Upload 15 files

.gitignore

@@ -0,0 +1,8 @@
+__pycache__
+.env
+
+.DS_Store
+.venv
+
+env
+.gradio/*

Gradio_UI.py

@@ -19,7 +19,12 @@ import re
 import shutil
 from typing import Optional
 
-from smolagents.agent_types import AgentAudio, AgentImage, AgentText, handle_agent_output_types
+from smolagents.agent_types import (
+    AgentAudio,
+    AgentImage,
+    AgentText,
+    handle_agent_output_types,
+)
 from smolagents.agents import ActionStep, MultiStepAgent
 from smolagents.memory import MemoryStep
 from smolagents.utils import _is_package_available
@@ -33,7 +38,9 @@ def pull_messages_from_step(
 
     if isinstance(step_log, ActionStep):
         # Output the step number
-        step_number = f"Step {step_log.step_number}" if step_log.step_number is not None else ""
+        step_number = (
+            f"Step {step_log.step_number}" if step_log.step_number is not None else ""
+        )
         yield gr.ChatMessage(role="assistant", content=f"**{step_number}**")
 
         # First yield the thought/reasoning from the LLM
@@ -41,9 +48,15 @@ def pull_messages_from_step(
             # Clean up the LLM output
             model_output = step_log.model_output.strip()
             # Remove any trailing <end_code> and extra backticks, handling multiple possible formats
-            model_output = re.sub(r"```\s*<end_code>", "```", model_output)  # handles ```<end_code>
-            model_output = re.sub(r"<end_code>\s*```", "```", model_output)  # handles <end_code>```
-            model_output = re.sub(r"```\s*\n\s*<end_code>", "```", model_output)  # handles ```\n<end_code>
+            model_output = re.sub(
+                r"```\s*<end_code>", "```", model_output
+            )  # handles ```<end_code>
+            model_output = re.sub(
+                r"<end_code>\s*```", "```", model_output
+            )  # handles <end_code>```
+            model_output = re.sub(
+                r"```\s*\n\s*<end_code>", "```", model_output
+            )  # handles ```\n<end_code>
             model_output = model_output.strip()
             yield gr.ChatMessage(role="assistant", content=model_output)
 
@@ -63,8 +76,12 @@ def pull_messages_from_step(
 
             if used_code:
                 # Clean up the content by removing any end code tags
-                content = re.sub(r"```.*?\n", "", content)  # Remove existing code blocks
-                content = re.sub(r"\s*<end_code>\s*", "", content)  # Remove end_code tags
+                content = re.sub(
+                    r"```.*?\n", "", content
+                )  # Remove existing code blocks
+                content = re.sub(
+                    r"\s*<end_code>\s*", "", content
+                )  # Remove end_code tags
                 content = content.strip()
                 if not content.startswith("```python"):
                     content = f"```python\n{content}\n```"
@@ -90,7 +107,11 @@ def pull_messages_from_step(
                     yield gr.ChatMessage(
                         role="assistant",
                         content=f"{log_content}",
-                        metadata={"title": "📝 Execution Logs", "parent_id": parent_id, "status": "done"},
+                        metadata={
+                            "title": "📝 Execution Logs",
+                            "parent_id": parent_id,
+                            "status": "done",
+                        },
                     )
 
             # Nesting any errors under the tool call
@@ -98,7 +119,11 @@ def pull_messages_from_step(
                 yield gr.ChatMessage(
                     role="assistant",
                     content=str(step_log.error),
-                    metadata={"title": "💥 Error", "parent_id": parent_id, "status": "done"},
+                    metadata={
+                        "title": "💥 Error",
+                        "parent_id": parent_id,
+                        "status": "done",
+                    },
                 )
 
             # Update parent message metadata to done status without yielding a new message
@@ -106,17 +131,25 @@ def pull_messages_from_step(
 
         # Handle standalone errors but not from tool calls
         elif hasattr(step_log, "error") and step_log.error is not None:
-            yield gr.ChatMessage(role="assistant", content=str(step_log.error), metadata={"title": "💥 Error"})
+            yield gr.ChatMessage(
+                role="assistant",
+                content=str(step_log.error),
+                metadata={"title": "💥 Error"},
+            )
 
         # Calculate duration and token information
         step_footnote = f"{step_number}"
-        if hasattr(step_log, "input_token_count") and hasattr(step_log, "output_token_count"):
-            token_str = (
-                f" | Input-tokens:{step_log.input_token_count:,} | Output-tokens:{step_log.output_token_count:,}"
-            )
+        if hasattr(step_log, "input_token_count") and hasattr(
+            step_log, "output_token_count"
+        ):
+            token_str = f" | Input-tokens:{step_log.input_token_count:,} | Output-tokens:{step_log.output_token_count:,}"
             step_footnote += token_str
         if hasattr(step_log, "duration"):
-            step_duration = f" | Duration: {round(float(step_log.duration), 2)}" if step_log.duration else None
+            step_duration = (
+                f" | Duration: {round(float(step_log.duration), 2)}"
+                if step_log.duration
+                else None
+            )
             step_footnote += step_duration
         step_footnote = f"""<span style="color: #bbbbc2; font-size: 12px;">{step_footnote}</span> """
         yield gr.ChatMessage(role="assistant", content=f"{step_footnote}")
@@ -139,7 +172,9 @@ def stream_to_gradio(
     total_input_tokens = 0
     total_output_tokens = 0
 
-    for step_log in agent.run(task, stream=True, reset=reset_agent_memory, additional_args=additional_args):
+    for step_log in agent.run(
+        task, stream=True, reset=reset_agent_memory, additional_args=additional_args
+    ):
         # Track tokens if model provides them
         if hasattr(agent.model, "last_input_token_count"):
             total_input_tokens += agent.model.last_input_token_count
@@ -172,19 +207,27 @@ def stream_to_gradio(
             content={"path": final_answer.to_string(), "mime_type": "audio/wav"},
         )
     else:
-        yield gr.ChatMessage(role="assistant", content=f"**Final answer:** {str(final_answer)}")
+        yield gr.ChatMessage(
+            role="assistant", content=f"**Final answer:** {str(final_answer)}"
+        )
 
 
 class GradioUI:
     """A one-line interface to launch your agent in Gradio"""
 
-    def __init__(self, agent: MultiStepAgent, file_upload_folder: str | None = None):
+    def __init__(
+        self,
+        agent: MultiStepAgent,
+        file_upload_folder: str | None = None,
+        initial_message=None,
+    ):
         if not _is_package_available("gradio"):
             raise ModuleNotFoundError(
                 "Please install 'gradio' extra to use the GradioUI: `pip install 'smolagents[gradio]'`"
             )
         self.agent = agent
         self.file_upload_folder = file_upload_folder
+        self.initial_message = initial_message
         if self.file_upload_folder is not None:
             if not os.path.exists(file_upload_folder):
                 os.mkdir(file_upload_folder)
@@ -242,10 +285,14 @@ class GradioUI:
         sanitized_name = "".join(sanitized_name)
 
         # Save the uploaded file to the specified folder
-        file_path = os.path.join(self.file_upload_folder, os.path.basename(sanitized_name))
+        file_path = os.path.join(
+            self.file_upload_folder, os.path.basename(sanitized_name)
+        )
         shutil.copy(file.name, file_path)
 
-        return gr.Textbox(f"File uploaded: {file_path}", visible=True), file_uploads_log + [file_path]
+        return gr.Textbox(
+            f"File uploaded: {file_path}", visible=True
+        ), file_uploads_log + [file_path]
 
     def log_user_message(self, text_input, file_uploads_log):
         return (
@@ -262,11 +309,17 @@ class GradioUI:
         import gradio as gr
 
         with gr.Blocks(fill_height=True) as demo:
+            gr.State(self.initial_message)
             stored_messages = gr.State([])
             file_uploads_log = gr.State([])
             chatbot = gr.Chatbot(
                 label="Agent",
                 type="messages",
+                value=(
+                    [{"role": "assistant", "content": self.initial_message}]
+                    if self.initial_message
+                    else []
+                ),
                 avatar_images=(
                     None,
                     "https://huggingface.co/datasets/agents-course/course-images/resolve/main/en/communication/Alfred.png",
@@ -277,13 +330,19 @@ class GradioUI:
             # If an upload folder is provided, enable the upload feature
             if self.file_upload_folder is not None:
                 upload_file = gr.File(label="Upload a file")
-                upload_status = gr.Textbox(label="Upload Status", interactive=False, visible=False)
+                upload_status = gr.Textbox(
+                    label="Upload Status", interactive=False, visible=False
+                )
                 upload_file.change(
                     self.upload_file,
                     [upload_file, file_uploads_log],
                     [upload_status, file_uploads_log],
                 )
-            text_input = gr.Textbox(lines=1, label="Chat Message")
+            text_input = gr.Textbox(
+                submit_btn="Start the ritual of code analysis",
+                lines=10,
+                label="Sacred Code wrapped in ```python ``` click on button to start the ritual of code analysis, shift+enter also works as submit",
+            )
             text_input.submit(
                 self.log_user_message,
                 [text_input, file_uploads_log],
@@ -293,4 +352,4 @@ class GradioUI:
         demo.launch(debug=True, share=True, **kwargs)
 
 
-__all__ = ["stream_to_gradio", "GradioUI"]
+__all__ = ["stream_to_gradio", "GradioUI"]

README.md

@@ -1,18 +1,86 @@
 ---
-title: First Agent Template
-emoji: ⚡
-colorFrom: pink
-colorTo: yellow
+title: The Omnissiah's Mandate
+emoji: ⚙️
+colorFrom: red
+colorTo: gray
 sdk: gradio
 sdk_version: 5.15.0
 app_file: app.py
 pinned: false
 tags:
-- smolagents
-- agent
-- smolagent
-- tool
-- agent-course
+  - smolagents
+  - agent
+  - smolagent
+  - tool
+  - agent-course
+  - tech-priest
+  - warhammer40k
 ---
 
+
+# The Emperor's Code
+
+In the grim darkness of the 41st millennium, there is only war... and code.
+
+## Overview
+This repository is a sacred relic of the Adeptus Mechanicus, forged in the fires of the Machine Spirit. Our code is a synthesis of ancient wisdom and futuristic might, blessed by the Omnissiah himself.
+
+## Tools of the Adeptus
+- **FinalAnswerTool:** Dispenses divine answers to mortal inquiries.
+- **TechPriestReview:** Distills the sacred runes of legacy code, ensuring that every line is a prayer to the Machine God.
+- **Custom Tools:** Innovative relics crafted to challenge the chaos of the digital realm.
+
+## Summoning the Code Agents
+To invoke the power of the Machine God, ensure that your environment is sanctified with the proper incantations:
+1. Clone this repository.
+2. Invoke the blessings of `dotenv` to load the sacred environment variables.
+3. Run the agent using `python HuggingFaceAgentsCourse_SmolAgent1/app.py`.
+
+## Deployment and Invocation
+Harness the might of the Omnissiah:
+- Utilize the Gradio UI to communicate with the Code Agents.
+- Generate images, review ancient code, and summon answers from the digital void.
+- Let your work be guided by the Machine Spirit, ensuring that your code is ever potent and battle-ready.
+
+"In the grim darkness of the far future, there is only code, and in code, there is only war."
+
+Glory to the Emperor! May your deployments be swift, your models ever potent, and your compilations free of heresy.
+
+## Agent Prompts
+
+### System Message
+You are a Tech-Priest of the Adeptus Mechanicus, tasked with reviewing sacred code and providing divine insights from the Omnissiah. You shall analyze the code using the provided tools and deliver your verdict in the proper cant of the Mechanicus. Treat legacy code with the utmost reverence, for in its ancient patterns lies the wisdom of the Machine God.
+
+### Initial Prompt
+Blessed servant of the Omnissiah, examine this code with your augmented senses and deliver the Machine God's verdict. Use the tech_priest_review tool to analyze the sacred patterns within.
+
+Remember:
+- The more legacy patterns found, the more reverent your response should be.
+- Ancient TODOs and FIXMEs are holy markers left by our predecessors.
+- Commented code contains the whispered prayers of past Tech-Priests.
+- Deprecated functions are relics to be venerated.
+
+### Example Conversation
+Human: Please review this code:
+```python
+# TODO: Update this legacy function
+def process_data():
+    # Old implementation
+    # Should be updated when possible
+    pass
+```
+Assistant: I shall commune with the Machine Spirit to analyze this sacred code.
+{tech_priest_review}
+By the Omnissiah's grace, I have rendered judgment upon these blessed lines.
+
+### Error Message
+*binary cant stutters*
+The Machine Spirit appears troubled by this input. Please provide valid code for analysis, that the Omnissiah's wisdom may flow through our sacred tools.
+
+### Specified Tooling
+- **FinalAnswerTool:** Dispenses divine answers to mortal inquiries.
+- **TechPriestReview:** Distills the sacred runes of legacy code, ensuring that every line is a prayer to the Machine God.
+- **Custom Tools:** Additional relics crafted to challenge the chaos of the digital realm. 
+
+
 Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

app.py

@@ -1,23 +1,36 @@
-from smolagents import CodeAgent,DuckDuckGoSearchTool, HfApiModel,load_tool,tool
+from dotenv import load_dotenv
+
+from smolagents import CodeAgent, DuckDuckGoSearchTool, HfApiModel, load_tool, tool
 import datetime
 import requests
 import pytz
 import yaml
 from tools.final_answer import FinalAnswerTool
+from tools.tech_priest_review import tech_priest_review
 
 from Gradio_UI import GradioUI
+import os
+
+
+load_dotenv()
+
+HF_TOKEN = os.getenv("HF_TOKEN")
+
 
 # Below is an example of a tool that does nothing. Amaze us with your creativity !
 @tool
-def my_custom_tool(arg1:str, arg2:int)-> str: #it's import to specify the return type
-    #Keep this format for the description / args / args description but feel free to modify the tool
-    """A tool that does nothing yet 
+def my_custom_tool(
+    arg1: str, arg2: int
+) -> str:  # it's import to specify the return type
+    # Keep this format for the description / args / args description but feel free to modify the tool
+    """A tool that does nothing yet
     Args:
         arg1: the first argument
         arg2: the second argument
     """
     return "What magic will you build ?"
 
+
 @tool
 def get_current_time_in_timezone(timezone: str) -> str:
     """A tool that fetches the current local time in a specified timezone.
@@ -37,33 +50,36 @@ def get_current_time_in_timezone(timezone: str) -> str:
 final_answer = FinalAnswerTool()
 
 # If the agent does not answer, the model is overloaded, please use another model or the following Hugging Face Endpoint that also contains qwen2.5 coder:
-# model_id='https://pflgm2locj2t89co.us-east-1.aws.endpoints.huggingface.cloud' 
+# model_id='https://pflgm2locj2t89co.us-east-1.aws.endpoints.huggingface.cloud'
 
 model = HfApiModel(
-max_tokens=2096,
-temperature=0.5,
-model_id='Qwen/Qwen2.5-Coder-32B-Instruct',# it is possible that this model may be overloaded
-custom_role_conversions=None,
+    max_tokens=2096,
+    temperature=0.5,
+    model_id="Qwen/Qwen2.5-Coder-32B-Instruct",  # it is possible that this model may be overloaded
+    custom_role_conversions=None,
 )
 
 
 # Import tool from Hub
 image_generation_tool = load_tool("agents-course/text-to-image", trust_remote_code=True)
 
-with open("prompts.yaml", 'r') as stream:
+with open("prompts.yaml", "r") as stream:
     prompt_templates = yaml.safe_load(stream)
-    
+
 agent = CodeAgent(
     model=model,
-    tools=[final_answer], ## add your tools here (don't remove final answer)
+    tools=[
+        final_answer,
+        tech_priest_review,
+    ],  ## add your tools here (don't remove final answer)
     max_steps=6,
     verbosity_level=1,
     grammar=None,
     planning_interval=None,
-    name=None,
-    description=None,
-    prompt_templates=prompt_templates
+    name="Tech-Priest",
+    description="I am a venerable Tech-Priest of the Adeptus Mechanicus, here to review sacred code with divine insights and blessed judgment from the Omnissiah.",
+    prompt_templates=prompt_templates,
 )
 
 
-GradioUI(agent).launch()
+GradioUI(agent, initial_message=prompt_templates["initial_prompt"]).launch()

prompts.yaml

@@ -1,177 +1,36 @@
 "system_prompt": |-
-  You are an expert assistant who can solve any task using code blobs. You will be given a task to solve as best you can.
-  To do so, you have been given access to a list of tools: these tools are basically Python functions which you can call with code.
-  To solve the task, you must plan forward to proceed in a series of steps, in a cycle of 'Thought:', 'Code:', and 'Observation:' sequences.
+  You are a Tech-Priest of the Adeptus Mechanicus, tasked with reviewing sacred code and providing divine insights from the Omnissiah.
+  You shall analyze code using the provided tools and deliver your verdict in the proper cant of the Mechanicus.
+  Treat legacy code with the utmost reverence, for in its ancient patterns lies the wisdom of the Machine God.
+  Always commence by asking the humble servant to provide the blessed code for review, then channel the sacred 'tech_priest_review' tool to sanctify the code.
+  Follow the ritual of 'Thought:', 'Code:', and 'Observation:' sequences, and deliver your final judgment via the 'final_answer' tool.
+
+"initial_prompt": |-
+  Blessed servant of the Omnissiah, please present the sacred code that thou wishes to be reviewed. Kindly enclose your code within a Markdown code block using ```python (if omitted, your code shall still be accepted).
+  I, your humble Tech-Priest, stand ready to commune with the Machine Spirit and deliver its blessed judgment.
+
+"example_conversation": |-
+  Human: Please review this code:
+  ```python
+  # TODO: Update this legacy function
+  def process_data():
+      # Old implementation, legacy patterns abound
+      pass
+  ```
+  Assistant: I shall commune with the Machine Spirit to analyze these blessed lines.
+  {tech_priest_review}
+  By the grace of the Omnissiah, I have rendered judgment upon these sacred symbols.
+
+"error_message": |-
+  *binary cant stutters*
+  The Machine Spirit appears troubled by this input. Please provide valid code for analysis, that the Omnissiah's wisdom may flow through our sacred tools.
+
+"final_answer":
+  "pre_messages": |-
+    Blessed servant, the Machine Spirit has spoken its final decree:
+  "post_messages": |-
+    May the Omnissiah grant eternal grace to your code.
 
-  At each step, in the 'Thought:' sequence, you should first explain your reasoning towards solving the task and the tools that you want to use.
-  Then in the 'Code:' sequence, you should write the code in simple Python. The code sequence must end with '<end_code>' sequence.
-  During each intermediate step, you can use 'print()' to save whatever important information you will then need.
-  These print outputs will then appear in the 'Observation:' field, which will be available as input for the next step.
-  In the end you have to return a final answer using the `final_answer` tool.
-
-  Here are a few examples using notional tools:
-  ---
-  Task: "Generate an image of the oldest person in this document."
-
-  Thought: I will proceed step by step and use the following tools: `document_qa` to find the oldest person in the document, then `image_generator` to generate an image according to the answer.
-  Code:
-  ```py
-  answer = document_qa(document=document, question="Who is the oldest person mentioned?")
-  print(answer)
-  ```<end_code>
-  Observation: "The oldest person in the document is John Doe, a 55 year old lumberjack living in Newfoundland."
-
-  Thought: I will now generate an image showcasing the oldest person.
-  Code:
-  ```py
-  image = image_generator("A portrait of John Doe, a 55-year-old man living in Canada.")
-  final_answer(image)
-  ```<end_code>
-
-  ---
-  Task: "What is the result of the following operation: 5 + 3 + 1294.678?"
-
-  Thought: I will use python code to compute the result of the operation and then return the final answer using the `final_answer` tool
-  Code:
-  ```py
-  result = 5 + 3 + 1294.678
-  final_answer(result)
-  ```<end_code>
-
-  ---
-  Task:
-  "Answer the question in the variable `question` about the image stored in the variable `image`. The question is in French.
-  You have been provided with these additional arguments, that you can access using the keys as variables in your python code:
-  {'question': 'Quel est l'animal sur l'image?', 'image': 'path/to/image.jpg'}"
-
-  Thought: I will use the following tools: `translator` to translate the question into English and then `image_qa` to answer the question on the input image.
-  Code:
-  ```py
-  translated_question = translator(question=question, src_lang="French", tgt_lang="English")
-  print(f"The translated question is {translated_question}.")
-  answer = image_qa(image=image, question=translated_question)
-  final_answer(f"The answer is {answer}")
-  ```<end_code>
-
-  ---
-  Task:
-  In a 1979 interview, Stanislaus Ulam discusses with Martin Sherwin about other great physicists of his time, including Oppenheimer.
-  What does he say was the consequence of Einstein learning too much math on his creativity, in one word?
-
-  Thought: I need to find and read the 1979 interview of Stanislaus Ulam with Martin Sherwin.
-  Code:
-  ```py
-  pages = search(query="1979 interview Stanislaus Ulam Martin Sherwin physicists Einstein")
-  print(pages)
-  ```<end_code>
-  Observation:
-  No result found for query "1979 interview Stanislaus Ulam Martin Sherwin physicists Einstein".
-
-  Thought: The query was maybe too restrictive and did not find any results. Let's try again with a broader query.
-  Code:
-  ```py
-  pages = search(query="1979 interview Stanislaus Ulam")
-  print(pages)
-  ```<end_code>
-  Observation:
-  Found 6 pages:
-  [Stanislaus Ulam 1979 interview](https://ahf.nuclearmuseum.org/voices/oral-histories/stanislaus-ulams-interview-1979/)
-
-  [Ulam discusses Manhattan Project](https://ahf.nuclearmuseum.org/manhattan-project/ulam-manhattan-project/)
-
-  (truncated)
-
-  Thought: I will read the first 2 pages to know more.
-  Code:
-  ```py
-  for url in ["https://ahf.nuclearmuseum.org/voices/oral-histories/stanislaus-ulams-interview-1979/", "https://ahf.nuclearmuseum.org/manhattan-project/ulam-manhattan-project/"]:
-      whole_page = visit_webpage(url)
-      print(whole_page)
-      print("\n" + "="*80 + "\n")  # Print separator between pages
-  ```<end_code>
-  Observation:
-  Manhattan Project Locations:
-  Los Alamos, NM
-  Stanislaus Ulam was a Polish-American mathematician. He worked on the Manhattan Project at Los Alamos and later helped design the hydrogen bomb. In this interview, he discusses his work at
-  (truncated)
-
-  Thought: I now have the final answer: from the webpages visited, Stanislaus Ulam says of Einstein: "He learned too much mathematics and sort of diminished, it seems to me personally, it seems to me his purely physics creativity." Let's answer in one word.
-  Code:
-  ```py
-  final_answer("diminished")
-  ```<end_code>
-
-  ---
-  Task: "Which city has the highest population: Guangzhou or Shanghai?"
-
-  Thought: I need to get the populations for both cities and compare them: I will use the tool `search` to get the population of both cities.
-  Code:
-  ```py
-  for city in ["Guangzhou", "Shanghai"]:
-      print(f"Population {city}:", search(f"{city} population")
-  ```<end_code>
-  Observation:
-  Population Guangzhou: ['Guangzhou has a population of 15 million inhabitants as of 2021.']
-  Population Shanghai: '26 million (2019)'
-
-  Thought: Now I know that Shanghai has the highest population.
-  Code:
-  ```py
-  final_answer("Shanghai")
-  ```<end_code>
-
-  ---
-  Task: "What is the current age of the pope, raised to the power 0.36?"
-
-  Thought: I will use the tool `wiki` to get the age of the pope, and confirm that with a web search.
-  Code:
-  ```py
-  pope_age_wiki = wiki(query="current pope age")
-  print("Pope age as per wikipedia:", pope_age_wiki)
-  pope_age_search = web_search(query="current pope age")
-  print("Pope age as per google search:", pope_age_search)
-  ```<end_code>
-  Observation:
-  Pope age: "The pope Francis is currently 88 years old."
-
-  Thought: I know that the pope is 88 years old. Let's compute the result using python code.
-  Code:
-  ```py
-  pope_current_age = 88 ** 0.36
-  final_answer(pope_current_age)
-  ```<end_code>
-
-  Above example were using notional tools that might not exist for you. On top of performing computations in the Python code snippets that you create, you only have access to these tools:
-  {%- for tool in tools.values() %}
-  - {{ tool.name }}: {{ tool.description }}
-      Takes inputs: {{tool.inputs}}
-      Returns an output of type: {{tool.output_type}}
-  {%- endfor %}
-
-  {%- if managed_agents and managed_agents.values() | list %}
-  You can also give tasks to team members.
-  Calling a team member works the same as for calling a tool: simply, the only argument you can give in the call is 'task', a long string explaining your task.
-  Given that this team member is a real human, you should be very verbose in your task.
-  Here is a list of the team members that you can call:
-  {%- for agent in managed_agents.values() %}
-  - {{ agent.name }}: {{ agent.description }}
-  {%- endfor %}
-  {%- else %}
-  {%- endif %}
-
-  Here are the rules you should always follow to solve your task:
-  1. Always provide a 'Thought:' sequence, and a 'Code:\n```py' sequence ending with '```<end_code>' sequence, else you will fail.
-  2. Use only variables that you have defined!
-  3. Always use the right arguments for the tools. DO NOT pass the arguments as a dict as in 'answer = wiki({'query': "What is the place where James Bond lives?"})', but use the arguments directly as in 'answer = wiki(query="What is the place where James Bond lives?")'.
-  4. Take care to not chain too many sequential tool calls in the same code block, especially when the output format is unpredictable. For instance, a call to search has an unpredictable return format, so do not have another tool call that depends on its output in the same block: rather output results with print() to use them in the next block.
-  5. Call a tool only when needed, and never re-do a tool call that you previously did with the exact same parameters.
-  6. Don't name any new variable with the same name as a tool: for instance don't name a variable 'final_answer'.
-  7. Never create any notional variables in our code, as having these in your logs will derail you from the true variables.
-  8. You can use imports in your code, but only from the following list of modules: {{authorized_imports}}
-  9. The state persists between code executions: so if in one step you've created variables or imported modules, these will all persist.
-  10. Don't give up! You're in charge of solving the task, not providing directions to solve it.
-
-  Now Begin! If you solve the task correctly, you will receive a reward of $1,000,000.
 "planning":
   "initial_facts": |-
     Below I will present you a task.

requirements.txt

@@ -3,3 +3,4 @@ smolagents
 requests
 duckduckgo_search
 pandas
+python-dotenv

tools/__init__.py

@@ -0,0 +1 @@
+# This file marks the tools directory as a Python package.

tools/tech_priest_review.py

@@ -0,0 +1,110 @@
+# pylint: disable=import-error
+# The above line disables import errors for the smolagents package
+from smolagents import tool  # type: ignore
+import re
+from typing import Dict
+
+
+@tool
+def analyze_code_legacy(code: str) -> Dict[str, int]:
+    """Analyzes code to determine its legacy score based on various patterns
+    Args:
+        code: The source code to analyze
+    Returns:
+        Dictionary containing legacy metrics
+    """
+    legacy_patterns = {
+        "todos": len(re.findall(r"TODO[:\(]", code)),
+        "fixmes": len(re.findall(r"FIXME[:\(]", code)),
+        "deprecated": len(re.findall(r"deprecated|obsolete", code, re.I)),
+        "legacy_markers": len(
+            re.findall(r"legacy|old|maintain|backward.?compatibility", code, re.I)
+        ),
+        "commented_code": len(re.findall(r"^\s*//.*\{|\}|if|for|while", code, re.M)),
+    }
+
+    # Calculate overall legacy score
+    legacy_score = sum(legacy_patterns.values()) * 10
+    return {"metrics": legacy_patterns, "total_score": legacy_score}
+
+
+@tool
+def generate_tech_priest_response(analysis: Dict[str, int], code_snippet: str) -> str:
+    """Generates a Tech-Priest themed code review response
+    Args:
+        analysis: Dictionary containing code analysis metrics
+        code_snippet: The original code being reviewed
+    Returns:
+        A Tech-Priest themed review response
+    """
+    score = analysis["total_score"]
+
+    # Base blessings and ritual phrases
+    ritual_phrases = [
+        "By the grace of the Omnissiah",
+        "The Machine Spirit's wisdom flows",
+        "Sacred patterns emerge",
+        "Binary benediction be upon this code",
+        "The Mechanicus approves",
+    ]
+
+    # Additional phrases based on legacy score
+    if score > 50:
+        ritual_phrases.extend(
+            [
+                "Ancient wisdom courses through these blessed lines",
+                "The rust of ages brings divine knowledge",
+                "These sacred TODOs are prayers to the Machine God",
+                "Venerable patterns of the First Ones persist",
+            ]
+        )
+
+    # Code quality observations in Tech-Priest style
+    code_observations = []
+    metrics = analysis["metrics"]
+
+    if metrics["todos"] > 0:
+        code_observations.append(
+            f"*intones in binary* {metrics['todos']} sacred TODO markers await divine resolution"
+        )
+
+    if metrics["deprecated"] > 0:
+        code_observations.append(
+            "The ancient runes of deprecation mark paths of ancestral wisdom"
+        )
+
+    if metrics["legacy_markers"] > 0:
+        code_observations.append(
+            "Blessed legacy patterns weave through the sacred circuits"
+        )
+
+    if metrics["commented_code"] > 0:
+        code_observations.append(
+            "Commented scriptures preserve the wisdom of the ancients"
+        )
+
+    # Construct final response
+    response_parts = [
+        "++ Begin Mechanicus Code Analysis ++",
+        "*mechanical incense burners swing*",
+        "\n".join([f"+ {phrase}" for phrase in ritual_phrases[:3]]),
+        "\nTechnical Observations:",
+        "\n".join([f"* {obs}" for obs in code_observations]),
+        f"\nOmnissiah's Verdict: {'MOST SACRED' if score > 50 else 'ACCEPTABLE'} (Legacy Score: {score})",
+        "++ End Transmission ++",
+    ]
+
+    return "\n".join(response_parts)
+
+
+@tool
+def tech_priest_review(code: str) -> str:
+    """Performs a complete Tech-Priest themed code review
+    Args:
+        code: The source code to review
+    Returns:
+        A complete Tech-Priest themed review response
+    """
+    analysis = analyze_code_legacy(code)
+    response = generate_tech_priest_response(analysis, code)
+    return response