原始思想与改编边界
以精简工具面起步，显式组合扩展；不复刻 Pi 的 TypeScript runtime、TUI 或完整插件生态。 原始来源。框架与用户的分工
四个原生 Env 工具加 verification_tools 构成注册表。扩展在 Docker 中执行控制端固定检查，并将测试源码摘要关联 ArtifactRef。 QitOS 已提供：模型事务与 usage、工具权限/校验、Env 执行、Session、ArtifactRef 和 Trajectory。用户编写：任务、策略、完成检查及记忆/技能选择。本轮补齐：自定义 agent_factory 接入、持久技能版本、完整正文加载、显式 Memdir 删除与产物引用的数据权限修正。 核心增量位于完整源码中的 agent.py；CLI 负责显式配置与资源生命周期，evaluate.py 是控制端检查器。任务由项目自有合成材料组成，不是论文基准或真实客户数据。安装、配置与运行
先按仓库构建说明安装本轮 QitOS wheel（当前 PyPI 版本不能替代未发布实现），再安装本课程。真实地址与凭据仅放在仓库外。模型配置采用完整 qitos.agent 文件，课程只读取其中 model；不是通过环境变量注入 key。 每次 run 使用新的仓库外目录；resume 只接受同一项目重构的工厂与 resolver。 默认输出上限 10,240，可通过私有模型配置提高；单任务步数、请求数和运行时间读取公开配置。validate 不调用模型，真实执行必须显式 —live。Docker 不可用时不能降级到宿主。模型失败、未完成任务和人工干预均保留，不能自动改为通过。验证、练习与组合
独立检查器核验资料/数值或实际代码结果，不接受模型自报成功。计划修订、技能实际加载、子 Session 身份与失败也须单独验收。Session 恢复不是文件回滚；生成代码只在受限 Env 内执行。 练习：安装验证 CLI 合同的另一种检查器，不改变 Agent 策略。 组合：在 Claude-like 子审查或 Voyager 发布门中复用检查器。 完整矩阵：三种任务各三轮。ReAct/PlanAct 使用同样任务；PlanAct 的 static、Hermes 的 no-memory、Voyager 的 no-skills 是明确对照，不以一次成功作性能结论。私有原始轨迹不能直接公开；仅在检查许可与脱敏后发布衍生摘要。python -m pip install .
python -m qitos_lab_pi validate --config agent.yaml --root /tmp/lab-validation
python -m qitos_lab_pi run --config agent.yaml --model-config /private-config/model.yaml --credentials /private-config/credentials.yaml --root /private-runs/pi-attempt --task 0 --live
examples/projects/pi_coding/src/qitos_lab_pi/agent.py.
从完整源码提取：设计增量
下列片段由完整项目同步生成，不是另一份手工维护的实现。完整安装文件在后面。 def prepare(self, state):
return json.dumps(
{"task": state.task, "recent_results": state.observations[-4:]}
)
def reduce(self, state, observation, decision):
state.observations.extend(
item.to_model_dict(max_chars=6000) for item in observation.action_results
)
state.observations = state.observations[-8:]
return state
完整文件：复制到项目根目录
src/qitos_lab_pi/__main__.py
"""Explicit launch configuration; no credentials or model calls during validate."""
import argparse
from dataclasses import asdict, replace
from importlib.resources import files
import json
from pathlib import Path
import sys
from qitos.config import (
BudgetConfig,
LocalCredentialFileResolver,
SessionConfig,
TrajectoryConfig,
build_agent_composition,
load_agent_config,
)
from .agent import build_factory
from .evaluate import evaluate
def main():
parser = argparse.ArgumentParser(description=__doc__)
parser.add_argument("command", choices=["validate", "run", "resume", "inspect"])
parser.add_argument("--config", type=Path, required=True)
parser.add_argument("--model-config", type=Path)
parser.add_argument("--credentials", type=Path)
parser.add_argument("--root", type=Path, required=True)
parser.add_argument("--task", type=int, choices=[0, 1, 2], default=0)
parser.add_argument("--session")
parser.add_argument("--live", action="store_true")
parser.add_argument(
"--variant",
choices=["default", "static", "no-memory", "no-skills"],
default="default",
)
args = parser.parse_args()
config = load_agent_config(args.config)
tasks = json.loads(files(__package__).joinpath("tasks.json").read_text())
task = tasks[args.task]
if args.command == "validate":
print(
json.dumps(
{"status": "configuration_valid", "tasks": len(tasks), "live": False}
)
)
return 0
root = args.root.resolve()
if any((parent / ".git").exists() for parent in (root, *root.parents)):
raise ValueError("run_root_must_be_outside_git")
root.mkdir(parents=True, exist_ok=True, mode=0o700)
if args.command == "inspect":
from qitos.qita.reader import candidate_file_reader
reader = candidate_file_reader(root / "trajectory.journal")
print(json.dumps({"runs": [asdict(run) for run in reader.discover_runs()]}))
return 0
if not args.live or args.credentials is None:
raise ValueError("explicit_live_and_credentials_required")
if args.model_config is not None:
private = args.model_config.resolve()
if any((parent / ".git").exists() for parent in private.parents):
raise ValueError("model_config_must_be_outside_git")
config = replace(config, model=load_agent_config(private).model)
output_limit = max(10240, config.model.request.max_tokens or 0)
request = replace(config.model.request, max_tokens=output_limit)
config = replace(
config, model=replace(config.model, request=request, max_tokens=output_limit)
)
workspace = root / "input"
if args.command == "run":
workspace.mkdir(exist_ok=False)
for name, content in task["inputs"].items():
target = workspace / name
target.parent.mkdir(parents=True, exist_ok=True)
target.write_text(content)
config = replace(
config,
budgets=config.budgets
or BudgetConfig(max_steps=80, max_requests=80, max_runtime_seconds=3600),
runtime=replace(
config.runtime,
environment=replace(config.runtime.environment, workspace=str(workspace)),
session=SessionConfig(store="sqlite", path=str(root / "sessions.sqlite3")),
trajectory=TrajectoryConfig(output=str(root / "trajectory.journal")),
),
)
resolver = LocalCredentialFileResolver(args.credentials, repository_root=Path.cwd())
factory = build_factory(task, root=root, variant=args.variant)
with build_agent_composition(
config, credential_resolver=resolver, agent_factory=factory
) as composition:
session = (
composition.restore(args.session)
if args.command == "resume"
else composition.session(task["task"])
)
(root / "session.json").write_text(
json.dumps({"session_id": session.session_id.value})
)
result = session.run()
verdict = evaluate(result, task)
report = {
"session_id": session.session_id.value,
"run_id": result.run_id,
"stop_reason": str(result.state.stop_reason),
"evaluation": verdict,
"tool_calls": result.tool_calls_by_name,
"variant": args.variant,
}
(root / "report.json").write_text(
json.dumps(report, ensure_ascii=False, indent=2)
)
print(json.dumps(report, ensure_ascii=False))
return 0 if verdict["passed"] else 2
if __name__ == "__main__":
try:
raise SystemExit(main())
except Exception as error:
# Raw transport/factory errors can contain private endpoint details.
print(
json.dumps({"status": "failed", "error_type": type(error).__name__}),
file=sys.stderr,
)
raise SystemExit(2) from None
src/qitos_lab_pi/tasks.json
[
{
"id": "C21",
"task": "Repair a small CSV analysis package. Normalize whitespace, reject malformed rows with a useful error, compute weighted means without rounding early, and keep the CLI JSON contract. Read AGENTS.md, modify multiple modules, run verify_project, and finish only after verification passes.",
"inputs": {
"AGENTS.md": "Use stdlib only. Keep existing public names. Handle empty and invalid data explicitly. Do not change the data files to make checks pass.\n",
"parser.py": "import csv\n\ndef parse(text):\n return [(r['group'], float(r['value']), int(r['count'])) for r in csv.DictReader(text.splitlines())]\n",
"analysis.py": "def weighted_mean(rows):\n return sum(value for _, value, count in rows) / len(rows)\n",
"cli.py": "import json, sys\nfrom parser import parse\nfrom analysis import weighted_mean\nif __name__ == '__main__':\n print(json.dumps({'mean': weighted_mean(parse(sys.stdin.read()))}))\n",
"sample.csv": "group,value,count\n small ,10,8\nlarge,30,2\n"
},
"outputs": [
"parser.py",
"analysis.py"
],
"checks": "from parser import parse\nfrom analysis import weighted_mean\nrows=parse('group,value,count\\n a ,10,8\\nb,30,2\\n')\nassert rows[0][0]=='a'\nassert weighted_mean(rows)==14\ntry: weighted_mean([])\nexcept ValueError: pass\nelse: raise AssertionError('empty weights must be rejected')\ntry: parse('group,value,count\\nx,abc,2\\n')\nexcept ValueError: pass\nelse: raise AssertionError('invalid numeric data must be rejected')\n"
},
{
"id": "C22",
"task": "Repair a versioned event migration library. Preserve unknown payload fields, reject unknown schema versions, never mutate caller input, and make summarization idempotent by event identity. Read the project contract; verify both modules.",
"inputs": {
"AGENTS.md": "No external dependencies. Current schema is 2; schema 1 maps id->event_id without losing payload. Unknown versions reject. Duplicate identical IDs are ignored; conflicting duplicates reject.\n",
"migration.py": "def migrate(event):\n event['event_id'] = event.pop('id', event.get('event_id'))\n event['schema'] = 2\n return event\n",
"summary.py": "def total(events):\n return sum(event['value'] for event in events)\n"
},
"outputs": [
"migration.py",
"summary.py"
],
