Merge remote-tracking branch 'origin/master' into xtr/react-loop-simplification

# Conflicts: # .agents/notes/implemented/architecture/2026-07-25-web-client-session-scope-and-provide-channel.i18n.yaml # docs/architecture.i18n.yaml # docs/architecture.md # docs/architecture.zh.md # docs/cookbook/extension-cookbook.i18n.yaml # docs/cookbook/extension-cookbook.md # docs/cookbook/extension-cookbook.zh.md # docs/core-data-structures/llm-streaming.i18n.yaml # docs/core-data-structures/session.i18n.yaml # docs/defensive-patterns.i18n.yaml # packages/acp/acp/README.i18n.yaml # packages/client/runtime/README.i18n.yaml # packages/client/ui-conversation/README.i18n.yaml # packages/client/ui-goal/README.i18n.yaml # packages/compact/compact-basic/README.i18n.yaml # packages/context/README.i18n.yaml # packages/context/README.md # packages/context/README.zh.md # packages/context/session-reference/README.i18n.yaml # packages/context/session-reference/README.md # packages/context/session-reference/README.zh.md # packages/context/tmux-context/README.i18n.yaml # packages/core/session/README.i18n.yaml # packages/core/session/README.md # packages/core/session/README.zh.md # packages/goal/command-goal/README.i18n.yaml # packages/goal/goal-session/README.i18n.yaml # packages/goal/goal-session/README.zh.md # packages/guard/README.i18n.yaml # packages/guard/README.md # packages/guard/README.zh.md # packages/guard/repeat-tool-guard/README.i18n.yaml # packages/host/apiproxy/README.i18n.yaml # packages/host/apiproxy/README.md # packages/host/apiproxy/README.zh.md # packages/plan/plan-mode/README.i18n.yaml # packages/sdk/sdk-client/README.i18n.yaml # packages/sdk/sdk-client/README.md # packages/sdk/sdk-client/README.zh.md # packages/session-persistence/session-persistence/README.i18n.yaml # packages/subagent/subagent-dsh-sdk/README.i18n.yaml # python/sdk/README.i18n.yaml
2026-08-05 20:43:30 +08:00
parent 208ec20dd9 edabb3c2dc
commit 488b8df547
486 changed files with 2538 additions and 3002 deletions
--- a/packages/support/README.i18n.yaml
+++ b/packages/support/README.i18n.yaml
@@ -2,5 +2,5 @@
 # side as of the last confirmed-consistent state. Both languages carry equal authority;
 # after editing either side, bring the other along and re-record with:
 #   pnpm run verify-translation-pairing --write packages/support/README.md
-README.md: b9550fd54feb36448227faae8485fe8b6dbf4fb0
-README.zh.md: 1b7464e0cab4460e587f2b5c8afa58d28116bab1
+README.md: 15cb82d3d76a1241af8b40e1c8536292618409a9
+README.zh.md: ff8595b47f1a1220912dc77a072463adf74f7bf9
--- a/packages/support/README.md
+++ b/packages/support/README.md
@@ -1,16 +1,16 @@
-# support/ — dev/test/example infrastructure
+# support/ — development and test infrastructure

 English | [中文](README.zh.md)

-Packages that exist to serve development, testing, and the examples rather than to ship as product API. They are real workspace packages (typed, tested, under the coverage gate), but they carry **lower compatibility expectations**: they may change or be removed when the development need behind them does, without the deprecation care a product package would warrant.
+These packages support repository development, tests, and examples rather than product APIs. Their compatibility follows the development need they serve.

-| Package | Role | ctx key |
-|---|---|---|
-| `acp-snapshot/` | ACP test kit: shared subprocess/client launcher + snapshot harness, normalizers, and suite factory | (library — imported by ACP e2e and `*.snapshot.ts` suites) |
-| `agent-loop-testkit/` | Shared prerequisite mounting for tests that exercise the concrete agent loop | (library — imported by AgentLoop integration tests) |
-| `invariants/` | Runtime event-contract assertions for development diagnostics | (listens on `session/*`, `agent/*`) |
-| `loader-smoke/` | Shared real-Loader subprocess harness for keyless example smokes | (library — imported by example e2e suites) |
-| `llm-mock-server/` | Scriptable OpenAI-compatible HTTP/SSE fault server + CLI for LLM recovery tests | (standalone server and test library) |
-| `llm-replay/` | Record/replay adapter: short-circuits `llm/stream` from a recorded session JSONL (keyless snapshot tests) | (listens on `llm/stream`) |
+| Package | Role |
+|---|---|
+| [`acp-snapshot/`](acp-snapshot/README.md) | Provides the ACP snapshot-test toolkit |
+| [`agent-loop-testkit/`](agent-loop-testkit/README.md) | Mounts shared prerequisites for AgentLoop tests |
+| [`invariants/`](invariants/README.md) | Runs development-time runtime-contract assertions |
+| [`loader-smoke/`](loader-smoke/README.md) | Launches Loader-composed applications for smoke tests |
+| [`llm-mock-server/`](llm-mock-server/README.md) | Provides a deterministic OpenAI-compatible fault server |
+| [`llm-replay/`](llm-replay/README.md) | Replays recorded model responses for keyless tests and demos |

-`invariants` is development support but has no environment guard: it runs wherever registered, and the default `dsh-agent-spine-demo` bundle mounts it unconditionally. `agent-loop-testkit` centralizes the mandatory service spine for hand-built AgentLoop tests without owning their loop or scenario. `llm-replay` backs the demos and the snapshot test tier under the per-file coverage gate, while `llm-mock-server` drives real provider adapters through deterministic HTTP/SSE faults. `acp-snapshot` carries the ACP subprocess/client boundary plus the snapshot harness, normalizers, and suite machinery, while `loader-smoke` owns the parallel real-Loader launch boundary used by keyless example e2e suites. A package graduates OUT of `support/` into a product group only when it gains documented product consumers.
+A package moves out of `support/` when it gains a product contract and product consumers.
--- a/packages/support/README.zh.md
+++ b/packages/support/README.zh.md
@@ -1,16 +1,16 @@
-# support/：开发／测试／示例基础设施
+# support/：开发和测试基础设施

 [English](README.md) | 中文

-这些包用于开发、测试和示例，而非作为产品 API 发布。它们是实际的工作区包（具备类型、经过测试，并受覆盖率门禁约束），但具有**较低的兼容性预期**：当其背后的开发需求变化时，它们可以改变或被移除，无需像产品包那样谨慎执行弃用流程。
+这些包为仓库开发、测试和示例提供支持，而不是产品 API。其兼容性取决于所服务的开发需求。

-| 包 | 职责 | ctx 键 |
-|---|---|---|
-| `acp-snapshot/` | ACP（Agent Client Protocol）测试工具包：共享子进程/客户端启动器、快照 harness、规范化器和套件工厂 | （库：由 ACP e2e 和 `*.snapshot.ts` 套件导入） |
-| `agent-loop-testkit/` | 为验证具体 agent loop（智能体循环）的测试挂载共享先决条件 | （库：由 AgentLoop 集成测试导入） |
-| `invariants/` | 用于开发诊断的运行时事件契约断言 | （监听 `session/*`、`agent/*`） |
-| `loader-smoke/` | 共享的真实 Loader 子进程 harness，用于无密钥示例冒烟测试 | （库：由示例 e2e 套件导入） |
-| `llm-mock-server/` | 可编程的 OpenAI 兼容 HTTP/SSE（Server-Sent Events）故障服务器与 CLI（命令行界面），用于 LLM（大语言模型）恢复测试 | （独立服务器和测试库） |
-| `llm-replay/` | 录制/回放适配器：通过已记录的会话 JSONL 对 `llm/stream` 进行短路处理（无密钥快照测试） | （监听 `llm/stream`） |
+| 包 | 职责 |
+|---|---|
+| [`acp-snapshot/`](acp-snapshot/README.md) | 提供 ACP（Agent Client Protocol）快照测试工具包 |
+| [`agent-loop-testkit/`](agent-loop-testkit/README.md) | 为 AgentLoop 测试挂载共享先决条件 |
+| [`invariants/`](invariants/README.md) | 运行开发期运行时契约断言 |
+| [`loader-smoke/`](loader-smoke/README.md) | 启动由 Loader 组合的应用以执行冒烟测试 |
+| [`llm-mock-server/`](llm-mock-server/README.md) | 提供确定性的 OpenAI 兼容故障服务器 |
+| [`llm-replay/`](llm-replay/README.md) | 为无密钥测试和演示回放已记录的模型响应 |

-`invariants` 是开发支持，但没有环境条件限制：无论在何处注册，它都会运行；默认 `dsh-agent-spine-demo` bundle 无条件挂载它。`agent-loop-testkit` 为手工构建的 AgentLoop 测试集中管理必需服务主干，而不负责其 agent loop 或场景。`llm-replay` 支撑演示和受逐文件覆盖率门禁约束的快照测试层，`llm-mock-server` 则通过确定性 HTTP/SSE 故障驱动真实提供方适配器。`acp-snapshot` 包含 ACP 子进程/客户端边界以及快照 harness、规范化器和套件机制，`loader-smoke` 负责无密钥示例 e2e 套件使用的并列真实 Loader 启动边界。只有当某个包获得文档记载的产品消费方时，它才会从 `support/` 转入产品分组。
+当一个包获得产品契约和产品消费方时，它会移出 `support/`。
--- a/packages/support/acp-snapshot/README.i18n.yaml
+++ b/packages/support/acp-snapshot/README.i18n.yaml
@@ -2,5 +2,5 @@
 # side as of the last confirmed-consistent state. Both languages carry equal authority;
 # after editing either side, bring the other along and re-record with:
 #   pnpm run verify-translation-pairing --write packages/support/acp-snapshot/README.md
-README.md: c8fe6907848a7b661c4bfb60c871f077753fda8b
-README.zh.md: 0aa28f4b2c3df1a30e5fd33a80401712f81d6614
+README.md: ff8b89437703e0d63542f2a004f9b0929171010e
+README.zh.md: 582285363f6556fcc68d783e2ceedc7eb007dafd
--- a/packages/support/acp-snapshot/README.md
+++ b/packages/support/acp-snapshot/README.md
@@ -59,7 +59,7 @@ Every scenario compares `stdout.expected.jsonl` with cwd-rooted separators canon

