mini-swe-agent 1.16.0__py3-none-any.whl → 1.17.1__py3-none-any.whl

{mini_swe_agent-1.16.0.dist-info → mini_swe_agent-1.17.1.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: mini-swe-agent
-Version: 1.16.0
+Version: 1.17.1
 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

{mini_swe_agent-1.16.0.dist-info → mini_swe_agent-1.17.1.dist-info}/RECORD

@@ -1,21 +1,20 @@
-mini_swe_agent-1.16.0.dist-info/licenses/LICENSE.md,sha256=D3luWPkdHAe7LBsdD4vzqDAXw6Xewb3G-uczss0uh1s,1094
-minisweagent/__init__.py,sha256=UdcN4hUoziBEob35FnOM4pf5nSD9dGt_-bv_QTWRBKY,2016
+mini_swe_agent-1.17.1.dist-info/licenses/LICENSE.md,sha256=D3luWPkdHAe7LBsdD4vzqDAXw6Xewb3G-uczss0uh1s,1094
+minisweagent/__init__.py,sha256=92sn1eUs4LJ0jSNW-ZAZjAIagd1Fbts0js5hTfuw-5E,2016
 minisweagent/__main__.py,sha256=FIyAOiw--c3FQ2g240FOM1FdL0lk_PxSpixu0pQ7WFo,194
 minisweagent/py.typed,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 minisweagent/agents/__init__.py,sha256=cpjJLzg1IGxLM-tZpoMJV9S33ye13XtdBO0x7DU_Lrk,48
-minisweagent/agents/default.py,sha256=M-cnJwLgAGwgFSUyKdf2nkE8xNr24ffcJHKuItLOoBg,5701
+minisweagent/agents/default.py,sha256=6XQEf4bawQL-J2r4ClsDsO_1uQ-VM7WrW3hGaHxKcQE,5657
 minisweagent/agents/interactive.py,sha256=NBeNamRuqww9ZRhOg1q8xPO9ziUw2gpAVV6hCPbpBxU,7470
 minisweagent/agents/interactive_textual.py,sha256=yUDMkuvhhnZAP8LtiBWmt5J5WzfWBeR0zNlJbdbEGa0,18153
-minisweagent/config/README.md,sha256=ABd9anA4aRWtx7Oh37z36Wv6ARvcxD2w9lPUE24R2mY,435
+minisweagent/config/README.md,sha256=ZGH5KbFHpkwYOwoZgwP1dHOikuvU11dIG_TqyI73dik,355
 minisweagent/config/__init__.py,sha256=0KzHaaIqWgRy2zbwIzhrg6BJPDzOvYi3jb4eBNY4sAU,823
-minisweagent/config/default.yaml,sha256=iVNFs-FHrjc81RAiaTjGk5435G6V7OPjbXECu6RxJPU,5129
-minisweagent/config/github_issue.yaml,sha256=qbjj3vmdukxz36_EY7e64vhNn1g2-_NrdNx5xgMOUAI,4569
+minisweagent/config/default.yaml,sha256=z1q91vFq_EeEb2fAuRiIwU7ZabiWP_-29M4GgaBxpgA,5108
+minisweagent/config/github_issue.yaml,sha256=Ws1IHO_lGA7JfLzXvDUzpSasf-4hQzXG7EjJqHORtho,4548
 minisweagent/config/mini.tcss,sha256=fmAP9cYAp2n7Ps2Dw3e-ZOGEF2E8JcwTgK1LDcis-x4,1141
-minisweagent/config/mini.yaml,sha256=-3c4eKeCysFAfKJX3whUuBI6wbQgt8vrlcTFp_pcdyY,5145
-minisweagent/config/mini_no_temp.yaml,sha256=g1Y5goNTYZlDcSuBgKWJUdMkoK09w_5vheASZg1yYYI,5190
+minisweagent/config/mini.yaml,sha256=eeOO6VkmiQcdU5dddESXUpGKFcSI2gBXsavNni4Xmig,5124
 minisweagent/config/extra/__init__.py,sha256=e1MoAlDn_wc9HnXNoncf1P-B4DQ-iRf6n7Q_txjZGRI,52
 minisweagent/config/extra/swebench.yaml,sha256=opFzxJPeMYY6oIpB6oUViXiax3ei7UTOlP0Lz1LbFss,7750
-minisweagent/config/extra/swebench_roulette.yaml,sha256=8O7PvO8tPGJN-mYuBGhWUlAzsjMPnbf3_i6Sn5v7RQ4,7813
+minisweagent/config/extra/swebench_roulette.yaml,sha256=ZYkh_ji0e7TuLcWXMrDhUQMPLiYH__EI0C4Skj3sK_Y,7871
 minisweagent/config/extra/swebench_xml.yaml,sha256=dWXAqzXgw167hgiKqoqOryPHwAgDV2JbgoiDABdEznY,7827
 minisweagent/environments/__init__.py,sha256=x80Ulx0UK21GAwg5jSTkOFeiZ7CQsGBP8cI_5BhazAo,1266
 minisweagent/environments/docker.py,sha256=hsKOPGAP2kjgEwA_2HQz_nCrr25qmR4fB8u5Ob6UbzY,4370
@@ -26,11 +25,11 @@ minisweagent/environments/extra/bubblewrap.py,sha256=G12Dm63N30qByfLb1SKNsI4G4gL
 minisweagent/environments/extra/swerex_docker.py,sha256=WPYbohT_vqTHkde9cxpbV6chLXCpLl0PDAcgMbZsV0M,1707
