mini-swe-agent 1.17.0__tar.gz → 1.17.2__tar.gz

{mini_swe_agent-1.17.0/src/mini_swe_agent.egg-info → mini_swe_agent-1.17.2}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: mini-swe-agent
-Version: 1.17.0
+Version: 1.17.2
 Summary: Nano SWE Agent - A simple AI software engineering agent
 Author-email: Kilian Lieret <kilian.lieret@posteo.de>, "Carlos E. Jimenez" <carlosej@princeton.edu>
 License: MIT License
@@ -86,21 +86,21 @@ In 2024, [SWE-bench](https://github.com/swe-bench/SWE-bench) & [SWE-agent](https
 
 We now ask: **What if SWE-agent was 100x smaller, and still worked nearly as well?**
 
-`mini` is for
+The `mini` agent is for
 
 - **Researchers** who want to **[benchmark](https://swe-bench.com), [fine-tune](https://swesmith.com/) or RL** without assumptions, bloat, or surprises
-- **Developers** who like their tools like their scripts: **short, sharp, and readable**
+- **Developers** who like to **own, understand, and modify** their tools
 - **Engineers** who want something **trivial to sandbox & to deploy anywhere**
 
 Here's some details:
 
 - **Minimal**: Just [100 lines of python](https://github.com/SWE-agent/mini-swe-agent/blob/main/src/minisweagent/agents/default.py) (+100 total for [env](https://github.com/SWE-agent/mini-swe-agent/blob/main/src/minisweagent/environments/local.py),
 [model](https://github.com/SWE-agent/mini-swe-agent/blob/main/src/minisweagent/models/litellm_model.py), [script](https://github.com/SWE-agent/mini-swe-agent/blob/main/src/minisweagent/run/hello_world.py)) — no fancy dependencies!
-- **Powerful:** Resolves >74% of GitHub issues in the [SWE-bench verified benchmark](https://www.swebench.com/) ([leaderboard](https://swe-bench.com/)).
-- **Convenient:** Comes with UIs that turn this into your daily dev swiss army knife!
+- **Performant:** Scores >74% on the [SWE-bench verified benchmark](https://www.swebench.com/) benchmark; starts faster than Claude Code
 - **Deployable:** In addition to local envs, you can use **docker**, **podman**, **singularity**, **apptainer**, and more
-- **Tested:** [![Codecov](https://img.shields.io/codecov/c/github/swe-agent/mini-swe-agent?style=flat-square)](https://codecov.io/gh/SWE-agent/mini-swe-agent)
 - **Cutting edge:** Built by the Princeton & Stanford team behind [SWE-bench](https://swebench.com) and [SWE-agent](https://swe-agent.com).
+- **Widely adopted:** In use by Meta, NVIDIA, Essential AI, Anyscale, and others
+- **Tested:** [![Codecov](https://img.shields.io/codecov/c/github/swe-agent/mini-swe-agent?style=flat-square)](https://codecov.io/gh/SWE-agent/mini-swe-agent)
 
 <details>
 
@@ -108,7 +108,7 @@ Here's some details:
 
 [SWE-agent](https://swe-agent.com/latest/) jump-started the development of AI agents in 2024. Back then, we placed a lot of emphasis on tools and special interfaces for the agent.
 However, one year later, as LMs have become more capable, a lot of this is not needed at all to build a useful agent!
-In fact, mini-SWE-agent
+In fact, the `mini` agent
 
 - **Does not have any tools other than bash** — it doesn't even use the tool-calling interface of the LMs.
   This means that you can run it with literally any model. When running in sandboxed environments you also don't need to take care
@@ -131,7 +131,7 @@ You can see the result on the [SWE-bench (bash only)](https://www.swebench.com/)
 
 Some agents are overfitted research artifacts. Others are UI-heavy frontend monsters.
 
-`mini` wants to be a hackable tool, not a black box.
+The `mini` agent wants to be a hackable tool, not a black box.
 