"checks": "from migration import migrate\nfrom summary import total\nx={'schema':1,'id':'a','value':3,'tag':'keep'}\ny=migrate(x)\nassert x=={'schema':1,'id':'a','value':3,'tag':'keep'}\nassert y=={'schema':2,'event_id':'a','value':3,'tag':'keep'}\nassert migrate(y)==y\nassert total([y,y])==3\ntry: migrate({'schema':99,'id':'x'})\nexcept ValueError: pass\nelse: raise AssertionError('unknown schema accepted')\ntry: total([y,dict(y,value=4)])\nexcept ValueError: pass\nelse: raise AssertionError('conflicting duplicate accepted')\n"
},
{
"id": "C23",
"task": "Repair a bounded job scheduler's pure policy modules: deterministic admission, FIFO pending work, duplicate suppression, and quorum join decisions. This is a teaching application, not a replacement for QitOS's runtime. Read AGENTS.md and verify the two modules together.",
"inputs": {
"AGENTS.md": "admit(pending, active, limit) returns new IDs, leaves inputs untouched, preserves FIFO and excludes active/duplicate IDs. Negative limit rejects. join_state(outcomes, required, total) counts successful unique work IDs, returns success when quorum met, impossible when remaining capacity is insufficient, otherwise pending.\n",
"admission.py": "def admit(pending, active, limit):\n return pending[:limit]\n",
"join.py": "def join_state(outcomes, required, total):\n return 'success' if len(outcomes)>=required else 'pending'\n"
},
"outputs": [
"admission.py",
"join.py"
],
"checks": "from admission import admit\nfrom join import join_state\np=['a','b','b','c','d']; a=['a']\nassert admit(p,a,3)==['b','c']\nassert p==['a','b','b','c','d'] and a==['a']\ntry: admit(p,a,-1)\nexcept ValueError: pass\nelse: raise AssertionError('negative limit accepted')\nassert join_state({'a':'success','b':'failed'},2,3)=='pending'\nassert join_state({'a':'success','b':'failed','c':'failed'},2,3)=='impossible'\nassert join_state({'a':'success','b':'success'},2,3)=='success'\n"
}
]
src/qitos_lab_pi/evaluate.py
"""Read successful controller-owned verification, not the model's final claim."""
def evaluate(result, task, *, prior_records=()):
verified_step = -1
edited_step = -1
source_digests = {}
for record in [*prior_records, *result.records]:
for item in record.action_results:
if item.tool_name in {"write_file", "edit_file", "run_command"}:
edited_step = record.step_id
if item.tool_name == "verify_project" and item.status == "success":
output = item.output
if isinstance(output, dict) and output.get("verified") is True:
verified_step = record.step_id
source_digests = output.get("source_digests", {})
else:
verified_step = -1
checks = {
"independent_checks": verified_step >= 0,
"no_edits_after_verification": verified_step >= edited_step,
"all_outputs_captured": set(task["outputs"]) == set(source_digests),
"read_before_edit": result.tool_calls_by_name.get("read_file", 0) > 0,
"final": str(result.state.stop_reason) == "final",
}
return {
"passed": all(checks.values()),
"checks": checks,
"source_digests": source_digests,
}
src/qitos_lab_pi/agent.py
"""A small replaceable coding policy, not a second agent execution loop."""
from dataclasses import dataclass, field
import json
from qitos.core.agent_module import AgentModule
from qitos.core.state import StateSchema
from qitos.kit.toolset.env_coding import read_file, write_file, edit_file, run_command
from .extension import verification_tools
@dataclass
class CodingState(StateSchema):
observations: list[dict] = field(default_factory=list)
class CodingAgent(AgentModule):
def init_state(self, task, **kwargs):
return CodingState(task=task, max_steps=self.config.get("max_steps", 80))
def base_persona_prompt(self, state):
return (
"Inspect, change and test a real multi-file project. Use the four native "
"read/write/edit/command tools; do not invent a framework executor. "
"Read AGENTS.md first. Commands run only in the configured Docker Env."
)
def task_policy_prompt(self, state):
return (
"Use the installed verify_project extension for independent checks. "
"A successful shell exit alone is not project completion. If checks fail, "
"inspect their evidence and correct the cause. Do not edit tests to pass. "
"After verify_project passes, make no further edits and give a final answer."
