feat(plugins): add managed runtime SDK and release 2.4.5

artemis/plugins/_process_worker.py

@@ -0,0 +1,57 @@
+"""Private launch barrier for sdk.run_process; stdlib-only under Python -I."""
+
+import json
+import os
+from pathlib import Path
+import signal
+import subprocess
+import sys
+import threading
+import time
+
+
+def watch_parent(expected: int):
+    while True:
+        if os.getppid() != expected:
+            os.killpg(os.getpid(), signal.SIGKILL)
+        time.sleep(0.1)
+
+
+def main():
+    status = Path(sys.argv[1])
+    if os.name != "nt":
+        threading.Thread(target=watch_parent, args=(int(sys.argv[2]),), daemon=True).start()
+    # Until the parent owns our job/session and sends this line, no business
+    # process can start. Buffering is local; tool stdin uses a separate pipe.
+    control = sys.stdin.buffer.readline(1024 * 1024 + 1)
+    if not control.endswith(b"\n") or len(control) > 1024 * 1024:
+        return
+    request = json.loads(control)
+    size = request["input_size"]
+    if type(size) is not int or not 0 <= size <= 64 * 1024 * 1024:
+        return
+    content = sys.stdin.buffer.read(size) if request["has_input"] else None
+    if content is not None and len(content) != size:
+        return
+    try:
+        result = subprocess.run(
+            request["argv"],
+            shell=False,
+            stdin=None if request["has_input"] else subprocess.DEVNULL,
+            input=content,
+            creationflags=subprocess.CREATE_NO_WINDOW if os.name == "nt" else 0,
+            check=False,
+        )
+        response = {"returncode": result.returncode}
+    except OSError:
+        response = {"launch_failed": True}
+    pending = status.with_suffix(".tmp")
+    pending.write_text(json.dumps(response), encoding="utf-8")
+    pending.replace(status)
+    # Remain the session/group leader until the owner reclaims the whole tree.
+    while True:
+        time.sleep(60)
+
+
+if __name__ == "__main__":
+    main()

artemis/plugins/_sdk_probe.py

@@ -0,0 +1,40 @@
+"""Synthetic tool used only by the opt-in SDK fault suite. No device/network I/O."""
+
+import json
+import os
+from pathlib import Path
+import subprocess
+import sys
+import time
+
+
+def main():
+    mode = sys.argv[1]
+    if mode == "sleep":
+        time.sleep(60)
+    elif mode == "tree":
+        child = subprocess.Popen(
+            [sys.executable, "-I", "-B", __file__, "sleep"],
+            stdin=subprocess.DEVNULL,
+            stdout=subprocess.DEVNULL,
+            stderr=subprocess.DEVNULL,
+            creationflags=subprocess.CREATE_NO_WINDOW if os.name == "nt" else 0,
+        )
+        Path(sys.argv[2]).write_text(json.dumps({"pid": child.pid}), encoding="utf-8")
+        if sys.argv[3] == "linger":
+            time.sleep(60)
+    elif mode == "echo":
+        data = sys.stdin.buffer.read()
+        sys.stdout.buffer.write(data)
+        sys.stderr.buffer.write(b"synthetic-stderr")
+    elif mode == "overflow":
+        while True:
+            os.write(1, b"x" * 65536)
+    elif mode == "failure":
+        raise SystemExit(7)
+    else:
+        raise SystemExit(2)
+
+
+if __name__ == "__main__":
+    main()

