feat(bash): generalize managed shell environment

This commit is contained in:
Yichen Jiang
2026-07-12 15:41:42 +08:00
parent acdbe7b828
commit df9617aaff
40 files changed
+790 -197

No files matched your search

+19 -4
View File
@@ -22,11 +22,26 @@ The plugin also contributes the `tool:bash` prompt section (order 105) — the c
`command`, `workdir`, and `timeoutMs` are resolved against the executor's config defaults via `ctx.bash.resolve()` before execution, so the executor seam (`BashExecSpec`) receives explicit `workdir`/`timeoutMs` values. The workdir default is applied in the tool layer (from the calling agent's `session.header.cwd`) BEFORE `resolve()` — the per-session cwd must come from `exec.agent`, since N sessions share one executor; only when no session cwd is available does the executor fall back to its own config / `process.cwd()`.
### Session identity environment
### Managed shell environment
Every foreground and background call made for an agent receives `DSH_SESSION_ID=agent.session.header.id`. When the active persistence backend locates a JSONL artifact, the call also receives `DSH_SESSION_JSONL=<absolute target path>`; absent persistence and non-file backends still provide the id but omit the JSONL variable. The path is a location hint: lazy materialization means it may not exist on the first turn, and during an open turn it can omit buffered events that have not reached `session/flush`. Neither value is an authorization credential.
Every foreground and background model bash call receives a newly collected trusted `DSH_*` environment. `DSH_HOME` is the absolute Harness home (`dshHome` config, then ambient `$DSH_HOME`, then `~/.dsh`) and `DSH_SHELL=1` identifies the managed child. Agent calls additionally receive `DSH_SESSION_ID=agent.session.header.id`; when the active persistence seam locates a JSONL artifact they also receive `DSH_SESSION_JSONL=<absolute target path>`. The JSONL path is a location hint: it may not exist before the first flush or contain the current buffered turn, and it is not an authorization credential.
The overlay is computed from `ToolExecution.agent` for each call and passed through `BashExecRequest.env`; `process.env` is never modified, so concurrent parent/child agents keep separate values. The tool description names both variables so the model can inspect them without a permanent system-prompt section.
`ctx.bashEnv` owns collection. Other plugins can register an effect-scoped contributor with a stable name, declared keys/descriptions, and `resolve(execution: ToolExecution)`; duplicate ownership and undeclared runtime keys fail loudly, while `list()` enumerates declarations without executing providers. Harness built-ins reserve `DSH_HOME`, `DSH_SHELL`, and `DSH_SESSION_ID`; tool-bash's persistence translator owns `DSH_SESSION_JSONL` by reading the backend-neutral `sessionPersistence.locate()` seam.
```ts
import type { Context } from 'cordis'
import type {} from '@deepseek-ai/dsh-tool-bash'
export function apply(ctx: Context): void {
ctx.bashEnv.register({
name: 'deployment-region',
variables: { DSH_DEPLOYMENT_REGION: { description: 'Current deployment region.' } },
resolve: execution => execution.agent === undefined ? {} : { DSH_DEPLOYMENT_REGION: 'cn-north' },
})
}
```
The overlay is computed from the current `ToolExecution` and passed through the dedicated `BashExecRequest.dshEnv` channel. The local executor removes all inherited `DSH_*` before merging that snapshot, so nested harnesses and concurrent parent/child agents cannot leak stale identities. `process.env` is never modified. The tool description teaches the generic `$DSH_*` convention rather than naming persistence-specific variables or adding a permanent system-prompt section.
Result text: stdout, then a `[stderr]` section, then status markers — `[sandbox: file access denied under <mode> mode]` when a sandboxing executor classified the failure as a policy denial (reported first so `[exit code: N]` stays the last line; the static description tells the model a denial is policy, not a command bug, and forbids retrying around it), `[timed out after Nms]` whenever the executor's timer fired (reported independently of how the process ended, so a command that traps SIGTERM and exits 0 still shows it), `[killed by signal: …]` for a signal death, `[exit code: N]` for a non-zero exit (reported, **not** `isError`: the model decides how to react), and `[output truncated; full output: <path>]` when the tail was kept and a safe spill file is available. If the executor knows output was dropped but cannot safely advertise a complete spill file, the path is reported as `(unavailable)`. Only infrastructure failures (spawn errors, aborts) surface as `isError` results.
