refactor: prune bash implementation surface

This commit is contained in:
Tianyi Cui
2026-07-14 03:37:51 +08:00
parent a0359bc4a9
commit 8c8b422f17
13 changed files with 88 additions and 109 deletions
+2
View File
@@ -4,6 +4,8 @@ The model-facing bash tools — `bash`, `bash_output`, `bash_kill` — registere
Requires a loaded executor implementation (e.g. `@deepseek-ai/dsh-bash-local`); the plugin stays pending until `ctx.bash` exists (`inject: ['tools', 'bash', 'systemPrompt']`).
The package root exposes only the Cordis plugin contract (`name`, `inject`, `apply`); result rendering remains an implementation detail covered by same-package tests.
The plugin also contributes the `tool:bash` prompt section (order 105) — the cross-call habit the per-tool descriptions cannot carry: check the `[exit code: N]` marker on every result and investigate failures before moving on. Under a sandboxing executor it additionally contributes the per-agent `env:bash-sandbox` section (order 110) stating each session's EFFECTIVE mode, and the pre-step narrator — see [Per-session mode](#per-session-mode-switching-and-visibility).
## Tools
+2 -63
View File
@@ -68,7 +68,8 @@ import type {} from '@deepseek-ai/dsh-system-prompt'
import type {} from '@deepseek-ai/dsh-user-approval'
import type { SandboxMode } from '@deepseek-ai/dsh-sandbox'
import { BashTaskId, OwnerToken, effectiveSandboxMode } from '@deepseek-ai/dsh-bash'
import type { BashRunResult, BashTask, CollectedOutput } from '@deepseek-ai/dsh-bash'
import type { BashTask } from '@deepseek-ai/dsh-bash'
import { renderResult } from './render.ts'
export const name = 'tool-bash'
export const inject = ['tools', 'bash', 'systemPrompt']
@@ -185,68 +186,6 @@ function bashDescription(escalationModes: readonly SandboxMode[]): string {
+ 'it — but it does not forbid attempting or escalating other commands later.'
}
/** Append the truncation notice (with the full-output spill path) to a stream's text. */
function streamText(output: CollectedOutput): string {
if (!output.truncated) return output.text
return `${output.text}\n[output truncated; full output: ${output.spillPath ?? '(unavailable)'}]`
}
/**
* Shape one finished run into the text the model sees: stdout, then a marked
* stderr section, then exit-status markers. Non-zero exits are REPORTED, not
* errored — the model decides how to react; only infrastructure failures
* (spawn errors, aborts) surface as isError results.
* @param result - the completed foreground run from the executor.
* @param escalationModes - the escalation targets this composition advertises;
* non-empty adds the same-turn escalation hint after a denial marker
* (default `[]`: no hint).
* @returns the model-facing text: output body (or `(no output)`), then any timeout/signal/exit markers, each on its own line.
*/
export function renderResult(
result: BashRunResult,
escalationModes: readonly SandboxMode[] = [],
): string {
const out = streamText(result.stdout)
const err = streamText(result.stderr)
let body = out
if (err.length > 0) {
// Single newline between sections (stdout usually ends with one already).
if (body.length > 0 && !body.endsWith('\n')) body += '\n'
body += `[stderr]\n${err}`
}
if (body.length === 0) body = '(no output)'
const markers: string[] = []
// The sandbox marker precedes the exit-status markers so `[exit code: N]`
// stays the LAST line (exitStatus() anchors its parse there). Denial is a
// reported fact like timeout: the model decides how to react.
if (result.sandbox?.denied) {
markers.push(`[sandbox: file access denied under ${result.sandbox.mode} mode]`)
// The same-turn nudge lives at the decision point: only when this
// composition advertises the fields (a lever is never hinted that the
// schema does not offer), and inside the sandbox marker family so the
// exit-code marker stays the last line.
if (escalationModes.length > 0) {
markers.push('[sandbox: escalation available — retry this exact command once with sandbox_permissions (the narrowest wider mode that suffices) + justification; the approval prompt asks the user]')
}
}
// Timeout is reported independently of how the process actually ended: a
// command can trap SIGTERM and exit 0 after our timer fired (e.g.