 - **Simple** enough to understand at a glance
 - **Convenient** enough to use in daily workflows

{mini_swe_agent-1.17.0 → mini_swe_agent-1.17.2}/README.md

@@ -15,21 +15,21 @@ In 2024, [SWE-bench](https://github.com/swe-bench/SWE-bench) & [SWE-agent](https
 
 We now ask: **What if SWE-agent was 100x smaller, and still worked nearly as well?**
 
-`mini` is for
+The `mini` agent is for
 
 - **Researchers** who want to **[benchmark](https://swe-bench.com), [fine-tune](https://swesmith.com/) or RL** without assumptions, bloat, or surprises
-- **Developers** who like their tools like their scripts: **short, sharp, and readable**
+- **Developers** who like to **own, understand, and modify** their tools
 - **Engineers** who want something **trivial to sandbox & to deploy anywhere**
 
 Here's some details:
 
 - **Minimal**: Just [100 lines of python](https://github.com/SWE-agent/mini-swe-agent/blob/main/src/minisweagent/agents/default.py) (+100 total for [env](https://github.com/SWE-agent/mini-swe-agent/blob/main/src/minisweagent/environments/local.py),
 [model](https://github.com/SWE-agent/mini-swe-agent/blob/main/src/minisweagent/models/litellm_model.py), [script](https://github.com/SWE-agent/mini-swe-agent/blob/main/src/minisweagent/run/hello_world.py)) — no fancy dependencies!
-- **Powerful:** Resolves >74% of GitHub issues in the [SWE-bench verified benchmark](https://www.swebench.com/) ([leaderboard](https://swe-bench.com/)).
-- **Convenient:** Comes with UIs that turn this into your daily dev swiss army knife!
+- **Performant:** Scores >74% on the [SWE-bench verified benchmark](https://www.swebench.com/) benchmark; starts faster than Claude Code
 - **Deployable:** In addition to local envs, you can use **docker**, **podman**, **singularity**, **apptainer**, and more
-- **Tested:** [![Codecov](https://img.shields.io/codecov/c/github/swe-agent/mini-swe-agent?style=flat-square)](https://codecov.io/gh/SWE-agent/mini-swe-agent)
 - **Cutting edge:** Built by the Princeton & Stanford team behind [SWE-bench](https://swebench.com) and [SWE-agent](https://swe-agent.com).
+- **Widely adopted:** In use by Meta, NVIDIA, Essential AI, Anyscale, and others
+- **Tested:** [![Codecov](https://img.shields.io/codecov/c/github/swe-agent/mini-swe-agent?style=flat-square)](https://codecov.io/gh/SWE-agent/mini-swe-agent)
 
 <details>
 
@@ -37,7 +37,7 @@ Here's some details:
 
 [SWE-agent](https://swe-agent.com/latest/) jump-started the development of AI agents in 2024. Back then, we placed a lot of emphasis on tools and special interfaces for the agent.
 However, one year later, as LMs have become more capable, a lot of this is not needed at all to build a useful agent!
-In fact, mini-SWE-agent
+In fact, the `mini` agent
 
 - **Does not have any tools other than bash** — it doesn't even use the tool-calling interface of the LMs.
   This means that you can run it with literally any model. When running in sandboxed environments you also don't need to take care
@@ -60,7 +60,7 @@ You can see the result on the [SWE-bench (bash only)](https://www.swebench.com/)
 
 Some agents are overfitted research artifacts. Others are UI-heavy frontend monsters.
 
-`mini` wants to be a hackable tool, not a black box.
+The `mini` agent wants to be a hackable tool, not a black box.
 
