Keep DeepSeekHarness.run() reusable, but make ownership of its lazy runtime process explicit. Document the context-manager/close contract and update every construction example to use a context manager so repeated runs remain valid without encouraging leaked subprocesses. Contain notification predicate failures at the subscription boundary. Remove only the subscriber whose callback raised, deliver that exception through its queue, and continue dispatching to healthy subscribers so arbitrary callback code cannot terminate the shared reader thread or strand later requests. Enforce one in-flight prompt per server session with an atomic activePrompt guard. Route overlap through the existing -32603 handler-error response and clear the guard in finally, preserving parallel prompts across sessions and sequential reuse without changing JSON-RPC request or notification shapes. Use StringDecoder for line framing so a UTF-8 code point split across Buffer chunks is not corrupted. Add a queued-write flush barrier, and make memoized shutdown await it before disposal and exit while retaining exactly-once cleanup when shutdown calls race or flushing fails. Cover callback isolation, same-session exclusion, cross-session concurrency, split multibyte input, delayed writes, racing shutdown, and flush failure with deterministic tests.
196 lines
6.6 KiB
Python
196 lines
6.6 KiB
Python
from __future__ import annotations
|
|
|
|
import uuid
|
|
from dataclasses import dataclass, field
|
|
from pathlib import Path
|
|
from typing import Callable
|
|
|
|
from .client import HarnessClient, HarnessConfig
|
|
from .models import 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.
|
|
"""
|
|
|
|
model: str = "deepseek-v4-flash"
|
|
cwd: str | None = None
|
|
runtime_cwd: str | None = None
|
|
session_root: str | None = None
|
|
cordis: str | None = None
|
|
env: dict[str, str] = field(default_factory=dict)
|
|
runtime_bin: str | None = None
|
|
launch_args_override: tuple[str, ...] | None = None
|
|
request_timeout_seconds: float | None = None
|
|
shutdown_timeout_seconds: float | None = 1.0
|
|
base_url: str | None = None
|
|
api_key: str | None = None
|
|
|
|
|
|
@dataclass(slots=True)
|
|
class TurnResult:
|
|
session_id: str
|
|
status: str
|
|
final_response: str
|
|
events: list[JsonObject]
|
|
notifications: list[Notification]
|
|
session_root: str | None = None
|
|
|
|
|
|
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, **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.session_root is not None:
|
|
env["DSH_SESSION_ROOT"] = self.config.session_root
|
|
if self.config.cordis is not None:
|
|
env["DSH_CORDIS_CONFIG"] = self.config.cordis
|
|
env["DSH_CWD"] = cwd
|
|
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(
|
|
runtime_bin=self.config.runtime_bin,
|
|
launch_args_override=self.config.launch_args_override,
|
|
cwd=runtime_cwd,
|
|
env=env,
|
|
request_timeout_seconds=self.config.request_timeout_seconds,
|
|
shutdown_timeout_seconds=self.config.shutdown_timeout_seconds,
|
|
)
|
|
)
|
|
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,
|
|
model=self.config.model,
|
|
)
|
|
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 run(
|
|
self,
|
|
input: str | list[JsonObject],
|
|
*,
|
|
session_id: str | None = None,
|
|
on_notification: Callable[[Notification], None] | None = None,
|
|
) -> TurnResult:
|
|
return self.start_session(session_id).run(input, on_notification=on_notification)
|
|
|
|
|
|
class Session:
|
|
def __init__(self, harness: DeepSeekHarness, session_id: str) -> None:
|
|
self.harness = harness
|
|
self.id = session_id
|
|
|
|
def run(
|
|
self,
|
|
input: str | list[JsonObject],
|
|
*,
|
|
on_notification: Callable[[Notification], None] | None = None,
|
|
) -> TurnResult:
|
|
content_blocks = normalize_input(input)
|
|
notifications: list[Notification] = []
|
|
events: list[JsonObject] = []
|
|
status = "error"
|
|
finished = False
|
|
|
|
def collect(notification: Notification) -> None:
|
|
nonlocal finished, status
|
|
notifications.append(notification)
|
|
if on_notification is not None:
|
|
on_notification(notification)
|
|
if notification.method == "session.event":
|
|
event = notification.payload.get("event")
|
|
if isinstance(event, dict):
|
|
events.append(event)
|
|
if notification.method == "session.finished" and notification.payload.get("sessionId") == self.id:
|
|
status = str(notification.payload.get("status") or "ok")
|
|
finished = True
|
|
|
|
with self.harness.client.subscribe_session_notifications(self.id) as subscription:
|
|
self.harness.client.session_prompt(
|
|
self.id,
|
|
content_blocks,
|
|
on_notification=collect,
|
|
notification_subscription=subscription,
|
|
)
|
|
|
|
while not finished:
|
|
notification = subscription.next()
|
|
collect(notification)
|
|
|
|
return TurnResult(
|
|
session_id=self.id,
|
|
status=status,
|
|
final_response=final_response(events),
|
|
events=events,
|
|
notifications=notifications,
|
|
session_root=self.harness.config.session_root,
|
|
)
|
|
|
|
|
|
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
|
|
content = data.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 ""
|