fast-agent-mcp 0.0.12__py3-none-any.whl → 0.0.14__py3-none-any.whl

mcp_agent/resources/examples/workflows/chaining.py

@@ -17,13 +17,27 @@ fast = FastAgent("Agent Chaining")
     Respond only with the post, never use hashtags.
     """,
 )
+@fast.chain(
+    name="post_writer",
+    sequence=["url_fetcher", "social_media"],
+)
 async def main():
     async with fast.run() as agent:
-        await agent.social_media(
-            await agent.url_fetcher("http://llmindset.co.uk/resources/mcp-hfspace/")
-        )
+        # using chain workflow
+        await agent.post_writer.prompt()
+
+        # calling directly
+        # await agent.url_fetcher("http://llmindset.co.uk/resources/mcp-hfspace/")
+        # await agent.social_media(
+        #     await agent.url_fetcher("http://llmindset.co.uk/resources/mcp-hfspace/")
+        # )
+
+        # agents can also be accessed like dictionaries:
+        # awwait agent["post_writer"].prompt()
+
 
-    # alternative syntax for above is agent["social_media"].send(message)
+# alternative syntax for above is result = agent["post_writer"].send(message)
+# alternative syntax for above is result = agent["post_writer"].prompt()
 
 
 if __name__ == "__main__":

mcp_agent/resources/examples/workflows/evaluator.py

@@ -9,7 +9,7 @@ from mcp_agent.core.fastagent import FastAgent
 fast = FastAgent("Evaluator-Optimizer")
 
 
-# Define optimizer agent
+# Define generator agent
 @fast.agent(
     name="generator",
     instruction="""You are a career coach specializing in cover letter writing.
@@ -44,7 +44,7 @@ fast = FastAgent("Evaluator-Optimizer")
 # Define the evaluator-optimizer workflow
 @fast.evaluator_optimizer(
     name="cover_letter_writer",
-    generator="generator",  # Reference to optimizer agent
+    generator="generator",  # Reference to generator agent
     evaluator="evaluator",  # Reference to evaluator agent
     min_rating="EXCELLENT",  # Strive for excellence
     max_refinements=3,  # Maximum iterations

mcp_agent/resources/examples/workflows/fastagent.config.yaml

@@ -0,0 +1,24 @@
+# Please edit this configuration file to match your environment (on Windows).
+# Examples in comments below - check/change the paths.
+#
+#
+
+execution_engine: asyncio
+logger:
+  type: file
+  level: error
+  truncate_tools: true
+
+mcp:
+  servers:
+    filesystem:
+      # On windows update the command and arguments to use `node` and the absolute path to the server.
+      # Use `npm i -g @modelcontextprotocol/server-filesystem` to install the server globally.
+      # Use `npm -g root` to find the global node_modules path.`
+      # command: "node"
+      # args: ["c:/Program Files/nodejs/node_modules/@modelcontextprotocol/server-filesystem/dist/index.js","."]
+      command: "npx"
+      args: ["-y", "@modelcontextprotocol/server-filesystem", "."]
+    fetch:
+      command: "uvx"
+      args: ["mcp-server-fetch"]

mcp_agent/resources/examples/workflows/orchestrator.py

@@ -45,10 +45,11 @@ fast = FastAgent("Orchestrator-Workers")
 @fast.orchestrator(
     name="orchestrate",
     agents=["finder", "writer", "proofreader"],
-    model="sonnet",
+    plan_type="iterative",
 )
 async def main():
     async with fast.run() as agent:
+
         await agent.author(
             "write a 250 word short story about kittens discovering a castle, and save it to short_story.md"
         )
@@ -65,7 +66,7 @@ async def main():
 
         # Send the task
         await agent.orchestrate(task)
-
+        await agent()
 
 if __name__ == "__main__":
     asyncio.run(main())

mcp_agent/resources/examples/workflows/parallel.py

@@ -69,8 +69,9 @@ async def main():
     # Use the app's context manager
     async with fast.run() as agent:
         await agent.parallel(f"student short story submission: {SHORT_STORY}")
+
         # follow-on prompt to task agent
-        # await agent.style_enforcer.prompt(default="STOP")
+        await agent.style_enforcer.prompt(default_prompt="STOP")
 
 
 if __name__ == "__main__":

mcp_agent/workflows/llm/augmented_llm.py

@@ -15,6 +15,7 @@ from mcp.types import (
 )
 
 from mcp_agent.context_dependent import ContextDependent
+from mcp_agent.core.exceptions import PromptExitError
 from mcp_agent.event_progress import ProgressAction
 from mcp_agent.mcp.mcp_aggregator import MCPAggregator, SEP
 from mcp_agent.workflows.llm.llm_selector import ModelSelector
@@ -608,6 +609,8 @@ class AugmentedLLM(ContextDependent, AugmentedLLMProtocol[MessageParamT, Message
                 result = postprocess
 
             return result
+        except PromptExitError:
+            raise
         except Exception as e:
             return CallToolResult(
                 isError=True,

mcp_agent/workflows/llm/model_factory.py

@@ -3,6 +3,7 @@ from enum import Enum, auto
 from typing import Optional, Type, Dict, Union, Callable
 
 from mcp_agent.agents.agent import Agent
+from mcp_agent.core.exceptions import ModelConfigError
 from mcp_agent.workflows.llm.augmented_llm_anthropic import AnthropicAugmentedLLM
 from mcp_agent.workflows.llm.augmented_llm_openai import OpenAIAugmentedLLM
 from mcp_agent.workflows.llm.augmented_llm import RequestParams
@@ -53,6 +54,7 @@ class ModelFactory:
 
     # TODO -- add context window size information for display/mmanagement
     # TODO -- add audio supporting got-4o-audio-preview
+    # TODO -- bring model parameter configuration here
     # Mapping of model names to their default providers
     DEFAULT_PROVIDERS = {
         "gpt-4o": Provider.OPENAI,
@@ -80,6 +82,7 @@ class ModelFactory:
         "claude": "claude-3-5-sonnet-latest",
         "haiku": "claude-3-5-haiku-latest",
         "haiku3": "claude-3-haiku-20240307",
+        "haiku35": "claude-3-5-haiku-latest",
         "opus": "claude-3-opus-latest",
         "opus3": "claude-3-opus-latest",
     }
@@ -121,7 +124,7 @@ class ModelFactory:
         if provider is None:
             provider = cls.DEFAULT_PROVIDERS.get(model_name)
             if provider is None:
-                raise ValueError(f"Unknown model: {model_name}")
+                raise ModelConfigError(f"Unknown model: {model_name}")
 
         return ModelConfig(
             provider=provider, model_name=model_name, reasoning_effort=reasoning_effort
@@ -173,16 +176,16 @@ class ModelFactory:
                 "request_params": factory_params,
                 "name": kwargs.get("name"),
             }
-            
+
             # Add reasoning effort if available
             if config.reasoning_effort:
                 llm_args["reasoning_effort"] = config.reasoning_effort.value
-                
+
             # Forward all other kwargs (including verb)
             for key, value in kwargs.items():
                 if key not in ["agent", "default_request_params", "name"]:
                     llm_args[key] = value
-                    
+
             llm = llm_class(**llm_args)
             return llm
 

mcp_agent/resources/examples/mcp_researcher/researcher.py

@@ -1,38 +0,0 @@
-import asyncio
-
-from mcp_agent.core.fastagent import FastAgent
-# from rich import print
-
-agents = FastAgent(name="Researcher")
-
-
-@agents.agent(
-    "Researcher",
-    instruction="""
-You are a research assistant, with access to internet search (via Brave),
-website fetch, a python interpreter (you can install packages with uv) and a filesystem.
-Use the current working directory to save and create files with both the Interpreter and Filesystem tools.
-The interpreter has numpy, pandas, matplotlib and seaborn already installed
-    """,
-    servers=["brave", "interpreter", "filesystem", "fetch"],
-)
-async def main():
-    research_prompt = """
-Produce an investment report for the company Eutelsat. The final report should be saved in the filesystem in markdown format, and
-contain at least the following: 
-1 - A brief description of the company
-2 - Current financial position (find data, create and incorporate charts)
-3 - A PESTLE analysis
-4 - An investment thesis for the next 3 years. Include both 'buy side' and 'sell side' arguments, and a final 
-summary and recommendation.
-Todays date is 15 February 2025. Include the main data sources consulted in presenting the report."""  # noqa: F841
-
-    async with agents.run() as agent:
-        await agent.prompt()
-
-        # await agent.prompt(default="STOP")
-        #        await agent.prompt(default=research_prompt)
-
-
-if __name__ == "__main__":
-    asyncio.run(main())

mcp_agent/resources/examples/workflows/agent.py

@@ -1,17 +0,0 @@
-import asyncio
-from mcp_agent.core.fastagent import FastAgent
-
-# Create the application
-fast = FastAgent("FastAgent Example")
-
-
-# Define the agent
-@fast.agent(servers=["fetch"])
-async def main():
-    # use the --model command line switch or agent arguments to change model
-    async with fast.run() as agent:
-        await agent()
-
-
-if __name__ == "__main__":
-    asyncio.run(main())

mcp_agent/resources/examples/workflows/fastagent.py

@@ -1,22 +0,0 @@
-import asyncio
-from mcp_agent.core.fastagent import FastAgent
-
-# Create the application
-agent_app = FastAgent("FastAgent Example")
-# Uncomment the below to disable human input callback tool
-# agent_app.app._human_input_callback = None
-
-
-# Define the agent
-@agent_app.agent(
-    instruction="You are a helpful AI Agent",
-    servers=[],
-)
-async def main():
-    # use the --model= command line switch to specify model
-    async with agent_app.run() as agent:
-        await agent()
-
-
-if __name__ == "__main__":
-    asyncio.run(main())