@@ -52,7 +67,7 @@ When a background task finishes, a short notice is injected into the owning agen
## The tool builds its request from named args only
The `BashExecRequest` seam carries optional `stdin` and `env`, used by trusted consumers. This tool does **not** expose them as model parameters: it builds the request from named schema fields and adds only the session overlay above, so model-supplied `env`/`stdin` keys are ignored and cannot replace the trusted values. This is not a trust boundary — a model already has equivalent power through shell syntax (`FOO=bar cmd`, a heredoc), and the real defense against leaking ambient secrets is `dsh-bash-local`'s credential scrub. Regression guards assert extra model fields never enter the request while the trusted overlay still does. See [the bash-stdin-env RFC](../../../docs/rfc/implemented/architecture/2026-06-30-bash-stdin-env-trusted-plugin-surface.md).
The `BashExecRequest` seam carries optional `stdin` and ordinary `env` for in-process consumers plus the harness-owned `dshEnv` channel above. This tool does **not** expose any of them as model parameters: it builds the request from named schema fields, so model-supplied `env`/`stdin` keys are ignored and cannot replace the managed values. A model already has equivalent command-local power through shell syntax (`FOO=bar cmd`, a heredoc); ambient-secret protection comes from `dsh-bash-local`'s credential scrub, while `dshEnv` ownership prevents stale or spoofed Harness context. See [the bash-stdin-env RFC](../../../docs/rfc/implemented/architecture/2026-06-30-bash-stdin-env-trusted-plugin-surface.md).
## Permissions and escalation
+3
View File
@@ -32,6 +32,9 @@
"@deepseek-ai/dsh-tools": "^0.0.1",
"cordis": "^4.0.0-rc.6"
},
"dependencies": {
"schemastery": "^3.18.0"
},
"devDependencies": {
"@deepseek-ai/dsh-agent": "workspace:^",
"@deepseek-ai/dsh-agent-loop": "workspace:^",
+192 -24
View File
@@ -55,8 +55,10 @@
* @module @deepseek-ai/dsh-tool-bash
*/
import type { Context } from 'cordis'
import { isAbsolute, resolve as resolvePath } from 'node:path'
import { Service, type Context } from 'cordis'
import z from 'schemastery'
import { homedir } from 'node:os'
import { isAbsolute, join, resolve as resolvePath } from 'node:path'
import { defineTool } from '@deepseek-ai/dsh-tools'
import type { GenericCallView, TerminalCallView, ToolExecution, ToolResult, ToolResultView } from '@deepseek-ai/dsh-tools'
import type { Agent } from '@deepseek-ai/dsh-agent'
@@ -69,11 +71,178 @@ 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 { BashRunResult, BashTask, CollectedOutput, DshEnvironment } from '@deepseek-ai/dsh-bash'
declare module 'cordis' {
interface Context {
bashEnv: BashEnvRegistry
}
}
export const name = 'tool-bash'
export const inject = ['tools', 'bash', 'systemPrompt']
/** Configuration for the bash tool and its managed child environment. */
export interface Config {
/** DeepSeek Harness home directory exposed as `DSH_HOME`; defaults to `$DSH_HOME` or `~/.dsh`. */
dshHome?: string
}
/** Runtime configuration schema for the bash tool plugin. */
export const Config: z<Config> = z.object({
dshHome: z.string(),
})
/** Model-visible metadata for one managed `DSH_*` environment variable. */
export interface BashEnvVariable {
/** Concise description of the environment fact represented by the variable. */
description: string
}
/**
* A plugin contribution to the managed environment of each model bash call.
* Declared keys make ownership conflicts detectable before the first command;
* `resolve` computes only the values available for the current execution.
*/
export interface BashEnvContributor {
/** Stable contributor name used in diagnostics and duplicate detection. */
name: string
/** Complete set of `DSH_*` keys this contributor may return. */
variables: Readonly<Record<`DSH_${string}`, BashEnvVariable>>
/**
* Resolve this contributor's available values for one tool execution.
* @param execution - the bash tool execution and its optional calling agent.
* @returns a partial map containing only keys declared in {@link variables}.
*/
resolve(execution: ToolExecution): Readonly<Partial<Record<`DSH_${string}`, string>>>
}
/** An enumerable declaration returned by {@link BashEnvRegistry.list}. */
export interface BashEnvVariableInfo extends BashEnvVariable {
/** Contributor that owns the variable. */
contributor: string
/** Declared `DSH_*` environment variable name. */
key: `DSH_${string}`
}
const RESERVED_BASH_ENV_KEYS = new Set<`DSH_${string}`>([
'DSH_HOME',
'DSH_SHELL',
'DSH_SESSION_ID',
])
const BASH_ENV_KEY = /^DSH_[A-Z][A-Z0-9_]*$/
/**
* Registry (`ctx.bashEnv`) for trusted, per-execution `DSH_*` variables.
* The namespace is rebuilt for every model bash call: ambient `DSH_*` values
* are discarded by the executor, then the registry's current snapshot is
* injected. Built-in shell facts remain owned by the registry itself while
* plugins can register additional, enumerable facts with effect-scoped
* disposal.
*/
export class BashEnvRegistry extends Service {
private readonly contributors = new Map<string, BashEnvContributor>()
private readonly keyOwners = new Map<`DSH_${string}`, string>()
private readonly dshHome: string
/**
* Create and install the `ctx.bashEnv` service.
* @param ctx - Cordis context that owns the service and registrations.
* @param config - home-directory configuration for the built-in variables.
*/
constructor(ctx: Context, config: Config = {}) {
super(ctx, 'bashEnv')
this.dshHome = resolvePath(config.dshHome ?? process.env.DSH_HOME ?? join(homedir(), '.dsh'))
}
/**
* Register one environment contributor. Names and keys are unique; built-in
* keys are reserved. Registration is disposed with the calling plugin fiber.
* @param contributor - declared key ownership and per-execution resolver.
* @returns the disposer that unregisters the contribution.
*/
register(contributor: BashEnvContributor): () => void {
const dispose = this.ctx.effect(function* (this: BashEnvRegistry) {
if (contributor.name.trim().length === 0) {
throw new Error('bash env contributor name must be non-empty')
}
if (this.contributors.has(contributor.name)) {
throw new Error(`bash env contributor "${contributor.name}" is already registered`)
}
const variables = Object.entries(contributor.variables) as [`DSH_${string}`, BashEnvVariable][]
for (const [key, variable] of variables) {
if (!BASH_ENV_KEY.test(key)) {
throw new Error(`bash env contributor "${contributor.name}" declared invalid key "${key}"`)
}
if (RESERVED_BASH_ENV_KEYS.has(key)) {
throw new Error(`bash env contributor "${contributor.name}" cannot own reserved key "${key}"`)
}
if (variable.description.trim().length === 0) {
throw new Error(`bash env contributor "${contributor.name}" must describe "${key}"`)
}
const owner = this.keyOwners.get(key)
if (owner !== undefined) {
throw new Error(`bash env key "${key}" is already owned by contributor "${owner}"; contributor "${contributor.name}" cannot also own it`)
}
}
this.contributors.set(contributor.name, contributor)
for (const [key] of variables) this.keyOwners.set(key, contributor.name)
yield () => {
this.contributors.delete(contributor.name)
for (const [key] of variables) this.keyOwners.delete(key)
}
}.bind(this), 'bashEnv.register()')
return () => void dispose()
}
/**
* Build the trusted `DSH_*` snapshot for one bash tool execution.
* @param execution - the current tool execution.
* @returns an immutable environment overlay containing built-ins and current contributions.
*/
collect(execution: ToolExecution): DshEnvironment {
const values: Record<`DSH_${string}`, string> = {
DSH_HOME: this.dshHome,
DSH_SHELL: '1',
}
if (execution.agent !== undefined) {
values.DSH_SESSION_ID = execution.agent.session.header.id
}
for (const contributor of [...this.contributors.values()].sort((left, right) => left.name.localeCompare(right.name))) {
const resolved = contributor.resolve(execution)
for (const [rawKey, value] of Object.entries(resolved)) {
const key = rawKey as `DSH_${string}`
if (!Object.hasOwn(contributor.variables, key)) {
throw new Error(`bash env contributor "${contributor.name}" returned undeclared key "${key}"`)
}
if (typeof value !== 'string') {
throw new Error(`bash env contributor "${contributor.name}" returned a non-string value for "${key}"`)
}
values[key] = value
}
}
return Object.freeze(Object.fromEntries(Object.entries(values).sort(([left], [right]) => left.localeCompare(right))))
}
/**
* Enumerate plugin-contributed variables without executing their resolvers.
* @returns declarations sorted by environment variable name.
*/
list(): BashEnvVariableInfo[] {
return [...this.contributors.values()]
.flatMap(contributor => Object.entries(contributor.variables).map(([key, variable]) => ({
contributor: contributor.name,
description: variable.description,
key: key as `DSH_${string}`,
})))
.sort((left, right) => left.key.localeCompare(right.key))
}
}
/**
* Validate the constraints the SchemaSpec can't express. `defineTool` now
* validates parsed args against the SchemaSpec before `execute` runs (the
@@ -168,8 +337,7 @@ function bashDescription(escalationModes: readonly SandboxMode[]): string {
const base = 'Execute a bash command (`bash -c`) and return its stdout/stderr. '
+ 'Each call runs in a fresh shell: no state (cwd, variables, functions) persists between calls — '
+ 'pass `workdir` instead of using `cd`. Non-zero exits are reported as `[exit code: N]`. '
+ 'The current agent session id is available as `$DSH_SESSION_ID`; when JSONL persistence is configured, '
+ '`$DSH_SESSION_JSONL` is its absolute target path and may not exist or contain the current unflushed turn yet. '
+ 'Current harness environment facts are exposed through managed `$DSH_*` variables; inspect them when needed. '
+ 'Commands may run under a file sandbox; a blocked file operation is reported as `[sandbox: file access denied under <mode> mode]` — a policy denial, not a bug in the command; do not retry another way (a background task reports the same marker via bash_output once it has finished). '
+ 'Long output is truncated to its tail; the full output is saved to a file whose path is reported when available. '
+ 'Set `run_in_background: true` for long-running commands: the call returns a task id immediately; '
@@ -397,22 +565,6 @@ function resolveWorkdir(modelWorkdir: string | undefined, exec: { agent?: Agent
return modelWorkdir
}
/**
* Build the trusted per-execution session environment. Identity always comes
* from the calling agent's immutable session header; an optional JSONL path
* comes from the active persistence backend's side-effect-free locator. A
* non-agent caller has no current session, so it receives neither variable.
*/
function sessionEnvironment(ctx: Context, exec: { agent?: Agent }): Record<string, string> | undefined {
const agent = exec.agent
if (agent === undefined) return undefined
const env: Record<string, string> = { DSH_SESSION_ID: agent.session.header.id }
const location = ctx.get('sessionPersistence')?.locate(agent.session.header)
if (location?.kind === 'jsonl') env.DSH_SESSION_JSONL = location.path
return env
}
/** Status line for background task reads. */
function statusLine(task: BashTask): string {
switch (task.status) {
@@ -422,7 +574,23 @@ function statusLine(task: BashTask): string {
}
}
export function apply(ctx: Context): void {
export function apply(ctx: Context, config: Config = {}): void {
const bashEnv = new BashEnvRegistry(ctx, config)
bashEnv.register({
name: 'session-persistence',
variables: {
DSH_SESSION_JSONL: {
description: 'Absolute target path of the current session JSONL when the active persistence backend provides one.',
},
},
resolve(execution) {
const agent = execution.agent
if (agent === undefined) return {}
const location = ctx.get('sessionPersistence')?.locate(agent.session.header)
return location?.kind === 'jsonl' ? { DSH_SESSION_JSONL: location.path } : {}
},
})
// The bash tools' cross-call HABIT, which the per-tool descriptions cannot
// carry (they describe one call each): the exit-code marker is only useful
// if the model actually checks it every time.
