Merge branch 'codex/disable-telemetry-default' into master

Resolved conflicts:
- packages/client/ui-settings-general/README.md, README.zh.md: kept PR
  opt-in telemetry description (DSH_TELEMETRY_MODE)
- scripts/snapshots/translation-prompt-v4: kept master's newer README
  structure snapshot
- i18n.yaml pairing records: resolved per file state
- pnpm-lock.yaml: regenerated
- Modify/delete conflicts (scaffold/telemetry, sdk-follow-up-capabilities):
  kept master deletions
This commit is contained in:
Chinesezjc
2026-08-12 17:27:37 +08:00
2021 changed files with 43956 additions and 23769 deletions
@@ -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/architecture/2026-06-20-generic-long-running-tool-runtime.md
2026-06-20-generic-long-running-tool-runtime.md: 457eaac7de92ea37287803349672271148d59185
2026-06-20-generic-long-running-tool-runtime.zh.md: 9a86c4cf2b49973212adfd4b9acdb54150af01d1
2026-06-20-generic-long-running-tool-runtime.md: 1edc3422c253e06178a5c8ebf68dfd4ef1289e31
2026-06-20-generic-long-running-tool-runtime.zh.md: 8cfc2b2ec7ecce1a358b0be63ca52e9319bf362a
@@ -25,6 +25,8 @@ Long-running tools are producers. `dsh-tool-bash` adapts a `BashProcess` into in
The literal types live on the [tasks subsystem page](../../../../docs/subsystems/tasks.md). A producer calls `ctx.tasks.start()` with a kind, label, optional owning `Agent`, optional positive `outputLimitBytes`, and a `run()` function. The runtime completes all failable preflight work before calling `run()` and invokes it once. After `run()` returns hooks, registration commits without another failable step; a producer cannot start work that lacks a collectable task id.
The process-local provider also owns bounded admission, whose rationale is recorded in the [bounded background task admission decision](../bug-fix/2026-08-11-bounded-background-task-admission.md). Its positive-safe-integer `maxConcurrentTasksPerOwner` config defaults to `10`; `start()` derives each exact `Agent` object's active count from `running` and `stopping` records, while every unowned task shares one service bucket. Capacity rejection occurs before `run()` and id allocation, and producer `done` settlement is the only event that releases a stopping task's place. The provider does not queue, preempt, or retain a second mutable count.
`outputLimitBytes` is producer-owned presentation policy, not a registry buffer. The registry validates and projects it unchanged into `TaskSnapshot`; generic control APIs apply the cap to complete model-facing output after adding their own status or notice metadata. Omitting it preserves the existing controller behavior, so the runtime does not impose a hidden default on unrelated producer families.
A model-facing producer exposes that committed id in its canonical success value, normally `{ kind: 'background', taskId }`; Native rendering may keep human-readable prose. A pre-aborted background call fails rather than returning a no-op because no task exists to satisfy the promised handle. Once registration publishes the id, cancellation belongs to the task's own controller and the task runtime: later cancellation of the producing tool call must not kill the published task. `task_kill`, owner disposal, and service teardown request cancellation; foreground execution remains coupled to the call's `exec.signal`.
@@ -55,7 +57,7 @@ For contract-compliant producers, `AgentHandle.dispose()` resolves only after ow
`TaskService` provides:
- `start(spec)` for preflighted, atomic registration.
- `start(spec)` for preflighted, provider-admitted, atomic registration.
- `get(id, caller?)` and `list(caller?)` for non-consuming snapshots.
- `read(id, caller?)` for a consuming stream delta or an idempotent final result.
- `kill(id, caller?, reason?)` for cancellation.
@@ -77,7 +79,7 @@ A producer loaded without any controller would let callers start work they canno
Stream reads share one task-scoped consuming cursor because the owning model is the intended reader. A UI or multiple independent readers need a separate non-consuming observation API; sharing this cursor would let readers consume one another's output.
The system prompt tells the model to retain task ids, continue independent work instead of busy-polling or duplicating a running task, collect relevant tasks before its final answer, and kill work that no longer matters. Completion injects a logged `context/message` into the exact owner's session; it becomes durable context for the next request but does not wake an idle agent.
The system prompt tells the model to retain task ids, continue independent work instead of busy-polling or duplicating a running task, collect relevant tasks before its final answer, and kill work that no longer matters. Completion delivers a logged message to the exact owner's session. A busy owner is injected; an idle owner is woken, under the bounded policy the [idle-owner wake decision](../feature/2026-08-11-background-task-completion-wakes-an-idle-owner.md) owns.
The runtime marks a terminal task `reported` when a read or wait delivers it, when a live waiter has claimed delivery at settlement, or when the model explicitly kills it. Reported tasks do not inject redundant completion notices. Listener failures are logged independently, do not stop later listeners, and are not awaited by waiters or teardown. When a snapshot carries `outputLimitBytes`, `dsh-tool-tasks` preserves UTF-8 boundaries and reuses an existing producer truncation marker rather than duplicating it. Reads reserve status suffixes and retain the output tail; completion notices reserve the stable `background task <id>` prefix and `task_output` instruction before truncating variable kind, label, status, detail, or the truncation marker itself, so the minimum PTY cap still identifies the task to collect. The task controller resolves the caller-visible producer cap in a prepended pre-execute listener before policy can deny or short-circuit dispatch, then applies it through the task definitions' last-mile `finalizeContent` callback so normalized tool errors, outer pipeline failures, and single-text policy results cannot escape the bound; deliberately structured multi-block policy results retain policy ownership of their shape and size.
@@ -125,10 +127,12 @@ Authorization, not unguessability, is the access boundary, and ids do not derive
## Testing
Unit coverage pins preflight atomicity, per-kind ids, output-limit validation and projection, complete UTF-8 result bounds, stream and final reads, wait timeout and abort races, cancellation, first-wins settlement, listener containment, notice suppression, owner isolation, stale owner instances, owner cleanup, service teardown, and the no-controller fence. Producer tests cover bash process mapping, subagent startup cancellation, terminal mapping, and disposal. Snapshot coverage pins the control-tool schemas and prompt guidance.
Unit coverage pins preflight atomicity, per-kind ids, per-exact-owner and unowned-bucket admission, `stopping` occupancy, terminal release, output-limit validation and projection, complete UTF-8 result bounds, stream and final reads, wait timeout and abort races, cancellation, first-wins settlement, listener containment, notice suppression, owner isolation, stale owner instances, owner cleanup, service teardown, and the no-controller fence. Producer tests cover bash process mapping, subagent startup cancellation, terminal mapping, and disposal. Snapshot coverage pins the control-tool schemas, prompt guidance, and an assembled ACP path where the configured limit rejects a second real background Bash task with a `task_kill` recovery action.
## Consequences
Bash commands and subagents share one id vocabulary, listing, notice format, prompt habit, and set of control tools. New long-running producers implement execution hooks instead of another registry and tool family. The [tool cookbook](../../../../docs/cookbook/adding-a-tool.md) points producers to this contract.
Owned background bash now stops with its agent instead of surviving it. Background processes have no executor timeout; callers must kill irrelevant work or rely on owner/service disposal. Stream reads support one consuming reader, completion notices do not wake idle agents, and a producer that returns from `cancel` without settling `done` can still stall teardown. Durable jobs, independent observation cursors, and foreground promotion remain separate designs.
One exact owner cannot grow process-local Task-backed work without bound, and another owner does not consume its allowance. A cancellation request keeps capacity occupied until the producer actually releases its resource, so replacing slow-stopping work cannot exceed the configured live-resource budget.
Owned background bash now stops with its agent instead of surviving it. Background processes have no executor timeout; callers must kill irrelevant work or rely on owner/service disposal. Stream reads support one consuming reader, and a producer that returns from `cancel` without settling `done` can still stall teardown. Durable jobs, independent observation cursors, and foreground promotion remain separate designs.
@@ -25,6 +25,8 @@ Status: implemented
字面类型见[任务子系统页面](../../../../docs/subsystems/tasks.md)。生产方调用 `ctx.tasks.start()`,传入 kind、label、可选的所属 `Agent`、可选的正数 `outputLimitBytes` 与一个 `run()` 函数。运行时会在调用 `run()` 前完成所有可能失败的预检工作,并且只调用一次。`run()` 返回钩子后,注册过程不会再执行可能失败的步骤而直接提交;生产方无法启动没有可收集 task id 的工作。
进程内 Service provider 还拥有有界准入,其理由记录在[有界后台任务准入决策](../bug-fix/2026-08-11-bounded-background-task-admission.md)中。它的 `maxConcurrentTasksPerOwner` 配置必须是正的安全整数,默认值为 `10``start()``running``stopping` 记录派生每个确切 `Agent` 对象的活动数量,而全部无 owner 任务共享一个服务级桶。容量拒绝发生在 `run()` 与 id 分配之前,处于 stopping 的任务只有在生产方 `done` 结算时才释放名额。Service provider 不排队或抢占任务,也不保留第二份可变计数。
`outputLimitBytes` 是生产方拥有的呈现策略,而非注册表缓冲区。注册表校验该值,并将其原样投影到 `TaskSnapshot`;通用任务控制器添加自身的状态或通知元数据后,再将该上限应用于完整的面向模型输出。省略该值时保持现有控制器行为,因此运行时不会向无关的生产方类别施加隐式默认值。
面向模型的生产方会在规范成功值中暴露已提交的 id,通常为 `{ kind: 'background', taskId }`;Native 渲染仍可保留便于人类阅读的行文。预先被中止的后台调用会失败,而不是返回空操作,因为不存在可履行所承诺句柄的任务。一旦注册过程发布 id,取消就归任务自身的控制器与任务运行时所有:随后取消生产工具调用不得终止已发布的任务。`task_kill`、所有者资源释放和服务拆除会请求取消;前台执行仍与调用的 `exec.signal` 耦合。
@@ -55,7 +57,7 @@ task id 在运行时全局可见且可预测,因此注册表会授权每次访
`TaskService` 提供:
- `start(spec)`:经过预检的原子注册。
- `start(spec)`:经过预检与 Service provider 准入的原子注册。
- `get(id, caller?)``list(caller?)`:非消费式快照。
- `read(id, caller?)`:消费式流增量或幂等的最终结果。
- `kill(id, caller?, reason?)`:取消。
@@ -77,7 +79,7 @@ task id 在运行时全局可见且可预测,因此注册表会授权每次访
流式读取共享一个任务作用域内的消费游标,因为所属模型是预期读取方。UI 或多个独立读取方需要单独的非消费式观察 API;共享该游标会让读取方彼此消费对方的输出。
系统提示词要求模型保留 task id、在后台工作运行时继续处理独立工作而非忙轮询或重复启动同一任务、在给出最终答案前收集相关任务,并终止不再重要的工作。完成时,系统会向确切所有者的会话注入一条已记录的 `context/message`;它会成为下一个请求的持久上下文,但不会唤醒空闲的 agent
系统提示词要求模型保留 task id、在后台工作运行时继续处理独立工作而非忙轮询或重复启动同一任务、在给出最终答案前收集相关任务,并终止不再重要的工作。完成时,系统会向确切所有者的会话交付一条已记录的消息:繁忙的所有者走注入,空闲的所有者会被唤醒,其有界策略由[空闲所有者唤醒决策](../feature/2026-08-11-background-task-completion-wakes-an-idle-owner.md)负责
当读取或等待交付终止任务、实时等待方在结算时认领了投递,或模型显式终止任务时,运行时将终止任务标为 `reported`。已报告的任务不会注入冗余的完成通知。监听器失败会独立记录,不会阻止后续监听器,也不会被等待方或资源销毁过程等待。当快照携带 `outputLimitBytes` 时,`dsh-tool-tasks` 会保持 UTF-8 边界,并复用生产方已有的截断标记,而不会重复添加。读取会为状态后缀预留空间并保留输出尾部;完成通知会先为稳定的 `background task <id>` 前缀与 `task_output` 指令预留空间,再截断可变的 kind、label、status、detail,乃至截断标记本身,因此 PTY 的最小上限仍能标识需要收集的任务。任务控制器在策略有机会拒绝或短路分发之前,于最先执行的 pre-execute 监听器中解析调用方可见的生产方上限;随后通过任务定义最后一道的 `finalizeContent` 回调应用该上限,使规范化的工具错误、外层流水线失败与单文本策略结果都无法绕过该边界;经特意结构化的多块策略结果仍由策略拥有其形状与大小。
@@ -125,10 +127,12 @@ bash seam 暴露 `resolve`、`run` 和 `start`。`start(spec)` 返回一个 `Bas
## 测试
单元覆盖固定预检原子性、按 kind 分配的 id、输出上限的校验与投影、完整结果的 UTF-8 字节上限、流式与最终读取、等待超时与中止竞态、取消、首次结果优先的结算、监听器隔离、通知压制、所有者隔离、陈旧的所有者实例、所有者清理、服务资源销毁和无控制器防线。生产方测试覆盖 bash 进程映射、subagent 启动取消、终止映射与释放。快照覆盖固定控制工具 schema提示词指导。
单元覆盖固定预检原子性、按 kind 分配的 id、按确切 owner 与无 owner 桶执行的准入、`stopping` 占位、终态释放、输出上限的校验与投影、完整结果的 UTF-8 字节上限、流式与最终读取、等待超时与中止竞态、取消、首次结果优先的结算、监听器隔离、通知压制、所有者隔离、陈旧的所有者实例、所有者清理、服务资源销毁和无控制器防线。生产方测试覆盖 bash 进程映射、subagent 启动取消、终止映射与释放。快照覆盖固定控制工具 schema提示词指导,以及一条组合完整的 ACP 路径:配置上限会拒绝第二个真实后台 Bash 任务,并给出 `task_kill` 恢复动作
## 后果
bash 命令与 subagent 共享一套 id 词汇、列表、通知格式、提示词习惯和控制工具。新的长时间运行生产方只需实现执行钩子,而不必再实现一套注册表与工具族。[工具实操手册](../../../../docs/cookbook/adding-a-tool.md)将生产方指向本约定。
有所属后台 bash 会随其 agent 一起停止,不再比 agent 存活更久。后台进程没有执行器超时;调用方必须终止无关工作,或依赖所有者/服务释放。流式读取只支持一个消费方,完成通知不会唤醒空闲 agent;生产方的 `cancel` 返回后如果未使 `done` 完成,仍可能阻塞资源销毁。持久任务、独立观察游标和前台提升仍属于单独设计
单个确切 owner 无法再无限增加进程内由 Task 承载的工作,另一个 owner 也不会消耗它的额度。取消请求会继续占用容量,直到生产方真正释放资源,因此用新工作替换缓慢停止的任务不会突破已配置的实时资源预算
有所属后台 bash 会随其 agent 一起停止,不再比 agent 存活更久。后台进程没有执行器超时;调用方必须终止无关工作,或依赖所有者/服务释放。流式读取只支持一个消费方;生产方的 `cancel` 返回后如果未使 `done` 完成,仍可能阻塞资源销毁。持久任务、独立观察游标和前台提升仍属于单独设计。
@@ -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/architecture/2026-06-21-mandatory-app-attribution-headers.md
2026-06-21-mandatory-app-attribution-headers.md: 39050a53ec76e8c5a6cac4d8e31fa15b992c406e
2026-06-21-mandatory-app-attribution-headers.zh.md: bfd6aa2540022f68cf9f69ccc2c12b3bc0978960
2026-06-21-mandatory-app-attribution-headers.md: c90b136a556da81e1c15828926f18b865cea4ece
2026-06-21-mandatory-app-attribution-headers.zh.md: f68cad7e9f642319dc508de9261e33180bfe5748
@@ -24,7 +24,7 @@ The immediate prompt came from OpenRouter's [App Attribution](https://openrouter
## Decision
Provider request attribution is mandatory at the LLM adapter boundary, using the standard `User-Agent` header only. The rule: every product LLM adapter sends a static, non-secret application identity on every provider HTTP request, and every adapter has tests proving that `User-Agent` reaches the wire (a mock server asserting received headers; for a library-backed adapter, the library's header hook feeding the same mock-server assertion).
Provider-neutral app attribution is mandatory at the LLM adapter boundary, using the standard `User-Agent` header only. The rule: every product LLM adapter sends a static, non-secret application identity on every provider HTTP request, and every adapter has tests proving that `User-Agent` reaches the wire (a mock server asserting received headers; for a library-backed adapter, the library's header hook feeding the same mock-server assertion). This rule governs app attribution, not provider-specific request identity: [the DeepSeek request-identity decision](../feature/2026-08-11-deepseek-request-user-id-header.md) separately owns its user and session headers.
OpenRouter app attribution is deliberately not implemented. `HTTP-Referer`, `X-OpenRouter-Title`, `X-Title`, and `X-OpenRouter-Categories` are OpenRouter-specific product-surface headers, not provider-neutral model-request attribution. They can be proposed later by an OpenRouter adapter or explicit OpenRouter mode, with its own privacy/product decision, tests, and docs. Until then, even requests pointed at OpenRouter send only the shared `User-Agent` attribution from this decision.
@@ -41,7 +41,7 @@ Wire mapping (`attributionHeaders`; header names lowercase in code - HTTP field
| Target | Mapping |
|---|---|
| All HTTP-based adapters | `User-Agent: {product}/{version} (+{url})` - the parenthesized `+url` comment stays within RFC 9110's conservative product/comment syntax. |
| Direct DeepSeek endpoint | `User-Agent`; do not send OpenRouter-only headers unless DeepSeek documents an equivalent contract. |
| Direct DeepSeek endpoint | `User-Agent` for app attribution; `x-deepseek-harness-user-id` and conditional `x-deepseek-harness-session-id` are separate request identity under the DeepSeek-specific decision. Do not send OpenRouter-only headers unless DeepSeek documents an equivalent contract. |
| OpenRouter endpoints | `User-Agent` only for now. Do not send `HTTP-Referer`, `X-OpenRouter-Title`, `X-Title`, or `X-OpenRouter-Categories` under this decision. |
| Future providers | `User-Agent` only unless a later provider-specific Agent Note accepts additional headers. Do not reuse `HTTP-Referer` by analogy. |
@@ -24,7 +24,7 @@ LLM(大语言模型)提供方请求应当标识发出请求的产品。这
## 决策
在 LLM 适配器边界,提供方请求归属是强制的,且仅使用标准 `User-Agent` 头部。规则:每个产品级 LLM 适配器在每个提供方 HTTP 请求上发送一个静态、非机密的应用身份,且每个适配器都有测试证明 `User-Agent` 到达了线路(mock 服务器断言收到的头部;对于基于库的适配器,通过库的头部钩子馈入同一个 mock 服务器断言)。
在 LLM 适配器边界,提供方无关的应用归属是强制的,且仅使用标准 `User-Agent` 头部。规则:每个产品级 LLM 适配器在每个提供方 HTTP 请求上发送一个静态、非机密的应用身份,且每个适配器都有测试证明 `User-Agent` 到达了线路(mock 服务器断言收到的头部;对于基于库的适配器,通过库的头部钩子馈入同一个 mock 服务器断言)。这条规则约束应用归属,不约束提供方特有的请求身份;[DeepSeek 请求身份决策](../feature/2026-08-11-deepseek-request-user-id-header.md)另行负责其用户与会话头部。
OpenRouter 应用归属刻意未实现。`HTTP-Referer``X-OpenRouter-Title``X-Title``X-OpenRouter-Categories` 是 OpenRouter 特有的产品展示头部,不是提供方无关的模型请求归属。它们可以后续由 OpenRouter 适配器或显式 OpenRouter 模式提出,附带自己的隐私/产品决策、测试和文档。在此之前,即使请求指向 OpenRouter,也只发送本决策定义的共享 `User-Agent` 归属。
@@ -41,7 +41,7 @@ OpenRouter 应用归属刻意未实现。`HTTP-Referer`、`X-OpenRouter-Title`
| 目标 | 映射 |
|---|---|
| 所有基于 HTTP 的适配器 | `User-Agent: {product}/{version} (+{url})`——括号中的 `+url` 注释符合 RFC 9110 保守的 product/comment 语法。 |
| 直连 DeepSeek 端点 | `User-Agent`除非 DeepSeek 文档化了等效约定,否则不发送 OpenRouter 特有头部。 |
| 直连 DeepSeek 端点 | `User-Agent` 用于应用归属;`x-deepseek-harness-user-id` 与条件性的 `x-deepseek-harness-session-id` 由 DeepSeek 特有决策作为独立请求身份管理。除非 DeepSeek 文档化了等效约定,否则不发送 OpenRouter 特有头部。 |
| OpenRouter 端点 | 目前仅 `User-Agent`。本决策下不发送 `HTTP-Referer``X-OpenRouter-Title``X-Title``X-OpenRouter-Categories`。 |
| 未来提供方 | 仅 `User-Agent`,除非后续提供方特有的 Agent Note 接受额外头部。不要类比复用 `HTTP-Referer`。 |
@@ -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/architecture/2026-07-10-single-file-executable-sdk-runtime-distribution.md
2026-07-10-single-file-executable-sdk-runtime-distribution.md: fd39d8c10d7f76003c93b6fa45a3b0211cead23e
2026-07-10-single-file-executable-sdk-runtime-distribution.zh.md: d7758a77083e07b1d2cac99ae2be3f15e6edd2dc
2026-07-10-single-file-executable-sdk-runtime-distribution.md: 4fe9ea3c4073e249a8c961634be9d329b35a3f4e
2026-07-10-single-file-executable-sdk-runtime-distribution.zh.md: d7a4b91a48175edcc624e6af44efa3e4c7676554
@@ -23,11 +23,11 @@ The exe is packaged with the **`--sea` (enhanced SEA) mode** of [@yao-pkg/pkg](h
Terminology reminder: pkg's `/snapshot` VFS has nothing to do with this repo's testing-system "snapshot" (ACP replay expected outputs, `$DSH_SNAPSHOT`); this document says "VFS" for the former.
### The serving interface is a plugin: the two packages ui/jsonrpc + examples/jsonrpc-demo
### The serving interface is a plugin: the two packages sdk/server + examples/jsonrpc-demo
The deterministic protocol implementation (`server.ts` / `transport.ts`) lands as two packages on the existing `acp/acp` + `examples/acp-demo` pattern — the serving surface is itself a plugin:
- [`packages/scaffold/server`](../../../../packages/scaffold/server/README.md) (`@deepseek-ai/dsh-jsonrpc`): the pure protocol plugin; on apply it mounts `HarnessSdkServer` plus a line-delimited JSON-RPC transport on the process stdio, with disposal through `ctx.effect()`. Whether to serve is decided by `cordis.yml`; a yml that does not mount it is a legitimate process that does not serve. Protocol-level exit belongs to the plugin (after answering and flushing the `shutdown` response it disposes the root runtime so persistence drains, then `exit(0)`; an HMR-style unload only stops the service without exiting the process).
- [`packages/sdk/server`](../../../../packages/sdk/server/README.md) (`@deepseek-ai/dsh-jsonrpc`): the pure protocol plugin; on apply it mounts `HarnessSdkServer` plus a line-delimited JSON-RPC transport on the process stdio, with disposal through `ctx.effect()`. Whether to serve is decided by `cordis.yml`; a yml that does not mount it is a legitimate process that does not serve. Protocol-level exit belongs to the plugin (after answering and flushing the `shutdown` response it disposes the root runtime so persistence drains, then `exit(0)`; an HMR-style unload only stops the service without exiting the process).
- [`packages/examples/jsonrpc-demo`](../../../../packages/examples/jsonrpc-demo/README.md) (`@deepseek-ai/dsh-jsonrpc-demo`): a thin app bin — `installFailLoud` + `loadEnv` + config discovery + `boot()` from [`dsh-app-boot`](../../../../packages/boot/app-boot/src/index.ts), done once boot completes; the server is brought up by the `dsh-jsonrpc` entry in the yml. Its only dependency is app-boot. Process-level exit belongs to the bin (stdin EOF/SIGTERM → dispose then 0, SIGINT → 130).
Config discovery has two channels and fails loudly when both are missing: the `DSH_CORDIS_CONFIG` environment variable first (the SDK client convention), then an argv positional argument; no default path and no built-in fallback whatsoever — "the plugins actually booted are decided by an external cordis.yml" is a hard semantic.
@@ -40,15 +40,15 @@ The deploy root is [`python/sdk-runtime/package.json`](../../../../python/sdk-ru
### Build pipeline and artifacts
[`scripts/build-exe-for-python-sdk.ts`](../../../../scripts/build-exe-for-python-sdk.ts): runtime closure verification → `pnpm run build` → (after clearing) `pnpm --filter dsh-jsonrpc-agent-pkg deploy --legacy --prod --config.node-linker=hoisted --config.auto-install-peers=false --config.link-workspace-packages=true` **directly into** `python/sdk-runtime/src/deepseek_harness_runtime/runtime/node/` → restore any direct workspace package that legacy deploy hoisted back under the source manifest's `node_modules`, omitting its package-local dependency tree and rejecting any remaining manifest gap → replace every staged dependency symlink with its target bytes, remove package-manager `.bin` links, and fail if any symlink remains → inject the pkg configuration (`bin` points at `node_modules/@deepseek-ai/dsh-jsonrpc-demo/lib/packaged-bin.js` inside the closure, `assets` is a full glob — dynamic import is invisible to pkg's static analysis, so everything must be packed in explicitly) → stage the target `node-pty` addon → one `pkg --sea` per target → the executables `dsh-jsonrpc-agent-pkg-<platform>-<arch>` land in `dist-exe/` and are copied back into the runtime directory. Linux installs build `pty.node` from source, so the builder copies it from the root install into the staged closure because legacy deploy omits that side-effect directory; macOS uses its target prebuild and emits the required `-spawn-helper` beside the executable. CI treats these products as intermediate test inputs and retains their platform wheels. All four deploy flags are grounded in measurement: `--legacy` is the mandatory path with inject-workspace-packages off; hoisted gives pkg a stable single-instance layout that the explicit materialization pass makes symlink-free; disabling automatic peer installation prevents undeclared peers from expanding the closure; link-workspace-packages selects direct workspace dependencies. [`pnpm-workspace.yaml`](../../../../pnpm-workspace.yaml) overrides the transitive `@deepseek-ai/cosmokit` and `@deepseek-ai/schemastery` semver requests to the pinned vendor sources so legacy deploy never resolves those unpublished names from a registry.
[`scripts/build-exe-for-python-sdk.ts`](../../../../scripts/build-exe-for-python-sdk.ts): runtime closure verification → `pnpm run build` → (after clearing) `pnpm --filter dsh-jsonrpc-agent-pkg deploy --legacy --prod --config.node-linker=hoisted --config.auto-install-peers=false --config.link-workspace-packages=true` **directly into** `python/sdk-runtime/src/deepseek_harness_runtime/runtime/node/` → restore any direct workspace package that legacy deploy hoisted back under the source manifest's `node_modules`, omitting its package-local dependency tree and rejecting any remaining manifest gap → replace every staged dependency symlink with its target bytes, remove package-manager `.bin` links, and fail if any symlink remains → inject the pkg configuration (`bin` points at `node_modules/@deepseek-ai/dsh-jsonrpc-demo/lib/packaged-bin.js` inside the closure, `assets` is a full glob — dynamic import is invisible to pkg's static analysis, so everything must be packed in explicitly) → stage the target `node-pty` addon → one `pkg --sea` per target → the executables `dsh-jsonrpc-agent-pkg-<platform>-<arch>` land in `dist-exe/` and are copied back into the runtime directory. Linux installs build `pty.node` from source; CI rebuilds that addon inside the matching manylinux 2.28 container before packaging, and the builder copies it from the root install into the staged closure because legacy deploy omits that side-effect directory. macOS uses its target prebuild and emits the required `-spawn-helper` beside the executable. CI treats these products as intermediate test inputs and retains their platform wheels. All four deploy flags are grounded in measurement: `--legacy` is the mandatory path with inject-workspace-packages off; hoisted gives pkg a stable single-instance layout that the explicit materialization pass makes symlink-free; disabling automatic peer installation prevents undeclared peers from expanding the closure; link-workspace-packages selects direct workspace dependencies. [`pnpm-workspace.yaml`](../../../../pnpm-workspace.yaml) overrides the transitive `@deepseek-ai/cosmokit` and `@deepseek-ai/schemastery` semver requests to the pinned vendor sources so legacy deploy never resolves those unpublished names from a registry.
CI: [`.github/workflows/build-exe-for-python-sdk.yml`](../../../../.github/workflows/build-exe-for-python-sdk.yml), triggered explicitly only — `workflow_dispatch`, or the `build-exe` label on a pull request; native builds on the three platforms linux-x64 / linux-arm64 (`ubuntu-24.04-arm`) / macos-arm64, with `~/.pkg-cache` cached; macOS ad-hoc signing is handled by pkg. Each leg drives a mock SSE model through the SDK with the default config and a custom `cordis.yml`, drives the exe directly over NDJSON JSON-RPC, verifies the JSONL and final response, and installs release-shaped wheels into a clean venv without `runtime_bin`; Linux additionally inspects GLIBC requirements and runs in a manylinux 2.28 container. A full three-target run retains four artifacts, each containing one release file: the platform-independent SDK wheel and three native runtime wheels; a subset dispatch retains the SDK wheel and selected runtime wheels. Bare executables and source bundles remain intermediate test inputs. [`.gitlab-ci.yml`](../../../../.gitlab-ci.yml) accepts only `python-vX.Y.Z` tag pipelines whose version matches the root `package.json`, builds one SDK wheel and three native runtime wheels, then a single serialized job checks and publishes all four to the project PyPI registry. Windows is a non-goal.
CI: [`.github/workflows/build-exe-for-python-sdk.yml`](../../../../.github/workflows/build-exe-for-python-sdk.yml), triggered explicitly by `workflow_dispatch`, the `build-exe` label on a pull request, or the [public publication workflow](../process/2026-08-11-python-publication-workflow.md); native builds run on linux-x64 / linux-arm64 (`ubuntu-24.04-arm`) / macos-arm64, with `~/.pkg-cache` cached, and pkg handles macOS ad-hoc signing. Each leg drives a mock SSE model through the SDK with the default config and a custom `cordis.yml`, drives the exe directly over NDJSON JSON-RPC, verifies the JSONL and final response, and installs release-shaped wheels into a clean venv without `runtime_bin`; Linux additionally inspects both the executable and native addon's GLIBC requirements and runs in a manylinux 2.28 container, while macOS verifies that the executable's deployment target fits the wheel tag. A full three-target run retains four artifacts, each containing one release file: the platform-independent SDK wheel and three native runtime wheels; a subset dispatch retains the SDK wheel and selected runtime wheels. Bare executables and source bundles remain intermediate test inputs. [`.gitlab-ci.yml`](../../../../.gitlab-ci.yml) accepts `python-v<repository-version>` tag pipelines whose version matches the root `package.json`, builds one SDK wheel and three native runtime wheels, then a single serialized job checks and publishes all four to the project PyPI registry. Windows is a non-goal.
### Python SDK distribution: two carriers, exe for production, node for development
The Python SDK lives at [`python/`](../../../../python/README.md): `python/sdk` (the client) + `python/sdk-runtime` (the runtime carrier package). The runtime package's data directory holds the checked-in default `runtime/cordis.yml`, the build-injected platform exe and optional helper, and the build-injected `runtime/node/` closure tree. `resolve_bundled_launch_args()` automatic resolution **finds the exe only**; the node carrier is enabled only by an explicit `DSH_RUNTIME_MODE=node` (running `runtime/node/node_modules/@deepseek-ai/dsh-jsonrpc-demo/lib/packaged-bin.js`, requiring a system node ≥22.19), positioned as the development-verification channel for members of this repo, and does not enter wheel distributions.
[`scripts/build-python-release.py`](../../../../scripts/build-python-release.py) reads the authoritative stable `X.Y.Z` from the repository root `package.json` and stages both packages at that version, with `deepseek-harness-sdk` depending exactly on `deepseek-harness-runtime-bin==X.Y.Z`. An optional `python-vX.Y.Z` release tag is a consistency assertion and is rejected when it differs from the repository version; the source `pyproject.toml` development sentinel never determines a release version. The SDK is a `py3-none-any` wheel; each wheel-only runtime package contains one exe, and the macOS wheel also contains its architecture-matched helper. Runtime wheels use one of `py3-none-manylinux_2_28_x86_64`, `py3-none-manylinux_2_28_aarch64`, or `py3-none-macosx_11_0_arm64`; the Hatch hook rejects sdists, universal tags, mixed-platform payloads, missing or extra helpers, and unsupported platforms.
[`scripts/build-python-release.py`](../../../../scripts/build-python-release.py) reads the authoritative `X.Y.Z` or prerelease version from the repository root `package.json`, converts prereleases to their PEP 440 spelling, and stages both packages at that wheel version, with `deepseek-harness-sdk` depending exactly on the matching `deepseek-harness-runtime-bin`. An optional `python-v<repository-version>` release tag is a consistency assertion and is rejected when it differs from the repository version; the source `pyproject.toml` development sentinel never determines a release version. Staging also carries the repository license into both wheels and the third-party notices into the bundled runtime wheel. The SDK is a `py3-none-any` wheel; each wheel-only runtime package contains one exe, and the macOS wheel also contains its architecture-matched helper. Runtime wheels use one of `py3-none-manylinux_2_28_x86_64`, `py3-none-manylinux_2_28_aarch64`, or the conservative `py3-none-macosx_14_0_arm64` tag for the Node 24 executable's macOS 13.5 deployment target; the Hatch hook rejects sdists, universal tags, mixed-platform payloads, missing or extra helpers, and unsupported platforms.
The exe's "must be explicitly configured" hard semantic is unchanged; the zero-config experience is restored by the wrapper: when the caller gave no `cordis`, named no explicit runtime, and the environment has no `DSH_CORDIS_CONFIG`, the client explicitly injects the checked-in default `cordis.yml` (agent-core + preloaded llm-deepseek + JSONL persistence + bash-local + the `dsh-jsonrpc` serving entry, with `!!js` environment-variable fallbacks) via `DSH_CORDIS_CONFIG`.
@@ -23,11 +23,11 @@ exe 使用 [@yao-pkg/pkg](https://github.com/yao-pkg/pkg)vercel/pkg 归档后
术语提醒:pkg 的 `/snapshot` VFS 与本仓库测试体系的「快照」(ACP 回放预期输出、`$DSH_SNAPSHOT`)无关,本文用「VFS」指前者。
### 对外服务接口也是插件:ui/jsonrpc + examples/jsonrpc-demo 两个包
### 对外服务接口也是插件:sdk/server + examples/jsonrpc-demo 两个包
确定性协议实现(`server.ts` / `transport.ts`)按 `acp/acp` + `examples/acp-demo` 的既有模式落为两包——对外服务接口本身也是插件:
- [`packages/scaffold/server`](../../../../packages/scaffold/server/README.md)`@deepseek-ai/dsh-jsonrpc`):纯协议插件;执行 `apply` 时,在进程 stdio 上挂载 `HarnessSdkServer` 与按行传输的 JSON-RPC 层,资源释放走 `ctx.effect()`。是否提供服务由 `cordis.yml` 决定;未挂载该插件的配置会启动一个不提供此服务的合法进程。协议级退出归插件所有(应答并确保 `shutdown` 响应发送完毕后,对根运行时执行 dispose(资源释放),让待处理的持久化操作完成,再调用 `exit(0)`;HMR 式卸载只停止服务,不退出进程)。
- [`packages/sdk/server`](../../../../packages/sdk/server/README.md)`@deepseek-ai/dsh-jsonrpc`):纯协议插件;执行 `apply` 时,在进程 stdio 上挂载 `HarnessSdkServer` 与按行传输的 JSON-RPC 层,资源释放走 `ctx.effect()`。是否提供服务由 `cordis.yml` 决定;未挂载该插件的配置会启动一个不提供此服务的合法进程。协议级退出归插件所有(应答并确保 `shutdown` 响应发送完毕后,对根运行时执行 dispose(资源释放),让待处理的持久化操作完成,再调用 `exit(0)`;HMR 式卸载只停止服务,不退出进程)。
- [`packages/examples/jsonrpc-demo`](../../../../packages/examples/jsonrpc-demo/README.md)`@deepseek-ai/dsh-jsonrpc-demo`):轻量应用入口——`installFailLoud` + `loadEnv` + 配置发现 + [`dsh-app-boot`](../../../../packages/boot/app-boot/src/index.ts) 的 `boot()``boot()` 完成后入口即完成,服务器由 `cordis.yml` 中的 `dsh-jsonrpc` 条目启动。它只依赖 `app-boot`。进程级退出归 `bin` 所有(stdin EOF/SIGTERM → dispose 后返回 0SIGINT → 130)。
配置发现有两个通道,均缺失时立即报错:优先使用 `DSH_CORDIS_CONFIG` 环境变量(SDK 客户端约定),其次使用 argv 位置参数;没有默认路径或内置回退——「实际启动的插件由外部 `cordis.yml` 决定」是硬语义。
@@ -40,15 +40,15 @@ exe 的 VFS 内是**构建产物形态的真实包树**(各包的 `lib/` + 真
### 构建管线与产物
[`scripts/build-exe-for-python-sdk.ts`](../../../../scripts/build-exe-for-python-sdk.ts):运行时闭包校验 → `pnpm run build` →(清空后)`pnpm --filter dsh-jsonrpc-agent-pkg deploy --legacy --prod --config.node-linker=hoisted --config.auto-install-peers=false --config.link-workspace-packages=true` **直接写入** `python/sdk-runtime/src/deepseek_harness_runtime/runtime/node/` → 恢复被 legacy deploy 提升回源 manifest 的 `node_modules` 下的任何直接工作区包,同时省略其包内依赖树,并拒绝剩余的 manifest 缺口 → 将暂存依赖中的每个符号链接替换为目标文件内容,删除包管理器的 `.bin` 链接,并在仍有任何符号链接时失败 → 注入 pkg 配置(`bin` 指向闭包内的 `node_modules/@deepseek-ai/dsh-jsonrpc-demo/lib/packaged-bin.js``assets` 使用全量 glob,因为动态 `import()` 对 pkg 静态分析不可见,必须显式打入全部内容)→ 暂存目标平台的 `node-pty` addon → 每个构建目标调用一次 `pkg --sea` → 可执行文件 `dsh-jsonrpc-agent-pkg-<platform>-<arch>` 写入 `dist-exe/`,并拷回运行时目录。Linux 安装会从源码构建 `pty.node`,而 `--legacy` 部署会省略副作用目录,因此构建器会把它从根安装目录复制到暂存闭包macOS 使用对应目标的预构建产物,并在可执行文件旁生成所需的 `-spawn-helper`。CI 将这些产物作为测试中间输入,只保留对应平台的 wheel 包。四个部署标志都有实测依据:未启用 `inject-workspace-packages` 时必须使用 `--legacy``hoisted` 为 pkg 提供稳定的单实例布局,再由显式物化步骤消除符号链接;关闭对等依赖自动安装可防止未声明的对等依赖扩大闭包;`link-workspace-packages` 选择直接工作区依赖。[`pnpm-workspace.yaml`](../../../../pnpm-workspace.yaml) 将传递的 `@deepseek-ai/cosmokit``@deepseek-ai/schemastery` semver 请求覆盖到固定的 vendor 源码,使 legacy deploy 不会从注册表解析这些未发布名称。
[`scripts/build-exe-for-python-sdk.ts`](../../../../scripts/build-exe-for-python-sdk.ts):运行时闭包校验 → `pnpm run build` →(清空后)`pnpm --filter dsh-jsonrpc-agent-pkg deploy --legacy --prod --config.node-linker=hoisted --config.auto-install-peers=false --config.link-workspace-packages=true` **直接写入** `python/sdk-runtime/src/deepseek_harness_runtime/runtime/node/` → 恢复被 legacy deploy 提升回源 manifest 的 `node_modules` 下的任何直接工作区包,同时省略其包内依赖树,并拒绝剩余的 manifest 缺口 → 将暂存依赖中的每个符号链接替换为目标文件内容,删除包管理器的 `.bin` 链接,并在仍有任何符号链接时失败 → 注入 pkg 配置(`bin` 指向闭包内的 `node_modules/@deepseek-ai/dsh-jsonrpc-demo/lib/packaged-bin.js``assets` 使用全量 glob,因为动态 `import()` 对 pkg 静态分析不可见,必须显式打入全部内容)→ 暂存目标平台的 `node-pty` addon → 每个构建目标调用一次 `pkg --sea` → 可执行文件 `dsh-jsonrpc-agent-pkg-<platform>-<arch>` 写入 `dist-exe/`,并拷回运行时目录。Linux 安装会从源码构建 `pty.node`;CI 会在打包前进入匹配架构的 manylinux 2.28 容器重新构建该 addon,而 `--legacy` 部署会省略这一副作用目录,因此构建器会把它从根安装目录复制到暂存闭包macOS 使用对应目标的预构建产物,并在可执行文件旁生成所需的 `-spawn-helper`。CI 将这些产物作为测试中间输入,只保留对应平台的 wheel 包。四个部署标志都有实测依据:未启用 `inject-workspace-packages` 时必须使用 `--legacy``hoisted` 为 pkg 提供稳定的单实例布局,再由显式物化步骤消除符号链接;关闭对等依赖自动安装可防止未声明的对等依赖扩大闭包;`link-workspace-packages` 选择直接工作区依赖。[`pnpm-workspace.yaml`](../../../../pnpm-workspace.yaml) 将传递的 `@deepseek-ai/cosmokit``@deepseek-ai/schemastery` semver 请求覆盖到固定的 vendor 源码,使 legacy deploy 不会从注册表解析这些未发布名称。
CI 使用 [`.github/workflows/build-exe-for-python-sdk.yml`](../../../../.github/workflows/build-exe-for-python-sdk.yml)且只允许显式触发:手动派发 `workflow_dispatch`,或给 PRPull Request添加 `build-exe` 标签。linux-x64、linux-arm64`ubuntu-24.04-arm`)和 macos-arm64 三个平台分别进行原生构建,并缓存 `~/.pkg-cache`macOS 的 ad-hoc 签名由 pkg 处理。每个平台都使用 mock SSEServer-Sent Events)模型,分别通过默认配置和自定义 `cordis.yml` 驱动 SDK,再通过 NDJSON JSON-RPC 直接驱动 exe,校验 JSONL 与最终响应;最后把发布形态的 wheel 包安装到干净的 venv 中,并在不传 `runtime_bin` 的情况下运行。Linux 还会检查 GLIBC 依赖,并在 manylinux 2.28 容器中运行。完整构建三个目标时保留 4 个产物,每个产物只含一个发布文件:平台无关的 SDK wheel 包与 3 个原生运行时 wheel 包;手动选择部分目标时保留 SDK wheel 与所选运行时 wheel。裸 exe 与源码包只作为测试中间输入。[`.gitlab-ci.yml`](../../../../.gitlab-ci.yml) 只接受版本与根目录 `package.json` 匹配的 `python-vX.Y.Z` 标签流水线,构建一个 SDK wheel 包和 3 个原生运行时 wheel 包,再由单个串行任务校验并将这 4 个文件发布到项目的 PyPI 注册表。Windows 不在目标范围内。
CI 使用 [`.github/workflows/build-exe-for-python-sdk.yml`](../../../../.github/workflows/build-exe-for-python-sdk.yml)手动派发 `workflow_dispatch`PRPull Request `build-exe` 标签或[公开发布工作流](../process/2026-08-11-python-publication-workflow.md)显式触发。linux-x64、linux-arm64`ubuntu-24.04-arm`)和 macos-arm64 三个平台分别进行原生构建,并缓存 `~/.pkg-cache`macOS 的 ad-hoc 签名由 pkg 处理。每个平台都使用 mock SSEServer-Sent Events)模型,分别通过默认配置和自定义 `cordis.yml` 驱动 SDK,再通过 NDJSON JSON-RPC 直接驱动 exe,校验 JSONL 与最终响应;最后把发布形态的 wheel 包安装到干净的 venv 中,并在不传 `runtime_bin` 的情况下运行。Linux 还会检查可执行文件和原生 addon 各自的 GLIBC 依赖,并在 manylinux 2.28 容器中运行;macOS 则验证可执行文件的部署目标符合 wheel 包标签。完整构建三个目标时保留 4 个产物,每个产物只含一个发布文件:平台无关的 SDK wheel 包与 3 个原生运行时 wheel 包;手动选择部分目标时保留 SDK wheel 与所选运行时 wheel。裸 exe 与源码包只作为测试中间输入。[`.gitlab-ci.yml`](../../../../.gitlab-ci.yml) 只接受版本与根目录 `package.json` 匹配的 `python-v<repository-version>` 标签流水线,构建一个 SDK wheel 包和 3 个原生运行时 wheel 包,再由单个串行任务校验并将这 4 个文件发布到项目的 PyPI 注册表。Windows 不在目标范围内。
### Python SDK 分发:双载体,exe 用于生产,`node` 用于开发
Python SDK 位于 [`python/`](../../../../python/README.md)`python/sdk` 是客户端,`python/sdk-runtime` 是运行时载体包。运行时包的数据目录包含检入的默认 `runtime/cordis.yml`、构建注入的平台 exe 与可选 helper,以及构建注入的 `runtime/node/` 闭包树。`resolve_bundled_launch_args()` 的自动解析**只查找 exe**`node` 载体仅在显式设置 `DSH_RUNTIME_MODE=node` 时启用(运行 `runtime/node/node_modules/@deepseek-ai/dsh-jsonrpc-demo/lib/packaged-bin.js`,需要系统 Node ≥22.19),定位为本仓库成员的开发验证通道,不随 wheel 包分发。
[`scripts/build-python-release.py`](../../../../scripts/build-python-release.py) 从仓库根目录的 `package.json` 读取权威的稳定版本 `X.Y.Z`,以该版本暂存两个包,`deepseek-harness-sdk` 精确依赖 `deepseek-harness-runtime-bin==X.Y.Z`。可选的 `python-vX.Y.Z` 发布标签只是一项一致性断言,与仓库版本不同时会被拒绝;源码 `pyproject.toml` 中的开发占位版本从不决定发布版本。SDK 是 `py3-none-any` wheel 包;每个只提供 wheel 包的运行时包都包含一个 exe,macOS wheel 包还包含与其架构匹配的 helper。运行时 wheel 包使用 `py3-none-manylinux_2_28_x86_64``py3-none-manylinux_2_28_aarch64` `py3-none-macosx_11_0_arm64` 三种标签之一Hatch 钩子拒绝 sdist、通用标签、混合平台载荷、helper 缺失或多余,以及不支持的平台。
[`scripts/build-python-release.py`](../../../../scripts/build-python-release.py) 从仓库根目录的 `package.json` 读取权威的 `X.Y.Z` 或预发布版本,把预发布版本转换为 PEP 440 写法,并以该 wheel 包版本暂存两个包,让 `deepseek-harness-sdk` 精确依赖匹配版本的 `deepseek-harness-runtime-bin`。可选的 `python-v<repository-version>` 发布标签只是一项一致性断言,与仓库版本不同时会被拒绝;源码 `pyproject.toml` 中的开发占位版本从不决定发布版本。暂存过程还会把仓库许可证放入两个 wheel 包,并把第三方声明放入内置运行时 wheel 包。SDK 是 `py3-none-any` wheel 包;每个只提供 wheel 包的运行时包都包含一个 exe,macOS wheel 包还包含与其架构匹配的 helper。运行时 wheel 包使用 `py3-none-manylinux_2_28_x86_64``py3-none-manylinux_2_28_aarch64`,或针对 Node 24 可执行文件 macOS 13.5 部署目标而保守选择的 `py3-none-macosx_14_0_arm64` 标签Hatch 钩子拒绝 sdist、通用标签、混合平台载荷、helper 缺失或多余,以及不支持的平台。
exe「必须显式配置」的硬语义不变;零配置体验由包装层恢复:调用方没有提供 `cordis`、没有显式指定运行时,且环境中没有 `DSH_CORDIS_CONFIG` 时,客户端将检入的默认 `cordis.yml``agent-core` + 预载的 `llm-deepseek` + JSONL 持久化 + `bash-local` + `dsh-jsonrpc` 对外服务条目,并通过 `!!js` 使用环境变量兜底)显式注入 `DSH_CORDIS_CONFIG`
@@ -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/architecture/2026-07-23-client-plugin-loading-model.md
2026-07-23-client-plugin-loading-model.md: 860186294059facf17d1eba38423092acf7a4a7d
2026-07-23-client-plugin-loading-model.zh.md: 68f2e70253485d4e215c981d3b338d5046390247
2026-07-23-client-plugin-loading-model.md: 3347bdac95eb8e06be3e7c20d24319103f738149
2026-07-23-client-plugin-loading-model.zh.md: d52409e167b536162a8efb9a9ecc3092f6e5d1d2
@@ -31,7 +31,7 @@ What makes a package a plugin? One rule: **a package is a plugin package once it
- **Plain packages** are the absolute base the module system itself needs, plus libraries not yet converted to DI: the react family, cordis, `@deepseek-ai/dsh-client-modules` (the module system itself — it can never be a plugin, because modules precede all modules), the web shell kernel, and — for now — ui-slots, web-react, ui-primitives. Plain packages are shell-bundled, seeded into the module table, and invisible to the host graph.
