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

{fast_agent_mcp-0.0.12.dist-info → fast_agent_mcp-0.0.14.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: fast-agent-mcp
-Version: 0.0.12
+Version: 0.0.14
 Summary: Define, Prompt and Test MCP enabled Agents and Workflows
 Author-email: Shaun Smith <fastagent@llmindset.co.uk>, Sarmad Qadri <sarmad@lastmileai.dev>
 License:                                  Apache License
@@ -247,13 +247,19 @@ Description-Content-Type: text/markdown
 
 ## Overview
 
-**`fast-agent`** lets you define, test and interact with agents, tools and workflows in minutes.
+**`fast-agent`** lets you build and interact with Agents and Workflows in minutes.
 
-The simple declarative syntax lets you concentrate on the prompts, MCP Servers and compositions to build effective agents.
+The simple declarative syntax lets you concentrate on composing your Prompts and MCP Servers to [build effective agents](https://www.anthropic.com/research/building-effective-agents).
 
-Quickly compare how different models perform at Agent and MCP Server calling tasks, and build mixed multi-model workflows using the best provider for each task.
+Evaluate how different models handle Agent and MCP Server calling tasks, then build multi-model workflows using the best provider for each task.
 
-### Get started:
+### Agent Application Development
+
+Prompts and configurations that define your Agent Applications are stored in simple files, with minimal boilerplate, enabling simple management and version control.
+
+Chat with individual Agents and Components before, during and after workflow execution to tune and diagnose your agent application. Simple model selection makes testing Model <-> MCP Server interaction painless.
+
+## Get started:
 
 Start by installing the [uv package manager](https://docs.astral.sh/uv/) for Python. Then:
 
@@ -265,10 +271,190 @@ uv run agent.py --model=o3-mini.low # specify a model
 fast-agent bootstrap workflow       # create "building effective agents" examples
 ```
 
-Other bootstrap examples include a Researcher (with Evaluator-Optimizer workflow) and Data Analysis (similar to ChatGPT experience), demonstrating MCP Roots support.
+Other bootstrap examples include a Researcher Agent (with Evaluator-Optimizer workflow) and Data Analysis Agent (similar to the ChatGPT experience), demonstrating MCP Roots support.
 
 > Windows Users - there are a couple of configuration changes needed for the Filesystem and Docker MCP Servers - necessary changes are detailed within the configuration files.
 
+### Basic Agents
+
+Defining an agent is as simple as:
+
+```python
+@fast.agent(
+  instruction="Given an object, respond only with an estimate of its size."
+)
+```
+
+We can then send messages to the Agent:
+
+```python
+async with fast.run() as agent:
+  moon_size = await agent("the moon")
+  print(moon_size)
+```
+
+Or start an interactive chat with the Agent:
+```python
+async with fast.run() as agent:  
+  await agent()
+```
+
+Here is the complete `sizer.py` Agent application, with boilerplate code:
+```python
+import asyncio
+from mcp_agent.core.fastagent import FastAgent
+
+# Create the application
+fast = FastAgent("Agent Example")
+
+@fast.agent(
+  instruction="Given an object, respond only with an estimate of its size."
+)
+
+async def main():
+  async with fast.run() as agent:
+    await agent()
+
+if __name__ == "__main__":
+    asyncio.run(main())
+```
+
+The Agent can be run with `uv run sizer.py` and with a specific model using the command line option `--model gpt-4o-mini`.
+
+### Combining Agents and using MCP Servers
+
+_To generate examples use `fast-agent bootstrap workflow`. This example can be run with `uv run chaining.py`. fast-agent looks for configuration files in the current directory before checking parent directories recursively._
+
+Agents can be chained to build a workflow:
+```python
+@fast.agent(
+    "url_fetcher",
+    instruction="Given a URL, provide a complete and comprehensive summary",
+    servers=["fetch"], # Name of an MCP Server defined in fastagent.config.yaml
+)
+@fast.agent(
+    "social_media",
+    instruction="""
+    Write a 280 character social media post for any given text.
+    Respond only with the post, never use hashtags.
+    """,
+)
+
+async def main():
+    async with fast.run() as agent:
+        await agent.social_media(
+            await agent.url_fetcher("http://llmindset.co.uk/resources/mcp-hfspace/")
+        )
+```
+
+All Agents and Workflows respond to `.send("message")` to send a message and `.prompt()` to begin a chat session. 
+
+## Workflows
+
+### Chain
+
+Alternatively, use the `chain` workflow type and the `prompt()` method to capture user input:
+```python
+
+@fast.chain(
+  "post_writer",
+  sequence=["url_fetcher","social_media"]
+)
+
+# we can them prompt it directly:
+async with fast.run() as agent:
+  await agent.post_writer.prompt()
+
+```
+Chains can be incorporated in other workflows, or contain other workflow elements (including other Chains). You can set an `instruction` to precisely describe it's capabilities to other workflow steps if needed.
+
+### Parallel
+
+The Parallel Workflow sends the same message to multiple Agents simultaneously (`fan-out`), then uses the `fan-in` agent to process the combined content. 
+
+```python
+
+@fast.agent(
+  name="consolidator"
+  instruction="combine the lists, remove duplicates"
+)
+
+@fast.parallel(
+  name="ensemble"
+  fan_out=["agent_o3-mini","agent_sonnet37",...]
+  fan_in="consolidator"
+)
+
+async with fast.run() as agent:
+  result = agent.ensemble.send("what are the 10 most important aspects of project management")
+```
+
+Look at the `parallel.py` workflow example for more details.
+
+### Evaluator-Optimizer
+
+Evaluator-Optimizers use 2 agents: one to generate content (the `generator`), and one to judge the content and provide actionable feedback (the `evaluator`). Messages are sent to the generator first, then the pair run in a loop until either the evaluator is satisfied with the quality, or the maximum number of refinements is reached.
+
+```python
+@fast.evaluator_optimizer(
+  name="researcher"
+  generator="web_searcher"
+  evaluator="quality_assurance"
+  min_rating="EXCELLENT"
+  max_refinements=3
+)
+
+async with fast.run() as agent:
+  await agent.researcher.send("produce a report on how to make the perfect espresso")
+```
+
+See the `evaluator.py` workflow example, or `fast-agent bootstrap researcher` for a more complete example. 
+
+### Router
+
+Routers use an LLM to assess a message, and route it to the most appropriate Agent direct . The routing prompt is automatically generated by the router.
+
+```python
+@fast.router(
+  name="route"
+  agents["agent1","agent2","agent3"]
+)
+```
+
+Look at the `router.py` workflow for an example.
+
+### Orchestrator
+
+Given a task, an Orchestrator uses an LLM to generate a plan to divide the task amongst the available agents and aggregate a result. The planning and aggregation prompts are generated by the Orchestrator, which benefits from using more capable models. Plans can either be built once at the beginning (`plantype="full"`) or iteratively (`plantype="iterative"`).  
+
+```python
+@fast.orchestrator(
+  name="orchestrate"
+  agents=["task1","task2","task3"]
+)
+```
+
+## Agent Features
+
+```python
+@fast.agent(
+  name="agent",
+  instructions="instructions",
+  servers=["filesystem"],     # list of MCP Servers for the agent, configured in fastagent.config.yaml
+  model="o3-mini.high",       # specify a model for the agent
+  use_history=True,           # agent can maintain chat history
+  human_input=True,           # agent can request human input
+)
+```
+
+### Human Input
+
+When `human_input` is set to true for an Agent, it is presented with the option to prompt the User for input.
+
+## Project Notes
+
+`fast-agent` builds on the [`mcp-agent`](https://github.com/lastmile-ai/mcp-agent) project by Sarmad Qadri.
+
 ### llmindset.co.uk fork:
 
 - "FastAgent" style prototyping, with per-agent models
@@ -286,10 +472,7 @@ Other bootstrap examples include a Researcher (with Evaluator-Optimizer workflow
 - Enhanced Human Input Messaging and Handling
 - Declarative workflows
 
-## Get Started
-
-We recommend using [uv](https://docs.astral.sh/uv/) to manage your Python projects:
+### Features to add.
 
-## Table of Contents
+ - Chat History Clear.
 
-We welcome any and all kinds of contributions. Please see the [CONTRIBUTING guidelines](./CONTRIBUTING.md) to get started.

{fast_agent_mcp-0.0.12.dist-info → fast_agent_mcp-0.0.14.dist-info}/RECORD

@@ -8,18 +8,18 @@ mcp_agent/event_progress.py,sha256=25iz0yyg-O4glMmtijcYpDdUmtUIKsCmR_8A52GgeC4,2
 mcp_agent/mcp_server_registry.py,sha256=5x30L1IlmC18JASl7NQbZYHMqPWS3ay0f_3U3uleaMM,9884
 mcp_agent/progress_display.py,sha256=GeJU9VUt6qKsFVymG688hCMVCsAygG9ifiiEb5IcbN4,361
 mcp_agent/agents/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-mcp_agent/agents/agent.py,sha256=utMR_QWKD1_MqWE_fYY-xqUMKtGlekW0laJfduU6Ckw,9831
+mcp_agent/agents/agent.py,sha256=losanPSdZXZzmeiX-J6ctOinLlkhNZsxwi3Swr8lnxA,11482
 mcp_agent/cli/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 mcp_agent/cli/__main__.py,sha256=bhxe66GYqy0q78OQhi7dkuubY1Tn0bQL6hU5Nn47E34,73
-mcp_agent/cli/main.py,sha256=h_TqBlpIMGhsJr6pp_oxUl00x3F9d1R-JQVwJ9uAreA,2449
+mcp_agent/cli/main.py,sha256=cqRxYTpeZ656lzf9qLR3LPnQXrFVDxlWm5gRuqyzUQg,2456
 mcp_agent/cli/terminal.py,sha256=5fqrKlJvIpKEuvpvZ653OueQSYFFktBEbosjr2ucMUc,1026
-mcp_agent/cli/commands/bootstrap.py,sha256=Q55I2gL-K3Ja8c6MmbLZMVQQ_MaOTxnEC5se09XTI2s,10742
+mcp_agent/cli/commands/bootstrap.py,sha256=z1wZSy8vO_GZPGLrFGzG3EKFQgAHC08jiIdVyylo-58,10778
 mcp_agent/cli/commands/config.py,sha256=32YTS5jmsYAs9QzAhjkG70_daAHqOemf4XbZBBSMz6g,204
-mcp_agent/cli/commands/setup.py,sha256=dI_01B5nye707Rcd15gvZZCYlZGSiKajlnuLf6hJf2A,6197
+mcp_agent/cli/commands/setup.py,sha256=8ofxUAF2nUSu1IarDZSAsTt6_6PoEht3TGbz9N6WSbs,6239
 mcp_agent/core/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-mcp_agent/core/enhanced_prompt.py,sha256=U4hbAbm5WFUwTiwmBlNR7nadbMD9oHYgKuNNQVrGdvc,11047
-mcp_agent/core/exceptions.py,sha256=xDdhYh83ni3t0NiXQTEL0_Yyx0qQxBPQL1gSwRToeaw,1469
-mcp_agent/core/fastagent.py,sha256=Wn5uHR6DIzMXu4S93Ll8oFD7VJUcSBH4wMm4c0aofpw,48858
+mcp_agent/core/enhanced_prompt.py,sha256=0V5q0xcCk8PBwtc0p62B8JJ1VvqxN_wuJiXC2QPqv1M,12750
+mcp_agent/core/exceptions.py,sha256=a2-JGRwFFRoQEPuAq0JC5PhAJ5TO3xVJfdS4-VN29cw,2225
+mcp_agent/core/fastagent.py,sha256=nMAOhxoS1KqV9IueIFpsYz7yZoVr2pNntI5FoHnzWFE,58011
 mcp_agent/core/server_validation.py,sha256=_59cn16nNT4HGPwg19HgxMtHK4MsdWYDUw_CuL-5xek,1696
 mcp_agent/eval/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 mcp_agent/executor/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
@@ -30,7 +30,7 @@ mcp_agent/executor/temporal.py,sha256=U-wyltgWlVmzJoyivT6rR0Z1U3S6TbMXpeCxyuXako
 mcp_agent/executor/workflow.py,sha256=lA6r7PNEvxCVFHp4XkEJkaR0QCTf-J6iw9JwNx-tzNY,6727
 mcp_agent/executor/workflow_signal.py,sha256=3PWwSgXhz3PhkA8SRX3u0BDVoSlQqRGqC9d1qLC25vE,11210
 mcp_agent/human_input/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-mcp_agent/human_input/handler.py,sha256=_gVIyvjDo53Aj8NFoKCiM8nBdQIuCxiStvgEtRBwYv8,1812
+mcp_agent/human_input/handler.py,sha256=37ERNg9OXaFgm4Ew-6aaU4y2jKre4VpekSnYZtRYFFI,2904
 mcp_agent/human_input/types.py,sha256=ZvuDHvI0-wO2tFoS0bzrv8U5B83zYdxAG7g9G9jCxug,1489
 mcp_agent/logging/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 mcp_agent/logging/events.py,sha256=qfYJnrqgXdujV-nl-iOwBEBh6HMraowBI4zeAWPPU4A,3461
@@ -46,7 +46,7 @@ mcp_agent/mcp/mcp_activity.py,sha256=CajXCFWZ2cKEX9s4-HfNVAj471ePTVs4NOkvmIh65tE
 mcp_agent/mcp/mcp_agent_client_session.py,sha256=NtWcQhjmnnaR3yYcYj2d2lh-m563NexZUa57K1tAjeM,9477
 mcp_agent/mcp/mcp_agent_server.py,sha256=xP09HZTeguJi4Fq0p3fjLBP55uSYe5AdqM90xCgn9Ho,1639
 mcp_agent/mcp/mcp_aggregator.py,sha256=RVsgNnSJ1IPBkqKgF_Gp-Cpv97FVBIdppPey6FRoHB0,14751
-mcp_agent/mcp/mcp_connection_manager.py,sha256=LH9ZmK-fXC-_7exAFclzWEjfFjwwdPqO_ZERqoHI_JM,13166
+mcp_agent/mcp/mcp_connection_manager.py,sha256=WLli0w3TVcsszyD9M7zP7vLKPetnQLTf_0PGhvMm9YM,13145
 mcp_agent/mcp/stdio.py,sha256=tW075R5rQ-UlflXWFKIFDgCbWbuhKqxhiYolWvyEkFs,3985
 mcp_agent/resources/examples/data-analysis/analysis.py,sha256=Sp-umPPfwVjG3yNrHdQA6blGtG6jc5of1e_0oS4njYc,1379
 mcp_agent/resources/examples/data-analysis/fastagent.config.yaml,sha256=eTKGbjnTHhDTeNRPQvG_fr9OQpEZ5Y9v7X2NyCj0V70,530
@@ -54,18 +54,16 @@ mcp_agent/resources/examples/data-analysis/mount-point/WA_Fn-UseC_-HR-Employee-A
 mcp_agent/resources/examples/internal/agent.py,sha256=f-jTgYabV3nWCQm0ZP9NtSEWjx3nQbRngzArRufcELg,384
 mcp_agent/resources/examples/internal/job.py,sha256=WEKIAANMEAuKr13__rYf3PqJeTAsNB_kqYqbqVYQlUM,4093
 mcp_agent/resources/examples/mcp_researcher/researcher-eval.py,sha256=kNPjIU-JwE0oIBQKwhv6lZsUF_SPtYVkiEEbY1ZVZxk,1807
-mcp_agent/resources/examples/mcp_researcher/researcher.py,sha256=jPRafm7jbpHKkX_dQiYGG3Sw-e1Dm86q-JZT-WZDhM0,1425
 mcp_agent/resources/examples/researcher/fastagent.config.yaml,sha256=2_VXZneckR6zk6RWzzL-smV_oWmgg4uSkLWqZv8jF0I,1995
 mcp_agent/resources/examples/researcher/researcher-eval.py,sha256=kNPjIU-JwE0oIBQKwhv6lZsUF_SPtYVkiEEbY1ZVZxk,1807
 mcp_agent/resources/examples/researcher/researcher.py,sha256=jPRafm7jbpHKkX_dQiYGG3Sw-e1Dm86q-JZT-WZDhM0,1425
-mcp_agent/resources/examples/workflows/agent.py,sha256=f-jTgYabV3nWCQm0ZP9NtSEWjx3nQbRngzArRufcELg,384
 mcp_agent/resources/examples/workflows/agent_build.py,sha256=vdjS02rZR88RU53WYzXxPscfFNEFFe_niHYE_i49I8Q,2396
-mcp_agent/resources/examples/workflows/chaining.py,sha256=QD_r_PKIoDedWqOTzg7IBnTY8OVoDSMot5WnArJubnc,751
-mcp_agent/resources/examples/workflows/evaluator.py,sha256=kC8uBcCMoeDROip4B_X6jLr-1QXXvcUB0fZ6elun7k4,3147
-mcp_agent/resources/examples/workflows/fastagent.py,sha256=lkO3waYLt_zQtAVqGjirmIsG73jpHA5ad1WSm4BXv2I,532
+mcp_agent/resources/examples/workflows/chaining.py,sha256=1G_0XBcFkSJCOXb6N_iXWlSc_oGAlhENR0k_CN1vJKI,1208
+mcp_agent/resources/examples/workflows/evaluator.py,sha256=FZy-ciZafdqSHUW67LKdHw0t9rvX6X67waMOoeIN3GY,3147
+mcp_agent/resources/examples/workflows/fastagent.config.yaml,sha256=k2AiapOcK42uqG2nWDVvnSLqN4okQIQZK0FTbZufBpY,809
 mcp_agent/resources/examples/workflows/human_input.py,sha256=c8cBdLEPbaMXddFwsfN3Z7RFs5PZXsdrjANfvq1VTPM,605
-mcp_agent/resources/examples/workflows/orchestrator.py,sha256=kHUDDALqjA8TRjkbsDP2MwspEj1a5DdSUOPAiI17izQ,2545
-mcp_agent/resources/examples/workflows/parallel.py,sha256=cNYcIcsdo0-KK-S7KEPCc11aWELeVlQJdJ2LIC9xgDs,3090
+mcp_agent/resources/examples/workflows/orchestrator.py,sha256=pRJqB-ok79_iEj8aG4FysHyXz6wAHLUX-5tS8khUI7k,2574
+mcp_agent/resources/examples/workflows/parallel.py,sha256=pLbQrtXfbdYqMVddxtg5dZnBnm5Wo2mXlIa1Vf2F1FQ,3096
 mcp_agent/resources/examples/workflows/router.py,sha256=XT_ewCrxPxdUTMCYQGw34qZQ3GGu8TYY_v5Lige8By4,1707
 mcp_agent/telemetry/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 mcp_agent/telemetry/usage_tracking.py,sha256=ePujKMSjPxB7k6X34DGaVlnsV1728mcWZq38OqahiCU,501
@@ -85,11 +83,11 @@ mcp_agent/workflows/intent_classifier/intent_classifier_llm.py,sha256=WSLUv2Casb
 mcp_agent/workflows/intent_classifier/intent_classifier_llm_anthropic.py,sha256=Hp4454IniWFxV4ml50Ml8ip9rS1La5FBn5pd7vm1FHA,1964
 mcp_agent/workflows/intent_classifier/intent_classifier_llm_openai.py,sha256=zj76WlTYnSCYjBQ_IDi5vFBQGmNwYaoUq1rT730sY98,1940
 mcp_agent/workflows/llm/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-mcp_agent/workflows/llm/augmented_llm.py,sha256=AjYxTn2XdBDHnibmjlCKwaVfQQlQRES9sRBMIU6NaPQ,23258
+mcp_agent/workflows/llm/augmented_llm.py,sha256=8D0hUePn47ChZrmUL8nt60u-iw09EFnJIV7wiQDd2fo,23362
 mcp_agent/workflows/llm/augmented_llm_anthropic.py,sha256=yrOv1V6rOfm2TTDR58fnf8YU8hBnTIpOZhB2sUgZw6o,21246
 mcp_agent/workflows/llm/augmented_llm_openai.py,sha256=5PwTh0QJSQ29EtK0UuiltgX6snRSBoau75C35S4xQcQ,24477
 mcp_agent/workflows/llm/llm_selector.py,sha256=G7pIybuBDwtmyxUDov_QrNYH2FoI0qFRu2JfoxWUF5Y,11045
-mcp_agent/workflows/llm/model_factory.py,sha256=5JrMXZ5jbE8isiteF2A912gGuCyomGpjtC_BCVSAM9s,6806
+mcp_agent/workflows/llm/model_factory.py,sha256=7zTJrO2ReHa_6dfh_gY6xO8dTySqGFCKlOG9-AMJ-i8,6920
 mcp_agent/workflows/orchestrator/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 mcp_agent/workflows/orchestrator/orchestrator.py,sha256=Fn5r0uUGNAiUq5NLFDjaJ04t19MnGEgr9iknbUj0DSA,14733
 mcp_agent/workflows/orchestrator/orchestrator_models.py,sha256=UWn7_HFLcqFGlcjZ1Rn2SYQfm5k9seS6QJN_FRST5Kc,4513
@@ -108,8 +106,8 @@ mcp_agent/workflows/swarm/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJW
 mcp_agent/workflows/swarm/swarm.py,sha256=-lAIeSWDqbGHGRPTvjiP9nIKWvxxy9DAojl9yQzO1Pw,11050
 mcp_agent/workflows/swarm/swarm_anthropic.py,sha256=pW8zFx5baUWGd5Vw3nIDF2oVOOGNorij4qvGJKdYPcs,1624
 mcp_agent/workflows/swarm/swarm_openai.py,sha256=wfteywvAGkT5bLmIxX_StHJq8144whYmCRnJASAjOes,1596
-fast_agent_mcp-0.0.12.dist-info/METADATA,sha256=mgH0wJrtVRReqKTn2a-ANc_reC_quUXY-texT2zGdVI,16583
-fast_agent_mcp-0.0.12.dist-info/WHEEL,sha256=qtCwoSJWgHk21S1Kb4ihdzI2rlJ1ZKaIurTj_ngOhyQ,87
-fast_agent_mcp-0.0.12.dist-info/entry_points.txt,sha256=2IXtSmDK9XjWN__RWuRIJTgWyW17wJnJ_h-pb0pZAxo,174
-fast_agent_mcp-0.0.12.dist-info/licenses/LICENSE,sha256=cN3FxDURL9XuzE5mhK9L2paZo82LTfjwCYVT7e3j0e4,10939
-fast_agent_mcp-0.0.12.dist-info/RECORD,,
+fast_agent_mcp-0.0.14.dist-info/METADATA,sha256=7qlGcDMbyR9SsI2Sx5bnSdZxrUmrGxptJLmSKVQm4l4,22080
+fast_agent_mcp-0.0.14.dist-info/WHEEL,sha256=qtCwoSJWgHk21S1Kb4ihdzI2rlJ1ZKaIurTj_ngOhyQ,87
+fast_agent_mcp-0.0.14.dist-info/entry_points.txt,sha256=2IXtSmDK9XjWN__RWuRIJTgWyW17wJnJ_h-pb0pZAxo,174
+fast_agent_mcp-0.0.14.dist-info/licenses/LICENSE,sha256=cN3FxDURL9XuzE5mhK9L2paZo82LTfjwCYVT7e3j0e4,10939
+fast_agent_mcp-0.0.14.dist-info/RECORD,,

mcp_agent/agents/agent.py

@@ -11,6 +11,7 @@ from mcp.types import (
     Tool,
 )
 
+from mcp_agent.core.exceptions import PromptExitError
 from mcp_agent.mcp.mcp_aggregator import MCPAggregator
 from mcp_agent.workflows.llm.augmented_llm import RequestParams
 from mcp_agent.human_input.types import (
@@ -24,6 +25,7 @@ from mcp_agent.logging.logger import get_logger
 
 if TYPE_CHECKING:
     from mcp_agent.context import Context
+import traceback
 
 logger = get_logger(__name__)
 
@@ -148,10 +150,7 @@ class Agent(MCPAggregator):
         """
         await super().close()
 
-    async def request_human_input(
-        self,
-        request: HumanInputRequest,
-    ) -> str:
+    async def request_human_input(self, request: HumanInputRequest) -> str:
         """
         Request input from a human user. Pauses the workflow until input is received.
 
@@ -170,14 +169,23 @@ class Agent(MCPAggregator):
         # Generate a unique ID for this request to avoid signal collisions
         request_id = f"{HUMAN_INPUT_SIGNAL_NAME}_{self.name}_{uuid.uuid4()}"
         request.request_id = request_id
-
+        # Use metadata as a dictionary to pass agent name
+        request.metadata = {"agent_name": self.name}
         self.logger.debug("Requesting human input:", data=request)
 
         async def call_callback_and_signal():
             try:
                 user_input = await self.human_input_callback(request)
+
                 self.logger.debug("Received human input:", data=user_input)
                 await self.executor.signal(signal_name=request_id, payload=user_input)
+            except PromptExitError as e:
+                # Propagate the exit error through the signal system
+                self.logger.info("User requested to exit session")
+                await self.executor.signal(
+                    signal_name=request_id,
+                    payload={"exit_requested": True, "error": str(e)},
+                )
             except Exception as e:
                 await self.executor.signal(
                     request_id, payload=f"Error getting human input: {str(e)}"
@@ -197,6 +205,10 @@ class Agent(MCPAggregator):
             signal_type=HumanInputResponse,  # TODO: saqadri - should this be HumanInputResponse?
         )
 
+        if isinstance(result, dict) and result.get("exit_requested", False):
+            raise PromptExitError(
+                result.get("error", "User requested to exit FastAgent session")
+            )
         self.logger.debug("Received human input signal", data=result)
         return result
 
@@ -253,13 +265,39 @@ class Agent(MCPAggregator):
     ) -> CallToolResult:
         # Handle human input request
         try:
-            request = HumanInputRequest(**arguments.get("request"))
-            result: HumanInputResponse = await self.request_human_input(request=request)
+            # Make sure arguments is not None
+            if arguments is None:
+                arguments = {}
+
+            # Extract request data
+            request_data = arguments.get("request")
+
+            # Handle both string and dict request formats
+            if isinstance(request_data, str):
+                request = HumanInputRequest(prompt=request_data)
+            elif isinstance(request_data, dict):
+                request = HumanInputRequest(**request_data)
+            else:
+                # Fallback for invalid or missing request data
+                request = HumanInputRequest(prompt="Please provide input:")
+
+            result = await self.request_human_input(request=request)
+
+            # Use response attribute if available, otherwise use the result directly
+            response_text = (
+                result.response
+                if isinstance(result, HumanInputResponse)
+                else str(result)
+            )
+
             return CallToolResult(
                 content=[
-                    TextContent(type="text", text=f"Human response: {result.response}")
+                    TextContent(type="text", text=f"Human response: {response_text}")
                 ]
             )
+
+        except PromptExitError:
+            raise
         except TimeoutError as e:
             return CallToolResult(
                 isError=True,
@@ -271,6 +309,8 @@ class Agent(MCPAggregator):
                 ],
             )
         except Exception as e:
+            print(f"Error in _call_human_input_tool: {traceback.format_exc()}")
+
             return CallToolResult(
                 isError=True,
                 content=[

mcp_agent/cli/commands/bootstrap.py

@@ -26,8 +26,9 @@ EXAMPLE_TYPES = {
             "orchestrator.py",
             "parallel.py",
             "router.py",
+            "fastagent.config.yaml",
         ],
-        "create_subdir": False,
+        "create_subdir": True,
     },
     "researcher": {
         "description": "Research agent example with additional evaluation/optimization\n"

mcp_agent/cli/commands/setup.py

@@ -119,7 +119,7 @@ fast = FastAgent("FastAgent Example")
 
 
 # Define the agent
-@fast.agent(servers=["fetch"])
+@fast.agent(instruction="You are a helpful AI Agent", servers=["fetch"])
 async def main():
     # use the --model command line switch or agent arguments to change model
     async with fast.run() as agent:

mcp_agent/cli/main.py

@@ -32,7 +32,7 @@ def show_welcome():
 
     table.add_row("setup", "Set up a new agent project with configuration files")
     table.add_row(
-        "bootstrap", "Create example applications (decorator, researcher, etc.)"
+        "bootstrap", "Create example applications (workflow, researcher, etc.)"
     )
     # table.add_row("config", "Manage agent configuration settings")
 
@@ -41,8 +41,8 @@ def show_welcome():
     console.print("\n[bold]Getting Started:[/bold]")
     console.print("1. Set up a new project:")
     console.print("   fastagent setup")
-    console.print("\n2. Try an example:")
-    console.print("   fastagent bootstrap create decorator")
+    console.print("\n2. Try an example workflow:")
+    console.print("   fastagent bootstrap create workflow")
     console.print("\nUse --help with any command for more information")
     console.print("Example: fastagent bootstrap --help")