iomgaa
30895cd306
ToolSpec 五个字段加构造期校验（空名字、非映射 parameters），parameters 深拷贝一份存下来 ——不拷贝的话调用方在别处改那个字典会连带改掉模型看见的 schema，而那次修改没有任何地方 记录得到。 ToolRegistry 是不可变值对象：注册顺序保留（工具清单要贴进提示词，而 restrict_to 收到的 常常是 set，照集合顺序输出会让同一份配置在不同进程里渲染出不同提示词）；相等按内容判 不按身份判，供 RunRequest 那条一致性校验用；restrict_to 遇到不认识的名字直接报错， 不静默丢弃。 validate 校验的是 JSON Schema 的一个子集（必填键、additionalProperties: false 时的多余键、 顶层 type），子集边界写在 docstring 里。完整校验只能靠第三方库，而公共签名上不许出现 第三方类型。剩下那部分由工具自己报错，那是一条正常观察。 executor() 没写，缺口见 design/0008（待确认，要过人类门）。
317 lines
12 KiB
Python
317 lines
12 KiB
Python
"""工具规格与注册表的行为。
|
|
|
|
这里断言的不是「注册表有哪些方法」，是它对外的行为——名字与签名本身由
|
|
`research-wiki/design/0006-public-names-and-signatures.md` 决策六承诺，改了是破坏性变更。
|
|
|
|
最要紧的一条是**四者同源**：模型看见的 schema、存在性校验、参数校验、分发都由同一个实例
|
|
驱动。收窄之后模型看不见的工具，校验也必须拒绝它——这一条单独写在下面，因为它正是这个
|
|
模块存在的理由。
|
|
"""
|
|
|
|
import json
|
|
|
|
import pytest
|
|
|
|
from polyloop.ports import ToolCall
|
|
from polyloop.tools import ToolRegistry, ToolSpec, ToolValidationError
|
|
from polyloop.types import ReplayPolicy
|
|
|
|
pytestmark = pytest.mark.unit
|
|
|
|
|
|
def _spec(name: str, **kwargs: object) -> ToolSpec:
|
|
"""造一个规格，只有 `name` 是必须自己填的。"""
|
|
parameters = kwargs.pop("parameters", {})
|
|
return ToolSpec(name=name, description=f"{name} 的说明", parameters=parameters, **kwargs) # type: ignore[arg-type]
|
|
|
|
|
|
# ---------------------------------------------------------------------------
|
|
# ToolSpec
|
|
# ---------------------------------------------------------------------------
|
|
|
|
|
|
def test_spec_rejects_an_empty_name() -> None:
|
|
"""空名字在提示词里不可见，模型永远调不到它。"""
|
|
with pytest.raises(ValueError, match="工具名"):
|
|
ToolSpec(name="", description="", parameters={})
|
|
|
|
|
|
def test_spec_rejects_non_mapping_parameters() -> None:
|
|
with pytest.raises(TypeError, match="parameters"):
|
|
ToolSpec(name="search", description="", parameters=["query"]) # type: ignore[arg-type]
|
|
|
|
|
|
def test_spec_snapshots_the_parameters_it_was_given() -> None:
|
|
"""注册之后改调用方那份字典，注册表看见的仍是注册那一刻的形状。
|
|
|
|
不拷贝的话，「模型看见的 schema」会随调用方在别处的一次修改一起变，而那次修改没有任何
|
|
地方记录得到——事后翻轨迹，模型当时到底看见的是哪一份，查不出来。
|
|
"""
|
|
schema: dict[str, object] = {"properties": {"query": {"type": "string"}}}
|
|
spec = _spec("search", parameters=schema)
|
|
|
|
schema["properties"] = {"query": {"type": "integer"}} # type: ignore[index]
|
|
|
|
assert spec.parameters["properties"] == {"query": {"type": "string"}}
|
|
|
|
|
|
def test_spec_defaults_are_the_conservative_ones() -> None:
|
|
"""重放策略默认「绝不重放」、完成标记默认「不完成」。
|
|
|
|
两个默认值的方向都是「漏了声明只会多停一次，有人会看见」，反过来则是静默重复副作用、
|
|
或者一次运行永远停不下来。
|
|
"""
|
|
spec = _spec("write_file")
|
|
|
|
assert spec.replay_policy is ReplayPolicy.NEVER
|
|
assert spec.completes_run is False