- **Plugin packages** are everything else. Each one carries a `dsh.client` manifest declaration (`{ platform, inject, immediately? }`) and one uniform shape: the shared tsdown preset emits `lib/client.js`, and `exports["./client"]` points at that bundle. Each is a governed entry of the host-authored graph. The current set is connection, runtime, ui-theme, i18n, hmr (dev graphs only), ui-layout, ui-sidebar, ui-conversation, ui-model-selector, ui-question, and ui-trajectory.
The manifest owns the package's loading contract: its `inject` dependency edges, plus the optional `immediately` prefetch mark (absent means lazy). The composing app owns only the roster and the `--dev` switch.
The manifest owns the package's loading contract: its `inject` dependency edges, plus the optional `immediately` prefetch mark (absent means lazy). The composing app owns only the roster.
To add a plugin package: declare `dsh.client`, emit the `./client` bundle through the shared preset, add the name to the composing app's roster. Nothing else changes hands.
@@ -66,7 +66,7 @@ What happens between `dsh web` starting and the UI appearing? Three stages: the
**Host side — compose the graph.**
1. The composing app (`apps/cli`) ships the roster as ordinary rows in its `cordis.yml` config tree — client plugin packages are entry rows like every host plugin, and `--dev` appends the `client-hmr` row in code (`AppCLIEntry`) before the host activation audit so the same check covers it. A roster row that fails to import is caught by `assertEntriesLoaded`; a row whose fiber rejects is reported with its original stack by `assertEntriesActivated` ([host boot decision](2026-07-24-web-config-tree-boot-and-transport-layering.md)).
1. The composing app (`apps/cli`) ships the roster as ordinary rows in its `cordis.yml` config tree — client plugin packages are entry rows like every host plugin, including the always-mounted `client-hmr` row. A roster row that fails to import is caught by `assertEntriesLoaded`; a row whose fiber rejects is reported with its original stack by `assertEntriesActivated` ([host boot decision](2026-07-24-web-config-tree-boot-and-transport-layering.md)).
2. The `dsh-client-modules` node half (the package is dual-face: its browser half is the module table) scans loader entries' package.json `dsh.client` declarations and composes `window.__DSH_BOOT__`: `{ rev, entries: [{ id, url, rev, inject?, immediately? }] }`. The `inject` edges and the `immediately` mark come from manifests, never hand-copied. It refuses declared plugins without built `./client` bundles and groups their package/path rows under one required source-build instruction; malformed declaration fields also fail activation, and the host audit reports either error from the FAILED fiber.
3. Scanning is incremental per package — there is no full-rescan code path. Each cordis `internal/plugin` emission marks the fiber's entry name dirty (entry-less fibers drop O(1)); a microtask flush reconciles each dirty name against live loader entries, with package metadata (including the negative "not a client package" verdict) cached per name forever and bundle re-hashing reachable only through `rebuilt(id)`. The activation pass seeds the same dirty set from current entries and flushes synchronously, so first scan and steady state share one implementation. Each bundle's content hash is its `rev` (cache busting + HMR diff anchor), the row set hashes into `graph.rev`, and every row is served as a script resource at `/plugins/<id>/client.js?rev=…`, with its source map at the same path plus `.map`. The graph types are single-sourced in the modules package's `./client` export — the webserver knows nothing about the graph (it is a plain route-registration plugin; modules registers the bundle route and taps the index render itself).
@@ -84,7 +84,7 @@ Why is the roster yml rows and not a scan? Because which plugins compose into a
### Hot reload: one driver plugin, self-watched bundles
Whether hot reload is active is a composition decision: dev compositions mount the `client-hmr` row (a normal plugin package, appended by `--dev`) whose node half brings the bundle watch and the SSE channel; prod compositions mount nothing and have neither.
Hot reload is a composition decision: the web bundle mounts the `client-hmr` row (a normal plugin package) unconditionally; its node half brings the bundle watch and the SSE channel, and the chain stays idle until a rebuild watcher rewrites client bundles. A composition that must not expose it disables the row.
How does a rebuilt bundle become a reload signal? The hmr node half observes it itself — no builder tells it. It reads bundle paths from `ctx.clientModuleHost.clientPath(id)`, and one HMR-owned interval stat-polls every current graph row. Adding a row is ordered as synchronous stat baseline, then immediate `clientModuleHost.rebuilt(id)`: a write after the module host's graph hash but before that baseline is caught by the immediate re-hash, while a write after the baseline leaves a stat delta for the next poll. This avoids `fs.watchFile`, whose asynchronous first baseline can silently absorb a construction-time rebuild. Watch membership follows `onGraphChanged`; vanished rows drop out, and a bundle missing at poll time keeps its row dirty so reappearance forces a re-hash even with identical metadata. On a mtime/size delta or dirty row, `clientModuleHost.rebuilt(id)` is the single re-hash entry point; when the `rev` actually changed, the node half broadcasts a `rebuilt` frame on `GET /plugins/events` — a system SSE channel that sends the full graph on connect and `rebuilt` frames on change, presentation-only wire that never enters the session log. Polling is deliberate because inotify does not fire on the weka network mount, the same reason the build-side watcher needs `--poll`; the interval is a validated config field (default 500ms), and disposal clears the one timer. Rebuilding bundles is any tsdown watch process's business — `scripts/dev-web.ts` remains the watch-build entry point, discovering its package list through `dsh.client` while scanning `packages/*/*/package.json` at startup — and builder and host share zero protocol. A torn read self-heals: stats keep changing while the write completes, so the next poll re-hashes and broadcasts the final rev.
@@ -117,12 +117,12 @@ The support boundary, stated honestly. Reload is coarse by design: fresh fiber,
| `dsh-client-runtime` | session object layer + slots service + store engine | plugin, declares `immediately` | keeps shrinking toward a pure session object layer |
| `dsh-client-ui-theme` | theme tokens/service | plugin, declares `immediately`, plus the `./styles/*` source channel | Theme Registry (separate ruling) |
| `dsh-client-i18n` | I18nService | plugin, declares `immediately` | per-deployment locale composition |
| `dsh-client-hmr` | hot reload driver | plugin, declares `immediately`; dev graphs only | rollback; reconnect handshake |
| `dsh-client-hmr` | hot reload driver | plugin, declares `immediately` | rollback; reconnect handshake |
| ui-layout / ui-sidebar / ui-conversation / ui-trajectory | UI features | plugins, on-demand | conversation domain split; trajectory real implementation |
## Consequences
One governance implementation runs on both sides of the wire; the browser-specific layer is one module system plus one reload plugin. Plugin packages have one shape, so the purity gate covers them all. Dependency edges and the boot tier live with their owners — the manifests — while the composing app holds only the roster and the `--dev` switch. The drift classes stay structurally closed: share-list hand-sync, load-order coupling, cross-plugin imports, roster/tier double bookkeeping. Browser-native script loading preserves the standard mapping among plugin network resources, generated bundles, and TypeScript/TSX sources, while the module system keeps only one replaceable `loadBundle` hook.
One governance implementation runs on both sides of the wire; the browser-specific layer is one module system plus one reload plugin. Plugin packages have one shape, so the purity gate covers them all. Dependency edges and the boot tier live with their owners — the manifests — while the composing app holds only the roster. The drift classes stay structurally closed: share-list hand-sync, load-order coupling, cross-plugin imports, roster/tier double bookkeeping. Browser-native script loading preserves the standard mapping among plugin network resources, generated bundles, and TypeScript/TSX sources, while the module system keeps only one replaceable `loadBundle` hook.
Costs accepted: the vendored Loader carries idle machinery in the browser (EntryTree persistence is a no-op, groups/isolation unused); every plugin edit in dev pays a bundle rebuild plus fiber remount; graph `inject` rows are informational — activation truth is service-level — so a mismatch appears at the settled sweep, not at graph validation; the three not-yet-promoted libraries keep their static-import exports until their DI conversions land; every bundle gains a source-map artifact; and external-script failures provide only coarse URL diagnostics instead of the HTTP status available to an explicit fetch.
@@ -31,7 +31,7 @@ host 侧,cordis 插件装载站在 Node 的模块机制之上——require cac
- **普通包**是模块系统自身所需的绝对基座,加上尚未转成 DI 的库:react 家族、cordis、`@deepseek-ai/dsh-client-modules`(模块系统本身——它永远不可能是插件,因为模块先于一切模块)、web 壳内核,以及——暂时——ui-slots、web-react、ui-primitives。普通包打进壳 bundle、播种进模块表、对 host 图不可见。
- **插件包**是其余一切。每个都携带 `dsh.client` manifest(元数据清单)声明(`{ platform, inject, immediately? }`)和同一种统一形态:共享 tsdown 预设产出 `lib/client.js``exports["./client"]` 指向该 bundle。每个都是 host 独家撰写的图里受治理的 entry。当前包括:connection、runtime、ui-theme、i18n、hmr(仅进 dev 图)、ui-layout、ui-sidebar、ui-conversation、ui-model-selector、ui-question、ui-trajectory。
manifest 拥有包的装载约定:它的 `inject` 依赖边,加可选的 `immediately` 预取标记(缺省即 lazy)。负责组合的 app 只拥有名册`--dev` 开关
manifest 拥有包的装载约定:它的 `inject` 依赖边,加可选的 `immediately` 预取标记(缺省即 lazy)。负责组合的 app 只拥有名册。
新增一个插件包:声明 `dsh.client`,经共享预设产出 `./client` bundle,把包名加进负责组合的 app 的名册。除此之外无需任何交接。
@@ -66,7 +66,7 @@ vendored Loader 经其 `internal` 约定消费模块系统——唯一调用点
**host 侧——组合这张图。**
1. 负责组合的 app`apps/cli`)把名册作为普通行放进它的 `cordis.yml` 配置树——client 插件包与每个 host 插件一样是 entry 行,`--dev` 由代码(`AppCLIEntry`)在 host 激活检查之前追加 `client-hmr`,使同一项检查覆盖它。名册行 import 失败由 `assertEntriesLoaded` 捕获;fiber reject 的行则由 `assertEntriesActivated` 报告原始 stack[host boot 决策](2026-07-24-web-config-tree-boot-and-transport-layering.md))。
1. 负责组合的 app`apps/cli`)把名册作为普通行放进它的 `cordis.yml` 配置树——client 插件包与每个 host 插件一样是 entry 行,包括无条件挂载的 `client-hmr` 行。名册行 import 失败由 `assertEntriesLoaded` 捕获;fiber reject 的行则由 `assertEntriesActivated` 报告原始 stack[host boot 决策](2026-07-24-web-config-tree-boot-and-transport-layering.md))。
2. `dsh-client-modules` 的 node 半(该包是双面的:浏览器半就是模块表)扫描 loader entry 的 package.json `dsh.client` 声明,组合出 `window.__DSH_BOOT__``{ rev, entries: [{ id, url, rev, inject?, immediately? }] }``inject` 边与 `immediately` 标记都来自 manifest,永不人肉抄写。它会拒绝没有已构建 `./client` bundle 的已声明插件,并把它们的 package/path 行归到一条源码构建要求下;畸形声明字段同样会让激活失败,host 检查会从 FAILED fiber 报告这两类错误。
3. 扫描是单包增量——不存在全量重扫代码路径。每次 cordis `internal/plugin` 发射把该 fiber 的 entry 名标脏(无 entry 的 fiber O(1) 丢弃);微任务 flush 把每个脏名对账 live loader entries,包元数据(含「非 client 包」的否定结论)按名永久缓存,bundle 重哈希只经 `rebuilt(id)` 可达。激活趟从当前 entries 灌同一脏集合并同步 flush,初扫与稳态共享一条实现。每个 bundle 的内容哈希是其 `rev`(缓存失效 + HMR diff 锚点),行集合哈希进 `graph.rev`,每一行都作为脚本资源供给:`/plugins/<id>/client.js?rev=…`,对应 sourcemap 位于同一路径加 `.map`。图类型单源在 modules 包的 `./client` 出口——webserver 对图一无所知(它是朴素路由注册插件;bundle 路由和 index 渲染 tap 都由 modules 自己注册)。
@@ -84,7 +84,7 @@ vendored Loader 经其 `internal` 约定消费模块系统——唯一调用点
### 热重载:一个驱动插件,自行监视的 bundle
热重载是否启用是一项组合决策:dev 组合挂载 `client-hmr` 行(一个常规的插件包,由 `--dev` 追加),其 node 半带来 bundle 监视与 SSEServer-Sent Events)通道;prod 组合不挂载,两者皆无
热重载是一项组合决策:web 组合包无条件挂载 `client-hmr` 行(一个常规的插件包),其 node 半带来 bundle 监视与 SSEServer-Sent Events)通道;没有重建 watcher 改写客户端 bundle 时链路保持空闲。不得暴露它的组合可在 patch 层禁用该行
重建好的 bundle 怎么变成重载信号?hmr 的 node 半自己观察——没有构建器来通知它。它从 `ctx.clientModuleHost.clientPath(id)` 读取图上各行的 bundle 路径,由 HMR 自持的单个定时器对当前图上的每一行做 stat 轮询。新增图行时,顺序固定为先同步取得 stat 基线,再立即调用 `clientModuleHost.rebuilt(id)`:在模块 host 算出图哈希之后、取得基线之前发生的写入会被这次立即重哈希捕获;取得基线之后发生的写入则会留下 stat 差异,供下一次轮询捕获。这避开了 `fs.watchFile`:它以异步首次 stat 建立基线,可能把构造期间的重建静默吸收进基线。监视集合的成员随 `onGraphChanged` 更新;消失的行撤下监视,轮询时缺失的 bundle 则让对应行保持标脏状态,文件重现时即使元数据相同也强制重哈希。mtime/size 变化或行处于标脏状态时,`clientModuleHost.rebuilt(id)` 是重哈希的唯一入口;当 `rev` 真的变了,node 半才在 `GET /plugins/events` 上广播 `rebuilt` 帧——这是一条系统级 SSE 通道,连接即发全量图,变更时发 `rebuilt` 帧,仅供呈现的 wire,永不进会话日志。轮询是刻意选择:inotify 在 weka 网络挂载上不触发,构建侧监视器需要 `--poll` 也是同一原因;轮询间隔是一个经校验的配置字段(默认 500ms),dispose(资源释放)会清掉那一个定时器。重建 bundle 则是任意一个 tsdown watch 进程的事——`scripts/dev-web.ts` 仍作为 watch 构建入口保留,其包清单在启动时扫描 `packages/*/*/package.json` 按 dsh.client 发现——构建器与 host 共享零协议。写一半的 bundle 被撕裂读取会自愈:写入完成期间 stat 持续变化,下一个轮询节拍会再次重哈希并广播最终的 rev。
@@ -117,12 +117,12 @@ vendored Loader 经其 `internal` 约定消费模块系统——唯一调用点
| `dsh-client-runtime` | 会话对象层 + slots 服务 + store 引擎 | 插件,声明 `immediately` | 持续缩向纯会话对象层 |
| `dsh-client-ui-theme` | 主题 token/服务 | 插件,声明 `immediately`,外加 `./styles/*` 源码通道 | Theme Registry(另行裁定) |
| `dsh-client-i18n` | I18nService | 插件,声明 `immediately` | 按部署组合语言包 |
| `dsh-client-hmr` | 热重载驱动 | 插件,声明 `immediately`;仅进 dev 图 | 回滚;重连握手 |
| `dsh-client-hmr` | 热重载驱动 | 插件,声明 `immediately` | 回滚;重连握手 |
| ui-layout / ui-sidebar / ui-conversation / ui-trajectory | UI 功能 | 插件,按需到达 | conversation 域拆分;trajectory 真实现 |
## Consequences
wire 两侧跑着同一份治理实现;浏览器特有层只包含一套模块系统和一个重载插件。插件包只有一种形态,纯度门禁因此覆盖全部插件。依赖边与启动档位都与其所有者——manifest——同住,负责组合的 app 只握名册`--dev` 开关。各漂移缺陷类被结构性关死:共享清单人肉同步、装载顺序耦合、跨插件 import、名册/档位双重记账。浏览器原生脚本装载使插件网络资源、生成 bundle 与 TypeScript/TSX 源码保持标准映射,模块系统也只保留一个可替换的 `loadBundle` 钩子。
wire 两侧跑着同一份治理实现;浏览器特有层只包含一套模块系统和一个重载插件。插件包只有一种形态,纯度门禁因此覆盖全部插件。依赖边与启动档位都与其所有者——manifest——同住,负责组合的 app 只握名册。各漂移缺陷类被结构性关死:共享清单人肉同步、装载顺序耦合、跨插件 import、名册/档位双重记账。浏览器原生脚本装载使插件网络资源、生成 bundle 与 TypeScript/TSX 源码保持标准映射,模块系统也只保留一个可替换的 `loadBundle` 钩子。
接受的代价:vendored Loader 在浏览器里背着闲置机件(EntryTree 持久化是 no-op,分组/隔离未用);开发期每次修改插件都要付一次 bundle 重建加 fiber 重挂;图中 `inject` 行仅是信息性说明——激活的真相在服务层——因此不匹配会在 settled 扫描时浮出,而不是在图校验时被拦下;三个尚未升格的库在各自的 DI 转换落地之前保持静态 import 的导出面;每个 bundle 多出一份 sourcemap 产物,外部脚本失败也只能给出粗粒度的 URL 诊断,不能像显式 fetch 那样报告 HTTP 状态。
@@ -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/architecture/2026-07-24-single-harness-home-resolver.md
2026-07-24-single-harness-home-resolver.md: 1e128911dce0b50dc95722c6edd82cb322d18f3d
2026-07-24-single-harness-home-resolver.zh.md: 258a16e6ca139da191db564aae40d23d05ca46b7
2026-07-24-single-harness-home-resolver.md: 27db7e23b1ae3d2c9a05259bfb3047591589627d
2026-07-24-single-harness-home-resolver.zh.md: 5eec850c9c7ecc70b2327eacca422662ec39a9cc
@@ -6,13 +6,12 @@ English | [中文](2026-07-24-single-harness-home-resolver.zh.md)
## Problem
The harness had three inconsistent conventions for "where does DeepSeek Harness user data live":
The harness had two inconsistent conventions for "where does DeepSeek Harness user data live":
- `@deepseek-ai/dsh-home` resolved `configured ?? $DSH_HOME ?? ~/.dsh`.
- `@deepseek-ai/dsh-paths` shipped a **second** `resolveDshHome` with the same precedence plus tilde expansion — a near-duplicate of `dsh-home` that no gate flagged because the two lived in different packages and had already drifted (only one expanded tildes).
- `@deepseek-ai/dsh-telemetry`'s `globalConfigDir` used a *different* policy entirely: `DSH_CONFIG_HOME > $XDG_CONFIG_HOME/deepseek-harness > %APPDATA%/deepseek-harness > ~/.config/deepseek-harness`.
So most of the product parked everything under one `~/.dsh` root while telemetry alone stored its anonymous id elsewhere, under a `deepseek-harness` namespace that contradicts the repo-wide `dsh` shorthand (`DSH_HOME`, `@deepseek-ai/dsh-*`, `~/.dsh`). Two resolvers plus a divergent third policy means no single home fact.
Two resolvers for the same cross-cutting fact meant there was no single home policy.
## Decision
@@ -22,20 +21,18 @@ One resolver owns the harness home, in `@deepseek-ai/dsh-paths`, single-root:
explicit configured path > $DSH_HOME > ~/.dsh
```
An empty or whitespace-only `$DSH_HOME` is treated as unset, matching the guard telemetry's old resolver carried: without it `resolve('')` would silently place the home at the current working directory. The harness keeps all user data under one root; there is no XDG config/data/cache split. `dshHomePath(...segments)` joins deployment-owned children onto that root, and `dsh-app-boot` exposes it to Loader `!!js` config expressions before mounting entries, so shipped compositions derive `sessions` and `storages` without copying the resolver. `dshHomeDisplay()` names a resolved root symbolically for user-facing paths — `~/.dsh` for the default home, `$DSH_HOME` for any configured home — so the user-global `AGENTS.md` label never leaks an absolute machine path. It replaces workspace-context's bespoke default-vs-`$DSH_HOME` check.
An empty or whitespace-only `$DSH_HOME` is treated as unset; otherwise `resolve('')` would silently place the home at the current working directory. The harness keeps all user data under one root; there is no XDG config/data/cache split. `dshHomePath(...segments)` joins deployment-owned children onto that root, and `dsh-app-boot` exposes it to Loader `!!js` config expressions before mounting entries, so shipped compositions derive `sessions` and `storages` without copying the resolver. `dshHomeDisplay()` names a resolved root symbolically for user-facing paths — `~/.dsh` for the default home, `$DSH_HOME` for any configured home — so the user-global `AGENTS.md` label never leaks an absolute machine path. It replaces workspace-context's bespoke default-vs-`$DSH_HOME` check.
`@deepseek-ai/dsh-home` is deleted. Its three importers (`dsh-tool-bash`, `dsh-skill-local`, `dsh-agent-spine-demo`) now import `resolveDshHome` from `dsh-paths`. `dsh-telemetry`'s `globalConfigDir` delegates to `resolveDshHome`, dropping its second resolver, the `DSH_CONFIG_HOME` override, the XDG/`%APPDATA%` branches, and the `deepseek-harness` namespace; the anonymous id now lives directly under the harness home.
`@deepseek-ai/dsh-home` is deleted. Its three importers (`dsh-tool-bash`, `dsh-skill-local`, `dsh-agent-spine-demo`) import `resolveDshHome` from `dsh-paths`.
`dsh-telemetry` and its separate home policy are absent under the [SDK project toolchain removal](../simplification/2026-08-11-remove-sdk-project-toolchain.md), leaving this resolver as the sole home policy.
## Alternatives considered
**Leave the two `resolveDshHome` copies in place.** They had already drifted (one expands tildes, one didn't) and encode the same cross-cutting fact twice. Consolidation is the point of the `util/` layer; a duplicate resolver is a latent divergence bug.
**Adopt XDG (honor `$XDG_CONFIG_HOME`, or split config/data/cache into separate trees).** Considered and dropped in favor of one obvious root. A single `$DSH_HOME || ~/.dsh` ground truth matches `~/.claude` / `~/.aws`, needs no per-kind reclassification of every `~/.dsh` consumer, and leaves no resolver asymmetry to reconcile. Telemetry aligning onto the same root — rather than keeping its own XDG path — is precisely the divergence this removes.
**Keep telemetry's own config dir.** Its `deepseek-harness` namespace and separate XDG policy were the lone exception to the `dsh`/`~/.dsh` convention. Folding it onto the shared resolver is what makes "one home fact" true. The cost is that the anonymous id becomes scoped to `$DSH_HOME` rather than the machine: a project that points `DSH_HOME` at a repo-local path (or a command that loads a project `.env` before telemetry) gets a home-local id, so the id counts harness homes, not machines. This is accepted as the intended meaning of single-root — a relocated `$DSH_HOME` moves *all* harness state, telemetry identity included — and the module contract is stated as per-harness-home rather than per-machine. A machine-global identity that ignored `$DSH_HOME` would reintroduce exactly the second home policy this decision removes.
**Adopt XDG (honor `$XDG_CONFIG_HOME`, or split config/data/cache into separate trees).** Considered and dropped in favor of one obvious root. A single `$DSH_HOME || ~/.dsh` ground truth matches `~/.claude` / `~/.aws`, needs no per-kind reclassification of every `~/.dsh` consumer, and leaves no resolver asymmetry to reconcile.
## Consequences
- One home fact, one resolver. `dsh-paths` is the sole owner; the `util/` group loses the `home` package.
- Telemetry's anonymous id moves from `~/.config/deepseek-harness/telemetry.json` to the harness home (`~/.dsh/telemetry.json` by default). Under the pre-release "backends reject old formats" stance this needs no migration: an orphaned old id simply regenerates once, and the id is anonymous by construction.
- Telemetry drops Windows `%APPDATA%` handling. `resolveDshHome` uses `os.homedir()`, which is correct on Windows; the harness does not special-case `%APPDATA%` for its single root.
@@ -6,13 +6,12 @@ Status: implemented
## 问题
对于"DeepSeek Harness 用户数据存放在哪里"harness 里存在套互不一致的约定:
对于"DeepSeek Harness 用户数据存放在哪里"harness 里存在套互不一致的约定:
- `@deepseek-ai/dsh-home``configured ?? $DSH_HOME ?? ~/.dsh` 解析。
- `@deepseek-ai/dsh-paths` 又提供了**第二个** `resolveDshHome`,优先级相同但额外做了波浪号展开——它几乎是 `dsh-home` 的重复实现,却没有任何门禁发现,因为两者分属不同的包,而且早已漂移(只有一个会展开波浪号)。
- `@deepseek-ai/dsh-telemetry``globalConfigDir` 采用了*完全不同*的策略:`DSH_CONFIG_HOME > $XDG_CONFIG_HOME/deepseek-harness > %APPDATA%/deepseek-harness > ~/.config/deepseek-harness`
于是产品的大部分内容都停放在同一个 `~/.dsh` 根目录下,唯独 telemetry 把匿名 id 存到别处,落在一个 `deepseek-harness` 命名空间里,这与全仓库通行的 `dsh` 简写(`DSH_HOME``@deepseek-ai/dsh-*``~/.dsh`)相冲突。两个解析器再加上一个各行其是的第三套策略,意味着不存在单一的 home 事实
同一条横切事实有两个解析器,意味着不存在单一的 home 策略
## 决策
@@ -22,20 +21,18 @@ Status: implemented
explicit configured path > $DSH_HOME > ~/.dsh
```
空或仅含空白的 `$DSH_HOME` 被当作未设置处理,这与 telemetry 旧解析器所带的保护一致:若无此保护`resolve('')` 会悄悄把 home 落在当前工作目录。harness 把所有用户数据都放在同一个根目录下;不存在 XDG 的 config/data/cache 拆分。`dshHomePath(...segments)` 将部署负责的子路径拼接到该根目录下,`dsh-app-boot` 在挂载条目前向 Loader `!!js` 配置表达式暴露它,因此出厂组合无需复制解析器即可派生 `sessions``storages``dshHomeDisplay()` 为面向用户的路径以符号形式命名已解析的根目录——默认 home 显示为 `~/.dsh`,任何已配置的 home 显示为 `$DSH_HOME`——这样面向用户全局的 `AGENTS.md` 标签就绝不会泄露机器上的绝对路径。它取代了 workspace-context 中自定义的"默认值 vs `$DSH_HOME`"判断。
空或仅含空白的 `$DSH_HOME` 被当作未设置处理;否则`resolve('')` 会悄悄把 home 落在当前工作目录。harness 把所有用户数据都放在同一个根目录下;不存在 XDG 的 config/data/cache 拆分。`dshHomePath(...segments)` 将部署负责的子路径拼接到该根目录下,`dsh-app-boot` 在挂载条目前向 Loader `!!js` 配置表达式暴露它,因此出厂组合无需复制解析器即可派生 `sessions``storages``dshHomeDisplay()` 为面向用户的路径以符号形式命名已解析的根目录——默认 home 显示为 `~/.dsh`,任何已配置的 home 显示为 `$DSH_HOME`——这样面向用户全局的 `AGENTS.md` 标签就绝不会泄露机器上的绝对路径。它取代了 workspace-context 中自定义的"默认值 vs `$DSH_HOME`"判断。
`@deepseek-ai/dsh-home` 被删除。它的三个引用方(`dsh-tool-bash``dsh-skill-local``dsh-agent-spine-demo`现在`dsh-paths` 导入 `resolveDshHome``dsh-telemetry``globalConfigDir` 转而委托给 `resolveDshHome`,去掉了它的第二个解析器、`DSH_CONFIG_HOME` 覆盖项、XDG/`%APPDATA%` 分支以及 `deepseek-harness` 命名空间;匿名 id 现在直接存放在 harness home 之下。
`@deepseek-ai/dsh-home` 被删除。它的三个引用方(`dsh-tool-bash``dsh-skill-local``dsh-agent-spine-demo`)从 `dsh-paths` 导入 `resolveDshHome`
`dsh-telemetry` 及其独立 home 策略已随 [SDK 项目工具链移除](../simplification/2026-08-11-remove-sdk-project-toolchain.md)一并消失,因此该解析器是唯一的 home 策略。
## 备选方案
**保留两份 `resolveDshHome` 副本。** 它们早已漂移(一个展开波浪号,一个不展开),并把同一条横切事实编码了两遍。`util/` 层的意义正是在于合并,重复的解析器是一个潜在的分歧 bug。
**采用 XDG(遵从 `$XDG_CONFIG_HOME`,或把 config/data/cache 拆分到各自的目录树)。** 经过考虑后放弃,转而采用一个显而易见的根目录。单一的 `$DSH_HOME || ~/.dsh` 基准事实与 `~/.claude` / `~/.aws` 一致,无需对每个 `~/.dsh` 消费方按类别重新归类,也不留下任何需要协调的解析器不对称。telemetry 对齐到同一根目录——而不是保留自己的 XDG 路径——正是本决策所要消除的那种分歧。
**保留 telemetry 自己的 config 目录。** 它的 `deepseek-harness` 命名空间和独立的 XDG 策略是唯一违背 `dsh`/`~/.dsh` 约定的例外。把它折叠到共享解析器上,才让"单一 home 事实"成真。代价是匿名 id 的作用域从机器变成了 `$DSH_HOME`:若某个项目把 `DSH_HOME` 指向仓库本地路径(或某条命令在 telemetry 之前加载了项目的 `.env`),得到的就是 home 本地的 id,因此该 id 统计的是 harness home,而非机器。这被接受为单一根目录的应有含义——重定位 `$DSH_HOME` 会移动*全部* harness 状态,telemetry 身份也在其中——模块约定据此表述为 per-harness-home 而非 per-machine。一个忽略 `$DSH_HOME` 的机器级全局身份,恰恰会重新引入本决策所要消除的那第二套 home 策略。
**采用 XDG(遵从 `$XDG_CONFIG_HOME`,或把 config/data/cache 拆分到各自的目录树)。** 经过考虑后放弃,转而采用一个显而易见的根目录。单一的 `$DSH_HOME || ~/.dsh` 基准事实与 `~/.claude` / `~/.aws` 一致,无需对每个 `~/.dsh` 消费方按类别重新归类,也不留下任何需要协调的解析器不对称。
## 影响
- 单一 home 事实,单一解析器。`dsh-paths` 是唯一归属方;`util/` 组失去了 `home` 包。
- telemetry 的匿名 id 从 `~/.config/deepseek-harness/telemetry.json` 移到 harness home(默认为 `~/.dsh/telemetry.json`)。在预发布的"后端拒绝旧格式"立场下,这无需迁移:一个遗留的旧 id 只会重新生成一次,而且该 id 本就是匿名构造的。
- telemetry 去掉了 Windows `%APPDATA%` 处理。`resolveDshHome` 使用 `os.homedir()`,这在 Windows 上是正确的;harness 不会为它的单一根目录对 `%APPDATA%` 做特殊处理。
@@ -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/architecture/2026-07-24-web-config-tree-boot-and-transport-layering.md
2026-07-24-web-config-tree-boot-and-transport-layering.md: a730a14ac29b84c97c3f9c5b122eb907def4d389
2026-07-24-web-config-tree-boot-and-transport-layering.zh.md: 4fe315bb7673ba219286b176123ccbbe08f02f0d
2026-07-24-web-config-tree-boot-and-transport-layering.md: be0a75d98c3d0004e49ad574e7e0e37ba35259bb
2026-07-24-web-config-tree-boot-and-transport-layering.zh.md: 316cb0bc2ef23b440f52b35774c38a47f1e0570b
@@ -12,7 +12,7 @@ English | [中文](2026-07-24-web-config-tree-boot-and-transport-layering.zh.md)
## Decision
**Composition is one flat assembled tree.** `apps/cli/config/base.cordis.yml` plus `apps/cli/config/web.cordis.yml` holds every row — the host runtime (32 rows), the `api-gateway` row, the `webserver` row, and the `dsh.client` rows (the browser roster; the modules row is simultaneously a host row). No spine bundle: every plugin is one row and every config field is yml-editable. That stance later became repository-wide, with the rows both surfaces share factored into `apps/cli/config/base.cordis.yml` and each surface reduced to an overlay ([shared-base overlays](../simplification/2026-07-29-shared-base-config-overlays.md)). `--dev` appends the `dsh-client-hmr` row in code before the settle audit — prod and dev differ by exactly that row. Row order carries no load semantics; activation is service-availability driven. The shared audit rejects imports with no fiber, awaits only failed fibers to recover original activation errors, and reports services that leave a fiber `PENDING`; before throwing, it marks those exact rejection reasons through one process checkpoint so `installFailLoud` coalesces Loader's duplicate notification while unrelated unhandled rejections remain fatal. The Node app-boot artifact embeds `@cordisjs/plugin-include` while leaving `@cordisjs/plugin-loader` external, so the include's `EntryTree` and the host bind to one Loader peer instead of splitting a config tree across two Loader implementations.
**Composition is one flat assembled tree.** `apps/cli/config/base.cordis.yml` plus `apps/cli/config/web.cordis.yml` holds every row — the host runtime (32 rows), the `api-gateway` row, the `webserver` row, and the `dsh.client` rows (the browser roster; the modules row is simultaneously a host row). No spine bundle: every plugin is one row and every config field is yml-editable. That stance later became repository-wide, with the rows both surfaces share factored into `apps/cli/config/base.cordis.yml` and each surface reduced to an overlay ([shared-base overlays](../simplification/2026-07-29-shared-base-config-overlays.md)). The `dsh-client-hmr` row is an ordinary always-on bundle row (originally appended in code by `--dev`; the flag is retired). Row order carries no load semantics; activation is service-availability driven. The shared audit rejects imports with no fiber, awaits only failed fibers to recover original activation errors, and reports services that leave a fiber `PENDING`; before throwing, it marks those exact rejection reasons through one process checkpoint so `installFailLoud` coalesces Loader's duplicate notification while unrelated unhandled rejections remain fatal. The Node app-boot artifact embeds `@cordisjs/plugin-include` while leaving `@cordisjs/plugin-loader` external, so the include's `EntryTree` and the host bind to one Loader peer instead of splitting a config tree across two Loader implementations.
**Boot glue is a class pair.** `AppCLIEntry` (apps/cli) and `AppWebEntry` (the shell kernel) hold only what must exist independently of cordis: argv facts, the composed patch set, the parsed boot manifest, the module system instance, loading-page handles — everything else lives in plugins. `AppCLIEntry.run()` is three stages: layered env (ambient > cwd `.env` > `$DSH_HOME/.env`, closing the defect above) → patch composition → Loader include boot plus the activation audit. `AppWebEntry.run()` mirrors it browser-side: parse `window.__DSH_BOOT__` into a `BootManifest` (two views: npm-package rows for the module table, cordis-plugin rows for entry composition; malformed wire throws), build the module system, render the loading page, prefetch the `immediately` tier in parallel with Context/Loader setup, **await the prefetch before creating entries** (materialization is `tree.import`'s synchronous require, unprotected by fiber inject waiting; cross-package require edges such as i18n → runtime/client need every immediately-tier factory registered first — an empirically found 1025% boot race otherwise), adopt the modules entry, create the graph rows, settle, sweep.
