Merge branch 'exp/consistent-loop-break' of github.com:codeflash-ai/codeflash into exp/consistent-loop-break

Author: mohammedahmed18

.github/workflows/claude-code-review.yml

@@ -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:*)"'
+

.github/workflows/claude.yml

@@ -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:*)'
+

codeflash/verification/pytest_plugin.py

@@ -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
 
@@ -309,20 +308,28 @@ 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

docs/images/priority-order.png

@@ -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: