Fix path-dependent Code Mode snapshots
This commit is contained in:
@@ -11,6 +11,7 @@
|
||||
* @module @deepseek-ai/dsh-tools/src/code-mode
|
||||
*/
|
||||
|
||||
import { parse } from 'node:path'
|
||||
import { inspect } from 'node:util'
|
||||
import { CallId, HarnessError } from '@deepseek-ai/dsh-llm'
|
||||
import type { ContentBlock } from '@deepseek-ai/dsh-llm'
|
||||
@@ -27,7 +28,10 @@ declare module '@deepseek-ai/dsh-session' {
|
||||
* (`<parent>:code:<n>`), the tool `name` with its JSON-normalized
|
||||
* `arguments` — the exact value dispatched, normalized BEFORE dispatch,
|
||||
* so this append can never fail on payload shape — whether the sub-call
|
||||
* errored, and a bounded `resultSummary` of its model-facing text.
|
||||
* errored, and a bounded `resultSummary` of its model-facing text. Before
|
||||
* bounding, occurrences of a non-root session workspace path are
|
||||
* normalized to `.` so host-specific absolute path lengths cannot change
|
||||
* the summary.
|
||||
* Log-only: `deriveMessages()` ignores it, so sub-calls never re-enter
|
||||
* model context; persistence and UIs get every call. Appended inside the
|
||||
* parent `run_code`'s execution (the bridge drains its queue before
|
||||
@@ -81,9 +85,12 @@ function textOf(content: ContentBlock[]): string {
|
||||
.join('\n')
|
||||
}
|
||||
|
||||
/** Bound a sub-call's model-facing text for the log event's `resultSummary`. */
|
||||
function summarize(text: string): string {
|
||||
return text.length > SUMMARY_MAX_CHARS ? `${text.slice(0, SUMMARY_MAX_CHARS)}…` : text
|
||||
/** Normalize workspace paths, then bound a sub-call's model-facing text for its durable log summary. */
|
||||
function summarize(text: string, cwd: string | undefined): string {
|
||||
const stableText = cwd === undefined || cwd === parse(cwd).root
|
||||
? text
|
||||
: text.replaceAll(cwd, '.')
|
||||
return stableText.length > SUMMARY_MAX_CHARS ? `${stableText.slice(0, SUMMARY_MAX_CHARS)}…` : stableText
|
||||
}
|
||||
|
||||
/**
|
||||
@@ -219,7 +226,7 @@ export function createRunCodeTool(registry: ToolRegistry, requireRuntime: () =>
|
||||
// this record from what it actually received.
|
||||
arguments: normalized.logged,
|
||||
isError: result.isError,
|
||||
resultSummary: summarize(text),
|
||||
resultSummary: summarize(text, exec.agent.session.header.cwd),
|
||||
})
|
||||
return { text, isError: result.isError }
|
||||
})
|
||||
|
||||
@@ -70,10 +70,11 @@ function registerEcho(ctx: Context, name = 'echo'): unknown[] {
|
||||
}
|
||||
|
||||
/** A structural fake of the owning agent: captures session appends. */
|
||||
function fakeAgent(): { agent: Agent; events: { type: string; data: unknown }[] } {
|
||||
function fakeAgent(options: { cwd?: string } = { cwd: '/workspace' }): { agent: Agent; events: { type: string; data: unknown }[] } {
|
||||
const events: { type: string; data: unknown }[] = []
|
||||
const agent = {
|
||||
session: {
|
||||
header: options.cwd === undefined ? {} : { cwd: options.cwd },
|
||||
append: (type: string, data: unknown) => { events.push({ type, data }) },
|
||||
},
|
||||
} as unknown as Agent
|
||||
@@ -547,6 +548,52 @@ describe('the run_code dispatch bridge', () => {
|
||||
expect(dispatch.resultSummary.endsWith('…')).toBe(true)
|
||||
})
|
||||
|
||||
it('normalizes the session workspace root before bounding durable result summaries', async () => {
|
||||
const { ctx, runtime } = await setup({ mode: 'code' })
|
||||
ctx.tools.register(defineTool({
|
||||
name: 'workspace_path',
|
||||
description: 'Return a path beneath the session workspace.',
|
||||
parameters: {},
|
||||
execute(_args, exec) {
|
||||
const cwd = exec.agent?.session.header.cwd ?? ''
|
||||
return Promise.resolve([{ type: 'text' as const, text: `<path>${cwd}/nested/task.txt</path>\n${'x'.repeat(240)}` }])
|
||||
},
|
||||
}))
|
||||
runtime.behavior = async request => ({
|
||||
logs: [],
|
||||
value: await request.bindings[0]!.functions.workspace_path!({}),
|
||||
})
|
||||
|
||||
const short = fakeAgent({ cwd: '/tmp/workspace' })
|
||||
const long = fakeAgent({ cwd: `/tmp/${'long-segment/'.repeat(30)}workspace` })
|
||||
const shortResult = await runCode(ctx, 'program', { agent: short.agent })
|
||||
const longResult = await runCode(ctx, 'program', { agent: long.agent })
|
||||
const shortDispatch = short.events[0]!.data as SessionEventMap['tool/code-dispatch']
|
||||
const longDispatch = long.events[0]!.data as SessionEventMap['tool/code-dispatch']
|
||||
|
||||
expect(shortResult.content).not.toEqual(longResult.content)
|
||||
expect(shortDispatch.resultSummary).toBe(longDispatch.resultSummary)
|
||||
expect(shortDispatch.resultSummary).toHaveLength(201)
|
||||
expect(shortDispatch.resultSummary).toMatch(/^<path>\.\/nested\/task\.txt<\/path>\n.+…$/)
|
||||
})
|
||||
|
||||
it('leaves result summaries unchanged when a session cwd is absent or is the filesystem root', async () => {
|
||||
const { ctx, runtime } = await setup({ mode: 'code' })
|
||||
registerEcho(ctx)
|
||||
runtime.behavior = async request => ({
|
||||
logs: [],
|
||||
value: await request.bindings[0]!.functions.echo!({ value: '/workspace/value' }),
|
||||
})
|
||||
|
||||
const absent = fakeAgent({})
|
||||
const root = fakeAgent({ cwd: '/' })
|
||||
await runCode(ctx, 'program', { agent: absent.agent })
|
||||
await runCode(ctx, 'program', { agent: root.agent })
|
||||
|
||||
expect((absent.events[0]!.data as SessionEventMap['tool/code-dispatch']).resultSummary).toBe('echo:/workspace/value')
|
||||
expect((root.events[0]!.data as SessionEventMap['tool/code-dispatch']).resultSummary).toBe('echo:/workspace/value')
|
||||
})
|
||||
|
||||
it('rejects undefined, JSON-throwing, and JSON-unrepresentable binding arguments BEFORE dispatch', async () => {
|
||||
const { ctx, runtime } = await setup({ mode: 'code' })
|
||||
const calls = registerEcho(ctx)
|
||||
|
||||
Reference in New Issue
Block a user