@@ -12,7 +12,7 @@ Status: implemented
## 决策
**组合结果是一棵平铺配置树。** `apps/cli/config/base.cordis.yml``apps/cli/config/web.cordis.yml` 共同持有全部行——host 运行时(32 行)、`api-gateway` 行、`webserver` 行、`dsh.client` 行(浏览器 rostermodules 行同时是 host 行)。不做 spine bundle:每插件一行、每个 config 字段 yml 可改。这一立场后来推广到全仓:两个 surface 共享的配置项被抽取进 `apps/cli/config/base.cordis.yml`,各 surface 则收敛为一份 overlay[共享 base overlay](../simplification/2026-07-29-shared-base-config-overlays.md))。`--dev` 在 settle audit 之前由代码追加 `dsh-client-hmr` 行——prod 与 dev 的全部差异就是这一行。行序无装载语义;激活由服务可用性驱动。共享 audit 会拒绝没有 fiber 的 import、仅等待失败的 fiber 以恢复原始激活错误,并报告让 fiber 停在 `PENDING` 的服务;抛出错误前,审计会通过一个进程级检查点标记这些 rejection 的确切原因,从而让 `installFailLoud` 将 Loader 的重复通知合并为一次,而无关的未处理 rejection 仍然致命。Node app-boot 产物内嵌 `@cordisjs/plugin-include`,但将 `@cordisjs/plugin-loader` 保持为外部依赖,因此 include 的 `EntryTree` 与 host 会绑定到同一个 Loader peer,而不会让一棵配置树横跨两个 Loader 实现。
**组合结果是一棵平铺配置树。** `apps/cli/config/base.cordis.yml``apps/cli/config/web.cordis.yml` 共同持有全部行——host 运行时(32 行)、`api-gateway` 行、`webserver` 行、`dsh.client` 行(浏览器 rostermodules 行同时是 host 行)。不做 spine bundle:每插件一行、每个 config 字段 yml 可改。这一立场后来推广到全仓:两个 surface 共享的配置项被抽取进 `apps/cli/config/base.cordis.yml`,各 surface 则收敛为一份 overlay[共享 base overlay](../simplification/2026-07-29-shared-base-config-overlays.md))。`dsh-client-hmr` 行是普通的常开组合包行(最初由 `--dev` 在代码中追加;该旗标已废除)。行序无装载语义;激活由服务可用性驱动。共享 audit 会拒绝没有 fiber 的 import、仅等待失败的 fiber 以恢复原始激活错误,并报告让 fiber 停在 `PENDING` 的服务;抛出错误前,审计会通过一个进程级检查点标记这些 rejection 的确切原因,从而让 `installFailLoud` 将 Loader 的重复通知合并为一次,而无关的未处理 rejection 仍然致命。Node app-boot 产物内嵌 `@cordisjs/plugin-include`,但将 `@cordisjs/plugin-loader` 保持为外部依赖,因此 include 的 `EntryTree` 与 host 会绑定到同一个 Loader peer,而不会让一棵配置树横跨两个 Loader 实现。
**boot 胶水由两个类组成。** `AppCLIEntry`apps/cli)与 `AppWebEntry`(壳内核)只持有那些必须独立于 cordis、提前存在的东西:argv 事实、合成的 patch 集、解析出的 boot manifest(元数据清单)、模块系统实例、loading 页句柄——其余一律进插件。`AppCLIEntry.run()` 三段:分层 envambient > cwd `.env` > `$DSH_HOME/.env`,顺手关掉上述缺陷)→ patch 合成 → Loader include boot 加 activation audit。`AppWebEntry.run()` 在浏览器侧镜像它:把 `window.__DSH_BOOT__` 解析成 `BootManifest`(双视角:npm 包行给模块表、cordis 插件行给 entry 组合;畸形 wire 大声抛)、建模块系统、渲染 loading 页、immediately 层预取与 Context/Loader 准备并行、**create entry 之前等预取齐**(物化是 `tree.import` 的同步 require,不受 fiber inject 等待保护;i18n → runtime/client 这类跨包 require 边要求 immediately 层工厂全部注册完——否则有实测 10–25% 的 boot 竞态)、收编 modules entry、逐一创建图行、settle、sweep。
@@ -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/architecture/2026-07-25-web-client-session-scope-and-provide-channel.md
2026-07-25-web-client-session-scope-and-provide-channel.md: 561f5792e40ef740cdac56af5efb2d08fa15333c
2026-07-25-web-client-session-scope-and-provide-channel.zh.md: 78440131c4e09c9a458009fbe5a2a34a707a481c
2026-07-25-web-client-session-scope-and-provide-channel.md: cca090096dfff8dee1f221a87cdf406252a52a34
2026-07-25-web-client-session-scope-and-provide-channel.zh.md: 701a4f585c41a23be12883417c5ae0074431096c
@@ -106,7 +106,7 @@ Slot scope is the closed set `root | session-maybe | session`:
### Host wire smalls
- The summary `blank` column and the `host/session-added` frame's `blank` field (see the blank bit above).
- The SSE frame `host/commands-changed` (a pure invalidation signal); the client routes it into the typed events `commands/changed` and `connection/reset` (broadcast after each connection generation is established; wire-derived caches uniformly treat prior state as stale).
- The SSE frame `host/commands-changed` (a pure invalidation signal); the client routes it into the typed events `commands/changed` and `connection/reset` (broadcast after each connection generation is established; wire-derived caches uniformly treat prior state as stale). The commands frame and its typed client event were later replaced by verbatim forwarding of `commands/change` through `ctx.remote.$on` ([forwarded Remote events](2026-08-10-remote-event-delivery.md)); `connection/reset` is unchanged, and the invalidation-not-diffing contract this bullet states still holds.
- `command.list/execute` and `skill.list` are uniformly single-addressed by `sessionId` (a session always has an Agent; `agentFor`'s resume semantics come ready-made); the command-surface narrative lives in the [command surfaces note](2026-07-25-web-command-surfaces-and-assembly.md).
- The `session.create` request shape: workspaceId/cwd as either-or, plus an optional caller-preallocated sessionId (a same-id same-cwd retry is idempotent; a different cwd reports `session-conflict`).
@@ -106,7 +106,7 @@ slot scope 是闭集 `root | session-maybe | session`
### host wire 小件
- summary `blank` 列与 `host/session-added``blank` 字段(见上文 blank 位)。
- SSEServer-Sent Events)帧 `host/commands-changed`(纯失效信号);client 路由为类型事件 `commands/changed``connection/reset`(连接代建立后广播,wire 派生缓存一律视旧态为陈旧)。
- SSEServer-Sent Events)帧 `host/commands-changed`(纯失效信号);client 路由为类型事件 `commands/changed``connection/reset`(连接代建立后广播,wire 派生缓存一律视旧态为陈旧)。 该 commands 帧及其类型化 client 事件后来被「`commands/change``ctx.remote.$on` 原样转发」取代([转发的 Remote 事件](2026-08-10-remote-event-delivery.md));`connection/reset` 不变,本条陈述的「失效而非差分」契约依然成立。
- `command.list/execute``skill.list` 一律 `sessionId` 单址(会话恒有 Agent`agentFor` 的恢复语义现成);命令面叙述见[命令业务面 note](2026-07-25-web-command-surfaces-and-assembly.md)。
- `session.create` 请求形状:workspaceId/cwd 二选一 + 可选调用方预分配 sessionId(同 id 同 cwd 重试幂等,异 cwd 报 `session-conflict`)。
@@ -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/architecture/2026-07-26-subprocess-seam.md
2026-07-26-subprocess-seam.md: 7899af56259d39a4e3f924bcba673c8efa99c682
2026-07-26-subprocess-seam.zh.md: d9cbc0ebf33bc785984b0a9bd58fa8ebc6aab436
2026-07-26-subprocess-seam.md: f43b55b0b760c2aabe317abacdb800b755de059b
2026-07-26-subprocess-seam.zh.md: df8c3ddab80933882bf3587a9f01e019eb721a87
@@ -17,11 +17,11 @@ A new `subprocess/` capability family owns "run and manage a process"; the bash
- **`dsh-bash-local` (Consumer)** — `inject: ['subprocess']`; maps each resolved `BashExecSpec` onto a `SubprocessSpawnSpec` (`['bash', '-c', command]`), keeps its config, `resolve()` defaulting, fused-deadline `timedOut`/`aborted` classification, the `[stderr]`-marked background read merge with its consuming cursor, and the `onProcessDone` subclass hook. `dsh-bash-sandbox` is unchanged apart from redeclaring the inherited inject; it still wraps at the command-string level and re-enters the inherited spawn path.
- **`dsh-bash` (Service Definition)** — re-exports the moved vocabulary from `dsh-subprocess`, so no bash Consumer changes an import; `BashExecRequest`/`BashExecSpec`/`BashProcess` and the sandbox facts remain bash-owned.
Every composition that loads a bash executor now also loads `@deepseek-ai/dsh-subprocess-local` (CLI, examples, python bundled runtime, create-sdk's bash feature resources, inline test configs).
Every composition that loads a bash executor also loads `@deepseek-ai/dsh-subprocess-local` (CLI, examples, the Python bundled runtime, and inline test configs).
Background-process lifetime moved from the executor to the subprocess service: the executor no longer retains a live-process set, so an executor reload leaves background work running and readable, and composition teardown (the service's disposal) remains the kill-and-join boundary. One behavioral contract shifted with it: a background spawn failure can no longer be buffered as fake stderr inside the plumbing (the service rejects `done` and buffers nothing for a process that never ran), so the executor injects the `spawn failed: …` note into exactly one `readOutput()` delta.
Observed stream and lifecycle needs then moved the eligible process consumers onto the seam: LSP uses piped protocol streams plus a collected stderr tail; the ACP backend uses piped ndjson, inherited stderr, and a consumer-owned stdin-EOF disposal ladder; PTY uses `spawnTerminal()` while keeping readiness and terminal policy. `dsh-subagent-subprocess` and the private LSP tree helpers were deleted. MCP transport spawning, the SDK package-manager runner, synchronous TUI Git probing, and dependency-light test-support launchers remain outside by ownership or execution shape; their production callers share the scrub where applicable.
Observed stream and lifecycle needs then moved the eligible process consumers onto the seam: LSP uses piped protocol streams plus a collected stderr tail; the ACP backend uses piped ndjson, inherited stderr, and a consumer-owned stdin-EOF disposal ladder; PTY uses `spawnTerminal()` while keeping readiness and terminal policy. `dsh-subagent-subprocess` and the private LSP tree helpers were deleted. MCP transport spawning and dependency-light test-support launchers remain outside by ownership or execution shape; their production callers share the scrub where applicable.
## Alternatives considered
@@ -31,7 +31,7 @@ Observed stream and lifecycle needs then moved the eligible process consumers on
**Use one `stdio: 'pipe' | 'inherit' | 'collect'` mode for all streams.** Rejected because real consumers mix modes per stream: LSP uses pipe/pipe/collect, ACP uses pipe/pipe/inherit, and Bash uses data/collect/collect.
**Route every process launch through `ctx.subprocess`.** Rejected because the MCP SDK owns its transport spawn, the SDK wizard has no Cordis context and needs inherited redirection, the TUI probe is synchronous, and support launchers deliberately stay independent of product seams. PTY allocation did move behind `spawnTerminal()` because the provider, not the consumer, owns that substrate-specific primitive.
**Route every process launch through `ctx.subprocess`.** Rejected because the MCP SDK owns its transport spawn and support launchers deliberately stay independent of product seams. PTY allocation did move behind `spawnTerminal()` because the provider, not the consumer, owns that substrate-specific primitive.
**Put `run_in_background`/task semantics into the subprocess capability seam instead.** Rejected: that boundary already exists — `ctx.tasks` owns ids, ownership, and notices, and the bash tool adapts a `BashProcess` into task hooks. The subprocess seam sits *below* the bash executor, not beside the task registry.
@@ -17,11 +17,11 @@ Status: implemented
- **`dsh-bash-local`Consumer**——`inject: ['subprocess']`;把每个解析后的 `BashExecSpec` 映射为一个 `SubprocessSpawnSpec``['bash', '-c', command]`),并保留自身配置、`resolve()` 默认值补全、基于融合 deadline 的 `timedOut`/`aborted` 分类、带 `[stderr]` 标记的后台读取合并及其消费游标,以及 `onProcessDone` 子类钩子。`dsh-bash-sandbox` 除了重新声明继承来的 inject 之外没有变化;它仍在命令字符串层面做包装,并重新进入继承的 spawn 路径。
- **`dsh-bash`Service Definition**——把迁走的词汇从 `dsh-subprocess` 重导出,因此没有任何 bash Consumer 需要改动导入;`BashExecRequest`/`BashExecSpec`/`BashProcess` 与沙箱事实仍归 bash 所有。
如今,每个加载 bash 执行器的组合都同时加载 `@deepseek-ai/dsh-subprocess-local`:CLI(命令行界面)、各示例、Python 捆绑运行时、create-sdk 的 bash 功能资源,以及各内联测试配置。
每个加载 bash 执行器的组合都同时加载 `@deepseek-ai/dsh-subprocess-local`:CLI(命令行界面)、各示例、Python 捆绑运行时以及各内联测试配置。
后台进程的存续期从执行器移到了管理器:执行器不再保有存活进程集合,于是重载执行器后,后台工作会继续运行且仍可读取,而组合拆除(管理器的 dispose)仍是先终止再等待退出的边界。一条行为约定随之挪动:后台 spawn 失败不再能在管道内部被缓冲成伪造的 stderr(对一个从未真正运行的进程,管理器会 reject `done`,且不缓冲任何内容),因此执行器把 `spawn failed: …` 提示注入恰好一个 `readOutput()` 增量。
基于已观察到的流与生命周期需求,具备条件的进程消费方随后迁到该 seam:LSP 使用管道化协议流加收集式 stderr 尾部;ACPAgent Client Protocol)后端使用管道化 ndjson、继承式 stderr 和消费方拥有的 stdin-EOF dispose 阶梯;PTY 使用 `spawnTerminal()`,同时保留就绪与终端策略。`dsh-subagent-subprocess` 与 LSP 私有进程树辅助函数均被删除。MCP 传输 spawn、SDK 包管理器运行器、同步 TUI Git 探测和刻意保持轻依赖的 test-support 启动器因所有权或执行形状仍留在外部;适用的生产调用方共享凭据清除。
基于已观察到的流与生命周期需求,具备条件的进程消费方随后迁到该 seam:LSP 使用管道化协议流加收集式 stderr 尾部;ACPAgent Client Protocol)后端使用管道化 ndjson、继承式 stderr 和消费方拥有的 stdin-EOF dispose 阶梯;PTY 使用 `spawnTerminal()`,同时保留就绪与终端策略。`dsh-subagent-subprocess` 与 LSP 私有进程树辅助函数均被删除。MCP 传输 spawn 和刻意保持轻依赖的 test-support 启动器因所有权或执行形状仍留在外部;适用的生产调用方共享凭据清除。
## 曾考虑的替代方案
@@ -31,7 +31,7 @@ Status: implemented
**用单个 `stdio: 'pipe' | 'inherit' | 'collect'` 模式统一全部流。**否决:真实消费方按流混用模式——LSP 使用 pipe/pipe/collectACP 使用 pipe/pipe/inheritBash 使用 data/collect/collect。
**把每一次进程启动都路由到 `ctx.subprocess`。**否决:MCP SDK 拥有其传输 spawnSDK 向导没有 Cordis 上下文且需要继承式重定向,TUI 探测是同步的,support 启动器则刻意独立于产品 seam。PTY 分配迁到 `spawnTerminal()`,因为这项底层专用原语归提供方而非消费方所有。
**把每一次进程启动都路由到 `ctx.subprocess`。**否决:MCP SDK 拥有其传输 spawn,support 启动器则刻意独立于产品 seam。PTY 分配迁到 `spawnTerminal()`,因为这项底层专用原语归提供方而非消费方所有。
**改把 `run_in_background`/任务语义放进 subprocess 能力 seam。**否决:那条边界已经存在。`ctx.tasks` 拥有 id、所有权与通知,bash 工具则把 `BashProcess` 适配成任务钩子。subprocess seam 位于 bash 执行器*之下*,而不是与任务注册表并列。
@@ -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/architecture/2026-07-26-task-registry-seam.md
2026-07-26-task-registry-seam.md: d5864d86577839c77ab27d70c9dc1c6a79685d56
2026-07-26-task-registry-seam.zh.md: 096cf41c614d1e9e15b6421412e9dc8160e38099
2026-07-26-task-registry-seam.md: b3cbae94c2d90b0834fd3221a153808ffc763258
2026-07-26-task-registry-seam.zh.md: 2551b503069abe237d1b95610531af256f23b508
@@ -12,8 +12,8 @@ The [background-task runtime](2026-06-20-generic-long-running-tool-runtime.md) s
`tasks/` is now a three-package capability family in the bash-trio shape:
- **`@deepseek-ai/dsh-tasks` (Service Definition)** — the abstract `TaskService extends Service` owning `ctx.tasks`, the eight-method contract (`start`, `list`, `get`, `read`, `kill`, `wait`, `onTaskDone`, `attachController`), all vocabulary types (`TaskId`, `TaskKindMap`, `TaskStart`, `TaskHooks`, `TaskOutcome`, `TaskSnapshot`, `TaskRead`, `TaskDoneListener`), and the snapshot invariant companion. The class-level JSDoc states the semantics every Service provider owes: registrations outlive producer and controller fibers, owned access is session-fenced, settlement is first-wins with contained listeners, and `start` refuses work while no attached task controller serves the spec's owner (controllers and listeners are scope-layered, so one process-wide registry answers both questions per owner).
- **`@deepseek-ai/dsh-tasks-local` (Service provider)** — `LocalTaskService`, the process-local registry moved verbatim: the in-memory store, per-kind counters, waiter bookkeeping, `TASK_WAIT_TIMEOUT` deadline code, owner-cleanup effects, and force-fail teardown. The `dsh-timeout` dependency moves here with it; the Service Definition package has no provider dependencies.
- **`@deepseek-ai/dsh-tasks` (Service Definition)** — the abstract `TaskService extends Service` owning `ctx.tasks`, the nine-method contract (`start`, `list`, `get`, `read`, `kill`, `wait`, `onTaskDone`, `onTasksChanged`, `attachController`), all vocabulary types (`TaskId`, `TaskKindMap`, `TaskStart`, `TaskHooks`, `TaskOutcome`, `TaskSnapshot`, `TaskRead`, `TaskDoneListener`), and the snapshot invariant companion. The class-level JSDoc states the semantics every Service provider owes: registrations outlive producer and controller fibers, owned access is session-fenced, settlement is first-wins with contained listeners, and `start` refuses work while no attached task controller serves the spec's owner (controllers and listeners are scope-layered, so one process-wide registry answers both questions per owner).
- **`@deepseek-ai/dsh-tasks-local` (Service provider)** — `LocalTaskService`, the process-local registry: the in-memory store, per-kind id counters, waiter bookkeeping, `TASK_WAIT_TIMEOUT` deadline code, owner-cleanup effects, force-fail teardown, and the default-10 configurable admission policy. Admission derives `running` plus `stopping` capacity from the same records per exact owner, with one unowned bucket; it adds no public count or second state owner. The `dsh-timeout` dependency and Schemastery-owned provider config live here; the Service Definition package has no provider dependencies.
- **`@deepseek-ai/dsh-tool-tasks` (Consumer)** — unchanged; it injects `'tasks'` and never imports provider types.
Compositions load `dsh-tasks-local` where they previously loaded `dsh-tasks` (the CLI cordis.yml row, `agent-spine-demo`, test harnesses, the tool-catalog generator boot). Producer misconfiguration diagnostics ("background tasks unavailable: load …") name `dsh-tasks` — the Service Definition package that declares the absent `ctx.tasks` service — and the Service Definition package's own APIs (its README and the direct-mount fence) point at Service providers, so the producer message stays correct when another backend becomes the recommended default. Producers, `TaskKindMap` declaration merges, and the controller keep importing `@deepseek-ai/dsh-tasks` only.
@@ -22,7 +22,7 @@ The seam keeps the in-process contract semantics unchanged: `TaskStart.run()` st
## Alternatives considered
**Keep the concrete service until a second backend exists (status quo).** This was the original runtime note's position: extracting a Service Definition before a second provider risks freezing the wrong boundary. It lost because the boundary is no longer speculative — the eight service methods and their semantics have been stable across every producer integration since introduction, they are exactly the API `dsh-tool-tasks` and the producers already program against, and the repository convention treats swappable capabilities as three packages by default. The residual risk (a durable backend needing contract changes) is unchanged by the split: those changes would land in the Service Definition package either way, and today they would also churn every Consumer's provider dependency.
**Keep the concrete service until a second backend exists (status quo).** This was the original runtime note's position: extracting a Service Definition before a second provider risks freezing the wrong boundary. It lost because the boundary is no longer speculative — the nine service methods and their semantics have been stable across every producer integration since introduction, they are exactly the API `dsh-tool-tasks` and the producers already program against, and the repository convention treats swappable capabilities as three packages by default. The residual risk (a durable backend needing contract changes) is unchanged by the split: those changes would land in the Service Definition package either way, and today they would also churn every Consumer's provider dependency.
**Service-Definition-only extraction inside one package (export an abstract class beside the concrete one).** Rejected because it separates nothing operationally: Consumers still depend on the package that carries the provider and its dependencies, and a replacement backend still cannot ship without the local one in its graph. The package boundary is the unit of independent evolution here.
@@ -30,6 +30,6 @@ The seam keeps the in-process contract semantics unchanged: `TaskStart.run()` st
## Consequences
Bought: the task registry now matches the repository-wide seam shape; a durable, remote, or instrumented registry is a sibling Service provider implementing eight abstract methods, and no producer, controller, or `TaskKindMap` extender changes when one lands. The Service Definition README states the contract; the provider README owns the lifecycle bookkeeping facts. The registry behavior suite (owner cleanup, settlement, waits, teardown) lives with `dsh-tasks-local`; the Service Definition package keeps a stub-subclass test pinning registration under `ctx.tasks` and single-service duplication behavior, plus the probe-based invariant suite.
Bought: the task registry now matches the repository-wide seam shape; a durable, remote, or instrumented registry is a sibling Service provider implementing nine abstract methods, and no producer, controller, or `TaskKindMap` extender changes when one lands. The Service Definition README states the contract; the provider README owns the lifecycle bookkeeping facts. The registry behavior suite (owner cleanup, settlement, waits, teardown) lives with `dsh-tasks-local`; the Service Definition package keeps a stub-subclass test pinning registration under `ctx.tasks` and single-service duplication behavior, plus the probe-based invariant suite.
Cost: one more package (manifest, tsconfig, README, invariant companion), and compositions must name the Service provider package. `abstract` erases at runtime and this package name used to be the mountable registry, so the Service Definition constructor fails loudly when mounted directly — a stale composition row gets "load a Service provider such as @deepseek-ai/dsh-tasks-local" at load time instead of a half-registered `ctx.tasks` failing far from the misconfiguration.
@@ -12,8 +12,8 @@ Status: implemented
`tasks/` 如今是一个 bash 三件套形态的三包能力家族:
- **`@deepseek-ai/dsh-tasks`Service Definition**——抽象的 `TaskService extends Service`,拥有 `ctx.tasks`个方法的约定(`start``list``get``read``kill``wait``onTaskDone``attachController`)、全部词汇类型(`TaskId``TaskKindMap``TaskStart``TaskHooks``TaskOutcome``TaskSnapshot``TaskRead``TaskDoneListener`),以及快照不变式配套插件。类级 JSDoc 陈述了每个 Service provider 都必须兑现的语义:注册的存续期长于生产方与控制器的 fiber,有所有者的访问以会话为界,结算遵循首次结果优先且监听器错误被隔离,并且当没有任何已附加的任务控制器服务于 spec 的所有者时 `start` 拒绝启动工作(控制器与监听器按 scope 分层,因此一个进程级注册表能逐所有者地回答这两个问题)。
- **`@deepseek-ai/dsh-tasks-local`Service provider**——`LocalTaskService`,即原样迁移的进程内注册表:内存存储、按 kind 划分的计数器、等待方簿记、`TASK_WAIT_TIMEOUT` deadline 代码、所有者清理 effect,以及强制失败的拆除`dsh-timeout` 依赖随之迁入此包;Service Definition 包不含任何提供方依赖。
- **`@deepseek-ai/dsh-tasks`Service Definition**——抽象的 `TaskService extends Service`,拥有 `ctx.tasks`个方法的约定(`start``list``get``read``kill``wait``onTaskDone``onTasksChanged``attachController`)、全部词汇类型(`TaskId``TaskKindMap``TaskStart``TaskHooks``TaskOutcome``TaskSnapshot``TaskRead``TaskDoneListener`),以及快照不变式配套插件。类级 JSDoc 陈述了每个 Service provider 都必须兑现的语义:注册的存续期长于生产方与控制器的 fiber,有所有者的访问以会话为界,结算遵循首次结果优先且监听器错误被隔离,并且当没有任何已附加的任务控制器服务于 spec 的所有者时 `start` 拒绝启动工作(控制器与监听器按 scope 分层,因此一个进程级注册表能逐所有者地回答这两个问题)。
- **`@deepseek-ai/dsh-tasks-local`Service provider**——`LocalTaskService`,即进程内注册表:内存存储、按 kind 划分的 id 计数器、等待方簿记、`TASK_WAIT_TIMEOUT` deadline 代码、所有者清理 effect强制失败的拆除,以及默认值为 10 且可配置的准入策略。准入从同一组记录中按确切 owner 派生 `running``stopping` 容量,并为无 owner 任务使用一个共享桶;它不新增公开计数或第二个状态 owner。`dsh-timeout` 依赖与由 Schemastery 管理的 Service provider 配置都位于此包;Service Definition 包不含任何提供方依赖。
- **`@deepseek-ai/dsh-tool-tasks`(Consumer)**——保持不变;它注入 `'tasks'`,从不导入提供方类型。
各组合在原先加载 `dsh-tasks` 的位置改为加载 `dsh-tasks-local`CLI(命令行界面)的 cordis.yml 配置项、`agent-spine-demo`、各测试 harness,以及工具目录生成器的启动流程。生产方的配置错误诊断信息(「background tasks unavailable: load …」)点名 `dsh-tasks`——即声明缺失的 `ctx.tasks` 服务的 Service Definition 包;Service Definition 包自身的 API(其 README 与直接挂载防线)会指向各 Service provider,因此当另一个后端日后成为推荐默认时,生产方的消息依旧正确。生产方、`TaskKindMap` 声明合并和控制器仍然只导入 `@deepseek-ai/dsh-tasks`
@@ -22,7 +22,7 @@ Status: implemented
## 曾考虑的替代方案
**在第二个后端出现之前保持具体服务(维持现状)。**这正是运行时 Agent Note 当初的立场:在第二个 Service provider 出现前抽取 Service Definition,可能固化错误的边界。该方案落选,因为这条边界已不再是臆测:个服务方法及其语义自引入以来在每一次生产方集成中都保持稳定,它们正是 `dsh-tool-tasks` 与各生产方已经面向编程的那套接口,而且仓库约定默认将可替换能力拆成三个包。剩余风险(持久化后端可能需要变更约定)不因这次拆分而改变:无论拆分与否,这类变更都会落在 Service Definition 包里;而若维持现状,它们今天还会连带搅动每个 Consumer 的提供方依赖。
**在第二个后端出现之前保持具体服务(维持现状)。**这正是运行时 Agent Note 当初的立场:在第二个 Service provider 出现前抽取 Service Definition,可能固化错误的边界。该方案落选,因为这条边界已不再是臆测:个服务方法及其语义自引入以来在每一次生产方集成中都保持稳定,它们正是 `dsh-tool-tasks` 与各生产方已经面向编程的那套接口,而且仓库约定默认将可替换能力拆成三个包。剩余风险(持久化后端可能需要变更约定)不因这次拆分而改变:无论拆分与否,这类变更都会落在 Service Definition 包里;而若维持现状,它们今天还会连带搅动每个 Consumer 的提供方依赖。
**在单个包内仅抽取 Service Definition(在具体类旁导出一个抽象类)。**否决,因为它在运作层面并未分离任何东西:Consumer 依然依赖携带 Service provider 及其依赖项的那个包,而替换后端若不把本地 Service provider 纳入自身依赖图,就仍然无法发布。在这里,包边界才是独立演进的单位。
@@ -30,6 +30,6 @@ Status: implemented
## 后果
换来的是:任务注册表如今与全仓库通行的 seam 形态一致;持久化、远程或带插桩的注册表将是一个实现个抽象方法的同级 Service provider,这样的注册表落地时,任何生产方、控制器或 `TaskKindMap` 扩展方都无需改动。Service Definition 的 README 陈述约定;生命周期簿记方面的事实归 Service provider 的 README 所有。注册表行为测试套件(所有者清理、结算、等待、拆除)随 `dsh-tasks-local` 存放;Service Definition 包保留一个桩子类(stub subclass)测试,固定 `ctx.tasks` 下的注册行为与单一服务的重复注册行为,外加基于探针的不变式测试套件。
换来的是:任务注册表如今与全仓库通行的 seam 形态一致;持久化、远程或带插桩的注册表将是一个实现个抽象方法的同级 Service provider,这样的注册表落地时,任何生产方、控制器或 `TaskKindMap` 扩展方都无需改动。Service Definition 的 README 陈述约定;生命周期簿记方面的事实归 Service provider 的 README 所有。注册表行为测试套件(所有者清理、结算、等待、拆除)随 `dsh-tasks-local` 存放;Service Definition 包保留一个桩子类(stub subclass)测试,固定 `ctx.tasks` 下的注册行为与单一服务的重复注册行为,外加基于探针的不变式测试套件。
代价是:多出一个包,即多一份 manifest(元数据清单)、tsconfig、README 与不变式配套插件;同时各组合必须点名 Service provider 包。`abstract` 在运行时会被擦除,而这个包名过去正是可挂载的具体注册表,因此直接挂载 Service Definition 时,其构造函数会明确报错——一条陈旧的组合配置行会在加载时得到「load a Service provider such as @deepseek-ai/dsh-tasks-local」,而不是一个未完整注册的 `ctx.tasks` 在远离错误配置处才失败。
@@ -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/architecture/2026-07-29-dsh-source-launch-tsx-esm.md
2026-07-29-dsh-source-launch-tsx-esm.md: b2428602a780f2880f0f803ba59b16a76b39790e
2026-07-29-dsh-source-launch-tsx-esm.zh.md: 866bc8886725788e6e619f9507f5c8ccab63f82d
2026-07-29-dsh-source-launch-tsx-esm.md: effa61d8e0f54023d6971f73149214683d79b8d6
2026-07-29-dsh-source-launch-tsx-esm.zh.md: 055b374af20559a79bd912918f2e9e0e1cf26a24
@@ -14,7 +14,7 @@ Startup latency also mattered: the off-thread `module.register()` hooks worker s
## Decision
The `dsh` TUI, Web, and headless source launches run `node --import tsx/esm`: tsx's ESM-only hook owns both TypeScript transformation and tsconfig `paths` projection. The root `dsh` script completes the repository build, then uses that vector from the repository root. The CJS hook stays off because the CLI source graph is ESM-only; measured runtime launch to the TUI banner is ~0.7s versus ~1.1s under the full tsx default and ~0.75s under the removed native chain.
The `dsh` TUI, Web, and headless source launches run `node --import tsx/esm`: tsx's ESM-only hook owns both TypeScript transformation and tsconfig `paths` projection. The root `dsh` script uses that vector directly from the repository root; artifact generation is a separate operation under the [source-launch/build separation decision](../simplification/2026-08-12-separate-source-launch-from-build.md). The CJS hook stays off because the CLI source graph is ESM-only; measured runtime launch to the TUI banner is ~0.7s versus ~1.1s under the full tsx default and ~0.75s under the removed native chain.
`scripts/tspath-loader.ts` and `apps/cli/src/tsconfig-paths-loader.ts` are deleted. With them went the loader's runtime rule of mapping a workspace import only for declared runtime dependencies — tsx applies the `paths` map unconditionally. Declaration completeness now rests on the static gates alone: `verify-cordis-config` for configured bare plugins, and workspace constraints for manifests. (That runtime rule found real bugs: `dsh-plan-mode` and `dsh-tool-tasks` imported `@deepseek-ai/dsh-llm` while declaring it only in devDependencies; since fixed.)
@@ -14,7 +14,7 @@ Status: implemented
## 决策
`dsh` 的 TUI、Web 与无头源码启动运行 `node --import tsx/esm`:由 tsx 的 ESM-only 钩子同时负责 TypeScript 转换与 tsconfig `paths` 投影。根目录的 `dsh` 脚本先完成仓库构建,然后从仓库根目录使用同一启动方式。CJS 钩子保持关闭,因为 CLI(命令行界面)源码图是纯 ESM;实测运行时启动至 TUI banner 耗时约 0.7s,对比完整 tsx 默认形态约 1.1s、已移除的原生链约 0.75s。
`dsh` 的 TUI、Web 与无头源码启动运行 `node --import tsx/esm`:由 tsx 的 ESM-only 钩子同时负责 TypeScript 转换与 tsconfig `paths` 投影。根目录的 `dsh` 脚本直接从仓库根目录使用同一启动方式;产物生成是独立操作,由[源码启动与构建分离决策](../simplification/2026-08-12-separate-source-launch-from-build.md)规定。CJS 钩子保持关闭,因为 CLI(命令行界面)源码图是纯 ESM;实测运行时启动至 TUI banner 耗时约 0.7s,对比完整 tsx 默认形态约 1.1s、已移除的原生链约 0.75s。
`scripts/tspath-loader.ts``apps/cli/src/tsconfig-paths-loader.ts` 已删除。随之消失的还有该 loader「仅为已声明运行时依赖映射 workspace import」的运行时规则——tsx 无条件应用 `paths` 映射。声明完整性现在仅由静态门禁保障:配置的裸插件走 `verify-cordis-config`manifest(元数据清单)走 workspace constraints。(该运行时规则确实发现过真实缺陷:`dsh-plan-mode``dsh-tool-tasks` 导入 `@deepseek-ai/dsh-llm` 却只声明在 devDependencies;后已修复。)
@@ -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/architecture/2026-07-29-package-regrouping.md
2026-07-29-package-regrouping.md: 30fc45a122263350b4a2ad1998850f631c20f9b8
2026-07-29-package-regrouping.zh.md: a3a9a11ec71b7f894dcea7c733eb39a80b71ac50
2026-07-29-package-regrouping.md: 6b85fafaebd75b051d239966a30bb81bdaf5522f
2026-07-29-package-regrouping.zh.md: 06eb210e318833d9651af2c4f0e4d792799a2018
@@ -10,29 +10,26 @@ The two-level `packages/<group>/<pkg>` hierarchy ([original decision](../../arch
- `ui/` mixed four unrelated planes: the human terminal channel (`tui`), the SDK's JSON-RPC server half (`jsonrpc`, whose peer dependency on `dsh-sdk-protocol` binds it to the SDK wire stack), the human-interaction seams (`user-interaction`, `user-approval`, `permission`, `tool-ask-user`, `commands`), and channel-neutral boot glue (`app-boot`). Its own README narrated the mixture instead of stating a role.
- The session family was fragmented across five groups — `session-persistence/`, `session-projection/`, `session-query/`, `session-title/`, and `telemetry/` — although the measured dependency edges tie them together (query → persistence, title → projection, projection → persistence; see [docs/module-graph.md](../../../../docs/module-graph.md)).
- Two group names collided with unrelated packages: `telemetry/` (session reporting) vs `dsh-telemetry` (launcher-side SDK telemetry), and `timeout/` (a tool-call guard) vs `util/timeout` (the generic promise utility).
- The `timeout/` group for a tool-call guard collided with `util/timeout`, the generic promise utility.
- `cordis/` named its group after the framework every package is built on, so the name discriminated nothing; its single package `tool-cordis` is the runtime self-modification toolset.
- The old `sdk/` folder names were inconsistent: `sdk/sdk-client` and `sdk/sdk-protocol` repeated the group name while `sdk/telemetry`, `sdk/helper`, and `sdk/scripts` did not.
The north star for the regrouping: **closely clustered packages share a group.** A cluster is measured — peer-dependency edges and co-change — not thematic. An isolated seam family may stand alone as a small group; the failure mode to avoid is the grab-bag whose name describes no single role.
## Decision
Six groups are recomposed; every other group keeps its prior boundary and contents (the dependency analysis confirmed the capability families — `bash/`, `pty/`, `code-runtime/`, `sandbox/`, `subprocess/`, `fs/`, `lsp/`, `web/`, `skill/`, and the rest — were already drawn correctly). npm package names did not change; the folder tree carries the whole change.
Five regrouping decisions remain current; every other group keeps its prior boundary and contents (the dependency analysis confirmed the capability families — `bash/`, `pty/`, `code-runtime/`, `sandbox/`, `subprocess/`, `fs/`, `lsp/`, `web/`, `skill/`, and the rest — were already drawn correctly). The original sixth decision collected the SDK project initializer, launcher tooling, and runtime JSON-RPC packages under `scaffold/`; [removing that unreleased toolchain](../simplification/2026-08-11-remove-sdk-project-toolchain.md) superseded it by deleting the project tooling and moving the surviving runtime trio to `sdk/`.
| Group | Members (folder names) | From |
|---|---|---|
| `session/` | session-persistence, session-persistence-jsonl, session-persistence-sqlite, session-checkpoint-policy, session-projection, session-projection-cache, session-title, session-title-llm, session-title-first-message-llm, session-title-all-messages-llm, session-telemetry, session-telemetry-otel | `session-persistence/` + `session-projection/` + `session-title/` + `telemetry/` |
| `interaction/` | user-interaction, user-approval, permission, tool-ask-user, commands, tui | `ui/` |
| `boot/` | app-boot | `ui/` |
| `scaffold/` | helper, scripts, create-sdk, protocol, client, server, telemetry | `sdk/` + `ui/jsonrpc` |
| `guard/` | repeat-tool-guard, timeout-policy | `guard/` + `timeout/` |
| `self-modification/` | tool-cordis | `cordis/` |
- **`session/`** is the durable session data plane: the persistence seam with its backends and checkpoint policy, the projection fold that serves whole values from that log, log-backed titles, and OTel reporting. The title fold is itself load-bearing for the read side (`session-query` peer-depends on `dsh-session-title`), so titles belong with the data plane, not in a derived-services annex. The plain name is deliberate (prefer names a human would say); the nearby `core/session` package remains the live in-memory service, while this group is the durable family around it. `session-query/` stays a standalone group — the read/tool surface has its own model tools and SQLite FTS backend and is consumed independently of persistence internals. Absorbing `telemetry/` ended the group-name collision with `dsh-telemetry`.
- **`session/`** is the durable session data plane: the persistence seam with its backends and checkpoint policy, the projection fold that serves whole values from that log, log-backed titles, and OTel reporting. The title fold is itself load-bearing for the read side (`session-query` peer-depends on `dsh-session-title`), so titles belong with the data plane, not in a derived-services annex. The plain name is deliberate (prefer names a human would say); the nearby `core/session` package remains the live in-memory service, while this group is the durable family around it. `session-query/` stays a standalone group — the read/tool surface has its own model tools and SQLite FTS backend and is consumed independently of persistence internals.
- **`interaction/`** is the human-collaboration plane plus the terminal channel that answers it: the question/approval seams, the permission preset, the model-facing `ask_user_question` tool, the human-command registry (`plan-mode` and `command-goal` already consume `commands` together with the interaction seams), and `tui` — the interactive channel is the plane's richest provider and consumer (peer edges to `commands` and `user-interaction`), and a one-package `tui/` group would spend a top-level name on one plugin.
- **`boot/`** is a role-complete single-package group: the shared bin boot glue that belongs to no channel and no assembly (consumed by `apps/cli`, the `scaffold/` launcher, and the `examples/` demo bins).
- **`scaffold/`** is the developer-tooling family: project helper, launcher, initializer, wire protocol with both ends (`server` is the former `ui/jsonrpc`), and launcher telemetry. Renamed from `sdk/`: the whole `packages/` tree *is* the SDK, so a group named `sdk/` inside it said nothing; `scaffold/` names the create/launch/drive-a-project role. Folders drop the legacy `sdk-` prefix (`protocol`, `client`, `server`), matching the `client/`/`host/` role-named folder style; the three affected npm names are mapped explicitly beside the group wildcard in `tsconfig.base.json` until the deferred renames land.
- **`boot/`** is a role-complete single-package group: the shared bin boot glue that belongs to no channel and no assembly (consumed by `apps/cli` and the `examples/` demo bins).
- **`guard/`** keeps its documented role, loop-hygiene guards, and gains the tool-call timeout enforcer, dissolving the one-package `timeout/` group whose name collided with `util/timeout`.
- **`self-modification/`** names the role `cordis/` obscured: the toolset with which the agent inspects and mounts plugins in its own live runtime, and the landing zone for future self-modification packages.
@@ -40,21 +37,16 @@ Six groups are recomposed; every other group keeps its prior boundary and conten
## Deferred renames (FIXME markers)
Five npm names should eventually change, but renaming inside the reorganization would have turned a pure-move PR into an import-churn PR. Instead, each affected package's module JSDoc carries a `FIXME` naming the intended new name. `FIXME` blocks a tagged release ([marker semantics](../../../../docs/development.md)), which is the wanted forcing function: these renames are only free while nothing external consumes the packages.
Two npm names should eventually change, but renaming inside the reorganization would have turned a pure-move PR into an import-churn PR. Each affected package's module JSDoc carries a `FIXME` naming the intended new name. `FIXME` blocks a tagged release ([marker semantics](../../../../docs/development.md)), which is the wanted forcing function: these renames are only free while nothing external consumes the packages. Removing the unreleased SDK project toolchain deleted the other three packages and their rename markers instead of preserving names for code that no longer exists.
| Current npm name | Intended name | Why |
|---|---|---|
| `@deepseek-ai/dsh-jsonrpc` | `@deepseek-ai/dsh-sdk-server` | Names the wire encoding, not the role; it is the server half of the SDK protocol |
| `@deepseek-ai/dsh-telemetry` | `@deepseek-ai/dsh-sdk-telemetry` | Collides with the `dsh-session-telemetry` family; it is launcher-side SDK telemetry |
| `@deepseek-ai/dsh-helper` | `@deepseek-ai/dsh-sdk-helper` | Indefensibly generic as a published name |
| `@deepseek-ai/dsh-scripts` | `@deepseek-ai/dsh-sdk-scripts` | Same |
| `@deepseek-ai/dsh-timeout-policy` | `@deepseek-ai/dsh-timeout-guard` | Suggestion, not settled: aligns the name with its `guard/` home; decide at resolution time |
The first four are settled intent; resolving them converges the SDK wire stack's npm names on `dsh-sdk-*` (the npm prefix names the product stack; the `scaffold/` folder names the role). `@deepseek-ai/create-sdk` keeps its documented npm-initializer exception.
