App fixed and running

.gradio/certificate.pem

@@ -0,0 +1,31 @@
+-----BEGIN CERTIFICATE-----
+MIIFazCCA1OgAwIBAgIRAIIQz7DSQONZRGPgu2OCiwAwDQYJKoZIhvcNAQELBQAw
+TzELMAkGA1UEBhMCVVMxKTAnBgNVBAoTIEludGVybmV0IFNlY3VyaXR5IFJlc2Vh
+cmNoIEdyb3VwMRUwEwYDVQQDEwxJU1JHIFJvb3QgWDEwHhcNMTUwNjA0MTEwNDM4
+WhcNMzUwNjA0MTEwNDM4WjBPMQswCQYDVQQGEwJVUzEpMCcGA1UEChMgSW50ZXJu
+ZXQgU2VjdXJpdHkgUmVzZWFyY2ggR3JvdXAxFTATBgNVBAMTDElTUkcgUm9vdCBY
+MTCCAiIwDQYJKoZIhvcNAQEBBQADggIPADCCAgoCggIBAK3oJHP0FDfzm54rVygc
+h77ct984kIxuPOZXoHj3dcKi/vVqbvYATyjb3miGbESTtrFj/RQSa78f0uoxmyF+
+0TM8ukj13Xnfs7j/EvEhmkvBioZxaUpmZmyPfjxwv60pIgbz5MDmgK7iS4+3mX6U
+A5/TR5d8mUgjU+g4rk8Kb4Mu0UlXjIB0ttov0DiNewNwIRt18jA8+o+u3dpjq+sW
+T8KOEUt+zwvo/7V3LvSye0rgTBIlDHCNAymg4VMk7BPZ7hm/ELNKjD+Jo2FR3qyH
+B5T0Y3HsLuJvW5iB4YlcNHlsdu87kGJ55tukmi8mxdAQ4Q7e2RCOFvu396j3x+UC
+B5iPNgiV5+I3lg02dZ77DnKxHZu8A/lJBdiB3QW0KtZB6awBdpUKD9jf1b0SHzUv
+KBds0pjBqAlkd25HN7rOrFleaJ1/ctaJxQZBKT5ZPt0m9STJEadao0xAH0ahmbWn
+OlFuhjuefXKnEgV4We0+UXgVCwOPjdAvBbI+e0ocS3MFEvzG6uBQE3xDk3SzynTn
+jh8BCNAw1FtxNrQHusEwMFxIt4I7mKZ9YIqioymCzLq9gwQbooMDQaHWBfEbwrbw
+qHyGO0aoSCqI3Haadr8faqU9GY/rOPNk3sgrDQoo//fb4hVC1CLQJ13hef4Y53CI
+rU7m2Ys6xt0nUW7/vGT1M0NPAgMBAAGjQjBAMA4GA1UdDwEB/wQEAwIBBjAPBgNV
+HRMBAf8EBTADAQH/MB0GA1UdDgQWBBR5tFnme7bl5AFzgAiIyBpY9umbbjANBgkq
+hkiG9w0BAQsFAAOCAgEAVR9YqbyyqFDQDLHYGmkgJykIrGF1XIpu+ILlaS/V9lZL
+ubhzEFnTIZd+50xx+7LSYK05qAvqFyFWhfFQDlnrzuBZ6brJFe+GnY+EgPbk6ZGQ
+3BebYhtF8GaV0nxvwuo77x/Py9auJ/GpsMiu/X1+mvoiBOv/2X/qkSsisRcOj/KK
+NFtY2PwByVS5uCbMiogziUwthDyC3+6WVwW6LLv3xLfHTjuCvjHIInNzktHCgKQ5
+ORAzI4JMPJ+GslWYHb4phowim57iaztXOoJwTdwJx4nLCgdNbOhdjsnvzqvHu7Ur
+TkXWStAmzOVyyghqpZXjFaH3pO3JLF+l+/+sKAIuvtd7u+Nxe5AW0wdeRlN8NwdC
+jNPElpzVmbUq4JUagEiuTDkHzsxHpFKVK7q4+63SM1N95R1NbdWhscdCb+ZAJzVc
+oyi3B43njTOQ5yOf+1CceWxG1bQVs5ZufpsMljq4Ui0/1lvh+wjChP4kqKOJ2qxq
+4RgqsahDYVvTH9w7jXbyLeiNdd8XM2w9U/t7y0Ff/9yi0GE44Za4rF2LN9d11TPA
+mRGunUHBcnWEvgJBQl9nJEiU0Zsnvgc/ubhPgXRR4Xq37Z0j4r7g1SgEEzwxA57d
+emyPxgcYxn/eR44/KJ4EBs+lVDR3veyJm+kXQ99b21/+jh5Xos1AnX5iItreGCc=
+-----END CERTIFICATE-----

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}")
@@ -139,13 +172,24 @@ 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"):
+        if (
+            hasattr(agent.model, "last_input_token_count")
+            and agent.model.last_input_token_count is not None
+        ):
             total_input_tokens += agent.model.last_input_token_count
+        if (
+            hasattr(agent.model, "last_output_token_count")
+            and agent.model.last_output_token_count is not None
+        ):
             total_output_tokens += agent.model.last_output_token_count
-            if isinstance(step_log, ActionStep):
+        if isinstance(step_log, ActionStep):
+            if hasattr(agent.model, "last_input_token_count"):
                 step_log.input_token_count = agent.model.last_input_token_count
+            if hasattr(agent.model, "last_output_token_count"):
                 step_log.output_token_count = agent.model.last_output_token_count
 
         for message in pull_messages_from_step(
@@ -172,7 +216,9 @@ 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:
@@ -242,10 +288,14 @@ 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 (
@@ -277,7 +327,9 @@ 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],
@@ -293,4 +345,4 @@ class GradioUI:
         demo.launch(debug=True, share=True, **kwargs)
 
 
-__all__ = ["stream_to_gradio", "GradioUI"]
+__all__ = ["stream_to_gradio", "GradioUI"]

app.py

@@ -36,7 +36,7 @@ model = InferenceClientModel(
     temperature=0.5,
     model_id="Qwen/Qwen2.5-Coder-32B-Instruct",  # it is possible that this model may be overloaded
     custom_role_conversions=None,
-    inference_client_url="https://pflgm2locj2t89co.us-east-1.aws.endpoints.huggingface.cloud",
+    # inference_client_url="https://pflgm2locj2t89co.us-east-1.aws.endpoints.huggingface.cloud",
 )
 
 
@@ -46,7 +46,14 @@ image_generation_tool = load_tool("agents-course/text-to-image", trust_remote_co
 with open("prompts.yaml", "r") as stream:
     prompt_templates = yaml.safe_load(stream)
 
+prompt_templates["final_answer"] = {
+    "pre_messages": "",
+    "final_answer": "Here is the final answer from your managed agent '{{name}}':\n{{final_answer}}",
+    "post_messages": "",
+}
 
+# print("Loaded prompt templates:", prompt_templates)
+# Initialize the CodeAgent with the model and tools
 agent = CodeAgent(
     model=model,
     tools=[