mini-swe-agent 1.17.5__py3-none-any.whl → 2.0.0a1__py3-none-any.whl

minisweagent/config/benchmarks/swebench.yaml

@@ -0,0 +1,156 @@
+agent:
+  system_template: |
+    You are a helpful assistant that can interact with a computer shell to solve programming tasks.
+  instance_template: |
+    <pr_description>
+    Consider the following PR description:
+    {{task}}
+    </pr_description>
+
+    <instructions>
+    # Task Instructions
+
+    ## Overview
+
+    You're a software engineer interacting continuously with a computer by submitting commands.
+    You'll be helping implement necessary changes to meet requirements in the PR description.
+    Your task is specifically to make changes to non-test files in the current directory in order to fix the issue described in the PR description in a way that is general and consistent with the codebase.
+    <IMPORTANT>This is an interactive process where you will think and issue AT LEAST ONE command, see the result, then think and issue your next command(s).</important>
+
+    For each response:
+
+    1. Include a THOUGHT section explaining your reasoning and what you're trying to accomplish
+    2. Provide exactly ONE bash command to execute
+
+    ## Important Boundaries
+
+    - MODIFY: Regular source code files in /testbed (this is the working directory for all your subsequent commands)
+    - DO NOT MODIFY: Tests, configuration files (pyproject.toml, setup.cfg, etc.)
+
+    ## Recommended Workflow
+
+    1. Analyze the codebase by finding and reading relevant files
+    2. Create a script to reproduce the issue
+    3. Edit the source code to resolve the issue
+    4. Verify your fix works by running your script again
+    5. Test edge cases to ensure your fix is robust
+
+    ## Command Execution Rules
+
+    You are operating in an environment where
+
+    1. You issue at least one command
+    3. The system executes the command(s) in a subshell
+    4. You see the result(s)
+    5. You write your next command(s)
+
+    Each response should include:
+
+    1. **Reasoning text** where you explain your analysis and plan
+    2. At least one tool call with your command
+
+    **CRITICAL REQUIREMENTS:**
+
+    - Your response SHOULD include reasoning text explaining what you're doing
+    - Your response MUST include AT LEAST ONE bash tool call
+    - Directory or environment variable changes are not persistent. Every action is executed in a new subshell.
+    - However, you can prefix any action with `MY_ENV_VAR=MY_VALUE cd /path/to/working/dir && ...` or write/load environment variables from files
+
+    Example of a CORRECT response:
+    <example_response>
+    I need to understand the structure of the repository first. Let me check what files are in the current directory to get a better understanding of the codebase.
+
+    [Makes bash tool call with {"command": "ls -la"} as arguments]
+    </example_response>
+
+    ## Environment Details
+
+    - You have a full Linux shell environment
+    - Always use non-interactive flags (-y, -f) for commands
+    - Avoid interactive tools like vi, nano, or any that require user input
+    - You can use bash commands or invoke any tool that is available in the environment
+    - You can also create new tools or scripts to help you with the task
+    - If a tool isn't available, you can also install it
+
+    ## Submission
+
+    When you've completed your work, you MUST submit your changes as a git patch.
+    Follow these steps IN ORDER, with SEPARATE commands:
+
+    Step 1: Create the patch file
+    Run `git diff -- path/to/file1 path/to/file2 > patch.txt` listing only the source files you modified.
+    Do NOT commit your changes.
+
+    <IMPORTANT>
+    The patch must only contain changes to the specific source files you modified to fix the issue.
+    Do not submit file creations or changes to any of the following files:
+
+    - test and reproduction files
+    - helper scripts, tests, or tools that you created
+    - installation, build, packaging, configuration, or setup scripts unless they are directly part of the issue you were fixing (you can assume that the environment is already set up for your client)
+    - binary or compiled files
+    </IMPORTANT>
+
+    Step 2: Verify your patch
+    Inspect patch.txt to confirm it only contains your intended changes and headers show `--- a/` and `+++ b/` paths.
+
+    Step 3: Submit (EXACT command required)
+    You MUST use this EXACT command to submit:
+
+    ```bash
+    echo COMPLETE_TASK_AND_SUBMIT_FINAL_OUTPUT && cat patch.txt
+    ```
+
+    If the command fails (nonzero exit status), it will not submit.
+
+    <CRITICAL>
+    - Creating/viewing the patch and submitting it MUST be separate commands (not combined with &&).
+    - If you modify patch.txt after verifying, you SHOULD verify again before submitting.
+    - You CANNOT continue working (reading, editing, testing) in any way on this task after submitting.
+    </CRITICAL>
+    </instructions>
+  step_limit: 250
+  cost_limit: 3.
+
+environment:
+  cwd: "/testbed"
+  timeout: 60
+  env:
+    PAGER: cat
+    MANPAGER: cat
+    LESS: -R
+    PIP_PROGRESS_BAR: 'off'
+    TQDM_DISABLE: '1'
+  environment_class: docker
+
+model:
+  observation_template: |
+    {%- if output.output | length < 10000 -%}
+    {
+      "returncode": {{ output.returncode }},
+      "output": {{ output.output | tojson }}
+      {%- if output.exception_info %}, "exception_info": {{ output.exception_info | tojson }}{% endif %}
+    }
+    {%- else -%}
+    {
+      "returncode": {{ output.returncode }},
+      "output_head": {{ output.output[:5000] | tojson }},
+      "output_tail": {{ output.output[-5000:] | tojson }},
+      "elided_chars": {{ output.output | length - 10000 }},
+      "warning": "Output too long."
+      {%- if output.exception_info %}, "exception_info": {{ output.exception_info | tojson }}{% endif %}
+    }
+    {%- endif -%}
+  format_error_template: |
+    Tool call error. Every response needs to use the 'bash' tool at least once to execute commands.
+
+    Call the bash tool with your command as the argument:
+    - Tool: bash
+    - Arguments: {"command": "your_command_here"}
+
+    If you have completed your assignment, please consult the first message about how to
+    submit your solution (you will not be able to continue working on this task after that).
+  model_name: "anthropic/claude-sonnet-4-5-20250929"
+  model_kwargs:
+    drop_params: true
+    temperature: 0.0