## What the move touched
The moves landed as pure `git mv` moves, so rename detection carries the history. A group move touched: the moved package's `tsconfig.json` relative `references` and every dependent's entry (including the `apps/cli` project references), the tsconfig aggregate and path maps, group READMEs (five new bilingual triplets, deletions for dissolved groups, the [packages/README.md](../../../../packages/README.md) hierarchy table, the root `AGENTS.md` layout map), regenerated artifacts (`docs/module-graph.md`, path-embedding catalogs, the lockfile's importer keys), and root-relative `packages/...` citations in prose and gate scripts. Remaining group-path referents (workspace configs, test globs, lint keys) were found mechanically by the acceptance gates failing loud — the repository's own misconfiguration rule.
The moves landed as pure `git mv` moves, so rename detection carries the history. A group move touched: the moved package's `tsconfig.json` relative `references` and every dependent's entry (including the `apps/cli` project references), the tsconfig aggregate and path maps, group READMEs, the [packages/README.md](../../../../packages/README.md) hierarchy table, the root `AGENTS.md` layout map, regenerated artifacts (`docs/module-graph.md`, path-embedding catalogs, and the lockfile's importer keys), and root-relative `packages/...` citations in prose and gate scripts. Remaining group-path referents (workspace configs, test globs, lint keys) were found mechanically by the acceptance gates failing loud — the repository's own misconfiguration rule.
A group move did not touch: npm names, imports, `cordis.yml` configs, snapshot fixtures, the `pnpm-workspace.yaml`/`tsdown` globs (both `packages/*/*`), or the Python runtime manifest — all reference packages by npm name.
@@ -62,13 +54,13 @@ A group move did not touch: npm names, imports, `cordis.yml` configs, snapshot f
## Alternatives considered
**Coarse domain buckets** (`exec/` = subprocess+sandbox+bash+pty+code-runtime, `workspace/` = fs+lsp+workspace, `orchestration/` = subagent+workflow+tasks, `knowledge/` = web+skill, `collab/` = plan+todo+goal; ~16 groups). Rejected: the measured graph contradicts the merges. `sandbox` and `subprocess` are shared infrastructure consumed across families (bash ×5, fs ×5, pty, lsp, mcp, subagent, scaffold edges), `web``skill` have zero edges, and a large bucket reproduces the `ui/` grab-bag at a larger scale.
**Coarse domain buckets** (`exec/` = subprocess+sandbox+bash+pty+code-runtime, `workspace/` = fs+lsp+workspace, `orchestration/` = subagent+workflow+tasks, `knowledge/` = web+skill, `collab/` = plan+todo+goal; ~16 groups). Rejected: the measured graph contradicts the merges. `sandbox` and `subprocess` are shared infrastructure consumed across families (bash ×5, fs ×5, pty, lsp, mcp, and subagent edges), `web``skill` have zero edges, and a large bucket reproduces the `ui/` grab-bag at a larger scale.
**Abstract layer names** (`capability/`, `policy/`, `extension/`, `provider/`). Rejected: they describe every plugin equally badly, and a `capability/` bucket would hold ~50 packages.
**A full npm rename sweep** (`dsh-<group>-<pkg>` for every package). Rejected: npm names are flat, so group-prefixing adds churn across imports, configs, and fixtures with no disambiguation gain; targeted FIXME-tracked renames cover the actual collisions.
**Performing the five renames inside the reorganization.** Rejected: renames multiply open-PR conflicts and destroy the pure-move review property. The FIXME markers keep them visible release blockers to resolve as small follow-up PRs.
**Performing the deferred renames inside the reorganization.** Rejected: renames multiply open-PR conflicts and destroy the pure-move review property. The remaining FIXME markers keep them visible release blockers to resolve as small follow-up PRs.
**A two-way session split** (`session-core/` + `session-utils/`). Rejected: query belongs to neither side cleanly, and `session-core` invites confusion with `core/session` (`dsh-session`, the live in-memory service, which stays in `core/`).
@@ -78,9 +70,7 @@ A group move did not touch: npm names, imports, `cordis.yml` configs, snapshot f
**A standalone one-package `tui/` group.** Rejected: `tui` is the interaction plane's primary provider/consumer (peer edges to `commands`, `user-interaction`), and a top-level name spent on one plugin adds a group without adding information; it folds into `interaction/`.
**Keeping the group name `sdk/`.** Rejected: the whole `packages/` tree is the SDK, so an `sdk/` group inside it discriminates nothing — the same disease as `cordis/`. `scaffold/` names the actual role (create, launch, and drive projects from outside).
**Moving `app-boot` to `apps/`.** Rejected: `apps/` is the assembly tier over the package tier, and `dsh-app-boot` is a library that package-tier code imports (`scaffold/scripts`' launcher peer-depends on it) — placing it in `apps/` would invert the tiers and put a workspace library outside the `packages/*/*` build globs. It stays a package; `boot/` is its role-complete home.
**Moving `app-boot` to `apps/`.** Rejected: `apps/` is the assembly tier over the package tier, and `dsh-app-boot` is a package-tier library — placing it in `apps/` would invert the tiers and put a workspace library outside the `packages/*/*` build globs. It stays a package; `boot/` is its role-complete home.
**Moving `tool-cordis` into `core/`.** Rejected: self-modification is its own product seam, expected to grow; the spine stays minimal. The group was first named `self-evolve/`; the name settled on `self-modification/` as the plainer term.
@@ -88,9 +78,9 @@ A group move did not touch: npm names, imports, `cordis.yml` configs, snapshot f
## Consequences
- The tree matches the map: the six recomposed groups hold exactly the listed members; the groups `ui/`, `sdk/`, `telemetry/`, `timeout/`, `cordis/`, `session-persistence/`, `session-projection/`, and `session-title/` no longer exist; every other group's contents are unchanged. The workspace package-name set is identical before and after (zero npm renames), and the five FIXME markers pin the deferred ones. A FIXME that later proves wrong must be removed explicitly with rationale, never silently dropped.
- The five still-current regrouped families hold the listed members; the groups `ui/`, `telemetry/`, `timeout/`, `cordis/`, `session-persistence/`, `session-projection/`, and `session-title/` no longer exist. The regrouping itself changed no npm names. The later SDK toolchain removal intentionally changed the package set and restored `sdk/` as the precise home of the runtime SDK trio. Two FIXME markers pin the remaining deferred renames; a FIXME that later proves wrong must be removed explicitly with rationale, never silently dropped.
- What pins the result: `pnpm run typecheck`, the unit suites of every moved group, `verify-package-paths`, `verify-md-links`, and the corpus-wide translation pairing all pass on the moved tree; the group-scoped test globs in `vitest.snapshot.config.ts` were rewritten with the moves so the suites collect the same test files as before (a fail-open glob would silently drop coverage).
- Every open PR touching a moved file rebases across the move once; rename detection resolves most hunks mechanically.
- Single-package groups remain (`boot/`, `self-modification/`, and existing ones such as `acp/`). Accepted deliberately: each is role-complete rather than a fragment of a family, and a truthful small group beats a nominal merge.
- The `scaffold/` folders diverge from their npm names until the deferred renames land — the one transitional asymmetry, carried by three explicit `paths` entries in `tsconfig.base.json` and resolved by the FIXME renames.
- The `sdk/` role folders map explicitly to their npm names in `tsconfig.base.json`; the `server/` mapping remains transitional until `dsh-jsonrpc` is renamed.
- What this gave up: nothing functional — the change is navigational. Muscle memory and external links to old GitHub paths break, which is acceptable pre-release with no external consumers.
@@ -10,29 +10,26 @@ Status: implemented
- `ui/` 混杂了四个互不相关的平面:人类终端通道(`tui`)、SDK 的 JSON-RPC 服务端一半(`jsonrpc`,它对 `dsh-sdk-protocol` 的对等依赖(peer dependency)把它绑在 SDK 通信栈上)、人机交互 seam(`user-interaction``user-approval``permission``tool-ask-user``commands`),以及与通道无关的 boot 胶水(`app-boot`)。它自己的 README 只能逐一叙述这堆混杂,说不出一个统一职责。
- 会话家族被割裂在五个组里——`session-persistence/``session-projection/``session-query/``session-title/``telemetry/`——而实测依赖边明明把它们连成一体(query → persistence、title → projection、projection → persistence;见 [docs/module-graph.md](../../../../docs/module-graph.md))。
- 两个组名与不相干的包撞名:`telemetry/`(会话上报)撞上 `dsh-telemetry`(启动器侧 SDK telemetry),`timeout/`(一个工具调用守卫)撞上 `util/timeout`(通用 promise 工具)
- 用于工具调用守卫的 `timeout/` 组与通用 promise 工具 `util/timeout` 撞名
- `cordis/` 拿所有包共同依托的框架给自己的组命名,这个名字因此毫无区分度;组里唯一的包 `tool-cordis` 是运行时自我修改工具集。
-`sdk/` 的目录命名不一致:`sdk/sdk-client``sdk/sdk-protocol` 重复了组名,而 `sdk/telemetry``sdk/helper``sdk/scripts` 没有。
这次重新分组的指导准则:**聚类紧密的包同处一组。**聚类以实测为准(对等依赖边与 co-change),而非按主题归类。孤立的 seam 家族可以自成一个小组;要避免的失败形态,是名字概括不出单一职责的大杂烩组。
## Decision
重组六个组;其余每个组都保持先前的边界与内容不变(依赖分析确认各能力家族——`bash/``pty/``code-runtime/``sandbox/``subprocess/``fs/``lsp/``web/``skill/` 及其余——本来就划得正确)。npm 包名一个未改;整个变更全部由目录树承载
五项重组决策仍然有效;其余每个组都保持先前的边界与内容不变(依赖分析确认各能力家族——`bash/``pty/``code-runtime/``sandbox/``subprocess/``fs/``lsp/``web/``skill/` 及其余——本来就划得正确)。原本的第六项决策把 SDK 项目初始化器、启动器工具与运行时 JSON-RPC 包汇集到 `scaffold/`[移除这套未发布工具链](../simplification/2026-08-11-remove-sdk-project-toolchain.md)的决策删除了项目工具,并将存留的运行时三包移到 `sdk/`,从而取代了该项决策
| 组 | 成员(目录名) | 来源 |
|---|---|---|
| `session/` | session-persistence、session-persistence-jsonl、session-persistence-sqlite、session-checkpoint-policy、session-projection、session-projection-cache、session-title、session-title-llm、session-title-first-message-llm、session-title-all-messages-llm、session-telemetry、session-telemetry-otel | `session-persistence/` + `session-projection/` + `session-title/` + `telemetry/` |
| `interaction/` | user-interaction、user-approval、permission、tool-ask-user、commands、tui | `ui/` |
| `boot/` | app-boot | `ui/` |
| `scaffold/` | helper、scripts、create-sdk、protocol、client、server、telemetry | `sdk/` + `ui/jsonrpc` |
| `guard/` | repeat-tool-guard、timeout-policy | `guard/` + `timeout/` |
| `self-modification/` | tool-cordis | `cordis/` |
- **`session/`** 是持久会话数据平面:持久化 seam 连同其各后端与检查点策略、从该日志折叠(fold)出全量值对外供值的投影、日志兜底的标题,以及 OTel 上报。标题折叠本身就是读取侧的承重构件(`session-query``dsh-session-title` 声明对等依赖),所以标题属于数据平面,而非某个「派生服务」附属区。用这个朴素的名字是有意为之(名字要像人起的);旁边的 `core/session` 包仍是常驻内存的实时服务,本组则是围绕它的持久家族。`session-query/` 保持独立成组:这个读取/工具面自带模型工具和 SQLite FTS 后端,其消费不依赖持久化内部实现。吸收 `telemetry/` 之后,与 `dsh-telemetry` 的组名冲突就此终结。
- **`session/`** 是持久会话数据平面:持久化 seam 连同其各后端与检查点策略、从该日志折叠(fold)出全量值对外供值的投影、日志兜底的标题,以及 OTel 上报。标题折叠本身就是读取侧的承重构件(`session-query``dsh-session-title` 声明对等依赖),所以标题属于数据平面,而非某个「派生服务」附属区。用这个朴素的名字是有意为之(名字要像人起的);旁边的 `core/session` 包仍是常驻内存的实时服务,本组则是围绕它的持久家族。`session-query/` 保持独立成组:这个读取/工具面自带模型工具和 SQLite FTS 后端,其消费不依赖持久化内部实现。
- **`interaction/`** 是人机协作平面加上应答它的终端通道:提问/批准 seam、权限预设、面向模型的 `ask_user_question` 工具、人类命令注册表(`plan-mode``command-goal` 已经把 `commands` 和各交互 seam 放在一起消费),以及 `tui`——这个交互通道是该平面最重的提供方与消费方(对 `commands``user-interaction` 均有对等依赖边),而一个单包 `tui/` 组会把一个顶层名字花在一个插件上。
- **`boot/`** 是角色完备的单包组:不归属任何通道也不归属任何组装的共享 bin boot 胶水(被 `apps/cli``scaffold/` 的启动器和 `examples/` 各演示 bin 消费)。
- **`scaffold/`** 是开发者工具家族:项目 helper、启动器、初始化器、连同两端的通信协议(`server` 即原先的 `ui/jsonrpc`),以及启动器侧 telemetry。从 `sdk/` 改名:整个 `packages/` 树本身就是 SDK,树里再放一个叫 `sdk/` 的组等于什么都没说;`scaffold/` 说出了「创建/启动/驱动项目」这一实际角色。目录去掉遗留的 `sdk-` 前缀(`protocol``client``server`),与 `client/`/`host/` 的角色命名风格一致;在推迟的改名落地之前,受影响的三个 npm 名在 `tsconfig.base.json` 里于组通配符旁显式映射。
- **`boot/`** 是角色完备的单包组:不归属任何通道也不归属任何组装的共享 bin boot 胶水(被 `apps/cli` `examples/` 各演示 bin 消费)。
- **`guard/`** 保留其文档记载的角色(循环卫生守卫),并新纳入强制执行工具调用超时的包;那个与 `util/timeout` 撞名的单包组 `timeout/` 随之解散。
- **`self-modification/`** 把 `cordis/` 遮蔽掉的角色说了出来:它是 agent(智能体)检查并挂载自身实时运行时中插件所用的工具集,也是未来自我修改类包的落点。
@@ -40,21 +37,16 @@ Status: implemented
## Deferred renames (FIXME markers)
个 npm 名最终应当改掉,但在这次重组内部改名,会把一个纯移动的 PR(Pull Request)变成大量翻改 import 的 PR。因此每个受影响包的模块 JSDoc 里带有一条 `FIXME`,写明意图中的新名字。`FIXME` 会阻塞打 tag 的发布([标记语义](../../../../docs/development.md)),这正是想要的倒逼机制:只有趁还没有外部消费方使用这些包时,这些改名才是零成本的。
个 npm 名最终应当改掉,但在这次重组内部改名,会把一个纯移动的 PR(Pull Request)变成大量翻改 import 的 PR。每个受影响包的模块 JSDoc 里带有一条 `FIXME`,写明意图中的新名字。`FIXME` 会阻塞打 tag 的发布([标记语义](../../../../docs/development.md)),这正是想要的倒逼机制:只有趁还没有外部消费方使用这些包时,这些改名才是零成本的。移除未发布的 SDK 项目工具链时,另外三个包及其改名标记一并删除,没有为已经不存在的代码保留包名。
| 当前 npm 名 | 目标名 | 原因 |
|---|---|---|
| `@deepseek-ai/dsh-jsonrpc` | `@deepseek-ai/dsh-sdk-server` | 名字说的是协议编码而非角色;它是 SDK 协议的服务端一半 |
| `@deepseek-ai/dsh-telemetry` | `@deepseek-ai/dsh-sdk-telemetry` | 与 `dsh-session-telemetry` 家族撞名;它是启动器侧 SDK telemetry |
| `@deepseek-ai/dsh-helper` | `@deepseek-ai/dsh-sdk-helper` | 作为公开发布名空泛得站不住脚 |
| `@deepseek-ai/dsh-scripts` | `@deepseek-ai/dsh-sdk-scripts` | 同上 |
| `@deepseek-ai/dsh-timeout-policy` | `@deepseek-ai/dsh-timeout-guard` | 仅为建议、尚未定案:使名字与其 `guard/` 归属对齐;到解决时再定 |
前四个是已定的意图;兑现之后,SDK 通信栈的 npm 名随之收敛为 `dsh-sdk-*`npm 前缀指产品栈,`scaffold/` 目录名指角色)。`@deepseek-ai/create-sdk` 保留其文档记载的 npm 初始化器特例。
## What the move touched
移动以纯 `git mv` 形式落地,历史由重命名检测承载。组移动触及了:被移动包的 `tsconfig.json` 相对 `references` 及每个依赖方的对应条目(含 `apps/cli` 的 project references);tsconfig 聚合与路径映射;各组 README(五组新的双语三文件配对、被解散组的 README 删除、[packages/README.md](../../../../packages/README.md) 的层级结构表`AGENTS.md` 的布局图;重新生成的产物(`docs/module-graph.md`、内嵌路径的目录锁文件的 importer 键);以及散文与门禁脚本中以仓库根为基准的 `packages/...` 引用。其余每一处组路径引用(workspace 配置、测试 glob、lint 键)都由验收门禁的响亮失败机械地找了出来——这正是本仓库自己的「配置错误必须响亮失败」规则。
移动以纯 `git mv` 形式落地,历史由重命名检测承载。组移动触及了:被移动包的 `tsconfig.json` 相对 `references` 及每个依赖方的对应条目(含 `apps/cli` 的 project references);tsconfig 聚合与路径映射;各组 README[packages/README.md](../../../../packages/README.md) 的层级结构表`AGENTS.md` 的布局图;重新生成的产物(`docs/module-graph.md`、内嵌路径的目录以及锁文件的 importer 键);以及散文与门禁脚本中以仓库根为基准的 `packages/...` 引用。其余每一处组路径引用(workspace 配置、测试 glob、lint 键)都由验收门禁的响亮失败机械地找了出来——这正是本仓库自己的「配置错误必须响亮失败」规则。
组移动未触及:npm 包名、import、`cordis.yml` 配置、快照 fixture(测试前置数据)、`pnpm-workspace.yaml``tsdown` 的 glob(都是 `packages/*/*`),以及 Python 运行时 manifest(元数据清单)——它们全部按 npm 包名引用包。
@@ -62,13 +54,13 @@ Status: implemented
## Alternatives considered
**粗粒度领域桶**`exec/` = subprocess+sandbox+bash+pty+code-runtime`workspace/` = fs+lsp+workspace`orchestration/` = subagent+workflow+tasks`knowledge/` = web+skill`collab/` = plan+todo+goal;约 16 个组)。不予采纳:实测依赖图与这些合并相矛盾。`sandbox``subprocess` 是被各家族跨界消费的共享基础设施(与 bash ×5、fs ×5、pty、lsp、mcpsubagent、scaffold 均有依赖边),`web``skill` 之间零依赖边,而大桶只会在更大尺度上复现 `ui/` 式大杂烩。
**粗粒度领域桶**`exec/` = subprocess+sandbox+bash+pty+code-runtime`workspace/` = fs+lsp+workspace`orchestration/` = subagent+workflow+tasks`knowledge/` = web+skill`collab/` = plan+todo+goal;约 16 个组)。不予采纳:实测依赖图与这些合并相矛盾。`sandbox``subprocess` 是被各家族跨界消费的共享基础设施(与 bash ×5、fs ×5、pty、lsp、mcpsubagent 均有依赖边),`web``skill` 之间零依赖边,而大桶只会在更大尺度上复现 `ui/` 式大杂烩。
**抽象分层名**`capability/``policy/``extension/``provider/`)。不予采纳:这些名字对每个插件都同样地不达意,而且一个 `capability/` 桶会装下约 50 个包。
**一轮全量 npm 重命名**(每个包都改为 `dsh-<group>-<pkg>`)。不予采纳:npm 包名是扁平的,加组前缀只会在 import、配置和 fixture 之间制造改动,却换不来任何消歧收益;用 FIXME 跟踪的定点改名足以覆盖真正的撞名。
**在重组内部一并完成那五个改名。** 不予采纳:改名会成倍放大开放 PR 的冲突,并破坏纯移动的评审属性。FIXME 标记让这些改名保持为可见的发布阻塞项,留待以小型后续 PR 逐一解决。
**在重组内部一并完成推迟的改名。** 不予采纳:改名会成倍放大开放 PR 的冲突,并破坏纯移动的评审属性。剩余的 FIXME 标记让这些改名保持为可见的发布阻塞项,留待以小型后续 PR 逐一解决。
**会话两分法**`session-core/` + `session-utils/`)。不予采纳:query 放哪一侧都不干净,而且 `session-core` 容易与 `core/session` 混淆(后者是 `dsh-session`,常驻内存的实时服务,留在 `core/` 不动)。
@@ -78,9 +70,7 @@ Status: implemented
**独立的单包 `tui/` 组。** 不予采纳:`tui` 是交互平面最重的提供方/消费方(对 `commands``user-interaction` 有对等依赖边),把一个顶层名字花在一个插件上只添组不添信息;它折入 `interaction/`
**保留组名 `sdk/`。** 不予采纳:整个 `packages/` 树本身就是 SDK,树里的 `sdk/` 组毫无区分度——与 `cordis/` 同病。`scaffold/` 说出了实际角色(从外部创建、启动、驱动项目)
**把 `app-boot` 挪到 `apps/`。** 不予采纳:`apps/` 是包层之上的组装层,而 `dsh-app-boot` 是被包层代码 import 的库(`scaffold/scripts` 的启动器对它声明对等依赖)——放进 `apps/` 会颠倒层级,并把一个 workspace 库放到 `packages/*/*` 构建 glob 之外。它仍是一个包;`boot/` 是它角色完备的家。
**把 `app-boot` 挪到 `apps/`。** 不予采纳:`apps/` 是包层之上的组装层,而 `dsh-app-boot` 是包层的库——放进 `apps/` 会颠倒层级,并把一个 workspace 库放到 `packages/*/*` 构建 glob 之外。它仍是一个包;`boot/` 是它角色完备的家
**把 `tool-cordis` 挪进 `core/`。** 不予采纳:自我修改是独立的产品 seam,预期还会生长;主干保持精简。该组最初命名为 `self-evolve/`;名字最终定为更朴素的 `self-modification/`
@@ -88,9 +78,9 @@ Status: implemented
## Consequences
- 目录树与映射表一致:重组的六个组恰好持有所列成员;`ui/``sdk/``telemetry/``timeout/``cordis/``session-persistence/``session-projection/``session-title/` 这些组不复存在;其余每个组的内容不变。workspace 的包名集合在前后完全相同(npm 改名为零),五条 FIXME 标记钉住推迟改名日后若某条 FIXME 被证明不对,必须连同理由显式移除,绝不允许无声消失。
- 五个仍然有效的重组家族持有所列成员;`ui/``telemetry/``timeout/``cordis/``session-persistence/``session-projection/``session-title/` 这些组不复存在。重组本身没有更改 npm 名。后续移除 SDK 工具链的决策有意改变包集合,并恢复 `sdk/` 作为运行时 SDK 三包的精确归属。两条 FIXME 标记钉住剩余的推迟改名日后若某条 FIXME 被证明不对,必须连同理由显式移除,绝不允许无声消失。
- 结果由以下检查钉住:`pnpm run typecheck`、每个被移动组的单元测试套件、`verify-package-paths``verify-md-links` 与全语料翻译配对在移动后的树上全部通过;`vitest.snapshot.config.ts` 中按组划定的测试 glob 随移动一并改写,套件收集到与移动前相同的测试文件(glob 匹配为空会无声地丢失覆盖)。
- 每个触碰被移动文件的开放 PR 都跨过这次移动做一次变基;重命名检测可机械化解决大多数改动块。
- 单包组依然存在(`boot/``self-modification/`,以及 `acp/` 等既有单包组)。这是有意接受的:每个都是角色完备的整体而非某个家族的碎片,一个名实相符的小组胜过一次徒有其名的合并。
- 在推迟的改名落地之前,`scaffold/` 的目录名与其 npm 名并不一致——这是唯一的过渡性不对称,由 `tsconfig.base.json` 里三条显式 `paths` 映射承载,并由 FIXME 改名最终消除
- `sdk/` 的角色目录在 `tsconfig.base.json` 中显式映射到各自的 npm 名;在 `dsh-jsonrpc` 完成改名之前,`server/` 的映射仍是过渡性的
- **这次变更放弃了什么:** 功能上一无所失——变更只关乎导航。肌肉记忆和指向旧 GitHub 路径的外部链接会失效;在 pre-release、尚无外部消费者的前提下,这可以接受。
@@ -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/architecture/2026-07-30-config-plane-boundaries.md
2026-07-30-config-plane-boundaries.md: 383163d5315ce0fcb39d06ac8b5f7762758fa9b2
2026-07-30-config-plane-boundaries.zh.md: 0a412d5b8517c98accd056b690129f4e485f0e13
2026-07-30-config-plane-boundaries.md: 0a689603b9619453f4a6613d79a82a1e671f0401
2026-07-30-config-plane-boundaries.zh.md: b0e306a1adad971b611d315edfcdf9103091d022
@@ -26,7 +26,7 @@ Three smaller defects sat beside them. `llm/adapters-updated` documented contain
**Staleness is detected, not ordered away.** Each namespace carries a monotonic `revision` over its RAW section; writes may carry `expectedRevision`, and a mismatch rejects with `SettingsConflictError``settings-conflict` on the wire, both revisions attached. The editor captures the revision it opened at and, on conflict, tells the user to reopen rather than replaying its snapshot.
**The raw layer gets its own event.** `settings/updated` stays gated on the resolved value — that is what a consumer means by change. `settings/document-updated (ns, revision)` fires on any raw-section change, because a configuration surface must learn that a field went from inherited to overridden (same resolved value, different meaning) and that its held revision is stale. The host frame `host/settings-changed` now rides this event, and a change to an exposed provider namespace also emits `host/models-changed`: that namespace holds the provider's catalog, which no route change announces.
**The raw layer gets its own event.** `settings/updated` stays gated on the resolved value — that is what a consumer means by change. `settings/document-updated (ns, revision)` fires on any raw-section change, because a configuration surface must learn that a field went from inherited to overridden (same resolved value, different meaning) and that its held revision is stale. The event is forwarded verbatim, and model consumers subscribe to it alongside `llm/adapters-updated`, because provider settings hold catalog data that no route change announces.
## Alternatives considered
@@ -26,7 +26,7 @@ Status: implemented
**过期是被检测出来的,而不是靠排序绕过去的。**每个 namespace 都带有一个针对其**原始**分节的单调 `revision`;写入可携带 `expectedRevision`,不匹配即以 `SettingsConflictError` 拒绝——在协议上是 `settings-conflict`,并附上两个 revision。编辑器记住自己打开时的 revision,冲突时请用户重新打开,而不是把自己的快照重放上去。
**原始层拥有自己的事件。**`settings/updated` 仍以解析值为门槛——那才是消费方所说的"变化"。`settings/document-updated (ns, revision)` 则在任何原始分节变化时触发,因为配置界面必须知道某个字段从继承变成了覆盖(解析值相同,含义不同),也必须知道自己持有的 revision 已经过期。host 帧 `host/settings-changed` 现在搭乘这个事件;而已暴露提供方 namespace 的变更还会额外发出 `host/models-changed`:该 namespace 正持有这个提供方的目录,而没有任何路由变更会宣告它
**原始层拥有自己的事件。**`settings/updated` 仍以解析值为门槛——那才是消费方所说的"变化"。`settings/document-updated (ns, revision)` 则在任何原始分节变化时触发,因为配置界面必须知道某个字段从继承变成了覆盖(解析值相同,含义不同),也必须知道自己持有的 revision 已经过期。该事件被原样转发,模型消费方同时订阅它与 `llm/adapters-updated`,因为提供方设置持有不会由路由变化宣告的目录数据
## 曾考虑的替代方案
@@ -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/architecture/2026-07-30-followup-enqueue-and-owned-runs.md
2026-07-30-followup-enqueue-and-owned-runs.md: e0561f8cfc975dd60e69307b160070c292efff8e
2026-07-30-followup-enqueue-and-owned-runs.zh.md: a807b3ebe47399cae95c38bc2232e20e00e839f5
2026-07-30-followup-enqueue-and-owned-runs.md: 9978b3a8ab8678fe98e000476505cee9dcaa1bc6
2026-07-30-followup-enqueue-and-owned-runs.zh.md: 6501266d32b5ae884a478bfae9e4f1e3d5d85575
@@ -16,7 +16,7 @@ Keep `Agent.followup(message): void` as an enqueue-only operation. `Agent.whenId
The low-level SDK protocol answers `session/prompt` as soon as enqueue succeeds with `{ messageId }`. It streams durable facts through `session.event`, publishes whole-agent transitions through `session.status`, and has no `session.finished`. A low-level client may observe that receipt and later idleness, but receives no prompt result.
High-level automation APIs return a `RunResult` only when they explicitly own an activity interval. The TypeScript and Python SDK `run()` methods collect from the submitted message's durable inbox receipt through the next whole-agent `idle`; their `finalResponse` is the last committed assistant message in that interval, not a response causally attributed to the submitted prompt. The one-shot CLI owns the analogous idle-to-idle interval. An isolated child-agent run may report a result because its caller owns the complete child lifecycle and any steering belongs to that run.
High-level automation APIs return a `RunResult` only when they explicitly own an activity interval. The TypeScript and Python SDK `run()` methods collect from the submitted message's durable inbox receipt through the next whole-agent `idle`; their final response is the last committed assistant message in that interval, not a response causally attributed to the submitted prompt. The Python SDK also reports the last root turn's reason kind as the run-level [`finish_reason`](../bug-fix/2026-08-11-owned-run-finish-reason.md), without attributing it to the submitted prompt. The one-shot CLI owns the analogous idle-to-idle interval. An isolated child-agent run may report a result because its caller owns the complete child lifecycle and any steering belongs to that run.
ACP must return a protocol `stopReason`. Its bridge serializes one in-flight prompt per ACP session, waits for whole-agent idle, and otherwise reports the generic `end_turn`. Token-limit endings are not attributed to the prompt: they settle as `end_turn`. A model error on the prompt's correlated turn does reject the prompt immediately (the error is attributed by its owning turn), and a turnless slot (admission discarded the prompt) settles as `cancelled` at idle alongside explicit ACP cancellation or disposal.
@@ -33,10 +33,10 @@ Goal continuation retains `MessageId` only to recognize its durable queued and a
## Verification
- Agent and inbox tests pin enqueue-only follow-up, durable admission or cancellation, and whole-agent idle observation.
- SDK protocol, TypeScript SDK, and Python SDK tests pin the `{ messageId }` receipt, `session.status`, the absence of `session.finished`, and receipt-to-idle `RunResult` collection without prompt-level `status` or `reason`.
- SDK protocol, TypeScript SDK, and Python SDK tests pin the `{ messageId }` receipt, `session.status`, the absence of `session.finished`, and receipt-to-idle `RunResult` collection without prompt-level `status` or `reason`; Python SDK tests separately pin its run-level `finish_reason` observation.
- ACP, one-shot CLI, goal continuation, and subagent tests pin the distinct activity ownership each integration possesses.
- Consumer tests pin that no production integration derives a follow-up result by correlating `MessageId` with `turn/end`.
## Consequences
An owned activity interval can include steering, injected context, or other work submitted before idleness, so its final response and events are deliberately broader than the initiating message. Prompt-level model error and token-limit classifications disappear from SDK and ACP results; callers that need those facts must inspect the durable event stream without claiming causal attribution. Concurrent automation on one session requires an explicit serialization or ownership policy rather than an implicit per-prompt result.
An owned activity interval can include steering, injected context, or other work submitted before idleness, so its final response, finish reason, and events are deliberately broader than the initiating message. Prompt-level model error and token-limit classifications remain absent from SDK and ACP results; callers may inspect run-level or durable event facts without claiming causal attribution. Concurrent automation on one session requires an explicit serialization or ownership policy rather than an implicit per-prompt result.
@@ -16,7 +16,7 @@ Status: implemented
底层 SDK 协议在入队成功后立即以 `{ messageId }` 响应 `session/prompt`。它通过 `session.event` 流式传输持久事实,通过 `session.status` 发布整个 agent 的状态转换,且不包含 `session.finished`。底层客户端可以观察该回执和之后的 idle,但不会收到提示词结果。
只有明确拥有一个活动区间时,高层自动化 API 才返回 `RunResult`。TypeScript 和 Python SDK 的 `run()` 方法从已提交消息的持久 inbox 回执开始收集,直至整个 agent 下一次进入 `idle`;其 `finalResponse` 是该区间内最后一条已提交的 assistant 消息,而不是按因果关系归属于已提交提示词的响应。单次 CLI(命令行界面)拥有相应的 idle 到 idle 区间。隔离的子 agent 运行可以报告结果,因为调用方拥有完整的子级生命周期,任何 steering 都属于该运行。
只有明确拥有一个活动区间时,高层自动化 API 才返回 `RunResult`。TypeScript 和 Python SDK 的 `run()` 方法从已提交消息的持久 inbox 回执开始收集,直至整个 agent 下一次进入 `idle`;其最终响应是该区间内最后一条已提交的 assistant 消息,而不是按因果关系归属于已提交提示词的响应。Python SDK 还把根会话最后一个轮次的结束原因 kind 作为运行级 [`finish_reason`](../bug-fix/2026-08-11-owned-run-finish-reason.md) 返回,但不会将其归因于已提交的提示词。单次 CLI(命令行界面)拥有相应的 idle 到 idle 区间。隔离的子 agent 运行可以报告结果,因为调用方拥有完整的子级生命周期,任何 steering 都属于该运行。
ACPAgent Client Protocol)必须返回协议规定的 `stopReason`。其桥接层串行处理每个 ACP 会话中唯一一个正在处理的提示词,等待整个 agent 进入 idle,其他情况均报告通用的 `end_turn`。token 上限的轮次结束不归因于提示词:它们以 `end_turn` 结算。与该提示词关联的轮次上的模型错误会立即以该错误拒绝提示词(错误按其所属轮次归因),而 turnless 槽位(准入已丢弃提示词)会在 idle 时以 `cancelled` 结算,与显式 ACP 取消或 dispose(资源释放)并列。
@@ -33,10 +33,10 @@ Goal 续行只保留 `MessageId`,用于识别持久排队和已准入的 goal
## 验证
- Agent 与 inbox 测试固定 follow-up 仅入队、持久准入或取消以及整个 agent 的 idle 观测。
- SDK 协议、TypeScript SDK 和 Python SDK 测试固定 `{ messageId }` 回执、`session.status`、不存在 `session.finished`,以及不含提示词级 `status``reason` 的回执到 idle `RunResult` 收集。
- SDK 协议、TypeScript SDK 和 Python SDK 测试固定 `{ messageId }` 回执、`session.status`、不存在 `session.finished`,以及不含提示词级 `status``reason` 的回执到 idle `RunResult` 收集;Python SDK 测试另行固定其运行级 `finish_reason` 观测
- ACP、单次 CLI、goal 续行和 subagent 测试固定各集成实际拥有的不同活动边界。
- 消费方测试固定生产集成都不会通过关联 `MessageId``turn/end` 来推导 follow-up 结果。
## 后果
自有活动区间可以包含进入 idle 前提交的 steering、注入上下文或其他工作,因此其最终响应和事件有意比初始消息涵盖更广。SDK 和 ACP 结果不包含提示词级模型错误和 token 上限分类;需要这些事实的调用方必须检查持久事件,但不能声称这些事实具有因果归属。在同一会话上并发执行自动化操作时,必须采用显式串行或所有权策略,不能依赖隐式的按提示词结果。
自有活动区间可以包含进入 idle 前提交的 steering、注入上下文或其他工作,因此其最终响应、结束原因和事件有意比初始消息涵盖更广。SDK 和 ACP 结果不包含提示词级模型错误和 token 上限分类;调用方可以检查运行级或持久事件事实,但不能声称这些事实具有因果归属。在同一会话上并发执行自动化操作时,必须采用显式串行或所有权策略,不能依赖隐式的按提示词结果。
@@ -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/architecture/2026-07-30-web-config-plane.md
2026-07-30-web-config-plane.md: 1af86fc7917cc40b0544bb5c6254994a87ad7a55
2026-07-30-web-config-plane.zh.md: 15916fe86e2f5e19e9752721917317aa8c39442d
2026-07-30-web-config-plane.md: 8673ad76c761c8a139a811a2efc1b7b21bcd4483
2026-07-30-web-config-plane.zh.md: 0571b6aee2062cad12af1aa61156fb7da3a9bead
@@ -12,7 +12,7 @@ The request-level configuration seam made LLM adapter configuration restart-free
## Decision
**Wire domains on the compiled RPC map, rejections as codes, invalidations as frames.** `settings.describe/openDocument/update/replace/mutate`, `credentials.describe/set/unset`, `llm.providers`, and `llm.models` (claiming the reserved `host.listModels` surface) join `RpcMethodMap`, so the seven compiler-locked wiring sites keep contract, schema, handler, and client in lockstep. Seam rejections fold into `settings-rejected {ns}` / `credential-rejected {ref}` business errors (HTTP stays a carrier), and three `HostFrame`s — `host/settings-changed {ns}`, `host/credentials-changed {ref}`, `host/models-changed` — follow the `host/commands-changed` shape so every client converges without polling. Settings reads, native actions, and writes join `pickDirectory`/`openPath` in the connection guard's privileged set: loopback + same-origin or 403, because a LAN-exposed dsh web must not accept configuration access from another origin.
**Wire domains on the compiled RPC map, rejections as codes, owner events forwarded verbatim.** `settings.describe/openDocument/update/replace/mutate`, `credentials.describe/set/unset`, `llm.providers`, and `llm.models` join `RpcMethodMap`, so the compiler-locked wiring sites keep schema, handler, and client in lockstep. Seam rejections fold into `settings-rejected {ns}` / `credential-rejected {ref}` business errors, while clients subscribe to forwarded settings, credentials, and LLM owner events and converge without polling ([forwarded Remote events](2026-08-10-remote-event-delivery.md)). Settings reads, native actions, and writes join `pickDirectory`/`openPath` in the connection guard's privileged set: loopback + same-origin or 403, because a LAN-exposed dsh web must not accept configuration access from another origin.
**`describe()` grows layers and structural secret redaction.** `SettingsDescriptor` carries `base`/`user` beside the effective value, so the form marks "overridden" by presence in the user layer, not value inequality (an override *equal* to the base is still an override). `describe({ redactSecrets: true })` — mandatory at every wire face — strips `role('secret')` subtrees from all three layers via a pure structural walk of the schema (object/dict/array containers; a secret-role subtree is one opaque leaf) and enumerates the stripped slots as `{path, set}`, so a page can render write-only inputs without ever receiving a value.
@@ -12,7 +12,7 @@ Status: implemented
## 决策
**wire 领域挂上编译期 RPC 映射,拒绝落为错误码,失效落为帧**`settings.describe/openDocument/update/replace/mutate``credentials.describe/set/unset``llm.providers``llm.models`(认领预留的 `host.listModels` 面)一同加入 `RpcMethodMap`七处由编译器锁定的接线位点因此让约定、schema、处理器与客户端保持步调一致。seam 侧拒绝折叠为 `settings-rejected {ns}`/`credential-rejected {ref}` 业务错误(HTTP 仍只是载体),三个 `HostFrame`——`host/settings-changed {ns}``host/credentials-changed {ref}``host/models-changed`——沿用 `host/commands-changed` 的形状,因此每个客户端都无需轮询即可收敛。settings 读取、原生操作与写入和 `pickDirectory`/`openPath` 一起进入连接守卫的特权集合:回环 + 同源,否则 403,因为暴露在局域网上的 dsh web 绝不能接受来自其他源的配置访问。
**wire 领域挂上编译期 RPC 映射,拒绝落为错误码,owner 事件原样转发**`settings.describe/openDocument/update/replace/mutate``credentials.describe/set/unset``llm.providers``llm.models` 一同加入 `RpcMethodMap`,由编译器锁定的接线位点schema、处理器与客户端保持步调一致。seam 侧拒绝折叠为业务错误,客户端则订阅转发的 settings、credentials 与 LLM owner 事件,无需轮询即可收敛(见[转发的 Remote 事件](2026-08-10-remote-event-delivery.md)。settings 读取、原生操作与写入和 `pickDirectory`/`openPath` 一起进入连接守卫的特权集合:回环 + 同源,否则 403,因为暴露在局域网上的 dsh web 绝不能接受来自其他源的配置访问。
**`describe()` 增加分层与结构化 secret 脱敏。**`SettingsDescriptor` 在生效值之外携带 `base`/`user`,表单据此按「字段是否出现在用户层」来标记「已覆盖」,而非按值是否不等(与 base *相等*的覆盖仍然是覆盖)。`describe({ redactSecrets: true })`——在每个 wire 面都强制启用——经由对 schema 的纯结构遍历(object/dict/array 容器;secret 角色子树整体是一个不透明叶节点)从全部三层剥除 `role('secret')` 子树,并把剥除的槽位枚举为 `{path, set}`,页面因此不必收到任何值就能渲染只写输入框。
@@ -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/architecture/2026-08-02-typert-remote-method-calls.md
2026-08-02-typert-remote-method-calls.md: b316d1a42c4f69c8e1163f1f36249b61a7d126ef
2026-08-02-typert-remote-method-calls.zh.md: 02714de3c522ce597e89976b6e03d455ff0bf872
2026-08-02-typert-remote-method-calls.md: 04d4581a8f9a265e5374dae4b76ac8d7e1f91fc6
2026-08-02-typert-remote-method-calls.zh.md: d0940d0cd95b04901caafa214058a272b23ded5d
@@ -238,7 +238,7 @@ import goalsRemote from '@deepseek-ai/dsh-goal/remote'
This import brings the `.d.ts` map augmentation into the current TypeScript project while supplying the JS descriptor for the same contract as a value to the runtime. A business package that is not imported does not extend the current project's Remote API types.
