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

2026-07-30 15:53:46 +08:00
parent 4370004360 09c217eba7
commit f6db60b52c
139 changed files with 4683 additions and 710 deletions
--- a/docs/config-catalog.md
+++ b/docs/config-catalog.md
@@ -116,9 +116,9 @@ Source: [`packages/core/agent-loop/src/index.ts:155`](../packages/core/agent-loo
 /**
 * Bundle config: each field forwarded verbatim to the child that owns it —
 * `agents` to the agent loop (an app that pre-creates no agents, like the ACP
- * bridge, simply omits it), `persona` and `toolOrder` to the system-prompt
- * plugin (the deployment's persona section and the explicit model-facing tool
- * order), the `tools` object to the tool registry (its presentation `mode`),
+ * bridge, simply omits it), `includeHarnessIdentity`, `persona`, and `toolOrder`
+ * to the system-prompt plugin (the fixed opener, deployment persona, and explicit
+ * model-facing tool order), the `tools` object to the tool registry (its presentation `mode`),
 * `dshHome` to bash environment and local skill discovery, `sessionTitle` to
 * the fallback title service, `skills` to the
 * skill registry/local provider/tool consumer, `workspaceContext` to the
@@ -131,13 +131,16 @@ Source: [`packages/core/agent-loop/src/index.ts:155`](../packages/core/agent-loo
 * workspace context instead requires an explicit byte budget or `false` because
 * it changes model-visible input. Producer opt-in stays producer-local:
 * `toolBash` configures bash only; independently composed producers keep their
- * own config.
+ * own config. Set `toolBash: false` when another plugin owns the model-facing
+ * `bash` name.
 */
 export interface Config {
  /** The agent-loop `agents` list (see dsh-agent-loop's `Config`). */
  agents?: AgentLoopConfig['agents']
  /** Agent-loop concurrency cap; `1` is serial. */
  maxParallelToolCalls?: AgentLoopConfig['maxParallelToolCalls']
+  /** Whether the system prompt includes the fixed Harness identity (default true). */
+  includeHarnessIdentity?: SystemPromptConfig['includeHarnessIdentity']
  /** The deployment persona (see dsh-system-prompt's `Config`). */
  persona?: SystemPromptConfig['persona']
  /** The explicit model-facing tool order (see dsh-system-prompt's `Config`). */
@@ -150,10 +153,14 @@ export interface Config {
  sessionTitle?: SessionTitleConfig
  /** Workspace-context loader controls with an explicit byte budget; set `false` for hermetic prompts. */
  workspaceContext: workspaceContext.Config | false
-  /** Skill registry, local provider, and model-facing consumer config. */
+  /**
+   * Skill registry, local provider, and model-facing consumer config.
+   * Skills use `enabled` because one nested config controls a provider stack;
+   * single model-tool plugins use `Config | false` to disable that one consumer.
+   */
  skills?: SkillConfig
-  /** Model-facing bash tool config, including this producer's background opt-in. */
-  toolBash?: toolBash.Config
+  /** Model-facing bash tool config, or false when another plugin owns `bash`. */
+  toolBash?: toolBash.Config | false
  /** Generic background-task controls; set false to keep the task service without model-facing task tools. */
  toolTasks?: toolTasks.Config | false
  /** Global enablement and package-name filters for invariant companions. */
@@ -185,7 +192,7 @@ export interface GoalConfig {

 Depends on: [`AgentLoopConfig`](#deepseek-aidsh-agent-loop) · [`GoalDomainConfig`](#deepseek-aidsh-goal) · [`InvariantConfig`](#deepseek-aidsh-invariants) · [`SessionTitleConfig`](#deepseek-aidsh-session-title) · [`SkillLocal`](../packages/skill/skill-local/src/index.ts) · [`SkillRegistryConfig`](#deepseek-aidsh-skill) · [`SystemPromptConfig`](#deepseek-aidsh-system-prompt) · [`toolBash`](../packages/bash/tool-bash/src/index.ts) · [`toolGoal`](../packages/goal/tool-goal/src/index.ts) · [`ToolsConfig`](#deepseek-aidsh-tools) · [`toolSkill`](../packages/skill/tool-skill/src/index.ts) · [`toolTasks`](../packages/tasks/tool-tasks/src/index.ts) · [`workspaceContext`](../packages/context/workspace-context/src/index.ts)

-Source: [`packages/examples/agent-spine-demo/src/index.ts:88`](../packages/examples/agent-spine-demo/src/index.ts)
+Source: [`packages/examples/agent-spine-demo/src/index.ts:89`](../packages/examples/agent-spine-demo/src/index.ts)

 ## `@deepseek-ai/dsh-bash-local`

@@ -1521,6 +1528,8 @@ Source: [`packages/subagent/subagent-spawn/src/index.ts:20`](../packages/subagen
 ```ts config-catalog
 /** Plugin config: the deployment-authored fragment of the system prompt (see {@link Config.persona} for its contract). */
 export interface Config {
+  /** Include the fixed DeepSeek Harness identity before the deployment persona (default true). */
+  includeHarnessIdentity?: boolean
  /**
   * Deployment-wide order-0 persona template. A scoped section named
   * `deployment:persona` shadows it; `{{variable}}` references are strict.