 - **Simple** enough to understand at a glance
 - **Convenient** enough to use in daily workflows

{mini_swe_agent-1.17.0 → mini_swe_agent-1.17.2/src/mini_swe_agent.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: mini-swe-agent
-Version: 1.17.0
+Version: 1.17.2
 Summary: Nano SWE Agent - A simple AI software engineering agent
 Author-email: Kilian Lieret <kilian.lieret@posteo.de>, "Carlos E. Jimenez" <carlosej@princeton.edu>
 License: MIT License
@@ -86,21 +86,21 @@ In 2024, [SWE-bench](https://github.com/swe-bench/SWE-bench) & [SWE-agent](https
 
 We now ask: **What if SWE-agent was 100x smaller, and still worked nearly as well?**
 
-`mini` is for
+The `mini` agent is for
 
 - **Researchers** who want to **[benchmark](https://swe-bench.com), [fine-tune](https://swesmith.com/) or RL** without assumptions, bloat, or surprises
-- **Developers** who like their tools like their scripts: **short, sharp, and readable**
+- **Developers** who like to **own, understand, and modify** their tools
 - **Engineers** who want something **trivial to sandbox & to deploy anywhere**
 
 Here's some details:
 
 - **Minimal**: Just [100 lines of python](https://github.com/SWE-agent/mini-swe-agent/blob/main/src/minisweagent/agents/default.py) (+100 total for [env](https://github.com/SWE-agent/mini-swe-agent/blob/main/src/minisweagent/environments/local.py),
 [model](https://github.com/SWE-agent/mini-swe-agent/blob/main/src/minisweagent/models/litellm_model.py), [script](https://github.com/SWE-agent/mini-swe-agent/blob/main/src/minisweagent/run/hello_world.py)) — no fancy dependencies!
-- **Powerful:** Resolves >74% of GitHub issues in the [SWE-bench verified benchmark](https://www.swebench.com/) ([leaderboard](https://swe-bench.com/)).
-- **Convenient:** Comes with UIs that turn this into your daily dev swiss army knife!
+- **Performant:** Scores >74% on the [SWE-bench verified benchmark](https://www.swebench.com/) benchmark; starts faster than Claude Code
 - **Deployable:** In addition to local envs, you can use **docker**, **podman**, **singularity**, **apptainer**, and more
-- **Tested:** [![Codecov](https://img.shields.io/codecov/c/github/swe-agent/mini-swe-agent?style=flat-square)](https://codecov.io/gh/SWE-agent/mini-swe-agent)
 - **Cutting edge:** Built by the Princeton & Stanford team behind [SWE-bench](https://swebench.com) and [SWE-agent](https://swe-agent.com).
+- **Widely adopted:** In use by Meta, NVIDIA, Essential AI, Anyscale, and others
+- **Tested:** [![Codecov](https://img.shields.io/codecov/c/github/swe-agent/mini-swe-agent?style=flat-square)](https://codecov.io/gh/SWE-agent/mini-swe-agent)
 
 <details>
 
@@ -108,7 +108,7 @@ Here's some details:
 
 [SWE-agent](https://swe-agent.com/latest/) jump-started the development of AI agents in 2024. Back then, we placed a lot of emphasis on tools and special interfaces for the agent.
 However, one year later, as LMs have become more capable, a lot of this is not needed at all to build a useful agent!
-In fact, mini-SWE-agent
+In fact, the `mini` agent
 
 - **Does not have any tools other than bash** — it doesn't even use the tool-calling interface of the LMs.
   This means that you can run it with literally any model. When running in sandboxed environments you also don't need to take care
@@ -131,7 +131,7 @@ You can see the result on the [SWE-bench (bash only)](https://www.swebench.com/)
 
 Some agents are overfitted research artifacts. Others are UI-heavy frontend monsters.
 
-`mini` wants to be a hackable tool, not a black box.
+The `mini` agent wants to be a hackable tool, not a black box.
 
 - **Simple** enough to understand at a glance
 - **Convenient** enough to use in daily workflows

{mini_swe_agent-1.17.0 → mini_swe_agent-1.17.2}/src/mini_swe_agent.egg-info/SOURCES.txt

@@ -20,7 +20,6 @@ src/minisweagent/config/default.yaml
 src/minisweagent/config/github_issue.yaml
 src/minisweagent/config/mini.tcss
 src/minisweagent/config/mini.yaml
-src/minisweagent/config/mini_no_temp.yaml
 src/minisweagent/config/extra/__init__.py
 src/minisweagent/config/extra/swebench.yaml
 src/minisweagent/config/extra/swebench_roulette.yaml