@@ -614,13 +782,13 @@ export function apply(ctx: Context): void {
// session runs in its own workspace (see resolveWorkdir); an explicit
// model workdir still wins.
const workdir = resolveWorkdir(args.workdir, exec)
const env = sessionEnvironment(ctx, exec)
const dshEnv = bashEnv.collect(exec)
const request = {
command: args.command,
...workdir !== undefined ? { workdir } : {},
...args.timeoutMs !== undefined ? { timeoutMs: args.timeoutMs } : {},
...exec.signal ? { signal: exec.signal } : {},
...env !== undefined ? { env } : {},
dshEnv,
...sandboxMode !== undefined ? { sandboxMode } : {},
}
if (args.run_in_background === true) {
@@ -0,0 +1,189 @@
import { homedir } from 'node:os'
import { join, resolve } from 'node:path'
import { afterEach, describe, expect, it, vi } from 'vitest'
import { Context } from 'cordis'
import { CallId } from '@deepseek-ai/dsh-llm'
import type { Agent } from '@deepseek-ai/dsh-agent'
import type { ToolExecution } from '@deepseek-ai/dsh-tools'
import { BashEnvRegistry } from '@deepseek-ai/dsh-tool-bash'
afterEach(() => vi.unstubAllEnvs())
function execution(sessionId?: string): ToolExecution {
return {
callId: CallId('bash-env-call'),
name: 'bash',
arguments: { command: 'true' },
...(sessionId === undefined
? {}
: { agent: { session: { header: { version: 0, id: sessionId, createdAt: 0 } } } as Agent }),
}
}
describe('BashEnvRegistry', () => {
it('collects unconditional shell facts and the current agent session id', () => {
const ctx = new Context()
const registry = new BashEnvRegistry(ctx, { dshHome: './test-dsh-home' })
expect(registry.collect(execution())).toEqual({
DSH_HOME: resolve('./test-dsh-home'),
DSH_SHELL: '1',
})
expect(registry.collect(execution('session-a'))).toEqual({
DSH_HOME: resolve('./test-dsh-home'),
DSH_SESSION_ID: 'session-a',
DSH_SHELL: '1',
})
})
it('resolves DSH_HOME from the ambient override or the user-home default', () => {
vi.stubEnv('DSH_HOME', './ambient-dsh-home')
const fromEnvironment = new BashEnvRegistry(new Context())
expect(fromEnvironment.collect(execution()).DSH_HOME).toBe(resolve('./ambient-dsh-home'))
vi.stubEnv('DSH_HOME', undefined)
const fromDefault = new BashEnvRegistry(new Context())
expect(fromDefault.collect(execution()).DSH_HOME).toBe(join(homedir(), '.dsh'))
})
it('collects declared contributor variables and omits unavailable values', () => {
const ctx = new Context()
const registry = new BashEnvRegistry(ctx, { dshHome: './test-dsh-home' })
registry.register({
name: 'optional-session-fact',
variables: {
DSH_SESSION_OPTIONAL: { description: 'Optional session-scoped test fact.' },
},
resolve: exec => exec.agent === undefined ? {} : { DSH_SESSION_OPTIONAL: exec.agent.session.header.id },
})
registry.register({
name: 'always-available-fact',
variables: {
DSH_ALWAYS_AVAILABLE: { description: 'Always-available test fact.' },
},
resolve: () => ({ DSH_ALWAYS_AVAILABLE: 'yes' }),
})
expect(registry.collect(execution())).not.toHaveProperty('DSH_SESSION_OPTIONAL')
expect(registry.collect(execution()).DSH_ALWAYS_AVAILABLE).toBe('yes')
expect(registry.collect(execution('session-b')).DSH_SESSION_OPTIONAL).toBe('session-b')
expect(registry.list()).toEqual([
{
contributor: 'always-available-fact',
description: 'Always-available test fact.',
key: 'DSH_ALWAYS_AVAILABLE',
},
{
contributor: 'optional-session-fact',
description: 'Optional session-scoped test fact.',
key: 'DSH_SESSION_OPTIONAL',
},
])
})
it('rejects duplicate variable ownership at registration time', () => {
const ctx = new Context()
const registry = new BashEnvRegistry(ctx, { dshHome: './test-dsh-home' })
registry.register({
name: 'first',
variables: { DSH_SHARED: { description: 'First owner.' } },
resolve: () => ({ DSH_SHARED: 'first' }),
})
expect(() => registry.register({
name: 'second',
