Merge pull request #1560 from codeflash-ai/sync-main-batch-4

chore: sync main into omni-java (batch 4/4)

Author: KRRT7

.codex/config.toml

@@ -0,0 +1,4 @@
+[mcp_servers.tessl]
+type = "stdio"
+command = "tessl"
+args = [ "mcp", "start" ]

.codex/skills/.gitignore

@@ -0,0 +1,12 @@
+{
+  "mcpServers": {
+    "tessl": {
+      "type": "stdio",
+      "command": "tessl",
+      "args": [
+        "mcp",
+        "start"
+      ]
+    }
+  }
+}

.gemini/settings.json

@@ -6,20 +6,48 @@ on:
       - main
     paths:
       - 'codeflash/version.py'
+      - 'codeflash-benchmark/codeflash_benchmark/version.py'
 
 jobs:
-  publish:
+  detect-changes:
+    runs-on: ubuntu-latest
+    outputs:
+      codeflash: ${{ steps.filter.outputs.codeflash }}
+      benchmark: ${{ steps.filter.outputs.benchmark }}
+    steps:
+      - name: Checkout
+        uses: actions/checkout@v5
+        with:
+          fetch-depth: 2
+
+      - name: Detect which packages changed
+        id: filter
+        run: |
+          if git diff --name-only HEAD~1 HEAD | grep -q '^codeflash/version.py$'; then
+            echo "codeflash=true" >> $GITHUB_OUTPUT
+          else
+            echo "codeflash=false" >> $GITHUB_OUTPUT
+          fi
+          if git diff --name-only HEAD~1 HEAD | grep -q '^codeflash-benchmark/codeflash_benchmark/version.py$'; then
+            echo "benchmark=true" >> $GITHUB_OUTPUT
+          else
+            echo "benchmark=false" >> $GITHUB_OUTPUT
+          fi
+
+  publish-codeflash:
+    needs: detect-changes
+    if: needs.detect-changes.outputs.codeflash == 'true'
     runs-on: ubuntu-latest
     environment:
       name: pypi
     permissions:
       id-token: write
-      contents: write  # Changed from 'read' to 'write' to allow tag creation
+      contents: write
     steps:
       - name: Checkout
         uses: actions/checkout@v5
         with:
-          fetch-depth: 0  # Fetch all history for proper versioning
+          fetch-depth: 0
 
       - name: Extract version from version.py
         id: extract_version
@@ -76,4 +104,76 @@ jobs:
           prerelease: false
           generate_release_notes: true
           files: |
-            dist/*
+            dist/*
+
+  publish-benchmark:
+    needs: detect-changes
+    if: needs.detect-changes.outputs.benchmark == 'true'
+    runs-on: ubuntu-latest
+    environment:
+      name: pypi
+    permissions:
+      id-token: write
+      contents: write
+    steps:
+      - name: Checkout
+        uses: actions/checkout@v5
+        with:
+          fetch-depth: 0
+
+      - name: Extract version from version.py
+        id: extract_version
+        run: |
+          VERSION=$(grep -oP '__version__ = "\K[^"]+' codeflash-benchmark/codeflash_benchmark/version.py)
+          echo "version=$VERSION" >> $GITHUB_OUTPUT
+          echo "tag=benchmark-v$VERSION" >> $GITHUB_OUTPUT
+          echo "Extracted version: $VERSION"
+
+      - name: Check if tag already exists
+        id: check_tag
+        run: |
+          if git rev-parse "${{ steps.extract_version.outputs.tag }}" >/dev/null 2>&1; then
+            echo "exists=true" >> $GITHUB_OUTPUT
+            echo "Tag ${{ steps.extract_version.outputs.tag }} already exists, skipping release"
+          else
+            echo "exists=false" >> $GITHUB_OUTPUT
+            echo "Tag ${{ steps.extract_version.outputs.tag }} does not exist, proceeding with release"
+          fi
+
+      - name: Create and push git tag
+        if: steps.check_tag.outputs.exists == 'false'
+        run: |
+          git config user.name "github-actions[bot]"
+          git config user.email "github-actions[bot]@users.noreply.github.com"
+          git tag -a "${{ steps.extract_version.outputs.tag }}" -m "Release ${{ steps.extract_version.outputs.tag }}"
+          git push origin "${{ steps.extract_version.outputs.tag }}"
+
+      - name: Install uv
+        if: steps.check_tag.outputs.exists == 'false'
+        uses: astral-sh/setup-uv@v6
+
+      - name: Build
+        if: steps.check_tag.outputs.exists == 'false'
+        run: uv build --package codeflash-benchmark
+
+      - name: Publish to PyPI
+        if: steps.check_tag.outputs.exists == 'false'
+        run: uv publish
+
+      - name: Create GitHub Release
+        if: steps.check_tag.outputs.exists == 'false'
+        uses: softprops/action-gh-release@v2
+        with:
+          tag_name: ${{ steps.extract_version.outputs.tag }}
+          name: codeflash-benchmark ${{ steps.extract_version.outputs.tag }}
+          body: |
+            ## What's Changed
+
+            Release ${{ steps.extract_version.outputs.version }} of codeflash-benchmark.
+
+            **Full Changelog**: https://github.com/${{ github.repository }}/commits/${{ steps.extract_version.outputs.tag }}
+          draft: false
+          prerelease: false
+          generate_release_notes: true
+          files: |
+            dist/*

.gemini/skills/.gitignore

@@ -15,9 +15,25 @@ jobs:
     strategy:
       fail-fast: false
       matrix:
-        python-version: ["3.9", "3.10", "3.11", "3.12", "3.13", "3.14"]
+        include:
+          - os: ubuntu-latest
+            python-version: "3.9"
+          - os: ubuntu-latest
+            python-version: "3.10"
+          - os: ubuntu-latest
+            python-version: "3.11"
+          - os: ubuntu-latest
+            python-version: "3.12"
+          - os: ubuntu-latest
+            python-version: "3.13"
+          - os: ubuntu-latest
+            python-version: "3.14"
+          - os: windows-latest
+            python-version: "3.13"
     continue-on-error: true
-    runs-on: ubuntu-latest
+    runs-on: ${{ matrix.os }}
+    env:
+      PYTHONIOENCODING: utf-8
     steps:
       - uses: actions/checkout@v4
         with:

.github/workflows/publish.yml

@@ -28,6 +28,10 @@ Discovery → Ranking → Context Extraction → Test Gen + Optimization → Bas
 - **Tracer**: Profiling system that records function call trees and timings (`tracing/`, `tracer.py`)
 - **Worktree mode**: Git worktree-based parallel optimization (`--worktree` flag)
 
+## PR Reviews
+
+- GitHub PR comments and review feedback can be stale — they may reference issues already fixed by a later commit. Before acting on review feedback, verify it still applies to the current code. If the issue no longer exists, resolve the conversation in the GitHub UI.
+
 <!-- Section below is auto-generated by `tessl install` - do not edit manually -->
 
 # Agent Rules <!-- tessl-managed -->