@@ -1592,6 +1601,26 @@ export interface Config {

 Source: [`packages/bash/tool-bash/src/index.ts:41`](../packages/bash/tool-bash/src/index.ts)

+## `@deepseek-ai/dsh-tool-bash-persistent`
+
+Requires: `tools` · `pty`
+
+```ts config-catalog
+/** Configuration for the persistent Bash tool. */
+export interface Config {
+  /** PTY backend used for each owner-isolated persistent shell (default `shell`). */
+  backendType?: string
+  /** Wall-clock limit for one command (default 300000). */
+  timeoutMs?: number
+  /** Maximum returned command-output characters before clipping (default 16000). */
+  maxOutputChars?: number
+  /** Model-facing tool description; deployments may describe their environment. */
+  description?: string
+}
+```
+
+Source: [`packages/pty/tool-bash-persistent/src/index.ts:405`](../packages/pty/tool-bash-persistent/src/index.ts)
+
 ## `@deepseek-ai/dsh-tool-cordis`

 Requires: `tools`
@@ -1750,6 +1779,22 @@ export interface Config {

 Source: [`packages/skill/tool-skill/src/index.ts:30`](../packages/skill/tool-skill/src/index.ts)

+## `@deepseek-ai/dsh-tool-str-replace-editor`
+
+Requires: `tools` · `fs`
+
+```ts config-catalog
+/** Configuration for the string-replacement editor tool. */
+export interface Config {
+  /** Maximum returned view characters before clipping (default 16000). */
+  maxOutputChars?: number
+  /** Model-facing tool description. */
+  description?: string
+}
+```
+
+Source: [`packages/fs/tool-str-replace-editor/src/index.ts:496`](../packages/fs/tool-str-replace-editor/src/index.ts)
+
 ## `@deepseek-ai/dsh-tool-subagent`

 Requires: `tools` · `subagents`
--- a/docs/cordis-catalog/services.md
+++ b/docs/cordis-catalog/services.md
@@ -1899,7 +1899,7 @@ async assemble(context: AssembleContext = {}): Promise<PromptAssembly>

 Types: [AssembleContext](../core-data-structures/system-prompt.md) · [PromptSection](../core-data-structures/system-prompt.md) · [ToolProviderResult](../core-data-structures/system-prompt.md)

-Source: [`packages/core/system-prompt/src/index.ts:246`](../../packages/core/system-prompt/src/index.ts)
+Source: [`packages/core/system-prompt/src/index.ts:248`](../../packages/core/system-prompt/src/index.ts)

 ## `ctx.tasks` — `TaskService` (abstract seam)

--- a/docs/event-producer-consumer.md
+++ b/docs/event-producer-consumer.md
@@ -27,9 +27,9 @@ This matrix shows which packages dispatch each harness-owned event and which pac
 | `approval/request` | `waterfall` | [`packages/ui/user-approval/src/index.ts:30`](../packages/ui/user-approval/src/index.ts) | [`user-approval`](../packages/ui/user-approval) (`waterfall`) | [`acp`](../packages/acp/acp), `apiproxy` |
 | `commands/change` | `emit` | [`packages/ui/commands/src/index.ts:154`](../packages/ui/commands/src/index.ts) | [`commands`](../packages/ui/commands) (`events.dispatch`) | `apiproxy`, [`tui`](../packages/ui/tui) |
 | `domain/changed` | `emit` | [`packages/storage/storage-domain/src/events.ts:46`](../packages/storage/storage-domain/src/events.ts) | [`storage-domain`](../packages/storage/storage-domain) (`emit`) | `apiproxy`, [`storage-domain`](../packages/storage/storage-domain), [`workspace`](../packages/workspace/workspace) |
-| `fs/edit-intent` | `waterfall` | [`packages/fs/fs/src/index.ts:62`](../packages/fs/fs/src/index.ts) | [`tool-fs`](../packages/fs/tool-fs) (`waterfall`) | [`fs-policy`](../packages/fs/fs-policy) |
-| `fs/observed` | `emit` | [`packages/fs/fs/src/index.ts:71`](../packages/fs/fs/src/index.ts) | [`tool-fs`](../packages/fs/tool-fs) (`emit`) | [`fs-policy`](../packages/fs/fs-policy), [`skill-local`](../packages/skill/skill-local) |
-| `fs/write-intent` | `waterfall` | [`packages/fs/fs/src/index.ts:54`](../packages/fs/fs/src/index.ts) | [`tool-fs`](../packages/fs/tool-fs) (`waterfall`) | [`fs-policy`](../packages/fs/fs-policy) |
