Fix extended thinking and allow per-repo context files (AGENTS.md, CLAUDE.md, etc.) to be included as context#2387
Open
avidspartan1 wants to merge 9 commits into
Open
Conversation
Contributor
Review Summary by QodoSupport Claude model overrides and repository context files in AI prompts
WalkthroughsDescription• Add support for overriding Claude extended thinking models via config • Include repository context files (AGENTS.md, CLAUDE.md, etc.) in AI prompts • Extend git provider interface with repo file content retrieval capability • Add comprehensive tests for new features and fix minor code issues Diagramflowchart LR
A["Config Settings"] -->|claude_extended_thinking_models_override| B["LiteLLM Handler"]
C["Repo Context Files"] -->|repo_context_files config| D["build_repo_context"]
D -->|fetches files| E["Git Provider"]
D -->|renders context| F["Instruction Files"]
F -->|injected into| G["AI Prompts"]
B -->|uses models| G
File Changes1. pr_agent/algo/__init__.py
|
Contributor
Code Review by Qodo
Context used 1. test_repo_context.py import order
|
![qodo-free-for-open-source-projects[bot]](https://avatars.githubusercontent.com/in/1068000?s=60&v=4){kind=small}
Contributor
|
Persistent review updated to latest commit 2b313ad |
avidspartan1
force-pushed
the
feat/improvements
branch
from
2b313ad to
50de2c6
Compare
Contributor
|
Persistent review updated to latest commit 50de2c6 |
avidspartan1
force-pushed
the
feat/improvements
branch
from
50de2c6 to
e93cad2
Compare
Contributor
|
Persistent review updated to latest commit e93cad2 |
Comment on lines
+136
to
+140
| cache_key = _get_repo_context_cache_key(context_files, max_lines) | ||
| process_cache_key = _get_repo_context_process_cache_key(git_provider, context_files, max_lines) | ||
| if process_cache_key is not None and process_cache_key in _repo_context_process_cache: | ||
| return _repo_context_process_cache[process_cache_key] | ||
|
|
Contributor
There was a problem hiding this comment.
1. Unbounded context process cache 🐞 Bug ☼ Reliability
build_repo_context() stores repo context in a module-level _repo_context_process_cache keyed by PR URL without TTL/eviction, so long-lived servers can accumulate entries indefinitely and can keep serving stale instruction files for a PR until process restart.
Agent Prompt
## Issue description
`build_repo_context()` uses a module-level dict (`_repo_context_process_cache`) as a process-wide cache keyed by PR URL. Because it has no TTL/max-size eviction, long-lived servers will:
1) grow memory unbounded as more PR URLs are processed, and
2) potentially serve stale instruction-file contents for the same PR URL even if the repo default-branch instruction files change.
## Issue Context
This cache is independent of any single provider instance and persists for the lifetime of the Python process. The repo runs as a long-lived FastAPI/uvicorn app in webhook deployments, so the cache lifetime is effectively “forever”.
## Fix Focus Areas
- pr_agent/algo/repo_context.py[13-14]
- pr_agent/algo/repo_context.py[136-140]
- pr_agent/algo/repo_context.py[175-185]
## How to fix
- Replace `_repo_context_process_cache` with a bounded/evicting structure (e.g., `functools.lru_cache(maxsize=...)`, or a TTL cache).
- If keeping cross-instance caching, include an invalidation strategy (TTL is simplest) so updated repo instruction files eventually refresh.
- Ensure empty-string entries also follow the eviction policy to avoid permanently pinning “missing” results for long-running processes.
ⓘ Copy this prompt and use it to remediate the issue with your preferred AI generation tools
|
Hey, could you adjust your implementation for Gitea in I made it manually for now, but I think it would be interesting to include it in this PR as well. |
Contributor
Code Review by QodoNew Review StartedThis review has been superseded by a new analysis |
Author
done! |
avidspartan1
force-pushed
the
feat/improvements
branch
from
aae35a9 to
2e11c1f
Compare
Contributor
|
Persistent review updated to latest commit 2e11c1f |
Comment on lines
+3
to
+4
| import pytest | ||
| from jinja2 import Environment, StrictUndefined |
Contributor
There was a problem hiding this comment.
1. test_repo_context.py import order 📘 Rule violation ⚙ Maintainability
The new test file has third-party imports out of isort order (pytest imported before jinja2), which will violate the repository’s Ruff/isort checks. This can fail CI linting and introduce style churn.
Agent Prompt
## Issue description
The imports in `tests/unittest/test_repo_context.py` are not ordered as isort/Ruff expects for third-party imports.
## Issue Context
`pyproject.toml` enables Ruff isort checks (`I001`/`I002`). The file currently imports `pytest` before `jinja2`, which is not deterministic/alphabetical.
## Fix Focus Areas
- tests/unittest/test_repo_context.py[3-5]
ⓘ Copy this prompt and use it to remediate the issue with your preferred AI generation tools
Author
There was a problem hiding this comment.
believe this is a false positive; ruff puts back the order they currently are in
Contributor
|
Persistent review updated to latest commit 145b93f |
Contributor
|
Persistent review updated to latest commit a92f7b3 |
Contributor
|
Persistent review updated to latest commit 982821f |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Resolves #2357.
I backed out my other PR because it was too many changes (previously included "de-dupe inline comments") in one PR.