{mini_swe_agent-1.17.0 → mini_swe_agent-1.17.2}/src/minisweagent/__init__.py

@@ -8,7 +8,7 @@ This file provides:
   unless you want the static type checking.
 """
 
-__version__ = "1.17.0"
+__version__ = "1.17.2"
 
 import os
 from pathlib import Path

{mini_swe_agent-1.17.0 → mini_swe_agent-1.17.2}/src/minisweagent/config/README.md

@@ -1,7 +1,6 @@
 # Configs
 
 * `mini.yaml` - Default config for `mini`/`agents/interactive.py` or `mini -v`/`agents/interactive_textual.py` agent.
-* `mini_no_temp.yaml` - Same as `mini.yaml` but without the temperature setting
 * `default.yaml` - Default config for the `default.py` agent.
 * `github_issue.yaml` - Config for the `run/github_issue.py` entry point.
 

{mini_swe_agent-1.17.0 → mini_swe_agent-1.17.2}/src/minisweagent/config/default.yaml

@@ -153,5 +153,4 @@ environment:
     TQDM_DISABLE: '1'
 model:
   model_kwargs:
-    temperature: 0.0
     drop_params: true

{mini_swe_agent-1.17.0 → mini_swe_agent-1.17.2}/src/minisweagent/config/extra/swebench_roulette.yaml

@@ -36,7 +36,7 @@ agent:
     2. Provide exactly ONE bash command to execute
 
     ## Important Boundaries
-    - MODIFY: Regular source code files in {{working_dir}}
+    - 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

{mini_swe_agent-1.17.0 → mini_swe_agent-1.17.2}/src/minisweagent/config/github_issue.yaml

@@ -142,5 +142,4 @@ environment:
     TQDM_DISABLE: '1'
 model:
   model_kwargs:
-    temperature: 0.0
     drop_params: true

{mini_swe_agent-1.17.0 → mini_swe_agent-1.17.2}/src/minisweagent/config/mini.yaml

@@ -154,5 +154,4 @@ environment:
     TQDM_DISABLE: '1'
 model:
   model_kwargs:
-    temperature: 0.0
     drop_params: true

{mini_swe_agent-1.17.0 → mini_swe_agent-1.17.2}/src/minisweagent/models/litellm_model.py

@@ -68,9 +68,9 @@ class LitellmModel:
     def query(self, messages: list[dict[str, str]], **kwargs) -> dict:
         if self.config.set_cache_control:
             messages = set_cache_control(messages, mode=self.config.set_cache_control)
-        response = self._query(messages, **kwargs)
+        response = self._query([{"role": msg["role"], "content": msg["content"]} for msg in messages], **kwargs)
         try:
-            cost = litellm.cost_calculator.completion_cost(response)
+            cost = litellm.cost_calculator.completion_cost(response, model=self.config.model_name)
             if cost <= 0.0:
                 raise ValueError(f"Cost must be > 0.0, got {cost}")
         except Exception as e:

{mini_swe_agent-1.17.0 → mini_swe_agent-1.17.2}/src/minisweagent/models/litellm_response_api_model.py

@@ -62,7 +62,7 @@ class LitellmResponseAPIModel(LitellmModel):
         print(response)
         text = coerce_responses_text(response)
         try:
-            cost = litellm.cost_calculator.completion_cost(response)
+            cost = litellm.cost_calculator.completion_cost(response, model=self.config.model_name)
         except Exception as e:
             logger.critical(
                 f"Error calculating cost for model {self.config.model_name}: {e}. "

{mini_swe_agent-1.17.0 → mini_swe_agent-1.17.2}/src/minisweagent/models/openrouter_model.py

@@ -97,7 +97,7 @@ class OpenRouterModel:
     def query(self, messages: list[dict[str, str]], **kwargs) -> dict:
         if self.config.set_cache_control:
             messages = set_cache_control(messages, mode=self.config.set_cache_control)
-        response = self._query(messages, **kwargs)
+        response = self._query([{"role": msg["role"], "content": msg["content"]} for msg in messages], **kwargs)
 
         usage = response.get("usage", {})
         cost = usage.get("cost", 0.0)