+| `fs/edit-intent` | `waterfall` | [`packages/fs/fs/src/index.ts:62`](../packages/fs/fs/src/index.ts) | [`tool-fs`](../packages/fs/tool-fs) (`waterfall`), [`tool-str-replace-editor`](../packages/fs/tool-str-replace-editor) (`waterfall`) | [`fs-policy`](../packages/fs/fs-policy) |
+| `fs/observed` | `emit` | [`packages/fs/fs/src/index.ts:71`](../packages/fs/fs/src/index.ts) | [`tool-fs`](../packages/fs/tool-fs) (`emit`), [`tool-str-replace-editor`](../packages/fs/tool-str-replace-editor) (`emit`) | [`fs-policy`](../packages/fs/fs-policy), [`skill-local`](../packages/skill/skill-local) |
+| `fs/write-intent` | `waterfall` | [`packages/fs/fs/src/index.ts:54`](../packages/fs/fs/src/index.ts) | [`tool-fs`](../packages/fs/tool-fs) (`waterfall`), [`tool-str-replace-editor`](../packages/fs/tool-str-replace-editor) (`waterfall`) | [`fs-policy`](../packages/fs/fs-policy) |
 | `goal/changed` | `emit` | [`packages/goal/goal/src/domain.ts:135`](../packages/goal/goal/src/domain.ts) | [`goal`](../packages/goal/goal) (`emit`) | [`goal-session`](../packages/goal/goal-session) |
 | `llm/stream` | `waterfall` | [`packages/llm/llm/src/index.ts:58`](../packages/llm/llm/src/index.ts) | [`llm`](../packages/llm/llm) (`waterfall`) | [`agent-loop`](../packages/core/agent-loop), [`llm`](../packages/llm/llm), [`llm-replay`](../packages/support/llm-replay), [`session-checkpoint-policy`](../packages/session-persistence/session-checkpoint-policy), [`session-title`](../packages/session-title/session-title) |
 | `session/created` | `emit` | [`packages/core/session/src/index.ts:71`](../packages/core/session/src/index.ts) | [`session`](../packages/core/session) (`events.dispatch`) | `apiproxy`, [`compact`](../packages/compact/compact), [`goal`](../packages/goal/goal), [`hook-protocol`](../packages/hooks/hook-protocol), [`jsonrpc`](../packages/ui/jsonrpc), [`llm-retry`](../packages/llm/llm-retry), [`plan-mode`](../packages/plan/plan-mode), [`session`](../packages/core/session), [`session-persistence`](../packages/session-persistence/session-persistence), [`session-telemetry`](../packages/telemetry/session-telemetry), [`tools`](../packages/core/tools), [`user-approval`](../packages/ui/user-approval) |
--- a/docs/module-graph.md
+++ b/docs/module-graph.md
@@ -48,6 +48,7 @@ flowchart TD
    pkg_fs_sandbox["fs-sandbox"]
    pkg_tool_fs["tool-fs"]
    pkg_tool_fs_search["tool-fs-search"]
+    pkg_tool_str_replace_editor["tool-str-replace-editor"]
  end
  subgraph group_skill["packages/skill"]
    pkg_skill["skill"]
@@ -204,6 +205,7 @@ flowchart TD
  subgraph group_pty["packages/pty"]
    pkg_pty["pty"]
    pkg_pty_local["pty-local"]
+    pkg_tool_bash_persistent["tool-bash-persistent"]
    pkg_tool_pty["tool-pty"]
  end
  subgraph group_sandbox["packages/sandbox"]
@@ -687,6 +689,11 @@ flowchart TD
  pkg_tool_fs_search --> pkg_spill
  pkg_tool_fs_search --> pkg_system_prompt
  pkg_tool_fs_search --> pkg_tools
+  pkg_tool_str_replace_editor --> pkg_fs
+  pkg_tool_str_replace_editor --> pkg_invariants
+  pkg_tool_str_replace_editor --> pkg_sandbox
+  pkg_tool_str_replace_editor --> pkg_sandbox_policy
+  pkg_tool_str_replace_editor --> pkg_tools
  pkg_tool_skill --> pkg_agent
  pkg_tool_skill --> pkg_invariants
  pkg_tool_skill --> pkg_llm
@@ -807,6 +814,11 @@ flowchart TD
  pkg_mcp_client --> pkg_llm
  pkg_mcp_client --> pkg_subprocess
  pkg_mcp_client --> pkg_tools
+  pkg_tool_bash_persistent --> pkg_agent
+  pkg_tool_bash_persistent --> pkg_invariants
+  pkg_tool_bash_persistent --> pkg_pty
+  pkg_tool_bash_persistent --> pkg_timeout
+  pkg_tool_bash_persistent --> pkg_tools
  pkg_tool_pty --> pkg_agent
  pkg_tool_pty --> pkg_invariants
