Tianyi Cui
b49c37f83a
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.
DeepSeek Harness Python SDK
English | 中文
Python subprocess SDK for driving DeepSeek Harness over JSON-RPC stdio. The
runtime inherits normal DeepSeek Harness environment variables such as
DEEPSEEK_BASE_URL and DEEPSEEK_API_KEY, so callers can use real model
endpoints directly or point those variables at a local proxy during
benchmark runs.
Installing deepseek-harness installs the exact same-version deepseek-harness-runtime-bin platform wheel. The normal entry point therefore needs no executable argument:
from deepseek_harness import DeepSeekHarness
with DeepSeekHarness() as harness:
result = harness.run("Say hi.")
DeepSeekHarness keeps its lazily started runtime subprocess for reuse across calls. Use it as a context manager, as above, or call close() explicitly when finished.
By default, the SDK launches the bundled single-file dsh-jsonrpc-agent executable from the deepseek-harness-runtime-bin package and injects that package's default configuration (the stdio JSON-RPC server, agent core, preloaded DeepSeek adapter, JSONL session persistence, local bash) via DSH_CORDIS_CONFIG. To run a plugin composition of your own, keep the @deepseek-ai/dsh-jsonrpc entry in the config and pass the Cordis config path.
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 is the text content from the last
assistant/message event in the turn. Use TurnResult.events for the complete
event stream, including intermediate assistant messages and tool activity.
The same behavior can be selected for the runtime subprocess with DSH_CORDIS_CONFIG. The injection lives in HarnessClient.start(), so the low-level client's default launch gets it too: when the launch resolves to the bundled runtime and neither cordis nor a non-empty DSH_CORDIS_CONFIG is set (the runtime treats an empty value as absent, and so does the injection check), the bundled default configuration is used; an explicit runtime_bin or launch_args_override disables the injection entirely. See the sdk-runtime README for the runtime carriers (production exe vs dev-only node closure) and how to obtain them.
cwd and runtime_cwd are resolved to absolute paths before subprocess launch, environment injection, and the wire handshake. The public API exposes only applied options: deployment persona and persistence belong in cordis.yml, while session_root remains the high-level convenience that sets DSH_SESSION_ROOT.