The business package's published files must include both `lib/typert.remote-client.d.ts.map` and the `src` file referenced by that map. The generated DTS refers to its adjacent map with `//# sourceMappingURL=typert.remote-client.d.ts.map`; the map source points from `lib` to the business source by a relative path such as `../src/index.ts`. The `/remote` export does not list the map separately; the package `files` field publishes it together with the source.
The business package's published files must include `lib/typert.remote-client.d.ts.map`. The generated DTS refers to its adjacent map with `//# sourceMappingURL=typert.remote-client.d.ts.map`; the map source points from `lib` to the business source by a relative path such as `../src/index.ts`. The `/remote` export does not list the map separately; the package `files` field publishes it. That target is a development-time path: a workspace consumer resolves it through the package link, so the published payload keeps excluding `src` and a published map simply resolves nothing.
Code that needs only static types may use `import type {} from '@deepseek-ai/dsh-goal/remote'`. This import is erased at runtime, loads no JS, and cannot trigger runtime registration. An environment that makes real calls must pass the contribution from a normal value import to the Client Remote Service.
@@ -238,7 +238,7 @@ import goalsRemote from '@deepseek-ai/dsh-goal/remote'
该 import 让 `.d.ts` 的 map augmentation 进入当前 TypeScript project,同时把同一约定的 JS descriptor 作为值交给运行时。未 import 的业务包不会扩展当前 project 的 Remote API 类型。
业务 package 的发布文件必须同时包含 `lib/typert.remote-client.d.ts.map` 和 map 指向的 `src` 文件。生成 DTS 以 `//# sourceMappingURL=typert.remote-client.d.ts.map` 引用相邻 mapmap 中的 source 从 `lib` 相对指向业务源码,例如 `../src/index.ts``/remote` export 不单独列出 mappackage `files` 负责把它与源码一起发布。
业务 package 的发布文件必须包含 `lib/typert.remote-client.d.ts.map`。生成 DTS 以 `//# sourceMappingURL=typert.remote-client.d.ts.map` 引用相邻 mapmap 中的 source 从 `lib` 相对指向业务源码,例如 `../src/index.ts``/remote` export 不单独列出 mappackage `files` 负责发布它。该目标是开发期路径:workspace 消费者经 package link 解析它,因此发布产物仍然不含 `src`,已发布的 map 只是解析不到东西
仅需要静态类型时可以使用 `import type {} from '@deepseek-ai/dsh-goal/remote'`;这种 import 在运行时会被擦除,不会加载 JS,也不能触发任何运行时注册。需要真实调用的环境必须把普通 value import 得到的 contribution 交给 Client Remote Service。
@@ -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/architecture/2026-08-03-pi-ai-declared-provider-catalog.md
2026-08-03-pi-ai-declared-provider-catalog.md: 45de54f29e718ed1c9364b03da762700e1282e7b
2026-08-03-pi-ai-declared-provider-catalog.zh.md: 43206bc21dfa74f6ddf0583c72dc4e8be1dbb9e5
2026-08-03-pi-ai-declared-provider-catalog.md: 571986a94c8547538b44b11510609e0000923537
2026-08-03-pi-ai-declared-provider-catalog.zh.md: 917c19e77dc1db7fe4dc20acf1d9b280277a76d2
@@ -14,7 +14,7 @@ The adapter also streamed through `streamSimple` from `@earendil-works/pi-ai/com
A provider route is a **declaration**, and the installed catalog is its default. `resolveProfiles` no longer checks route keys against `getBuiltinProviders()`. Instead each route resolves to a materialized model list plus the pi-ai `Provider` that serves it:
- `catalog.ts` merges the installed catalog under the profile's own entries. A profile's `models` list *replaces* the route's catalog (an absent or empty list serves it unchanged), and each entry defaults its unset fields from the installed model of the same `id`. Only the fields the harness consumes are configurable — `id`, `name`, `contextWindow`, `maxTokens`; [[2026-08-08-pi-ai-per-model-reasoning-declarations]] later added `reasoningEfforts` and `compat`, which is also where the original "reasoning rides the installed entry or is absent" stance was revisited (a bare capability flag stays rejected; a full per-level declaration with wire spellings does not have its problem). Pricing and input modalities remain absent from the surface because nothing reads them: `replay.ts` zeroes pi-ai's cost metadata and `context.ts` keeps only text blocks. Materialization spreads the installed entry and overrides the configured fields, rather than enumerating the result: an enumerated rebuild silently drops every `Model` field this package does not model, which is how `headers` went missing from an nvidia route once already.
- `catalog.ts` merges the installed catalog under the profile's own entries. A profile's `models` list *replaces* the route's catalog (an absent or empty list serves it unchanged), and each entry defaults its unset fields from the installed model of the same `id`. Only the fields the harness consumes are configurable — `id`, `name`, `contextWindow`, `maxTokens`; [[2026-08-08-pi-ai-per-model-reasoning-declarations]] later added `reasoningEfforts` and `compat`, which is also where the original "reasoning rides the installed entry or is absent" stance was revisited (a bare capability flag stays rejected; a full per-level declaration with wire spellings does not have its problem). Input modalities were opened later, as `input` on an entry plus a route-level `defaultInput`, once the image-admission points turned an unreported modality into a refusal a deployment could not lift ([[2026-08-12-pi-ai-route-default-input-modalities]]); the "nothing reads them" reasoning had described `llm-deepseek`'s serializer rather than this route, whose converter carries images. Pricing stays absent for the original reason: `replay.ts` zeroes pi-ai's cost metadata and no consumer reports spend. Materialization spreads the installed entry and overrides the configured fields, rather than enumerating the result: an enumerated rebuild silently drops every `Model` field this package does not model, which is how `headers` went missing from an nvidia route once already.
- `provider.ts` builds the route's `Provider`. A catalog route that keeps its catalog protocol **reuses** the installed provider with `getModels()` replaced; every other route is built by `createProvider()` over a protocol table whose entries are the same `@earendil-works/pi-ai/api/*.lazy` factories pi-ai's own provider factories use. That table is narrower than pi-ai's full API set on purpose — it holds only protocols a profile can completely describe with a key, an endpoint, and headers, so Bedrock (SigV4 plus a region), Vertex (project, location, ADC), Azure (provider environment plus an api-version), and Codex (OAuth) are absent rather than offered as routes that cannot authenticate. Catalog routes still reach them through their own provider; only an explicit override is refused.
- `adapter.ts` turns each resolution into an **immutable snapshot** — the profiles plus a `createModels()` collection holding those providers — and every operation captures a whole snapshot before its first `await`.
- A model's **explicitly configured** `maxTokens` becomes the seam's `defaultMaxTokens`. The value inherited from the installed catalog does not: pi-ai requires `Model.maxTokens` as the model's output *capability*, while `defaultMaxTokens` is a cap the deployment chose to send on requests that name none, and materializing the former as the latter would start capping every request at a number nobody picked.
@@ -50,7 +50,7 @@ A route's auth follows from that. A catalog route keeps the installed provider's
- **Keep `createProvider()` but skip the `Models` collection**, streaming through `provider.streamSimple(model, ctx, {apiKey})`. Smallest diff and the credential path is untouched, but `createProvider`'s `auth` is a required field that this path never invokes — a required-by-signature implementation with no caller. It also leaves `refreshModels` needing a hand-built `RefreshModelsContext`, and keeps the adapter off the runtime pi-ai actually supports.
- **Reuse the installed provider for catalog routes and `createProvider()` only for declared ones**, with no shared resolution. Zero risk to catalog behavior, but catalog materialization, endpoint override, and per-model configuration would each exist twice, and a catalog route that repoints its protocol would have to jump paths mid-resolution. The chosen split confines the asymmetry to provider construction, where it is forced by pi-ai not exposing a built provider's API implementations.
- **Rebuild every route through `createProvider()`**, including catalog ones. Fully symmetric, but a built `Provider` does not expose its `api`, so the protocol table would become the ceiling on which providers work — Bedrock loads its Smithy module through a separate entry point and would silently stop working.
- **Expose pi-ai's whole `Model` shape** (cost, input modalities, `thinkingLevelMap`, `compat`). Maximum configurability, but no current consumer read those fields then, so a configured price or modality would change nothing while reading as supported. The consumer-driven half of this arrived later: [[2026-08-08-pi-ai-per-model-reasoning-declarations]] opened reasoning (as `reasoningEfforts`, not a raw `thinkingLevelMap`) and the two reasoning-dispatch `compat` switches once selectors and dispatch actually consumed them; cost and modalities stay closed for the original reason.
- **Expose pi-ai's whole `Model` shape** (cost, input modalities, `thinkingLevelMap`, `compat`). Maximum configurability, but no current consumer read those fields then, so a configured price or modality would change nothing while reading as supported. The consumer-driven half of this arrived later, field by field as a consumer appeared: [[2026-08-08-pi-ai-per-model-reasoning-declarations]] opened reasoning (as `reasoningEfforts`, not a raw `thinkingLevelMap`) and the two reasoning-dispatch `compat` switches once selectors and dispatch actually consumed them, and [[2026-08-12-pi-ai-route-default-input-modalities]] opened modalities (as `input` and `defaultInput`, not a raw `Model.input` passthrough) once the image-admission points read them. Cost stays closed for the original reason.
- **Keep one mutable `Models` collection and re-sync it.** Fewer allocations, and correct for every operation that resolves synchronously. It is exactly wrong for the one that does not: `stream()` awaits a credential between capturing its model and dispatching it.
- **Simulate an atomic directory swap with dispose-then-register.** No seam change, and it works whenever the new set is valid — which is the case that never needed atomicity.
@@ -14,7 +14,7 @@ Status: implemented
提供方路由是一份**声明**,已安装 catalog 是它的默认值。`resolveProfiles` 不再拿路由键去核对 `getBuiltinProviders()`,而是把每条路由解析成一份物化模型列表,外加服务它的 pi-ai `Provider`
- `catalog.ts` 把已安装 catalog 合并到 profile 自身条目之下。profile 的 `models` 列表*替换*该路由的 catalog(列表缺席或为空则原样服务),每个条目从同 `id` 的已安装模型继承自身未设置的字段。只有 harness 会消费的字段可配置——`id``name``contextWindow``maxTokens`[[2026-08-08-pi-ai-per-model-reasoning-declarations]] 之后加入了 `reasoningEfforts``compat`,当初「推理(reasoning)沿用已安装条目或直接缺席」的立场也在那里被重新审视(孤立的能力布尔量仍被拒绝;带 wire 拼写的逐档位完整声明没有它那个问题)。定价与输入模态仍不出现在配置面,因为没有任何读取方`replay.ts` 把 pi-ai 的成本元数据清零,`context.ts` 只保留文本块。物化时以已安装条目铺底、再覆盖已配置的字段,而不是逐字段枚举结果:枚举式重建会静默丢弃本包未建模的每一个 `Model` 字段——`headers` 就是这样从某条 nvidia 路由上消失过一次。
- `catalog.ts` 把已安装 catalog 合并到 profile 自身条目之下。profile 的 `models` 列表*替换*该路由的 catalog(列表缺席或为空则原样服务),每个条目从同 `id` 的已安装模型继承自身未设置的字段。只有 harness 会消费的字段可配置——`id``name``contextWindow``maxTokens`[[2026-08-08-pi-ai-per-model-reasoning-declarations]] 之后加入了 `reasoningEfforts``compat`,当初「推理(reasoning)沿用已安装条目或直接缺席」的立场也在那里被重新审视(孤立的能力布尔量仍被拒绝;带 wire 拼写的逐档位完整声明没有它那个问题)。输入模态后来被开放,形态是条目上的 `input` 加路由级 `defaultInput`——图片准入点使得「未被报告的模态」变成部署无法解除的拒绝之后([[2026-08-12-pi-ai-route-default-input-modalities]]);当初「没有任何读取方」那句论证描述的其实是 `llm-deepseek` 的序列化器,而不是这条路由,它的转换器能携带图片。定价仍因原有理由不出现在配置面`replay.ts` 把 pi-ai 的成本元数据清零,且没有任何消费方报告开销。物化时以已安装条目铺底、再覆盖已配置的字段,而不是逐字段枚举结果:枚举式重建会静默丢弃本包未建模的每一个 `Model` 字段——`headers` 就是这样从某条 nvidia 路由上消失过一次。
- `provider.ts` 构造路由的 `Provider`。保持 catalog 协议不变的 catalog 路由会**复用**已安装提供方,只替换 `getModels()`;其余路由都由 `createProvider()` 基于一张协议表构造,表中条目正是 pi-ai 自己的提供方工厂所用的 `@earendil-works/pi-ai/api/*.lazy` factory。该表刻意窄于 pi-ai 的完整 API 集合——只保留 profile 能用密钥、端点与标头完整描述的协议,因此 BedrockSigV4 加 region)、Vertexproject、location、ADC)、Azure(提供方环境加 api-version)与 CodexOAuth)不在其中,而不是被当作无法认证的路由提供出去。catalog 路由仍可经自己的 provider 抵达它们;被拒的只有显式覆盖。
- `adapter.ts` 把每次解析变成一份**不可变快照**——profiles 加上持有这些 provider 的 `createModels()` 集合——每个操作都在自己第一个 `await` 之前整体捕获一份。
- 模型**显式配置**的 `maxTokens` 会成为 seam 的 `defaultMaxTokens`;从已安装 catalog 继承来的那份不会:pi-ai 要求 `Model.maxTokens` 表示模型的输出*能力*,而 `defaultMaxTokens` 是部署选定、发给未点名上限的请求的那个值,把前者物化成后者会让每个请求都被一个无人选择的数字封顶。
@@ -50,7 +50,7 @@ pi-ai 的 `Models` 自带一套凭据概念——按提供方 id 索引的 `Cred
- **保留 `createProvider()` 但不建 `Models` 集合**,改由 `provider.streamSimple(model, ctx, {apiKey})` 发起。改动最小且凭据路径原封不动,但 `createProvider``auth` 是必填字段,这条路上它永远不会被调用——一份因签名而必填、却没有调用方的实现。它还让 `refreshModels` 需要手工构造 `RefreshModelsContext`,并使适配器始终不在 pi-ai 真正支持的运行时上。
- **catalog 路由复用已安装提供方,只有声明式路由走 `createProvider()`**,且两者不共享解析。对 catalog 行为零风险,但 catalog 物化、端点覆盖与每模型配置这三件事都要各写两遍,而改指协议的 catalog 路由还得在解析中途跳到另一条路径。已采纳的拆法把不对称收敛在提供方构造这一处——那里的不对称是 pi-ai 不暴露已构造提供方的 API 实现所强加的。
- **让每条路由都经 `createProvider()` 重建**,包括 catalog 路由。完全对称,但已构造的 `Provider` 不暴露自己的 `api`,于是协议表会成为「哪些提供方能用」的天花板——Bedrock 经独立入口加载其 Smithy 模块,会因此静默失效。
- **完整暴露 pi-ai 的 `Model` 形状**(成本、输入模态、`thinkingLevelMap``compat`)。可配置性最大,但这些字段当时没有任何读取方,因此配了价格或模态什么也不会改变,却看起来像是受支持的。这条否决里由消费方驱动的那一半后来兑现了[[2026-08-08-pi-ai-per-model-reasoning-declarations]] 在选择器与分派真正消费之后开放了推理(以 `reasoningEfforts` 的形态,而非裸 `thinkingLevelMap`)和两个推理分派 `compat` 开关;成本与模态仍因原有理由保持关闭。
- **完整暴露 pi-ai 的 `Model` 形状**(成本、输入模态、`thinkingLevelMap``compat`)。可配置性最大,但这些字段当时没有任何读取方,因此配了价格或模态什么也不会改变,却看起来像是受支持的。这条否决里由消费方驱动的那一半后来逐字段兑现了,每次都等到出现真实读取方[[2026-08-08-pi-ai-per-model-reasoning-declarations]] 在选择器与分派真正消费之后开放了推理(以 `reasoningEfforts` 的形态,而非裸 `thinkingLevelMap`)和两个推理分派 `compat` 开关;[[2026-08-12-pi-ai-route-default-input-modalities]] 在图片准入点开始读取之后开放了模态(以 `input``defaultInput` 的形态,而非裸 `Model.input` 直通)。成本仍因原有理由保持关闭。
- **保留单个可变 `Models` 集合并重新同步。** 分配更少,且对每个同步完成解析的操作都是正确的;唯独对那个不同步的操作恰恰是错的:`stream()` 会在捕获模型与派发模型之间 await 一次凭据。
- **用「先 dispose 再注册」模拟目录原子替换。** 无需改 seam,且在新集合有效时确实可用——而那正是从不需要原子性的那种情形。
@@ -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/architecture/2026-08-04-declaring-a-provider-from-the-models-page.md
2026-08-04-declaring-a-provider-from-the-models-page.md: 3e7ff9c3bd58b73185c669a224a59cd017ecfb42
2026-08-04-declaring-a-provider-from-the-models-page.zh.md: a4255f8e29b696e84ff3accf636714cdfc0855f1
2026-08-04-declaring-a-provider-from-the-models-page.md: 179a31396d34228e7a0cd510edac4c535af3162e
2026-08-04-declaring-a-provider-from-the-models-page.zh.md: 3fca60554769fbf5f5be0d2bc76edf3ab3b71578
@@ -48,4 +48,4 @@ What it costs: only pi-ai routes can be hand-declared, because `llm-pi-ai` is th
## Testing
`packages/client/ui-models/tests/provider-form.spec.tsx` drives the rendered page over a scripted wire face: adding, editing, and removing rows; a cleared optional field leaving the profile and a non-integer capacity never entering it; the interrogation carrying the edited endpoint, the unsaved key, and the profile's protocol; the picker's default selection, toggling, cancel, and adopt-keeps-tuned-rows; the empty, refused, and rejected-transport paths; the create writing one profile plus its credential; every gate on the create button; and the read-only posture. `protocolChoices` is covered against a schema that declares the union and one that does not. The stylesheet gate reads the package's own sources and fails any `<select>` that takes `.input` without `.selectInput`, because the OS arrow it would otherwise keep sits flush inside the 240px cap `select.input` imposes. The editor's own field inventory is asserted per route kind — a catalog route stops at the key and the endpoint, a declared one also carries the protocol — along with the protocol edit travelling as a single `api` path op, a rename travelling as a single `displayName` one, a cleared name unsetting rather than storing the empty string the adapter refuses, and a declared profile naming no protocol selecting nothing rather than the first choice. `apps/web/tests/models-settings.e2e.ts` reopens the declared route through the real wire, captures the card, and asserts the chosen protocol and the new name both reach `settings.yaml` and the row re-registers under the rename.
`packages/client/ui-models/tests/provider-form.client.spec.tsx` drives the rendered page over a scripted wire face: adding, editing, and removing rows; a cleared optional field leaving the profile and a non-integer capacity never entering it; the interrogation carrying the edited endpoint, the unsaved key, and the profile's protocol; the picker's default selection, toggling, cancel, and adopt-keeps-tuned-rows; the empty, refused, and rejected-transport paths; the create writing one profile plus its credential; every gate on the create button; and the read-only posture. `protocolChoices` is covered against a schema that declares the union and one that does not. The stylesheet gate reads the package's own sources and fails any `<select>` that takes `.input` without `.selectInput`, because the OS arrow it would otherwise keep sits flush inside the 240px cap `select.input` imposes. The editor's own field inventory is asserted per route kind — a catalog route stops at the key and the endpoint, a declared one also carries the protocol — along with the protocol edit travelling as a single `api` path op, a rename travelling as a single `displayName` one, a cleared name unsetting rather than storing the empty string the adapter refuses, and a declared profile naming no protocol selecting nothing rather than the first choice. `apps/web/tests/models-settings.e2e.ts` reopens the declared route through the real wire, captures the card, and asserts the chosen protocol and the new name both reach `settings.yaml` and the row re-registers under the rename.
@@ -48,4 +48,4 @@ Status: implemented
## Testing
`packages/client/ui-models/tests/provider-form.spec.tsx` 在脚本化的协议面之上驱动渲染后的页面:添加、编辑与移除行;被清空的可选字段离开 profile、非整数容量从不进入;询问携带已修改的端点、未保存的密钥,以及 profile 自身的协议;选择框的默认选中、勾选切换、取消,以及「采纳保留已调优的行」;空列表、被拒、传输被拒三条路径;创建写入一份 profile 加其凭据;创建按钮上的每一道门控;以及只读姿态。`protocolChoices` 针对「声明了该 union」与「没有声明」两种 schema 都有覆盖。样式 gate 读取本包自己的源码,任何只取 `.input` 而不取 `.selectInput``<select>` 都会失败——否则它保留的系统箭头会紧贴 `select.input` 所设 240px 上限的右边缘。编辑器自身的字段清单按路由种类各有断言——内置目录路由止于密钥与端点,已声明路由还带着协议——同时覆盖协议改动只以单条 `api` path op 传出、改名只以单条 `displayName` path op 传出、清空名称是取消设置而不是存入适配器会拒绝的空串,以及不写协议的已声明 profile 什么都不选中、而非选中第一个候选。`apps/web/tests/models-settings.e2e.ts` 经真实协议层重新打开这条已声明路由,捕获该卡片,并断言选定的协议与新名称都抵达了 `settings.yaml`、该行也以新名重新注册。
`packages/client/ui-models/tests/provider-form.client.spec.tsx` 在脚本化的协议面之上驱动渲染后的页面:添加、编辑与移除行;被清空的可选字段离开 profile、非整数容量从不进入;询问携带已修改的端点、未保存的密钥,以及 profile 自身的协议;选择框的默认选中、勾选切换、取消,以及「采纳保留已调优的行」;空列表、被拒、传输被拒三条路径;创建写入一份 profile 加其凭据;创建按钮上的每一道门控;以及只读姿态。`protocolChoices` 针对「声明了该 union」与「没有声明」两种 schema 都有覆盖。样式 gate 读取本包自己的源码,任何只取 `.input` 而不取 `.selectInput``<select>` 都会失败——否则它保留的系统箭头会紧贴 `select.input` 所设 240px 上限的右边缘。编辑器自身的字段清单按路由种类各有断言——内置目录路由止于密钥与端点,已声明路由还带着协议——同时覆盖协议改动只以单条 `api` path op 传出、改名只以单条 `displayName` path op 传出、清空名称是取消设置而不是存入适配器会拒绝的空串,以及不写协议的已声明 profile 什么都不选中、而非选中第一个候选。`apps/web/tests/models-settings.e2e.ts` 经真实协议层重新打开这条已声明路由,捕获该卡片,并断言选定的协议与新名称都抵达了 `settings.yaml`、该行也以新名重新注册。
@@ -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/architecture/2026-08-05-profile-plugin-bundles.md
2026-08-05-profile-plugin-bundles.md: 54626e3f48a2ba7db19813e6e883f0e77499d0e2
2026-08-05-profile-plugin-bundles.zh.md: 357e0f63d4eba0f0985c9e14aad54595c7b41c77
2026-08-05-profile-plugin-bundles.md: ffef7b67a11617599674e0515e16bfd5283d8445
2026-08-05-profile-plugin-bundles.zh.md: b190d5e834ba3ce8b719a4a3e61f256eb2c0d82b
@@ -22,7 +22,7 @@ Two supporting refactors: the webserver's built-in static dist serving became th
- **Dependency-scan plus partial `patchOrder`** (the original sketch): scanning `dependencies` for bundles and ordering unlisted ones alphabetically has two sources of truth and an implicit tie-break; one explicit ordered `dsh.profile.bundles` list is smaller and fully deterministic. A raw `pnpm add` inside the profile installs a library without activating any patch — explicit, no spooky scan.
- **`link:` entries for in-box bundles**: pnpm cannot version, install, or update a `link:` into the installation, it embeds a machine path in a user file, and it breaks when the installation moves. The two-anchor resolution plus healed symlink fallback gives the same guarantee ("bundles come from the installation") without ceremony.
- **A pre-boot `context` module in the bundle manifest** for boot-time values (dist path, flag facts): rejected in favor of pure plugins — the glue is ordinary rows and app-owned startup services, so the composition stays fully dumpable and the manifest stays data-only. The launcher-owned `ctx.headlessIo` host hook is the one host-provided slot, and it is provided in `boot()`'s `prepare` hook, before any config-tree entry mounts.
- **A pre-boot `context` module in the bundle manifest** for boot-time values (dist path, flag facts): rejected in favor of pure plugins — the glue is ordinary rows and app-owned startup services, so the composition stays fully dumpable and the manifest stays data-only. The launcher-provided host slots (`ctx.cmdlineArgs`, `ctx.appExit`, and the environment snapshot) are provided in `boot()`'s `prepare` hook, before any config-tree entry mounts.
- **Transitive bundle auto-application**: only direct `dsh.profile.bundles` entries contribute layers; a meta-bundle wanting to re-export another bundle's patch must do so explicitly in its own patch file.
## Consequences
@@ -22,7 +22,7 @@ Status: implemented
- **依赖扫描加部分 `patchOrder`**(最初的草案):扫描 `dependencies` 找出组合包、未列出者按字母序排列,会产生两个真源和一条隐式决胜规则;一份显式有序的 `dsh.profile.bundles` 列表更小、完全确定。在 profile 内直接 `pnpm add` 只会安装一个库,不激活任何 patch——行为显式,没有暗中扫描。
- **内置组合包使用 `link:` 条目**:pnpm 无法对指向安装目录的 `link:` 做版本管理、安装或更新,它会把机器路径嵌进用户文件,并且在安装目录移动后失效。双锚点解析加上每次启动修复的符号链接回退提供了同样的保证(「组合包来自安装目录」),且没有这些繁文缛节。
- **在组合包 manifest 中放一个启动前 `context` 模块**承载启动期取值(dist 路径、flag 事实):否决,改用纯插件——粘合逻辑就是普通配置行和由应用持有的启动服务,因此组合始终可完整 dump,manifest 保持纯数据。启动器持有的 `ctx.headlessIo` 宿主钩子是唯一由宿主提供的 slot,且在任何配置树条目挂载之前,于 `boot()``prepare` 钩子中提供。
- **在组合包 manifest 中放一个启动前 `context` 模块**承载启动期取值(dist 路径、flag 事实):否决,改用纯插件——粘合逻辑就是普通配置行和由应用持有的启动服务,因此组合始终可完整 dump,manifest 保持纯数据。启动器提供的宿主 slot`ctx.cmdlineArgs``ctx.appExit` 与环境快照)在任何配置树条目挂载之前,于 `boot()``prepare` 钩子中提供。
- **组合包的传递式自动应用**:只有直接列在 `dsh.profile.bundles` 中的条目才贡献层;想重新导出另一个组合包 patch 的元组合包,必须在自己的 patch 文件中显式完成。
## Consequences
@@ -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/architecture/2026-08-06-app-owned-command-line.md
2026-08-06-app-owned-command-line.md: 4a05cac5ed7f44fb55c2d4498bf28a43befdb073
2026-08-06-app-owned-command-line.zh.md: 86a37f416d17c4615152b29d73f171803f24c4c3
2026-08-06-app-owned-command-line.md: 6d84ba457564ef250e1acfbcc71fcc91b1d49aee
2026-08-06-app-owned-command-line.zh.md: f964f7a7de7aae7e97b52fbc572443352dc5ae26
@@ -12,22 +12,21 @@ After profiles, compositions were installable but their command lines were not.
The launcher parses only what it owns — `--profile`, `--patch`, the config dumps — and hands **everything after its own flags** to the booted tree verbatim. The split is positional: the first token the launcher does not recognize starts the app's arguments (commander's `passThroughOptions` + `allowUnknownOption` + `helpOption(false)`). A bare `dsh -h`, which has no app to hand the flag to, still prints the launcher's own help.
The new `@deepseek-ai/dsh-cmdline` package owns the handoff. A launcher calls `provideCmdline(ctx, host)` before any entry mounts, providing `ctx.cmdlineArgs` (whose whole interface is `get(): readonly string[]`) and `ctx.appExit`. Any ordinary app plugin may inject `cmdlineArgs`, call `parseCmdline(ctx, program, plan)` with its own commander program, and provide the returned value as an app-owned service. Its Loader row carries no launcher marker or special kind, and the launcher does not inspect the composition for an owner. Multiple plugins may read the same immutable snapshot; a profile with no reader ignores its app arguments. Rows configured from a provider inject its service and read direct lazy config expressions (`port: !!js ctx.webStartup.port ?? 3080`), so a flag beats the value written beside it and nothing is written back into any row.
The new `@deepseek-ai/dsh-cmdline` package owns the handoff. A launcher calls `provideCmdline(ctx, host)` before any entry mounts, providing `ctx.cmdlineArgs` (whose whole interface is `get(): readonly string[]`) and `ctx.appExit`. Any ordinary app plugin may inject `cmdlineArgs`, call `parseCmdline(ctx, program)` with its own commander program, and provide the resolved value as an app-owned service from the program's action. Its Loader row carries no launcher marker or special kind, and the launcher does not inspect the composition for an owner. Multiple plugins may read the same immutable snapshot; a profile with no reader ignores its app arguments. Rows configured from a provider inject its service and read direct lazy config expressions (`port: !!js ctx.webStartup.port ?? 3080`), so a flag beats the value written beside it and nothing is written back into any row.
The boot mounts the composition once. Cordis holds each row until its injections are active; Loader then interpolates that row's `!!js` against the injection-ready plugin context immediately before activation. Include keeps nested row expressions raw until their target row reaches this point. `--help` leaves the provider's service absent, so dependent rows never activate, and a live patch reload interpolates again against the service that remains active, so a served port cannot be silently reset.
The shipped apps moved their flags into their bundles: `dsh-web-app` owns the Web family (and enables the `client-hmr` row it now ships disabled, for `--dev`), and `dsh-headless` owns the task positional and rejects a missing task as a usage error. `apps/cli/src/web.ts` is gone; `runProfile` no longer knows any flag-target row id. Out of tree, turtle-ui gained `--resume <session>` / `--session <id>` the same way, which is the design's real validation: an installed plugin added a flag with no launcher change.
The shipped apps moved their flags into their bundles: `dsh-web-app` owns the Web family, and `dsh-headless` owns the task positional and rejects a missing task as a usage error. `apps/cli/src/web.ts` is gone; `runProfile` no longer knows any flag-target row id. Out of tree, turtle-ui gained `--resume <session>` / `--session <id>` the same way, which is the design's real validation: an installed plugin added a flag with no launcher change.
Two further consequences. Loader mounts sibling rows concurrently, so one row can activate while another still mounts or while the whole boot is rolling back; the Web bundle therefore publishes its URL only after its own Loader tree settles. The Web bundle's runtime plugin owns the harness-source prompt section too, so `dsh web` and `dsh --profile web` boot identically without Web-specific launcher setup.
## Why Loader owns the ordering
Four framework facts shape the mechanism:
Three framework facts shape the mechanism:
- **A profile's rows arrive inside the root include's `patches` option.** Include is an entry-tree owner, so its static entry-config resolver interpolates Include's own options while preserving nested `!!js` nodes for their target rows instead of recursively evaluating them in the Include context.
- **A profile's rows arrive inside the root include's `patches` option.** Include declares the `EntryGroup.key` tree-carrier marker (as Group does), so Loader keeps its config — entry and patch lists, including Include's own `path` — literal instead of recursively evaluating nested `!!js` nodes in the Include context; each expression resolves in its target row's fiber.
- **Cordis activates a fiber only after all declared injections are active.** Immediately before each activation, Cordis runs the `internal/config` waterfall against the fiber's own context; Loader's listener interpolates the raw config after Cordis snapshots its injected services.
- **Provider replacement and HMR must preserve the same contract.** Fiber reactivation re-runs the waterfall, HMR carries the raw config to the replacement fiber, and a pending row accepts option changes without prematurely evaluating expressions against absent services.
- **A row cannot be inserted from inside a mounting plugin** — `tree.create` returns a prefixed id it then fails to resolve — so a conditional row ships `disabled: true` and an active row enables it (`dsh web --dev` and its reload chain). Enablement is an in-memory Loader override rather than an options rewrite, so Include reapplication cannot silently disable it. The Web bundle also starts client discovery only after enabling the optional row, ensuring the first browser graph already contains its HMR receiver.
This leaves dependency ordering in Cordis activation and Loader interpolation, which own it. Rows keep their `inject` and config, Loader mounts the composition once, and the launcher only provides argv and process-lifecycle services.
@@ -43,7 +42,7 @@ This leaves dependency ordering in Cordis activation and Loader interpolation, w
## Consequences
- An app's flags, help text, and usage errors live with the rows they configure; adding a flag to an installed plugin needs no launcher change.
- The launcher still recognizes the headless runner for one-shot process lifetime and the telemetry row for its environment switch; neither path interprets app arguments.
- The launcher recognizes no app row at all: the telemetry row remains its only composition probe (for the environment switch), SIGTERM exits 0 on every surface, every boot watches its user patch layers, and the one-shot runner exits through `ctx.appExit` like any other app.
- `--help` leaves every row that depends on the provider's service pending and requests bounded exit; unrelated rows may activate concurrently before teardown.
- An app-owned service has no statically declared provider: a bundle shipping consumer rows without that provider fails at settlement with pending entries naming the service, not at load.
- A user patch that replaces a row's whole `config` drops its expressions, and with them the flag's precedence for that row.
@@ -12,22 +12,21 @@ profile 落地之后,组合可以安装,命令行却不能。`apps/cli` 仍
启动器只解析属于自己的部分(`--profile``--patch`、配置 dump),并把**自己 flag 之后的一切**原样交给引导起来的配置树。切分按位置进行:启动器不认识的第一个 token 就是应用参数的起点(依靠 commander 的 `passThroughOptions` + `allowUnknownOption` + `helpOption(false)`)。裸的 `dsh -h` 没有可交付的应用,仍然打印启动器自己的 help。
新包 `@deepseek-ai/dsh-cmdline` 持有这次交接。启动器在任何条目挂载之前调用 `provideCmdline(ctx, host)`,提供 `ctx.cmdlineArgs`(其全部接口就是 `get(): readonly string[]`)与 `ctx.appExit`。任何普通应用插件都可以注入 `cmdlineArgs`,用自己的 commander program 调用 `parseCmdline(ctx, program, plan)`,再把返回值作为应用自有服务提供出去。它的 Loader 行不携带启动器标记或特殊类型,启动器也不会检查组合中的所有者。多个插件可以读取同一份不可变快照;没有读取方的 profile 会忽略自己的应用参数。由提供方配置的行注入其服务,并在惰性配置表达式中直接读取它(`port: !!js ctx.webStartup.port ?? 3080`),因此 flag 胜过写在它旁边的值,也没有任何东西被写回任何一行。
新包 `@deepseek-ai/dsh-cmdline` 持有这次交接。启动器在任何条目挂载之前调用 `provideCmdline(ctx, host)`,提供 `ctx.cmdlineArgs`(其全部接口就是 `get(): readonly string[]`)与 `ctx.appExit`。任何普通应用插件都可以注入 `cmdlineArgs`,用自己的 commander program 调用 `parseCmdline(ctx, program)`,再在 program 自己的 action 中把解析出的取值作为应用自有服务提供出去。它的 Loader 行不携带启动器标记或特殊类型,启动器也不会检查组合中的所有者。多个插件可以读取同一份不可变快照;没有读取方的 profile 会忽略自己的应用参数。由提供方配置的行注入其服务,并在惰性配置表达式中直接读取它(`port: !!js ctx.webStartup.port ?? 3080`),因此 flag 胜过写在它旁边的值,也没有任何东西被写回任何一行。
boot 只挂载一次整套组合。Cordis 让每一行等待其注入激活;Loader 随后在激活前一刻,基于已注入就绪的插件上下文插值该行的 `!!js`。Include 会保留嵌套的行表达式,直到目标行到达这一时点。`--help` 会让提供方服务保持缺失,因此依赖行永不激活;活动 patch 重载会针对仍然在线的服务再次插值,所以已经服务中的端口不会被悄悄重置。
已交付的各应用把自己的 flag 搬进了组合包:`dsh-web-app` 持有 Web 家族(并为 `--dev` 启用它如今以禁用状态交付的 `client-hmr` 行)`dsh-headless` 持有任务位置参数,缺少任务时按用法错误拒绝。`apps/cli/src/web.ts` 已删除;`runProfile` 不再知道任何 flag 目标行 id。在树外,turtle-ui 以同样的方式获得了 `--resume <session>` / `--session <id>`,这才是这套设计的真正验证:一个已安装的插件加上了一个 flag,启动器毫无改动。
已交付的各应用把自己的 flag 搬进了组合包:`dsh-web-app` 持有 Web 家族,`dsh-headless` 持有任务位置参数,缺少任务时按用法错误拒绝。`apps/cli/src/web.ts` 已删除;`runProfile` 不再知道任何 flag 目标行 id。在树外,turtle-ui 以同样的方式获得了 `--resume <session>` / `--session <id>`,这才是这套设计的真正验证:一个已安装的插件加上了一个 flag,启动器毫无改动。
还有两条后果。Loader 会并发挂载兄弟行,因此一行可能已经激活,而另一行仍在挂载,或整次 boot 正在回滚;所以 Web 组合包只会在自身的 Loader 配置树结算后公布 URL。另外,Web 组合包的运行时插件也持有 harness 源码提示词段,因此 `dsh web``dsh --profile web` 无需 Web 专用启动器设置即可按完全相同的方式启动。
## 为什么由 Loader 持有顺序
条框架事实塑造了这套机制:
条框架事实塑造了这套机制:
- **profile 的各行位于根 include 的 `patches` 选项内部。** Include 是条目树所有者,因此它的静态条目配置解析器会插值 Include 自身的选项,同时为目标行保留嵌套的 `!!js` 节点,而不是在 Include 上下文中递归求值
- **profile 的各行位于根 include 的 `patches` 选项内部。** Include 声明了 `EntryGroup.key` 树载体标记(与 Group 相同),因此 Loader 让它的配置——条目与 patch 列表,包括 Include 自己的 `path`——保持字面值,而不是在 Include 上下文中递归求值嵌套的 `!!js` 节点;每个表达式都在其目标行的 fiber 中解析
- **Cordis 只在所有声明的注入都已激活后才激活 fiber。** 每次激活前一刻,Cordis 会基于 fiber 自身上下文运行 `internal/config` waterfallCordis 快照注入服务之后,Loader 的监听器再插值原始配置。
- **提供方替换与 HMR 必须保持相同契约。** fiber 重新激活时会重跑 waterfall,HMR 会把原始配置带给替换 fiber,而待处理行可以接受选项变更,不会针对缺失服务提前求值表达式。
- **不能从正在挂载的插件内部插入一行**——`tree.create` 返回一个带前缀的 id,随后它自己解析不出来——因此条件性的行以 `disabled: true` 交付,再由活跃行启用(`dsh web --dev` 及其重载链路)。启用采用 Loader 的内存覆盖而非改写选项,因此 Include 重新应用配置时不会悄然将其禁用。Web 组合包还会在启用可选行之后才启动客户端发现,确保首份浏览器图中已经包含 HMR 接收端。
这样,依赖顺序仍由负责它的 Cordis 激活与 Loader 插值流程处理。各行保留自己的 `inject` 和配置,Loader 只挂载一次组合,启动器只提供 argv 与进程生命周期服务。
@@ -43,7 +42,7 @@ boot 只挂载一次整套组合。Cordis 让每一行等待其注入激活;Lo
## 后果
- 应用的 flag、help 文本和用法错误与它们所配置的行放在一起;给已安装的插件加一个 flag 不需要改动启动器。
- 启动器仍会识别 headless runner 以管理一次性进程生命周期,并识别 telemetry 行以应用环境开关;两条路径都不解析应用参数
- 启动器完全不识别任何应用行:telemetry 行仍是它唯一的组合探测(用于环境开关),SIGTERM 在所有 surface 上以 0 退出,每次启动都监视用户 patch 层,一次性 runner 像任何应用一样经 `ctx.appExit` 退出
- `--help` 会让所有依赖提供方服务的行保持待处理并请求有边界的退出;无关行可能在拆除前并发激活。
- 应用自有服务没有静态声明的提供方:交付了消费行却缺少对应提供方的组合包会在结算时失败,报出指向该服务的待处理条目,而不是在加载时失败。
- 用户 patch 若整体替换某行的 `config`,会连同其中的表达式一起丢掉,该行上 flag 的优先级也随之消失。
@@ -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/architecture/2026-08-07-shared-feedback-telemetry-user-id.md
2026-08-07-shared-feedback-telemetry-user-id.md: 6d4020828cb1f2ab3de0328c8959a18a0fcfe6c4
2026-08-07-shared-feedback-telemetry-user-id.zh.md: 892fa0f848d656609885d008ab36e3ebbe09b992
2026-08-07-shared-feedback-telemetry-user-id.md: 9e4bd02d78b11858163c36376dbb438fca8aef73
2026-08-07-shared-feedback-telemetry-user-id.zh.md: ecc451718812eb0a8b7e50bc949137fe8571ea09
@@ -1,4 +1,4 @@
# Agent Note: Shared feedback and telemetry anonymous user id
# Agent Note: Shared anonymous user id across telemetry, feedback, and DeepSeek requests
Status: implemented
@@ -8,13 +8,13 @@ English | [中文](2026-08-07-shared-feedback-telemetry-user-id.zh.md)
The OpenTelemetry backend already persisted one anonymous UUID in `$DSH_HOME/.userid`. `/feedback` now needs to report both the receiving session id and a user id so an operator can correlate the acknowledgement with exported records. Duplicating or independently generating that identity would make the reported user meaningless, while importing it from `session-telemetry-otel` would make a direct command depend on an exporter backend and create a dependency cycle when feedback export is mounted by telemetry.
The earlier [anonymous-user-id decision](../feature/2026-07-31-telemetry-anonymous-user-id.md) deliberately kept the helper inside the OTel backend until a second real consumer existed. Feedback is that consumer.
The earlier [anonymous-user-id decision](../feature/2026-07-31-telemetry-anonymous-user-id.md) deliberately kept the helper inside the OTel backend until a second real consumer existed. Feedback became that second consumer. [Direct DeepSeek request identity](../feature/2026-08-11-deepseek-request-user-id-header.md) is the third.