|
|
|
|
|
|
# ---------------------------------------------------------------------------
|
|
# 注册与查询
|
|
# ---------------------------------------------------------------------------
|
|
|
|
|
|
def test_registry_rejects_duplicate_names() -> None:
|
|
"""重名会让「模型看见的那一份」和「分发时取到的那一份」取决于注册顺序。"""
|
|
with pytest.raises(ValueError, match="重复"):
|
|
ToolRegistry([_spec("search"), _spec("search")])
|
|
|
|
|
|
def test_registry_rejects_things_that_are_not_specs() -> None:
|
|
with pytest.raises(TypeError):
|
|
ToolRegistry([{"name": "search"}]) # type: ignore[list-item]
|
|
|
|
|
|
def test_an_empty_registry_is_constructible() -> None:
|
|
"""不注册任何工具是一种正常装配：模型输出的是一整段代码，不是工具调用。"""
|
|
registry = ToolRegistry()
|
|
|
|
assert registry.names() == ()
|
|
assert list(registry.schema_for_model()) == []
|
|
|
|
|
|
def test_registration_order_is_preserved() -> None:
|
|
"""工具清单要贴进提示词，顺序必须是确定的。"""
|
|
registry = ToolRegistry([_spec("read"), _spec("write"), _spec("search")])
|
|
|
|
assert registry.names() == ("read", "write", "search")
|
|
assert [entry["name"] for entry in registry.schema_for_model()] == ["read", "write", "search"]
|
|
|
|
|
|
def test_spec_for_returns_none_for_an_unregistered_name() -> None:
|
|
"""问一个不在注册表里的名字是正常情形，不是错误。
|
|
|
|
没有工具的动作（一整段代码）就问不出规格，那时调用方取「绝不重放」。抛异常的话这条
|
|
正常路径要用捕获异常来走。
|
|
"""
|
|
registry = ToolRegistry([_spec("read")])
|
|
|
|
assert registry.spec_for("read") is not None
|
|
assert registry.spec_for("write") is None
|
|
|
|
|
|
# ---------------------------------------------------------------------------
|
|
# 收窄
|
|
# ---------------------------------------------------------------------------
|
|
|
|
|
|
def test_restrict_to_keeps_registration_order_not_the_caller_order() -> None:
|
|
"""收窄结果按注册顺序排，不按传进来的那个集合的迭代顺序。
|
|
|
|
收窄清单常常是一个 `set`，而 Python 的字符串哈希每进程随机——照集合顺序输出会让同一份
|
|
配置在不同进程里渲染出不同的提示词。
|
|
"""
|
|
registry = ToolRegistry([_spec("read"), _spec("write"), _spec("search")])
|
|
|
|
narrowed = registry.restrict_to({"search", "read"})
|
|
|
|
assert narrowed.names() == ("read", "search")
|
|
|
|
|
|
def test_restrict_to_leaves_the_original_alone() -> None:
|
|
"""注册表是不可变值对象，取子集返回新实例。"""
|
|
registry = ToolRegistry([_spec("read"), _spec("write")])
|
|
|
|
narrowed = registry.restrict_to(["read"])
|
|
|
|
assert narrowed.names() == ("read",)
|
|
assert registry.names() == ("read", "write")
|
|
|
|
|
|
def test_restrict_to_rejects_a_name_it_does_not_have() -> None:
|
|
"""静默丢弃的话，模型看不见调用方以为已经开放的那个工具，而表现是模型在绕圈。"""
|
|
registry = ToolRegistry([_spec("read")])
|
|
|
|
with pytest.raises(ValueError, match="不在注册表里"):
|
|
registry.restrict_to(["read", "reed"])
|
|
|
|
|
|
def test_two_registries_with_the_same_specs_are_equal() -> None:
|
|
"""相等按「注册了哪些规格、什么顺序」判，不按对象身份判。
|
|
|
|
构造运行请求时要比对「执行器持有的注册表」和「本次可见的注册表」，两份内容相同的注册表
|
|
在模型可见 schema 与实际分发上完全一致，没有可失败的地方。
|
|
"""
|
|
specs = [_spec("read"), _spec("write")]
|
|
|
|
assert ToolRegistry(specs) == ToolRegistry(specs)
|
|
assert ToolRegistry(specs) != ToolRegistry(list(reversed(specs)))
|
|
assert ToolRegistry(specs) != ToolRegistry([_spec("read")])
|
|
|
|
|
|
# ---------------------------------------------------------------------------
|
|
# 模型可见的 schema
|
|
# ---------------------------------------------------------------------------
|
|
|
|
|
|
def test_schema_for_model_is_json_serialisable() -> None:
|
|
"""这份清单要贴进提示词或者发给模型 API，必须能直接序列化。"""
|
|
registry = ToolRegistry(
|
|
[_spec("read", parameters={"properties": {"path": {"type": "string"}}})]
|
|
)
|
|
|
|
json.dumps(list(registry.schema_for_model()))
|
|
|
|
|
|
def test_mutating_the_returned_schema_does_not_touch_the_registry() -> None:
|
|
"""每次调用现造一份新的普通字典，调用方改它不会影响后面几步看见的东西。"""
|
|
registry = ToolRegistry(
|
|
[_spec("read", parameters={"properties": {"path": {"type": "string"}}})]
|
|
)
|
|
|
|
entry = registry.schema_for_model()[0]
|
|
entry["parameters"]["properties"]["path"]["type"] = "integer" # type: ignore[index]
|
|
|
|
assert registry.schema_for_model()[0]["parameters"] == {
|
|
"properties": {"path": {"type": "string"}}
|
|
}
|
|
|
|
|
|
# ---------------------------------------------------------------------------
|
|
# 校验
|
|
# ---------------------------------------------------------------------------
|
|
|
|
|
|
def test_validate_accepts_a_well_formed_call() -> None:
|
|
registry = ToolRegistry(
|
|
[
|
|
_spec(
|
|
"read",
|
|
parameters={
|
|
"properties": {"path": {"type": "string"}},
|
|
"required": ["path"],
|
|
"additionalProperties": False,
|
|
},
|
|
)
|
|
]
|
|
)
|
|
|
|
registry.validate(ToolCall(name="read", arguments={"path": "a.txt"}))
|
|
|
|
|
|
def test_validate_rejects_a_tool_that_is_not_registered() -> None:
|
|
registry = ToolRegistry([_spec("read")])
|
|
|
|
with pytest.raises(ToolValidationError, match="不存在"):
|
|
registry.validate(ToolCall(name="write", arguments={}))
|
|
|
|
|
|
def test_validate_rejects_a_missing_required_parameter() -> None:
|
|
registry = ToolRegistry(
|
|
[
|
|
_spec(
|
|
"read",
|
|
parameters={"properties": {"path": {"type": "string"}}, "required": ["path"]},
|
|
)
|
|
]
|
|
)
|
|
|
|
with pytest.raises(ToolValidationError, match="必填"):
|
|
registry.validate(ToolCall(name="read", arguments={}))
|
|
|
|
|
|
def test_validate_rejects_an_undeclared_parameter_only_when_the_schema_says_so() -> None:
|
|
"""多出来的键只在 schema 显式写了 `additionalProperties: false` 时才拒绝。
|
|
|
|
JSON Schema 里这一项默认为真，跟着它走；自作主张收紧的话，一份合法 schema 在库里和在别处
|
|
的含义就不一样了，而不一样的地方没有任何标记。
|
|
"""
|
|
lenient = ToolRegistry([_spec("read", parameters={"properties": {"path": {"type": "string"}}})])
|
|
strict = ToolRegistry(
|
|
[
|
|
_spec(
|
|
"read",
|
|
parameters={
|
|
"properties": {"path": {"type": "string"}},
|
|
"additionalProperties": False,
|
|
},
|
|
)
|
|
]
|
|
)
|
|
call = ToolCall(name="read", arguments={"path": "a.txt", "encoding": "utf-8"})
|
|
|
|
lenient.validate(call)
|
|
with pytest.raises(ToolValidationError, match="未声明"):
|
|
strict.validate(call)
|
|
|
|
|
|
def test_validate_rejects_a_wrong_top_level_type() -> None:
|
|
registry = ToolRegistry(
|
|
[_spec("read", parameters={"properties": {"path": {"type": "string"}}})]
|
|
)
|
|
|
|
with pytest.raises(ToolValidationError, match="类型"):
|
|
registry.validate(ToolCall(name="read", arguments={"path": 7}))
|
|
|
|
|
|
def test_a_boolean_is_not_an_integer() -> None:
|
|
"""布尔在 Python 里是整数的子类，在 JSON 里不是。
|
|
|
|
不排掉的话，一个声明收整数的工具会收下 `True`，然后在工具内部被当成 1 用。
|
|
"""
|
|
registry = ToolRegistry([_spec("head", parameters={"properties": {"n": {"type": "integer"}}})])
|
|
|
|
with pytest.raises(ToolValidationError, match="类型"):
|
|
registry.validate(ToolCall(name="head", arguments={"n": True}))
|
|
|
|
|
|
def test_a_type_may_be_declared_as_a_list_of_alternatives() -> None:
|
|
registry = ToolRegistry(
|
|
[_spec("head", parameters={"properties": {"n": {"type": ["integer", "null"]}}})]
|
|
)
|
|
|
|
registry.validate(ToolCall(name="head", arguments={"n": 3}))
|
|
registry.validate(ToolCall(name="head", arguments={"n": None}))
|
|
with pytest.raises(ToolValidationError, match="类型"):
|
|
registry.validate(ToolCall(name="head", arguments={"n": "3"}))
|
|
|
|
|
|
def test_an_empty_schema_accepts_anything() -> None:
|
|
"""没声明参数就等于不约束参数，不等于「不许带参数」。"""
|
|
registry = ToolRegistry([_spec("ping")])
|
|
|
|
registry.validate(ToolCall(name="ping", arguments={"anything": [1, 2, 3]}))
|
|
|
|
|
|
# ---------------------------------------------------------------------------
|
|
# 四者同源
|
|
# ---------------------------------------------------------------------------
|
|
|
|
|
|
def test_narrowing_hides_a_tool_from_the_model_and_from_validation_together() -> None:
|
|
"""收窄之后模型看不见的工具，校验也拒绝它。
|
|
|
|
这是这个模块存在的理由：模型看见的 schema、存在性校验、参数校验、分发四者同源。不同源
|
|
的表现是「模型调了一个它看得见的工具却说不存在」，或者反过来——校验放行了一个分发时
|
|
找不到的名字。
|
|
"""
|
|
registry = ToolRegistry([_spec("read"), _spec("write")])
|
|
|
|
narrowed = registry.restrict_to(["read"])
|
|
|
|
assert [entry["name"] for entry in narrowed.schema_for_model()] == ["read"]
|
|
assert narrowed.spec_for("write") is None
|
|
with pytest.raises(ToolValidationError):
|
|
narrowed.validate(ToolCall(name="write", arguments={}))
|