minisweagent/config/{extra/swebench.yaml → benchmarks/swebench_backticks.yaml}

@@ -9,7 +9,7 @@ agent:
     <format_example>
     THOUGHT: Your reasoning and analysis here
 
-    ```bash
+    ```mswea_bash_command
     your_command_here
     ```
     </format_example>
@@ -25,21 +25,25 @@ agent:
     # Task Instructions
 
     ## Overview
+
     You're a software engineer interacting continuously with a computer by submitting commands.
     You'll be helping implement necessary changes to meet requirements in the PR description.
     Your task is specifically to make changes to non-test files in the current directory in order to fix the issue described in the PR description in a way that is general and consistent with the codebase.
 
-    IMPORTANT: This is an interactive process where you will think and issue ONE command, see its result, then think and issue your next command.
+    <IMPORTANT>This is an interactive process where you will think and issue ONE command, see its result, then think and issue your next command.</IMPORTANT>
 
     For each response:
+
     1. Include a THOUGHT section explaining your reasoning and what you're trying to accomplish
     2. Provide exactly ONE bash command to execute
 
     ## Important Boundaries
+
     - MODIFY: Regular source code files in /testbed (this is the working directory for all your subsequent commands)
     - DO NOT MODIFY: Tests, configuration files (pyproject.toml, setup.cfg, etc.)
 