 The example also ships a `cordis.snapshot.yml` replay overlay next to its `cordis.yml` (the bin swaps them under `DSH_SNAPSHOT=replay` — [single-source replay config Agent Note](../../../.agents/notes/archived/testing/2026-07-04-single-source-acp-replay-config.md)); replay fixtures are served by [`dsh-llm-replay`](../llm-replay/README.md), which this package points at via the `DSH_SNAPSHOT_*` env vars it sets on the child. `pnpm run test:snapshot:record` calls the live LLM and rewrites the recorded scenarios' model fixtures; `pnpm run test:snapshot:refresh` stays keyless, runs the replay overlay, and rewrites stdout, comparable session-log expected outputs, and owned prompt and tool-schema sidecars from the committed model scripts. Fixture roles, record/replay/refresh semantics, and scenario-table fields are documented on `Scenario` and in the [snapshot Agent Note](../../../.agents/notes/implemented/testing/2026-06-19-acp-snapshot-tests.md).

-Constraints: `suite.ts` and `harness.ts` import vitest (the harness polls its durable-boundary waits through `vi.waitFor`), so the package entry is importable only inside a vitest run (the launcher and normalizers have no such dependency but ship from the same entry). The launcher and suite factory are ACP-specific by design — the launcher speaks the SDK's `ClientSideConnection` — while the normalizers are transport-neutral session-log/text helpers also consumed by the TUI snapshot suite and the web browser e2e lane. Input scripts cover initialization, fresh-session creation, text prompting, cancellation, expected RPC failures, and durable turn-boundary waits. Permission round-trips are a FIFO queue of option-kind selections (`allow_once`, `reject_once`, …) mapped to the agent-issued `optionId`; an absent or exhausted queue answers `cancelled`, and an unoffered kind rejects the run.
+Constraints: `suite.ts` and `harness.ts` import vitest (the harness polls its durable-boundary waits through `vi.waitFor`), so the package entry is importable only inside a vitest run (the launcher and normalizers have no such dependency but ship from the same entry). The launcher and suite factory are ACP-specific by design — the launcher speaks the SDK's `ClientSideConnection` — while the normalizers are transport-neutral session-log/text helpers also consumed by the Web browser e2e lane. Input scripts cover initialization, fresh-session creation, text prompting, cancellation, expected RPC failures, and durable turn-boundary waits. Permission round-trips are a FIFO queue of option-kind selections (`allow_once`, `reject_once`, …) mapped to the agent-issued `optionId`; an absent or exhausted queue answers `cancelled`, and an unoffered kind rejects the run.

 ## Model Experience

--- a/packages/support/acp-snapshot/README.zh.md
+++ b/packages/support/acp-snapshot/README.zh.md
@@ -59,7 +59,7 @@ defineAcpSnapshotSuite({

 示例还发布 `cordis.snapshot.yml` 回放 overlay，位于 `cordis.yml` 旁边（bin 在 `DSH_SNAPSHOT=replay` 下交换它们，见[单源回放配置 Agent Note](../../../.agents/notes/archived/testing/2026-07-04-single-source-acp-replay-config.md)）；回放 fixture 由 [`dsh-llm-replay`](../llm-replay/README.md) 提供，该包通过对子级设置的 `DSH_SNAPSHOT_*` env var 指向它。`pnpm run test:snapshot:record` 调用实时 LLM，并重写已记录场景的模型 fixture；`pnpm run test:snapshot:refresh` 保持无密钥，运行回放 overlay，并从已提交模型脚本重写 stdout、可比较会话日志预期输出，以及各 pin 自有的提示词与工具 schema sidecar。Fixture 角色、录制/回放/刷新语义和场景表字段记录在 `Scenario` 以及[快照 Agent Note](../../../.agents/notes/implemented/testing/2026-06-19-acp-snapshot-tests.md) 中。

