Merge branch 'main' into docker_s6

.github/workflows/supply-chain-audit.yml

@@ -47,14 +47,17 @@ jobs:
           HEAD="${{ github.event.pull_request.head.sha }}"
 
           # Added lines only, excluding lockfiles.
-          DIFF=$(git diff "$BASE".."$HEAD" -- . ':!uv.lock' ':!*.lock' ':!package-lock.json' ':!yarn.lock' || true)
+          # Three-dot diff (base...head) diffs from the merge base to HEAD,
+          # so only changes introduced by this PR are included — not changes
+          # that landed on main after the PR branched off.
+          DIFF=$(git diff "$BASE"..."$HEAD" -- . ':!uv.lock' ':!*.lock' ':!package-lock.json' ':!yarn.lock' || true)
 
           FINDINGS=""
 
           # --- .pth files (auto-execute on Python startup) ---
           # The exact mechanism used in the litellm supply chain attack:
           # https://github.com/BerriAI/litellm/issues/24512
-          PTH_FILES=$(git diff --name-only "$BASE".."$HEAD" | grep '\.pth$' || true)
+          PTH_FILES=$(git diff --name-only "$BASE"..."$HEAD" | grep '\.pth$' || true)
           if [ -n "$PTH_FILES" ]; then
             FINDINGS="${FINDINGS}
           ### 🚨 CRITICAL: .pth file added or modified
@@ -97,7 +100,7 @@ jobs:
 
           # --- Install-hook files (setup.py/sitecustomize/usercustomize/__init__.pth) ---
           # These execute during pip install or interpreter startup.
-          SETUP_HITS=$(git diff --name-only "$BASE".."$HEAD" | grep -E '(^|/)(setup\.py|setup\.cfg|sitecustomize\.py|usercustomize\.py|__init__\.pth)$' || true)
+          SETUP_HITS=$(git diff --name-only "$BASE"..."$HEAD" | grep -E '(^|/)(setup\.py|setup\.cfg|sitecustomize\.py|usercustomize\.py|__init__\.pth)$' || true)
           if [ -n "$SETUP_HITS" ]; then
             FINDINGS="${FINDINGS}
           ### 🚨 CRITICAL: Install-hook file added or modified
@@ -158,7 +161,7 @@ jobs:
           HEAD="${{ github.event.pull_request.head.sha }}"
 
           # Only check added lines in pyproject.toml
-          ADDED=$(git diff "$BASE".."$HEAD" -- pyproject.toml | grep '^+' | grep -v '^+++' || true)
+          ADDED=$(git diff "$BASE"..."$HEAD" -- pyproject.toml | grep '^+' | grep -v '^+++' || true)
 
           if [ -z "$ADDED" ]; then
             echo "found=false" >> "$GITHUB_OUTPUT"

.github/workflows/tests.yml

@@ -23,11 +23,22 @@ concurrency:
 jobs:
   test:
     runs-on: ubuntu-latest
-    timeout-minutes: 60
+    timeout-minutes: 30
+    strategy:
+      fail-fast: false
+      matrix:
+        slice: [1, 2, 3, 4, 5, 6]
     steps:
       - name: Checkout code
         uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd  # v6.0.2
 
+      - name: Restore duration cache
+        uses: actions/cache/restore@27d5ce7f107fe9357f9df03efb73ab90386fccae  # v5.0.5
+        with:
+          path: test_durations.json
+          # Single stable key. main always overwrites, PRs always find it.
+          key: test-durations
+
       - name: Install ripgrep (prebuilt binary)
         run: |
           set -euo pipefail
@@ -54,7 +65,7 @@ jobs:
           source .venv/bin/activate
           uv pip install -e ".[all,dev]"
 
-      - name: Run tests
+      - name: Run tests (slice ${{ matrix.slice }}/6)
         # Per-file isolation via scripts/run_tests_parallel.py: discovers
         # every test_*.py file under tests/ (excluding integration/ + e2e/),
         # then runs `python -m pytest <file>` in a freshly-spawned subprocess
@@ -72,15 +83,61 @@ jobs:
         # state across files, which is exactly the leakage we wanted to
         # fix. ThreadPoolExecutor + subprocess.run is ~60 lines and does
         # the job with cleaner semantics.
+        #
+        # Matrix slicing (--slice I/N): files are distributed across 6
+        # jobs by cached duration (LPT algorithm) so each job gets
+        # roughly equal wall time. Without a cache, files default to 2s
+        # estimate and get split roughly evenly by count — still correct,
+        # just not perfectly balanced.
         run: |
           source .venv/bin/activate
-          python scripts/run_tests_parallel.py
+          python scripts/run_tests_parallel.py --slice ${{ matrix.slice }}/6
         env:
           # Ensure tests don't accidentally call real APIs
           OPENROUTER_API_KEY: ""
           OPENAI_API_KEY: ""
           NOUS_API_KEY: ""
 
+      - name: Upload per-slice durations
+        uses: actions/upload-artifact@043fb46d1a93c77aae656e7c1c64a875d1fc6a0a  # v7.0.1
+        with:
+          name: test-durations-slice-${{ matrix.slice }}
+          path: test_durations.json
+          retention-days: 1
+
+  # Merge per-slice duration data into a single cache, so future runs
+  # (including PRs) get balanced slicing.
+  save-durations:
+    needs: test
+    if: always() && github.ref == 'refs/heads/main'
+    runs-on: ubuntu-latest
+    steps:
+      - name: Download all slice durations
+        uses: actions/download-artifact@3e5f45b2cfb9172054b4087a40e8e0b5a5461e7c  # v8.0.1
+        with:
+          pattern: test-durations-slice-*
+          path: durations
+          merge-multiple: true
+
+      - name: Merge into single durations file
+        run: |
+          python3 -c "
+          import json, glob, os
+          merged = {}
+          for f in glob.glob('durations/*test_durations.json'):
+            with open(f) as fh:
+              merged.update(json.load(fh))
+          with open('test_durations.json', 'w') as fh:
+            json.dump(merged, fh, indent=2, sort_keys=True)
+          print(f'Merged {len(merged)} file durations')
+          "
+
+      - name: Save merged duration cache
+        uses: actions/cache/save@27d5ce7f107fe9357f9df03efb73ab90386fccae  # v5.0.5
+        with:
+          path: test_durations.json
+          key: test-durations
+
   e2e:
     runs-on: ubuntu-latest
     timeout-minutes: 15
@@ -121,4 +178,4 @@ jobs:
         env:
           OPENROUTER_API_KEY: ""
           OPENAI_API_KEY: ""
-          NOUS_API_KEY: ""
+          NOUS_API_KEY: ""