  pkg_tool_pty --> pkg_llm
@@ -1113,6 +1125,7 @@ flowchart TD
 | [`tool-bash`](../packages/bash/tool-bash) | `bash` | [`agent`](../packages/core/agent), [`bash`](../packages/bash/bash), [`invariants`](../packages/support/invariants), [`llm`](../packages/llm/llm), [`paths`](../packages/util/paths), [`sandbox`](../packages/sandbox/sandbox), [`sandbox-policy`](../packages/sandbox/sandbox-policy), [`session-persistence`](../packages/session-persistence/session-persistence), [`system-prompt`](../packages/core/system-prompt), [`tasks`](../packages/tasks/tasks), [`tools`](../packages/core/tools), [`user-approval`](../packages/ui/user-approval) |
 | [`tool-fs`](../packages/fs/tool-fs) | `fs` | [`fs`](../packages/fs/fs), [`invariants`](../packages/support/invariants), [`llm`](../packages/llm/llm), [`sandbox`](../packages/sandbox/sandbox), [`sandbox-policy`](../packages/sandbox/sandbox-policy), [`session`](../packages/core/session), [`system-prompt`](../packages/core/system-prompt), [`tools`](../packages/core/tools), [`user-approval`](../packages/ui/user-approval) |
 | [`tool-fs-search`](../packages/fs/tool-fs-search) | `fs` | [`bash`](../packages/bash/bash), [`invariants`](../packages/support/invariants), [`llm`](../packages/llm/llm), [`retention`](../packages/util/retention), [`session`](../packages/core/session), [`spill`](../packages/spill/spill), [`system-prompt`](../packages/core/system-prompt), [`tools`](../packages/core/tools) |
+| [`tool-str-replace-editor`](../packages/fs/tool-str-replace-editor) | `fs` | [`fs`](../packages/fs/fs), [`invariants`](../packages/support/invariants), [`sandbox`](../packages/sandbox/sandbox), [`sandbox-policy`](../packages/sandbox/sandbox-policy), [`tools`](../packages/core/tools) |
 | [`tool-skill`](../packages/skill/tool-skill) | `skill` | [`agent`](../packages/core/agent), [`invariants`](../packages/support/invariants), [`llm`](../packages/llm/llm), [`skill`](../packages/skill/skill), [`tools`](../packages/core/tools) |
 | [`subagent`](../packages/subagent/subagent) | `subagent` | [`agent`](../packages/core/agent), [`brand`](../packages/util/brand), [`invariants`](../packages/support/invariants), [`llm`](../packages/llm/llm), [`scope`](../packages/core/scope), [`session`](../packages/core/session), [`tools`](../packages/core/tools) |
 | [`tool-web`](../packages/web/tool-web) | `web` | [`invariants`](../packages/support/invariants), [`llm`](../packages/llm/llm), [`system-prompt`](../packages/core/system-prompt), [`tools`](../packages/core/tools), [`web`](../packages/web/web) |
@@ -1135,6 +1148,7 @@ flowchart TD
 | [`repeat-tool-guard`](../packages/guard/repeat-tool-guard) | `guard` | [`agent`](../packages/core/agent), [`invariants`](../packages/support/invariants), [`tools`](../packages/core/tools) |
 | [`tool-lsp`](../packages/lsp/tool-lsp) | `lsp` | [`invariants`](../packages/support/invariants), [`llm`](../packages/llm/llm), [`lsp`](../packages/lsp/lsp), [`system-prompt`](../packages/core/system-prompt), [`timeout`](../packages/util/timeout), [`tools`](../packages/core/tools) |
 | [`mcp-client`](../packages/mcp/mcp-client) | `mcp` | [`invariants`](../packages/support/invariants), [`llm`](../packages/llm/llm), [`subprocess`](../packages/subprocess/subprocess), [`tools`](../packages/core/tools) |
+| [`tool-bash-persistent`](../packages/pty/tool-bash-persistent) | `pty` | [`agent`](../packages/core/agent), [`invariants`](../packages/support/invariants), [`pty`](../packages/pty/pty), [`timeout`](../packages/util/timeout), [`tools`](../packages/core/tools) |
 | [`tool-pty`](../packages/pty/tool-pty) | `pty` | [`agent`](../packages/core/agent), [`invariants`](../packages/support/invariants), [`llm`](../packages/llm/llm), [`pty`](../packages/pty/pty), [`retention`](../packages/util/retention), [`system-prompt`](../packages/core/system-prompt), [`tasks`](../packages/tasks/tasks), [`tools`](../packages/core/tools) |