## Decision
`@deepseek-ai/dsh-user-id` owns `getOrCreateAnonymousUserId()` and the `$DSH_HOME/.userid` storage contract. `session-telemetry-otel` uses the returned id as OpenTelemetry Resource `user.id`; the `/feedback` success acknowledgement reports `Feedback recorded for session {sessionId}` followed by `User: {userId}` on a second line, which keeps both identifiers available through the generic command row's expandable body. Invalid feedback is rejected before resolving the id, so an empty command does not create `.userid`.
`@deepseek-ai/dsh-user-id` owns `getOrCreateAnonymousUserId()` and the `$DSH_HOME/.userid` storage contract. `session-telemetry-otel` uses the returned id as OpenTelemetry Resource `user.id`; the `/feedback` success acknowledgement reports `Feedback recorded for session {sessionId}` followed by `User: {userId}` on a second line; and direct DeepSeek requests carry it as `x-deepseek-harness-user-id`. Invalid feedback is rejected before resolving the id, and the DeepSeek adapter resolves it only after credentials succeed, so neither an empty command nor a credential failure creates `.userid`.
The extraction preserves the existing random UUID, home resolution, process memo, exclusive-create concurrency, corruption replacement, and best-effort write semantics. It does not unify the dsh-sdk launcher's separate `telemetry.json` identity.
The extraction preserves the existing random UUID, home resolution, process memo, exclusive-create concurrency, corruption replacement, and best-effort write semantics.
## Alternatives considered
@@ -23,11 +23,10 @@ The extraction preserves the existing random UUID, home resolution, process memo
| Import the helper from `session-telemetry-otel` | Couples feedback to an optional exporter backend and forms a reverse dependency cycle once telemetry exports feedback |
| Duplicate the persistence helper in feedback | Two implementations of one file contract can drift and race with different validation or failure semantics |
| Generate a separate feedback user id | The acknowledgement could not correlate with the OTel Resource and would not satisfy the reporting purpose |
| Move the launcher telemetry id too | The launcher feed is not a consumer of `.userid`; unifying unrelated stores remains out of scope |
## Consequences
- One harness home now has one anonymous id shared by feedback acknowledgements and session telemetry exports.
- One harness home has one anonymous id shared by feedback acknowledgements, session telemetry exports, and direct DeepSeek requests.
- The feedback package depends only on the identity capability, not the telemetry seam or OTel SDK.
- The new package is a justified shared seam with two consumers; its empty invariant companion explains why reading the private file is not a useful runtime relationship check.
- The package is a justified shared library with three consumers; its empty invariant companion explains why reading the private file is not a useful runtime relationship check.
- The original anonymous-user-id Note remains authoritative for storage and privacy semantics, while this Note supersedes only its OTel-local ownership decision.
@@ -1,4 +1,4 @@
# Agent Note: 反馈与遥测共享匿名用户 id
# Agent Note: 遥测、反馈与 DeepSeek 请求共享匿名用户 id
Status: implemented
@@ -8,13 +8,13 @@ Status: implemented
OpenTelemetry 后端已在 `$DSH_HOME/.userid` 中持久化一个匿名 UUID。`/feedback` 需要同时报告接收反馈的会话 id 与用户 id,以便运维人员将确认文本与导出的记录相关联。复制该身份或单独生成身份会使报告的用户失去意义;从 `session-telemetry-otel` 导入身份则会让直接命令依赖导出后端,并在遥测侧挂载反馈导出时形成依赖环。
早先的[匿名用户 id 决策](../feature/2026-07-31-telemetry-anonymous-user-id.md)刻意将辅助函数留在 OTel 后端内,直至出现第二个真实消费方。反馈就是这个消费方
早先的[匿名用户 id 决策](../feature/2026-07-31-telemetry-anonymous-user-id.md)刻意将辅助函数留在 OTel 后端内,直至出现第二个真实消费方。反馈成为第二个消费方,[直连 DeepSeek 请求身份](../feature/2026-08-11-deepseek-request-user-id-header.md)则是第三个
## 决策
`@deepseek-ai/dsh-user-id` 负责 `getOrCreateAnonymousUserId()``$DSH_HOME/.userid` 存储契约。`session-telemetry-otel` 将返回的 id 用作 OpenTelemetry Resource 的 `user.id``/feedback` 的成功确认先报告 `Feedback recorded for session {sessionId}`,再在第二行显示 `User: {userId}`,使两个标识符都可通过通用命令行的可展开正文查看。系统在获取 id 前拒绝无效反馈,因此空命令不会创建 `.userid`
`@deepseek-ai/dsh-user-id` 负责 `getOrCreateAnonymousUserId()``$DSH_HOME/.userid` 存储契约。`session-telemetry-otel` 将返回的 id 用作 OpenTelemetry Resource 的 `user.id``/feedback` 的成功确认先报告 `Feedback recorded for session {sessionId}`,再在第二行显示 `User: {userId}`;直连 DeepSeek 请求则通过 `x-deepseek-harness-user-id` 携带它。系统在获取 id 前拒绝无效反馈,DeepSeek 适配器也仅在凭据解析成功后获取 id,因此空命令和凭据失败都不会创建 `.userid`
此次抽取保留既有的随机 UUID、home 解析、进程内缓存、独占创建并发、损坏文件替换与 best-effort 写入语义。它不会统一 dsh-sdk launcher 独立的 `telemetry.json` 身份。
此次抽取保留既有的随机 UUID、home 解析、进程内缓存、独占创建并发、损坏文件替换与 best-effort 写入语义。
## 考虑过的替代方案
@@ -23,11 +23,10 @@ OpenTelemetry 后端已在 `$DSH_HOME/.userid` 中持久化一个匿名 UUID。`
| 从 `session-telemetry-otel` 导入辅助函数 | 使反馈耦合到可选的导出后端,并在遥测导出反馈后形成反向依赖环 |
| 在反馈中复制持久化辅助函数 | 同一文件契约的两份实现可能发生偏差,并因校验或失败语义不同而产生竞态 |
| 生成独立的反馈用户 id | 确认文本无法与 OTel Resource 相关联,因而不能达到报告目的 |
| 同时移动 launcher telemetry id | launcher 回流不是 `.userid` 的消费方;统一无关存储仍不在范围内 |
## 后果
- 一个 harness home 只有一个匿名 id,由反馈确认会话遥测导出共享。
- 一个 harness home 只有一个匿名 id,由反馈确认会话遥测导出与直连 DeepSeek 请求共享。
- 反馈包只依赖身份能力,不依赖遥测 seam 或 OTel SDK。
- 包由个消费方使用,成为有充分依据的共享 seam;其空不变式伴生插件解释了为何读取私有文件并非有用的运行时关系检查。
- 包由个消费方使用,成为有充分依据的共享;其空不变式伴生插件解释了为何读取私有文件并非有用的运行时关系检查。
- 原始匿名用户 id Note 仍是存储与隐私语义的权威记录;本 Note 仅取代其中由 OTel 本地拥有身份的决策。
@@ -0,0 +1,6 @@
# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each
# side as of the last confirmed-consistent state. Both languages carry equal authority;
# after editing either side, bring the other along and re-record with:
# pnpm run verify-translation-pairing --write .agents/notes/implemented/architecture/2026-08-10-remote-event-delivery.md
2026-08-10-remote-event-delivery.md: c6433ce847258a1a2768b7fb848df8e98bf4c371
2026-08-10-remote-event-delivery.zh.md: 9eb124331ba97ae498dd6500f7b0ed944d2a81ba
@@ -0,0 +1,176 @@
# Agent Note: Remote event delivery (ctx.remote.$on)
Status: implemented
English | [中文](2026-08-10-remote-event-delivery.zh.md)
## Problem
[TypeRT Gateway targeted method calls](../../implemented/architecture/2026-08-02-typert-remote-method-calls.md) cover only the request/response shape and deliberately leave Session event streams and stateful interactions to separate designs. Every **one-way Host-to-consumer push** therefore still rides the legacy API Proxy.
The Host owns a family of one-way events whose payloads are already JSON and whose emission never binds an AgentScope: `agent-preset/selected`, `commands/change`, `credentials/updated`, `llm/adapters-updated`, and `settings/document-updated`. Reaching one UI subscriber took four hops: the Host cordis event, a hand-written `HostFrame` variant plus its zod branch in apiproxy, a hand-written bridge in client/runtime that re-emitted it as a Client cordis event, and finally the consumer's `ctx.on(...)`. Adding one such event edited five places (frame union, zod union, host-stream listener, client bridge, a duplicated Client-side `Events` declaration), and not one of them stated a new fact: the name, the payload type, and the emission point were all declared by the owner package's cordis `Events` merge.
That duplicated declaration is also **lossy**: the Client side restates it as `settings/changed(ns: string)`, flattening a branded type into bare `string` — the opposite of the Remote method contract, where a consumer type points at the business package's one canonical symbol.
## Decision
The consumer Remote surface carries one one-way subscription verb, `ctx.remote.$on(event, listener)`, driven by an allowlist and forwarding verbatim:
- `packages/api/remotes/src/remote-events.ts` holds the allowlist of forwardable Host events, and it is the single control point over what a consumer may subscribe to. `src/types.ts` beside it derives the type projection and fills the selection seat, staying type-only per the package convention. Both files are listed in the `files` of **both** of this package's faces, so the Host forwarding loop and the consumer key surface read one declaration.
- The wire event name **is** the Host cordis event name (`settings/document-updated`) with no `host/` prefix, and the payload **is** the Host argument list, element for element, with no projection, redaction, or renaming.
- The carrier reuses the existing host stream: `HostFrame` gains one wrapper variant, `host/remote-event`. No new downlink.
- Event **signatures** get no second table. Each owner package moves its cordis `Events` declaration into its client-safe, type-only `./types` export, so both faces read the same declaration and `$on`'s listener type is `Events[Event]` itself. "Verbatim" then holds by construction rather than by proof.
- Only cordis's *type shape* is borrowed, not its event system: delivery semantics, the subscription registry, and failure containment belong to TypeRT.
When an `Events` entry's signature reaches a Host-only symbol (a Service, `Agent`, a Context), the answer is to **split the code until the entry lands cleanly in `./types`** — never a declaration half-left in `index.ts`, and never a structurally equivalent shadow type in `./types`. None of the five packages needs that here: their entries reach only `SettingsNamespace`, `SettingsUpdateSource`, `CredentialRef`, and `SessionId`, all pure types. The agent-presets package renames its previous vocabulary module to `preset.ts`, leaving the exported `types.ts` dedicated to the client-safe event declaration.
All five events ride this path, and their dedicated `HostFrame` variants or Client aliases are gone. Model consumers subscribe directly to both owner inputs, `llm/adapters-updated` and `settings/document-updated`; preset-derived consumers subscribe to `agent-preset/selected`. Frames that actually project or deduplicate data stay dedicated: `host/workspace-changed`/`-removed`/`host/archived-sessions-changed` (view derivation plus per-connection dedup state), and `host/session-added`/`-removed`/`host/session-status`/`host/agent-error` (live-object projection or frame-time derived fields).
`skills/change`, `tools/change`, and `system-prompt/change` have the same shape but **no consumer today**; under "require a current owner and need" they stay out of the allowlist and are recorded here only as the extension seat.
### Consumer contract (dsh-type-meta)
type-meta gains one **shape predicate**, one **selection seat**, and **one** member on `TypeRTClientRemote`. No runtime code:
```ts
import type { Events } from '@deepseek-ai/cordis'
/** Cordis events shaped for one-way remote delivery: no Scope binding, void return. */
export type TypeRTForwardableEvent = {
[Event in keyof Events]: unknown extends ThisParameterType<Events[Event]>
? ReturnType<Events[Event]> extends void ? Event : never
: never
}[keyof Events]
/** The Host assembly's forwarding selection; api/remotes' allowlist fills it, no other package does. */
export interface TypeRTRemoteEventSelection {}
/** `$on`'s legal keys: selected, and present in the current compilation face. */
export type TypeRTRemoteEvent = Extract<keyof Events, keyof TypeRTRemoteEventSelection>
```
```ts ignore-check
/** Subscribe to one forwarded Host event; the returned disposer belongs to the calling fiber. */
$on<Event extends TypeRTRemoteEvent>(event: Event, listener: Events[Event]): () => void
```
`Events` resolves per program: the full Host vocabulary in the Host program, whatever the Client face can see in the Client program. The same predicate therefore holds on both sides without dragging Host declarations into the Client.
**The surface separates the consumer verb from the carrier handoff**: consumers subscribe with `$on`, and whoever owns the Host frame sink hands each decoded frame over with `$dispatch`. It cannot be a module-level function reaching across Client plugins — the client bundle purity gate (`packages/client/tsdown.client.ts`) admits value imports only from `CLIENT_EXTERNALS`, the `INLINE_SAFE` wire layer, and generated `/remote` contributions, and inlining around it would copy `ClientRemoteService` into the runtime bundle, making `instanceof` permanently false. A cordis service method is the collaboration shape that gate prescribes:
```ts ignore-check
$dispatch(event: string, args: readonly unknown[]): void
```
client/runtime — the owner of the host frame sink — calls it directly, so the frame reaches the subscription table without an intermediate event to relay it. The `event` parameter is `string`, not `TypeRTRemoteEvent`: this is a wire boundary, and a name nobody subscribed to is dropped silently.
Delivery shares no implementation with the cordis event system: one-way only, no waterfall/bail/parallel/serial modes and no `@mode` concept (`ReturnType extends void` is the static expression of that rule), no `this` binding, no `EventOptions`, `prepend`, or priority. Listeners run in registration order, and one that throws is contained and logged — it must never take down the frame pump (the same posture `ConnectionController` already applies to its sinks).
### The allowlist: one declaration both faces read
`packages/api/remotes/src/remote-events.ts` is listed in the `files` of both `tsconfig.host.json` and `tsconfig.client.json`, and is the allowlist's single home; `src/types.ts` derives its type face:
```ts
// remote-events.ts — the value
export const API_REMOTE_FORWARDED_EVENTS = [
'agent-preset/selected',
'commands/change',
'credentials/updated',
'llm/adapters-updated',
'settings/document-updated',
] as const
// types.ts — the type face, derived
export type ApiRemoteForwardedEvent = typeof API_REMOTE_FORWARDED_EVENTS[number]
declare module '@deepseek-ai/dsh-type-meta' {
interface TypeRTRemoteEventSelection extends Record<ApiRemoteForwardedEvent, true> {}
}
```
Forwarding one more event is therefore **one line in that array**: the type projection, `$on`'s key surface, and the Host forwarding loop all derive from it. `ctx.remote.$on('slots/changed', …)` (a Client-local event) and `$on('skills/change', …)` (declared but unselected) are both **compile errors**.
The Host face adds one shape assertion, binding the Host event vocabulary to that same array:
```ts ignore-check
API_REMOTE_FORWARDED_EVENTS satisfies readonly TypeRTForwardableEvent[]
```
It is an expression statement rather than a named constant, which `noUnusedLocals` would reject (the underscore prefix exempts parameters only). It enforces three things: the **name is real** (the predicate is keyed on `keyof Events`), the event **binds no Scope** (`goal/changed` and kin have a `ThisParameterType` other than `unknown` and drop out — the static expression of "no AgentScope dependency"), and the event is **one-way** (a non-`void` return, i.e. a waterfall/bail shape, drops out).
**"Verbatim" is proved nowhere because it holds by construction**: `$on`'s listener type comes from the one cordis `Events` declaration in the owner package's `./types`, and Host forwarding reads that same declaration. There is no second declaration that could drift.
JSON-safety is a runtime concern: before forwarding, apiproxy validates each argument with `dsh-session`'s `isJsonValue` and **throws loudly** when one fails, because that is an allowlist composition mistake rather than untrusted input.
### Wire contract (apiproxy)
```ts ignore-check
| { type: 'host/remote-event'; event: string; args: JsonValue[] }
```
The zod branch keeps `args: z.array(z.unknown())`: the frame arrives from `JSON.parse`, so every element is already a JSON value, and the structural contract belongs to the owner package's `Events` declaration — the same posture the existing `session/projection` frame takes with its `value`.
`events.host()` subscribes by allowlist when the stream opens. Each stream owns its disposers, so no broadcast set or derived invalidation listener is needed.
`api/events.ts` is a wire contract file the browser side also compiles, so every type it references must come from an owner package's **client-safe, type-only subpath**, never the package root. Evidence: importing one type from `@deepseek-ai/dsh-session` root drags the root's `declare module 'cordis' { interface Context { sessions: SessionStore } }` into the Client compilation face and overrides the Client's `ctx.sessions: ISessions`, producing 18 errors in the unrelated `ui-slash` and `ui-conversation`. `JsonValue` therefore needs a re-export from `dsh-session/src/types.ts`.
### The apps/web browser e2e belong to the Host face
The `apps/web/tests/**` e2e type-check in the root **`tsconfig.host.json`**: they boot a real harness in-process and read `ctx.apiProxy`, the Host `SessionStore`'s `get`/`create`/`flush`, and `ctx.sessionProjectionCache`. **Driving a browser at runtime does not make a file part of the Client program** — moving them into the Client aggregate immediately produces 21 errors, because one program cannot hold both faces' merges for the same Context key.
That yields a discipline this design depends on: **when those tests import a value or a type from a Client package, they pull that package's whole project — and every project it references — into the Host build graph**. Four consumers (`ui-settings-general`, `ui-models`, `ui-permission`, `ui-command`) reference `api/remotes`' Client face, and that face cannot compile until Host tsdown has generated `@deepseek-ai/dsh-goal/remote`. The result is a build-order deadlock: Host tsc needs the Client face, which needs the generated artifact, which Host tsdown produces after Host tsc.
The few Client-owned symbols are therefore **mirrored** on the test side (`scaffold.ts` exports the mirrored welcome-notice constants; the two chat e2e keep importing `dsh-client-runtime/client` because the `runtime` project is already in the Host graph), which lets those four consumers leave the Host graph. The 15 Client project references in `apps/cli/tsconfig.json` lost their owner-map role and are gone. Each mirrored value matches its source verbatim; a drift shows up as a missed selector or an unsuppressed notice, both loud failures.
### Change inventory
| Location | Change |
|---|---|
| `dsh-type-meta` | `src/types.ts` gains `TypeRTForwardableEvent`, `TypeRTRemoteEventSelection`, and `TypeRTRemoteEvent`; `TypeRTClientRemote` gains `$on` and `$dispatch`. Types only, no runtime |
| `api/gateway` Client half | `ClientRemoteService` implements `$on` (subscriptions addressed by registration, `ctx.effect` ownership for the calling fiber) and `$dispatch` (snapshot delivery in registration order, containing a listener that throws or rejects) |
| `api/remotes` | New `src/remote-events.ts` (the allowlist value) and `src/types.ts` (type projection, selection seat), both listed in both faces' `files`; a `./types` export with `lib/types/**/*.js` added to `files`; the Host face adds the shape assertion and `import type {}` for the five owner `./types`; the Client half re-exports those five plus `@deepseek-ai/dsh-api-gateway/client` |
| Root `tsconfig.base.json` | Client-safe `paths` entries for settings, credentials, llm, agent-presets, and api-remotes types point at the **source** plane |
| `dsh-commands` / `dsh-settings` / `dsh-credentials` / `dsh-llm` / `dsh-agent-presets` | Each forwarded `interface Events` member lives in the owner's client-safe `./types`; agent-presets moves its previous domain vocabulary to `preset.ts` so the exported file itself remains `types.ts` |
| `host/apiproxy` | `HostFrame` gains `host/remote-event` and loses the five dedicated passthrough or invalidation variants with their zod branches; `events.host()` subscribes by allowlist and validates through `assertJsonArgs` |
| `dsh-session` | `src/types.ts` re-exports `JsonValue` so wire contract files can use the client-safe subpath |
| `client/runtime` | The five Client-event bridge branches collapse into `ctx.remote.$dispatch(frame.event, frame.args)`, adding a `remote` injection and deleting their duplicated `Events` declarations |
| Seven consumers | ui-command / ui-model / ui-models / ui-settings-general / ui-permission / ui-agent-preset / ui-skill subscribe through `ctx.remote.$on(...)`, following `ui-goal`'s precedent for the type-only facade import and the `'remote'` injection |
| `client/connection` | The fixture's `emitHost` produces `host/remote-event` |
| `apps/web/tests` + `apps/cli` | Client symbols mirrored on the test side (see above); `apps/cli/tsconfig.json` drops its 15 Client project references |
## Alternatives considered
**Open a general downlink channel for Remote events** (the push counterpart of `ctx.connection.rpc`, a third WebSocket). This best matches "Connection owns the carrier, the Gateway never touches transport", but it means a new stream in the Host downlink, `WebApiClient`, `ConnectionController`, the fixture, and the web e2e — a cost out of proportion to this change. Reusing the host stream costs a temporary tenancy inside a legacy frame union; when that stream moves, the wrapper moves with it and the consumer contract does not change.
**Declare a separate `TypeRTRemoteEventMap` in type-meta and let owner packages merge into it.** The consumer key set would equal exactly "events declared remotely deliverable", but every signature would be written a second time outside cordis `Events`, requiring a bidirectional `extends` proof to stop the two from drifting, plus a new type-meta dependency for three owner packages. Sharing the one `Events` declaration makes that equivalence structural, so the table is not created.
**Have the typert generator project Host `Events` declarations** (codec, `.d.ts`, declaration map, like `/remote`). The generator already analyzes Host events, but it cannot see projection or redaction intent, and it would change the generator and the build surface. Verbatim forwarding needs no projection.
**Give forwardable events a payload projection function** (a `{ name, project, zod }` forwarding table). This could fold the two model-directory inputs into one derived invalidation and also cover workspace view derivation, at the cost of hand-aligning projection logic with payload types — the central table the method side just removed.
**Move the apps/web browser e2e into the Client aggregate.** "Client tests belong to the Client face" looks right and fails immediately with 21 errors: those tests use Host services, and in the Client program `ctx.sessions` is `ISessions`.
**Split `directory-picker-browse`/`-native` into Host and Client faces** so no Client package reaches the Host graph. The direction is right — they are genuinely unsplit dual-half packages — but the change lands in another owner's packages and buys only a cleaner build graph; once this design mirrors the Client symbols on the test side, it no longer needs the split. **Assessed and declined.**
## Verification
What pins this behavior:
- A real composition test puts one `host/remote-event` frame on the real host stream per Host emit, with `event` the Host name and `args` equal element for element.
- Type-level negatives reject three candidate classes: a name that is not an event, a Scope-bound event (`goal/changed`), and an event whose return is not `void`. `$on('slots/changed', …)` (Client-local) and `$on('skills/change', …)` (declared but unselected) both fail to compile, so `$on`'s key surface equals the allowlist.
- On the consumer side, `$on('settings/document-updated', …)` resolves `ns` as `SettingsNamespace`: the brand survives the wire.
- `$on`'s disposer belongs to the calling fiber, and two registrations of one function object retire independently — a table keyed on listener identity would collapse them, so subscriptions are addressed by registration.
- Delivery contains a listener that throws AND one that rejects a returned promise: the declared return is `void`, so nobody awaits an async listener, and its rejection would otherwise escape this containment entirely. Delivery iterates a snapshot, so subscribing or disposing mid-frame cannot change who receives that frame.
- `assertJsonArgs` is unit-tested directly rather than by driving a malformed emit through the event bus: a typed `ctx.emit` cannot construct one, since every allowlisted event has a statically JSON-safe payload.
- The five dedicated `HostFrame` variants, five Client-side aliases, and their bridge branches are absent. The model directories observe both owner inputs, while command, skill, and session-row consumers observe the preset owner's committed-selection event.
## Consequences
- **Tenancy inside a legacy frame union.** The contract lives in apiproxy's `HostFrame`, so a reader may assume apiproxy owns Remote events. The frame's JSDoc names `api-remotes` as the allowlist owner, and apiproxy's README records the tenancy under known limitations. When the host stream moves off that package, the wrapper moves with it and the consumer contract does not change.
- **Two files break api/remotes' face-disjointness contract.** `src/remote-events.ts` and `src/types.ts` belong to both projects, so each emits an identical declaration into the shared `lib/types`. Content is byte-identical and the `.tsbuildinfo` files stay separate, so this is harmless in practice; the README's build-boundary section states the exception and its cause (the `paths` entry points at source).
- **The carrier handoff is developer-visible.** Any Client plugin holding `ctx.remote` can call `$dispatch` and synthesize a forwarded event. That exposure predates the verb — `ctx.emit` was equally reachable while an internal event relayed the frame — and matches what `connection/reset` already allows for a fabricated reconnect; the Client is one trust domain. Tests pin the handoff-to-`$on` conversion and do not pretend the port authenticates its caller.
- **A malformed argument fails in the emitter's containment, not at load.** `assertJsonArgs` throws inside the forwarding listener, so the emitting seam's listener containment logs it and drops that frame: loud in the Host log rather than at load or at the emit point.
- **Mirrored test values can drift.** Nothing mechanically checks the Client constants mirrored in `apps/web/tests` against their source; the safety net is only that a drift misses a selector. The rule lives in `apps/web/tests/README.md` and is held by review — a grep-level gate was considered and deliberately skipped.
- **Capabilities given up.** No projected or redacted payloads, no Scope-bound events (`agentCtx.remote.$on`), and no replay on reconnect — these are pure invalidation signals, and `connection/reset` already covers refetching after a reconnect. The mux stream's session events, answerable frames, and snapshot baselines stay out of scope.
- **Client packages remain in the Host graph.** Twelve projects (`connection`, `runtime`, `ui-slots`, and kin) still reach it through the unsplit `directory-picker-browse`/`-native` pair and `api/gateway → client/connection`. They compile and no longer implicate api/remotes' Client face, so they did not block this change; splitting those packages would remove a few but was assessed and declined. The two chat e2e importing `dsh-client-runtime/client` rely on `runtime` already being in that graph — incidental, not a guarantee.
- **The invariant companion holds no runtime check.** An earlier revision asserted the dispatch shape (`thisArg === null`, `mode === 'emit'`) over the live event bus, which coupled the companion to the allowlist value and made rolldown hoist it into a third bundle chunk the mechanical publication list does not carry. The Host face's `TypeRTForwardableEvent` assertion already refuses both deviations at compile time, so the companion is an explained empty installer.
@@ -0,0 +1,177 @@
# Agent Note: Remote 事件投递(ctx.remote.$on
Status: implemented
[English](2026-08-10-remote-event-delivery.md) | 中文
## 问题
[TypeRT Remote 方法调用](../../implemented/architecture/2026-08-02-typert-remote-method-calls.md)只覆盖「一次请求一个结果」的定向调用,明确把 Session 事件流与有状态交互留在别处;Host 向消费端的**单向事件推送**因此仍然全部压在遗留的 API Proxy 上。
Host 拥有 `agent-preset/selected``commands/change``credentials/updated``llm/adapters-updated``settings/document-updated` 这五条单向事件;它们既不依赖 AgentScope,载荷也本来就是 JSON。过去每条都要穿过 host cordis 事件、apiproxy 手写帧、client/runtime 手写桥和 Client 事件别名才能抵达 UI,而这些层没有陈述 owner 事件之外的新事实。
那份重复声明还是**有损**的:client 侧写成 `settings/changed(ns: string)`brand 类型在这一跳被拍平成裸 `string`,与 Remote 方法侧「消费端类型指向业务包唯一符号」的既有契约相反。
## 决策
消费端 Remote 面持有一个单向事件订阅动词 `ctx.remote.$on(event, listener)`**名单驱动、原样转发**
- `packages/api/remotes/src/remote-events.ts` 持有一份可转发 host 事件名单,它同时是「消费端能订阅什么」的唯一控制点。旁边的 `src/types.ts` 由它派生类型投影并填充 selection 座位,按包约定保持纯类型。两个文件**都同时列进本包 host 与 client 两个 face 的 `files`**,两侧读同一份。
- wire 上的事件名 **就是 host cordis 事件原名**`settings/document-updated`),不加 `host/` 前缀;载荷 **就是 host 的实参列表**,逐元素原样过 JSON,无投影、无脱敏、无改名。
- 载体**寄生现有 host 流**`HostFrame` 加一个包裹帧 `host/remote-event`,不新开下行通道。
- 事件**签名**不另立表:owner 包把自己的 cordis `Events` 声明搬进 client-safe 的 `./types` 纯类型出口,两侧读**同一份**——`$on` 的 listener 类型就是 `Events[Event]` 本身。「原样」不需要证明,是构造性成立的。
- 但**只借 cordis 的类型形状,不接 cordis 的事件系统**:投递语义、注册表、异常处置全归 TypeRT 自己。
一条 `Events` 条目若签名里够到了 host-only 符号(Service、`Agent`、Context 等),处理方式是**把代码拆到能干净落进 `./types` 为止**;不接受「一半留 index、一半搬走」的分裂声明,也不接受在 `./types` 里造结构等价的影子类型。这五个包都不需要拆:它们的条目只够到纯类型。agent-presets 把原词汇模块改名为 `preset.ts`,让导出的 `types.ts` 专门承载 client-safe 事件声明。
五条事件全部走这条路径,专用帧与 Client 别名都已删除。模型消费方直接订阅 `llm/adapters-updated``settings/document-updated`preset 消费方订阅 `agent-preset/selected`。真正需要投影或去重的数据仍保留专用帧。
`skills/change``tools/change``system-prompt/change` 是同形状的纯失效事件但目前**没有任何消费者**,按「每个抽象都要有当前 owner 与需求」不进名单,只作为扩展位记录在此。
### 消费端契约(dsh-type-meta
type-meta 加一个**形状谓词**、一个**选择座位**和 `TypeRTClientRemote` 的**一个**成员;零运行时代码:
```ts
import type { Events } from '@deepseek-ai/cordis'
/** Cordis events shaped for one-way remote delivery: no Scope binding, void return. */
export type TypeRTForwardableEvent = {
[Event in keyof Events]: unknown extends ThisParameterType<Events[Event]>
? ReturnType<Events[Event]> extends void ? Event : never
: never
}[keyof Events]
/** The Host assembly's forwarding selection; api/remotes' allowlist fills it, no other package does. */
export interface TypeRTRemoteEventSelection {}
/** `$on`'s legal keys: selected, and present in the current compilation face. */
export type TypeRTRemoteEvent = Extract<keyof Events, keyof TypeRTRemoteEventSelection>
```
```ts ignore-check
/** Subscribe to one forwarded Host event; the returned disposer belongs to the calling fiber. */
$on<Event extends TypeRTRemoteEvent>(event: Event, listener: Events[Event]): () => void
```
`Events` 按程序解析:host 程序里是 host 事件全集,client 程序里是 client 编译面看得见的那些——同一个谓词在两侧各自成立,不需要把 host 声明拖进 client。
**契约把消费动词与载体交接分开**:消费方用 `$on` 订阅,持有 host 帧 sink 的一方用 `$dispatch` 把解码后的帧交进来。它**不能**是一个跨插件的模块级函数:client bundle 纯度门禁(`packages/client/tsdown.client.ts`)只放行 `CLIENT_EXTERNALS`、`INLINE_SAFE` 那层 wire 契约与 `/remote` 生成物三类值导入,而靠 inline 绕过会把 `ClientRemoteService` 复制一份进 runtime bundle、令 `instanceof` 恒假。cordis 服务方法正是该门禁指定的协作形态:
```ts ignore-check
$dispatch(event: string, args: readonly unknown[]): void
```
持有 host 帧 sink 的 client/runtime 直接调用它,帧不经中转事件即到达订阅表。`event` 形参是 `string` 而非 `TypeRTRemoteEvent`:这是 wire 边界,收到无人订阅的名字即静默丢弃。
投递语义与 cordis 事件系统不共用实现:只有单向投递,没有 waterfall / bail / parallel / serial 模式,也没有 `@mode` 概念(`ReturnType extends void` 是这条纪律的静态表达);不绑 `this`;没有 `EventOptions`、`prepend`、优先级;按注册顺序逐个调用,单个 listener 抛错就地隔离并记日志——它绝不能拖垮帧泵(沿用 `ConnectionController` 对 sink 异常的既有处置)。
### 名单:两个 face 共读的同一份声明
`packages/api/remotes/src/remote-events.ts` 同时列进 `tsconfig.host.json` 与 `tsconfig.client.json` 的 `files`,是名单的**唯一家**`src/types.ts` 由它派生类型面:
```ts
// remote-events.ts — the value
export const API_REMOTE_FORWARDED_EVENTS = [
'agent-preset/selected',
'commands/change',
'credentials/updated',
'llm/adapters-updated',
'settings/document-updated',
] as const
// types.ts — the type face, derived
export type ApiRemoteForwardedEvent = typeof API_REMOTE_FORWARDED_EVENTS[number]
declare module '@deepseek-ai/dsh-type-meta' {
interface TypeRTRemoteEventSelection extends Record<ApiRemoteForwardedEvent, true> {}
}
```
于是**加一个事件只改这一行数组**:类型投影、`$on` 的键面、host 的转发循环全部从它派生。`ctx.remote.$on('slots/changed', …)`client 本地事件)或 `$on('skills/change', …)`(名单没开)都是**编译错误**。
host 半再加一处形状断言,把 host 事件词汇的约束落到同一份名单上:
```ts ignore-check
API_REMOTE_FORWARDED_EVENTS satisfies readonly TypeRTForwardableEvent[]
```
写成表达式语句而不是命名常量:后者会被 `noUnusedLocals` 判为未使用(下划线前缀只豁免参数)。它卡住三件事:**名字合法**(谓词以 `keyof Events` 为基)、**不绑 Scope**`goal/changed` 那族的 `ThisParameterType` 不是 `unknown`,被排除——「不依赖 AgentScope」的静态表达)、**单向**(非 `void` 返回的 waterfall/bail 形状被排除)。
**「原样」不在任何地方证明,而是构造性成立**:`$on` 的 listener 类型取自 owner 包 `./types` 里那一份 cordis `Events` 声明,host 转发读的是同一份,不存在可以彼此偏离的第二份声明。
载荷 JSON-safe 交给运行时:apiproxy 转发前用 `dsh-session` 的 `isJsonValue` 逐元素校验,不合格**抛错 fail loud**(这是名单配置错误,不是外部输入)。
### 线协议(apiproxy
```ts ignore-check
| { type: 'host/remote-event'; event: string; args: JsonValue[] }
```
zod 侧 `args: z.array(z.unknown())`:帧本身来自 `JSON.parse`,元素必然已是 JSON 值,结构契约由 owner 包的 `Events` 声明承担——与既有 `session/projection` 帧的 `value` 同 posture。
`events.host()` 打开时按名单挂监听;每条流自持 disposers,无需新增广播集合或派生失效 listener。
`api/events.ts` 是浏览器侧也要编译的 wire 契约文件,所以它引用的每个类型都必须走 owner 包的 **client-safe type-only 子路径**,绝不能走包根出口。实证:从 `@deepseek-ai/dsh-session` 根引一个类型,就把根出口的 `declare module 'cordis' { interface Context { sessions: SessionStore } }` 拖进 client 编译面、把 client 的 `ctx.sessions: ISessions` 顶掉,在完全无关的 `ui-slash` / `ui-conversation` 里炸出 18 条错。`JsonValue` 因此需要 `dsh-session/src/types.ts` 补一条 re-export。
### apps/web 的 browser e2e 属于 Host 面
`apps/web/tests/**` 那批 e2e 在**根 `tsconfig.host.json`** 做类型检查:它们在进程内起真 harness、直接摸 `ctx.apiProxy`、host `SessionStore.get/create/flush`、`ctx.sessionProjectionCache`。**运行时用浏览器 ≠ 类型上属于 client 程序**——把它们搬进 client 聚合会立刻报 21 条错,因为一个 program 装不下两个 face 对同一个 Context key 的合并。
由此得到一条对本设计要紧的连带纪律:**这些测试从客户端包 import 值或类型,会把该包的整个 project——以及它引用的每个 project——拖进 Host 构建图**。`ui-settings-general`/`ui-models`/`ui-permission`/`ui-command` 四个消费者 references `api/remotes` 的 client face,而该 face 必须等 host tsdown 生成 `@deepseek-ai/dsh-goal/remote` 才能编译,于是形成构建期死锁:host tsc → api/remotes client face → `goal/remote` → host tsdown → 排在 host tsc 之后。
所需的客户端符号在测试侧**镜像**了一份(`scaffold.ts` 导出镜像后的 welcome-notice 常量,两个 chat e2e 直接引 `dsh-client-runtime/client` 因为 `runtime` 工程本来就在 host 图里),从而让那 4 个消费者离开了 host 图;`apps/cli/tsconfig.json` 里 15 条 client 工程引用随之失去 owner-map 职责,已一并删除。镜像值与源逐字一致,漂移的表现是选择器失配或通知未被抑制,都是响亮失败。
### 改动清单
| 位置 | 改动 |
|---|---|
| `dsh-type-meta` | `src/types.ts` 加 `TypeRTForwardableEvent`、`TypeRTRemoteEventSelection`、`TypeRTRemoteEvent``TypeRTClientRemote` 增 `$on` 与 `$dispatch`。纯类型,零运行时 |
| `api/gateway` client 半 | `ClientRemoteService` 实现 `$on`(订阅按注册项寻址、`ctx.effect` 归属调用方 fiber)与 `$dispatch`(快照后按注册顺序派发,收容抛出或拒绝的 listener) |
| `api/remotes` | 新增 `src/remote-events.ts`(名单值)与 `src/types.ts`(类型投影 + 选择座位),两者都双列进两个 face 的 `files``./types` 出口 + `files` 补 `lib/types/**/*.js`host 半加形状断言并 `import type {}` 三个 owner 包的 `./types`client 半 `export type {}` 那三个 `./types` 与 `@deepseek-ai/dsh-api-gateway/client` |
| 根 `tsconfig.base.json` | 加 `dsh-settings/types`、`dsh-credentials/types`、`dsh-api-remotes/types` 三条 `paths`,全部指向**源**平面 |
| `dsh-commands` / `dsh-settings` / `dsh-credentials` | `interface Events` 子块移入各自 client-safe 的 `./types`settings/credentials 新建该出口,brand 与纯类型一并移入,index 继续 re-export 并留住构造器;`files` 补 `lib/types/**/*.js` |
| `host/apiproxy` | `HostFrame` 增 `host/remote-event`、删除五个专用变体及其 zod`events.host()` 按名单挂监听并通过 `assertJsonArgs` 校验 |
| `dsh-session` | `src/types.ts` 补 `export type { JsonValue }`,让 wire 契约文件能走 client-safe 子路径 |
| `client/runtime` | 五条 Client 事件桥分支收敛为 `ctx.remote.$dispatch(frame.event, frame.args)`,并删除重复声明 |
| 5 个消费者 | ui-command / ui-models / ui-settings-general / ui-permission / ui-agent-preset 改订 `ctx.remote.$on(...)`;照 `ui-goal` 先例 type-only 引 `@deepseek-ai/dsh-api-remotes/client` 并把 `'remote'` 加进 `inject` |
| `client/connection` | fixture 的 `emitHost` 造 `host/remote-event` |
| `apps/web/tests` + `apps/cli` | 客户端符号镜像(见上节);`apps/cli/tsconfig.json` 删 15 条 client 工程引用 |
## 备选方案
**给 Remote 事件新开一条通用下行通道**(`ctx.connection.rpc` 的推送对偶,第三条 WebSocket)。最符合「Connection 独占载体、Gateway 不碰传输」;但要同时改 host 下行、`WebApiClient`、`ConnectionController`、fixture 与 web e2e 各一条流,代价与本次收益不匹配。寄生 host 流的代价是新契约暂时寄居在 legacy 帧联合里——host 流将来整体搬家时它随之搬走,消费端契约不变。
**在 type-meta 立一张独立的 `TypeRTRemoteEventMap`,让 owner 包 declare-merge 进去**。消费端键集会精确等于「被声明为可远程投递的事件」;代价是每条事件的签名要在 cordis `Events` 之外**再写一遍**,于是需要一条双向 `extends` 的等价性证明来防漂移,还要给三个 owner 包新增 type-meta 依赖。共用同一份 `Events` 声明让等价性变成构造性成立,这张表因此不立。
**让 typert generator 从 host `Events` 声明生成事件投影**codec + `.d.ts` + 声明映射,与 `/remote` 同族)。generator 已经在分析 host 事件;但它拿不到投影与脱敏语义,且要动生成器与构建面。原样转发这条路本就不需要投影。
**给可转发事件加载荷投影函数**`{ 事件名, 投影, zod }` 转发表)。能一举覆盖 `models-changed` 的 fan-in 与 workspace 的 view 派生;代价是投影逻辑与载荷类型手工对齐,回到方法侧刚刚消灭的中心表形态。
**把 apps/web 的 browser e2e 搬进 client 聚合**。看似「客户端测试归客户端面」,实测立刻 21 条错:它们用 host 服务,而 client 程序里 `ctx.sessions` 是 `ISessions`。已否。
**给 `directory-picker-browse`/`-native` 做 host/client 双 face 切分**,从根上让客户端包不进 host 图。方向正确(它们确实是未切分的双半包),但改动落在别人属地,而收益只是「构建图更干净」——本设计在测试侧镜像客户端符号之后已经不需要它。**已评估不做**。
## 验证
钉住该行为的东西:
- 一个真组合测试:host 每 emit 一次,真实 host 流就出一帧 `host/remote-event``event` 为 host 原名、`args` 与实参逐元素相等。
- 类型层负例拒绝三类候选:不是事件的名字、绑 Scope 的事件(`goal/changed`)、返回值非 `void` 的事件。`$on('slots/changed', …)`client 本地事件)与 `$on('skills/change', …)`(已声明但未选中)都编译失败——因此 `$on` 的键面恰好等于名单。
- 消费端 `$on('settings/document-updated', …)` 把 `ns` 解析为 `SettingsNamespace`brand 穿过 wire 存活。
- `$on` 的 disposer 归属调用方 fiber;同一个函数对象订阅两次时两条注册各自独立退订——按 listener 身份做键的表会把它们合并,所以订阅按注册项寻址。
- 投递同时收容抛出的 listener 与拒绝所返回 promise 的 listener:声明返回值是 `void`,没人 await 异步 listener,其拒绝否则会完全逃出这层收容。投递遍历快照,因此派发中订阅或退订都不会改变本帧的接收者集合。
- `assertJsonArgs` 直接单测,而不是从事件总线造畸形 emit:类型化的 `ctx.emit` 造不出来——名单内每条事件的载荷在静态上都是 JSON-safe 的。
- 五个专用帧、五条 Client 别名及其桥分支都不存在;各消费方直接观察 owner 事件。
## 后果
- **寄居在 legacy 帧联合里**:契约住在 apiproxy 的 `HostFrame` 中,读者可能误以为 apiproxy 拥有 Remote 事件。该帧的 JSDoc 点名名单归 `api-remotes`apiproxy README 在 known limitations 记录这项寄居。host 流将来整体搬家时,包裹帧随之搬走,消费端契约不变。
- **两个文件打破了 api/remotes 的 face 互斥约定**`src/remote-events.ts` 与 `src/types.ts` 同属两个工程,各自向共享的 `lib/types` 发射一份相同声明。内容逐字节相同、`.tsbuildinfo` 各自独立,实践上无害;README 的构建边界节陈述了这个例外及其成因(`paths` 指向源码面)。
- **载体交接是开发者可见的**:任何持有 `ctx.remote` 的 client 插件都能调 `$dispatch` 合成一条转发事件。这个暴露面早于该动词存在——先前由内部事件中转帧时,`ctx.emit` 同样可达——与 `connection/reset` 可被伪造成重连同一量级(client 是单一信任域)。测试只钉「交接到 `$on` 的转换」,不假装该端口鉴别调用方。
- **畸形实参在发射方的收容里失败,而非加载期**:`assertJsonArgs` 在转发监听内抛出,因此由发射 seam 自己的 listener 收容记录并丢弃该帧——响亮地出现在 host 日志里,而不是加载时或 emit 点。
- **测试侧镜像值可能漂移**:没有任何机制核对 `apps/web/tests` 中镜像的 client 常量与其源;安全网只是漂移会让选择器失配。规则写在 `apps/web/tests/README.md`,由 review 守;grep 级门禁经评估后刻意不做。
- **放弃的能力**:不支持投影或脱敏载荷、不支持 Scope 化事件(`agentCtx.remote.$on`)、重连不重放——这些都是纯失效信号,且 `connection/reset` 已覆盖重连后的重新拉取。mux 流的会话事件、可应答帧与快照基线不在范围内。
- **仍有 client 包留在 host 图里**12 个工程(`connection`、`runtime`、`ui-slots` 等)经未拆分的 `directory-picker-browse`/`-native` 与 `api/gateway → client/connection` 仍可达 host 图。它们都能编译且不再牵连 api/remotes 的 client face,因此没有阻塞本次改动;拆分那些包能减少几个,但经评估后不做。两个 chat e2e 直接引 `dsh-client-runtime/client` 依赖 `runtime` 本来就在图里——属偶然而非保证。
- **invariant companion 不做运行期检查**:早先的修订曾在活事件总线上断言投递形状(`thisArg === null`、`mode === 'emit'`),这让 companion 与名单值耦合,并使 rolldown 把它提成第三个 bundle chunk——而机械推导的发布文件清单并不携带它。host 面的 `TypeRTForwardableEvent` 断言在编译期已拒绝这两种偏离,因此该 companion 是一个带说明的空 installer。
@@ -0,0 +1,6 @@
# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each
# 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/architecture/2026-08-11-cmdline-seam-trim.md
2026-08-11-cmdline-seam-trim.md: d7908d2c80552f13500ccd36c59a249f1374cbb1
2026-08-11-cmdline-seam-trim.zh.md: 275a32b584afdbcc77d2356775f35c74786445ab
@@ -0,0 +1,31 @@
# Agent Note: Trim the command-line seams to existing interfaces
Status: implemented
English | [中文](2026-08-11-cmdline-seam-trim.zh.md)
## Problem
The app-owned command line ([note](2026-08-06-app-owned-command-line.md)) shipped with three seams that were wider than their consumers needed: a vendored in-memory row-activation state machine (`Entry.enableRuntime` plus `enableRow` exported from `dsh-cmdline`, a command-line package owning a Loader concept) whose only purpose was the `--dev` conditional reload row, a vendored `EntryConfigResolver` protocol symbol whose only implementer was Include, and a launcher that still recognized the `headless-runner` row to pick SIGTERM exit codes, gate user-patch watching, and provide a `headlessIo` seam duplicating `ctx.appExit`.
