You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
feat: enhance documentation with additional repository metadata secti… (#2021)
* feat: enhance documentation with additional repository metadata section and update model references
* feat: update default model to GPT-5 and clarify configuration instructions
Copy file name to clipboardExpand all lines: docs/docs/usage-guide/additional_configurations.md
+21-27Lines changed: 21 additions & 27 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -97,33 +97,6 @@ This will set the response language globally for all the commands to Italian.
97
97
98
98
[//]: #(which divides the PR into chunks, and processes each chunk separately. With this mode, regardless of the model, no compression will be done (but for large PRs, multiple model calls may occur))
99
99
100
-
## Patch Extra Lines
101
-
102
-
By default, around any change in your PR, git patch provides three lines of context above and below the change.
103
-
104
-
```
105
-
@@ -12,5 +12,5 @@ def func1():
106
-
code line that already existed in the file...
107
-
code line that already existed in the file...
108
-
code line that already existed in the file....
109
-
-code line that was removed in the PR
110
-
+new code line added in the PR
111
-
code line that already existed in the file...
112
-
code line that already existed in the file...
113
-
code line that already existed in the file...
114
-
```
115
-
116
-
Qodo Merge will try to increase the number of lines of context, via the parameter:
117
-
118
-
```
119
-
[config]
120
-
patch_extra_lines_before=3
121
-
patch_extra_lines_after=1
122
-
```
123
-
124
-
Increasing this number provides more context to the model, but will also increase the token budget, and may overwhelm the model with too much information, unrelated to the actual PR code changes.
125
-
126
-
If the PR is too large (see [PR Compression strategy](https://github.com/Codium-ai/pr-agent/blob/main/PR_COMPRESSION.md)), Qodo Merge may automatically set this number to 0, and will use the original git patch.
127
100
128
101
## Log Level
129
102
@@ -158,6 +131,27 @@ LANGSMITH_PROJECT=<project>
158
131
LANGSMITH_BASE_URL=<url>
159
132
```
160
133
134
+
## Bringing additional repository metadata to Qodo Merge 💎
135
+
136
+
To provide Qodo Merge with additional context about your project, you can enable automatic repository metadata detection.
137
+
138
+
If you set
139
+
140
+
```toml
141
+
[config]
142
+
add_repo_metadata = true
143
+
```
144
+
145
+
Qodo Merge will attempt to fetch repository metadata from the root directory of your PR's head branch, looking for common metadata files such as:
146
+
[AGENT.MD](https://agents.md/), [QODO.MD](https://docs.qodo.ai/qodo-documentation/qodo-command/getting-started/setup-and-quickstart), [CLAUDE.MD](https://www.anthropic.com/engineering/claude-code-best-practices), etc.
147
+
148
+
You can also specify custom filenames to search for:
Copy file name to clipboardExpand all lines: docs/docs/usage-guide/changing_a_model.md
+3-2Lines changed: 3 additions & 2 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -1,7 +1,8 @@
1
1
## Changing a model in PR-Agent
2
2
3
-
See [here](https://github.com/Codium-ai/pr-agent/blob/main/pr_agent/algo/__init__.py) for a list of available models.
4
-
To use a different model than the default (o4-mini), you need to edit in the [configuration file](https://github.com/Codium-ai/pr-agent/blob/main/pr_agent/settings/configuration.toml#L2) the fields:
3
+
See [here](https://github.com/Codium-ai/pr-agent/blob/main/pr_agent/algo/__init__.py) for a list of supported models in PR-Agent.
4
+
The default model of PR-Agent is `GPT-5` from OpenAI.
5
+
To use a different model than the default, you need to edit in the [configuration file](https://github.com/Codium-ai/pr-agent/blob/main/pr_agent/settings/configuration.toml#L2) the fields:
0 commit comments