 | [`tool-tasks`](../packages/tasks/tool-tasks) | `tasks` | [`agent`](../packages/core/agent), [`invariants`](../packages/support/invariants), [`llm`](../packages/llm/llm), [`retention`](../packages/util/retention), [`system-prompt`](../packages/core/system-prompt), [`tasks`](../packages/tasks/tasks), [`tools`](../packages/core/tools) |
 | [`tool-workflow`](../packages/workflow/tool-workflow) | `workflow` | [`agent`](../packages/core/agent), [`invariants`](../packages/support/invariants), [`llm`](../packages/llm/llm), [`system-prompt`](../packages/core/system-prompt), [`tools`](../packages/core/tools), [`workflow`](../packages/workflow/workflow) |
--- a/docs/testing.i18n.yaml
+++ b/docs/testing.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 docs/testing.md
-testing.md: 04bd7782fa4328b6b693f13f60f4e33b463f8a18
-testing.zh.md: 5712fd8ce7b0cd46ebeb237bdd12c6c572ebe3de
+testing.md: fd4879158d7aa1f4726043b0e519f1d2827f41ec
+testing.zh.md: bd78afb4fa29e8cc505bae12701f1651f7ba7b5e
--- a/docs/testing.md
+++ b/docs/testing.md
@@ -10,7 +10,7 @@ How this repo tests, tier by tier, and the rules that keep a green suite meaning
 - **Coverage gate** (`pnpm run test:coverage`): the gating run, per-file 100% on `packages/*/*/src`. An uncovered line is often dead code the gate is correctly flagging for deletion, not a missing test to bolt on. Line coverage is necessary, never sufficient — it proves lines ran, not that the feature works as shipped.
 - **Real-API e2e** (`pnpm run test:e2e`): with-key tests against live provider APIs — the DeepSeek model plus provider-specific smokes that gate on their own keys (`EXA_API_KEY`, `PERPLEXITY_API_KEY`, …); each suite self-skips without its key so keyless CI stays green ([real-API e2e Agent Note](../.agents/notes/implemented/testing/2026-06-19-real-api-e2e-ci.md)).
 - **Snapshot** (`pnpm run test:snapshot`): keyless expected outputs cover external behavior — transport contracts and presentation, while persisted logs pin assembled backend behavior. ACP boots the real automation-server example, replays a recorded session, and diffs normalized JSON-RPC plus the re-persisted log ([ACP snapshot Agent Note](../.agents/notes/implemented/testing/2026-06-19-acp-snapshot-tests.md)); headless pins `stream-json` through its real one-shot process. TUI journeys replay primary/child JSONL through the real loop and tools, then project ANSI into semantic terminal-state outputs; package snapshots retain transient states and a real PTY covers the process boundary ([TUI snapshot Agent Note](../.agents/notes/implemented/testing/2026-07-18-tui-terminal-state-snapshots.md)). Use `pnpm run test:snapshot:record` when a model transcript changes and `pnpm run test:snapshot:refresh` when replay input remains valid; review every JSONL and expected-output diff. One ACP scenario (`text-turn`) pins full system-prompt/tool-schema content; other fixtures tokenize it so an edit churns one line ([pinned-header Agent Note](../.agents/notes/archived/testing/2026-07-06-pin-request-header-content-in-one-scenario.md)).
- **Web browser snapshot** (gate-exempt `pnpm run test:web`): real chromium over the in-process web composition replays recorded fixtures against conversation aria goldens (`apps/web/tests/snapshots/`); record/refresh semantics and the deferred CI browser decision: [web e2e lane Agent Note](../.agents/notes/implemented/testing/2026-07-24-web-gui-browser-e2e-lane.md). [Runs `build` first](../.agents/notes/implemented/bug-fix/2026-07-28-themed-scrollbars-and-reserved-gutter.md): plugin CSS ships per plugin.