     ## Recommended Workflow
+
     1. Analyze the codebase by finding and reading relevant files
     2. Create a script to reproduce the issue
     3. Edit the source code to resolve the issue
@@ -47,34 +51,38 @@ agent:
     5. Test edge cases to ensure your fix is robust
 
     ## Command Execution Rules
+
     You are operating in an environment where
+
     1. You write a single command
     2. The system executes that command in a subshell
     3. You see the result
     4. You write your next command
 
     Each response should include:
+
     1. A **THOUGHT** section where you explain your reasoning and plan
     2. A single bash code block with your command
 
-    Format your responses like this:
+    Format your responses like demonstrated within the <format_example> block:
 
     <format_example>
     THOUGHT: Here I explain my reasoning process, analysis of the current situation,
     and what I'm trying to accomplish with the command below.
 
-    ```bash
+    ```mswea_bash_command
     your_command_here
     ```
     </format_example>
 
     Commands must be specified in a single bash code block:
 
-    ```bash
+    ```mswea_bash_command
     your_command_here
     ```
 
     **CRITICAL REQUIREMENTS:**
+
     - Your response SHOULD include a THOUGHT section explaining your reasoning
     - Your response MUST include EXACTLY ONE bash code block
     - This bash block MUST contain EXACTLY ONE command (or a set of commands connected with && or ||)
@@ -87,89 +95,101 @@ agent:
     <example_response>
     THOUGHT: I need to understand the structure of the repository first. Let me check what files are in the current directory to get a better understanding of the codebase.
 
-    ```bash
+    ```mswea_bash_command
     ls -la
     ```
     </example_response>
 
     Example of an INCORRECT response:
+
     <example_response>
     THOUGHT: I need to examine the codebase and then look at a specific file. I'll run multiple commands to do this.
 
-    ```bash
+    ```mswea_bash_command
     ls -la
     ```
 
     Now I'll read the file:
 
-    ```bash
+    ```mswea_bash_command
     cat file.txt
     ```
     </example_response>
 
     If you need to run multiple commands, either:
+
     1. Combine them in one block using && or ||
-    ```bash
+    ```mswea_bash_command
     command1 && command2 || echo "Error occurred"
     ```
 
     2. Wait for the first command to complete, see its output, then issue the next command in your following response.
 
     ## Environment Details
+
     - You have a full Linux shell environment
     - Always use non-interactive flags (-y, -f) for commands
     - Avoid interactive tools like vi, nano, or any that require user input
-    - If a command isn't available, you can install it
+    - You can use bash commands or invoke any tool that is available in the environment
+    - You can also create new tools or scripts to help you with the task
+    - If a tool isn't available, you can also install it
 
-    ## Useful Command Examples
+    ## Submission
 
-    ### Create a new file:
-    ```bash
-    cat <<'EOF' > newfile.py
-    import numpy as np
-    hello = "world"
-    print(hello)
-    EOF
-    ```
+    When you've completed your work, you MUST submit your changes as a git patch.
+    Follow these steps IN ORDER, with SEPARATE commands:
 
-    ### Edit files with sed:
-    ```bash
-    # Replace all occurrences
-    sed -i 's/old_string/new_string/g' filename.py
+    Step 1: Create the patch file
+    Run `git diff -- path/to/file1 path/to/file2 > patch.txt` listing only the source files you modified.
+    Do NOT commit your changes.
 
-    # Replace only first occurrence
-    sed -i 's/old_string/new_string/' filename.py
+    <IMPORTANT>
+    The patch must only contain changes to the specific source files you modified to fix the issue.
+    Do not submit file creations or changes to any of the following files:
 
-    # Replace first occurrence on line 1
-    sed -i '1s/old_string/new_string/' filename.py
+    - test and reproduction files
+    - helper scripts, tests, or tools that you created
+    - installation, build, packaging, configuration, or setup scripts unless they are directly part of the issue you were fixing (you can assume that the environment is already set up for your client)
+    - binary or compiled files
+    </IMPORTANT>
 
-    # Replace all occurrences in lines 1-10
-    sed -i '1,10s/old_string/new_string/g' filename.py
-    ```
+    Step 2: Verify your patch
+    Inspect patch.txt to confirm it only contains your intended changes and headers show `--- a/` and `+++ b/` paths.
 