artemis/plugins/market.py

@@ -0,0 +1,266 @@
+"""Evidence-bound market materials. Declarations still need source/rights review."""
+
+from __future__ import annotations
+
+from collections.abc import Iterator
+from contextlib import contextmanager
+import hashlib
+import json
+from pathlib import Path, PurePosixPath
+import stat
+import tempfile
+from typing import Literal
+
+from pydantic import BaseModel, ConfigDict, Field
+
+from artemis.config.settings import settings
+from artemis.plugins.installer import _extract
+from artemis.plugins.models import PluginManifest
+
+REPORT_NAME = "MARKET.json"
+CHECKS = (
+    "installation",
+    "tool_contract",
+    "failure_partial",
+    "timeout_cancel",
+    "process_tree",
+    "file_binding",
+    "resource_conflicts",
+    "evidence_export",
+    "history_uninstall",
+    "secret_redaction",
+    "real_task",
+    "source_review",
+)
+FORBIDDEN_DIRECTORIES = {".git", ".ruff_cache", ".pytest_cache", "__pycache__", ".venv"}
+
+
+class SubmissionModel(BaseModel):
+    model_config = ConfigDict(extra="forbid", strict=True)
+
+
+class Component(SubmissionModel):
+    name: str = Field(min_length=1)
+    paths: list[str] = Field(min_length=1)
+    license: str = Field(min_length=1)
+    permission: Literal["permitted", "local_only", "unknown"]
+    license_file: str
+    source_file: str
+
+
+class CheckRecord(SubmissionModel):
+    status: Literal["passed", "failed", "unverified", "not_applicable"]
+    evidence_file: str = ""
+    evidence_sha256: str = ""
+    notes: str = ""
+
+
+class Traits(SubmissionModel):
+    uses_subprocesses: bool | None
+    file_inputs_for_writes: bool | None
+
+
+class MarketSubmission(SubmissionModel):
+    schema_version: Literal[1]
+    plugin_id: str
+    plugin_version: str
+    content_sha256: str = Field(pattern=r"^[a-f0-9]{64}$")
+    traits: Traits
+    components: list[Component] = Field(min_length=1)
+    checks: dict[str, CheckRecord]
+
+
+@contextmanager
+def package_directory(path: Path) -> Iterator[tuple[Path, str | None]]:
+    """Inspect a directory or safely unpack a ZIP without installing or hooks."""
+    path = path.resolve(strict=True)
+    if path.is_dir():
+        yield path, None
+        return
+    if not path.is_file():
+        raise ValueError("检查输入必须是普通插件目录或 ZIP 文件")
+    with path.open("rb") as stream:
+        data = stream.read(settings.ARTEMIS_PLUGIN_DOWNLOAD_MAX_BYTES + 1)
+    if len(data) > settings.ARTEMIS_PLUGIN_DOWNLOAD_MAX_BYTES:
+        raise ValueError("插件 ZIP 超过下载大小限制")
+    with tempfile.TemporaryDirectory(prefix="artemis-plugin-check-") as temporary:
+        directory = Path(temporary)
+        _extract(data, directory)
+        archive_sha256 = hashlib.sha256(data).hexdigest()
+        yield directory, archive_sha256
+        # Re-read only to reject changes; never relabel the inspected snapshot.
+        current_digest = hashlib.sha256()
+        current_size = 0
+        with path.open("rb") as stream:
+            while chunk := stream.read(1024 * 1024):
+                current_size += len(chunk)
+                if current_size > settings.ARTEMIS_PLUGIN_DOWNLOAD_MAX_BYTES:
+                    raise ValueError("检查期间 ZIP 发生变化或超过大小限制")
+                current_digest.update(chunk)
+        if current_digest.hexdigest() != archive_sha256:
+            raise ValueError("检查期间 ZIP 发生变化，检查记录失效")
+
+
+def _relative(value: str, *, root_allowed: bool = False) -> str:
+    if root_allowed and value == ".":
+        return value
+    path = PurePosixPath(value)
+    if (
+        not value
+        or "\\" in value
+        or ":" in value
+        or path.is_absolute()
+        or any(p in {".", ".."} for p in value.split("/"))
+        or any(ord(c) < 32 for c in value)
+        or str(path) != value
+    ):
+        raise ValueError("市场材料必须使用包内普通相对路径")
+    return value
+
+
+def package_files(directory: Path) -> dict[str, str]:
+    """Hash every distributable file, excluding only the self-referential report."""
+    directory = directory.resolve(strict=True)
+    files = {}
+    seen = set()
+    size = 0
+    for path in sorted(directory.rglob("*")):
+        relative = path.relative_to(directory)
+        name = relative.as_posix()
+        if path.is_symlink() or path.is_junction() or not path.resolve().is_relative_to(directory):
+            raise ValueError("市场包不能包含链接")
+        if name.casefold() in seen:
+            raise ValueError("市场包存在大小写冲突的路径")
+        seen.add(name.casefold())
+        if len(seen) > 20000:
+            raise ValueError("市场包超过文件数量限制")
+        if any(p.casefold() in FORBIDDEN_DIRECTORIES for p in relative.parts):
+            raise ValueError(f"市场包包含缓存、依赖环境或版本库目录：{name}")
+        if path.is_dir():
+            continue
+        info = path.stat()
+        if not stat.S_ISREG(info.st_mode):
+            raise ValueError("市场包只能包含普通文件")
+        if name == REPORT_NAME:
+            continue
+        lower = path.name.casefold()
+        if (
