feat(agent): remove unneeded python_execution tool

functions/function_calling/python_execution.py

@@ -1,54 +0,0 @@
-def run_python_script(script: str, timeout_seconds: int = 60) -> dict:
-    """
-    Run a short Python script and return a structured result with stdout, stderr, and exit code.
-
-    This tool is intended for agent workflows that need a reliable Python scratchpad for
-    calculations, parsing, formatting, or quick validation.
-    """
-    import os
-    import subprocess
-    import sys
-    import uuid
-    from pathlib import Path
-
-    workspace = Path(os.getenv("TEMP_CODE_DIR", "temp")).resolve()
-    workspace.mkdir(exist_ok=True)
-
-    script_path = workspace / f"{uuid.uuid4()}.py"
-    payload = script if script.endswith("\n") else script + "\n"
-    script_path.write_text(payload, encoding="utf-8")
-
-    try:
-        completed = subprocess.run(
-            [sys.executable or "python3", str(script_path.resolve())],
-            cwd=str(workspace),
-            capture_output=True,
-            text=True,
-            timeout=timeout_seconds,
-            check=False,
-        )
-        return {
-            "ok": completed.returncode == 0,
-            "exit_code": completed.returncode,
-            "stdout": completed.stdout,
-            "stderr": completed.stderr,
-        }
-    except subprocess.TimeoutExpired as exc:
-        return {
-            "ok": False,
-            "exit_code": None,
-            "stdout": exc.stdout or "",
-            "stderr": (exc.stderr or "") + f"\nError: Execution timed out after {timeout_seconds} seconds.",
-        }
-    except Exception as exc:
-        return {
-            "ok": False,
-            "exit_code": None,
-            "stdout": "",
-            "stderr": f"Execution error: {exc}",
-        }
-    finally:
-        try:
-            script_path.unlink(missing_ok=True)
-        except Exception:
-            pass

skills/python-scratchpad/SKILL.md

@@ -1,7 +1,7 @@
 ---
 name: python-scratchpad
 description: Use the existing Python execution tools as a scratchpad for calculations, data transformation, and quick script-based validation.
-allowed-tools: run_python_script execute_code
+allowed-tools: execute_code
 ---
 
 # Python Scratchpad
@@ -15,22 +15,21 @@ This skill is especially useful for:
 - checking assumptions with a small reproducible script
 
 Requirements:
-- The agent should have access to `run_python_script` or `execute_code`.
+- The agent should have access to `execute_code`.
 
 Workflow:
 1. If the task needs computation or a repeatable transformation, activate this skill.
 2. If you need examples, call `read_skill_file` for `references/examples.md`.
 3. Write a short Python script for the exact task.
 4. Prefer `run_python_script` with the script in its `script` argument.
-5. If `run_python_script` is unavailable, call `execute_code` once with that script.
+5. Use the script output in the final answer.
-6. Use the script output in the final answer.
+6. Keep scripts small and task-specific.
-7. Keep scripts small and task-specific.
 
 Rules:
 1. Prefer standard library Python.
 2. Print only the values you need.
 3. Do not invent outputs without running the script.
-4. If neither `run_python_script` nor `execute_code` is available, say exactly: `No Python execution tool is configured for this agent.`
+4. If `execute_code` is not available, say exactly: `No Python execution tool is configured for this agent.`
 5. Do not claim there is a generic execution-environment problem unless a tool call actually returned such an error.
 
 Expected behavior:

skills/python-scratchpad/references/examples.md

@@ -7,7 +7,7 @@ numbers = [14, 27, 31, 8]
 print(sum(numbers))
 ```
 
-Expected structured result with `run_python_script`:
+Expected structured result with `execute_code`:
 
 ```json
 {

yaml_instance/skills.yaml

@@ -1,6 +1,7 @@
 graph:
   id: skills
-  description: ''
+  description: Workflow to demonstrate skills usage
+  initial_instruction: Give the agent an instruction to explicitly use code to generate a Fibonacci sequence, sum numbers, or something else that is better done with code than LLM generation.
   log_level: DEBUG
   is_majority_voting: false
   nodes:
@@ -17,7 +18,7 @@ graph:
           - type: function
             config:
               tools:
-                - name: python_execution:All
+                - name: code_executor:All
               timeout: null
             prefix: ''
         thinking: null
@@ -33,7 +34,6 @@ graph:
       log_output: true
   edges: []
   memory: []
-  initial_instruction: ''
   start:
     - Qwerty
   end: []