variables: { DSH_SHARED: { description: 'Second owner.' } },
resolve: () => ({ DSH_SHARED: 'second' }),
})).toThrow(/DSH_SHARED.*first.*second|DSH_SHARED.*second.*first/)
})
it('rejects duplicate contributor names and malformed declarations', () => {
const registry = new BashEnvRegistry(new Context(), { dshHome: './test-dsh-home' })
registry.register({
name: 'declared',
variables: { DSH_DECLARED: { description: 'Declared fact.' } },
resolve: () => ({}),
})
expect(() => registry.register({
name: 'declared',
variables: { DSH_ANOTHER: { description: 'Another fact.' } },
resolve: () => ({}),
})).toThrow(/already registered/)
expect(() => registry.register({
name: ' ',
variables: { DSH_BLANK_NAME: { description: 'Blank owner.' } },
resolve: () => ({}),
})).toThrow(/name must be non-empty/)
expect(() => registry.register({
name: 'invalid-key',
variables: { dsh_invalid: { description: 'Invalid key.' } } as unknown as Record<'DSH_INVALID', { description: string }>,
resolve: () => ({}),
})).toThrow(/invalid key/)
expect(() => registry.register({
name: 'reserved-key',
variables: { DSH_HOME: { description: 'Reserved key.' } },
resolve: () => ({}),
})).toThrow(/reserved key/)
expect(() => registry.register({
name: 'blank-description',
variables: { DSH_BLANK_DESCRIPTION: { description: ' ' } },
resolve: () => ({}),
})).toThrow(/must describe/)
})
it('rejects undeclared variables returned by a contributor', () => {
const ctx = new Context()
const registry = new BashEnvRegistry(ctx, { dshHome: './test-dsh-home' })
registry.register({
name: 'drifted-provider',
variables: { DSH_DECLARED: { description: 'Declared fact.' } },
resolve: () => ({ DSH_UNDECLARED: 'bad' }),
})
expect(() => registry.collect(execution())).toThrow(/drifted-provider.*DSH_UNDECLARED/)
})
it('rejects non-string values returned by a contributor', () => {
const registry = new BashEnvRegistry(new Context(), { dshHome: './test-dsh-home' })
registry.register({
name: 'wrong-value-type',
variables: { DSH_STRING: { description: 'String fact.' } },
resolve: () => ({ DSH_STRING: 42 }) as unknown as Record<'DSH_STRING', string>,
})
expect(() => registry.collect(execution())).toThrow(/wrong-value-type.*non-string.*DSH_STRING/)
})
it('removes an effect-scoped contributor when its plugin is disposed', async () => {
const ctx = new Context()
const registry = new BashEnvRegistry(ctx, { dshHome: './test-dsh-home' })
const fiber = await ctx.plugin({
inject: ['bashEnv'],
apply(inner: Context) {
inner.bashEnv.register({
name: 'temporary',
variables: { DSH_TEMPORARY: { description: 'Temporary fact.' } },
resolve: () => ({ DSH_TEMPORARY: 'present' }),
})
},
})
expect(registry.collect(execution()).DSH_TEMPORARY).toBe('present')
await fiber.dispose()
expect(registry.collect(execution())).not.toHaveProperty('DSH_TEMPORARY')
})
it('returns an explicit contributor disposer', () => {
const registry = new BashEnvRegistry(new Context(), { dshHome: './test-dsh-home' })
const dispose = registry.register({
name: 'explicit-disposal',
variables: { DSH_EXPLICIT_DISPOSAL: { description: 'Explicitly disposed fact.' } },
resolve: () => ({ DSH_EXPLICIT_DISPOSAL: 'present' }),
})
expect(registry.collect(execution()).DSH_EXPLICIT_DISPOSAL).toBe('present')
dispose()
expect(registry.collect(execution())).not.toHaveProperty('DSH_EXPLICIT_DISPOSAL')
})
})
@@ -1,4 +1,4 @@
import { afterEach, describe, expect, it } from 'vitest'
import { afterEach, describe, expect, it, vi } from 'vitest'
import { Context } from 'cordis'
import { existsSync, mkdtempSync, readFileSync, rmSync } from 'node:fs'
import { tmpdir } from 'node:os'
@@ -21,7 +21,7 @@ import { MockAdapter, textResponse, toolCallResponse } from '../../../core/agent
* through the agent loop, exercising the same seams a live model would
* (tool/call + tool/result session events, agent.inject notifications).
