mirror of
https://github.com/deepseek-ai/deepseek-harness
synced 2026-08-15 21:04:50 +00:00
Merge remote-tracking branch 'origin/master' into codex/agent-session-jsonl-location
# Conflicts: # packages/bash/bash-local/tests/run.spec.ts # packages/bash/tool-bash/src/index.ts
This commit is contained in:
Yichen Jiang
@@ -23,8 +23,9 @@ 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, DSH_ENV_PREFIX, OwnerToken, effectiveSandboxMode } from '@deepseek-ai/dsh-bash'
|
||||
import type { BashRunResult, BashTask, CollectedOutput, DshEnvironment, DshEnvironmentKey } from '@deepseek-ai/dsh-bash'
|
||||
import type { BashTask, DshEnvironment, DshEnvironmentKey } from '@deepseek-ai/dsh-bash'
|
||||
import { DSH_HOME_ENV, resolveDshHome } from '@deepseek-ai/dsh-home'
|
||||
import { parseExitStatus, renderResult } from './render.ts'
|
||||
|
||||
declare module 'cordis' {
|
||||
interface Context {
|
||||
@@ -295,65 +296,6 @@ 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: ${output.spillPath ?? '(unavailable)'}]`
|
||||
}
|
||||
|
||||
/**
|
||||
* Shape one finished run into model-visible stdout, marked stderr, and status
|
||||
* facts. Non-zero exits and sandbox denials remain ordinary results; only
|
||||
* infrastructure failure or abort makes the tool call itself fail.
|
||||
*
|
||||
* @param result - the completed foreground run from the executor.
|
||||
* @param escalationModes - the escalation targets this composition advertises; non-empty
|
||||
* adds the same-turn escalation hint after a denial marker (default `[]`: no hint).
|
||||
* @returns the model-facing text: output body (or `(no output)`), then any
|
||||
* timeout/signal/exit markers, each on its own line.
|
||||
*/
|
||||
export function renderResult(
|
||||
result: BashRunResult,
|
||||
escalationModes: readonly SandboxMode[] = [],
|
||||
): string {
|
||||
const out = streamText(result.stdout)
|
||||
const err = streamText(result.stderr)
|
||||
|
||||
let body = out
|
||||
if (err.length > 0) {
|
||||
// Single newline between sections (stdout usually ends with one already).
|
||||
if (body.length > 0 && !body.endsWith('\n')) body += '\n'
|
||||
body += `[stderr]\n${err}`
|
||||
}
|
||||
if (body.length === 0) body = '(no output)'
|
||||
|
||||
const markers: string[] = []
|
||||
// Keep `[exit code: N]` last so parseExitStatus() can recover it. A denial,
|
||||
// like a timeout, remains a reported fact for the model to handle.
|
||||
if (result.sandbox?.denied) {
|
||||
markers.push(`[sandbox: file access denied under ${result.sandbox.mode} mode]`)
|
||||
// Add the retry hint only when the schema advertises escalation, before
|
||||
// the final exit marker.
|
||||
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')
|
||||
}
|
||||
|
||||
// Pure tool-owned presentation used for both live events and replay.
|
||||
|
||||
/**
|
||||
@@ -401,18 +343,6 @@ function presentBashResult(args: unknown, result: ToolResult): ToolResultView |
|
||||
return { card: 'terminal', output: raw, ...parseExitStatus(raw) }
|
||||
}
|
||||
|
||||
/**
|
||||
* Recover exit status from the final marked line emitted by {@link renderResult}.
|
||||
* A program whose own final line exactly mimics a marker remains ambiguous for UI display.
|
||||
*/
|
||||
function parseExitStatus(text: string): { exitCode: number } | { signal: string } {
|
||||
const signal = /\n\[killed by signal: ([^\]\n]+)\]$/.exec(text)
|
||||
if (signal?.[1] !== undefined) return { signal: signal[1] }
|
||||
const exit = /\n\[exit code: (\d+)\]$/.exec(text)
|
||||
if (exit?.[1] !== undefined) return { exitCode: Number(exit[1]) }
|
||||
return { exitCode: 0 }
|
||||
}
|
||||
|
||||
/** Pending-state presentation for `bash_output`/`bash_kill` (background-task tools). */
|
||||
function presentTaskCall(verb: string, args: { task_id: string }): GenericCallView {
|
||||
return { card: 'generic', title: `${verb} background task ${args.task_id}`, kind: 'execute', rawInput: args.task_id }
|
||||
|
||||
92
packages/bash/tool-bash/src/render.ts
Normal file
92
packages/bash/tool-bash/src/render.ts
Normal file
@@ -0,0 +1,92 @@
|
||||
/**
|
||||
* Model-facing result rendering for the bash tool.
|
||||
*
|
||||
* @module @deepseek-ai/dsh-tool-bash/render
|
||||
*/
|
||||
|
||||
import type { BashRunResult, CollectedOutput } from '@deepseek-ai/dsh-bash'
|
||||
import type { SandboxMode } from '@deepseek-ai/dsh-sandbox'
|
||||
|
||||
/** Append the truncation notice (with the full-output spill path) to a stream's text. */
|
||||
function streamText(output: CollectedOutput): string {
|
||||
if (!output.truncated) return output.text
|
||||
return `${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')
|
||||
}
|
||||
|
||||
/**
|
||||
* Recover the structured exit status from a rendered {@link renderResult}
|
||||
* string — the inverse of the status markers it appends. A killed marker
|
||||
* yields `signal`; otherwise a non-zero marker yields `exitCode`; absent both
|
||||
* means a clean exit 0.
|
||||
*
|
||||
* Replay only retains the rendered content text, not the original
|
||||
* `BashRunResult`, so terminal presentation must recover the exit pill here.
|
||||
* Requiring a leading newline and the end of the string keeps ordinary output
|
||||
* that merely ends with marker-like text from matching unless the final line
|
||||
* is indistinguishable from a real marker.
|
||||
* @param text - rendered model-facing bash result.
|
||||
* @returns the recovered terminal exit code or signal.
|
||||
*/
|
||||
export function parseExitStatus(text: string): { exitCode: number } | { signal: string } {
|
||||
const signal = /\n\[killed by signal: ([^\]\n]+)\]$/.exec(text)
|
||||
if (signal?.[1] !== undefined) return { signal: signal[1] }
|
||||
const exit = /\n\[exit code: (\d+)\]$/.exec(text)
|
||||
if (exit?.[1] !== undefined) return { exitCode: Number(exit[1]) }
|
||||
return { exitCode: 0 }
|
||||
}
|
||||
Reference in New Issue
Block a user