fast-agent-mcp 0.1.12__py3-none-any.whl → 0.1.13__py3-none-any.whl

mcp_agent/workflows/intent_classifier/intent_classifier_embedding_cohere.py

@@ -1,4 +1,4 @@
-from typing import List, Optional, TYPE_CHECKING
+from typing import TYPE_CHECKING, List, Optional
 
 from mcp_agent.workflows.embedding.embedding_cohere import CohereEmbeddingModel
 from mcp_agent.workflows.intent_classifier.intent_classifier_base import Intent
@@ -21,11 +21,9 @@ class CohereEmbeddingIntentClassifier(EmbeddingIntentClassifier):
         embedding_model: CohereEmbeddingModel | None = None,
         context: Optional["Context"] = None,
         **kwargs,
-    ):
+    ) -> None:
         embedding_model = embedding_model or CohereEmbeddingModel()
-        super().__init__(
-            embedding_model=embedding_model, intents=intents, context=context, **kwargs
-        )
+        super().__init__(embedding_model=embedding_model, intents=intents, context=context, **kwargs)
 
     @classmethod
     async def create(
@@ -38,8 +36,6 @@ class CohereEmbeddingIntentClassifier(EmbeddingIntentClassifier):
         Factory method to create and initialize a classifier.
         Use this instead of constructor since we need async initialization.
         """
-        instance = cls(
-            intents=intents, embedding_model=embedding_model, context=context
-        )
+        instance = cls(intents=intents, embedding_model=embedding_model, context=context)
         await instance.initialize()
         return instance

mcp_agent/workflows/intent_classifier/intent_classifier_embedding_openai.py

@@ -1,4 +1,4 @@
-from typing import List, Optional, TYPE_CHECKING
+from typing import TYPE_CHECKING, List, Optional
 
 from mcp_agent.workflows.embedding.embedding_openai import OpenAIEmbeddingModel
 from mcp_agent.workflows.intent_classifier.intent_classifier_base import Intent
@@ -21,11 +21,9 @@ class OpenAIEmbeddingIntentClassifier(EmbeddingIntentClassifier):
         embedding_model: OpenAIEmbeddingModel | None = None,
         context: Optional["Context"] = None,
         **kwargs,
-    ):
+    ) -> None:
         embedding_model = embedding_model or OpenAIEmbeddingModel()
-        super().__init__(
-            embedding_model=embedding_model, intents=intents, context=context, **kwargs
-        )
+        super().__init__(embedding_model=embedding_model, intents=intents, context=context, **kwargs)
 
     @classmethod
     async def create(
@@ -38,8 +36,6 @@ class OpenAIEmbeddingIntentClassifier(EmbeddingIntentClassifier):
         Factory method to create and initialize a classifier.
         Use this instead of constructor since we need async initialization.
         """
-        instance = cls(
-            intents=intents, embedding_model=embedding_model, context=context
-        )
+        instance = cls(intents=intents, embedding_model=embedding_model, context=context)
         await instance.initialize()
         return instance

mcp_agent/workflows/intent_classifier/intent_classifier_llm.py

@@ -1,12 +1,13 @@
-from typing import List, Literal, Optional, TYPE_CHECKING
+from typing import TYPE_CHECKING, List, Literal, Optional
+
 from pydantic import BaseModel
 
-from mcp_agent.workflows.llm.augmented_llm import AugmentedLLM
 from mcp_agent.workflows.intent_classifier.intent_classifier_base import (
     Intent,
-    IntentClassifier,
     IntentClassificationResult,
+    IntentClassifier,
 )
+from mcp_agent.workflows.llm.augmented_llm import AugmentedLLM
 
 if TYPE_CHECKING:
     from mcp_agent.context import Context
@@ -75,7 +76,7 @@ class LLMIntentClassifier(IntentClassifier):
         classification_instruction: str | None = None,
         context: Optional["Context"] = None,
         **kwargs,
-    ):
+    ) -> None:
         super().__init__(intents=intents, context=context, **kwargs)
         self.llm = llm
         self.classification_instruction = classification_instruction
@@ -99,28 +100,20 @@ class LLMIntentClassifier(IntentClassifier):
         await instance.initialize()
         return instance
 
-    async def classify(
-        self, request: str, top_k: int = 1
-    ) -> List[LLMIntentClassificationResult]:
+    async def classify(self, request: str, top_k: int = 1) -> List[LLMIntentClassificationResult]:
         if not self.initialized:
             self.initialize()
 
-        classification_instruction = (
-            self.classification_instruction or DEFAULT_INTENT_CLASSIFICATION_INSTRUCTION
-        )
+        classification_instruction = self.classification_instruction or DEFAULT_INTENT_CLASSIFICATION_INSTRUCTION
 
         # Generate the context with intent descriptions and examples
         context = self._generate_context()
 
         # Format the prompt with all the necessary information
-        prompt = classification_instruction.format(
-            context=context, request=request, top_k=top_k
-        )
+        prompt = classification_instruction.format(context=context, request=request, top_k=top_k)
 
         # Get classification from LLM
-        response = await self.llm.generate_structured(
-            message=prompt, response_model=StructuredIntentResponse
-        )
+        response = await self.llm.generate_structured(message=prompt, response_model=StructuredIntentResponse)
 
         if not response or not response.classifications:
             return []
@@ -142,18 +135,14 @@ class LLMIntentClassifier(IntentClassifier):
         context_parts = []
 
         for idx, intent in enumerate(self.intents.values(), 1):
-            description = (
-                f"{idx}. Intent: {intent.name}\nDescription: {intent.description}"
-            )
+            description = f"{idx}. Intent: {intent.name}\nDescription: {intent.description}"
 
             if intent.examples:
                 examples = "\n".join(f"- {example}" for example in intent.examples)
                 description += f"\nExamples:\n{examples}"
 
             if intent.metadata:
-                metadata = "\n".join(
-                    f"- {key}: {value}" for key, value in intent.metadata.items()
-                )
+                metadata = "\n".join(f"- {key}: {value}" for key, value in intent.metadata.items())
                 description += f"\nAdditional Information:\n{metadata}"
 
             context_parts.append(description)

mcp_agent/workflows/intent_classifier/intent_classifier_llm_anthropic.py

@@ -1,10 +1,10 @@
-from typing import List, Optional, TYPE_CHECKING
+from typing import TYPE_CHECKING, List, Optional
 
-from mcp_agent.workflows.llm.augmented_llm_anthropic import AnthropicAugmentedLLM
 from mcp_agent.workflows.intent_classifier.intent_classifier_base import Intent
 from mcp_agent.workflows.intent_classifier.intent_classifier_llm import (
     LLMIntentClassifier,
 )
+from mcp_agent.workflows.llm.augmented_llm_anthropic import AnthropicAugmentedLLM
 
 if TYPE_CHECKING:
     from mcp_agent.context import Context
@@ -27,7 +27,7 @@ class AnthropicLLMIntentClassifier(LLMIntentClassifier):
         classification_instruction: str | None = None,
         context: Optional["Context"] = None,
         **kwargs,
-    ):
+    ) -> None:
         anthropic_llm = AnthropicAugmentedLLM(
             instruction=CLASSIFIER_SYSTEM_INSTRUCTION, context=context
         )

mcp_agent/workflows/intent_classifier/intent_classifier_llm_openai.py

@@ -1,10 +1,10 @@
-from typing import List, Optional, TYPE_CHECKING
+from typing import TYPE_CHECKING, List, Optional
 
-from mcp_agent.workflows.llm.augmented_llm_openai import OpenAIAugmentedLLM
 from mcp_agent.workflows.intent_classifier.intent_classifier_base import Intent
 from mcp_agent.workflows.intent_classifier.intent_classifier_llm import (
     LLMIntentClassifier,
 )
+from mcp_agent.workflows.llm.augmented_llm_openai import OpenAIAugmentedLLM
 
 if TYPE_CHECKING:
     from mcp_agent.context import Context
@@ -27,10 +27,8 @@ class OpenAILLMIntentClassifier(LLMIntentClassifier):
         classification_instruction: str | None = None,
         context: Optional["Context"] = None,
         **kwargs,
-    ):
-        openai_llm = OpenAIAugmentedLLM(
-            instruction=CLASSIFIER_SYSTEM_INSTRUCTION, context=context
-        )
+    ) -> None:
+        openai_llm = OpenAIAugmentedLLM(instruction=CLASSIFIER_SYSTEM_INSTRUCTION, context=context)
 
         super().__init__(
             llm=openai_llm,

mcp_agent/workflows/llm/anthropic_utils.py

@@ -8,11 +8,10 @@ leveraging existing code for resource handling and delimited formats.
 from anthropic.types import (
     MessageParam,
 )
-
 from mcp.types import (
-    TextContent,
-    ImageContent,
     EmbeddedResource,
+    ImageContent,
+    TextContent,
     TextResourceContents,
 )
 
@@ -37,9 +36,7 @@ def anthropic_message_param_to_prompt_message_multipart(
 
     # Handle string content (user messages can be simple strings)
     if isinstance(content, str):
-        return PromptMessageMultipart(
-            role=role, content=[TextContent(type="text", text=content)]
-        )
+        return PromptMessageMultipart(role=role, content=[TextContent(type="text", text=content)])
 
     # Convert content blocks to MCP content types
     mcp_contents = []
@@ -50,29 +47,13 @@ def anthropic_message_param_to_prompt_message_multipart(
                 text = block.get("text", "")
 
                 # Check if this is a resource marker
-                if (
-                    text
-                    and (
-                        text.startswith("[Resource:")
-                        or text.startswith("[Binary Resource:")
-                    )
-                    and "\n" in text
-                ):
+                if text and (text.startswith("[Resource:") or text.startswith("[Binary Resource:")) and "\n" in text:
                     header, content_text = text.split("\n", 1)
                     if "MIME:" in header:
                         mime_match = header.split("MIME:", 1)[1].split("]")[0].strip()
-                        if (
-                            mime_match != "text/plain"
-                        ):  # Only process non-plain text resources
-                            if (
-                                "Resource:" in header
-                                and "Binary Resource:" not in header
-                            ):
-                                uri = (
-                                    header.split("Resource:", 1)[1]
-                                    .split(",")[0]
-                                    .strip()
-                                )
+                        if mime_match != "text/plain":  # Only process non-plain text resources
+                            if "Resource:" in header and "Binary Resource:" not in header:
+                                uri = header.split("Resource:", 1)[1].split(",")[0].strip()
                                 mcp_contents.append(
                                     EmbeddedResource(
                                         type="resource",
@@ -94,8 +75,6 @@ def anthropic_message_param_to_prompt_message_multipart(
                 if isinstance(source, dict) and source.get("type") == "base64":
                     media_type = source.get("media_type", "image/png")
                     data = source.get("data", "")
-                    mcp_contents.append(
-                        ImageContent(type="image", data=data, mimeType=media_type)
-                    )
+                    mcp_contents.append(ImageContent(type="image", data=data, mimeType=media_type))
 
     return PromptMessageMultipart(role=role, content=mcp_contents)