+            lower.endswith((".pyc", ".pyo"))
+            or lower == ".env"
+            or (
+                lower.startswith(".env.")
+                and not lower.endswith((".example", ".sample", ".template"))
+            )
+        ):
+            raise ValueError(f"市场包不能包含缓存或个人环境配置：{name}")
+        _relative(name)
+        digest = hashlib.sha256()
+        read = 0
+        with path.open("rb") as handle:
+            for chunk in iter(lambda: handle.read(1024 * 1024), b""):
+                read += len(chunk)
+                size += len(chunk)
+                if size > settings.ARTEMIS_PLUGIN_EXTRACT_MAX_BYTES:
+                    raise ValueError("市场包超过展开大小或文件数量限制")
+                digest.update(chunk)
+        if read != info.st_size:
+            raise ValueError("文件校验期间大小发生变化")
+        files[name] = digest.hexdigest()
+    return files
+
+
+def content_fingerprint(files: dict[str, str]) -> str:
+    encoded = json.dumps(files, ensure_ascii=False, sort_keys=True, separators=(",", ":"))
+    return hashlib.sha256(encoded.encode("utf-8")).hexdigest()
+
+
+def draft_submission(manifest: PluginManifest, files: dict[str, str]) -> dict:
+    """Drafts never fabricate passed results or distribution permission."""
+    return {
+        "schema_version": 1,
+        "plugin_id": manifest.id,
+        "plugin_version": manifest.version,
+        "content_sha256": content_fingerprint(files),
+        "traits": {"uses_subprocesses": None, "file_inputs_for_writes": None},
+        "components": [
+            {
+                "name": "请拆分原始代码、适配层与第三方资料",
+                "paths": ["."],
+                "license": manifest.license or "待补充",
+                "permission": "unknown",
+                "license_file": "LICENSE",
+                "source_file": "SOURCE.md",
+            }
+        ],
+        "checks": {
+            name: {"status": "unverified", "evidence_file": "", "evidence_sha256": "", "notes": ""}
+            for name in CHECKS
+        },
+    }
+
+
+def _document(directory: Path, files: dict[str, str], value: str) -> str:
+    name = _relative(value)
+    if name not in files or not 0 < (directory / name).stat().st_size <= 1024 * 1024:
+        raise ValueError("许可、来源与验证记录必须是非空包内文档，且不超过 1 MiB")
+    return name
+
+
+def validate_submission(
+    directory: Path, manifest: PluginManifest, files: dict[str, str]
+) -> MarketSubmission:
+    path = directory / REPORT_NAME
+    if not path.is_file() or path.stat().st_size > 1024 * 1024:
+        raise ValueError("市场检查需要包内 MARKET.json；先生成草稿并补充真实记录")
+    report = MarketSubmission.model_validate_json(path.read_text("utf-8"))
+    if (report.plugin_id, report.plugin_version) != (manifest.id, manifest.version):
+        raise ValueError("市场材料的插件 ID/版本与清单不一致")
+    if report.content_sha256 != content_fingerprint(files):
+        raise ValueError("包内容已变化，旧的市场验证记录失效")
+    if not manifest.license.strip():
+        raise ValueError("市场清单必须声明许可证或具体的 LicenseRef")
+    if None in (report.traits.uses_subprocesses, report.traits.file_inputs_for_writes):
+        raise ValueError("必须明确是否使用子进程、是否将文件用于写操作")
+    covered = set()
+    for component in report.components:
+        if component.permission != "permitted" or component.license.strip().casefold() in {
+            "",
+            "unknown",
+            "todo",
+            "待补充",
+        }:
+            raise ValueError(f"组件未明确允许市场分发或未提供许可证：{component.name}")
+        _document(directory, files, component.license_file)
+        _document(directory, files, component.source_file)
+        for scope in component.paths:
+            scope = _relative(scope, root_allowed=True)
+            selected = {
+                name
+                for name in files
+                if scope == "." or name == scope or name.startswith(scope + "/")
+            }
+            if not selected:
+                raise ValueError("来源组件声明了不存在的文件范围")
+            covered.update(selected)
+    if set(files) - covered:
+        raise ValueError("市场包有文件未记录来源与分发许可")
+    if set(report.checks) != set(CHECKS):
+        raise ValueError("市场验证项目缺失或包含未知项目")
+    optional = {
+        "tool_contract": manifest.server is None,
+        "timeout_cancel": manifest.server is None,
+        "process_tree": not report.traits.uses_subprocesses,
+        "file_binding": not report.traits.file_inputs_for_writes,
+        "resource_conflicts": not manifest.resources,
+    }
+    for name, record in report.checks.items():
+        if not record.notes.strip():
+            raise ValueError(f"验证项目必须说明实际范围或不适用原因：{name}")
+        if record.status == "not_applicable" and optional.get(name, False):
+            continue
+        if record.status != "passed":
+            raise ValueError(f"市场验证项目未通过：{name}")
+        evidence = _document(directory, files, record.evidence_file)
+        if files[evidence] != record.evidence_sha256:
+            raise ValueError(f"验证记录 SHA256 不一致：{name}")
+    return report