## Decision
Express all three with interfaces that already exist:
- **No conditional dev row.** The reload chain stops being conditional: `dsh-web-app` mounts the `client-hmr` row unconditionally and `--dev` is deleted, along with the web runtime's `mode` config, the mode-forked prompt contract, and the `DSH_WEB_MODE` bash variable. Without a rebuild watcher (`pnpm run dev:web`) rewriting client bundles, the chain polls unchanged files and stays idle, so the always-on row costs one stat-poll interval and an SSE route. `Entry.enableRuntime`, its two state fields, and `enableRow` are deleted with nothing replacing them.
- **Tree-carrier config.** Include declares the existing `EntryGroup.key` marker instead of implementing `EntryConfigResolver`; the Loader hook keeps every tree carrier's config literal. Include's own `path` loses `!!js` support — no configuration ever used it, and the pinning test now asserts the literal tree-carrier contract instead.
- **Launcher app-knowledge.** The launcher recognizes no app row. SIGTERM is a supervisor's ordinary stop request and exits 0 on every surface (SIGINT stays 130); the launcher cannot know whether the app considered its work complete, and the previous 143 depended on naming the headless row. Every boot watches its user patch layers — a one-shot surface exits through bounded shutdown, which disposes the watchers before the loop drains. The headless runner exits through `ctx.appExit` like any other app; its output streams are a package-internal `internals` test seam, and `ctx.headlessIo` is deleted.
## Alternatives considered
- **Keeping `enableRuntime` but moving `enableRow` out of `dsh-cmdline`**: relocation fixes the package boundary but keeps the vendored state machine whose semantics (survives reapplication, rollback on failure) must be re-derived at every upstream sync.
- **`entry.update({ disabled: null })`**: mutates the entry's serialized options, so the next include reapplication restores `disabled: true` and unmounts the row mid-session.
- **SIGTERM 143 for one-shot surfaces via an app-registered signal handler**: the launcher's own handler races it for the exit code; winning that race needs a new launcher interface, which is the cost this change removes.
- **Keeping `--dev` with the row created at runtime**: an interim state of this change; it still needed a mode fork in the prompt contract, a `DSH_WEB_MODE` variable, and creation-versus-user-row arbitration, all to avoid an idle poll whose cost is negligible.
## Consequences
- A deployment that supervises `dsh --profile headless` with SIGTERM now observes exit 0 instead of 143; the caller sent the signal and sees no answer on stdout.
- The reload chain runs in every `dsh web` process; a deployment that must not expose `/plugins/events` disables the `client-hmr` row in its patch layer.
- One-shot runs mount the config-watch rows they previously skipped, costing a few milliseconds of startup.
- The vendored Loader/Include divergence shrinks by one protocol symbol and one state machine, and `rescope-vendor:check` passes again (the modification log's rescope entry is restored to the position its exact-edit anchor requires).
@@ -0,0 +1,31 @@
# Agent Note:把命令行接缝收窄到既有接口
Status: implemented
[English](2026-08-11-cmdline-seam-trim.md) | 中文
## 问题
应用自有命令行([笔记](2026-08-06-app-owned-command-line.md))交付时带着三条比其消费者所需更宽的接缝:一台 vendored 的内存行激活状态机(`Entry.enableRuntime`,外加从 `dsh-cmdline` 导出的 `enableRow` —— 一个命令行包拥有了 Loader 概念),其唯一用途是 `--dev` 条件重载行、一个只有 Include 一个实现者的 vendored `EntryConfigResolver` 协议符号,以及仍然识别 `headless-runner` 行的启动器 —— 用它选择 SIGTERM 退出码、门控用户 patch 监视,并提供与 `ctx.appExit` 重复的 `headlessIo` 接缝。
## 决策
三者全部改用已经存在的接口表达:
- **不再有条件 dev 行。** 重载链不再是条件性的:`dsh-web-app` 无条件挂载 `client-hmr` 行,`--dev` 连同 web runtime 的 `mode` 配置、按模式分叉的提示词约定和 `DSH_WEB_MODE` bash 变量一并删除。没有重建 watcher(`pnpm run dev:web`)改写客户端 bundle 时,链路轮询到的文件从不变化、保持空闲,因此常开的行只花费一个 stat 轮询间隔和一条 SSE 路由。`Entry.enableRuntime`、它的两个状态字段和 `enableRow` 删除后无任何替代物。
- **树载体配置。** Include 改为声明已有的 `EntryGroup.key` 标记,不再实现 `EntryConfigResolver`;Loader 钩子让每个树载体的配置保持字面值。Include 自己的 `path` 失去 `!!js` 支持 —— 从未有配置用过它,固定该行为的测试改为断言字面值树载体约定。
- **启动器的应用知识。** 启动器不再识别任何应用行。SIGTERM 是监督进程的普通停止请求,在所有 surface 上以 0 退出(SIGINT 仍为 130);启动器无从知道应用是否认为工作已完成,而之前的 143 依赖于点名 headless 行。每次启动都监视用户 patch 层 —— 一次性 surface 经由有界关闭退出,关闭会先 dispose 监视器再排空事件循环。headless runner 像任何应用一样经 `ctx.appExit` 退出;其输出流是包内 `internals` 测试接缝,`ctx.headlessIo` 删除。
## 考虑过的替代方案
- **保留 `enableRuntime` 但把 `enableRow` 移出 `dsh-cmdline`**:搬迁修正了包边界,却保留了 vendored 状态机,其语义(在重新应用后仍生效、失败时回滚)在每次上游同步时都要重新推导。
- **`entry.update({ disabled: null })`**:改写条目的序列化选项,下一次 include 重新应用会恢复 `disabled: true` 并在会话中途卸载该行。
- **通过应用注册的信号处理器为一次性 surface 保留 SIGTERM 143**:启动器自己的处理器会与它竞争退出码;要赢得竞争需要新的启动器接口,而这正是本次变更要移除的成本。
- **保留 `--dev`、改为运行时创建该行**:本次变更的中间形态;它仍需要提示词约定里的模式分叉、`DSH_WEB_MODE` 变量,以及创建与用户自有行之间的仲裁,而这一切只为省下一个成本可忽略的空闲轮询。
## 后果
- 用 SIGTERM 监督 `dsh --profile headless` 的部署现在观察到退出码 0 而非 143;信号是调用方自己发的,且 stdout 上没有答案。
- 重载链在每个 `dsh web` 进程中运行;不得暴露 `/plugins/events` 的部署应在其 patch 层禁用 `client-hmr` 行。
- 一次性运行会挂载之前跳过的配置监视行,启动多花几毫秒。
- vendored Loader/Include 偏差减少一个协议符号和一台状态机,`rescope-vendor:check` 重新通过(修改日志的 rescope 条目回到其精确编辑锚点要求的位置)。
@@ -0,0 +1,6 @@
# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each
# 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/architecture/2026-08-11-loader-entry-disabled-interpolation.md
2026-08-11-loader-entry-disabled-interpolation.md: fd760ea0f15f19e5f287aaddc36fb8eeb5f519ba
2026-08-11-loader-entry-disabled-interpolation.zh.md: 15f5a80931c58555dceab359d05e8515334513b2
@@ -0,0 +1,25 @@
# Agent Note: Loader interpolates the entry `disabled` field
Status: implemented
English | [中文](2026-08-11-loader-entry-disabled-interpolation.zh.md)
## Problem
The Windows platform layer (then a separate `windows.cordis.patch.yml` beside the base patch, since folded into the base rows — see Decision) disabled `tool-bash` on win32, but the shipped presets each mount a `tool-bash` row. Preset rows compose last, so the same-id row re-enabled the tool on Windows — the session had both `tool-bash` (PowerShell-backed) and `tool-pwsh`, silently, because no spec pinned the composed preset layer. Entry metadata had no conditional mechanism: `!!js` interpolates only under plugin `config`, and [postmortem 0002](../../../../docs/postmortem/0002-js-expression-disabled-filesystem-tools.md) documents that `disabled: !!js ...` stays a truthy expression object, disabling the row everywhere.
## Decision
The Loader interpolates the entry `disabled` field (`vendor/loader/src/config/entry.ts`): a `!!js` expression evaluates against the loader context at every mount decision. `disabled` is the only interpolated metadata field; `id`, `name`, `group`, and `inject` stay static. The raw node stays in the options, so write-back keeps the `!!js` form. The shipped presets (standard, code, cordis) declare the shell tool rows themselves and gate them by platform — `tool-bash` with `disabled: !!js process.platform === 'win32'` and its `tool-pwsh` twin with the inverted expression — so the preset layer exposes exactly one shell tool per host; the web-app overlay disables the host rows of both tools, letting each session's preset decide. `verify-cordis-config` now allows expressions in `disabled` only.
The mechanism completes the platform-layer fold: the base bundle's `cordis.patch.yml` gates both shell stacks on its own rows — `bash-sandbox`/`tool-bash` carry `disabled: !!js process.platform === 'win32'`, and their twins `pwsh-sandbox`/`tool-pwsh` mount only on win32 with the inverted expression. The launcher's separate Windows platform layer (`windows.cordis.patch.yml` plus `apps/cli/src/windows-shell.ts` and its injection into boot, live recomposition, and config dumps) is deleted — the layer existed only because entry metadata was static, and with `disabled` interpolated the condition lives on the row it governs.
## Alternatives considered
**A declarative `platform` field on the row.** Static and gate-checkable, but a second composition mechanism beside `!!js`, and platform is only today's condition.
**Preset-level platform overlays.** Rejected: the condition belongs on the row it governs — the same principle folds the launcher's separate Windows platform layer into the base rows.
## Consequences
A row can gate itself on platform or environment; a bad expression fails loud at boot. Every other metadata field remains literal and the gate keeps rejecting expressions there — the postmortem-0002 hazard is closed for `disabled` by evaluation, not prohibition. The Windows shell swap moved from a launcher-injected patch layer to the base bundle's own rows: win32 mounts the confined pwsh stack, POSIX carries the pwsh rows disabled, and one shared patch file serves both rosters — the [Windows pwsh default](../feature/2026-08-01-windows-pwsh-default.md) note's layer mechanism is superseded. The shell TOOL rows follow the same one-plane rule as every other preset-declared row: the web-app overlay disables the host `tool-bash`/`tool-pwsh` rows and the presets declare both with inverted platform gates, so a preset can drop or replace the shell tool per session on either host. The `minimal` preset's missing win32 PTY stack is a preset-metadata follow-up.
@@ -0,0 +1,25 @@
# Agent NoteLoader 插值条目 `disabled` 字段
Status: implemented
[English](2026-08-11-loader-entry-disabled-interpolation.md) | 中文
## 问题
Windows 平台层(当时是 base patch 旁独立的 `windows.cordis.patch.yml`,现已折入 base 行——见「决策」)在 win32 上禁用 `tool-bash`,但 shipped 预设各自挂载了一行 `tool-bash`。预设行最后组合,同名行在 Windows 上重新启用了该工具——会话同时拥有 `tool-bash`PowerShell 后端)与 `tool-pwsh`,且是静默的,因为没有 spec pin 组合后的预设层。条目元数据没有条件机制:`!!js` 只在插件 `config` 下插值,[postmortem 0002](../../../../docs/postmortem/0002-js-expression-disabled-filesystem-tools.md) 记录了 `disabled: !!js ...` 保持真值表达式对象、在所有平台上禁用该行的事故。
## 决策
Loader 插值条目 `disabled` 字段(`vendor/loader/src/config/entry.ts`):`!!js` 表达式在每次挂载决策时基于 loader 上下文求值。`disabled` 是唯一被插值的元数据字段;`id``name``group``inject` 保持静态。原始节点保留在 options 中,写回保持 `!!js` 形式。shipped 预设(standard、code、cordis)自己声明 shell 工具行并按平台门控——`tool-bash` 携带 `disabled: !!js process.platform === 'win32'`,其孪生行 `tool-pwsh` 以取反的表达式——因此预设层每台宿主恰好暴露一个 shell 工具;web-app overlay 禁用两个工具的 host 行,由每个会话的预设决定。`verify-cordis-config` 现在只允许 `disabled` 中的表达式。
该机制补全了平台层折叠:base bundle 的 `cordis.patch.yml` 在自身行上按平台门控两个 shell 栈——`bash-sandbox`/`tool-bash` 携带 `disabled: !!js process.platform === 'win32'`,它们的孪生行 `pwsh-sandbox`/`tool-pwsh` 以取反的表达式仅在 win32 挂载。启动器的独立 Windows 平台层(`windows.cordis.patch.yml` 以及 `apps/cli/src/windows-shell.ts` 及其注入到 boot、live 重组合、config dump 的逻辑)被删除——该层只因条目元数据是静态的而存在,`disabled` 可插值后条件就落在它所治理的行上。
## 备选方案
**行上的声明式 `platform` 字段。** 静态且可被门禁检查,但它是 `!!js` 之外的第二种组合机制,且平台只是今天的条件。
**预设级平台 overlay。** 被否:条件应当属于它所治理的行——同一原则把启动器独立的 Windows 平台层折入 base 行。
## 后果
行可以按平台或环境门控自身;错误的表达式在启动时响亮失败。其余元数据字段保持字面值,门禁继续拒绝那里的表达式——`disabled` 上的 postmortem-0002 隐患以「求值」而非「禁止」关闭。Windows shell 栈的切换从启动器注入的 patch 层移到 base bundle 自身的行上:win32 挂载受限 pwsh 栈,POSIX 携带被禁用的 pwsh 行,同一份 patch 文件服务两种阵容——[Windows 默认 pwsh](../feature/2026-08-01-windows-pwsh-default.md) note 的层机制已被取代。shell 工具行遵循与其他预设声明行相同的 one-plane 规则:web-app overlay 禁用 host 面的 `tool-bash`/`tool-pwsh` 行,预设以互逆的平台门控声明两者,因此任一宿主的每个会话都可以按预设丢弃或替换 shell 工具。`minimal` 预设缺失的 win32 PTY 栈是预设元数据的后续工作。
@@ -0,0 +1,6 @@
# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each
# 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/architecture/2026-08-12-pi-ai-route-default-input-modalities.md
2026-08-12-pi-ai-route-default-input-modalities.md: efd20b2cd73979208bb777fa42536bc5b918e29e
2026-08-12-pi-ai-route-default-input-modalities.zh.md: 069a7916c8d4ffe738ff910a851e0a9cd1f66d0a
@@ -0,0 +1,53 @@
# Agent Note: A pi-ai model declares its own input modalities, and undeclared means text
Status: implemented
English | [中文](2026-08-12-pi-ai-route-default-input-modalities.zh.md)
## Problem
Nothing in `settings.yaml` could describe a hand-declared pi-ai model as accepting images, and the adapter assumed text-only for every model the installed pi-ai catalog does not describe. Every model a deployment adds through the web UI's "add a custom provider" card is such a model, so an OpenAI-compatible gateway serving a vision model reported `inputModalities: ['text']` no matter what it actually served.
The harness treats an omitted modality as negative capability, and three admission points act on it before any request is built: model selection refuses to switch into a session that already holds images, prompt admission refuses an image, and `read_image` refuses to read one. Their diagnostics tell the user to select an image-capable model — advice with no reachable referent, because no configuration key could make a hand-declared model image-capable. The route was closed at the metadata, not at the capability: the request converter and every pi-ai wire protocol carry images, and `llm-pi-ai`'s own stream guard is the only thing that would have stopped one.
The assumption was justified in the source as the adapter's real capability rather than a deployment choice, and [[2026-08-03-pi-ai-declared-provider-catalog]] recorded the same reasoning when it decided which `Model` fields the configuration surface would expose ("nothing reads them: … `context.ts` keeps only text blocks"). That justification described the DeepSeek chat-completions adapter, whose serializer genuinely rejects image blocks, and had never been true of the pi-ai route. This note supersedes that one on modalities alone; pricing stays closed there for its own, still-current reason.
## Decision
**Modalities resolve entry `input` → installed catalog entry → route `defaultInput`, which itself defaults to `[text]`.** That is the chain `contextWindow` and `maxTokens` already use, field for field. pi-ai types `Model.input` required and per-model, so the entry field mirrors upstream directly: one route can serve a vision model beside a text-only one, and an override can correct a catalog model whose gateway serves other modalities than the catalog records. The route field spares a gateway whose *undescribed* models all take images from repeating itself on every entry.
**The route value is a fallback, not an override — the catalog outranks it.** This is the `default*` ordering rather than `compat`'s, and the two are not interchangeable: `compat` shadows the catalog because a route-level protocol repoint invalidates the catalog's reasoning-dispatch facts wholesale, while a modality is a per-model property the catalog states accurately for the models it ships. Making the route value win would mean `defaultInput: [text]` silently strips images from every catalog vision model on the route — a footgun with no matching benefit, since narrowing one such model is what that model's own `input` is for.
**Undeclared means `[text]`, and that is the absence of a declaration rather than a guess at the endpoint.** Nothing can interrogate a gateway for its modalities — no OpenAI-compatible listing endpoint reports them — so the only honest floor is the modality every supported protocol certainly carries. This is where the modality fallback parts company with the capacity ones: 262,144 tokens is merely plausible and wrong in both directions (a gateway serving 8k overflows, one serving 1M is wasted), while text is safe in one direction. The two wrong answers do not cost the same either. Under-claiming refuses the image before it is attached, naming the model, and the remedy is one documented line. Over-claiming admits an image the provider then rejects mid-turn, *after* prompt admission has committed the message durably, so the session keeps re-sending a request that cannot succeed and model selection refuses a switch to any text-only model. A cheap refusal at the earliest resolvable point beats an expensive one at the latest.
**An entry's empty list means the same as an absent one; the route's is refused.** `[]` describes a model that accepts nothing and could serve no request, so it states no answer and resolution continues past it. That reading is not cosmetic: the config schema materializes `[]` for an absent array, so treating it as "accepts nothing" would silently strip images from every catalog vision model a `models` list happens to name. The route value has nothing below it to answer instead, so its empty list is refused where it is written. The route's `models` list already resolves absent-and-empty the same way for the same reason.
**No configuration surface edits `input`.** It joins `compat`, `reasoningEfforts`, `thinkingBudgets`, and `headers` as a settings-document field, and the model-list editor stays a hand-written form over id, name, and the two capacities. This costs nothing durable because that card was already built to carry fields it does not edit: its row patch spreads the stored row before applying changes, and adoption keeps an existing row over a rediscovered candidate, so a hand-written `input` survives both.
The DeepSeek chat-completions adapter is untouched. Its `['text']` is a fact about its serializer, not a missing declaration, and it keeps refusing before the send.
## Alternatives considered
- **An optimistic `[text, image]` default** — makes the motivating case work with zero configuration, and the web form writes no modality at all, so a conservative default leaves the remedy in a file a web-only user has no reason to open. Rejected on the severity of being wrong: a refused attachment is a speed bump with a documented fix, while a provider rejection poisons the session, presents as an unexplained repeating failure, and is escapable only by switching models or starting over. Documenting the remedy on the model-configuration page closes the discoverability gap; nothing closes the poisoned session.
- **A route value that overrides the catalog** (`compat`'s ordering: entry → route → catalog) — lets a deployment that repoints a catalog route at its own gateway declare "no vision here" once. Rejected because the same sentence then silently disables every catalog vision model on a route where someone wrote it by analogy with the capacity fields, and the legitimate case is served by that model's own `input`. An override would also have to be named `input` at the route, since calling it `default*` beside two genuine fallbacks would misdescribe it.
- **No route field at all, only the entry one** — closest to upstream, which has no route-level concept. Rejected on the bulk case the product's own flow produces: "fetch available models" adopts thirty ids with no modality, and an all-vision gateway would need `input` hand-written on each.
- **A route-level `defaultInput` with no entry field** — cannot mix modalities on one route or correct a single catalog model, leaving "split the provider across two route keys" as the only workaround, at the cost of a second permanent provider id and a duplicate entry in every model selector.
- **Probe the endpoint for its modalities** — no OpenAI-compatible listing endpoint reports them.
- **Infer from the model id** (`*-vision`, `*-vl`) — a naming convention is not a capability, and a gateway renames freely.
- **Keep refusing and improve the diagnostic** — the message was already accurate about the state and useless about the remedy; the missing thing was the remedy.
## Consequences
A vision model on a custom provider costs one line, `input: [text, image]`, written in the settings document — or one line at the route when every model it lists takes images. That is the whole of the fix: the three admission points then admit images on it and `read_image` works. A deployment that writes nothing keeps exactly the behavior it had, so no existing route changes what it reports.
The image-admission gate keeps its meaning everywhere, because every modality it reads is now either recorded by the installed catalog or written by a person. Nothing claims a capability on a deployment's behalf.
A model that declares images its endpoint does not serve is not caught locally — the claim is not verified — and the resulting failure is expensive. Prompt admission commits the user message durably (`agent/inbox/spliced`) before the request is built, so the rejected image stays in the session log: that model keeps re-sending it, and model selection refuses a switch to any text-only model. Recovery is to select a model that does serve images, fork before the image, or start a session. Making that failure non-destructive — rolling an unconsumed image message back out of the log when the send fails — is the change that would make an optimistic default reconsiderable, and is not attempted here.
## Testing
`packages/llm/llm-pi-ai/tests/catalog.spec.ts` covers each rung of the chain and both readings of an empty list at the resolver: one route mixing an undeclared model with entry-declared text-only and vision models, a route default answering an undeclared model while an entry still outranks it, a catalog vision model keeping its modalities under a narrower route default, an entry's `[]` inheriting rather than emptying, and the route's `[]` refused. A separate case re-asserts every rung end to end — a written settings section, the plugin's own registration, and `ctx.llm.listModels` / `resolveModelInfo` — so a break between the document and `LlmModelInfo` cannot pass.
`config.spec.ts` holds the schema boundary: an unknown modality refused at both levels, the empty route list accepted by the schema and refused by the namespace validator that the settings seam actually runs, and the `[]` materialization for an absent array that the inheritance rule depends on.
No keyless snapshot lane exercises a pi-ai route: the snapshot examples drive `dsh-llm-replay`, which declares modalities directly in its configuration, and a pi-ai route needs a live endpoint whose port a static `cordis.yml` cannot name. The admission points this change feeds are already covered there through that provider (`examples/acp-agent/image.cordis.snapshot.yml` and `image-text-route.cordis.snapshot.yml`) and are unaffected — what changed is what one adapter reports, not how a gate reads it.
@@ -0,0 +1,53 @@
# Agent Notepi-ai 模型自行声明输入模态,未声明即为文本
Status: implemented
[English](2026-08-12-pi-ai-route-default-input-modalities.md) | 中文
## 问题
`settings.yaml` 里没有任何写法能把一个手写的 pi-ai 模型描述成接受图片,而适配器对已安装 pi-ai catalog 未描述的每个模型都假定纯文本。部署通过 Web UI 的“添加自定义提供商”卡片新增的模型统统属于这一类,因此一个提供视觉模型的 OpenAI 兼容网关,无论实际提供什么,报出来的都是 `inputModalities: ['text']`
Harness 把缺失的模态当作否定能力,并有三个准入点在构造任何请求之前就依据它行动:模型选择拒绝切换进已含图片的会话,prompt 准入拒绝图片,`read_image` 拒绝读取。它们的诊断让用户去选一个支持图片的模型——这条建议没有可达的指向对象,因为没有任何配置键能让手写模型变得支持图片。这条路封死在元数据上而非能力上:请求转换器和每种 pi-ai 线路协议都能携带图片,`llm-pi-ai` 自身的流前置检查才是唯一会拦下它的东西。
源码中把这一假定论证为适配器的真实能力而非部署选择,而 [[2026-08-03-pi-ai-declared-provider-catalog]] 在决定配置面公开哪些 `Model` 字段时记录了同一套论证(「没有任何读取方:…… `context.ts` 只保留文本块」)。该论证描述的是 DeepSeek chat-completions 适配器——它的序列化器确实拒绝 image block——对 pi-ai 路由从来就不成立。本 note 仅在模态一项上取代那一条;定价在那里依然因其自身、仍然成立的理由保持关闭。
## 决策
**模态的解析顺序是:条目的 `input` → 已安装 catalog 条目 → 路由的 `defaultInput`,后者自身默认为 `[text]`。** 这与 `contextWindow``maxTokens` 已经在用的链条逐字段一致。pi-ai 把 `Model.input` 定义为必填且按模型给出,因此条目字段直接镜像上游:一条路由可以让视觉模型与纯文本模型并存,而 override 可以修正那些网关实际提供的模态与 catalog 记录不符的模型。路由字段则让那些**未被 catalog 描述的**模型全都接受图片的网关,不必在每个条目上重复一遍。
**路由值是回退值而非覆盖值——catalog 的优先级更高。** 这采用的是 `default*` 的顺序而非 `compat` 的,两者不可互换:`compat` 之所以盖住 catalog,是因为路由级的协议改指会整体作废 catalog 关于推理分派的事实;而模态是按模型的属性,对 catalog 自己出货的那些模型,它记录得准确无误。让路由值获胜就意味着 `defaultInput: [text]` 会悄悄剥掉该路由上每一个 catalog 视觉模型的图片能力——一个没有对应收益的坑,因为收窄其中某个模型正是该模型自己的 `input` 要做的事。
**未声明即 `[text]`,而这是「尚未声明」,不是对端点的猜测。** 没有任何环节能去询问网关的模态——没有任何 OpenAI 兼容的列表端点会报告它们——因此唯一诚实的底线是每个受支持协议都确定携带的那个模态。这也正是模态回退值与容量回退值分道扬镳之处:262,144 只是个说得过去的数字,且两个方向都会错(网关只给 8k 会溢出,给 1M 则被浪费),而 text 在一个方向上是安全的。两种猜错的代价同样并不对等。少声明会在图片被附加之前就拒绝并点名该模型,补救办法是一行有文档可依的配置。多声明会接纳一张图片、再由提供方在轮次中途拒绝——而此时 prompt 准入**早已**把消息持久化提交,于是会话会不断重发一个不可能成功的请求,且模型选择拒绝切换到任何纯文本模型。在最早可解析点付出一次廉价的拒绝,胜过在最晚点付出一次昂贵的。
**条目的空列表与缺省同义;路由的空列表则被拒绝。** `[]` 描述的是一个什么都不接受、无法服务任何请求的模型,因此不作答,解析继续往下走。这个读法不是修辞:配置 schema 会为缺省数组物化出 `[]`,把它当作“什么都不接受”,会悄悄剥掉 `models` 列表恰好点到的每一个 catalog 视觉模型的图片能力。而路由值下面没有可以代为作答的层级,因此它的空列表在写入处即被拒绝。路由的 `models` 列表出于同样的理由,早已用同一种方式解析缺省与空。
**没有任何配置界面编辑 `input`。** 它和 `compat``reasoningEfforts``thinkingBudgets``headers` 一样是 settings 文档字段,而模型列表编辑器仍是一张只覆盖 id、名称和两个容量的手写表单。这不会带来持久代价,因为那张卡片本来就是按“承载自己并不编辑的字段”建造的:它的行 patch 会先展开已存储的行再应用改动,而采纳候选时已有行优先于重新发现的候选,因此手写的 `input` 在两条路径上都能存活。
DeepSeek chat-completions 适配器保持不动。它的 `['text']` 是关于其序列化器的事实,而不是一处缺失的声明,它继续在发送前拒绝。
## 备选方案
- **乐观的 `[text, image]` 默认值** —— 让触发本次变更的场景零配置即可工作;而且网页表单不会写入任何模态,因此保守默认值会把补救办法留在一个纯 Web 用户没有理由打开的文件里。被否决的理由是猜错时的严重程度:被拒绝的附件是一个有文档可依的减速带,而提供方拒绝会毒化整个会话、表现为一次无从解释的反复失败,且只能靠换模型或重开会话脱身。把补救办法写进配置模型页即可补上可发现性的缺口;而毒化的会话没有任何东西能补。
- **让路由值盖住 catalog**`compat` 的顺序:条目 → 路由 → catalog)—— 可以让把 catalog 路由改指到自家网关的部署,一句话声明「这里没有视觉能力」。被否决是因为同一句话也会在有人照着容量字段类比写下它的路由上,悄悄禁用每一个 catalog 视觉模型;而那个正当场景由该模型自己的 `input` 承担。覆盖值还必须在路由级改名叫 `input`,因为在两个货真价实的回退值旁边把它叫作 `default*` 是名不副实。
- **完全不要路由字段,只要条目字段** —— 最贴近上游(上游没有路由级概念)。被否决的理由是产品自身流程会产生的批量场景:「获取可用模型」一次采纳三十个不带模态的 id,全是视觉模型的网关就得逐个手写 `input`
- **只要路由级 `defaultInput`,不要条目字段** —— 无法在一条路由上混合模态,也无法修正单个 catalog 模型,唯一的变通办法只剩「把该提供方拆成两个路由键」,代价是多一个永久的 provider id 和每个模型选择器里的一项重复。
- **探测端点的模态** —— 没有任何 OpenAI 兼容的列表端点会报告它们。
- **从模型 id 推断**`*-vision``*-vl`)—— 命名约定不是能力,网关可以随意改名。
- **继续拒绝,只改进诊断** —— 那条消息对状态的描述本来就准确,对补救办法则毫无用处;缺的正是补救办法。
## 影响
自定义提供方下的视觉模型只需在 settings 文档里写一行 `input: [text, image]`——或者当该路由列出的模型全都接受图片时,在路由上写一行。这就是修复的全部:三个准入点随即接纳它上面的图片,`read_image` 也可用。什么都不写的部署保持原有行为完全不变,因此没有任何既有路由改变它报出的内容。
图片准入门禁在各处都保住了自己的意义,因为它读到的每一个模态,如今要么由已安装 catalog 记录,要么由人写下。没有任何环节会替部署宣称一项能力。
声明了端点并不提供的图片能力的模型不会在本地被拦下——该断言不经验证——而由此产生的失败代价高昂。prompt 准入在构造请求之前就把用户消息持久化提交(`agent/inbox/spliced`),因此被拒绝的图片会留在会话日志里:该模型会不断重发它,而模型选择拒绝切换到任何纯文本模型。恢复途径是选择一个确实提供图片能力的模型、fork 到图片之前,或者开启新会话。让这次失败不具破坏性——发送失败时把尚未消费的图片消息从日志中回滚出去——才是能让乐观默认值重新可考虑的那项改动,本次未做尝试。
## 测试
`packages/llm/llm-pi-ai/tests/catalog.spec.ts` 在 resolver 层覆盖了这条链的每一级以及空列表的两种读法:一条路由上未声明的模型与条目声明的纯文本、视觉模型并存,路由默认值为未声明的模型作答而条目仍然压过它,catalog 视觉模型在更窄的路由默认值下保住自身模态,条目的 `[]` 走继承而非清空,以及路由的 `[]` 被拒绝。另有一条用例把每一级端到端复验一遍——写入的 settings 段、插件自身的注册、以及 `ctx.llm.listModels` / `resolveModelInfo`——因此文档与 `LlmModelInfo` 之间若有断点无法蒙混过关。
`config.spec.ts` 负责 schema 边界:两个层级上的未知模态拒绝、路由空列表被 schema 接受而由 settings seam 真正运行的命名空间校验器拒绝,以及继承规则所倚赖的「缺省数组物化为 `[]`」这一事实。
没有任何无密钥 snapshot 通道会跑 pi-ai 路由:snapshot 示例驱动的是 `dsh-llm-replay`,它在自己的配置里直接声明模态,而 pi-ai 路由需要一个真实端点,其端口是静态 `cordis.yml` 无法写出的。本次变更所供给的那些准入点已经通过该提供方在那里得到覆盖(`examples/acp-agent/image.cordis.snapshot.yml``image-text-route.cordis.snapshot.yml`)且不受影响——改变的是某个适配器报告什么,而非门禁如何读取它。
@@ -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/bug-fix/2026-07-28-themed-scrollbars-and-reserved-gutter.md
2026-07-28-themed-scrollbars-and-reserved-gutter.md: 8ad5d801358823576c37d6b6824d7ce3fdcdac11
2026-07-28-themed-scrollbars-and-reserved-gutter.zh.md: d6d2c64703df95ea2a4ff79435512eabdb3d2f81
2026-07-28-themed-scrollbars-and-reserved-gutter.md: a820a92406ce4054f16922064772d03c6ac3ab83
2026-07-28-themed-scrollbars-and-reserved-gutter.zh.md: 80104c4aca5986c3a1f49186ac4adf3169f46da5
@@ -20,7 +20,7 @@ The rules sit on `body`, not `html`. `design-platform.css` declares the `--dsw-a
The two renderings are mutually exclusive, and the exclusion is enforced rather than assumed. A non-`auto` `scrollbar-width` or `scrollbar-color` makes Chromium and Safari discard every `::-webkit-scrollbar*` rule for that element, `::-webkit-scrollbar-thumb:hover` included. Declaring both unconditionally therefore leaves the hover token rendering nowhere at all: the engines that implement the hover pseudo-element are exactly the ones the standard properties silence, and Firefox has no hover pseudo-element to fall back on. The standard properties consequently sit inside `@supports not selector(::-webkit-scrollbar)`, which is true only where the pseudo-element is unimplemented, so Firefox takes the standard path and WebKit-based engines take the pseudo-element path. The WebKit rules are not gated in turn: an engine without those pseudo-elements drops them as unknown selectors, so a gate would only restate what selector matching already does. An engine too old for the `selector()` function makes the condition invalid, which evaluates false and selects the pseudo-element path — the correct side for the pre-16.4 Safari that is the realistic case for that reading.
Both paths read one indirection pair, `--dsh-scrollbar-thumb` and `--dsh-scrollbar-thumb-hover`, bound on `body` to the l1 (base-surface) tokens. **This is the rebinding contract, and it is the part the CSS alone does not state**: an elevated surface sets `--dsh-scrollbar-thumb: var(--dsw-alias-scrollbar-bg-l2)` and `--dsh-scrollbar-thumb-hover: var(--dsw-alias-scrollbar-hover-l2)` on its own container, and that one rebind reaches the standard properties and the WebKit pseudo-elements together. The pair is rebound as a pair; rebinding the resting thumb alone leaves the hover state on the base-surface token. `transparent` is the pair's other legal target, added when the sidebar's bars [started following the pointer](../feature/2026-08-04-pointer-revealed-sidebar-scrollbars.md); the gate below admits those two and nothing else. The mechanically discoverable subset is owned by `packages/client/ui-theme/tests/scrollbar-styles.spec.ts`: any sheet that both scrolls and paints an elevated surface must rebind, so this note no longer maintains a complete surface inventory. Most declare the pair on the elevated card rather than on the scrolling descendant, because elevation belongs to the surface and custom properties inherit to whichever child actually scrolls.
Both paths read one indirection pair, `--dsh-scrollbar-thumb` and `--dsh-scrollbar-thumb-hover`, bound on `body` to the l1 (base-surface) tokens. **This is the rebinding contract, and it is the part the CSS alone does not state**: an elevated surface sets `--dsh-scrollbar-thumb: var(--dsw-alias-scrollbar-bg-l2)` and `--dsh-scrollbar-thumb-hover: var(--dsw-alias-scrollbar-hover-l2)` on its own container, and that one rebind reaches the standard properties and the WebKit pseudo-elements together. The pair is rebound as a pair; rebinding the resting thumb alone leaves the hover state on the base-surface token. `transparent` is the pair's other legal target, added when the sidebar's bars [started following the pointer](../feature/2026-08-04-pointer-revealed-sidebar-scrollbars.md); the gate below admits those two and nothing else. The mechanically discoverable subset is owned by `packages/client/ui-theme/tests/scrollbar-styles.client.spec.ts`: any sheet that both scrolls and paints an elevated surface must rebind, so this note no longer maintains a complete surface inventory. Most declare the pair on the elevated card rather than on the scrolling descendant, because elevation belongs to the surface and custom properties inherit to whichever child actually scrolls.
Four surfaces — `Menu`, `InputBar`, `QuestionComposer`, and `TodoPanel` — were initially missed, which is why the per-sheet rebinding contract is checked mechanically rather than by inspection.