+- **Web browser snapshot** (`pnpm run test:web`; required Linux PR gate): Chromium compares replayed browser output with `apps/web/tests/snapshots/`. CI forces read-only `DSH_SNAPSHOT=replay`, never writing expected outputs; record/refresh stay local and every diff is reviewed ([web e2e lane](../.agents/notes/implemented/testing/2026-07-24-web-gui-browser-e2e-lane.md), [CI gate decision](../.agents/notes/implemented/testing/2026-07-30-web-browser-snapshot-ci-gate.md)). `test:web` [builds first](../.agents/notes/implemented/bug-fix/2026-07-28-themed-scrollbars-and-reserved-gutter.md) for plugin CSS.

 Committed session-format JSONL uses the canonical packed-row layout, and the keyless snapshot gate discovers every such fixture by its `session` header. In-flight branches carrying older fixture edits merge current `master` and run the [temporary migrator](../scripts/migrate-packed-session-fixtures.ts) through `pnpm run migrate:packed-session-fixtures`; the [removal proposal](../.agents/notes/proposed/process/2026-07-26-remove-packed-session-fixture-migrator.md) retires that command and these links after all affected branches converge.

--- a/docs/testing.zh.md
+++ b/docs/testing.zh.md
@@ -10,7 +10,7 @@
 - **覆盖率门禁**（`pnpm run test:coverage`）：门禁级运行，对 `packages/*/*/src` 按文件 100% 覆盖。未覆盖的行往往是门禁正确标记出的死代码（应删除），而非需要补写的测试。行覆盖率是必要条件，但永远不是充分条件：它证明行被执行过，不证明功能按交付预期工作。
 - **真实 API e2e**（`pnpm run test:e2e`）：带密钥测试调用真实提供方 API，包括 DeepSeek 模型以及各提供方特有的冒烟测试；这些测试各自由自己的密钥控制（`EXA_API_KEY`、`PERPLEXITY_API_KEY` 等），缺少密钥时套件会自动跳过，使 keyless CI 保持绿色（[真实 API e2e Agent Note](../.agents/notes/implemented/testing/2026-06-19-real-api-e2e-ci.md)）。
 - **快照**（`pnpm run test:snapshot`）：无密钥预期输出覆盖对外行为（传输契约与呈现），持久化日志则固定组装后的后端行为。ACP 启动真实的自动化服务器示例、回放录制会话，并对归一化 JSON-RPC 与重新持久化的日志执行 diff（[ACP 快照 Agent Note](../.agents/notes/implemented/testing/2026-06-19-acp-snapshot-tests.md)）；headless 通过真实单次运行进程固定 `stream-json`。TUI 旅程通过真实循环与工具回放主会话与子会话 JSONL，再将 ANSI 投影为语义化终端状态输出；包级快照保留瞬态状态，真实 PTY 覆盖进程边界（[TUI 快照 Agent Note](../.agents/notes/implemented/testing/2026-07-18-tui-terminal-state-snapshots.md)）。当模型 transcript（文本记录）发生变化时使用 `pnpm run test:snapshot:record`，回放输入仍然有效时使用 `pnpm run test:snapshot:refresh`；请审查每一处 JSONL 与预期输出差异。一个 ACP 场景（`text-turn`）固定完整的系统提示词与工具 schema 内容；其他 fixture（测试前置数据）将其 token 化，因此修改只会扰动一行（[pinned-header Agent Note](../.agents/notes/archived/testing/2026-07-06-pin-request-header-content-in-one-scenario.md)）。
- **Web 浏览器快照**（豁免门禁的 `pnpm run test:web`）：真实 chromium 在进程内 web 组装之上回放已录制 fixture，与会话区 aria 预期输出比对（`apps/web/tests/snapshots/`）；`DSH_SNAPSHOT=record`/`refresh` 的语义与暂缓的 CI 浏览器决策见 [web e2e 车道 Agent Note](../.agents/notes/implemented/testing/2026-07-24-web-gui-browser-e2e-lane.md)。[先跑 `build`](../.agents/notes/implemented/bug-fix/2026-07-28-themed-scrollbars-and-reserved-gutter.md)：插件 CSS 按插件分别发布。
+- **Web 浏览器快照**（`pnpm run test:web`；必需的 Linux PR（Pull Request）门禁）：Chromium 将回放后的浏览器输出与 `apps/web/tests/snapshots/` 比较。CI 强制只读的 `DSH_SNAPSHOT=replay`，绝不写入预期输出；record/refresh 留在本地，每处 diff 都须评审（[web e2e 车道](../.agents/notes/implemented/testing/2026-07-24-web-gui-browser-e2e-lane.md)、[CI 门禁决策](../.agents/notes/implemented/testing/2026-07-30-web-browser-snapshot-ci-gate.md)）。`test:web` 会[先构建](../.agents/notes/implemented/bug-fix/2026-07-28-themed-scrollbars-and-reserved-gutter.md)以交付插件 CSS。

 签入仓库的会话格式 JSONL 使用规范打包行布局，无密钥快照门禁会通过 `session` header 发现每一份此类 fixture。仍携带旧版 fixture 改动的在途分支应合并当前 `master`，并通过 `pnpm run migrate:packed-session-fixtures` 运行[临时迁移器](../scripts/migrate-packed-session-fixtures.ts)；待所有受影响分支收敛后，[移除提案](../.agents/notes/proposed/process/2026-07-26-remove-packed-session-fixture-migrator.md)会移除该命令及这些链接。

--- a/docs/tool-catalog.md
+++ b/docs/tool-catalog.md
@@ -20,6 +20,8 @@ This table connects model-visible tool names to the plugin package and service s
