lm-deluge 0.0.50__tar.gz → 0.0.51__tar.gz

{lm_deluge-0.0.50/src/lm_deluge.egg-info → lm_deluge-0.0.51}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: lm_deluge
-Version: 0.0.50
+Version: 0.0.51
 Summary: Python utility for using LLM API models.
 Author-email: Benjamin Anderson <ben@trytaylor.ai>
 Requires-Python: >=3.10

{lm_deluge-0.0.50 → lm_deluge-0.0.51}/pyproject.toml

@@ -3,7 +3,7 @@ requires = ["setuptools", "wheel"]
 
 [project]
 name = "lm_deluge"
-version = "0.0.50"
+version = "0.0.51"
 authors = [{ name = "Benjamin Anderson", email = "ben@trytaylor.ai" }]
 description = "Python utility for using LLM API models."
 readme = "README.md"

{lm_deluge-0.0.50 → lm_deluge-0.0.51}/src/lm_deluge/tool.py

@@ -58,14 +58,14 @@ class Tool(BaseModel):
     """
 
     name: str
-    description: str | None
-    parameters: dict[str, Any] | None
+    description: str | None = None
+    parameters: dict[str, Any] | None = None
     required: list[str] = Field(default_factory=list)
     additionalProperties: bool | None = None  # only
     # if desired, can provide a callable to run the tool
     run: Callable | None = None
     # for built-in tools that don't require schema
-    built_in: bool = False
+    is_built_in: bool = False
     type: str | None = None
     built_in_args: dict[str, Any] = Field(default_factory=dict)
 
@@ -309,7 +309,7 @@ class Tool(BaseModel):
     def for_openai_completions(
         self, *, strict: bool = True, **kwargs
     ) -> dict[str, Any]:
-        if self.built_in:
+        if self.is_built_in:
             return {"type": self.type, **self.built_in_args, **kwargs}
         if strict:
             # For strict mode, remove defaults and make all parameters required
@@ -338,7 +338,7 @@ class Tool(BaseModel):
         return self.for_openai_completions(strict=strict, **kwargs)
 
     def for_openai_responses(self, **kwargs) -> dict[str, Any]:
-        if self.built_in:
+        if self.is_built_in:
             return {"type": self.type, **self.built_in_args, **kwargs}
         return {
             "type": "function",
@@ -349,7 +349,7 @@ class Tool(BaseModel):
 
     def for_anthropic(self, **kwargs) -> dict[str, Any]:
         # built-in tools have "name", "type", maybe metadata
-        if self.built_in:
+        if self.is_built_in:
             return {
                 "name": self.name,
                 "type": self.type,
@@ -392,6 +392,14 @@ class Tool(BaseModel):
             return self.for_google()
         raise ValueError(provider)
 
+    @classmethod
+    def built_in(cls, name: str, **kwargs):
+        if "type" in kwargs:
+            type = kwargs.pop("type")
+        else:
+            type = name
+        return cls(name=name, type=type, is_built_in=True, built_in_args=kwargs)
+
 
 class OpenAIMCPSpec(TypedDict):
     type: str

{lm_deluge-0.0.50 → lm_deluge-0.0.51/src/lm_deluge.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: lm_deluge
-Version: 0.0.50
+Version: 0.0.51
 Summary: Python utility for using LLM API models.
 Author-email: Benjamin Anderson <ben@trytaylor.ai>
 Requires-Python: >=3.10