mini-swe-agent 1.17.1__py3-none-any.whl → 1.17.3__py3-none-any.whl

{mini_swe_agent-1.17.1.dist-info → mini_swe_agent-1.17.3.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: mini-swe-agent
-Version: 1.17.1
+Version: 1.17.3
 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-1.17.1.dist-info → mini_swe_agent-1.17.3.dist-info}/RECORD

@@ -1,9 +1,9 @@
-mini_swe_agent-1.17.1.dist-info/licenses/LICENSE.md,sha256=D3luWPkdHAe7LBsdD4vzqDAXw6Xewb3G-uczss0uh1s,1094
-minisweagent/__init__.py,sha256=92sn1eUs4LJ0jSNW-ZAZjAIagd1Fbts0js5hTfuw-5E,2016
+mini_swe_agent-1.17.3.dist-info/licenses/LICENSE.md,sha256=D3luWPkdHAe7LBsdD4vzqDAXw6Xewb3G-uczss0uh1s,1094
+minisweagent/__init__.py,sha256=eWlfblsvb5AJPNFfCN2buiqwmeZ0h_Ssk7tzniLhn_8,2016
 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=6XQEf4bawQL-J2r4ClsDsO_1uQ-VM7WrW3hGaHxKcQE,5657
+minisweagent/agents/default.py,sha256=NLHCTR8CrM0-1aNXT0zZZ044RBYQWACfNzKwAg69IWM,6054
 minisweagent/agents/interactive.py,sha256=NBeNamRuqww9ZRhOg1q8xPO9ziUw2gpAVV6hCPbpBxU,7470
 minisweagent/agents/interactive_textual.py,sha256=yUDMkuvhhnZAP8LtiBWmt5J5WzfWBeR0zNlJbdbEGa0,18153
 minisweagent/config/README.md,sha256=ZGH5KbFHpkwYOwoZgwP1dHOikuvU11dIG_TqyI73dik,355
@@ -25,12 +25,12 @@ 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=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=muHiiRpm7nXP1jylZovE4Ttr_JwFt1b9-YZgRCthTbk,2938
-minisweagent/models/requesty_model.py,sha256=Dqr0cLNSstj3VrzYhf-Sqsju8OvJrRPK2mctajgRnNs,3781
+minisweagent/models/litellm_model.py,sha256=0HBnb53GdeqSAwNcJuu8hXrd3XqqIm4BHS1WkwK3ZGE,4394
+minisweagent/models/litellm_response_api_model.py,sha256=Niq4HepQm_dlCkGdXsg9_7zNNRxJlnwWK-JJE0lP9Qg,3150
+minisweagent/models/openrouter_model.py,sha256=YgML8_p9gHMjoBcxszmgyrIr5DLRX2vZiBwHC47N5mg,4796
+minisweagent/models/portkey_model.py,sha256=_eK8maRm2kwombWYbYtH7MXj8rhd18ZE7tGer2YXvws,7307
+minisweagent/models/portkey_response_api_model.py,sha256=JcODu40mYsqWnwWntTSjRUMTzifLUZZpFL5sF3FUk3s,2960
+minisweagent/models/requesty_model.py,sha256=t4iQD7mH61UlldQmydcGYmoj-dAG8K_2347DBjl-4vo,3865
 minisweagent/models/test_models.py,sha256=ItCA6ddntzkYA7dzSuUEaLMV-AE8TBuXBFP8CzpiO3U,1351
 minisweagent/models/extra/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 minisweagent/models/extra/roulette.py,sha256=idteU0pGvmmipNr0s-42GAbVkmKE20hY2LTFxbkAgoI,2048
@@ -49,13 +49,13 @@ minisweagent/run/extra/config.py,sha256=KDMwg6eQCxbwI6P1phosCwaLQhJQXB4ti65M_Hox
 minisweagent/run/extra/swebench.py,sha256=sO3LnjLXdU6Zbo409YhxVdizU8LaQcJUdcD8Tj6saMw,11741
 minisweagent/run/extra/swebench_single.py,sha256=KmoUkD6UQ1P0MY_73-OtYuQAsNPmOLlZIZSYKZGs5MQ,3699
 minisweagent/run/extra/utils/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-minisweagent/run/extra/utils/batch_progress.py,sha256=xhJ7FmsaTBGz-yh8pzYl4yMoUGjn7GA24eYrP-nHj60,6804
+minisweagent/run/extra/utils/batch_progress.py,sha256=URgnm5MpUA6liESNFqDIbzELM869PbXro7jKzvdbiv0,6804
 minisweagent/run/utils/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 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-1.17.1.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,,
+mini_swe_agent-1.17.3.dist-info/METADATA,sha256=zowefUb3iP7jiHwasuE_WQc40kshknJQpzlli4ix0mk,14836
+mini_swe_agent-1.17.3.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
+mini_swe_agent-1.17.3.dist-info/entry_points.txt,sha256=d1_yRbTaGjs1UXHa6JQK0sKDGBIVGm8oeW0k2kfbJgQ,182
+mini_swe_agent-1.17.3.dist-info/top_level.txt,sha256=zKF4t8bFpV87fdVABZt2Da-vnb4Vkh_CxkwQx5YT4Ew,13
+mini_swe_agent-1.17.3.dist-info/RECORD,,

minisweagent/__init__.py

@@ -8,7 +8,7 @@ This file provides:
   unless you want the static type checking.
 """
 