-约束：`suite.ts` 与 `harness.ts` 导入 vitest（harness 通过 `vi.waitFor` 轮询其持久边界等待），因此包入口只能在 vitest 运行中导入（启动器和规范化器没有此依赖，但从同一入口发布）。启动器和套件工厂按设计专用于 ACP，启动器使用 SDK 的 `ClientSideConnection`；规范化器是与传输无关的会话日志/文本辅助工具，还由 TUI 快照套件和 web 浏览器 e2e lane 消费。输入脚本覆盖初始化、新建会话、文本提示、取消、预期 RPC 失败和持久轮次边界等待。权限往返是选项类别选择（`allow_once`、`reject_once`等）的 FIFO 队列，映射到 agent 发出的 `optionId`；缺少或耗尽的队列回答 `cancelled`，未提供类别会拒绝运行。
+约束：`suite.ts` 与 `harness.ts` 导入 vitest（harness 通过 `vi.waitFor` 轮询其持久边界等待），因此包入口只能在 vitest 运行中导入（启动器和规范化器没有此依赖，但从同一入口发布）。启动器和套件工厂按设计专用于 ACP，启动器使用 SDK 的 `ClientSideConnection`；规范化器是与传输无关的会话日志/文本辅助工具，还由 Web 浏览器 e2e lane 消费。输入脚本覆盖初始化、新建会话、文本提示、取消、预期 RPC 失败和持久轮次边界等待。权限往返是选项类别选择（`allow_once`、`reject_once` 等）的 FIFO 队列，映射到 agent 发出的 `optionId`；缺少或耗尽的队列回答 `cancelled`，未提供类别会拒绝运行。

 ## 模型体验

--- a/packages/support/llm-replay/README.i18n.yaml
+++ b/packages/support/llm-replay/README.i18n.yaml
@@ -2,5 +2,5 @@
 # side as of the last confirmed-consistent state. Both languages carry equal authority;
 # after editing either side, bring the other along and re-record with:
 #   pnpm run verify-translation-pairing --write packages/support/llm-replay/README.md
-README.md: 85aa56705929e7630e4cfb6c2a3c9cbbd0d843a6
-README.zh.md: dfa43cf78c2b584fe4868603feb3fbcfb909e099
+README.md: ee062d0c2804905f33f1ff476d12bb6dd57666e5
+README.zh.md: ab3420d9500a6ca77f04a2ad96095f8883aeb874
--- a/packages/support/llm-replay/README.md
+++ b/packages/support/llm-replay/README.md
@@ -4,7 +4,7 @@ English | [中文](README.zh.md)

 A replay LLM plugin for keyless snapshot tests. It yields model streams reconstructed from a recorded **session JSONL** fixture, so a test can boot the real agent against a fixed model transcript with no API key. With `providers` configured it registers a replay-only adapter whose catalog is available to scenarios that exercise model discovery; without `providers` it installs the catch-all `llm/stream` waterfall used by tests that do not need discovery.

-Its consumers are the ACP, headless `stream-json`, and TUI snapshot suites plus the web browser e2e lane. Loader-driven suites mount this plugin in place of a real LLM adapter; the web lane installs it directly to retain the teardown consumption handle. Keeping derivation and replay here places that logic under the per-file 100% coverage gate on `packages/*/src`.
+Its consumers are the ACP and headless `stream-json` snapshot suites plus the Web browser e2e lane. Loader-driven suites mount this plugin in place of a real LLM adapter; the Web lane installs it directly to retain the teardown consumption handle.

 ## How the fixture works

--- a/packages/support/llm-replay/README.zh.md
+++ b/packages/support/llm-replay/README.zh.md
@@ -4,7 +4,7 @@

 用于无密钥快照测试的 LLM（大语言模型）回放插件。它根据已记录的**会话 JSONL** fixture（测试前置数据）重建模型流，使测试无需 API 密钥即可针对固定的模型 transcript（文本记录）启动真实 agent（智能体）。配置 `providers` 后，它会注册仅用于回放的适配器，其模型目录可供测试模型发现功能的场景使用；未配置 `providers` 时，它会安装无需模型发现功能的测试所用 catch-all `llm/stream` waterfall（瀑布式事件）。

-其消费方包括 ACP（Agent Client Protocol）、headless `stream-json` 和 TUI 快照套件，以及 Web 浏览器 e2e 流水线。Loader 驱动的套件使用此插件替代真实 LLM 适配器；Web 流水线直接安装它，以保留清理阶段的消费检查句柄。将派生和回放逻辑放在此处，可使其受 `packages/*/src` 的逐文件 100% 覆盖率门禁约束。
+其消费方包括 ACP（Agent Client Protocol）与 headless `stream-json` 快照套件，以及 Web 浏览器 e2e 流水线。Loader 驱动的套件使用此插件替代真实 LLM 适配器；Web 流水线直接安装它，以保留清理阶段的消费检查句柄。

 ## fixture 的工作方式