DFPY-79: Prepare 4.5 release readiness

.bumpversion.cfg

@@ -1,5 +1,5 @@
 [bumpversion]
-current_version = 4.3.0
+current_version = 4.4.0a5
 commit = True
 tag = True
 tag_name = v{new_version}
@@ -20,7 +20,3 @@ values =
 [bumpversion:file:datafog/__about__.py]
 search = __version__ = "{current_version}"
 replace = __version__ = "{new_version}"
-
-[bumpversion:file:setup.py]
-search = version="{current_version}"
-replace = version="{new_version}"

.github/workflows/benchmark.yml

@@ -13,12 +13,12 @@ jobs:
   benchmark:
     runs-on: ubuntu-latest
     steps:
-      - uses: actions/checkout@v4
+      - uses: actions/checkout@v6
         with:
           fetch-depth: 0 # Fetch all history for proper comparison
 
       - name: Set up Python
-        uses: actions/setup-python@v5
+        uses: actions/setup-python@v6
         with:
           python-version: "3.10"
           cache: "pip"
@@ -34,7 +34,7 @@ jobs:
           python -m pytest --collect-only tests/benchmark_text_service.py::test_regex_performance
 
       - name: Restore benchmark data
-        uses: actions/cache@v4
+        uses: actions/cache@v5
         with:
           path: .benchmarks
           # Updated cache key to reset baseline due to performance optimization changes
@@ -101,7 +101,7 @@ jobs:
           # fi
 
       - name: Upload benchmark results
-        uses: actions/upload-artifact@v4
+        uses: actions/upload-artifact@v7
         with:
           name: benchmark-results
           path: |

.github/workflows/ci.yml

@@ -14,8 +14,8 @@ jobs:
   lint:
     runs-on: ubuntu-latest
     steps:
-      - uses: actions/checkout@v4
-      - uses: actions/setup-python@v5
+      - uses: actions/checkout@v6
+      - uses: actions/setup-python@v6
         with:
           python-version: "3.10"
           cache: "pip"
@@ -31,18 +31,10 @@ jobs:
       matrix:
         python-version: ["3.10", "3.11", "3.12", "3.13"]
         install-profile: ["core", "nlp", "nlp-advanced"]
-        exclude:
-          # v4.4.0 claims Python 3.13 support for core + CLI first.
-          # Optional heavyweight profiles remain validated separately before
-          # we advertise Python 3.13 support for them.
-          - python-version: "3.13"
-            install-profile: "nlp"
-          - python-version: "3.13"
-            install-profile: "nlp-advanced"
     steps:
-      - uses: actions/checkout@v4
+      - uses: actions/checkout@v6
       - name: Set up Python
-        uses: actions/setup-python@v5
+        uses: actions/setup-python@v6
         with:
           python-version: ${{ matrix.python-version }}
           cache: "pip"
@@ -148,7 +140,7 @@ jobs:
           PY
 
       - name: Upload coverage
-        uses: codecov/codecov-action@v5
+        uses: codecov/codecov-action@v6
         with:
           files: ./coverage.xml
           flags: ${{ matrix.install-profile }}-py${{ matrix.python-version }}
@@ -159,6 +151,7 @@ jobs:
     strategy:
       fail-fast: false
       matrix:
+        python-version: ["3.11"]
         install-profile:
           - core
           - cli
@@ -167,18 +160,31 @@ jobs:
           - ocr
           - distributed
           - web
+        include:
+          - python-version: "3.13"
+            install-profile: nlp
+          - python-version: "3.13"
+            install-profile: nlp-advanced
+          - python-version: "3.13"
+            install-profile: ocr
     steps:
-      - uses: actions/checkout@v4
+      - uses: actions/checkout@v6
       - name: Set up Python
-        uses: actions/setup-python@v5
+        uses: actions/setup-python@v6
         with:
-          python-version: "3.11"
+          python-version: ${{ matrix.python-version }}
           cache: "pip"
 
       - name: Upgrade pip
         run: |
           python -m pip install --upgrade pip
 
+      - name: Install Tesseract OCR
+        if: matrix.install-profile == 'ocr'
+        run: |
+          sudo apt-get update
+          sudo apt-get install -y tesseract-ocr libtesseract-dev
+
       - name: Install dependencies (core)
         if: matrix.install-profile == 'core'
         run: |
@@ -192,14 +198,15 @@ jobs:
       - name: Run install profile smoke test
         env:
           DATAFOG_INSTALL_PROFILE: ${{ matrix.install-profile }}
+          DATAFOG_REQUIRE_TESSERACT: ${{ matrix.install-profile == 'ocr' && '1' || '' }}
         run: |
           pytest tests/test_install_profiles.py -q
 
   wheel-size:
     runs-on: ubuntu-latest
     steps:
-      - uses: actions/checkout@v4
-      - uses: actions/setup-python@v5
+      - uses: actions/checkout@v6
+      - uses: actions/setup-python@v6
         with:
           python-version: "3.10"
           cache: "pip"

