xiaxinhang/pr-agent
1
0
Fork 0
mirror of https://github.com/qodo-ai/pr-agent.git synced 2025-07-21 04:50:39 +08:00
Code Issues Packages Projects Releases Wiki Activity

Improve markdown docs formatting for consistency and readability

Browse Source
This commit is contained in:
Peter Dave Hello
2025-04-18 02:03:47 +08:00
parent 58f6943b12
commit f0fc777a44
62 changed files with 547 additions and 403 deletions
Download Patch File Download Diff File Expand all files Collapse all files

8
docs/docs/core-abilities/dynamic_context.md
View File

@ -7,7 +7,8 @@ This approach balances providing sufficient context for accurate analysis, while
## Introduction
Pull request code changes are retrieved in a unified diff format, showing three lines of context before and after each modified section, with additions marked by '+' and deletions by '-'.
```
```diff
@@ -12,5 +12,5 @@ def func1():
code line that already existed in the file...
code line that already existed in the file...
@ -25,7 +26,6 @@ Pull request code changes are retrieved in a unified diff format, showing three
This unified diff format can be challenging for AI models to interpret accurately, as it provides limited context for understanding the full scope of code changes.
The presentation of code using '+', '-', and ' ' symbols to indicate additions, deletions, and unchanged lines respectively also differs from the standard code formatting typically used to train AI models.
## Challenges of expanding the context window
While expanding the context window is technically feasible, it presents a more fundamental trade-off:
@ -43,6 +43,7 @@ Pull requests often encompass multiple changes across many files, potentially sp
- Increased context expands the token count, increasing processing time and cost, and may prevent the model from processing the entire pull request in a single pass.
## Asymmetric and dynamic context
To address these challenges, Qodo Merge employs an **asymmetric** and **dynamic** context strategy, providing the model with more focused and relevant context information for each code change.
**Asymmetric:**
@ -62,7 +63,8 @@ To prevent overwhelming the model with excessive context, we impose a limit on t
This balance allows for comprehensive understanding while maintaining efficiency and limiting context token usage.
## Appendix - relevant configuration options
```
```toml
[config]
patch_extension_skip_types =[".md",".txt"] # Skip files with these extensions when trying to extend the context
allow_dynamic_context=true # Allow dynamic context extension