A bit of restructuring for simplicity and organization

pyproject.toml

@@ -0,0 +1,28 @@
+[build-system]
+requires = ["setuptools>=61.0"]
+build-backend = "setuptools.build_meta"
+
+[project]
+name = "hermes-agent"
+version = "0.1.0"
+description = "AI agent with advanced tool-calling and toolsets"
+readme = "README.md"
+requires-python = ">=3.10"
+authors = [{ name = "Hermes Agent" }]
+license = { text = "MIT" }
+dependencies = [
+  "firecrawl-py",
+  "openai",
+  "fal-client",
+  "python-dotenv",
+  "fire"
+]
+
+[project.scripts]
+hermes-agent = "run_agent:main"
+
+[tool.setuptools]
+py-modules = ["run_agent", "model_tools", "toolsets"]
+
+[tool.setuptools.packages.find]
+include = ["tools"]

scripts/test_run.sh

@@ -13,6 +13,16 @@ PROMPT="$1"
 # Set debug mode for web tools
 export WEB_TOOLS_DEBUG=true
 
+# Resolve repository root relative to this script and run from there
+SCRIPT_DIR="$(cd "$(dirname "$0")" && pwd)"
+REPO_ROOT="$(cd "$SCRIPT_DIR/.." && pwd)"
+cd "$REPO_ROOT"
+
+# Prefer local venv if present
+if [ -f "venv/bin/activate" ]; then
+  source venv/bin/activate
+fi
+
 # Run the agent with the provided prompt
 python run_agent.py \
   --query "$PROMPT" \

tests/test_web_tools.py

@@ -23,8 +23,8 @@ import argparse
 from datetime import datetime
 from typing import List, Dict, Any
 
-# Import the web tools to test
-from web_tools import (
+# Import the web tools to test (updated path after moving tools/)
+from tools.web_tools import (
     web_search_tool, 
     web_extract_tool, 
     web_crawl_tool,

tools/terminal_tool.py

@@ -22,8 +22,6 @@ Usage:
 import json
 import os
 from typing import Optional, Dict, Any
-from hecate import run_tool_with_lifecycle_management
-from morphcloud._llm import ToolCall
 
 # Detailed description for the terminal tool based on Hermes Terminal system prompt
 TERMINAL_TOOL_DESCRIPTION = """Execute commands on a secure, persistent Linux VM environment with full interactive application support.
@@ -114,6 +112,22 @@ def terminal_tool(
         >>> result = terminal_tool(command="sleep 60", background=True)
     """
     try:
+        # Import hecate and ToolCall lazily so this module can be imported
+        # even when hecate is not installed. If unavailable, gracefully
+        # indicate that the terminal tool is disabled.
+        try:
+            from hecate import run_tool_with_lifecycle_management
+            from morphcloud._llm import ToolCall
+        except ImportError:
+            return json.dumps({
+                "output": "",
+                "screen": "",
+                "session_id": None,
+                "exit_code": -1,
+                "error": "Terminal tool is disabled: 'hecate' is not installed. Install with: pip install hecate",
+                "status": "disabled"
+            })
+
         # Build tool input based on provided parameters
         tool_input = {}
         

tools/web_tools.py

@@ -574,11 +574,15 @@ async def web_extract_tool(
             {
                 "title": r.get("title", ""),
                 "content": r.get("content", ""),
-                "error": r.get("error")
+                "error": r.get("error"),
+                **({"llm_model": model} if use_llm_processing else {})
             }
             for r in response.get("results", [])
         ]
         trimmed_response = {"results": trimmed_results}
+        # Include model name used for summarization when LLM processing was requested
+        if use_llm_processing:
+            trimmed_response["llm_model"] = model
         
         result_json = json.dumps(trimmed_response, indent=2)
         # Clean base64 images from extracted content
@@ -847,11 +851,15 @@ async def web_crawl_tool(
             {
                 "title": r.get("title", ""),
                 "content": r.get("content", ""),
-                "error": r.get("error")
+                "error": r.get("error"),
+                **({"llm_model": model} if use_llm_processing else {})
             }
             for r in response.get("results", [])
         ]
         trimmed_response = {"results": trimmed_results}
+        # Include model name used for summarization when LLM processing was requested
+        if use_llm_processing:
+            trimmed_response["llm_model"] = model
         
         result_json = json.dumps(trimmed_response, indent=2)
         # Clean base64 images from crawled content