-__version__ = "1.17.1"
+__version__ = "1.17.3"
 
 import os
 from pathlib import Path

minisweagent/agents/default.py

@@ -20,7 +20,15 @@ class AgentConfig:
     )
     timeout_template: str = (
         "The last command <command>{{action['action']}}</command> timed out and has been killed.\n"
-        "The output of the command was:\n <output>\n{{output}}\n</output>\n"
+        "The output of the command was:\n"
+        "{% if output | length < 10000 -%}\n"
+        "<output>\n{{output}}\n</output>\n"
+        "{%- else -%}\n"
+        "<warning>Output was too long and has been truncated.</warning>\n"
+        "<output_head>\n{{ output[:5000] }}\n</output_head>\n"
+        "<elided_chars>{{ output | length - 10000 }} characters elided</elided_chars>\n"
+        "<output_tail>\n{{ output[-5000:] }}\n</output_tail>\n"
+        "{%- endif %}\n"
         "Please try another command and make sure to avoid those requiring interactive input."
     )
     format_error_template: str = "Please always provide EXACTLY ONE action in triple backticks."

minisweagent/models/litellm_model.py

@@ -41,6 +41,7 @@ class LitellmModel:
             litellm.utils.register_model(json.loads(Path(self.config.litellm_model_registry).read_text()))
 
     @retry(
+        reraise=True,
         stop=stop_after_attempt(int(os.getenv("MSWEA_MODEL_RETRY_STOP_AFTER_ATTEMPT", "10"))),
         wait=wait_exponential(multiplier=1, min=4, max=60),
         before_sleep=before_sleep_log(logger, logging.WARNING),
@@ -68,7 +69,7 @@ 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, model=self.config.model_name)
             if cost <= 0.0:

minisweagent/models/litellm_response_api_model.py

@@ -28,6 +28,7 @@ class LitellmResponseAPIModel(LitellmModel):
         self._previous_response_id: str | None = None
 
     @retry(
+        reraise=True,
         stop=stop_after_attempt(10),
         wait=wait_exponential(multiplier=1, min=4, max=60),
         before_sleep=before_sleep_log(logger, logging.WARNING),
@@ -45,9 +46,11 @@ class LitellmResponseAPIModel(LitellmModel):
     )
     def _query(self, messages: list[dict[str, str]], **kwargs):
         try:
+            # Remove 'timestamp' field added by agent - not supported by OpenAI responses API
+            clean_messages = [{"role": msg["role"], "content": msg["content"]} for msg in messages]
             resp = litellm.responses(
                 model=self.config.model_name,
-                input=messages if self._previous_response_id is None else messages[-1:],
+                input=clean_messages if self._previous_response_id is None else clean_messages[-1:],
                 previous_response_id=self._previous_response_id,
                 **(self.config.model_kwargs | kwargs),
             )
@@ -59,7 +62,6 @@ class LitellmResponseAPIModel(LitellmModel):
 
     def query(self, messages: list[dict[str, str]], **kwargs) -> dict:
         response = self._query(messages, **kwargs)
-        print(response)
         text = coerce_responses_text(response)
         try:
             cost = litellm.cost_calculator.completion_cost(response, model=self.config.model_name)

minisweagent/models/openrouter_model.py

@@ -56,6 +56,7 @@ class OpenRouterModel:
         self._api_key = os.getenv("OPENROUTER_API_KEY", "")
 
     @retry(
+        reraise=True,
         stop=stop_after_attempt(int(os.getenv("MSWEA_MODEL_RETRY_STOP_AFTER_ATTEMPT", "10"))),
         wait=wait_exponential(multiplier=1, min=4, max=60),
         before_sleep=before_sleep_log(logger, logging.WARNING),
@@ -97,7 +98,7 @@ 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)

minisweagent/models/portkey_model.py

@@ -74,6 +74,7 @@ class PortkeyModel:
         self.client = Portkey(**client_kwargs)
 
     @retry(
+        reraise=True,
         stop=stop_after_attempt(int(os.getenv("MSWEA_MODEL_RETRY_STOP_AFTER_ATTEMPT", "10"))),
         wait=wait_exponential(multiplier=1, min=4, max=60),
         before_sleep=before_sleep_log(logger, logging.WARNING),
@@ -90,7 +91,7 @@ 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

minisweagent/models/portkey_response_api_model.py

@@ -30,6 +30,7 @@ class PortkeyResponseAPIModel(PortkeyModel):
         self._previous_response_id: str | None = None
 
     @retry(
+        reraise=True,
         stop=stop_after_attempt(int(os.getenv("MSWEA_MODEL_RETRY_STOP_AFTER_ATTEMPT", "10"))),
         wait=wait_exponential(multiplier=1, min=4, max=60),
         before_sleep=before_sleep_log(logger, logging.WARNING),

minisweagent/models/requesty_model.py

@@ -51,6 +51,7 @@ class RequestyModel:
         self._api_key = os.getenv("REQUESTY_API_KEY", "")
 
     @retry(
+        reraise=True,
         stop=stop_after_attempt(10),
         wait=wait_exponential(multiplier=1, min=4, max=60),
         before_sleep=before_sleep_log(logger, logging.WARNING),
@@ -91,7 +92,7 @@ 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", {})

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: