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
57 changes: 57 additions & 0 deletions .github/workflows/claude-code-review.yml
Original file line number Diff line number Diff line change
@@ -0,0 +1,57 @@
name: Claude Code Review

on:
pull_request:
types: [opened, synchronize]
# Optional: Only run on specific file changes
# paths:
# - "src/**/*.ts"
# - "src/**/*.tsx"
# - "src/**/*.js"
# - "src/**/*.jsx"

jobs:
claude-review:
# Optional: Filter by PR author
# if: |
# github.event.pull_request.user.login == 'external-contributor' ||
# github.event.pull_request.user.login == 'new-developer' ||
# github.event.pull_request.author_association == 'FIRST_TIME_CONTRIBUTOR'

runs-on: ubuntu-latest
permissions:
contents: read
pull-requests: read
issues: read
id-token: write

steps:
- name: Checkout repository
uses: actions/checkout@v4
with:
fetch-depth: 1

- name: Run Claude Code Review
id: claude-review
uses: anthropics/claude-code-action@v1
with:
anthropic_api_key: ${{ secrets.ANTHROPIC_API_KEY }}
prompt: |
REPO: ${{ github.repository }}
PR NUMBER: ${{ github.event.pull_request.number }}
Please review this pull request and provide feedback on:
- Code quality and best practices
- Potential bugs or issues
- Performance considerations
- Security concerns
- Test coverage
Use the repository's CLAUDE.md for guidance on style and conventions. Be constructive and helpful in your feedback.
Use `gh pr comment` with your Bash tool to leave your review as a comment on the PR.
# See https://github.com/anthropics/claude-code-action/blob/main/docs/usage.md
# or https://code.claude.com/docs/en/cli-reference for available options
claude_args: '--allowed-tools "Bash(gh issue view:*),Bash(gh search:*),Bash(gh issue list:*),Bash(gh pr comment:*),Bash(gh pr diff:*),Bash(gh pr view:*),Bash(gh pr list:*)"'

50 changes: 50 additions & 0 deletions .github/workflows/claude.yml
Original file line number Diff line number Diff line change
@@ -0,0 +1,50 @@
name: Claude Code

on:
issue_comment:
types: [created]
pull_request_review_comment:
types: [created]
issues:
types: [opened, assigned]
pull_request_review:
types: [submitted]

jobs:
claude:
if: |
(github.event_name == 'issue_comment' && contains(github.event.comment.body, '@claude')) ||
(github.event_name == 'pull_request_review_comment' && contains(github.event.comment.body, '@claude')) ||
(github.event_name == 'pull_request_review' && contains(github.event.review.body, '@claude')) ||
(github.event_name == 'issues' && (contains(github.event.issue.body, '@claude') || contains(github.event.issue.title, '@claude')))
runs-on: ubuntu-latest
permissions:
contents: read
pull-requests: read
issues: read
id-token: write
actions: read # Required for Claude to read CI results on PRs
steps:
- name: Checkout repository
uses: actions/checkout@v4
with:
fetch-depth: 1

- name: Run Claude Code
id: claude
uses: anthropics/claude-code-action@v1
with:
anthropic_api_key: ${{ secrets.ANTHROPIC_API_KEY }}

# This is an optional setting that allows Claude to read CI results on PRs
additional_permissions: |
actions: read
# Optional: Give a custom prompt to Claude. If this is not specified, Claude will perform the instructions specified in the comment that tagged it.
# prompt: 'Update the pull request description to include a summary of changes.'

# Optional: Add claude_args to customize behavior and configuration
# See https://github.com/anthropics/claude-code-action/blob/main/docs/usage.md
# or https://code.claude.com/docs/en/cli-reference for available options
# claude_args: '--allowed-tools Bash(gh pr:*)'

19 changes: 13 additions & 6 deletions codeflash/verification/pytest_plugin.py
Original file line number Diff line number Diff line change
Expand Up @@ -12,7 +12,6 @@

# System Imports
from pathlib import Path
from statistics import mean, median
from typing import TYPE_CHECKING, Any, Callable, Optional
from unittest import TestCase

Expand Down Expand Up @@ -297,20 +296,28 @@ def should_stop(
return False

recent = runtimes[-window:]
m = median(recent)

# Use sorted array for faster median and min/max operations
recent_sorted = sorted(recent)
mid = window // 2
m = recent_sorted[mid] if window % 2 else (recent_sorted[mid - 1] + recent_sorted[mid]) / 2

# 1) All recent points close to the median
centered = all(abs(r - m) / m <= center_rel_tol for r in recent)
centered = True
for r in recent:
if abs(r - m) / m > center_rel_tol:
centered = False
break

# 2) Window spread is small
r_min, r_max = min(recent), max(recent)
r_min, r_max = recent_sorted[0], recent_sorted[-1]
spread_ok = (r_max - r_min) / r_min <= spread_rel_tol

# 3) No strong downward trend (still improving)
# Compare first half vs second half
half = window // 2
first = mean(recent[:half])
second = mean(recent[half:])
first = sum(recent[:half]) / half
second = sum(recent[half:]) / (window - half)
slope_ok = (first - second) / first <= slope_rel_tol

return centered and spread_ok and slope_ok
Expand Down
Binary file added docs/images/priority-order.png
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
6 changes: 4 additions & 2 deletions docs/optimizing-with-codeflash/trace-and-optimize.mdx
Original file line number Diff line number Diff line change
Expand Up @@ -6,9 +6,11 @@ sidebarTitle: "Optimize E2E Workflows"
keywords: ["tracing", "workflow optimization", "replay tests", "end-to-end", "script optimization", "context manager"]
---

Codeflash supports optimizing an entire Python script end-to-end by tracing the script's execution and generating Replay Tests.
Codeflash can optimize an entire Python script end-to-end by tracing the script's execution and generating Replay Tests.
Tracing follows the execution of a script, profiles it and captures inputs to all functions it called, allowing them to be replayed during optimization.
Codeflash uses these Replay Tests to optimize all functions called in the script, starting from the most important ones.
Codeflash uses these Replay Tests to optimize the most important functions called in the script, delivering the best performance for your workflow.

![Function Optimization](/images/priority-order.png)

To optimize a script, `python myscript.py`, simply replace `python` with `codeflash optimize` and run the following command:

Expand Down
Loading