artemis/plugins/recording_process.py

@@ -4,8 +4,8 @@ import ctypes
 from ctypes import wintypes
 
 
-class CaptureProcessJob:
-    """A non-inheritable job handle: Windows kills captures when its owner exits."""
+class ProcessJob:
+    """A non-inheritable job handle that owns a Windows process tree."""
 
     def __init__(self):
         class BasicLimits(ctypes.Structure):
@@ -54,6 +54,12 @@ class CaptureProcessJob:
             ),
             ("OpenProcess", [wintypes.DWORD, wintypes.BOOL, wintypes.DWORD], wintypes.HANDLE),
             ("AssignProcessToJobObject", [wintypes.HANDLE, wintypes.HANDLE], wintypes.BOOL),
+            ("TerminateJobObject", [wintypes.HANDLE, wintypes.UINT], wintypes.BOOL),
+            (
+                "QueryInformationJobObject",
+                [wintypes.HANDLE, ctypes.c_int, wintypes.LPVOID, wintypes.DWORD, wintypes.LPVOID],
+                wintypes.BOOL,
+            ),
             ("CloseHandle", [wintypes.HANDLE], wintypes.BOOL),
         ):
             function = getattr(self._api, name)
@@ -84,3 +90,34 @@ class CaptureProcessJob:
         if self._handle:
             self._api.CloseHandle(self._handle)
             self._handle = None
+
+    def terminate(self):
+        if self._handle and not self._api.TerminateJobObject(self._handle, 1):
+            raise ctypes.WinError(ctypes.get_last_error())
+
+    def active_processes(self) -> int:
+        if not self._handle:
+            return 0
+
+        class Accounting(ctypes.Structure):
+            _fields_ = [
+                ("user_time", ctypes.c_int64),
+                ("kernel_time", ctypes.c_int64),
+                ("period_user_time", ctypes.c_int64),
+                ("period_kernel_time", ctypes.c_int64),
+                ("page_faults", wintypes.DWORD),
+                ("total", wintypes.DWORD),
+                ("active", wintypes.DWORD),
+                ("terminated", wintypes.DWORD),
+            ]
+
+        accounting = Accounting()
+        if not self._api.QueryInformationJobObject(
+            self._handle, 1, ctypes.byref(accounting), ctypes.sizeof(accounting), None
+        ):
+            raise ctypes.WinError(ctypes.get_last_error())
+        return accounting.active
+
+
+# Keep the recording implementation and its callers on the same ownership primitive.
+CaptureProcessJob = ProcessJob

artemis/plugins/sdk.py

@@ -0,0 +1,347 @@
+"""Plugin author helpers; no scheduler, device actions or implicit retries.
+
+Use snapshot_file before approving a write and consume its immutable bytes, not the
+original pathname. run_process owns the tool and its descendants on every exit.
+"""
+
+from __future__ import annotations
+
+import asyncio
+from collections.abc import Iterator, Mapping, Sequence
+from dataclasses import dataclass, field
+import hashlib
+import json
+import math
+import os
+from pathlib import Path
+import re
+import signal
+import stat
+import subprocess
+import sys
+import tempfile
+
+from artemis.plugins.recording_process import ProcessJob
+
+MAX_INPUT_BYTES = 64 * 1024 * 1024
+DEFAULT_OUTPUT_BYTES = 4 * 1024 * 1024
+
+
+class FileVerificationError(ValueError):
+    """The input cannot be bound to its explicitly approved digest."""
+
+
+@dataclass(frozen=True)
+class VerifiedFile:
+    """Bounded, immutable input. No original path is exposed for reopening."""
+
+    data: bytes = field(repr=False)
+    sha256: str = field(init=False)
+
+    def __post_init__(self):
+        if not isinstance(self.data, bytes):
+            raise TypeError("快照内容必须是不可变 bytes")
+        object.__setattr__(self, "sha256", hashlib.sha256(self.data).hexdigest())
+
+    @property
+    def size(self) -> int:
+        return len(self.data)
+
+    def chunks(self, size: int = 256 * 1024) -> Iterator[memoryview]:
+        if type(size) is not int or size <= 0:
+            raise ValueError("分块大小必须是正整数")
+        content = memoryview(self.data)
+        for offset in range(0, len(content), size):
+            yield content[offset : offset + size]
+
+
+def snapshot_file(
+    path: Path | str, expected_sha256: str, *, max_bytes: int = MAX_INPUT_BYTES
+) -> VerifiedFile:
+    """Copy once, then verify the exact bytes that will be consumed by the caller.
+
+    The source must already be authorized by the plugin. This is not a path or
+    permission sandbox. Memory use is bounded by max_bytes plus one read byte.
+    """
+    if type(max_bytes) is not int or max_bytes <= 0:
+        raise ValueError("文件大小上限必须是正整数")
+    if not isinstance(expected_sha256, str) or not re.fullmatch(
+        r"[a-fA-F0-9]{64}", expected_sha256
+    ):
+        raise FileVerificationError("必须明确提供已批准的 SHA256")
+    source = Path(path)
+    if source.is_symlink() or not stat.S_ISREG(source.lstat().st_mode):
+        raise FileVerificationError("输入必须是普通文件，不能是链接或设备")
+    flags = os.O_RDONLY | getattr(os, "O_NOFOLLOW", 0) | getattr(os, "O_NONBLOCK", 0)
+    descriptor = os.open(source, flags)
+    with os.fdopen(descriptor, "rb") as handle:
+        info = os.fstat(handle.fileno())
+        if not stat.S_ISREG(info.st_mode) or info.st_size > max_bytes:
+            raise FileVerificationError("输入不是普通文件或超过大小上限")
+        data = handle.read(max_bytes + 1)
+    if len(data) > max_bytes:
+        raise FileVerificationError("输入超过大小上限")
+    snapshot = VerifiedFile(data)
+    if snapshot.sha256 != expected_sha256.lower():
+        raise FileVerificationError("输入 SHA256 与批准值不一致；不得开始写操作")
+    return snapshot
+
+
+class ManagedProcessError(RuntimeError):
+    """Stable failure metadata. Do not infer a business verdict or retry a write."""
+
+    def __init__(self, code: str, *, may_have_started: bool = True):
+        super().__init__(code)
+        self.error_code = code
+        self.may_have_started = may_have_started
+
+
+class ProcessTimedOut(ManagedProcessError, TimeoutError):
+    pass
+
+
+@dataclass(frozen=True)
+class ProcessResult:
+    returncode: int
+    stdout: bytes = field(repr=False)
+    stderr: bytes = field(repr=False)
+
+
+async def _cleanup(process: asyncio.subprocess.Process, job: ProcessJob | None) -> None:
+    error = None
+    try:
+        if job is not None:
+            job.terminate()
+            async with asyncio.timeout(5):
+                while job.active_processes():
+                    await asyncio.sleep(0.02)
+        elif os.name != "nt":
+            # The bootstrap stays alive until cleanup, pinning the owned PGID.
+            try:
+                os.killpg(process.pid, signal.SIGKILL)
+            except ProcessLookupError:
+                pass
+    except (OSError, TimeoutError) as exc:
+        error = exc
+    finally:
+        if job is not None:
+            job.close()
+        if process.returncode is None:
+            try:
+                process.kill()
+            except ProcessLookupError:
+                pass
+    # Process.wait also waits for pipe EOF. A paused, full output reader must be
+    # drained separately; it cannot serve as evidence that the OS process lives.
+    try:
+        async with asyncio.timeout(5):
+            while process.returncode is None:
+                await asyncio.sleep(0.02)
+    except TimeoutError as exc:
+        error = exc
+    if error is not None:
+        raise ManagedProcessError("process_cleanup_unconfirmed") from error
+
+
+async def _finish_cleanup(task: asyncio.Task[None]) -> None:
+    cancelled = False
+    while not task.done():
+        try:
+            await asyncio.shield(task)
+        except asyncio.CancelledError:
+            cancelled = True
+    task.result()
+    if cancelled:
+        raise asyncio.CancelledError
+
+
+async def _read_output(stream: asyncio.StreamReader, consumed: list[int], limit: int) -> bytes:
+    chunks = []
+    while chunk := await stream.read(65536):
+        consumed[0] += len(chunk)
+        if consumed[0] > limit:
+            raise ManagedProcessError("process_output_limit")
+        chunks.append(chunk)
+    return b"".join(chunks)
+
+
+async def _drain(stream: asyncio.StreamReader | None) -> None:
+    if stream is not None:
+        while await stream.read(65536):
+            pass
+
+
+async def _wait_result(process: asyncio.subprocess.Process, path: Path) -> int:
+    while not path.exists():
+        if process.returncode is not None:
+            raise ManagedProcessError("process_worker_interrupted")
+        await asyncio.sleep(0.02)
+    if path.stat().st_size > 4096:
+        raise ManagedProcessError("process_invalid_status")
+    try:
+        result = json.loads(path.read_text("utf-8"))
+        if not isinstance(result, dict):
+            raise ValueError
+    except (OSError, ValueError) as exc:
+        raise ManagedProcessError("process_invalid_status") from exc
+    if result.get("launch_failed") is True:
+        raise ManagedProcessError("process_launch_failed", may_have_started=False)
+    if type(result.get("returncode")) is not int:
+        raise ManagedProcessError("process_invalid_status")
+    return result["returncode"]
+
+
+async def run_process(
+    argv: Sequence[str],
+    *,
+    cwd: Path | str,
+    timeout: float,
+    env: Mapping[str, str] | None = None,
+    input_data: bytes | None = None,
+    max_output_bytes: int = DEFAULT_OUTPUT_BYTES,
+) -> ProcessResult:
+    """Run one fixed argv without a shell; reclaim descendants even on normal exit.
+
+    Windows assigns a waiting bootstrap to a Job Object *before* it can start the
+    tool. POSIX uses a dedicated session. Cancellation completes cleanup before
+    propagating. Inputs are at most 64 MiB; stdout+stderr share a bounded budget.
+    Return codes/output are tool results, never a test verdict. No retries occur.
+    """
+    if (
+        not isinstance(argv, Sequence)
+        or isinstance(argv, (str, bytes))
+        or not argv
+        or any(not isinstance(arg, str) or "\0" in arg for arg in argv)
+    ):
+        raise ValueError("必须提供固定的 argv 字符串列表，不能使用 shell 命令文本")
+    if not argv[0] or isinstance(timeout, bool) or not math.isfinite(timeout) or timeout <= 0:
+        raise ValueError("启动程序和有限正数超时是必填项")
+    if type(max_output_bytes) is not int or max_output_bytes <= 0:
+        raise ValueError("输出上限必须是正整数")
+    if input_data is not None and (
+        not isinstance(input_data, bytes) or len(input_data) > MAX_INPUT_BYTES
+    ):
+        raise ValueError("标准输入必须是至多 64 MiB 的 bytes")
+    directory = Path(cwd).resolve(strict=True)
+    if not directory.is_dir():
+        raise ValueError("工作目录必须是已存在的目录")
+    control = (
+        json.dumps(
+            {
+                "argv": list(argv),
+                "has_input": input_data is not None,
+                "input_size": len(input_data or b""),
+            }
+        ).encode()
+        + b"\n"
+    )
+    if len(control) > 1024 * 1024:
+        raise ValueError("启动参数超过大小上限")
+    job = None
+    process: asyncio.subprocess.Process | None = None
+    cleanup: asyncio.Task[None] | None = None
+    tasks: list[asyncio.Task] = []
+
+    async def reclaim():
+        nonlocal cleanup
+        if process is None:
+            if job is not None:
+                job.close()
+            return
+        if cleanup is None:
+            cleanup = asyncio.create_task(_cleanup(process, job))
+        await _finish_cleanup(cleanup)
+
+    with tempfile.TemporaryDirectory(prefix="artemis-plugin-process-") as temporary:
+        status = Path(temporary) / "status.json"
+        try:
+            job = ProcessJob() if os.name == "nt" else None
+        except OSError as exc:
+            raise ManagedProcessError("process_ownership_failed", may_have_started=False) from exc
+        launch = asyncio.create_task(
+            asyncio.create_subprocess_exec(
+                sys.executable,
+                "-I",
+                "-B",
+                str(Path(__file__).with_name("_process_worker.py")),
+                str(status),
+                str(os.getpid()),
+                cwd=str(directory),
+                env=dict(env) if env is not None else None,
+                stdin=asyncio.subprocess.PIPE,
+                stdout=asyncio.subprocess.PIPE,
+                stderr=asyncio.subprocess.PIPE,
+                creationflags=subprocess.CREATE_NO_WINDOW if os.name == "nt" else 0,
+                start_new_session=os.name != "nt",
+            )
+        )
+        try:
+            cancelled = False
+            while process is None:
+                try:
+                    process = await asyncio.shield(launch)
+                except asyncio.CancelledError:
+                    cancelled = True
+                except OSError as exc:
+                    raise ManagedProcessError(
+                        "process_launch_failed", may_have_started=False
+                    ) from exc
+            if cancelled:
+                raise asyncio.CancelledError
+            if job is not None:
+                try:
+                    job.assign(process.pid)
+                except OSError as exc:
+                    raise ManagedProcessError(
+                        "process_ownership_failed", may_have_started=False
+                    ) from exc
+            stdin, stdout, stderr = process.stdin, process.stdout, process.stderr
+            assert stdin is not None and stdout is not None and stderr is not None
+            consumed = [0]
+
+            async def feed():
+                try:
+                    stdin.write(control)
+                    await stdin.drain()
+                    if input_data:
+                        stdin.write(input_data)
+                        await stdin.drain()
+                except (BrokenPipeError, ConnectionResetError):
+                    pass
+                finally:
+                    stdin.close()
+
+            async def wait_tool():
+                code = await _wait_result(process, status)
+                await reclaim()
+                return code
+
+            tasks = [
+                asyncio.create_task(feed()),
+                asyncio.create_task(_read_output(stdout, consumed, max_output_bytes)),
+                asyncio.create_task(_read_output(stderr, consumed, max_output_bytes)),
+                asyncio.create_task(wait_tool()),
+            ]
+            try:
+                _, stdout, stderr, code = await asyncio.wait_for(asyncio.gather(*tasks), timeout)
+            except TimeoutError as exc:
+                raise ProcessTimedOut("process_timeout") from exc
+            return ProcessResult(code, stdout, stderr)
+        finally:
+            for task in tasks:
+                task.cancel()
+
+            async def finalize():
+                try:
+                    await reclaim()
+                finally:
+                    await asyncio.gather(*tasks, return_exceptions=True)
+                    if process is not None:
+                        try:
+                            async with asyncio.timeout(5):
+                                await asyncio.gather(_drain(process.stdout), _drain(process.stderr))
+                                await process.wait()
+                        except TimeoutError as exc:
+                            raise ManagedProcessError("process_cleanup_unconfirmed") from exc
+
+            await _finish_cleanup(asyncio.create_task(finalize()))

