Simpler agent

.github/workflows/tests.yml

@@ -117,7 +117,9 @@ jobs:
           ALLOW_LOCAL_TERMINAL: true
           DEBUG_GYM_DEBUG: 1
         run: |
+          df -h
           pytest -vv -n 16 -k "not test_swe_bench and not test_swe_smith and not test_r2egym and not test_kubernetes" --timeout=600 --cov=debug_gym --cov-report=term-missing
+          df -h
       - name: Store coverage report
         uses: actions/upload-artifact@v4
         with:

README.md

@@ -99,11 +99,9 @@ We provide the below LLM-based agents, they all have minimal design and serve th
 
 | Agent name | Available Tools | Description |
 | :-: | :-: | :----- |
-| `debug_agent` | `pdb`, `rewrite`, `view`, `eval` | A minimal agent that dumps all available information into its prompt and queries the LLM to generate a command. |
-| `rewrite_agent` | `rewrite`, `view`, `eval`  | A `debug_agent` but `pdb` tool is disabled (an agent keeps rewriting). |
-| `debug_5_agent` | `pdb`, `rewrite`, `view`, `eval`  | A `debug_agent`, but `pdb` tool is only enabled after certain amount of rewrites. |
-| `grep_agent` | `grep`, `rewrite`, `view`, `eval`  | A variant of `rewrite_agent` that includes the `grep` tool for searching patterns in the codebase before making changes. |
+| `froggy_agent` | `grep`, `pdb`, `view`, `rewrite`, `eval` (configurable) | Primary debugging agent. Adjust prompts and tool lists in YAML to mimic rewrite-only, grep-heavy, or other workflows. |
 | `solution_agent` | `pdb`, `eval`  | An oracle agent that applies a gold patch (only works with `swebench` and `swesmith` benchmarks for now). The agent checks that tests are failing before applying the patch, and passing after. It also checks that `pdb` tool can be used as expected. |
+| `swe_agent` | `bash`, `rewrite`, `submit` | Baseline agent tailored for the SWE-bench setting that executes bash commands in addition to rewrites. |
 
 ---
 
@@ -171,27 +169,27 @@ We provide a human mode that enables developers to manually interact with `debug
 
 #### 3.3. Overriding Values in Config
 
-The `-p` flag is a handy way to override values defined in the config file. For example, the command below will run the rewrite_agent agent on Aider with human mode (even if the config file specifies gpt-4o). The command also overrides the default system prompt (see below for more information).
+The `-p` flag is a handy way to override values defined in the config file. For example, the command below will run the `froggy_agent` configuration on Aider with human mode (even if the config file specifies gpt-4o). The command also overrides the default system prompt (see below for more information).
 
     python scripts/run.py scripts/config_aider.yaml \
-        --agent debug_agent \
+        --agent froggy_agent \
         -v \
-        -p debug_agent.llm_name="human" \
-        -p debug_agent.system_prompt_template_file="scripts/templates/human_friendly_system_prompt.jinja"
+        -p froggy_agent.llm_name="human" \
+        -p froggy_agent.system_prompt="scripts/templates/human_friendly_system_prompt.jinja"
 
 
 #### 3.4. Customizing the System Prompt with Jinja Templates
 
 `debug-gym` allows you to fully customize the system prompt by providing a [Jinja](https://jinja.palletsprojects.com/) template file. This enables you to control the format and content of the prompt sent to the LLM, making it easier to adapt the environment to your specific needs or research experiments.
 
-To use a custom system prompt template, specify the path to your Jinja template file in your agent's configuration under `system_prompt_template_file`. For example:
+To use a custom system prompt template, specify the path to your Jinja template file in your agent's configuration under `system_prompt`. For example:
 
 ```yaml
-debug_agent:
-  system_prompt_template_file: scripts/templates/custom_system_prompt.jinja
+froggy_agent:
+    system_prompt: scripts/templates/custom_system_prompt.jinja
 ```
 
-Alternatively, you can provide a custom template from the command line with `-p <agent>.system_prompt_template_file="<path/to/template.jinja>"` (see above).
+Alternatively, you can provide a custom template from the command line with `-p <agent>.system_prompt="<path/to/template.jinja>"` (see above).
 
 Within your Jinja template, you have access to the `agent` and `info` objects, which provide all relevant context about the current environment and agent state.
 
@@ -215,10 +213,10 @@ In addition to all [built-in Jinja filters](https://jinja.palletsprojects.com/en
 
 #### Example Template
 
-```jinja
-System Prompt for Debug-Gym
+Here is an example of a custom system prompt template using Jinja:
 
-Task: {{ agent.system_prompt }}
+```jinja
+You are an autonomous debugging agent designed to fix bugs in Python code repositories.
 
 Instructions:
 {{ info.instructions }}

debug_gym/__init__.py

@@ -1 +1,3 @@
-from debug_gym.version import __version__
+from debug_gym.version import __version__ as __version__
+
+__all__ = ["__version__"]

debug_gym/agents/__init__.py

@@ -1,4 +1,9 @@
-from debug_gym.agents.debug_agent import Debug_5_Agent, DebugAgent
-from debug_gym.agents.rewrite_agent import RewriteAgent
+from debug_gym.agents.froggy_agent import FroggyAgent
 from debug_gym.agents.solution_agent import AgentSolution
 from debug_gym.agents.swe_agent import SWEAgent
+
+__all__ = [
+    "FroggyAgent",
+    "AgentSolution",
+    "SWEAgent",
+]