*/
async function harness(adapter: MockAdapter, sessionRoot?: string) {
async function harness(adapter: MockAdapter, sessionRoot?: string, dshHome?: string) {
const ctx = new Context()
await ctx.plugin(LlmService)
await ctx.plugin(SessionStore)
@@ -31,13 +31,16 @@ async function harness(adapter: MockAdapter, sessionRoot?: string) {
await ctx.plugin(AgentRegistry)
await ctx.plugin(AgentLoop, { agents: [] })
await ctx.plugin(LocalBashExecutor, { timeoutMs: 10_000 })
await ctx.plugin(ToolBash)
await ctx.plugin(ToolBash, dshHome === undefined ? {} : { dshHome })
ctx.llm.registerAdapter(['mock'], adapter)
return ctx
}
const dirs: string[] = []
afterEach(() => { for (const dir of dirs.splice(0)) rmSync(dir, { recursive: true, force: true }) })
afterEach(() => {
vi.unstubAllEnvs()
for (const dir of dirs.splice(0)) rmSync(dir, { recursive: true, force: true })
})
function waitForIdle(ctx: Context, agent: ReactLoopAgent): Promise<void> {
return new Promise((resolve) => {
@@ -79,14 +82,16 @@ describe('bash tool through the agent loop', () => {
it('first-turn bash receives session identity before the lazy JSONL file materializes', async () => {
const root = mkdtempSync(join(tmpdir(), 'dsh-bash-session-env-'))
dirs.push(root)
const dshHome = join(root, 'dsh-home')
vi.stubEnv('DSH_STALE_PARENT', 'stale')
const adapter = new MockAdapter([
toolCallResponse('call-1', 'bash', {
command: 'printf \'%s\\n%s\\n\' "$DSH_SESSION_ID" "$DSH_SESSION_JSONL"; if [ -e "$DSH_SESSION_JSONL" ]; then printf \'present\\n\'; else printf \'absent\\n\'; fi',
command: 'printf \'%s\\n%s\\n%s\\n%s\\n%s\\n\' "$DSH_HOME" "$DSH_SHELL" "$DSH_SESSION_ID" "$DSH_SESSION_JSONL" "${DSH_STALE_PARENT-unset}"; if [ -e "$DSH_SESSION_JSONL" ]; then printf \'present\\n\'; else printf \'absent\\n\'; fi',
description: 'inspect session environment',
}),
textResponse('Session environment inspected.'),
])
const ctx = await harness(adapter, root)
const ctx = await harness(adapter, root, dshHome)
const handle = ctx.agents.create({
agentId: AgentId('session-env'),
sessionId: SessionId('session-env-id'),
@@ -100,7 +105,7 @@ describe('bash tool through the agent loop', () => {
await waitForIdle(ctx, agent)
const result = findEvent(events(agent), 'tool/result')
expect(resultText(result)).toBe(`session-env-id\n${location?.path}\nabsent\n`)
expect(resultText(result)).toBe(`${dshHome}\n1\nsession-env-id\n${location?.path}\nunset\nabsent\n`)
expect(existsSync(location!.path)).toBe(true)
const header = JSON.parse(readFileSync(location!.path, 'utf8').split('\n')[0]!) as { type: string; id: string }
expect(header).toMatchObject({ type: 'session', id: 'session-env-id' })
+27 -11
View File
@@ -892,6 +892,8 @@ describe('tool-owned UI presentation (presentCall / presentResult)', () => {
})
describe('the model-facing bash tool builds its request from named args only (no {...args} forward)', () => {
const recordingDshHome = join(spillDir, 'dsh-home')
/**
* Records every {@link BashExecRequest} the consumer hands to `resolve()`, so a
* test can assert what the model-facing tool DID and DID NOT forward. The `bash`
@@ -899,7 +901,7 @@ describe('the model-facing bash tool builds its request from named args only (no
* model that power), so it must build its request from named args only and
* never spread unknown tool-call keys into it. This guard's job is to catch a
* future refactor that blindly forwards `...args` — which would silently thread
* model input into the post-scrub `env` merge — NOT to defend a trust boundary
* model input into the ordinary `env` channel — NOT to defend a trust boundary
* (the credential scrub in dsh-bash-local is the security control; see the
* bash-stdin-env RFC). Foreground `run()` returns a canned result; `start()` is
* unused here.
