Merge branch 'codex/simp-agent-entry-state' into codex/simp-unify-agent-session-id
# Conflicts: # docs/cordis-catalog/events.md # docs/cordis-catalog/services.md # docs/event-producer-consumer.md # docs/module-graph.md # packages/bash/tool-bash/src/index.ts # packages/ui/stdio-agent/README.md # packages/ui/stdio-agent/src/index.ts # packages/ui/stdio/src/index.ts # packages/workflow/workflow-workerthread/tests/workflow-workerthread.spec.ts # packages/workflow/workflow/package.json # scripts/gen-doc-graphs.ts
This commit is contained in:
Tianyi Cui
@@ -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. A sandboxing executor changes the `bash` schema and result markers but adds no mode statement or switch notice; see [Per-session mode](#per-session-mode-switching).
|
||||
|
||||
## Tools
|
||||
|
||||
@@ -29,7 +29,7 @@
|
||||
"@deepseek-ai/dsh-sandbox": "^0.0.1",
|
||||
"@deepseek-ai/dsh-system-prompt": "^0.0.1",
|
||||
"@deepseek-ai/dsh-tools": "^0.0.1",
|
||||
"cordis": "^4.0.0-rc.6"
|
||||
"cordis": "^4.0.0-rc.7"
|
||||
},
|
||||
"devDependencies": {
|
||||
"@deepseek-ai/dsh-agent": "workspace:^",
|
||||
@@ -44,6 +44,6 @@
|
||||
"@deepseek-ai/dsh-session": "workspace:^",
|
||||
"@deepseek-ai/dsh-system-prompt": "workspace:^",
|
||||
"@deepseek-ai/dsh-tools": "workspace:^",
|
||||
"cordis": "^4.0.0-rc.6"
|
||||
"cordis": "^4.0.0-rc.7"
|
||||
}
|
||||
}
|
||||
|
||||
@@ -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 { parseExitStatus, renderResult } from './render.ts'
|
||||
|
||||
export const name = 'tool-bash'
|
||||
export const inject = ['tools', 'bash', 'systemPrompt']
|
||||
@@ -185,73 +186,7 @@ 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
|
||||
// pure — a UI may call them during live streaming AND a session-log replay.
|
||||
// ---------------------------------------------------------------------------
|
||||
// Pure tool-owned presentation used for both live events and replay.
|
||||
|
||||
/**
|
||||
* Pending-state presentation for a `bash` call. The TITLE is the exact `command`
|
||||
@@ -336,39 +271,6 @@ function presentBashResult(args: unknown, result: ToolResult): ToolResultView |
|
||||
return { card: 'terminal', output: raw, ...parseExitStatus(raw) }
|
||||
}
|
||||
|
||||
/**
|
||||
* Recover the structured exit status from a rendered `renderResult` string — the
|
||||
* inverse of the status markers it appends. A `[killed by signal: SIG]` marker
|
||||
* yields `{signal}`; otherwise an `[exit code: N]` marker yields `{exitCode:N}`;
|
||||
* absent both we report `{exitCode:0}` (a clean run appends no marker — and a
|
||||
* trapped-timeout run that exits 0 also has none and is accurately exit 0).
|
||||
*
|
||||
* Why parse rendered text at all: `presentResult` is replay-safe and on a
|
||||
* `session/load` the ONLY thing persisted is this content text — the structured
|
||||
* `BashRunResult` is long gone — so unless the exit were added to the persisted
|
||||
* event schema (deliberately NOT done; see the terminal-rendering RFC), parsing
|
||||
* is the only channel. The match is anchored to a LEADING newline + end-of-string
|
||||
* because `renderResult` always inserts a `\n` before the marker (line ~124) onto
|
||||
* a non-empty body: a real marker is therefore always its own final line. That
|
||||
* defeats the common spoof (program output that simply ENDS in `[exit code: 5]`
|
||||
* with no trailing newline — a clean exit 0 — no longer reads as a failure).
|
||||
*
|
||||
* KNOWN RESIDUAL (inherent to the replay-only-sees-text design): a clean exit 0
|
||||
* whose body's FINAL line is itself exactly the marker text — `[exit code: N]`
|
||||
* or `[killed by signal: SIG]`, printed by the program with nothing after — is
|
||||
* still indistinguishable from a real marker and would show a wrong pill. This is
|
||||
* display-only (execution and the model-facing text are unaffected) and narrow;
|
||||
* the complete fix is to persist a structured exit on the result event, which the
|
||||
* RFC names as the escape hatch.
|
||||
*/
|
||||
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 }
|
||||
}
|
||||
@@ -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-'))
|
||||
|
||||
@@ -112,7 +112,6 @@ 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,
|
||||
@@ -287,9 +286,17 @@ describe('bash tool', () => {
|
||||
|
||||
it('contributes the exit-code habit as its prompt section (guidance the descriptions cannot carry)', async () => {
|
||||
const ctx = await setup()
|
||||
ctx.systemPrompt.section({ name: 'test:before-bash', order: 104, text: 'before' })
|
||||
ctx.systemPrompt.section({ name: 'test:after-bash', order: 106, text: 'after' })
|
||||
const assembly = await ctx.systemPrompt.assemble()
|
||||
const section = assembly.sections.find(s => s.name === 'tool:bash')
|
||||
expect(section?.order).toBe(105)
|
||||
expect(assembly.sections.map(s => s.name)).toEqual([
|
||||
'harness:identity',
|
||||
'deployment:persona',
|
||||
'test:before-bash',
|
||||
'tool:bash',
|
||||
'test:after-bash',
|
||||
])
|
||||
expect(section?.text).toContain('[exit code: N]')
|
||||
})
|
||||
|
||||
@@ -1059,7 +1066,6 @@ describe('sandbox rendering', () => {
|
||||
class FactsOnlyExecutor extends TestBashExecutor {
|
||||
private readonly task: BashTask = {
|
||||
id: BashTaskId('bash-facts'),
|
||||
command: 'fake',
|
||||
status: 'completed',
|
||||
exitCode: 1,
|
||||
signal: null,
|
||||
|
||||
Reference in New Issue
Block a user