 minisweagent/models/__init__.py,sha256=RGJgMPeF8W2Ix8_xwvHjjDCD9I6ygirz4v8Ps1KG6dI,4435
 minisweagent/models/anthropic.py,sha256=4p-LxQ_RYQUX1rBsffAj3T1bBb2uMRhA4IyKfDcMpgo,1517
-minisweagent/models/litellm_model.py,sha256=ph2j2gDwxl10p9NRUhldNJt-FAwYIyjfnNiaF8A0ThU,4280
-minisweagent/models/litellm_response_api_model.py,sha256=BJzDGE-rn9P_TVX60-8YJXS6SIgOTJAGgBszuHNKzEI,2916
+minisweagent/models/litellm_model.py,sha256=A_M5PEBhWa2NmANYCF1MGw4tNwA89HLdeZw_ay3Xugw,4310
+minisweagent/models/litellm_response_api_model.py,sha256=FF-Xab6xBvkxh_E6VoMx-Km1owRpHrkSIfgXZ31hCsU,2946
 minisweagent/models/openrouter_model.py,sha256=dsVl8pnZ9M6nZ5DpLy69v1bizMR73mixXdVZVNzvknc,4712
 minisweagent/models/portkey_model.py,sha256=6HMOsmHd6Q6WdLUDa_1XFCrU0BaCUP5RqI3h6L8AxJQ,7223
-minisweagent/models/portkey_response_api_model.py,sha256=knIKR88u5YP-FqE27ZEopsuTSchzslq8CDjyxsMHtbU,2908
+minisweagent/models/portkey_response_api_model.py,sha256=muHiiRpm7nXP1jylZovE4Ttr_JwFt1b9-YZgRCthTbk,2938
 minisweagent/models/requesty_model.py,sha256=Dqr0cLNSstj3VrzYhf-Sqsju8OvJrRPK2mctajgRnNs,3781
 minisweagent/models/test_models.py,sha256=ItCA6ddntzkYA7dzSuUEaLMV-AE8TBuXBFP8CzpiO3U,1351
 minisweagent/models/extra/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
@@ -42,7 +41,7 @@ minisweagent/models/utils/openai_utils.py,sha256=3OEOR65gFeVCTpcLJyMkzbFL_B-k8ft
 minisweagent/run/__init__.py,sha256=WIoYgHVl7iZF2YncrfV3IttupG6P5KogroKHKECka3A,38
 minisweagent/run/github_issue.py,sha256=35mZoPLc4JV6XXJKRv55lnuKbXf5lDftd51N89-x9J0,3192
 minisweagent/run/hello_world.py,sha256=erLnEwNmPFLxq3-8zyv66Vy1kIqMqQf97vISX7LrQXg,959
-minisweagent/run/inspector.py,sha256=QnY3oYzm-yq3w9Jzs112Lco2Rg84vSocAWrQRVz_1lc,7127
+minisweagent/run/inspector.py,sha256=P86kOmzySWdK4tx0DHAOfSF1h-s1vHboSsaRD3_0OKQ,7109
 minisweagent/run/mini.py,sha256=N3ZvTQmKHNJ9bEaiz5YHjJT4Arg0WtjxGLBTtj8-T0E,4922
 minisweagent/run/mini_extra.py,sha256=ecA1PnTWElpO60G9RktvVLtUOf3bZ_ESmnSttS6izhQ,1465
 minisweagent/run/extra/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
@@ -55,8 +54,8 @@ minisweagent/run/utils/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3
 minisweagent/run/utils/save.py,sha256=bokvblZ1SaIvCXimkRQqgvERKmVM0jn8SF7UoHBeerQ,2546
 minisweagent/utils/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 minisweagent/utils/log.py,sha256=ruDMNKMrVC9NPvCeHwO3QYz5jsVNUGQB2dRAEAPAWp8,996
-mini_swe_agent-1.16.0.dist-info/METADATA,sha256=wzWaGbiiRE2CaTxf3kxyfMscOMAJdAZ6I4x3NFWE2S4,14851
-mini_swe_agent-1.16.0.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
-mini_swe_agent-1.16.0.dist-info/entry_points.txt,sha256=d1_yRbTaGjs1UXHa6JQK0sKDGBIVGm8oeW0k2kfbJgQ,182
-mini_swe_agent-1.16.0.dist-info/top_level.txt,sha256=zKF4t8bFpV87fdVABZt2Da-vnb4Vkh_CxkwQx5YT4Ew,13
-mini_swe_agent-1.16.0.dist-info/RECORD,,
+mini_swe_agent-1.17.1.dist-info/METADATA,sha256=pDciZvio2ToJP8llJbDE2qP1PaeeaP1Inp8MchsKW4g,14851
+mini_swe_agent-1.17.1.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
+mini_swe_agent-1.17.1.dist-info/entry_points.txt,sha256=d1_yRbTaGjs1UXHa6JQK0sKDGBIVGm8oeW0k2kfbJgQ,182
+mini_swe_agent-1.17.1.dist-info/top_level.txt,sha256=zKF4t8bFpV87fdVABZt2Da-vnb4Vkh_CxkwQx5YT4Ew,13
+mini_swe_agent-1.17.1.dist-info/RECORD,,

