xiaxinhang/pr-agent
1
0
Fork 0
mirror of https://github.com/qodo-ai/pr-agent.git synced 2025-07-03 12:20:38 +08:00
Code Issues Packages Projects Releases Wiki Activity

feat: add example output duplication option for code suggestions prompts

Browse Source
This commit is contained in:
mrT23
2025-01-02 12:46:50 +02:00
parent e695af6917
commit a1a7c8e44c
4 changed files with 48 additions and 3 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
docs/docs/usage-guide/changing_a_model.md
View File

@ -48,8 +48,8 @@ api_base = "http://localhost:11434" # or whatever port you're running Ollama on
!!! note "Local models vs commercial models"
Qodo Merge is compatible with almost any AI model, but analyzing complex code repositories and pull requests requires a model specifically optimized for code analysis.
Commercial models such as GPT-4, Claude Sonnet, and Gemini have demonstrated robust capabilities in generating structured output for code analysis. In contrast, most open-source models currently available (as of January 2025) face challenges with these complex tasks.
Based on our testing, local open-source models are suitable for experimentation and learning purposes, but they may not be suitable for production-level code analysis tasks.
Commercial models such as GPT-4, Claude Sonnet, and Gemini have demonstrated robust capabilities in generating structured output for code analysis tasks with large input. In contrast, most open-source models currently available (as of January 2025) face challenges with these complex tasks.
Based on our testing, local open-source models are suitable for experimentation and learning purposes, but they are not suitable for production-level code analysis tasks.
Hence, for production workflows and real-world code analysis, we recommend using commercial models.
### Hugging Face Inference Endpoints

24
pr_agent/settings/pr_code_suggestions_prompts.toml
View File

@ -125,6 +125,30 @@ The PR Diff:
{{ diff_no_line_numbers|trim }}
======
{%- if duplicate_prompt_examples %}
Example output:
```yaml
code_suggestions:
- relevant_file: |
src/file1.py
language: |
python
suggestion_content: |
...
existing_code: |
...
improved_code: |
...
one_sentence_summary: |
...
label: |
...
```
(replace '...' with actual content)
{%- endif %}
Response (should be a valid YAML, and nothing else):
```yaml

19
pr_agent/settings/pr_code_suggestions_reflect_prompts.toml
View File

@ -122,6 +122,25 @@ Below are {{ num_code_suggestions }} AI-generated code suggestions for enhancing
======
{%- if duplicate_prompt_examples %}
Example output:
```yaml
code_suggestions:
- suggestion_summary: |
...
relevant_file: "..."
relevant_lines_start: ...
relevant_lines_end: ...
suggestion_score: ...
why: |
...
- ...
```
(replace '...' with actual content)
{%- endif %}
Response (should be a valid YAML, and nothing else):
```yaml
"""

4
pr_agent/tools/pr_code_suggestions.py
View File

@ -81,6 +81,7 @@ class PRCodeSuggestions:
"relevant_best_practices": "",
"is_ai_metadata": get_settings().get("config.enable_ai_metadata", False),
"focus_only_on_problems": get_settings().get("pr_code_suggestions.focus_only_on_problems", False),
'duplicate_prompt_examples': get_settings().config.get('duplicate_prompt_examples', False),
}
self.pr_code_suggestions_prompt_system = get_settings().pr_code_suggestions_prompt.system
@ -830,7 +831,8 @@ class PRCodeSuggestions:
"diff": patches_diff,
'num_code_suggestions': len(suggestion_list),
'prev_suggestions_str': prev_suggestions_str,
"is_ai_metadata": get_settings().get("config.enable_ai_metadata", False)}
"is_ai_metadata": get_settings().get("config.enable_ai_metadata", False),
'duplicate_prompt_examples': get_settings().config.get('duplicate_prompt_examples', False)}
environment = Environment(undefined=StrictUndefined)
if dedicated_prompt: