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: Improve FAQ organization

Kilian Lieretf54d514e7d9f
diff --git a/config/README.md b/config/README.md
index d708a407..a6aa80fc 100644
--- a/config/README.md
+++ b/config/README.md
@@ -6,6 +6,7 @@
* `demo`: Configs for demonstrations/talks
* Configs for running with SWE-smith are at https://github.com/SWE-bench/SWE-smith/blob/main/agent/swesmith_infer.yaml
+🔗 Tutorial on [adding custom tools](https://swe-agent.com/latest/usage/adding_custom_tools/)
🔗 For more information on config files, visit [our documentation website][docs].
You can also find the corresponding markdown files in the [`docs/` folder][source].
diff --git a/docs/faq.md b/docs/faq.md
index eb1d8f70..5cc8d118 100644
--- a/docs/faq.md
+++ b/docs/faq.md
@@ -1,8 +1,27 @@
# Frequently Asked Questions
-> What models are supported?
+## Basics
-Probably all of them! There's even a few for testing. See [models](installation/keys.md).
+> Does SWE-agent run on Windows/MacOS/Linux?
+
+Yes! Your only limitation might be the availability of the docker containers for your environments.
+But you can always execute SWE-agent in the cloud.
+
+> I got a very long error message about various configuration options not working. What's up?
+
+This is probably because of union types.
+See [this section](usage/cl_tutorial.md#union-types) for more information, but the short version is that some options (e.g., the repository or problem statement) can be specified in multiple ways, so we try every option until we find the one that works based on your inputs.
+If none of them work, we throw an error which then tells you why we cannot initialize any of the types, so this will get somewhat long and confusing.
+
+> I have a question/bug report/feature request...
+
+Please open a [github issue!](https://github.com/SWE-agent/SWE-agent/issues)!
+
+## Models
+
+> What models are supported? Do you support local models?
+
+Probably all of them, including local models! There's even a few for testing. See [models](installation/keys.md) and [more on models](config/models.md).
> What can I do if my model doesn't support function calling?
@@ -11,9 +30,7 @@ The default now is `function_calling`, but you can change it to `thought_action`
More information in the [reference](reference/parsers.md).
There are also some config example in our [config folder](https://github.com/SWE-agent/SWE-agent/tree/main/config).
-> What's up with all the output files?
-
-You're probably most interested in the `*.traj` files, which contain complete records of SWE-agent's thought process and actions. See [output files](usage/trajectories.md) for more information.
+## Configuring SWE-agent
> How can I change the demonstrations given to SWE-agent?
@@ -21,15 +38,14 @@ At the start of each run, we feed the agent a demonstration trajectory, showing
This substantially improves the agent's abilities to solve novel issues.
If you'd like to modify or totally change this demonstration, to better fit your use case, see [this](config/demonstrations.md).
-> Does SWE-agent run on Windows/MacOS/Linux?
+> Can I add custom tools?
-Yes! Your only limitation might be the availability of the docker containers for your environments.
-But you can always execute SWE-agent in the cloud.
+Yes! Take a look at [this tutorial](usage/adding_custom_tools.md).
-> I got a very long error message about various configuration options not working. What's up?
+## MISC
-This is probably because of union types.
-See [this section](usage/cl_tutorial.md#union-types) for more information, but the short version is that some options (e.g., the repository or problem statement) can be specified in multiple ways, so we try every option until we find the one that works based on your inputs.
-If none of them work, we throw an error which then tells you why we cannot initialize any of the types, so this will get somewhat long and confusing.
+> What's up with all the output files?
+
+You're probably most interested in the `*.traj` files, which contain complete records of SWE-agent's thought process and actions. See [output files](usage/trajectories.md) for more information.
{% include-markdown "_footer.md" %}
\ No newline at end of file