结果（发布应用里没有，因为两者都注册了）仍在行的展开开关后渲染其卡片，并带恢复脚注。
|
||||
- **details panel**（`skeleton/DetailsPanel`）在 Output 段以 primitive 自身的完整高度渲染卡片，恢复脚注画在其下方，保留 JSON Input 段。
|
||||
|
||||
|
||||
@@ -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 .agents/notes/implemented/feature/2026-07-31-code-mode-language-dispatch.md
|
||||
2026-07-31-code-mode-language-dispatch.md: 3a6e248160f165d6b341a5c8719abffd69a43820
|
||||
2026-07-31-code-mode-language-dispatch.zh.md: 46ef842f4b4209787c831b657159a97604324a66
|
||||
2026-07-31-code-mode-language-dispatch.md: 9e834ff2eb8e5f8326ef6d7f862385cadede6149
|
||||
2026-07-31-code-mode-language-dispatch.zh.md: d7d83146a7a5a9ed7fa4b051822e51b974e43b4e
|
||||
|
||||
@@ -19,7 +19,7 @@ Language selection is a lookup on `ctx.codeRuntime.language`, resolved lazily at
|
||||
|
||||
Both tables are read with `Object.hasOwn` before use so a language named `toString`/`constructor` cannot resolve an inherited `Object.prototype` member as a renderer. The two guards differ in reachability: `SDK_RENDERERS`' in-callback guard is unreachable because `requireCodeRuntime` validated the same `const` table earlier in the same callback (it carries a `/* v8 ignore */`), while `RUN_CODE_FLAVORS`' guard is the primary, publicly reachable rejection — any language absent from the flavor table hits it through `run_code`'s language-aware getters, which the public `schemas()` reaches without passing `requireCodeRuntime` first; the test reads one of those getters off the definition directly, under a language absent from both tables. A language present in `SDK_RENDERERS` but not `RUN_CODE_FLAVORS` is drift the shared `CodeSdkLanguage` `satisfies` pins reject at `typecheck`, so it is not an input either guard can see; what the guards still own is a mounted runtime reporting a language absent from both tables. Schema emission reads the runtime through `peekRuntime()` rather than `requireRuntime()`: `undefined` (no runtime mounted, reached by definition readers and `schemas()`, of which the doc-catalog harvest is the only shipped one and none of which feeds a model because assembly passes `requireCodeRuntime` first) degrades to the TypeScript flavor, whereas a mounted unknown language fails loud — this is NOT the silent fallback rejected below, which concerns emitting a wrong-language SDK for a real runtime. Adding a backend language is three parallel edits — a `CodeSdkLanguage` member and the two table entries — plus its renderer and the prose that names the well-known values instead of deriving them (the seam's `dsh-code-runtime` README pair, its `CodeRuntime.language` JSDoc, and the `docs/subsystems/code-runtime.md` pair; this package's own README pair and its `Config.mode` JSDoc — no gate checks any of it), with no `agent-loop` or registry-structure change.
|
||||
|
||||
`code-mode.ts` depends only on the runtime Service Definition (`@deepseek-ai/dsh-code-runtime`), never on a concrete backend; dispatch is by `runtime.language` at run time. The tool layer therefore lands independently of the protocol and backend PRs — it needs only the service's `language` field, which is already on master.
|
||||
`code-mode.ts` depends only on the runtime Service Definition (`@deepseek-ai/dsh-code-runtime`), never on a concrete backend; dispatch is by `runtime.language` at run time. The tool layer is therefore independent of the Python protocol and backend — it needs only the service's `language` field.
|
||||
|
||||
### The Python SDK renderer
|
||||
|
||||
@@ -37,9 +37,9 @@ The standard that cap serves is grammatical validity, and the boundary is delibe
|
||||
|
||||
## Consequences
|
||||
|
||||
Adding a backend language is three parallel edits — a `CodeSdkLanguage` member, an `SDK_RENDERERS` entry, and a `RUN_CODE_FLAVORS` entry — plus the renderer function the second points at, with no change to `agent-loop` or the registry structure. The two tables (`SDK_RENDERERS`, `RUN_CODE_FLAVORS`) must stay in step, and that invariant is checked statically rather than left to review: both are `satisfies`-checked against that one union, so a language added to one and not the other fails `typecheck`. This is the mechanical form the drift risk deserves — the runtime `Object.hasOwn` guards would catch it too, but only once a backend reporting that language ships: one PR after the drift, at the Consumer's integration point rather than where it was introduced, and on this base never, since no second backend exists. The tables keep their `Record<string, …>` declared type because `CodeRuntime.language` is an unconstrained `string`; the union pins what the harness ships, the guards reject what a runtime reports. What stays outside that check is the prose that names the well-known values instead of deriving them: `dsh-code-runtime`'s README pair, its `CodeRuntime.language` JSDoc, and the `docs/subsystems/code-runtime.md` pair at the seam, plus this package's own README pair and its `Config.mode` JSDoc. Earlier notes name the values as the state at their own PR and are not on that list. Two separate reasons keep it ungated. Prose is not type-checked at all, wherever the union lives. And no type-level pin can stand in for it here: the Service Definition package must not import its Consumer's table, and `CodeRuntime.language` stays an unconstrained `string` by design, so moving the union into the Service Definition would not apply it either. A unit test pinning the two key sets equal was rejected in favor of this: it would buy the same check at the cost of a test-only export of two private tables, and would run later than the compiler does. Which of the two runtime failures surfaces depends on the entry point, for a language absent from both tables: assembly reports the missing renderer, because `wireSchemas` calls `requireCodeRuntime` before projecting, while the public `schemas()` reaches `run_code`'s language-aware getters first and reports the missing flavor. The tool layer stays free of any concrete backend dependency, so it lands and is testable on master ahead of the Python protocol and backend.
|
||||
Adding a backend language is three parallel edits — a `CodeSdkLanguage` member, an `SDK_RENDERERS` entry, and a `RUN_CODE_FLAVORS` entry — plus the renderer function the second points at, with no change to `agent-loop` or the registry structure. The two tables (`SDK_RENDERERS`, `RUN_CODE_FLAVORS`) must stay in step, and that invariant is checked statically rather than left to review: both are `satisfies`-checked against that one union, so a language added to one and not the other fails `typecheck`. This is the mechanical form the drift risk deserves — the runtime `Object.hasOwn` guards would catch it too, but only once a backend reporting that language ships: at the Consumer's integration point rather than where the drift was introduced — and never while no second backend exists. The tables keep their `Record<string, …>` declared type because `CodeRuntime.language` is an unconstrained `string`; the union pins what the harness ships, the guards reject what a runtime reports. What stays outside that check is the prose that names the well-known values instead of deriving them: `dsh-code-runtime`'s README pair, its `CodeRuntime.language` JSDoc, and the `docs/subsystems/code-runtime.md` pair at the seam, plus this package's own README pair and its `Config.mode` JSDoc. Earlier notes name the values as they stood at the time and are not on that list. Two separate reasons keep it ungated. Prose is not type-checked at all, wherever the union lives. And no type-level pin can stand in for it here: the Service Definition package must not import its Consumer's table, and `CodeRuntime.language` stays an unconstrained `string` by design, so moving the union into the Service Definition would not apply it either. A unit test pinning the two key sets equal was rejected in favor of this: it would buy the same check at the cost of a test-only export of two private tables, and would run later than the compiler does. Which of the two runtime failures surfaces depends on the entry point, for a language absent from both tables: assembly reports the missing renderer, because `wireSchemas` calls `requireCodeRuntime` before projecting, while the public `schemas()` reaches `run_code`'s language-aware getters first and reports the missing flavor. The tool layer stays free of any concrete backend dependency, so it ships and is testable ahead of the Python protocol and backend.
|
||||
|
||||
The cost is that the Python branch of both tables is unreachable on this base: `CodeRuntime.language` is set by the loaded backend, the only published backend is `dsh-code-runtime-worker` (`'typescript'`), and the registry reads the loaded runtime rather than a config field, so no assembled application can select `renderToolsSdkPy` or `PYTHON_FLAVOR`. The model-visible surface is therefore unchanged by this note's work until a backend reporting `'python'` is published, and this PR's coverage is unit-level — the renderer output plus the dispatch and rejection paths. The keyless snapshot for the Python model interface belongs to the PR that publishes that backend, because only there does a real `cordis.yml` over published plugins produce a Python assembly; a snapshot example that mounted a fixture runtime here would assert against a test double, which [docs/testing.md](../../../../docs/testing.md) rejects as a substitute for the assembled application transcript.
|
||||
The cost is that the Python branch of both tables is unreachable in the shipped tree: `CodeRuntime.language` is set by the loaded backend, the only published backend is `dsh-code-runtime-worker` (`'typescript'`), and the registry reads the loaded runtime rather than a config field, so no assembled application can select `renderToolsSdkPy` or `PYTHON_FLAVOR`. The model-visible surface is therefore unchanged by this note's work until a backend reporting `'python'` is published, and this change's coverage is unit-level — the renderer output plus the dispatch and rejection paths. The keyless snapshot for the Python model interface belongs to the change that publishes that backend, because only there does a real `cordis.yml` over published plugins produce a Python assembly; a snapshot example that mounted a fixture runtime here would assert against a test double, which [docs/testing.md](../../../../docs/testing.md) rejects as a substitute for the assembled application transcript.
|
||||
|
||||
Two runtime contracts the Python SDK text asserts are owed by that same backend PR. First, the instructions tell the model that exactly `tools` and `ToolCallError` are bound and that the declared `TypedDict` classes are not, so the backend must inject those two names — with `ToolCallError.toolName` populated per the seam's `errorClass` contract — and must NOT bind the declared class names into the program's globals; injecting them "helpfully" would make the SDK text false. Second, the language has to be bound to the request: `requireCodeRuntime` resolves `ctx.codeRuntime` separately at assembly and at `run_code` execution, so a reload that swapped the runtime between those two points would hand a program written against one flavor to the other. The split is finer than those two points — `run_code`'s `description` and `parameters` getters each call `resolveFlavor(peekRuntime())`, and `schemaOf` destructures both, so one projection reads the runtime twice; both reads are for `run_code`'s own schema, since the getters are installed on that one definition and every other definition carries plain data properties. A reload between those two reads yields a single schema whose two halves name different languages. Neither is reachable here — one published backend means both reads return the same flavor and no program ever runs against this renderer's output — and the cross-language rejection is not testable until a second language exists.
|
||||
|
||||
|
||||
@@ -19,7 +19,7 @@ Code Mode 只生成一种 SDK 形态：TypeScript。`ToolRegistry` 为 `tools:sd
|
||||
|
||||
两张表在使用前都以 `Object.hasOwn` 读取，这样名为 `toString`/`constructor` 的语言不会把继承自 `Object.prototype` 的成员解析成渲染器。两个守卫的可达性不同：`SDK_RENDERERS` 的段内守卫不可达，因为 `requireCodeRuntime` 已在同一回调更早处校验过同一张 `const` 表（它带 `/* v8 ignore */`）；而 `RUN_CODE_FLAVORS` 的守卫是主要的、可公开到达的拒绝路径——任何缺席 flavor 表的语言都经 `run_code` 的语言感知 getter 到达它，而公共 `schemas()` 抵达那些 getter 时并未先过 `requireCodeRuntime`；测试直读 definition 上的其中一个 getter，用的是对两张表都缺席的语言。「在 `SDK_RENDERERS` 里却不在 `RUN_CODE_FLAVORS` 里」这种漂移已由共享的 `CodeSdkLanguage` `satisfies` 在 `typecheck` 处拒绝，两个守卫都看不到这种输入；它们如今负责的是所挂载运行时报告了一门两张表都缺席的语言。schema 发射通过 `peekRuntime()` 而非 `requireRuntime()` 读取运行时：`undefined`（无运行时，由直读 definition 的读者与 `schemas()` 到达，其中 doc-catalog 采集是唯一已交付的一个，而它们都不会喂给模型，因为组装路径先过 `requireCodeRuntime`）降级到 TypeScript flavor，而挂载了未知语言则 fail loud——这不是下方被否决的静默回退，那指的是为真实运行时发出错误语言的 SDK。新增一门后端语言是三处并列编辑——一个 `CodeSdkLanguage` 成员加两条表项——再加它的渲染器，以及点名已知值而非从中派生的散文（seam 侧的 `dsh-code-runtime` README 双语对、它的 `CodeRuntime.language` JSDoc 与 `docs/subsystems/code-runtime.md` 双语对；本包自己的 README 双语对与它的 `Config.mode` JSDoc，无任何 gate 检查其中任何一处），不动 `agent-loop`，也不动注册表结构。
|
||||
|
||||
`code-mode.ts` 只依赖运行时 Service Definition（`@deepseek-ai/dsh-code-runtime`），绝不依赖具体后端；分发在运行时按 `runtime.language` 进行。因此工具层独立于协议和后端 PR 落地——它只需要服务的 `language` 字段，而该字段已在 master 上。
|
||||
`code-mode.ts` 只依赖运行时 Service Definition（`@deepseek-ai/dsh-code-runtime`），绝不依赖具体后端；分发在运行时按 `runtime.language` 进行。因此工具层独立于 Python 协议和后端——它只需要服务的 `language` 字段。
|
||||
|
||||
### Python SDK 渲染器
|
||||
|
||||
@@ -32,14 +32,14 @@ Code Mode 只生成一种 SDK 形态：TypeScript。`ToolRegistry` 为 `tools:sd
|
||||
## Alternatives considered
|
||||
|
||||
- **在 `ToolRegistry` 上加一个 `language` 配置字段。** 那样部署方就会有两处命名语言（所加载的运行时与 tools 配置）且可能相互矛盾；所加载的运行时是唯一真相来源，故注册表读取它而不复制它。
|
||||
- **把 Python 后端 import 进 `code-mode.ts` 来检测它。** 那会把工具层耦合到具体后端，并迫使协议/后端 PR 先落地。按 `language` 运行时分发使该层保持后端无关、可独立发布。
|
||||
- **把 Python 后端 import 进 `code-mode.ts` 来检测它。** 那会把工具层耦合到具体后端，并迫使协议/后端 PR（Pull Request）先落地。按 `language` 运行时分发使该层保持后端无关、可独立发布。
|
||||
- **为未知语言提供默认渲染器。** 静默回退会在比如 Ruby 运行时上发出 TypeScript SDK——模型会看到错误语言的指令。在装配处 fail loud 是本仓库对错误配置的立场。
|
||||
|
||||
## Consequences
|
||||
|
||||
新增一门后端语言是三处并列编辑——一个 `CodeSdkLanguage` 成员、一个 `SDK_RENDERERS` 表项、一个 `RUN_CODE_FLAVORS` 表项——再加第二处所指向的渲染器函数，不动 `agent-loop`，也不动注册表结构。两张表（`SDK_RENDERERS`、`RUN_CODE_FLAVORS`）必须同步，且这条不变式由静态检查把关，而非交给 review：两张表都以 `satisfies` 对上述同一个 union 校验，因此只加其一而漏掉另一会在 `typecheck` 处失败。这正是该漂移风险应有的机械形式——运行期的 `Object.hasOwn` 守卫同样能捕获，但要等到有后端报告该语言之后：晚于漂移引入一个 PR，且触发点在 Consumer 的集成处而非漂移引入处；在当前 base 上则永远不会触发，因为不存在第二个后端。两张表的声明类型仍是 `Record<string, …>`，因为 `CodeRuntime.language` 是不受约束的 `string`：union 钉住本仓库交付了什么，守卫拒绝运行时报告了什么。落在这条检查之外的是点名已知值而非从中派生的散文：seam 侧的 `dsh-code-runtime` README 双语对、它的 `CodeRuntime.language` JSDoc 与 `docs/subsystems/code-runtime.md` 双语对，再加本包自己的 README 双语对与它的 `Config.mode` JSDoc。更早的 note 点名这些值时记的是其自身 PR 当时的状态，不在此列。让它无 gate 的是两条独立理由。其一，散文根本不受类型检查，union 放在哪里都一样。其二，类型级替代在这里也不可用：Service Definition 包不得 import 其 Consumer 的表，而 `CodeRuntime.language` 按设计保持不受约束的 `string`，即便把 union 迁进 Service Definition 也不会作用到它。用一个断言两张表键集相等的 unit test 的方案被否决：它买到的是同一条检查，代价却是把两张私有表做测试专用导出，且运行时机晚于编译器。对两张表都缺席的语言，两种运行期失败中报出哪一条随入口而异：组装路径报缺渲染器，因为 `wireSchemas` 在投影前先调 `requireCodeRuntime`；而公共 `schemas()` 先经过 `run_code` 的语言感知 getter，报的是缺 flavor 表项。工具层不依赖任何具体后端，因此它能先于 Python 协议和后端在 master 上落地并可测。
|
||||
新增一门后端语言是三处并列编辑——一个 `CodeSdkLanguage` 成员、一个 `SDK_RENDERERS` 表项、一个 `RUN_CODE_FLAVORS` 表项——再加第二处所指向的渲染器函数，不动 `agent-loop`，也不动注册表结构。两张表（`SDK_RENDERERS`、`RUN_CODE_FLAVORS`）必须同步，且这条不变式由静态检查把关，而非交给 review：两张表都以 `satisfies` 对上述同一个 union 校验，因此只加其一而漏掉另一会在 `typecheck` 处失败。这正是该漂移风险应有的机械形式——运行期的 `Object.hasOwn` 守卫同样能捕获，但要等到有后端报告该语言之后：触发点在 Consumer 的集成处而非漂移引入处——而只要不存在第二个后端，就永远不会触发。两张表的声明类型仍是 `Record<string, …>`，因为 `CodeRuntime.language` 是不受约束的 `string`：union 钉住本仓库交付了什么，守卫拒绝运行时报告了什么。落在这条检查之外的是点名已知值而非从中派生的散文：seam 侧的 `dsh-code-runtime` README 双语对、它的 `CodeRuntime.language` JSDoc 与 `docs/subsystems/code-runtime.md` 双语对，再加本包自己的 README 双语对与它的 `Config.mode` JSDoc。更早的 note 点名这些值时记的是当时的状态，不在此列。让它无 gate 的是两条独立理由。其一，散文根本不受类型检查，union 放在哪里都一样。其二，类型级替代在这里也不可用：Service Definition 包不得 import 其 Consumer 的表，而 `CodeRuntime.language` 按设计保持不受约束的 `string`，即便把 union 迁进 Service Definition 也不会作用到它。用一个断言两张表键集相等的 unit test 的方案被否决：它买到的是同一条检查，代价却是把两张私有表做测试专用导出，且运行时机晚于编译器。对两张表都缺席的语言，两种运行期失败中报出哪一条随入口而异：组装路径报缺渲染器，因为 `wireSchemas` 在投影前先调 `requireCodeRuntime`；而公共 `schemas()` 先经过 `run_code` 的语言感知 getter，报的是缺 flavor 表项。工具层不依赖任何具体后端，因此它能先于 Python 协议和后端交付并可测。
|
||||
|
||||
代价是两张表的 Python 分支在当前 base 上不可达：`CodeRuntime.language` 由所加载的后端设定，已发布的后端只有 `dsh-code-runtime-worker`（`'typescript'`），而注册表读取的是所加载的运行时而非某个配置字段，因此没有任何一份组装好的应用能选中 `renderToolsSdkPy` 或 `PYTHON_FLAVOR`。也就是说，在报告 `'python'` 的后端发布之前，本 note 的工作不改变模型可见表面，本 PR 的覆盖因此是 unit 级——渲染器输出加分发与拒绝路径。Python 模型界面的 keyless snapshot 归属于发布该后端的那个 PR，因为只有在那里，一份基于已发布插件的真实 `cordis.yml` 才会产出 Python 组装；在此处挂载 fixture 运行时的快照示例断言的是测试替身，而 [docs/testing.md](../../../../docs/testing.md) 明确拒绝以此替代组装好的应用 transcript。
|
||||
代价是两张表的 Python 分支在已交付的代码树中不可达：`CodeRuntime.language` 由所加载的后端设定，已发布的后端只有 `dsh-code-runtime-worker`（`'typescript'`），而注册表读取的是所加载的运行时而非某个配置字段，因此没有任何一份组装好的应用能选中 `renderToolsSdkPy` 或 `PYTHON_FLAVOR`。也就是说，在报告 `'python'` 的后端发布之前，本 note 的工作不改变模型可见表面，本变更的覆盖因此是 unit 级——渲染器输出加分发与拒绝路径。Python 模型界面的 keyless snapshot 归属于发布该后端的那个变更，因为只有在那里，一份基于已发布插件的真实 `cordis.yml` 才会产出 Python 组装；在此处挂载 fixture 运行时的快照示例断言的是测试替身，而 [docs/testing.md](../../../../docs/testing.md) 明确拒绝以此替代组装好的应用 transcript。
|
||||
|
||||
Python SDK 文本断言的两条运行时约定同样归属那个 backend PR。其一，说明文字告诉模型运行时恰好绑定 `tools` 与 `ToolCallError` 两个名字、所声明的 `TypedDict` 类不绑定，因此后端必须注入这两个名字（并按 seam 的 `errorClass` 约定填充 `ToolCallError.toolName`），且**不得**把所声明的类名绑进程序全局——「好心」注入会使这段 SDK 文本变成假话。其二，语言必须绑定到请求上：`requireCodeRuntime` 在组装时与 `run_code` 执行时分别解析 `ctx.codeRuntime`，若在这两点之间发生重载并换掉运行时，就会把针对一种形态写成的程序交给另一种形态执行。分裂比这两点更细——`run_code` 的 `description` 与 `parameters` 两个 getter 各自调用 `resolveFlavor(peekRuntime())`，而 `schemaOf` 会解构这两个字段，因此一次投影读两次运行时；两次都属于 `run_code` 自己的 schema，因为这两个 getter 只装在那一个 definition 上，其余 definition 携带的都是普通数据属性。在这两次读取之间重载会产出单个 schema 的两半分属不同语言。两者在此处都不可达——只有一个已发布后端意味着两次读取返回同一形态，且没有任何程序会针对本渲染器的输出运行——而跨语言拒绝在第二门语言存在之前也无法测试。
|
||||
|
||||
|
||||
@@ -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 .agents/notes/implemented/feature/2026-07-31-telemetry-anonymous-user-id.md
|
||||
2026-07-31-telemetry-anonymous-user-id.md: 3c8e3324cb418eac48cb5ae780c55bbcbaf3caa1
|
||||
2026-07-31-telemetry-anonymous-user-id.zh.md: 6ba1b7abe0f253fc91e7f8856d9dc9d1d961550b
|
||||
2026-07-31-telemetry-anonymous-user-id.md: f53fc9ce7eb3a5aefcb0be0a20c7403b5601e369
|
||||
2026-07-31-telemetry-anonymous-user-id.zh.md: 99b2dd88df94810ccfc85d099e74a6f0852153a7
|
||||
|
||||
Some files were not shown because too many files have changed in this diff Show More
Reference in New Issue
Block a user