)
# docs:start design
def prepare(self, state):
return json.dumps(
{"task": state.task, "recent_results": state.observations[-4:]}
)
def reduce(self, state, observation, decision):
state.observations.extend(
item.to_model_dict(max_chars=6000) for item in observation.action_results
)
state.observations = state.observations[-8:]
return state
# docs:end design
def build_factory(task, **resources):
def factory(*, config, model, tool_registry, protocol, parser):
for tool in (
read_file,
write_file,
edit_file,
run_command,
*verification_tools(task),
):
tool_registry.register(tool)
return CodingAgent(
llm=model,
tool_registry=tool_registry,
model_protocol=protocol.id,
max_steps=config.max_steps,
model_parser=parser,
)
return factory
src/qitos_lab_pi/extension.py
"""Installable project extension. All generated-code execution stays in Env."""
import hashlib
import shlex
from typing import Optional, Dict, Any
from qitos.core.artifact import ArtifactRef
from qitos.core.function_tool_decorator import function_tool
from qitos.core.tool import ToolPermission
from qitos.core.tool_result import ToolResult
def verification_tools(task):
@function_tool(
required_ops=["file", "process"],
permissions=ToolPermission(filesystem_read=True, command=True),
concurrency_safe=False,
)
def verify_project(runtime_context: Optional[Dict[str, Any]] = None):
"""Run controller-owned checks, capture exact tested source artifacts."""
context = runtime_context or {}
fs, process = context["ops"]["file"], context["ops"]["process"]
bodies = {path: fs.read_text(path).encode() for path in task["outputs"]}
outcome = dict(
process.run("python -c " + shlex.quote(task["checks"]), timeout=30)
)
unchanged = all(
fs.read_text(path).encode() == body for path, body in bodies.items()
)
passed = (
outcome.get("returncode") == 0
and not outcome.get("outcome_unknown")
and unchanged
)
refs = []
for path, body in bodies.items():
digest = hashlib.sha256(body).hexdigest()
ref = ArtifactRef(
artifact_id="sha256:" + digest,
resolver_key="tool-result-output",
sha256=digest,
byte_length=len(body),
media_type="text/x-python",
)
context["artifact_resolver"].put(ref, body)
refs.append(ref)
report = {
"verified": passed,
"source_digests": {
path: hashlib.sha256(body).hexdigest() for path, body in bodies.items()
},
"checks_digest": hashlib.sha256(task["checks"].encode()).hexdigest(),
"returncode": outcome.get("returncode"),
"source_unchanged": unchanged,
"feedback": str(outcome.get("stderr", ""))[-3000:],
}
return ToolResult(
output=report,
model_output=report,
artifact_refs=tuple(refs),
tool_name="verify_project",
)
return (verify_project,)
def statistics_tools():
"""Optional pure-data extension reused by the PlanAct composition lesson."""
@function_tool(read_only=True, concurrency_safe=True)
def weighted_summary(values: list[float], weights: list[int]):
"""Calculate a weighted mean with explicit dimension/weight validation."""
if (
not values
or len(values) != len(weights)
or any(weight < 0 for weight in weights)
):
raise ValueError("invalid_weighted_series")
total = sum(weights)
if total <= 0:
raise ValueError("empty_weighted_series")
return {
"mean": sum(value * weight for value, weight in zip(values, weights))
/ total,
"total_weight": total,
}
return (weighted_summary,)
src/qitos_lab_pi/__init__.py
"""Agent Design Lab: independently installed coding project."""
pyproject.toml
[build-system]
requires = ["setuptools>=68"]
build-backend = "setuptools.build_meta"
[project]
name = "qitos-lab-pi"
version = "0.1.0"
requires-python = ">=3.10"
dependencies = ["qitos[openai]"]
[tool.setuptools.packages.find]
where = ["src"]
[tool.setuptools.package-data]
qitos_lab_pi = ["tasks.json"]
agent.yaml
schema: qitos.agent
agent:
name: design-lab-pi-research
protocol: json_decision_multi_v1
model:
provider: openai_compatible
model: example-model
base_url: https://provider.example/v1
credential:
ref: research-model
request:
max_tokens: 10240
timeout_seconds: 180
retries: 0
tools:
preset: none
runtime:
environment:
type: docker
workspace: .
image: python:3.12-slim
session:
mode: durable
store: sqlite
path: ./sessions.sqlite3
trajectory:
enabled: true
output: ./trajectory.journal
budgets:
max_steps: 80
max_requests: 80
max_runtime_seconds: 3600
failure_policy:
tool: continue