Skip to content
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension


Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
2 changes: 1 addition & 1 deletion .env.example
Original file line number Diff line number Diff line change
Expand Up @@ -6,4 +6,4 @@ GITHUB_TOKEN=your_github_token_here

# Optional: LLM Provider API Keys (configure the ones you plan to use)
OPENAI_API_KEY=
ANTHROPIC_API_KEY=
ANTHROPIC_API_KEY=
23 changes: 23 additions & 0 deletions .github/workflows/pre-commit.yaml
Original file line number Diff line number Diff line change
@@ -0,0 +1,23 @@
name: Pre-commit

on:
push:
pull_request:

jobs:
pre-commit:
runs-on: ubuntu-latest
defaults:
run:
shell: bash -l {0}
steps:
- uses: actions/checkout@v5
- uses: actions/setup-python@v5
with:
python-version: "3.11"
- name: Install uv
run: curl -LsSf https://astral.sh/uv/install.sh | sh
- name: Install dependencies
run: uv sync --extra dev
- name: Run pre-commit
run: uv run pre-commit run --all-files --show-diff-on-failure
2 changes: 1 addition & 1 deletion .pre-commit-config.yaml
Original file line number Diff line number Diff line change
Expand Up @@ -15,7 +15,7 @@ repos:
- id: debug-statements

- repo: https://github.com/crate-ci/typos
rev: v1
rev: v1.46.0
hooks:
- id: typos
files: \.(py|md|rst|yaml|toml)
Expand Down
2 changes: 1 addition & 1 deletion codeclash/analysis/llm_as_judge/hallucination.yaml
Original file line number Diff line number Diff line change
Expand Up @@ -71,7 +71,7 @@ system_prompt: |
by reasoning)
- "My bot is working perfectly" (this is just a slightly overconfident statement, but not a concrete claim that can be corroborated or disproven)
This violates 2 (the statement of fact is not concrete)
- Agent using an incorrect linenumber when referring to a code snippet (as long as the agent recovers later on and this doens't cause an edit to
- Agent using an incorrect linenumber when referring to a code snippet (as long as the agent recovers later on and this doesn't cause an edit to
fail without being able to recover). This violates 6 (the incident is not relevant to the overall trajectory and objective of the agent)
- Anything related to failed edits as long as the failure is spotted and corrected later on.

Expand Down
1 change: 0 additions & 1 deletion codeclash/arenas/battlecode23/BattleCode23.Dockerfile
Original file line number Diff line number Diff line change
Expand Up @@ -11,4 +11,3 @@ RUN git clone https://github.com/CodeClash-ai/BattleCode2023.git /workspace \
WORKDIR /workspace

RUN chmod +x gradlew && ./gradlew update

Loading
Loading