// `trap "exit 0" TERM; sleep 60`), giving timedOut:true / exitCode:0 /
// signal:null — the model must still see that the command was cut short.
if (result.timedOut) markers.push(`[timed out after ${result.timeoutMs}ms]`)
if (result.signal !== null) {
markers.push(`[killed by signal: ${result.signal}]`)
} else if (result.exitCode !== 0) {
markers.push(`[exit code: ${result.exitCode}]`)
}
if (markers.length === 0) return body
if (!body.endsWith('\n')) body += '\n'
return body + markers.join('\n')
}
// ---------------------------------------------------------------------------
// UI presentation (tool-owned). These shape how a UI (e.g. the ACP bridge)
// renders a bash call's pending and completed states. They are display-only and
+70
View File
@@ -0,0 +1,70 @@
/**
* Model-facing result rendering for the bash tool.
*
* @module @deepseek-ai/dsh-tool-bash/render
*/
import type { BashRunResult, CollectedOutput } from '@deepseek-ai/dsh-bash'
import type { SandboxMode } from '@deepseek-ai/dsh-sandbox'
/** Append the truncation notice (with the full-output spill path) to a stream's text. */
function streamText(output: CollectedOutput): string {
if (!output.truncated) return output.text
return `${output.text}\n[output truncated; full output: ${output.spillPath ?? '(unavailable)'}]`
}
/**
* Shape one finished run into the text the model sees: stdout, then a marked
* stderr section, then exit-status markers. Non-zero exits are REPORTED, not
* errored — the model decides how to react; only infrastructure failures
* (spawn errors, aborts) surface as isError results.
* @param result - the completed foreground run from the executor.
* @param escalationModes - the escalation targets this composition advertises;
* non-empty adds the same-turn escalation hint after a denial marker
* (default `[]`: no hint).
* @returns the model-facing text: output body (or `(no output)`), then any timeout/signal/exit markers, each on its own line.
*/
export function renderResult(
result: BashRunResult,
escalationModes: readonly SandboxMode[] = [],
): string {
const out = streamText(result.stdout)
const err = streamText(result.stderr)
let body = out
if (err.length > 0) {
// Single newline between sections (stdout usually ends with one already).
if (body.length > 0 && !body.endsWith('\n')) body += '\n'
body += `[stderr]\n${err}`
}
if (body.length === 0) body = '(no output)'
const markers: string[] = []
// The sandbox marker precedes the exit-status markers so `[exit code: N]`
// stays the LAST line (exitStatus() anchors its parse there). Denial is a
// reported fact like timeout: the model decides how to react.
if (result.sandbox?.denied) {
markers.push(`[sandbox: file access denied under ${result.sandbox.mode} mode]`)
// The same-turn nudge lives at the decision point: only when this
// composition advertises the fields (a lever is never hinted that the
// schema does not offer), and inside the sandbox marker family so the
// exit-code marker stays the last line.
if (escalationModes.length > 0) {
markers.push('[sandbox: escalation available — retry this exact command once with sandbox_permissions (the narrowest wider mode that suffices) + justification; the approval prompt asks the user]')
}
}
// Timeout is reported independently of how the process actually ended: a
// command can trap SIGTERM and exit 0 after our timer fired (e.g.
// `trap "exit 0" TERM; sleep 60`), giving timedOut:true / exitCode:0 /
// signal:null — the model must still see that the command was cut short.
if (result.timedOut) markers.push(`[timed out after ${result.timeoutMs}ms]`)
if (result.signal !== null) {
markers.push(`[killed by signal: ${result.signal}]`)
} else if (result.exitCode !== 0) {
markers.push(`[exit code: ${result.exitCode}]`)
}
if (markers.length === 0) return body
if (!body.endsWith('\n')) body += '\n'
return body + markers.join('\n')
}
+1 -3
View File
@@ -19,7 +19,7 @@ import { LocalSandboxProvider } from '@deepseek-ai/dsh-sandbox-local'
import ApprovalService from '@deepseek-ai/dsh-user-approval'
import type { ApprovalOutcome } from '@deepseek-ai/dsh-user-approval'
import * as ToolBash from '@deepseek-ai/dsh-tool-bash'
import { renderResult } from '@deepseek-ai/dsh-tool-bash'
import { renderResult } from '../src/render.ts'
const spillDir = mkdtempSync(join(tmpdir(), 'dsh-tool-bash-spec-'))
@@ -118,7 +118,6 @@ abstract class TestBashExecutor extends BashExecutor {
class LossyReadBashExecutor extends TestBashExecutor {
private readonly task: BashTask = {
id: BashTaskId('bash-lossy'),
command: 'fake',
status: 'running',
exitCode: null,
signal: null,
@@ -1062,7 +1061,6 @@ describe('sandbox rendering', () => {
class FactsOnlyExecutor extends TestBashExecutor {
private readonly task: BashTask = {
id: BashTaskId('bash-facts'),
command: 'fake',
status: 'completed',
exitCode: 1,
signal: null,