@deepseek-ai/dsh-shell

description: "The shell executor seam for developers and maintainers choosing, composing, or implementing command execution over ctx.shell." kind: "package-reference"

@deepseek-ai/dsh-shell

English | 中文

Summary

Use ctx.shell to run shell commands with bounded output or keep them running as background work. One execution handle supports foreground results and background reads. A profile can select local or sandboxed Bash or PowerShell execution without changing callers. Resolve requests before execution to make the working directory, timeout, and output limits explicit. Command exits, timeouts, and caller aborts return results; only infrastructure failures reject, while the bash and pwsh tools own model-visible rendering and sandbox guidance.

Table of Contents

• Use this package
• Understand the implementation
• Further Exploration
• Model Experience
• Known Limitations and Deferred Work
• Dev Note

Use this package

Use ctx.shell when an agent or an in-process plugin needs to run a shell command and read its output, keep a process running and poll it, or hand a foreground command a way to outlive its deadline. There is one execution method — execute(spec) resolves with the prepared handle — and "foreground" is a property of what the caller awaits, not of the spawn. It is the contract every shell executor and the model-facing bash/pwsh tools build on, so code written against it works over any executor implementation.

Foreground commands

Await the handle's result() projection to run a command in the foreground. The promise resolves when the command finishes: a nonzero exit, an executor timeout kill, or a caller abort kill is a result, never a rejection. result() rejects only for infrastructure failures such as an unusable working directory or a missing shell. The result carries the exit code or signal, whether a timeout or an abort cut the run short (first-cause classification), and the collected stdout/stderr with spill-file paths when a stream overflowed its budget.

const execution = await ctx.shell.execute(ctx.shell.resolve({ command: 'ls -la' }))
const result = await execution.result()
console.log(result.exitCode, result.stdout.text)

Background processes

Resolve the request with onExpiry: 'none' and await execute for the prepared handle: no deadline is armed, and the process runs until killed or finished. Read output incrementally with readOutput() — consecutive reads never repeat output, and lossy reads point at full-stream spill files. Terminate the provider-managed range with kill() (returns false once the direct command has finished) and await done for direct-command settlement. Job ids, ownership, polling, and notices belong to the generic ctx.jobs runtime, where the tool layer registers the handle. ShellProcess.observed exposes non-consuming offset readers over the same captured streams — for observers independent of the consuming cursor, such as the job registry's pull sources — including the spawn failed: … note a rejected spawn leaves on stderr.

Deadlines and bounded waits

The deadline includes asynchronous preparation. Expiry before a process starts returns a settled handle whose result is timedOut: true, with empty output. Cancellation or preparation failure rejects execute before publication; late preparation cannot spawn a process.

The seam has two expiry policies and no hand-over protocol. 'kill' stops the command at the deadline and classifies the result timedOut; 'none' arms no deadline, so only the caller's signal and kill() stop the command. A caller that wants to wait only for a while runs the command under 'none' and bounds its own wait: the handle stays valid after the caller stops waiting, and nothing changes hands at that moment. The bash/pwsh tools do exactly this — with a job registry composed they register every command with ctx.jobs as it starts and wait on the job, so a foreground command that outlives its timeout simply keeps running as the job it already was.

Requests and resolved specs

Every execution starts from a ShellExecRequest with optional fields; the executor's resolve() turns it into a fully-resolved ShellExecSpec with explicit defaults and caps before anything runs. This request/spec split is the repository's template for explicit resolution at package boundaries: callers never rely on hidden defaults inside execute. resolve() fills the working directory, timeout, and expiry policy (default 'kill') from the executor's configuration and the request, caps per-call overrides, and carries optional inputs — stdin, ordinary env, and the trusted DSH_* snapshot — through verbatim.

Choosing and composing an executor

The seam is not an executor: mount exactly one provider per composition, and the tools work unchanged. On POSIX, dsh-bash-local runs commands as fresh bash -c processes and dsh-bash-sandbox confines every command through the sandbox capability; on Windows, dsh-pwsh-local and dsh-pwsh-sandbox are the counterparts. The bash and pwsh tools advertise escalation fields only while a sandboxing executor is mounted. The smallest composition is the executor alone:

- id: bash
  name: '@deepseek-ai/dsh-bash-local'
  config:
    cwd: /path/to/workspace

The shared exit-status contract

Tool results end with a machine-readable exit marker — [exit code: N] or [killed by signal: X] — so the model can always tell how a command ended. The seam owns that marker format and the parseExitStatus helper that splits a rendered result back into its output body and structured exit status, keeping the bash and pwsh tools from drifting on it.

Understand the implementation

Implementation internals — click to expand

This section explains the design of the seam and points at the code that realizes it; the observable behavior is fully covered in Use this package.

Design philosophy

The package is one role of a standard capability seam: the Service Definition that names the executor contract, with Service Providers and Consumers split so each role evolves independently (see the capability-seams note). Two decisions anchor the contract:

• Explicit resolution at the boundary. resolve(request) is the single place defaults and caps are applied; execute accepts only resolved specs and never re-defaults, so no hidden fallback lives inside an implementation.
• One execution, projected views. execute resolves with the prepared handle; the foreground result and the background cursor reads are projections over the same spawned process, so foreground/background is the caller's choice, never a second spawn path. The handle carries no id or owner; job identity, ownership, and lifecycle belong to the generic ctx.jobs runtime, keeping executors independent of sessions.

Source map

File	Role
src/index.ts	Plugin entry: abstract ShellExecutor service and the shared settings namespace
src/types.ts	Request/spec vocabulary, ShellExecution, ShellRunResult, and sandbox facts
src/render.ts	parseExitStatus: the exit-status marker contract the shell tools share

Settings namespace

SHELL_SETTINGS_NAMESPACE is exported here rather than by a provider because it names the capability, not an implementation: a host composes exactly one provider of ctx.shell, so the providers share one namespace without colliding, and a settings document carried between platforms keeps resolving on both.

Background lifecycle and ownership

A spawned process belongs to the subprocess service, not to the executor: it survives an executor-only reload and is killed and joined when the composition tears down. Implementations must honor the seam's semantics — result() rejects only for infrastructure failures; the handle is published after preparation and its done never rejects (provider rejections, synchronous or asynchronous, settle the handle as killed with a stage-neutral note on stderr while result() carries the same failure as its rejection; a live handle whose rejection follows the execution's own kill() or abort settles as its terminal outcome instead); readOutput is consuming and lossy reads report spill files.

Further Exploration

Read these pages when the seam contract is not enough. They move from the shared subsystem reference to the concrete executors and the model-facing tools.

• Bash executor subsystem — the request/spec vocabulary, results, and service contract in full.
• bash-local — the default POSIX executor: fresh bash -c processes, budgets, and deadlines.
• bash-sandbox — the confining executor: sandbox modes, denials, and escalation.
• tool-bash — the model-facing bash tool over this seam.
• Capability seams note — the Service Definition / Provider / Consumer split this seam follows.

Model Experience

Indirectly, through dsh-tool-bash, which turns executor output and sandbox facts into guidance and retained tool-result tokens.

KV Cache effect

No direct invalidation; the named consumer owns any request-prefix changes.

Known Limitations and Deferred Work

These limits define what the seam does not provide. They are current package constraints, not a roadmap.

• No interactive-input vocabulary — stdin is written once at spawn and closed; the seam has no channel to feed a running task and no PTY session concept.
• Foreground timeouts are always executor-owned — a caller-owned-deadline mode on the seam is explicitly deferred by the tool-call timeout-policy note.

Dev Note

Working context for maintainers — click to expand

None.