Files
deepseek-harness/python/sdk/README.zh.md
T
Tianyi Cui b49c37f83a docs(i18n): align single-exe terminology
Add canonical Chinese bindings for build target, deploy root, peer
dependency, serving surface, wheel, wrapper, and VFS so future translations
have one source of truth. Apply the existing runtime, plugin, artifact, and
pipeline bindings throughout every Chinese counterpart touched by this PR.

Require the first Chinese use of peer dependency to retain the English term
so readers can map it back to the package-manager concept without
reintroducing mixed prose throughout the document.

Rewrite mixed-language prose where the English term is not an identifier,
while retaining package names, paths, flags, pkg, single-exe, and other
literal names exactly. Explain VFS on first use and keep technical constraints
readable without inventing compatibility terminology.

Describe single-executable worker support as implemented behavior, including
the filesystem-string entry contract and CommonJS worker artifact required by
the pkg loader, and remove the obsolete bundled-but-unsupported limitation.

Regenerate pairing fingerprints and the generated catalog reference so the
mechanical documentation gates validate the revised English and Chinese
pairs. This keeps the terminology table authoritative and prevents the two
languages from drifting as the runtime documentation evolves.
2026-07-13 22:09:41 +08:00

2.5 KiB

DeepSeek Harness Python SDK

English | 中文

通过 JSON-RPC stdio 驱动 DeepSeek Harness 的 Python 子进程 SDK。运行时继承常规的 DeepSeek Harness 环境变量(如 DEEPSEEK_BASE_URLDEEPSEEK_API_KEY),调用方可以直接用真实模型端点,也可以在跑基准测试时把它们指向本地代理。

安装 deepseek-harness 会同时安装版本完全相同的 deepseek-harness-runtime-bin 平台 wheel 包。因此常规入口不需要传可执行文件参数:

from deepseek_harness import DeepSeekHarness

with DeepSeekHarness() as harness:
    result = harness.run("Say hi.")

DeepSeekHarness 会保留延迟启动的运行时子进程,以供多次调用复用。请像上例一样将其用作上下文管理器,或在用完后显式调用 close()

默认情况下,SDK 启动 deepseek-harness-runtime-bin 包内置的单文件 dsh-jsonrpc-agent 可执行程序,并通过 DSH_CORDIS_CONFIG 注入该包的默认配置(stdio JSON-RPC 服务器、agent-core、预载的 DeepSeek 适配器、JSONL 会话持久化、本地 bash)。要运行自己的插件组合,请在配置里保留 @deepseek-ai/dsh-jsonrpc 条目,并传入 Cordis 配置路径。

from deepseek_harness import DeepSeekHarness

with DeepSeekHarness(
    model="deepseek-v4-flash",
    cordis="examples/dsbench-coding-agent/cordis.yml",
) as harness:
    result = harness.run("Make the requested code change.")

TurnResult.final_response 是本轮次最后一个 assistant/message 事件的文本内容。完整的事件流(包括中间的助手消息与工具活动)用 TurnResult.events 获取。

同样的行为也可以通过 DSH_CORDIS_CONFIG 为运行时子进程选定。注入逻辑位于 HarnessClient.start(),因此底层客户端的默认启动也具有此行为:当启动解析到内置运行时,且 cordis 与非空的 DSH_CORDIS_CONFIG 均未设置时(运行时把空值视为缺省,注入检查与之一致),使用内置的默认配置;显式给出 runtime_binlaunch_args_override 则完全禁用注入。运行时载体(生产用 exe 与仅限开发的 node 闭包)及其获取方式见 sdk-runtime README

cwdruntime_cwd 会在启动子进程、注入环境变量和协议握手前解析为绝对路径。公开 API 只暴露真正生效的选项:部署的角色设定与持久化配置归 cordis.yml 管理,而 session_root 继续作为设置 DSH_SESSION_ROOT 的高层便捷选项。