 | `@deepseek-ai/dsh-plan-mode` | `exit_plan_mode` | `ctx.tools`, `ctx.systemPrompt`, `ctx.userInteraction (execution time, opportunistic)` | `tool/call`, `plan/mode inactive on an approved review`, `tool/result` | - | exit_plan_mode stays in the model-facing schema while planning is inactive so transitions add no tool-catalog churn on top of the plan-policy change. Its execute path rejects calls outside plan mode; in plan mode it presents the plan over the user-interaction seam (approve / keep planning with feedback), and approval logs plan mode inactive at the step boundary. |
 | `@deepseek-ai/dsh-tool-bash` | `bash` | `ctx.tools`, `ctx.bash`, `ctx.tasks at call time for run_in_background` | `tool/call`, `tool/result` | - | The bash tool is the model-facing consumer of the bash executor seam. A `run_in_background` run registers with the generic `ctx.tasks` runtime and is collected/stopped through the `task_*` tools from `@deepseek-ai/dsh-tool-tasks`; the `enableRunInBackground` config (default true) removes the parameter entirely when disabled. |
 | `@deepseek-ai/dsh-tool-cordis` | `cordis_inspect`, `cordis_mount`, `cordis_unmount` | `ctx.tools` | `tool/call`, `tool/result`, `process-local temporary Plugin lifecycle` | - | Ships in examples/cordis-agent only (a deliberate opt-in — temporary Plugin code reaches the real runtime, see .agents/notes/implemented/feature/2026-07-08-self-referential-cordis-toolset.md). Plugins created by cordis_mount may register ADDITIONAL model-visible tools until unmounted or DSH restarts; a full changed request header logs those tool-set changes. |
+| `@deepseek-ai/dsh-tool-bash-persistent` | `bash` | `ctx.tools`, `ctx.pty`, `an owning Agent at execution time` | `tool/call`, `PTY shell state`, `tool/result` | - | One owner-isolated persistent bash tool; deployment composition supplies the PTY backend and may override the model-facing environment description. |
+| `@deepseek-ai/dsh-tool-str-replace-editor` | `str_replace_editor` | `ctx.tools`, `ctx.fs` | `tool/call`, `fs/observed after successful file operations`, `tool/result` | - | Standalone view/create/unique literal replace/line insert tool over the filesystem seam; it composes with any shell or terminal surface. |
 | `@deepseek-ai/dsh-tool-fs` | `edit`, `read`, `write` | `ctx.tools`, `ctx.fs`, `ctx.systemPrompt` | `tool/call`, `fs/write-intent or fs/edit-intent for mutations`, `fs/observed after successful file operations`, `tool/result` | - | The read-before-write/edit policy is added by `@deepseek-ai/dsh-fs-policy` (an `fs/*` event-gate plugin, no schema change); a deployment that loads these tools is expected to also load it. The tool schemas above are identical with or without the policy plugin. |
 | `@deepseek-ai/dsh-tool-fs-search` | `glob`, `grep` | `ctx.tools`, `ctx.bash`, `ctx.systemPrompt` | `tool/call`, `tool/result` | - | glob and grep are conditional bash-backed discovery tools: they register only when ctx.bash can find `rg`, then run fixed ripgrep commands through ctx.bash as ordinary foreground calls (never background tasks). Capped results save the complete formatted list through the optional ctx.spillStore backend; returned locators are follow-up-readable/searchable when the backend exposes local paths in co-located deployments. |
 | `@deepseek-ai/dsh-tool-pty` | `terminal_close`, `terminal_list`, `terminal_open`, `terminal_read`, `terminal_send`, `terminal_signal` | `ctx.tools`, `ctx.pty`, `ctx.systemPrompt`, `ctx.tasks at call time for run_in_background` | `tool/call`, `tool/result` | - | The six terminal tools are opt-in and complement one-shot bash/filesystem tools. `terminal_send(run_in_background: true)` registers with `ctx.tasks`; TUI, named key sequences, BEL, resize, auto-start, and cross-agent sharing are absent from the schema. |
@@ -279,6 +281,99 @@ Source: [`packages/cordis/tool-cordis/src/index.ts`](../packages/cordis/tool-cor

 Ships in examples/cordis-agent only (a deliberate opt-in — temporary Plugin code reaches the real runtime, see .agents/notes/implemented/feature/2026-07-08-self-referential-cordis-toolset.md). Plugins created by cordis_mount may register ADDITIONAL model-visible tools until unmounted or DSH restarts; a full changed request header logs those tool-set changes.

+## `@deepseek-ai/dsh-tool-bash-persistent`
+
+### `bash`
+
+Run commands in a persistent bash shell. State, including the current directory and exported environment variables, persists across calls for this agent.
+
+```json
+{
+  "type": "object",
+  "properties": {
+    "command": {
+      "type": "string",
+      "description": "The bash command to run. Relative path is preferred in the command."
+    }
+  },
+  "required": [
+    "command"
+  ]
+}
+```
+
+Source: [`packages/pty/tool-bash-persistent/src/index.ts`](../packages/pty/tool-bash-persistent/src/index.ts)
+
+One owner-isolated persistent bash tool; deployment composition supplies the PTY backend and may override the model-facing environment description.
+
+## `@deepseek-ai/dsh-tool-str-replace-editor`
+
+### `str_replace_editor`
+
+Custom editing tool for viewing, creating and editing files
+* State is persistent across command calls and discussions with the user
+* If `path` is a file, `view` displays the result of applying `cat -n`. If `path` is a directory, `view` lists non-hidden files and directories up to 2 levels deep
+* The `create` command cannot be used if the specified `path` already exists as a file
+* If a `command` generates a long output, it will be truncated and marked with `<response clipped>`
+
+Notes for using the `str_replace` command:
+* The `old_str` parameter should match EXACTLY one or more consecutive lines from the original file. Be mindful of whitespaces!
+* If the `old_str` parameter is not unique in the file, the replacement will not be performed. Make sure to include enough context in `old_str` to make it unique
+* The `new_str` parameter should contain the edited lines that should replace the `old_str`
+
+```json
+{
+  "type": "object",
+  "properties": {
+    "command": {
+      "type": "string",
+      "description": "The commands to run. Allowed options are: `view`, `create`, `str_replace`, `insert`.",
+      "enum": [
+        "view",
+        "create",
+        "str_replace",
+        "insert"
+      ]
+    },
+    "path": {
+      "type": "string",
+      "description": "Absolute path to file or directory, e.g. `/repo/file.py` or `/repo`."
+    },
+    "file_text": {
+      "type": "string",
+      "description": "Required parameter of `create` command, with the content of the file to be created."
+    },
+    "insert_line": {
+      "type": "integer",
+      "description": "Required parameter of `insert` command. The `new_str` will be inserted AFTER the line `insert_line` of `path`."
+    },
+    "new_str": {
+      "type": "string",
+      "description": "Optional parameter of `str_replace` command containing the new string (if not given, no string will be added). Required parameter of `insert` command containing the string to insert."
+    },
+    "old_str": {
+      "type": "string",
+      "description": "Required parameter of `str_replace` command containing the string in `path` to replace."
+    },
+    "view_range": {
+      "type": "array",
+      "description": "Optional parameter of `view` command when `path` points to a file. If none is given, the full file is shown. If provided, the file will be shown in the indicated line number range, e.g. [11, 12] will show lines 11 and 12. Indexing at 1 to start. Setting `[start_line, -1]` shows all lines from `start_line` to the end of the file.",
+      "items": {
+        "type": "integer"
+      }
+    }
+  },
+  "required": [
+    "command",
+    "path"
+  ]
+}
+```
+
+Source: [`packages/fs/tool-str-replace-editor/src/index.ts`](../packages/fs/tool-str-replace-editor/src/index.ts)
+
+Standalone view/create/unique literal replace/line insert tool over the filesystem seam; it composes with any shell or terminal surface.
+
 ## `@deepseek-ai/dsh-tool-fs`

 ### `edit`