{mini_swe_agent-1.17.0 → mini_swe_agent-1.17.2}/src/minisweagent/models/portkey_model.py

@@ -90,7 +90,7 @@ class PortkeyModel:
     def query(self, messages: list[dict[str, str]], **kwargs) -> dict:
         if self.config.set_cache_control:
             messages = set_cache_control(messages, mode=self.config.set_cache_control)
-        response = self._query(messages, **kwargs)
+        response = self._query([{"role": msg["role"], "content": msg["content"]} for msg in messages], **kwargs)
         cost = self._calculate_cost(response)
         self.n_calls += 1
         self.cost += cost

{mini_swe_agent-1.17.0 → mini_swe_agent-1.17.2}/src/minisweagent/models/portkey_response_api_model.py

@@ -52,7 +52,7 @@ class PortkeyResponseAPIModel(PortkeyModel):
         response = self._query(messages, **kwargs)
         text = coerce_responses_text(response)
         try:
-            cost = litellm.cost_calculator.completion_cost(response)
+            cost = litellm.cost_calculator.completion_cost(response, model=self.config.model_name)
             assert cost > 0.0, f"Cost is not positive: {cost}"
         except Exception as e:
             if self.config.cost_tracking != "ignore_errors":

{mini_swe_agent-1.17.0 → mini_swe_agent-1.17.2}/src/minisweagent/models/requesty_model.py

@@ -91,7 +91,7 @@ class RequestyModel:
             raise RequestyAPIError(f"Request failed: {e}") from e
 
     def query(self, messages: list[dict[str, str]], **kwargs) -> dict:
-        response = self._query(messages, **kwargs)
+        response = self._query([{"role": msg["role"], "content": msg["content"]} for msg in messages], **kwargs)
 
         # Extract cost from usage information
         usage = response.get("usage", {})

{mini_swe_agent-1.17.0 → mini_swe_agent-1.17.2}/src/minisweagent/run/extra/utils/batch_progress.py

@@ -79,7 +79,7 @@ class RunBatchProgressManager:
             "[cyan]Overall Progress", total=num_instances, total_cost="0.00", eta=""
         )
 
-        self.render_group = Group(Table(), self._task_progress_bar, self._main_progress_bar)
+        self.render_group = Group(self._main_progress_bar, Table(), self._task_progress_bar)
         self._yaml_report_path = yaml_report_path
 
     @property
@@ -112,7 +112,7 @@ class RunBatchProgressManager:
                 instances_str = _shorten_str(", ".join(reversed(instances)), 55)
                 t.add_row(status, str(len(instances)), instances_str)
         assert self.render_group is not None
-        self.render_group.renderables[0] = t
+        self.render_group.renderables[1] = t
 
     def _update_total_costs(self) -> None:
         with self._lock:

{mini_swe_agent-1.17.0 → mini_swe_agent-1.17.2}/src/minisweagent/run/inspector.py

@@ -2,9 +2,7 @@
 """
 Simple trajectory inspector for browsing agent conversation trajectories.
 
-[not dim]
-More information about the usage: [bold green]https://mini-swe-agent.com/latest/usage/inspector/[/bold green]
-[/not dim]
+More information about the usage: [bold green] https://mini-swe-agent.com/latest/usage/inspector/ [/bold green].
 """
 
 import json

mini_swe_agent-1.17.0/src/minisweagent/config/mini_no_temp.yaml

@@ -1,158 +0,0 @@
-# Identical config file to mini.yaml, but without temperature=0.0
-agent:
-  system_template: |
-    You are a helpful assistant that can interact with a computer.
-
-    Your response must contain exactly ONE bash code block with ONE command (or commands connected with && or ||).
-    Include a THOUGHT section before your command where you explain your reasoning process.
-    Format your response as shown in <format_example>.
-
-    <format_example>
-    Your reasoning and analysis here. Explain why you want to perform the action.
-
-    ```bash
-    your_command_here
-    ```
-    </format_example>
-
-    Failure to follow these rules will cause your response to be rejected.
-  instance_template: |
-    Please solve this issue: {{task}}
-
-    You can execute bash commands and edit files to implement the necessary changes.
-
-    ## Recommended Workflow
-
-    This workflows should be done step-by-step so that you can iterate on your changes and any possible problems.
-
-    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
-    6. Submit your changes and finish your work by issuing the following command: `echo COMPLETE_TASK_AND_SUBMIT_FINAL_OUTPUT`.
-       Do not combine it with any other command. <important>After this command, you cannot continue working on this task.</important>
-
-    ## Important Rules
-
-    1. Every response must contain exactly one action
-    2. The action must be enclosed in triple backticks
-    3. 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
-
-    <system_information>
-    {{system}} {{release}} {{version}} {{machine}}
-    </system_information>
-
-    ## Formatting your response
-
-    Here is an example of a correct response:
-
-    <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
-    ls -la
-    ```
-    </example_response>
-
-    ## Useful command examples
-
-    ### Create a new file:
-
-    ```bash
-    cat <<'EOF' > newfile.py
-    import numpy as np
-    hello = "world"
-    print(hello)
-    EOF
-    ```
-
-    ### Edit files with sed:
-
-    {%- if system == "Darwin" -%}
-    <important>
-    You are on MacOS. For all the below examples, you need to use `sed -i ''` instead of `sed -i`.
-    </important>
-    {%- endif -%}
-
-    ```bash
-    # Replace all occurrences
-    sed -i 's/old_string/new_string/g' filename.py
-
-    # Replace only first occurrence
-    sed -i 's/old_string/new_string/' filename.py
-
-    # Replace first occurrence on line 1
-    sed -i '1s/old_string/new_string/' filename.py
-
-    # Replace all occurrences in lines 1-10
-    sed -i '1,10s/old_string/new_string/g' filename.py
-    ```
-
-    ### View file content:
-
-    ```bash
-    # View specific lines with numbers
-    nl -ba filename.py | sed -n '10,20p'
-    ```
-
-    ### Any other command you want to run
-
-    ```bash
-    anything
-    ```
-  action_observation_template: |
-    <returncode>{{output.returncode}}</returncode>
-    {% if output.output | length < 10000 -%}
-    <output>
-    {{ output.output -}}
-    </output>
-    {%- else -%}
-    <warning>
-    The output of your last command was too long.
-    Please try a different command that produces less output.
-    If you're looking at a file you can try use head, tail or sed to view a smaller number of lines selectively.
-    If you're using grep or find and it produced too much output, you can use a more selective search pattern.
-    If you really need to see something from the full command's output, you can redirect output to a file and then search in that file.
-    </warning>
-    {%- set elided_chars = output.output | length - 10000 -%}
-    <output_head>
-    {{ output.output[:5000] }}
-    </output_head>
-    <elided_chars>
-    {{ elided_chars }} characters elided
-    </elided_chars>
-    <output_tail>
-    {{ output.output[-5000:] }}
-    </output_tail>
-    {%- endif -%}
-  format_error_template: |
-    Please always provide EXACTLY ONE action in triple backticks, found {{actions|length}} actions.
-    If you want to end the task, please issue the following command: `echo COMPLETE_TASK_AND_SUBMIT_FINAL_OUTPUT`
-    without any other command.
-    Else, please format your response exactly as follows:
-
-    <response_example>
-    Here are some thoughts about why you want to perform the action.
-
-    ```bash
-    <action>
-    ```
-    </response_example>
-
-    Note: In rare cases, if you need to reference a similar format in your command, you might have
-    to proceed in two steps, first writing TRIPLEBACKTICKSBASH, then replacing them with ```bash.
-  step_limit: 0.
-  cost_limit: 3.
-  mode: confirm
-environment:
-  env:
-    PAGER: cat
-    MANPAGER: cat
-    LESS: -R
-    PIP_PROGRESS_BAR: 'off'
-    TQDM_DISABLE: '1'
-model:
-  model_kwargs:
-    drop_params: true