artemis/plugins/sdk_checks.py

@@ -0,0 +1,212 @@
+"""Run opt-in, offline SDK fault regressions in temporary directories only."""
+
+import argparse
+import asyncio
+from contextlib import suppress
+import hashlib
+import json
+from pathlib import Path
+import sys
+import tempfile
+import time
+
+import psutil
+
+from artemis.plugins.evidence import decode_receipt, persist_attachments
+from artemis.plugins.models import PluginCallResult
+from artemis.plugins.sdk import (
+    FileVerificationError,
+    ManagedProcessError,
+    ProcessTimedOut,
+    run_process,
+    snapshot_file,
+)
+
+PROBE = Path(__file__).with_name("_sdk_probe.py").resolve()
+
+
+def _require(condition, message):
+    if not condition:
+        raise AssertionError(message)
+
+
+def _owned_process(marker: Path, started: float):
+    if not marker.exists():
+        return None
+    pid = json.loads(marker.read_text("utf-8"))["pid"]
+    try:
+        process = psutil.Process(pid)
+        if process.status() == psutil.STATUS_ZOMBIE:
+            return None
+        _require(process.create_time() >= started - 1, "测试 PID 的启动时间不匹配")
+        _require(str(PROBE) in process.cmdline(), "测试 PID 的脚本身份不匹配")
+        return process
+    except psutil.NoSuchProcess:
+        return None
+
+
+async def _tree_case(root: Path, mode: str):
+    marker = root / f"{mode}.json"
+    started = time.time()
+    task = asyncio.create_task(
+        run_process(
+            [
+                sys.executable,
+                "-I",
+                "-B",
+                str(PROBE),
+                "tree",
+                str(marker),
+                "exit" if mode == "normal" else "linger",
+            ],
+            cwd=root,
+            timeout=2 if mode == "timeout" else 10,
+        )
+    )
+    try:
+        if mode == "cancel":
+            async with asyncio.timeout(5):
+                while not marker.exists() and not task.done():
+                    await asyncio.sleep(0.02)
+            _require(marker.exists(), "取消探针没有启动")
+            task.cancel()
+            try:
+                await task
+            except asyncio.CancelledError:
+                pass
+            else:
+                raise AssertionError("取消没有传播")
+        elif mode == "timeout":
+            try:
+                await task
+            except ProcessTimedOut:
+                pass
+            else:
+                raise AssertionError("超时没有生效")
+        else:
+            result = await task
+            _require(result.returncode == 0, "模拟工具异常退出")
+        _require(marker.exists(), "后代进程探针没有启动")
+        async with asyncio.timeout(3):
+            while _owned_process(marker, started) is not None:
+                await asyncio.sleep(0.02)
+    finally:
+        if not task.done():
+            task.cancel()
+        with suppress(asyncio.CancelledError, ManagedProcessError):
+            await task
+        # Failing implementations must not leave the fault suite's own sleeper alive.
+        process = _owned_process(marker, started)
+        if process is not None:
+            process.kill()
+            process.wait(timeout=5)
+
+
+async def run_checks() -> dict:
+    checks = []
+    with tempfile.TemporaryDirectory(prefix="artemis-sdk-faults-") as temporary:
+        root = Path(temporary)
+        source = root / "synthetic.rom"
+        approved = b"approved firmware bytes\x00\xff"
+        source.write_bytes(approved)
+        digest = hashlib.sha256(approved).hexdigest()
+        snapshot = snapshot_file(source, digest)
+        for replacement in (b"X" * len(approved), b"", b"Y" * (len(approved) + 10)):
+            source.write_bytes(replacement)
+            _require(b"".join(snapshot.chunks(3)) == approved, "快照受原文件修改影响")
+            try:
+                snapshot_file(source, digest)
+            except FileVerificationError:
+                pass
+            else:
+                raise AssertionError("摘要不符仍被接收")
+        _require(all(part.readonly for part in snapshot.chunks()), "分块内容可被修改")
+        checks.append("file_replacement_truncation_growth_and_digest")
+        result = await run_process(
+            [sys.executable, "-I", "-B", str(PROBE), "echo"],
+            cwd=root,
+            timeout=5,
+            input_data=snapshot.data,
+        )
+        _require(
+            result.stdout == approved and result.stderr == b"synthetic-stderr",
+            "二进制输入输出不一致",
+        )
+        checks.append("binary_input_and_separate_output")
+        failed = await run_process(
+            [sys.executable, "-I", "-B", str(PROBE), "failure"], cwd=root, timeout=5
+        )
+        _require(failed.returncode == 7, "非零退出码被隐藏")
+        checks.append("nonzero_returncode")
+        for mode in ("normal", "timeout", "cancel"):
+            await _tree_case(root, mode)
+            checks.append(f"descendants_reclaimed_on_{mode}")
+        try:
+            await run_process(
+                [sys.executable, "-I", "-B", str(PROBE), "overflow"],
+                cwd=root,
+                timeout=5,
+                max_output_bytes=1024,
+            )
+        except ManagedProcessError as exc:
+            _require(exc.error_code == "process_output_limit", "输出超限错误类型不正确")
+        else:
+            raise AssertionError("输出超限没有停止")
+        checks.append("output_limit_stops_process")
+        trace = root / "synthetic-trace"
+        artifacts = trace / "artifacts/plugins/sdk-faults"
+        artifacts.mkdir(parents=True)
+        sample = artifacts / "sample.txt"
+        sample.write_bytes(b"synthetic evidence")
+        receipt = {"name": sample.name, "sha256": hashlib.sha256(sample.read_bytes()).hexdigest()}
+        _require(len(persist_attachments(trace, "sdk-faults", [receipt])) == 1, "附件未被回读")
+        for invalid in ({**receipt, "sha256": "0" * 64}, {**receipt, "name": "../outside.txt"}):
+            try:
+                persist_attachments(trace, "sdk-faults", [invalid])
+            except ValueError:
+                pass
+            else:
+                raise AssertionError("证据摘要不符或路径穿越未拒绝")
+        checks.append("evidence_hash_and_path_rejection")
+        for execution in ("partial", "unknown"):
+            outcome = PluginCallResult(
+                status="success",
+                structured_content={
+                    "artemis": {
+                        "version": 1,
+                        "execution": execution,
+                        "side_effect": "possible",
+                        "retryable": True,
+                    }
+                },
+            )
+            decode_receipt(outcome)
+            _require(
+                not outcome.retryable and outcome.requires_observation, "不确定写操作被允许重试"
+            )
+        checks.append("partial_unknown_never_authorize_retries")
+    return {
+        "status": "passed",
+        "scope": "sdk_faults_only",
+        "python": sys.version.split()[0],
+        "platform": sys.platform,
+        "checks": checks,
+        "real_device_actions": False,
+    }
+
+
+def main():
+    parser = argparse.ArgumentParser(description=__doc__)
+    parser.add_argument("--json-output", type=Path)
+    args = parser.parse_args()
+    result = asyncio.run(run_checks())
+    if args.json_output:
+        args.json_output.write_text(
+            json.dumps(result, ensure_ascii=False, indent=2) + "\n", "utf-8"
+        )
+    print(json.dumps(result, ensure_ascii=False))
+    print("仅验证 SDK 自身；插件仍需对真实入口做故障注入、证据与任务验收。")
+
+
+if __name__ == "__main__":
+    main()