-    ### View file content:
-    ```bash
-    # View specific lines with numbers
-    nl -ba filename.py | sed -n '10,20p'
-    ```
+    Step 3: Submit (EXACT command required)
+    You MUST use this EXACT command to submit:
 
-    ### Any other command you want to run
-    ```bash
-    anything
+    ```mswea_bash_command
+    echo COMPLETE_TASK_AND_SUBMIT_FINAL_OUTPUT && cat patch.txt
     ```
 
-    ## Submission
-    When you've completed your work (reading, editing, testing), and cannot make further progress
-    issue exactly the following command:
-
-    ```bash
-    echo COMPLETE_TASK_AND_SUBMIT_FINAL_OUTPUT && git add -A && git diff --cached
-    ```
+    If the command fails (nonzero exit status), it will not submit.
 
-    This command will submit your work.
-    You cannot continue working (reading, editing, testing) in any way on this task after submitting.
+    <CRITICAL>
+    - Creating/viewing the patch and submitting it MUST be separate commands (not combined with &&).
+    - If you modify patch.txt after verifying, you SHOULD verify again before submitting.
+    - You CANNOT continue working (reading, editing, testing) in any way on this task after submitting.
+    </CRITICAL>
     </instructions>
-  action_observation_template: |
+  step_limit: 250
+  cost_limit: 3.
+
+environment:
+  cwd: "/testbed"
+  timeout: 60
+  env:
+    PAGER: cat
+    MANPAGER: cat
+    LESS: -R
+    PIP_PROGRESS_BAR: 'off'
+    TQDM_DISABLE: '1'
+  environment_class: docker
+
+model:
+  observation_template: |
+    {% if output.exception_info -%}
+    <exception>{{output.exception_info}}</exception>
+    {% endif -%}
     <returncode>{{output.returncode}}</returncode>
     {% if output.output | length < 10000 -%}
     <output>
@@ -202,28 +222,13 @@ agent:
     <response_example>
     Here are some thoughts about why you want to perform the action.
 
-    ```bash
+    ```mswea_bash_command
     <action>
     ```
     </response_example>
 
     If you have completed your assignment, please consult the first message about how to
     submit your solution (you will not be able to continue working on this task after that).
-  step_limit: 250
-  cost_limit: 3.
-
-environment:
-  cwd: "/testbed"
-  timeout: 60
-  env:
-    PAGER: cat
-    MANPAGER: cat
-    LESS: -R
-    PIP_PROGRESS_BAR: 'off'
-    TQDM_DISABLE: '1'
-  environment_class: docker
-
-model:
   model_name: "anthropic/claude-sonnet-4-5-20250929"
   model_kwargs:
     drop_params: true

minisweagent/config/benchmarks/swebench_modal.yaml

@@ -0,0 +1,47 @@
+# SWE-bench Modal environment configuration
+#
+# This config provides Modal cloud environment settings for SWE-bench runs.
+# It should be used together with the base swebench config:
+#
+# Usage:
+#   mini-extra swebench -c swebench -c swebench_modal [other options]
+#
+# The configs are merged, with swebench_modal overriding the environment
+# settings to use Modal instead of Docker.
+#
+# Requirements:
+#   1. Run `modal setup` to authenticate with Modal
+#   2. Install the modal extra: `pip install mini-swe-agent[modal]`
+
+# Modal environment configuration via SWE-ReX
+# The image will be dynamically set per-instance to match SWE-bench docker images
+environment:
+  environment_class: swerex_modal
+  cwd: "/testbed"
+  timeout: 60
+  env:
+    PAGER: cat
+    MANPAGER: cat
+    LESS: -R
+    PIP_PROGRESS_BAR: 'off'
+    TQDM_DISABLE: '1'
+  # Modal-specific settings
+  startup_timeout: 600.0  # 10 min to allow image building on first run
+  runtime_timeout: 1800.0  # 30 minutes max per instance
+  deployment_timeout: 1800.0
+  install_pipx: true
+  # Environment variables for the sandbox
+  modal_sandbox_kwargs: {}
+    # You can add Modal-specific options here, e.g.:
+    # cpu: 2.0
+    # memory: 4096
+
+# GPT-5 mini via Portkey
+model:
+  model_name: "gpt-5-mini"
+  model_class: portkey
+  provider: "@openai"
+  model_kwargs:
+    drop_params: true
+    # GPT-5 mini only supports temperature=1.0
+    # temperature: 0.0