minisweagent/__init__.py

@@ -8,7 +8,7 @@ This file provides:
   unless you want the static type checking.
 """
 
-__version__ = "1.16.0"
+__version__ = "1.17.1"
 
 import os
 from pathlib import Path

minisweagent/agents/default.py

@@ -2,6 +2,7 @@
 
 import re
 import subprocess
+import time
 from dataclasses import asdict, dataclass
 
 from jinja2 import StrictUndefined, Template
@@ -68,7 +69,7 @@ class DefaultAgent:
         )
 
     def add_message(self, role: str, content: str, **kwargs):
-        self.messages.append({"role": role, "content": content, **kwargs})
+        self.messages.append({"role": role, "content": content, "timestamp": time.time(), **kwargs})
 
     def run(self, task: str, **kwargs) -> tuple[str, str]:
         """Run step() until agent is finished. Return exit status & message"""
@@ -114,15 +115,13 @@ class DefaultAgent:
     def execute_action(self, action: dict) -> dict:
         try:
             output = self.env.execute(action["action"])
-        except subprocess.TimeoutExpired as e:
-            output = e.output.decode("utf-8", errors="replace") if e.output else ""
+        except (TimeoutError, subprocess.TimeoutExpired) as e:
+            output = e.output.decode("utf-8", errors="replace") if getattr(e, "output", None) else ""
             raise ExecutionTimeoutError(
                 self.render_template(self.config.timeout_template, action=action, output=output)
             )
-        except TimeoutError:
-            raise ExecutionTimeoutError(self.render_template(self.config.timeout_template, action=action, output=""))
         self.has_finished(output)
-        return output
+        return output | {"action": action["action"]}
 
     def has_finished(self, output: dict[str, str]):
         """Raises Submitted exception with final output if the agent has finished its task."""

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.
 

minisweagent/config/default.yaml

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

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

minisweagent/config/github_issue.yaml

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

minisweagent/config/mini.yaml

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

minisweagent/models/litellm_model.py

@@ -70,7 +70,7 @@ class LitellmModel:
             messages = set_cache_control(messages, mode=self.config.set_cache_control)
         response = self._query(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:

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}. "

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":

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

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