Files
deepseek-harness/python/sdk/src/deepseek_harness/api.py
T

355 lines
14 KiB
Python

from __future__ import annotations
import uuid
from dataclasses import dataclass, field
from pathlib import Path
from typing import Callable, Literal, overload
from .client import HarnessClient, HarnessConfig, UserQuestionHandler
from .errors import SdkProtocolError, TransportClosedError
from .models import CommandExecution, JsonObject, Notification
@dataclass(slots=True)
class DeepSeekHarnessConfig:
"""Configuration for launching the local DeepSeek Harness SDK runtime.
The runtime inherits the caller's environment by default, so existing
DEEPSEEK_API_KEY and DEEPSEEK_BASE_URL settings keep working. Use ``env`` to
intentionally override or inject variables for a subprocess.
These values are startup input, not a live Session state mirror; Session
commands do not rewrite this object.
"""
provider: str = "deepseek-official"
model: str = "deepseek-v4-flash"
reasoning_effort: str | None = None
max_tokens: int | None = None
cwd: str | None = None
runtime_cwd: str | None = None
dsh_bin: str | None = None
profile: str = "sdk"
patches: tuple[str, ...] = ()
dsh_home: str | None = None
env: dict[str, str] = field(default_factory=dict)
initialize_timeout_seconds: float = 30.0
request_timeout_seconds: float | None = None
shutdown_timeout_seconds: float | None = 1.0
base_url: str | None = None
api_key: str | None = None
on_user_question: UserQuestionHandler | None = None
approval_requests: bool = False
@dataclass(slots=True)
class RunResult:
session_id: str
final_response: str
finish_reason: str | None
events: list[JsonObject]
notifications: list[Notification]
class _PromptActivity:
"""Collect an ordinary prompt's notifications from its inbox receipt through idle."""
def __init__(self, session_id: str, message_id: str) -> None:
self.session_id = session_id
self.message_id = message_id
self.received = False
self.events: list[JsonObject] = []
self.notifications: list[Notification] = []
def record(self, notification: Notification, on_notification: Callable[[Notification], None] | None = None) -> bool:
if not self.received:
if not _is_inbox_receipt(notification, self.session_id, self.message_id):
return False
self.received = True
self.notifications.append(notification)
if on_notification is not None:
on_notification(notification)
if notification.method == "session.event" and notification.payload.get("sessionId") == self.session_id:
event = notification.payload.get("event")
if isinstance(event, dict):
self.events.append(event)
return True
def result(self) -> RunResult:
return RunResult(
session_id=self.session_id, final_response=final_response(self.events),
finish_reason=finish_reason(self.events), events=self.events, notifications=self.notifications,
)
class DeepSeekHarness:
"""Reusable synchronous SDK for running DeepSeek Harness agent turns.
The runtime subprocess starts lazily and remains owned by this instance
across calls to :meth:`run`. Use the instance as a context manager, or call
:meth:`close` explicitly when finished, so the subprocess is always reaped.
"""
def __init__(
self,
config: DeepSeekHarnessConfig | None = None,
*,
_launch_args: tuple[str, ...] | None = None,
**kwargs: object,
) -> None:
if config is not None and kwargs:
raise TypeError("pass either DeepSeekHarnessConfig or keyword options, not both")
self.config = config or DeepSeekHarnessConfig(**kwargs)
cwd = str(Path(self.config.cwd or Path.cwd()).resolve())
runtime_cwd = str(Path(self.config.runtime_cwd).resolve()) if self.config.runtime_cwd is not None else cwd
self._cwd = cwd
env = dict(self.config.env)
if self.config.base_url is not None:
env["DEEPSEEK_BASE_URL"] = self.config.base_url
if self.config.api_key is not None:
env["DEEPSEEK_API_KEY"] = self.config.api_key
self._client = HarnessClient(
HarnessConfig(
dsh_bin=self.config.dsh_bin,
profile=self.config.profile,
patches=self.config.patches,
dsh_home=self.config.dsh_home,
cwd=runtime_cwd,
env=env,
initialize_timeout_seconds=self.config.initialize_timeout_seconds,
request_timeout_seconds=self.config.request_timeout_seconds,
shutdown_timeout_seconds=self.config.shutdown_timeout_seconds,
on_user_question=self.config.on_user_question,
),
_launch_args=_launch_args,
)
self._initialized = False
def __enter__(self) -> "DeepSeekHarness":
self.start()
return self
def __exit__(self, _exc_type, _exc, _tb) -> None:
self.close()
@property
def client(self) -> HarnessClient:
return self._client
def start(self) -> None:
if self._initialized:
return
self._client.start()
self._client.initialize(
cwd=self._cwd,
provider=self.config.provider,
model=self.config.model,
reasoning_effort=self.config.reasoning_effort,
max_tokens=self.config.max_tokens,
approval_requests=self.config.approval_requests,
)
self._initialized = True
def close(self) -> None:
self._client.close()
self._initialized = False
def start_session(self, session_id: str | None = None) -> "Session":
self.start()
return Session(self, session_id or f"session-{uuid.uuid4().hex}")
def resume_session(self, session_id: str) -> "Session":
"""Restore persisted history from the configured Harness home without sending input.
Missing, unreadable, incompatible, or occupied sessions raise instead of creating a new session.
"""
self.start()
self._client.resume_session(session_id)
return Session(self, session_id)
@overload
def run(
self, input: list[JsonObject], *, session_id: str | None = None,
on_notification: Callable[[Notification], None] | None = None,
) -> RunResult: ...
