test(tools): close canonical output coverage gaps

This commit is contained in:
Tianyi Cui
2026-07-21 18:22:14 +08:00
parent 80603b22f9
commit 1f4f147699
6 changed files with 50 additions and 8 deletions

View File

@@ -433,6 +433,7 @@ describe('cordis_mount', () => {
['__proto__']: { type: 'string', required: true },
value: { type: 'json', default: { ['__proto__']: { safe: true } } },
},
${CONTENT_OUTPUT_CODE}
async execute() { return [] },
}))
},

View File

@@ -274,6 +274,6 @@ describe('structured tool error propagation (the runtime-validation Agent Note,
const toolResult = agent.session.events.find(e => e.type === 'tool/result')
expect(toolResult?.type === 'tool/result' && toolResult.data.isError).toBe(true)
expect(toolResult?.type === 'tool/result' && toolResult.data.error)
.toEqual({ message: 'exploded', info: { name: 'HarnessError', code: 'BOOM' } })
.toEqual({ name: 'HarnessError', code: 'BOOM' })
})
})

View File

@@ -253,7 +253,7 @@ describe('agent loop', () => {
['BigInt', { n: 1n }],
['Map', new Map([['key', 'value']])],
['class instance', new (class ResultMeta { x = 1 })()],
])('normalizes non-JSON presentation metadata (%s) before the durable result commit', async (_kind, meta) => {
])('rejects non-JSON presentation metadata (%s) before the durable result commit', async (_kind, meta) => {
const adapter = new MockAdapter([
toolCallResponse('bad-meta-call', 'bad-meta', {}, 'calling'),
textResponse('recovered'),
@@ -281,15 +281,16 @@ describe('agent loop', () => {
expect(result.data.callId).toBe('bad-meta-call')
expect(result.data.isError).toBe(true)
expect(result.data.meta).toBeUndefined()
expect(result.data.error).toEqual({ name: 'ToolOutputError', code: 'INVALID_TOOL_OUTPUT' })
expect(result.data.content).toEqual([{
type: 'text',
text: 'Error: tool result must be losslessly JSON-serializable',
text: 'Error: tool "bad-meta" returned invalid output: output.presentationMeta returned non-lossless JSON',
}])
}
// The normalized failure was durably logged and fed back to the model; the
// turn continued normally instead of failing after an apparent success.
expect(adapter.requests).toHaveLength(2)
expect(JSON.stringify(adapter.requests[1]!.messages)).toContain('losslessly JSON-serializable')
expect(JSON.stringify(adapter.requests[1]!.messages)).toContain('output.presentationMeta returned non-lossless JSON')
})
it('omits the system field when a system-prompt/assemble veto empties the assembly', async () => {

View File

@@ -1,6 +1,6 @@
import { describe, expect, expectTypeOf, it } from 'vitest'
import { Context } from 'cordis'
import { CallId, HarnessError } from '@deepseek-ai/dsh-llm'
import { CallId, HarnessError, type ContentBlock } from '@deepseek-ai/dsh-llm'
import SystemPrompt from '@deepseek-ai/dsh-system-prompt'
import type { Agent } from '@deepseek-ai/dsh-agent'
import ApprovalService, { type ApprovalOutcome, type ApprovalRequest } from '@deepseek-ai/dsh-user-approval'
@@ -217,6 +217,35 @@ describe('ToolRegistry', () => {
expect('value' in result).toBe(false)
})
it.each(['render', 'presentationMeta'] as const)('contains a throwing output.%s snapshot as one failed call', async (projector) => {
const ctx = await setup()
const hostile = Object.defineProperty({}, 'value', {
enumerable: true,
get: () => { throw new Error('snapshot getter exploded') },
})
ctx.tools.register(defineTool({
name: `hostile-${projector}`,
description: projector,
parameters: {},
output: {
schema: { type: 'string' },
render: () => projector === 'render'
? hostile as unknown as ContentBlock[]
: [{ type: 'text', text: 'ok' }],
presentationMeta: () => projector === 'presentationMeta'
? hostile as unknown as JsonValue
: null,
},
execute: async () => 'ok',
}))
const result = await ctx.tools.execute({
callId: CallId(`hostile-${projector}`), name: `hostile-${projector}`, arguments: {},
})
expect(result.error?.message).toContain('snapshot getter exploded')
expect(result.error?.info).toEqual({ name: 'ToolOutputError', code: 'INVALID_TOOL_OUTPUT' })
})
it('keeps value/meta through content replacement and recomputes both projections after value replacement', async () => {
const ctx = await setup()
ctx.tools.register(defineTool({

View File

@@ -77,7 +77,6 @@ function lineByteSize(line: string, currentLineCount: number): number {
function consumeLine(acc: WindowAccumulator, rawLine: string, request: ReadWindow): void {
acc.totalLines += 1
if (acc.done) return
if (acc.totalLines < request.offset || acc.lines.length >= request.limit) return
const text = truncateLine(rawLine, request.maxLineLength)

View File

@@ -15,14 +15,26 @@ import type { Config } from '@deepseek-ai/dsh-mcp-client'
const { mockConnect, mockClose, mockListTools, mockCallTool, mockSetNotificationHandler, MockClient } = vi.hoisted(() => {
const mockConnect = vi.fn<() => Promise<void>>()
const mockClose = vi.fn<() => Promise<void>>()
const mockListTools = vi.fn()
const mockCallTool = vi.fn()
const mockListTools = vi.fn<(_params?: Record<string, unknown>) => Promise<unknown>>()
const mockCallTool = vi.fn<(
_params?: Record<string, unknown>, _compatibilitySchema?: unknown, _options?: unknown,
) => Promise<unknown>>()
const mockSetNotificationHandler = vi.fn()
const mockRequest = vi.fn(async (
request: { method: string; params?: Record<string, unknown> },
_schema: unknown,
options?: unknown,
): Promise<unknown> => {
if (request.method === 'tools/list') return await mockListTools(request.params)
if (request.method === 'tools/call') return await mockCallTool(request.params, undefined, options)
throw new Error(`unexpected MCP request: ${request.method}`)
})
class MockClient {
connect = mockConnect
close = mockClose
listTools = mockListTools
callTool = mockCallTool
request = mockRequest
setNotificationHandler = mockSetNotificationHandler
}
return { mockConnect, mockClose, mockListTools, mockCallTool, mockSetNotificationHandler, MockClient }