.github/workflows/release.yml

@@ -61,11 +61,11 @@ jobs:
             BRANCH="dev"
           fi
 
-          echo "release_type=$TYPE" >> $GITHUB_OUTPUT
-          echo "target_branch=$BRANCH" >> $GITHUB_OUTPUT
+          echo "release_type=$TYPE" >> "$GITHUB_OUTPUT"
+          echo "target_branch=$BRANCH" >> "$GITHUB_OUTPUT"
           echo "Release type: $TYPE from $BRANCH"
 
-      - uses: actions/checkout@v4
+      - uses: actions/checkout@v6
         with:
           fetch-depth: 0
           ref: ${{ steps.resolve.outputs.target_branch }}
@@ -86,15 +86,15 @@ jobs:
           if [ -z "$LAST_TAG" ]; then
             COMMIT_COUNT=$(git rev-list --count --since="7 days ago" HEAD)
           else
-            COMMIT_COUNT=$(git rev-list --count ${LAST_TAG}..HEAD)
+            COMMIT_COUNT=$(git rev-list --count "${LAST_TAG}..HEAD")
           fi
 
           echo "Commits since ${LAST_TAG:-'(none)'}: $COMMIT_COUNT"
 
           if [ "$COMMIT_COUNT" -gt 0 ] || [ "${{ inputs.force_build }}" = "true" ]; then
-            echo "has_changes=true" >> $GITHUB_OUTPUT
+            echo "has_changes=true" >> "$GITHUB_OUTPUT"
           else
-            echo "has_changes=false" >> $GITHUB_OUTPUT
+            echo "has_changes=false" >> "$GITHUB_OUTPUT"
             echo "No changes detected, skipping release"
           fi
 
@@ -107,13 +107,13 @@ jobs:
       matrix:
         python-version: ["3.10", "3.11", "3.12"]
     steps:
-      - uses: actions/checkout@v4
+      - uses: actions/checkout@v6
         with:
           fetch-depth: 0
           ref: ${{ needs.determine-release.outputs.target_branch }}
 
       - name: Set up Python ${{ matrix.python-version }}
-        uses: actions/setup-python@v5
+        uses: actions/setup-python@v6
         with:
           python-version: ${{ matrix.python-version }}
           cache: "pip"
@@ -145,13 +145,13 @@ jobs:
     if: needs.determine-release.outputs.has_changes == 'true'
     runs-on: ubuntu-latest
     steps:
-      - uses: actions/checkout@v4
+      - uses: actions/checkout@v6
         with:
           fetch-depth: 0
           ref: ${{ needs.determine-release.outputs.target_branch }}
 
       - name: Set up Python 3.13
-        uses: actions/setup-python@v5
+        uses: actions/setup-python@v6
         with:
           python-version: "3.13"
           cache: "pip"
@@ -177,14 +177,14 @@ jobs:
     outputs:
       version: ${{ steps.version.outputs.version }}
     steps:
-      - uses: actions/checkout@v4
+      - uses: actions/checkout@v6
         with:
           fetch-depth: 0
           ref: ${{ needs.determine-release.outputs.target_branch }}
           token: ${{ secrets.GH_PAT }}
 
       - name: Set up Python
-        uses: actions/setup-python@v5
+        uses: actions/setup-python@v6
         with:
           python-version: "3.11"
 
@@ -241,7 +241,7 @@ jobs:
             VERSION="$BASE"
           fi
 
-          echo "version=$VERSION" >> $GITHUB_OUTPUT
+          echo "version=$VERSION" >> "$GITHUB_OUTPUT"
           echo "Publishing version: $VERSION"
 
           sed -i "s/__version__ = \".*\"/__version__ = \"$VERSION\"/" datafog/__about__.py
@@ -322,7 +322,7 @@ jobs:
     if: needs.determine-release.outputs.release_type != 'stable' && inputs.dry_run != true
     runs-on: ubuntu-latest
     steps:
-      - uses: actions/checkout@v4
+      - uses: actions/checkout@v6
 
       - name: Prune old alpha releases (keep 7)
         if: needs.determine-release.outputs.release_type == 'alpha'

.gitignore

@@ -24,6 +24,7 @@ error_log.txt
 # Environment
 .env
 .venv
+.venv*/
 venv/
 env/
 examples/venv/
@@ -58,14 +59,15 @@ docs/*
 !docs/conf.py
 !docs/Makefile
 !docs/make.bat
+!docs/optional-surfaces.rst
+!docs/agents/
+!docs/agents/**
 !docs/audit/
 !docs/audit/**
 
 # Keep all directories but ignore their contents
 */**/__pycache__/
 
-# Keep all files but ignore their contents
-Claude.md
 notes/benchmarking_notes.md
 Roadmap.md
 notes/*