artemis/plugins/validation.py

@@ -0,0 +1,157 @@
+"""Plugin development checks and a separate market materials gate."""
+
+import argparse
+import asyncio
+import json
+from pathlib import Path
+
+from pydantic import ValidationError
+
+from artemis.plugins.evidence import validate_tools
+from artemis.plugins.market import (
+    REPORT_NAME,
+    content_fingerprint,
+    draft_submission,
+    package_directory,
+    package_files,
+    validate_submission,
+)
+from artemis.plugins.models import PluginManifest, PluginProfile
+from artemis.plugins.session import PluginSession, resolve_server
+from artemis.plugins.store import contained_path
+
+
+async def check(
+    directory: Path,
+    live: bool,
+    values: dict[str, str],
+    *,
+    market: bool = False,
+    fingerprint: bool = False,
+    prepare_market: bool = False,
+) -> dict:
+    if prepare_market and not directory.is_dir():
+        raise ValueError("请在插件目录生成市场草稿，再打包 ZIP")
+    with package_directory(directory) as (root, archive_sha256):
+        manifest = PluginManifest.model_validate_json((root / "plugin.json").read_text("utf-8"))
+        manifest.check_compatible()
+        if manifest.skill:
+            skill = contained_path(root, manifest.skill)
+            if (
+                not skill.is_file()
+                or skill.stat().st_size > 256 * 1024
+                or not skill.read_text("utf-8").strip()
+            ):
+                raise ValueError("缺少有效的 Skill 或超过大小限制")
+        if manifest.schema_version not in {2, 3}:
+            raise ValueError("新市场插件必须适配 schema_version=2 或 3")
+        if any(name not in manifest.config or manifest.config[name].secret for name in values):
+            raise ValueError("--values 只能包含清单中声明的普通配置，不得包含密钥")
+        files = package_files(root) if market or fingerprint or prepare_market else None
+        if prepare_market:
+            assert files is not None
+            draft = draft_submission(manifest, files)
+            with (root / REPORT_NAME).open("x", encoding="utf-8") as handle:
+                handle.write(json.dumps(draft, ensure_ascii=False, indent=2) + "\n")
+            return {
+                "status": "draft",
+                "plugin_id": manifest.id,
+                "version": manifest.version,
+                "content_sha256": draft["content_sha256"],
+            }
+        submission = None
+        if market:
+            assert files is not None
+            submission = validate_submission(root, manifest, files)
+        handshake = bool((live or market) and manifest.server)
+        if handshake:
+            server = resolve_server(manifest, PluginProfile(values=values), root)
+            server.env["PYTHONDONTWRITEBYTECODE"] = "1"
+            session = await PluginSession(server, root).start()
+            try:
+                validate_tools(manifest, session.tools)
+            finally:
+                await session.aclose()
+            if files is not None and package_files(root) != files:
+                raise ValueError("MCP 握手期间包内容发生变化，检查记录失效")
+            if market:
+                assert files is not None
+                if validate_submission(root, manifest, files) != submission:
+                    raise ValueError("MCP 握手期间市场记录发生变化，检查记录失效")
+        result = {
+            "status": "passed",
+            "plugin_id": manifest.id,
+            "version": manifest.version,
+            "scope": "market_materials" if market else "development",
+            "mcp_handshake": handshake,
+        }
+        if files is not None:
+            result["content_sha256"] = content_fingerprint(files)
+        if archive_sha256 is not None:
+            result["archive_sha256"] = archive_sha256
+        return result
+
+
+def main() -> None:
+    parser = argparse.ArgumentParser(description=__doc__)
+    parser.add_argument("directory", type=Path, help="插件目录或 ZIP；不会安装到现有插件库")
+    parser.add_argument(
+        "--live", action="store_true", help="仅启动/关闭 MCP 并核对声明，不调用工具"
+    )
+    parser.add_argument("--values", default="{}", help="普通配置 JSON；不得包含密钥")
+    modes = parser.add_mutually_exclusive_group()
+    modes.add_argument(
+        "--market", action="store_true", help="核对市场分发、内容绑定和验收材料，含 MCP 握手"
+    )
+    modes.add_argument(
+        "--prepare-market", action="store_true", help="创建未验证的 MARKET.json 草稿，不覆盖旧文件"
+    )
+    modes.add_argument(
+        "--fingerprint", action="store_true", help="输出包内容摘要；不宣称市场验收通过"
+    )
+    parser.add_argument("--json-output", type=Path, help="将检查结果写到包外 JSON 文件")
+    args = parser.parse_args()
+    result = {}
+    can_write = True
+    try:
+        if args.json_output and (
+            args.json_output.resolve() == args.directory.resolve()
+            or (
+                args.directory.is_dir()
+                and args.json_output.resolve().is_relative_to(args.directory.resolve())
+            )
+        ):
+            can_write = False
+            raise ValueError("检查输出必须在插件包之外，不能覆盖输入包")
+        values = json.loads(args.values)
+        if not isinstance(values, dict) or any(not isinstance(v, str) for v in values.values()):
+            raise ValueError("--values 必须是字符串值的 JSON 对象")
+        result = asyncio.run(
+            check(
+                args.directory.resolve(),
+                args.live,
+                values,
+                market=args.market,
+                fingerprint=args.fingerprint,
+                prepare_market=args.prepare_market,
+            )
+        )
+    except (ValueError, OSError, RuntimeError) as exc:
+        message = (
+            "输入格式或清单/市场材料字段不合法"
+            if isinstance(exc, (json.JSONDecodeError, ValidationError))
+            else str(exc)
+        )
+        result = {"status": "failed", "error": message}
+    if args.json_output and can_write:
+        args.json_output.write_text(
+            json.dumps(result, ensure_ascii=False, indent=2) + "\n", "utf-8"
+        )
+    print(json.dumps(result, ensure_ascii=False))
+    print("检查范围不包括源码正确性与真实业务通过；市场材料仍需来源审查和真实任务验收。")
+    if result["status"] == "failed":
+        raise SystemExit(1)
+
+
+if __name__ == "__main__":
+    main()