@@ -915,6 +917,7 @@ describe('the model-facing bash tool builds its request from named args only (no
...request.signal ? { signal: request.signal } : {},
...request.stdin !== undefined ? { stdin: request.stdin } : {},
...request.env !== undefined ? { env: request.env } : {},
...request.dshEnv !== undefined ? { dshEnv: request.dshEnv } : {},
owner: request.owner,
sandboxMode: request.sandboxMode,
}
@@ -943,15 +946,15 @@ describe('the model-facing bash tool builds its request from named args only (no
await ctx.plugin(SessionPersistenceJsonl, { root: join(spillDir, 'jsonl') })
}
await ctx.plugin(RecordingBashExecutor)
await ctx.plugin(ToolBash)
await ctx.plugin(ToolBash, { dshHome: recordingDshHome })
return { ctx, bash: ctx.bash as RecordingBashExecutor }
}
it('describes the trusted session variables to the model', async () => {
it('describes the managed harness environment namespace to the model', async () => {
const { ctx } = await setupRecording()
const description = ctx.tools.get('bash')?.description ?? ''
expect(description).toContain('DSH_SESSION_ID')
expect(description).toContain('DSH_SESSION_JSONL')
expect(description).toContain('$DSH_*')
expect(description).not.toContain('DSH_SESSION_JSONL')
})
it('injects the session id and JSONL target path into a foreground request', async () => {
@@ -966,9 +969,11 @@ describe('the model-facing bash tool builds its request from named args only (no
agent,
})
expect(bash.requests[0]?.env).toEqual({
expect(bash.requests[0]?.dshEnv).toEqual({
DSH_HOME: recordingDshHome,
DSH_SESSION_ID: 'request-fg',
DSH_SESSION_JSONL: path,
DSH_SHELL: '1',
})
})
@@ -989,13 +994,16 @@ describe('the model-facing bash tool builds its request from named args only (no
agent,
})
expect(bash.requests[0]?.env).toEqual({
expect(bash.requests[0]?.env).toBeUndefined()
expect(bash.requests[0]?.dshEnv).toEqual({
DSH_HOME: recordingDshHome,
DSH_SESSION_ID: 'request-bg',
DSH_SESSION_JSONL: path,
DSH_SHELL: '1',
})
})
it('injects only the stable session id when no JSONL locator is available', async () => {
it('injects built-ins and the stable session id when no JSONL locator is available', async () => {
const { ctx, bash } = await setupRecording()
const agent = registerFakeAgent(ctx, 'request-id-only', () => undefined)
const ambient = process.env.DSH_SESSION_ID
@@ -1007,7 +1015,11 @@ describe('the model-facing bash tool builds its request from named args only (no
agent,
})
expect(bash.requests[0]?.env).toEqual({ DSH_SESSION_ID: 'request-id-only' })
expect(bash.requests[0]?.dshEnv).toEqual({
DSH_HOME: recordingDshHome,
DSH_SESSION_ID: 'request-id-only',
DSH_SHELL: '1',
})
expect(process.env.DSH_SESSION_ID).toBe(ambient)
})
@@ -1025,17 +1037,21 @@ describe('the model-facing bash tool builds its request from named args only (no
})
}
expect(bash.requests.map(request => request.env)).toEqual([
expect(bash.requests.map(request => request.dshEnv)).toEqual([
{
DSH_HOME: recordingDshHome,
DSH_SESSION_ID: 'request-parent',
DSH_SESSION_JSONL: ctx.sessionPersistence.locate(parent.session.header)?.path,
DSH_SHELL: '1',
},
{
DSH_HOME: recordingDshHome,
DSH_SESSION_ID: 'request-child',
DSH_SESSION_JSONL: ctx.sessionPersistence.locate(child.session.header)?.path,
DSH_SHELL: '1',
},
])
expect(bash.requests[0]?.env?.DSH_SESSION_JSONL).not.toBe(bash.requests[1]?.env?.DSH_SESSION_JSONL)
expect(bash.requests[0]?.dshEnv?.DSH_SESSION_JSONL).not.toBe(bash.requests[1]?.dshEnv?.DSH_SESSION_JSONL)
})
it('does not forward env/stdin even when the model includes them as extra arguments', async () => {