feat(tools): add persistent bash and str-replace editor

This commit is contained in:
Yichen Jiang
2026-07-29 14:12:27 +08:00
parent 75b32f7d76
commit 665c21693b
59 changed files with 2880 additions and 91 deletions

View File

@@ -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/feature/2026-07-29-persistent-bash-str-replace-editor.md
2026-07-29-persistent-bash-str-replace-editor.md: 286a53c1c686cc515b65119ed4b1a01a57b0614b
2026-07-29-persistent-bash-str-replace-editor.zh.md: d2417708c8a1334e9f8930481f4218cbefc5a87b

View File

@@ -0,0 +1,33 @@
# Agent Note: Persistent Bash and string-replacement editor tools
Status: implemented
English | [中文](2026-07-29-persistent-bash-str-replace-editor.zh.md)
## Problem
Some deployments need a one-call Bash schema whose shell state survives across model turns, while others need a Claude-style `str_replace_editor` independent of their terminal choice. Bundling the two tools or naming them after one benchmark would prevent reuse and blur configuration ownership.
## Decision
`@deepseek-ai/dsh-tool-bash-persistent` consumes `ctx.pty` and registers one `bash(command)` tool. It lazily creates one interactive shell per exact Agent and serializes that owner's calls. Cwd, exported variables, activated environments, functions, and background jobs persist. Random private markers delimit command output. Retained scrollback is paged backward to recover the command's original prefix; a dropped prefix is reported explicitly. Timeout or cancellation closes the shell before another call can reuse uncertain state, and model-visible timeout/exit results disclose that reset. The configurable description defaults to persistence facts only, so network and package-mirror claims remain deployment-owned.
`@deepseek-ai/dsh-tool-str-replace-editor` independently consumes `ctx.fs` and registers `str_replace_editor` with `view`, `create`, `str_replace`, and `insert`. It provides numbered text views, filtered two-level directory listings, unique literal replacement, canonical insertion boundaries, and bounded output. The public schema and failures use only `old_str`; canonical mode requires absolute paths and expands tabs before mutations. Deployments with an intentional session-cwd contract can disable the absolute-path requirement. The plugin can compose with persistent Bash, one-shot Bash, sandboxed Bash, or no shell.
`dsh-system-prompt` accepts `includeHarnessIdentity: false`, while `dsh-agent-spine-demo` forwards that setting and accepts `toolBash: false`. A deployment can therefore own an exact persona and replace the spine's native Bash without duplicate prompt or tool registrations. Existing defaults remain unchanged.
Both plugins are included in the Python runtime closure. The persistent Bash closure also includes the PTY service/local backend and the sandbox services required by that backend. Because `node-pty` executes a native `spawn-helper`, each packaged runtime executable ships with an architecture-matched `-spawn-helper` sibling. A pinned `node-pty` patch resolves that sibling only when present (or when `DSH_NODE_PTY_SPAWN_HELPER` explicitly selects one), preserving upstream lookup in ordinary Node runs; the executable and runtime-wheel builders fail before publication when the helper is absent, mismatched, or not executable.
## Alternatives considered
**One combined compatibility plugin.** Rejected because neither tool requires the other and the combined name would tie reusable capabilities to one benchmark.
**Reuse one-shot Bash.** Rejected because `bash -c` cannot preserve cwd or environment state across calls.
**Expose terminal management tools.** Rejected because open/send/read/close is a different model action space from one persistent `bash` call.
**Modify native read/write/edit.** Rejected because it would distort their general-purpose contracts instead of adding an independently composable editor.
## Consequences
Profiles can reproduce an external agent by configuring persona and descriptions while the underlying packages remain general. Persistent Bash requires an owning Agent and real PTY backend. Shell exit, timeout, or cancellation loses state. The editor delegates security and mutation policy to the mounted filesystem stack. Runtime-wheel consumers still need no Node installation, but the wheel now contains a main executable plus its private native helper rather than one physical file.

View File

@@ -0,0 +1,33 @@
# Agent Note持久 Bash 与字符串替换编辑器工具
状态:已实现
[English](2026-07-29-persistent-bash-str-replace-editor.md) | 中文
## 问题
部分部署需要只调用一次的 Bash schema同时要求 shell 状态跨模型轮次保留;另一些部署需要与终端选择无关的 Claude 风格 `str_replace_editor`。把两个工具绑在一起或按某个基准命名,会阻碍复用并模糊配置归属。
## 决策
`@deepseek-ai/dsh-tool-bash-persistent` 消费 `ctx.pty` 并注册一个 `bash(command)` 工具。它为每个精确 Agent 惰性创建一个交互式 shell并串行化该所有者的调用。Cwd、导出的变量、已激活环境、函数和后台任务会保留。随机私有标记划分命令输出保留的 scrollback 会向前分页,以恢复命令真正的输出前缀,若前缀已被丢弃则明确告知。超时或取消会先关闭 shell避免下一次调用复用状态不确定的会话模型可见的超时退出结果也会说明该重置。可配置描述默认只声明持久性事实因此网络和软件包镜像等声明仍归部署所有。
`@deepseek-ai/dsh-tool-str-replace-editor` 独立消费 `ctx.fs`,注册包含 `view``create``str_replace``insert``str_replace_editor`。它提供带行号文本查看、过滤后的两层目录列表、唯一字面量替换、规范插入边界和有界输出。公开 schema 与错误只使用 `old_str`;规范模式要求绝对路径,并在变更前展开制表符。有明确 session-cwd 契约的部署可以关闭绝对路径要求。它可以与持久 Bash、一次性 Bash、沙箱 Bash 或无 shell 组合。
`dsh-system-prompt` 接受 `includeHarnessIdentity: false``dsh-agent-spine-demo` 会转发该设置,并接受 `toolBash: false`。因此部署可以拥有精确 persona并替换 spine 的原生 Bash而不会重复注册提示词或工具。既有默认值不变。
两个插件都进入 Python runtime 闭包。持久 Bash 的闭包还包含 PTY 服务/本地后端,以及该后端要求的沙箱服务。由于 `node-pty` 会执行原生 `spawn-helper`,每个打包后的运行时可执行文件都会携带一个架构匹配的 `-spawn-helper` 伴随文件。固定版本的 `node-pty` 补丁只在该伴随文件存在时解析它(也可由 `DSH_NODE_PTY_SPAWN_HELPER` 显式指定),普通 Node 运行仍保留上游查找方式;若 helper 缺失、架构不匹配或不可执行,可执行文件与 runtime wheel 构建会在发布前失败。
## 考虑过的替代方案
**单一组合兼容插件。** 被拒绝,因为两个工具互不依赖,组合命名还会把可复用能力绑定到某个基准。
**复用一次性 Bash。** 被拒绝,因为 `bash -c` 无法跨调用保留 cwd 或环境状态。
**暴露终端管理工具。** 被拒绝,因为 open/send/read/close 与单个持久 `bash` 调用是不同的模型动作空间。
**修改原生 read/write/edit。** 被拒绝,因为这会扭曲其通用契约,而不是增加一个可独立组合的编辑器。
## 后果
Profile 可以通过配置 persona 和描述复现外部 Agent而底层包保持通用。持久 Bash 需要拥有它的 Agent 与真实 PTY 后端shell 退出、超时或取消会丢失状态。编辑器把安全与变更策略委托给挂载的文件系统栈。runtime wheel 的使用者仍不需要安装 Node但 wheel 现在包含主可执行文件及其私有原生 helper而不是单个物理文件。