@overload
def run(
self, input: str | list[JsonObject], *, session_id: str | None = None,
on_notification: Callable[[Notification], None] | None = None,
delivery: Literal["queue", "steer"] = "queue",
) -> RunResult | CommandExecution: ...
def run(
self,
input: str | list[JsonObject],
*,
session_id: str | None = None,
on_notification: Callable[[Notification], None] | None = None,
delivery: Literal["queue", "steer"] = "queue",
) -> RunResult | CommandExecution:
"""Run text or a native command on a fresh or named Session."""
return self.start_session(session_id).run(input, on_notification=on_notification, delivery=delivery)
class Session:
def __init__(self, harness: DeepSeekHarness, session_id: str) -> None:
self.harness = harness
self.id = session_id
def get_working_directory(self) -> str:
"""Read the effective directory, recovering a missing directory to the Session origin."""
self.harness.start()
return self.harness.client.get_working_directory(self.id)
def set_working_directory(self, path: str) -> str:
"""Change the effective directory while existing processes retain their own directories."""
self.harness.start()
return self.harness.client.set_working_directory(self.id, path)
@overload
def run(
self, input: list[JsonObject], *,
on_notification: Callable[[Notification], None] | None = None,
) -> RunResult: ...
@overload
def run(
self, input: str | list[JsonObject], *,
on_notification: Callable[[Notification], None] | None = None,
delivery: Literal["queue", "steer"] = "queue",
) -> RunResult | CommandExecution: ...
def run(
self,
input: str | list[JsonObject],
*,
on_notification: Callable[[Notification], None] | None = None,
delivery: Literal["queue", "steer"] = "queue",
) -> RunResult | CommandExecution:
"""Run text through native input routing, or queue literal content blocks.
Text returns the prompt's receipt-to-idle RunResult or a settled
CommandExecution; command completion does not wait for later model work.
Content blocks stay literal and accept only queue delivery. Notifications
retain wire order. Command callbacks replay Session-tree notifications
from subscription through their own command/done after the response,
including overlapping work. Handler errors remain command results;
routing, transport and observer failures raise without rolling back work.
"""
if delivery not in ("queue", "steer"):
raise ValueError("run delivery must be queue or steer")
if not isinstance(input, str) and delivery != "queue":
raise ValueError("content-block input requires queue delivery")
self.harness.start()
with self.harness.client.subscribe_session_notifications(self.id) as subscription:
if isinstance(input, str):
response = self.harness.client._request_raw(
"session/query", {"sessionId": self.id, "text": input, "delivery": delivery},
)
if not isinstance(response, dict):
raise SdkProtocolError("session/query response must be a JSON object")
if response.get("kind") == "command":
execution = CommandExecution.model_validate(response.get("execution"))
while True:
try:
notification = subscription._next_queued()
except TransportClosedError:
break
if notification is None:
break
if on_notification is not None:
on_notification(notification)
if _is_command_done(notification, self.id, execution.command_id):
break
return execution
if response.get("kind") != "prompt" or not isinstance(response.get("messageId"), str) or not response["messageId"]:
raise SdkProtocolError("session/query requires a prompt messageId or command execution result")
message_id = response["messageId"]
else:
message_id = self.harness.client.session_prompt(
self.id, input, notification_subscription=subscription,
)
activity = _PromptActivity(self.id, message_id)
while True:
notification = subscription.next()
if not activity.record(notification, on_notification):
continue
if (
notification.method == "session.status"
and notification.payload.get("sessionId") == self.id
and notification.payload.get("status") == "idle"
):
break
return activity.result()
def _is_inbox_receipt(notification: Notification, session_id: str, message_id: str) -> bool:
if notification.method != "session.event" or notification.payload.get("sessionId") != session_id:
return False
event = notification.payload.get("event")
if not isinstance(event, dict) or event.get("type") != "agent/inbox/spliced":
return False
data = event.get("data")
inserted = data.get("inserted") if isinstance(data, dict) else None
return isinstance(inserted, list) and any(
isinstance(message, dict) and message.get("id") == message_id for message in inserted
)
def _is_command_done(notification: Notification, session_id: str, command_id: str) -> bool:
if notification.method != "session.event" or notification.payload.get("sessionId") != session_id:
return False
event = notification.payload.get("event")
if not isinstance(event, dict) or event.get("type") != "command/done":
return False
data = event.get("data")
return isinstance(data, dict) and data.get("commandId") == command_id
def normalize_input(input: str | list[JsonObject]) -> list[JsonObject]:
if isinstance(input, str):
return [{"type": "text", "text": input}]
return input
def final_response(events: list[JsonObject]) -> str:
for event in reversed(events):
if event.get("type") != "assistant/message":
continue
data = event.get("data")
if not isinstance(data, dict):
continue
message = data.get("message")
content_owner = message if isinstance(message, dict) else data
content = content_owner.get("content")
if not isinstance(content, list):
continue
parts: list[str] = []
for block in content:
if isinstance(block, dict) and block.get("type") == "text":
parts.append(str(block.get("text") or ""))
return "".join(parts)
return ""
def finish_reason(events: list[JsonObject]) -> str | None:
"""Return the last turn-ending kind.
The input must contain root-session events from one owned run interval.
Raises:
SdkProtocolError: The last ``turn/end`` has no string reason kind.
"""
for event in reversed(events):
if event.get("type") != "turn/end":
continue
data = event.get("data")
reason = data.get("reason") if isinstance(data, dict) else None
kind = reason.get("kind") if isinstance(reason, dict) else None
if not isinstance(kind, str):
raise SdkProtocolError("turn/end event requires a string data.reason.kind")
return kind
return None