@@ -20,7 +20,7 @@ Status: implemented
两种渲染互斥,而这种互斥是被强制的,不是假定的。`scrollbar-width``scrollbar-color` 只要取非 `auto` 值,Chromium 与 Safari 就会丢弃该元素上的全部 `::-webkit-scrollbar*` 规则,`::-webkit-scrollbar-thumb:hover` 也在其中。因此无条件地同时声明会让 hover token 在任何地方都得不到渲染:实现了 hover 伪元素的引擎,恰恰就是被标准属性静音的那些,而 Firefox 没有 hover 伪元素可作退路。于是标准属性写在 `@supports not selector(::-webkit-scrollbar)` 之内,该条件只在伪元素未被实现处为真,因此 Firefox 走标准属性路径,WebKit 系引擎走伪元素路径。WebKit 规则不再反向加门禁:不实现这些伪元素的引擎会把它们当作未知选择器丢弃,因此加门禁只是重述选择器匹配本身已经做的事。对于旧到不支持 `selector()` 函数的引擎,该条件无效,从而求值为假并选中伪元素路径——对于这条判断下现实存在的 16.4 之前的 Safari,这正是正确的一侧。
两条路径都读取同一组间接变量 `--dsh-scrollbar-thumb``--dsh-scrollbar-thumb-hover`,它们在 `body` 上绑定到 l1(基础表面)token。**这就是重新绑定约定,也是单看 CSS 无法得知的部分**:抬升表面在自己的容器上设置 `--dsh-scrollbar-thumb: var(--dsw-alias-scrollbar-bg-l2)``--dsh-scrollbar-thumb-hover: var(--dsw-alias-scrollbar-hover-l2)`,这一次重新绑定同时作用于标准属性和 WebKit 伪元素。这组变量必须成对重新绑定;只改静止态滑块会让 hover 状态仍留在基础表面的 token 上。这组变量另一个合法的目标是 `transparent`,它随侧边栏滚动条[改为跟随指针](../feature/2026-08-04-pointer-revealed-sidebar-scrollbars.md)一并引入;下文的门禁只接受这两种目标。可由机械检查发现的子集归 `packages/client/ui-theme/tests/scrollbar-styles.spec.ts` 所有:任何既滚动又绘制抬升表面的样式表都必须重新绑定,因此本 note 不再维护完整的表面清单。多数把这组变量声明在抬升卡片上而非滚动的后代元素上,因为抬升层级属于这个表面,而自定义属性会继承到真正滚动的那个子元素。
两条路径都读取同一组间接变量 `--dsh-scrollbar-thumb``--dsh-scrollbar-thumb-hover`,它们在 `body` 上绑定到 l1(基础表面)token。**这就是重新绑定约定,也是单看 CSS 无法得知的部分**:抬升表面在自己的容器上设置 `--dsh-scrollbar-thumb: var(--dsw-alias-scrollbar-bg-l2)``--dsh-scrollbar-thumb-hover: var(--dsw-alias-scrollbar-hover-l2)`,这一次重新绑定同时作用于标准属性和 WebKit 伪元素。这组变量必须成对重新绑定;只改静止态滑块会让 hover 状态仍留在基础表面的 token 上。这组变量另一个合法的目标是 `transparent`,它随侧边栏滚动条[改为跟随指针](../feature/2026-08-04-pointer-revealed-sidebar-scrollbars.md)一并引入;下文的门禁只接受这两种目标。可由机械检查发现的子集归 `packages/client/ui-theme/tests/scrollbar-styles.client.spec.ts` 所有:任何既滚动又绘制抬升表面的样式表都必须重新绑定,因此本 note 不再维护完整的表面清单。多数把这组变量声明在抬升卡片上而非滚动的后代元素上,因为抬升层级属于这个表面,而自定义属性会继承到真正滚动的那个子元素。
`Menu``InputBar``QuestionComposer``TodoPanel` 这四个表面最初被漏掉,因此逐样式表的重新绑定约定由机械检查而非人工审阅把关。
@@ -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/bug-fix/2026-07-28-web-gui-feedback-loop.md
2026-07-28-web-gui-feedback-loop.md: aa488e1df087722c072d98c67d47cdf63a42f6b8
2026-07-28-web-gui-feedback-loop.zh.md: 9b6954092b737920ed18bc412037e917512e40dc
2026-07-28-web-gui-feedback-loop.md: fa7fcee80dc91ad7ec4a9a994927daa2cc293baa
2026-07-28-web-gui-feedback-loop.zh.md: ea83441efa83ad0c93e8cb1f0daf71ecfeabb69e
@@ -12,9 +12,9 @@ The [incident post-mortem](../../../../docs/postmortem/0003-web-agent-gui-feedba
## Decision
The ordinary `dsh web` composition mounts the Web bundle's `web-runtime` plugin, which publishes one canonical loopback URL and its actual runtime mode as both model-visible orientation and managed shell facts. The `app:web-surface` prompt section says that unqualified references identify this GUI and names the URL; `DSH_WEB_URL` and `DSH_WEB_MODE=production|development` carry the same facts into every foreground or managed background bash call. The section preserves the no-implicit-DOM, route, or screenshot boundary and does not claim that a LAN alias equals the browser's literal address. A complete-prompt profile sets the row's `surfaceContext` to false and receives neither the prompt section nor the managed variables; the Web launcher uses the same setting to suppress its source-checkout prompt section.
The ordinary `dsh web` composition mounts the Web bundle's `web-runtime` plugin, which publishes one canonical loopback URL as both model-visible orientation and a managed shell fact. The `app:web-surface` prompt section says that unqualified references identify this GUI and names the URL; `DSH_WEB_URL` carries the same fact into every foreground or managed background bash call. The section preserves the no-implicit-DOM, route, or screenshot boundary and does not claim that a LAN alias equals the browser's literal address. A complete-prompt profile sets the row's `surfaceContext` to false and receives neither the prompt section nor the managed variable; the Web launcher uses the same setting to suppress its source-checkout prompt section.
The mode-specific prompt makes the agent, rather than the user, own the hidden startup contract. Production mode defines acceptance as rebuilding the affected artifacts and refreshing the existing URL. Development mode states that `dsh web --dev` activates only the HMR receiver: automatic client-plugin reload additionally requires a same-checkout `pnpm run dev:web` watcher, which the agent verifies before promising no-refresh updates. Shell and other plain-package changes still require rebuild plus refresh. An agent in production mode explains both commands when a user requests no-refresh updates; it does not launch a replacement GUI unless asked.
The prompt makes the agent, rather than the user, own the hidden startup contract. The client-plugin HMR receiver is always mounted, but automatic client-plugin reload additionally requires a same-checkout `pnpm run dev:web` watcher, which the agent verifies before promising no-refresh updates. Shell and other plain-package changes still require rebuilding the affected artifacts and refreshing the existing URL. The agent does not launch a replacement GUI unless asked.
The `apps/web` development script and Vite configuration reject serve mode before opening a port. Their diagnostics identify `apps/web` as a build-only shell, explain that only `dsh web` injects `window.__DSH_BOOT__`, and name the production and HMR entry paths. Vite build mode remains unchanged.
@@ -22,7 +22,7 @@ No server restart or replacement is required merely because static artifacts cha
## Verification
The keyless fresh-round-trip browser scenario boots the shipped production Web composition, drives a real replayed session, snapshots the URL/mode-bearing system-prompt prefix, and invokes the assembled bash tool to prove `$DSH_WEB_URL` and `$DSH_WEB_MODE` match the actual bound runtime. The real CLI smoke launches `dsh web --dev` and captures the provider request, pinning the complete two-command development contract. The `dev:web` watcher test rebuilds an isolated client bundle after a source change; the browser HMR scenario launches `dsh web --dev`, changes an initial production-roster bundle, and observes the new DOM under the same page identity. A real Vite subprocess test requires serve mode to exit naturally with the full-host correction and instruments `Server.listen()` to prove it was never called. The real-Loader webserver test rewrites a static asset after the process binds and proves the same port returns the new bytes. These assertions inspect prompt state, process exit, shell output, DOM identity, and HTTP bytes rather than an agent's success statement.
The keyless fresh-round-trip browser scenario boots the shipped Web composition, drives a real replayed session, snapshots the URL-bearing system-prompt prefix, and invokes the assembled bash tool to prove `$DSH_WEB_URL` matches the actual bound runtime. The real CLI smoke launches `dsh web` and captures the provider request, pinning the complete two-command development contract. The `dev:web` watcher test rebuilds an isolated client bundle after a source change; the browser HMR scenario launches `dsh web`, changes an initial roster bundle, and observes the new DOM under the same page identity. A real Vite subprocess test requires serve mode to exit naturally with the full-host correction and instruments `Server.listen()` to prove it was never called. The real-Loader webserver test rewrites a static asset after the process binds and proves the same port returns the new bytes. These assertions inspect prompt state, process exit, shell output, DOM identity, and HTTP bytes rather than an agent's success statement.
## Alternatives considered
@@ -30,10 +30,10 @@ The keyless fresh-round-trip browser scenario boots the shipped production Web c
**Remove the `apps/web` development script without guarding Vite.** Rejected because `npx vite`, the exact incident command, bypasses package scripts. Serve mode itself must fail.
**Automatically restart or replace the current Web process after every edit.** Rejected because the static server already reads current artifacts per request, a restart would interrupt the session that requested the edit, and plugin HMR has a separate explicit `dsh web --dev` composition.
**Automatically restart or replace the current Web process after every edit.** Rejected because the static server already reads current artifacts per request, a restart would interrupt the session that requested the edit, and client-plugin reload is owned by the always-mounted HMR chain plus the `pnpm run dev:web` watcher.
**Send DOM, route, or screenshots with each request.** Deferred to a separate logged-input design. Stable URL identity closes this feedback loop without claiming browser state the host does not receive.
## Consequences
Ordinary Web prompts gain a dynamic URL-and-mode paragraph, so provider prefix reuse now varies by bound port and mode. Their Bash processes gain two non-secret managed environment variables. Bare Vite can no longer be used as a shell-only visual sandbox; developers use the full host or build mode instead. In exchange, GUI work has one mechanically observable target, the agent can teach the user the exact update behavior of the process actually serving their session, and the unsupported startup path fails before a white screen. The URL/mode contract guides the agent away from replacement ports; it does not prohibit arbitrary shell commands from starting one. Profiles that disable `surfaceContext` also give up this feedback-loop guidance and shell context.
Ordinary Web prompts gain a dynamic URL paragraph, so provider prefix reuse now varies by bound port. Their Bash processes gain one non-secret managed environment variable. Bare Vite can no longer be used as a shell-only visual sandbox; developers use the full host or build mode instead. In exchange, GUI work has one mechanically observable target, the agent can teach the user the exact update behavior of the process actually serving their session, and the unsupported startup path fails before a white screen. The URL contract guides the agent away from replacement ports; it does not prohibit arbitrary shell commands from starting one. Profiles that disable `surfaceContext` also give up this feedback-loop guidance and shell context.
@@ -12,9 +12,9 @@ Web agent(智能体)既无法识别承载当前会话的 GUI,也不知道
## 决策
常规 `dsh web` 组合会挂载 Web 组合包的 `web-runtime` 插件,由它发布一个规范的回环 URL 及其实际运行时模式,同时将二者作为模型可见的界面定位信息和受管 shell 事实。`app:web-surface` 提示词段说明:未加限定的指代指向此 GUI,并给出 URL;`DSH_WEB_URL``DSH_WEB_MODE=production|development` 会把同样的事实传入每次前台或受管后台 bash 调用。该段保留「不会隐式获得 DOM、路由或截图」这一边界,也不声称局域网别名等于浏览器中的实际地址。拥有完整提示词的 profile 会把该配置行的 `surfaceContext` 设为 false,并且不会收到该提示词段和这些受管变量中的任何一个;Web 启动器也会使用同一项设置来抑制其源码 checkout 提示词段。
常规 `dsh web` 组合会挂载 Web 组合包的 `web-runtime` 插件,由它发布一个规范的回环 URL,同时将作为模型可见的界面定位信息和受管 shell 事实。`app:web-surface` 提示词段说明:未加限定的指代指向此 GUI,并给出 URL;`DSH_WEB_URL` 会把同样的事实传入每次前台或受管后台 bash 调用。该段保留「不会隐式获得 DOM、路由或截图」这一边界,也不声称局域网别名等于浏览器中的实际地址。拥有完整提示词的 profile 会把该配置行的 `surfaceContext` 设为 false,并且不会收到该提示词段和受管变量;Web 启动器也会使用同一项设置来抑制其源码 checkout 提示词段。
按模式区分的提示词让 agent 而非用户负责隐藏的启动约定。生产模式将验收定义为重新构建受影响的产物并刷新现有 URL。开发模式说明,`dsh web --dev` 只会启用 HMR(热模块替换)接收端客户端插件要自动重新加载,还需要在同一检出中运行 `pnpm run dev:web` 监听进程,agent 会在承诺无需刷新即可更新前验证这一点。外壳和其他普通包的变更仍然需要重新构建并刷新。生产模式下的 agent 会在用户要求无需刷新即可更新时说明这两个命令;除非用户要求,否则不会启动替代 GUI。
提示词让 agent 而非用户负责隐藏的启动约定。HMR(热模块替换)接收端始终挂载,但客户端插件要自动重新加载,还需要在同一检出中运行 `pnpm run dev:web` 监听进程,agent 会在承诺无需刷新即可更新前验证这一点。外壳和其他普通包的变更仍然需要重新构建受影响的产物并刷新现有 URL。除非用户要求,agent 不会启动替代 GUI。
`apps/web` 开发脚本和 Vite 配置都会在打开端口前拒绝服务模式。诊断信息会指出 `apps/web` 只是一个仅供构建的外壳,说明只有 `dsh web` 才会注入 `window.__DSH_BOOT__`,并给出生产入口与 HMR 入口路径。Vite 构建模式保持不变。
@@ -22,7 +22,7 @@ Web agent(智能体)既无法识别承载当前会话的 GUI,也不知道
## 验证
无密钥的 fresh-round-trip 浏览器场景会启动已交付的生产 Web 组合,驱动真实的回放会话,对包含 URL 和模式的系统提示词前缀生成快照,并调用组装后的 bash 工具,证明 `$DSH_WEB_URL``$DSH_WEB_MODE` 与实际绑定的运行时一致。真实 CLI 冒烟测试会启动 `dsh web --dev` 并捕获模型提供方请求,从而固定完整的双命令开发约定。`dev:web` watcher 测试会在源码发生变化后重新构建隔离的客户端 bundle;浏览器 HMR 场景会启动 `dsh web --dev`,修改生产初始 roster 中的 bundle,并在页面 identity 不变的情况下观察新 DOM。真实 Vite 子进程测试要求服务模式在给出改用完整宿主的纠正信息后自然退出,并通过插桩 `Server.listen()` 证明它从未被调用。真实 loader Web 服务器测试会在进程完成绑定后改写静态资源,并证明同一端口返回新的字节。这些断言检查提示词状态、进程退出状态、shell 输出、DOM identity 和 HTTP 字节,而不是 agent 的成功声明。
无密钥的 fresh-round-trip 浏览器场景会启动已交付的 Web 组合,驱动真实的回放会话,对包含 URL 的系统提示词前缀生成快照,并调用组装后的 bash 工具,证明 `$DSH_WEB_URL` 与实际绑定的运行时一致。真实 CLI 冒烟测试会启动 `dsh web` 并捕获模型提供方请求,从而固定完整的双命令开发约定。`dev:web` watcher 测试会在源码发生变化后重新构建隔离的客户端 bundle;浏览器 HMR 场景会启动 `dsh web`,修改初始 roster 中的 bundle,并在页面 identity 不变的情况下观察新 DOM。真实 Vite 子进程测试要求服务模式在给出改用完整宿主的纠正信息后自然退出,并通过插桩 `Server.listen()` 证明它从未被调用。真实 loader Web 服务器测试会在进程完成绑定后改写静态资源,并证明同一端口返回新的字节。这些断言检查提示词状态、进程退出状态、shell 输出、DOM identity 和 HTTP 字节,而不是 agent 的成功声明。
## 考虑过的替代方案
@@ -30,10 +30,10 @@ Web agent(智能体)既无法识别承载当前会话的 GUI,也不知道
**删除 `apps/web` 开发脚本,但不为 Vite 添加防护。** 不予采纳,因为事故中实际使用的命令 `npx vite` 会绕过包脚本。服务模式本身必须失败。
**每次编辑后自动重启或替换当前 Web 进程。** 不予采纳,因为静态服务器本就会在每次请求时读取当前产物,重启还会中断发起编辑请求的会话,而插件 HMR 已有独立且显式的 `dsh web --dev` 组合
**每次编辑后自动重启或替换当前 Web 进程。** 不予采纳,因为静态服务器本就会在每次请求时读取当前产物,重启还会中断发起编辑请求的会话,而客户端插件重载由始终挂载的 HMR 链路加 `pnpm run dev:web` watcher 负责
**每次请求都发送 DOM、路由或截图。** 推迟到另行设计的已记录输入机制。稳定的 URL 身份足以闭合本次反馈循环,同时不会声称宿主掌握其未接收的浏览器状态。
## 影响
常规 Web 提示词会增加一个动态 URL 和模式段落,因此模型提供方的前缀复用会随绑定端口和模式变化。相应的 Bash 进程会增加个非敏感的受管环境变量。裸 Vite 不再能用作只依赖 shell 的视觉沙箱;开发者应改用完整宿主或构建模式。作为交换,GUI 工作有了一个可由机制观察的唯一目标,agent 可以向用户说明实际承载其会话的进程究竟如何更新,不受支持的启动路径也会在出现白屏前失败。URL/模式约定会引导 agent 避免使用替代端口,但不会禁止任意 shell 命令启动替代服务。禁用 `surfaceContext` 的 profile 也会放弃这项反馈闭环指引与 shell 上下文。
常规 Web 提示词会增加一个动态 URL 段落,因此模型提供方的前缀复用会随绑定端口变化。相应的 Bash 进程会增加个非敏感的受管环境变量。裸 Vite 不再能用作只依赖 shell 的视觉沙箱;开发者应改用完整宿主或构建模式。作为交换,GUI 工作有了一个可由机制观察的唯一目标,agent 可以向用户说明实际承载其会话的进程究竟如何更新,不受支持的启动路径也会在出现白屏前失败。URL 约定会引导 agent 避免使用替代端口,但不会禁止任意 shell 命令启动替代服务。禁用 `surfaceContext` 的 profile 也会放弃这项反馈闭环指引与 shell 上下文。
@@ -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/bug-fix/2026-07-30-hover-popup-pointer-grace.md
2026-07-30-hover-popup-pointer-grace.md: 3f60c98ec6453b633feebe408cbc0c0c49eedea1
2026-07-30-hover-popup-pointer-grace.zh.md: f53d77bae7b7f223621c4c42779e1a6a616aa485
2026-07-30-hover-popup-pointer-grace.md: 302592a2e9de8e749ef2450e8877a3ccbffd15d5
2026-07-30-hover-popup-pointer-grace.zh.md: 4020a6f1f7ab52b6340a07f4c099906a7353a8a5
@@ -32,4 +32,4 @@ The hover card is now hit-testable and covers 244px of whatever it overlays whil
## Testing
`packages/client/ui-primitives/tests/hover-card.spec.tsx` and `tests/atoms.spec.tsx` pin the grace boundary, cancel-on-return, no-second-dwell, disarm-on-owner-close, and the no-arming-while-closed case. The reachability gestures themselves — hovering onto the card, and moving between an open list and its trigger — are pinned in the real browser by `apps/web/tests/workspace-management.e2e.ts`, since they depend on hit testing and layout that jsdom does not model.
`packages/client/ui-primitives/tests/hover-card.client.spec.tsx` and `tests/atoms.spec.tsx` pin the grace boundary, cancel-on-return, no-second-dwell, disarm-on-owner-close, and the no-arming-while-closed case. The reachability gestures themselves — hovering onto the card, and moving between an open list and its trigger — are pinned in the real browser by `apps/web/tests/workspace-management.e2e.ts`, since they depend on hit testing and layout that jsdom does not model.
@@ -32,4 +32,4 @@ Status: implemented
## 测试
`packages/client/ui-primitives/tests/hover-card.spec.tsx``tests/atoms.spec.tsx` 固定验证宽限期边界、折返取消、不重启停留计时、所有者关闭时解除待执行关闭,以及列表关闭时不启动关闭。可抵达性手势本身——把指针移到卡片上,以及在打开的列表与其触发按钮之间移动——由 `apps/web/tests/workspace-management.e2e.ts` 在真实浏览器中固定验证,因为它们依赖 jsdom 无法建模的命中测试与布局。
`packages/client/ui-primitives/tests/hover-card.client.spec.tsx``tests/atoms.spec.tsx` 固定验证宽限期边界、折返取消、不重启停留计时、所有者关闭时解除待执行关闭,以及列表关闭时不启动关闭。可抵达性手势本身——把指针移到卡片上,以及在打开的列表与其触发按钮之间移动——由 `apps/web/tests/workspace-management.e2e.ts` 在真实浏览器中固定验证,因为它们依赖 jsdom 无法建模的命中测试与布局。
@@ -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/bug-fix/2026-07-30-web-transcript-log-ordered-projection.md
2026-07-30-web-transcript-log-ordered-projection.md: 1c65eeec0fbf0dc550043bb809ae8d7310f0602b
2026-07-30-web-transcript-log-ordered-projection.zh.md: 67bb41adde46ba7112896404ddc92a05f08f7aca
2026-07-30-web-transcript-log-ordered-projection.md: f2eda6983ab88a420a4506be7766320dc5da0fa2
2026-07-30-web-transcript-log-ordered-projection.zh.md: 4c8bb5d0b9b49762d12aba837cef9c0818740cb0
@@ -39,7 +39,7 @@ const COMPACT_PLUGIN: CompactCheckpointSource['plugin'] = 'compact'
Renaming the Service Definition's plugin id is now a compile error in the client: `TS2322: Type '"compact"' is not assignable to type '"compaction"'`. The import must stay **type-only** — a value import of any `@deepseek-ai` package that is neither a platform module nor an inline-safe wire layer is rejected by the client purity gate (`packages/client/tsdown.client.ts`), whose own message records that type-only imports are erased and never reach it. A type-only leaf import needs both a `tsconfig.base.json` `paths` entry and `{"path": "../../compact/compact"}` in `packages/client/runtime/tsconfig.json` `references`: composite `rootDir` rules apply to erased imports as well, and without the reference the diagnostic is `TS6059`/`TS6307`.
`packages/client/ui-conversation/tests/conversation-node-definitions.spec.ts` is the behavioral half, driving the compaction Definition with checkpoint and provenance records and proving that an older page can fill missing summary data. The Definition's type-only leaf import keeps the client isolated from the compact package root and the host-side `Context` merges reachable through it.
`packages/client/ui-conversation/tests/conversation-node-definitions.client.spec.ts` is the behavioral half, driving the compaction Definition with checkpoint and provenance records and proving that an older page can fill missing summary data. The Definition's type-only leaf import keeps the client isolated from the compact package root and the host-side `Context` merges reachable through it.
The divergence from the terminal is therefore narrow: both frontends recognize a checkpoint from the same declaration — the terminal value-imports `isCompactCheckpointSource` host-side, where no gate applies, and the client pins the type.
@@ -39,7 +39,7 @@ const COMPACT_PLUGIN: CompactCheckpointSource['plugin'] = 'compact'
重命名 Service Definition 的插件 id 现在会在客户端产生编译错误:`TS2322: Type '"compact"' is not assignable to type '"compaction"'`。该导入必须保持**仅类型**——任何既非平台模块又非 inline-safe wire 层的 `@deepseek-ai` 包值导入都会被客户端纯度门禁(`packages/client/tsdown.client.ts`)拒绝,而它自己的报错信息就记录着仅类型导入会被擦除、永不抵达该门禁。仅类型的叶子导入同时需要 `tsconfig.base.json` 的一条 `paths` 条目和 `packages/client/runtime/tsconfig.json` `references` 中的 `{"path": "../../compact/compact"}`composite 的 `rootDir` 规则同样适用于被擦除的导入,缺少该引用时的诊断是 `TS6059`/`TS6307`
`packages/client/ui-conversation/tests/conversation-node-definitions.spec.ts` 是行为侧的另一半,用检查点与溯源记录驱动压缩 Definition,并证明后续加载的旧分页可以补齐缺失的摘要数据。Definition 仅类型导入该叶子路径,使客户端继续与 compact 包根及经由它可达的宿主侧 `Context` 合并隔离。
`packages/client/ui-conversation/tests/conversation-node-definitions.client.spec.ts` 是行为侧的另一半,用检查点与溯源记录驱动压缩 Definition,并证明后续加载的旧分页可以补齐缺失的摘要数据。Definition 仅类型导入该叶子路径,使客户端继续与 compact 包根及经由它可达的宿主侧 `Context` 合并隔离。
因此与终端的分歧很窄:两个前端都从同一份声明识别检查点——终端在宿主侧值导入 `isCompactCheckpointSource`(那里不适用任何门禁),客户端钉住类型。
@@ -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/bug-fix/2026-07-31-composer-text-layers-share-one-scrollport.md
2026-07-31-composer-text-layers-share-one-scrollport.md: ba11384409714d6a64a964d63197705acf39d213
2026-07-31-composer-text-layers-share-one-scrollport.zh.md: 7a2500a6253c7cf50a57458b66c9b80503414ace
2026-07-31-composer-text-layers-share-one-scrollport.md: 6097779529f86e6d994296ae396f108c63f01abc
2026-07-31-composer-text-layers-share-one-scrollport.zh.md: 753d67d538d0c17512444639d60b7b5c8ff80e9a
@@ -71,7 +71,7 @@ Revealing the caret is the one thing that now depends on the browser rather than
## Testing
The unit spec in [input-bar.spec.tsx](../../../../packages/client/ui-conversation/tests/input-bar.spec.tsx) asserts what jsdom can see: that one scrolling box contains both the textarea and the backdrop, that the backdrop's text is now the draft and nothing else, and that a late persisted draft reveals its caret without taking focus from another control. jsdom reports `scrollHeight === clientHeight` for every element and never scrolls one, so the geometry belongs to the browser scenario; the wheel-chaining cases stub the scrollport's metrics rather than the textarea's.
The unit spec in [input-bar.spec.tsx](../../../../packages/client/ui-conversation/tests/input-bar.client.spec.tsx) asserts what jsdom can see: that one scrolling box contains both the textarea and the backdrop, that the backdrop's text is now the draft and nothing else, and that a late persisted draft reveals its caret without taking focus from another control. jsdom reports `scrollHeight === clientHeight` for every element and never scrolls one, so the geometry belongs to the browser scenario; the wheel-chaining cases stub the scrollport's metrics rather than the textarea's.
[composer-draft-scroll.e2e.ts](../../../../apps/web/tests/composer-draft-scroll.e2e.ts) measures the rest in chromium against the built client: a 40-line draft in a fresh workspace's blank composer, zero model calls. Every metric is read in the caret's own coordinate frame — where the textarea places line n, offset included — against a DOM Range over the backdrop's text for the same line, because that difference is what a user sees. The decisive case changes the offset and re-reads that difference **before the task ends**, which is before any `scroll` listener could have run: 0 with one scrollport, and the full delta with a mirror. A vacuity guard asserts the draft overflows the capped box first, and separate cases cover the cap, one wrap width across all three layers, a wheel gesture, a trailing-newline draft, and the caret-reveal path that the textarea's own scrolling used to handle — typing after scrolling away must bring the scrollport back to the caret.
@@ -71,7 +71,7 @@ composer 的文本由两层叠放绘制(见 [InputBar](../../../../packages/cl
## 测试
[input-bar.spec.tsx](../../../../packages/client/ui-conversation/tests/input-bar.spec.tsx) 中的单元用例断言 jsdom 能看见的部分:同一个滚动盒同时包含 textarea 与 backdropbackdrop 的文本现在就是草稿本身、不多不少,且渲染后才到达的持久化草稿会回视其光标,同时不从其他控件夺走焦点。jsdom 对任何元素都报告 `scrollHeight === clientHeight` 且从不滚动,因此几何属于浏览器场景;滚轮接力用例改为桩接滚动容器的度量,而非 textarea 的。
[input-bar.spec.tsx](../../../../packages/client/ui-conversation/tests/input-bar.client.spec.tsx) 中的单元用例断言 jsdom 能看见的部分:同一个滚动盒同时包含 textarea 与 backdropbackdrop 的文本现在就是草稿本身、不多不少,且渲染后才到达的持久化草稿会回视其光标,同时不从其他控件夺走焦点。jsdom 对任何元素都报告 `scrollHeight === clientHeight` 且从不滚动,因此几何属于浏览器场景;滚轮接力用例改为桩接滚动容器的度量,而非 textarea 的。
[composer-draft-scroll.e2e.ts](../../../../apps/web/tests/composer-draft-scroll.e2e.ts) 在 chromium 中针对构建产物度量其余部分:全新工作区的空白 composer 中一份 40 行草稿,零模型调用。每个度量都在光标自己的坐标系里读取——即 textarea 把第 n 行放在哪,含其自身偏移——再与 backdrop 同一行文本上的 DOM Range 相比,因为这个差值正是用户看到的东西。决定性的用例改变偏移,并**在本任务结束之前**重新读取该差值,也就是在任何 `scroll` 监听可能运行之前:单一滚动容器下为 0,镜像方案下则是整个增量。空洞性保护先断言草稿确实超过了带上限的盒子;其余用例分别覆盖高度上限、三层同一折行宽度、滚轮手势、以换行结尾的草稿,以及过去由 textarea 自身滚动承担的光标回视路径——滚离光标后输入,必须把滚动容器带回光标处。
@@ -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/bug-fix/2026-08-05-context-meter-blind-to-compaction.md
2026-08-05-context-meter-blind-to-compaction.md: 10ded250cec9c92d90803bdf5969cc7f5aa54c50
2026-08-05-context-meter-blind-to-compaction.zh.md: ca3fe59eecde82bb97b44af4c3383546d5672753
2026-08-05-context-meter-blind-to-compaction.md: b90208eda25101aeb55130cd1b6563dbfaee8a9a
2026-08-05-context-meter-blind-to-compaction.zh.md: 85387c50ebc981fc2f7f02d07432da677f69ef90
@@ -43,4 +43,4 @@ The panel's composition rows still do not sum to the header, and now for one cle
## Testing
`packages/llm/token-meter/tests/token-usage-projection.spec.ts` covers the carry-forward across surface growth and a compaction (the sample holding still while the projection shrinks) and the zero clamp when heuristic error would drive the figure negative. `packages/client/ui-conversation/tests/context-meter.spec.tsx` pins the ring reading the projected figure, and `chat-stats.spec.tsx` pins `contextOccupancy`'s preference and its fallback. The end-to-end numbers above came from driving `BasicCompactService.compactNow` through a real `AgentLoop` with the projection registry mounted.
`packages/llm/token-meter/tests/token-usage-projection.spec.ts` covers the carry-forward across surface growth and a compaction (the sample holding still while the projection shrinks) and the zero clamp when heuristic error would drive the figure negative. `packages/client/ui-conversation/tests/context-meter.client.spec.tsx` pins the ring reading the projected figure, and `chat-stats.spec.tsx` pins `contextOccupancy`'s preference and its fallback. The end-to-end numbers above came from driving `BasicCompactService.compactNow` through a real `AgentLoop` with the projection registry mounted.
@@ -43,4 +43,4 @@ AFTER compact: ring=4% header=~4227/100000 rows=[system 18, tools 0, messag
## 测试
`packages/llm/token-meter/tests/token-usage-projection.spec.ts` 覆盖了投影值在表层增长与一次压缩期间的延续更新(样本保持不动而投影值缩小),以及启发式误差会把数字压到负数时的零钳制。`packages/client/ui-conversation/tests/context-meter.spec.tsx` 钉住圆环读取投影值这一点,`chat-stats.spec.tsx` 钉住 `contextOccupancy` 的优先级与回退。上面那组端到端数字来自在挂载了投影注册表的真实 `AgentLoop` 上驱动 `BasicCompactService.compactNow`
`packages/llm/token-meter/tests/token-usage-projection.spec.ts` 覆盖了投影值在表层增长与一次压缩期间的延续更新(样本保持不动而投影值缩小),以及启发式误差会把数字压到负数时的零钳制。`packages/client/ui-conversation/tests/context-meter.client.spec.tsx` 钉住圆环读取投影值这一点,`chat-stats.spec.tsx` 钉住 `contextOccupancy` 的优先级与回退。上面那组端到端数字来自在挂载了投影注册表的真实 `AgentLoop` 上驱动 `BasicCompactService.compactNow`
@@ -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/bug-fix/2026-08-05-workspace-blank-session-reuse-membership.md
2026-08-05-workspace-blank-session-reuse-membership.md: 910a10e9ada1a835df7a38a04fb04c504b0921df
2026-08-05-workspace-blank-session-reuse-membership.zh.md: 0581b768679d78716c1bf70cfffec825c7281783
2026-08-05-workspace-blank-session-reuse-membership.md: 0d46a0ccf6924c508db2e6c0f3591468e2956722
2026-08-05-workspace-blank-session-reuse-membership.zh.md: e67810dc3a45d494f64a2b774557d04297b6fce3
@@ -26,4 +26,4 @@ Stray blank sessions remain visible in Ungrouped (the user can still open them)
## Testing
`packages/client/runtime/tests/workspaces-service.spec.ts` covers the four outcomes: a member blank session is reused (no create RPC); a stray blank with matching cwd is **not** reused and a fresh accounted session is created (regression case); an archived blank is not reused; a rejected first prompt keeps a member blank eligible. The full client suite (`pnpm run test:gui`) stays green.
`packages/client/runtime/tests/workspaces-service.client.spec.ts` covers the four outcomes: a member blank session is reused (no create RPC); a stray blank with matching cwd is **not** reused and a fresh accounted session is created (regression case); an archived blank is not reused; a rejected first prompt keeps a member blank eligible. The full client suite (`pnpm run test:gui`) stays green.
@@ -26,4 +26,4 @@ Status: implemented
## 测试
`packages/client/runtime/tests/workspaces-service.spec.ts` 覆盖四种结果:成员空白会话被复用(无 create RPC);cwd 匹配但非成员的游离空白会话**不被**复用、改为创建全新入账会话(回归用例);已归档空白会话不被复用;首次提示词被拒后成员空白会话仍可复用。完整客户端套件(`pnpm run test:gui`)保持绿色。
`packages/client/runtime/tests/workspaces-service.client.spec.ts` 覆盖四种结果:成员空白会话被复用(无 create RPC);cwd 匹配但非成员的游离空白会话**不被**复用、改为创建全新入账会话(回归用例);已归档空白会话不被复用;首次提示词被拒后成员空白会话仍可复用。完整客户端套件(`pnpm run test:gui`)保持绿色。
@@ -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/bug-fix/2026-08-06-onboarding-step-owned-takeover-chrome.md
2026-08-06-onboarding-step-owned-takeover-chrome.md: 4b3bbbc03c4494359297ae6e54bcc9a74c387e80
2026-08-06-onboarding-step-owned-takeover-chrome.zh.md: ba4f503f7bc318fcb16f4413465a86609fa1bc61
2026-08-06-onboarding-step-owned-takeover-chrome.md: 97f5335412f256bf7e60f36731c9e0c4475ee99e
2026-08-06-onboarding-step-owned-takeover-chrome.zh.md: 054072764a7b9a25586899a93596fdc922e71dcb
@@ -32,4 +32,4 @@ A future step that registers without wrapping its visible content in `Onboarding
## Testing
`packages/client/ui-primitives/tests/onboarding-surface.spec.tsx` pins the primitive: body portal around the content, mask/stage class presence, `#root` inert held for exactly the mount lifetime, and the no-`#root` composition. `packages/client/ui-settings/tests/settings-root.spec.tsx` pins the inverted shell contract: no takeover chrome and no inert while a mounted step renders nothing. `apps/web/tests/onboarding-deepseek-config.e2e.ts` gains the defect's assembled regression pin: a configured world reloads while every `settings.describe` response is held open at the browser's network boundary — widening the steps' deciding window from loopback-invisible to hundreds of milliseconds, which is what keeps the assertions non-vacuous — and an 8 ms in-page sampler proves the takeover chrome never mounts and `#root` never turns inert. The file's existing scenarios and the step specs (`ui-settings-general`, `ui-models`) pass unchanged — the mask selector and geometry pins survive because the stylesheet moved verbatim.
`packages/client/ui-primitives/tests/onboarding-surface.client.spec.tsx` pins the primitive: body portal around the content, mask/stage class presence, `#root` inert held for exactly the mount lifetime, and the no-`#root` composition. `packages/client/ui-settings-general/tests/settings-root.client.spec.tsx` pins the inverted shell contract: no takeover chrome and no inert while a mounted step renders nothing. `apps/web/tests/onboarding-deepseek-config.e2e.ts` gains the defect's assembled regression pin: a configured world reloads while every `settings.describe` response is held open at the browser's network boundary — widening the steps' deciding window from loopback-invisible to hundreds of milliseconds, which is what keeps the assertions non-vacuous — and an 8 ms in-page sampler proves the takeover chrome never mounts and `#root` never turns inert. The file's existing scenarios and the step specs (`ui-settings-general`, `ui-models`) pass unchanged — the mask selector and geometry pins survive because the stylesheet moved verbatim.
@@ -32,4 +32,4 @@
## 测试
`packages/client/ui-primitives/tests/onboarding-surface.spec.tsx` 钉住原语行为:内容外的 body portal、遮罩/展示层类名存在、`#root``inert` 恰好持续挂载生命周期,以及无 `#root` 的组合。`packages/client/ui-settings/tests/settings-root.spec.tsx` 钉住反转后的外壳约定:已挂载步骤什么都不渲染时,无接管界面框架、无 inert。`apps/web/tests/onboarding-deepseek-config.e2e.ts` 新增本缺陷的整装回归钉:已配置世界刷新页面,同时在浏览器网络边界扣住所有 `settings.describe` 响应——把步骤的判定窗口从 loopback 下不可见拉宽到数百毫秒,这正是断言保持非空洞的关键——页内 8ms 采样器证明接管界面框架从未挂载、`#root` 从未变为 inert。该文件的既有场景与步骤 spec(`ui-settings-general``ui-models`)原样通过——样式表逐字迁移,遮罩选择器与几何钉子得以幸存。
`packages/client/ui-primitives/tests/onboarding-surface.client.spec.tsx` 钉住原语行为:内容外的 body portal、遮罩/展示层类名存在、`#root``inert` 恰好持续挂载生命周期,以及无 `#root` 的组合。`packages/client/ui-settings-general/tests/settings-root.client.spec.tsx` 钉住反转后的外壳约定:已挂载步骤什么都不渲染时,无接管界面框架、无 inert。`apps/web/tests/onboarding-deepseek-config.e2e.ts` 新增本缺陷的整装回归钉:已配置世界刷新页面,同时在浏览器网络边界扣住所有 `settings.describe` 响应——把步骤的判定窗口从 loopback 下不可见拉宽到数百毫秒,这正是断言保持非空洞的关键——页内 8ms 采样器证明接管界面框架从未挂载、`#root` 从未变为 inert。该文件的既有场景与步骤 spec(`ui-settings-general``ui-models`)原样通过——样式表逐字迁移,遮罩选择器与几何钉子得以幸存。
@@ -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/bug-fix/2026-08-06-reader-scroll-attribution-observed-top-ledger.md
2026-08-06-reader-scroll-attribution-observed-top-ledger.md: ef5ddbeb9bea1393f474dfb4c809ae2e19bfea5c
2026-08-06-reader-scroll-attribution-observed-top-ledger.zh.md: 7a1142cdd793cfce46bfd3908ab28345701aec7a
2026-08-06-reader-scroll-attribution-observed-top-ledger.md: 66a1ca361cf28bf0beab95fa81da9cac3527474c
2026-08-06-reader-scroll-attribution-observed-top-ledger.zh.md: ce7cd6d0ade2702a6f717340cb7c9b354d0387c2
@@ -18,7 +18,7 @@ A shrink clamp whose layout regrows within the same rendering update before the
## Testing
Unit specs in `packages/client/ui-conversation/tests/chat-view.spec.tsx` pin the ledger contract directly: a `readerScroll` helper delivers a position the component never wrote, programmatic deliveries land on the ledger, and the stream-finalization shrink clamp keeps following. Two scenarios in `apps/web/tests/chat-scroll-contract.e2e.ts` extend the [browser e2e lane](../testing/2026-07-24-web-gui-browser-e2e-lane.md): keyboard paging over a settled transcript and a touch-style momentum fling against paced streaming, both red under the wheel-only implementation and green under the ledger.
Unit specs in `packages/client/ui-conversation/tests/chat-view.client.spec.tsx` pin the ledger contract directly: a `readerScroll` helper delivers a position the component never wrote, programmatic deliveries land on the ledger, and the stream-finalization shrink clamp keeps following. Two scenarios in `apps/web/tests/chat-scroll-contract.e2e.ts` extend the [browser e2e lane](../testing/2026-07-24-web-gui-browser-e2e-lane.md): keyboard paging over a settled transcript and a touch-style momentum fling against paced streaming, both red under the wheel-only implementation and green under the ledger.
The lane's Chromium cannot synthesize any non-wheel device scrolling, which bounds what the e2e can drive for real: `Input.synthesizeScrollGesture` with a touch source and hand-rolled `Input.dispatchTouchEvent` sequences deliver DOM events but never move a scroller (headless and headed-under-Xvfb alike); the `default` gesture source synthesizes wheel events; and compositor scrollbars ignore synthetic mouse input entirely, with a gutter visible only when `--hide-scrollbars` is removed. Keyboard is the one working non-wheel primitive, so it carries the real-input-pipeline proof, and the fling scenario replays touch's signature — per-frame decaying displacements the component never authored — through the scrollport directly.
@@ -18,7 +18,7 @@ ChatView 的贴底跟随此前只把滚轮/触控板手势识别为读者输
## 测试
`packages/client/ui-conversation/tests/chat-view.spec.tsx` 中的单元测试直接钉住 ledger 约定:`readerScroll` 辅助函数交付一个组件从未写入过的位置,程序化交付落在 ledger 上,流收尾阶段的收缩钳制保持跟随。`apps/web/tests/chat-scroll-contract.e2e.ts` 中的两个场景扩展了[浏览器 e2e 车道](../testing/2026-07-24-web-gui-browser-e2e-lane.md):在已停稳的 transcript 上做键盘翻页,以及对着按节奏推进的流式输出做一次触控式惯性快滑(momentum fling);两者在仅认滚轮的实现下均为红、在 ledger 下均为绿。
`packages/client/ui-conversation/tests/chat-view.client.spec.tsx` 中的单元测试直接钉住 ledger 约定:`readerScroll` 辅助函数交付一个组件从未写入过的位置,程序化交付落在 ledger 上,流收尾阶段的收缩钳制保持跟随。`apps/web/tests/chat-scroll-contract.e2e.ts` 中的两个场景扩展了[浏览器 e2e 车道](../testing/2026-07-24-web-gui-browser-e2e-lane.md):在已停稳的 transcript 上做键盘翻页,以及对着按节奏推进的流式输出做一次触控式惯性快滑(momentum fling);两者在仅认滚轮的实现下均为红、在 ledger 下均为绿。
该车道的 Chromium 无法合成任何非滚轮的设备滚动,这限定了 e2e 能真实驱动的范围:触控来源的 `Input.synthesizeScrollGesture` 与手工构造的 `Input.dispatchTouchEvent` 序列都能交付 DOM 事件,却从不移动滚动容器(无头模式与 Xvfb 下的有头模式皆然);`default` 手势来源合成的是滚轮事件;合成器滚动条则完全无视合成的鼠标输入,且只有移除 `--hide-scrollbars` 后才能看到滚动条槽。键盘是唯一可用的非滚轮原语,因此由它承担真实输入流水线的证明;快滑场景则把触控的特征(组件从未写入过的逐帧衰减位移)直接回放进滚动容器。
@@ -0,0 +1,6 @@
# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each
# 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/bug-fix/2026-08-07-code-mode-executor-collapse.md
2026-08-07-code-mode-executor-collapse.md: 3b64675f90f830628dcde427d4388153ec7accf1
2026-08-07-code-mode-executor-collapse.zh.md: 51b35ad44b9758805784834d1d036ba374140dd9

Some files were not shown because too many files have changed in this diff Show More