Merge branch 'mgx_ops' into add_swe_agent_ablilities_to_engineer2

metagpt/roles/di/engineer2.py

@@ -16,6 +16,7 @@ from metagpt.prompts.di.engineer2 import (
 from metagpt.roles.di.role_zero import RoleZero
 from metagpt.schema import Message, UserMessage
 from metagpt.strategy.experience_retriever import ENGINEER_EXAMPLE
+from metagpt.tools.libs.cr import CodeReview
 from metagpt.tools.libs.git import git_create_pull
 from metagpt.tools.libs.terminal import Terminal
 from metagpt.tools.tool_registry import register_tool
@@ -40,6 +41,7 @@ class Engineer2(RoleZero):
         "git_create_pull",
         "SearchEnhancedQA",
         "Engineer2",
+        "CodeReview",
     ]
     # SWE Agent parameter
     run_eval: bool = False
@@ -64,11 +66,15 @@ class Engineer2(RoleZero):
         self.cmd_prompt_current_state = CURRENT_STATE.format(**state).strip()
 
     def _update_tool_execution(self):
+        # validate = ValidateAndRewriteCode()
+        cr = CodeReview()
         self.tool_execution_map.update(
             {
                 "Terminal.run_command": self.terminal.run_command,
                 "git_create_pull": git_create_pull,
                 "Engineer2.write_new_code": self.write_new_code,
+                "CodeReview.review": cr.review,
+                "CodeReview.fix": cr.fix,
                 # "ValidateAndRewriteCode.run": validate.run,
                 # "ValidateAndRewriteCode": validate.run,
             }

metagpt/roles/di/role_zero.py

@@ -89,7 +89,7 @@ class RoleZero(Role):
     # Others
     command_rsp: str = ""  # the raw string containing the commands
     commands: list[dict] = []  # commands to be executed
-    memory_k: int = 100  # number of memories (messages) to use as historical context
+    memory_k: int = 200  # number of memories (messages) to use as historical context
     use_fixed_sop: bool = False
     requirements_constraints: str = ""  # the constraints in user requirements
     use_summary: bool = True  # whether to summarize at the end

metagpt/roles/di/swe_agent.py

@@ -11,7 +11,7 @@ from metagpt.prompts.di.swe_agent import (
 from metagpt.roles.di.role_zero import RoleZero
 from metagpt.schema import Message
 from metagpt.tools.libs.git import git_create_pull
-from metagpt.tools.libs.terminal import Terminal
+from metagpt.tools.libs.terminal import Bash
 
 
 class SWEAgent(RoleZero):
@@ -19,8 +19,13 @@ class SWEAgent(RoleZero):
     profile: str = "Issue Solver"
     goal: str = "Resolve GitHub issue or bug in any existing codebase"
     _instruction: str = NEXT_STEP_TEMPLATE
-    tools: list[str] = ["Browser:goto,scroll", "RoleZero", "git_create_pull", "Editor", "Terminal"]
-    terminal: Terminal = Field(default_factory=Terminal, exclude=True)
+    tools: list[str] = [
+        "Bash",
+        "Browser:goto,scroll",
+        "RoleZero",
+        "git_create_pull",
+    ]
+    terminal: Bash = Field(default_factory=Bash, exclude=True)
     output_diff: str = ""
     max_react_loop: int = 40
     run_eval: bool = False
@@ -33,29 +38,14 @@ class SWEAgent(RoleZero):
     def _update_tool_execution(self):
         self.tool_execution_map.update(
             {
-                "Terminal.run_command": self.eval_terminal_run if self.run_eval else self.terminal.run_command,
+                "Bash.run": self.terminal.run,
                 "git_create_pull": git_create_pull,
             }
         )
 
-    async def eval_terminal_run(self, cmd):
-        """change command pull/push/commit to end."""
-        if any([cmd_key_word in cmd for cmd_key_word in ["pull", "push", "commit"]]):
-            # Observe that SWEAgent tries to submit the repo after fixing the bug.
-            # Set self.rc.todo to None and use git -diff to record the change.
-            logger.info("SWEAgent use cmd:{cmd}")
-            logger.info("finish current task")
-            # stop the sweagent
-            self._set_state(-1)
-            command_output = "Current test case is finished."
-        else:
-            command_output = await self.terminal.run_command(cmd)
-        return command_output
-
     async def _format_instruction(self):
         """
         Formats the instruction message for the SWE agent.
-
         Runs the "state" command in the terminal, parses its output as JSON,
         and uses it to format the `_instruction` template.
         """
@@ -66,16 +56,14 @@ class SWEAgent(RoleZero):
     async def _act(self) -> Message:
         message = await super()._act()
         if self.run_eval:
-            await self._parse_commands_for_eval()
+            self._parse_commands_for_eval()
         return message
 
     async def _parse_commands_for_eval(self):
         """
         Handles actions based on parsed commands.
-
         Parses commands, checks for a "submit" action, and generates a patch using `git diff`.
         Stores the cleaned patch in `output_diff`. Logs any exceptions.
-
         This function is specifically added for SWE bench evaluation.
         """
         # If todo switches to None, it indicates that this is the final round of reactions, and the Swe-Agent will stop. Use git diff to store any changes made.
@@ -88,7 +76,6 @@ class SWEAgent(RoleZero):
                 logger.info(f"Diff output: \n{clear_diff}")
                 if clear_diff:
                     self.output_diff = clear_diff
-
             except Exception as e:
                 logger.error(f"Error during submission: {e}")