deepseek-harness/packages/test-support/tool-testkit/README.md

description, kind

description	kind
Define test tools and invoke tool pipelines or selected executors in repository tests and benchmarks.	package-library

@deepseek-ai/dsh-tool-testkit

English | 中文

Summary

Use this package to define content-producing test tools and exercise tool execution without running an Agent turn. Tests and benchmarks import its helpers as a development dependency. Callers own the Cordis context, plugin composition, and teardown.

Table of Contents

• Use this package
• Understand the implementation
• Further Exploration
• Model Experience
• Known Limitations and Deferred Work
• Dev Note

---

Use this package

Add @deepseek-ai/dsh-tool-testkit to the consuming package's devDependencies. Define a fixture when the test needs rendered content without a domain-specific result value:

import { defineContentToolFixture } from '@deepseek-ai/dsh-tool-testkit'

const tool = defineContentToolFixture({
  name: 'echo',
  description: 'Return a test message.',
  parameters: {},
  execute: async () => [{ type: 'text', text: 'hello' }],
})

Register the returned definition through the caller's tool registry. Use executeToolFixture for an already-parsed invocation, or executeModelToolFixture to pass one JSON-encoded call through the selected executor. The latter requires the caller to mount that executor and rejects arguments that cannot be JSON-encoded or an executor response without a result. See src/index.ts for invocation fields.

---

Understand the implementation

Implementation internals — click to expand

src/index.ts adapts content blocks into a tool's canonical JSON value and delegates execution to the production pipeline or registry. It creates no context and owns no plugin registrations.

---

Further Exploration

• Tools package — tool definitions, registry, and execution policy.
• Testing policy — choosing verification for production behavior.
• Test-support group map — sibling test utilities.

---

Model Experience

None, as these test helpers do not assemble or send model requests.

KV Cache effect

None; the package itself sends no provider request.

Known Limitations and Deferred Work

• Content-array values are test fixtures; product tools declare domain-owned output schemas.
• Direct pipeline execution omits model-batch scheduling. Both execution helpers omit root Session logging; use an Agent turn when verifying the recorded conversation.
• Plugin composition and context disposal remain caller-owned.

Dev Note

Working context for maintainers — click to expand

None.