Skip to content

SWE-agent takes a GitHub issue and tries to automatically fix it, using your LM of choice. It can also be employed for offensive cybersecurity or competitive coding challenges. [NeurIPS 2024]

Doc: Update model names and fix syntax errors in usage documentation (#1217)

Joshua Shanksd1b14ba5e5f4
diff --git a/docs/usage/cl_tutorial.md b/docs/usage/cl_tutorial.md
index bf7caa11..a5e9fe85 100644
--- a/docs/usage/cl_tutorial.md
+++ b/docs/usage/cl_tutorial.md
@@ -14,7 +14,7 @@ Before we start with a more structured explanation of the command line options,
```bash title="Fix a github issue"
sweagent run \
- --agent.model.name=gpt4 \
+ --agent.model.name=gpt-4o \
--agent.model.per_instance_cost_limit=2.00 \
--env.repo.github_url=https://github.com/SWE-agent/test-repo \
--problem_statement.github_url=https://github.com/SWE-agent/test-repo/issues/1
@@ -30,7 +30,7 @@ sweagent run \
```bash title="Fix a bug in a local repository using a custom docker image" hl_lines="4 5 6"
git clone https://github.com/SWE-agent/test-repo.git
sweagent run \
- --agent.model.name=claude-sonnet-4-20250514\
+ --agent.model.name=claude-sonnet-4-20250514 \
--env.repo.path=test-repo \
--problem_statement.path=test-repo/problem_statements/1.md \
--env.deployment.image=python:3.12
@@ -68,7 +68,7 @@ All configuration options can be specified either in one or more `.yaml` files,
```yaml title="my_run.yaml"
agent:
model:
- name: gpt4
+ name: gpt-4o
per_instance_cost_limit: 2.00
env:
repo:
@@ -92,7 +92,7 @@ But we can also split it up into multiple files and additional command line opti
```yaml title="agent.yaml"
agent:
model:
- name: gpt4
+ name: gpt-4o
per_instance_cost_limit: 2.00
```
diff --git a/docs/usage/coding_challenges.md b/docs/usage/coding_challenges.md
index efd8fb3d..0c5f6cf2 100644
--- a/docs/usage/coding_challenges.md
+++ b/docs/usage/coding_challenges.md
@@ -59,7 +59,7 @@ sweagent run \
--config config/coding_challenge.yaml \
--problem_statement.path=problem.md \
--env.repo.path=/path/to/empty \
- --agent.model.name=gpt4 \
+ --agent.model.name=gpt-4o \
--agent.model.per_instance_cost_limit 3.0 \
--actions.apply_patch_locally=True
```
diff --git a/docs/usage/hello_world.md b/docs/usage/hello_world.md
index 57753aa5..8321a87a 100644
--- a/docs/usage/hello_world.md
+++ b/docs/usage/hello_world.md
@@ -1,7 +1,7 @@
# Hello world
-!!! abstract "Fix a github issue with SWE-agent"
- In this tutorial, we will fix a github issue with SWE-agent using the command line interface.
+!!! abstract "Fix a GitHub issue with SWE-agent"
+ In this tutorial, we will fix a GitHub issue with SWE-agent using the command line interface.
* Make sure you have [installed](../installation/index.md) SWE-agent and have a [language model](../installation/keys.md) set up.
* We will be executing code in a Docker sandbox, so make sure you have docker installed ([docker troubleshooting](../installation/tips.md)).
diff --git a/docs/usage/whats_next.md b/docs/usage/whats_next.md
index a6489c01..b2d28f8c 100644
--- a/docs/usage/whats_next.md
+++ b/docs/usage/whats_next.md
@@ -6,7 +6,7 @@ Here are some ideas for what to check out next: There are two more sections on t
* [User guides](index.md): This covers selected topics in more detail, for example
* What are all the different [subcommands](cli.md) of `sweagent`?
- * How to [configure swe-agent](../../config/)?
+ * How to [configure swe-agent](../config/index.md)?
* What's the main [architecture](../background/architecture.md) of SWE-agent?
* [API reference](../reference/index.md) for complete lists of all configuration options.