ci: add notify-failure to auto-merge and cleanup jobs, clean up redundant env

- Add notify-failure composite action to ci/auto-merge and
  build-images/cleanup jobs (previously missing — failures in these
  jobs went unnoticed)
- Remove redundant step-level CI_GITEA_API_TOKEN/CI_GITEA_USERNAME
  env vars now that workflow-level env: block provides them
- Remove redundant step-level PYTHONPATH env (already in workflow env)
- Update ADR-0003 adoption scope to reflect notify-failure coverage
- Update ci-cd-workflow.md with explicit job list for notify-failure
- Update CHANGELOG with bug fix and cleanup entries

Generated with [Devin](https://devin.ai)

Co-Authored-By: Devin <158243242+devin-ai-integration[bot]@users.noreply.github.com>

.gitea/actions/notify-failure/action.yml

@@ -0,0 +1,47 @@
+name: 'Notify on failure'
+description: 'Create a Gitea issue when a CI workflow fails (calls devx.ci.notify_failure)'
+
+# Composite action for the common "Notify on failure" step pattern.
+# Replaces the repeated inline:
+#   - name: Notify on failure
+#     if: failure()
+#     env:
+#       CI_GITEA_API_TOKEN: ${{ secrets.CI_GITEA_API_TOKEN }}
+#     run: |
+#       . .venv/bin/activate 2>/dev/null || true
+#       export PATH="$HOME/.local/bin:$PATH"
+#       python3 -m devx.ci.notify_failure \
+#         --repo "${{ github.repository }}" \
+#         --run-id "${{ github.run_id }}" \
+#         --workflow "ci/validate" \
+#         --commit "${{ github.sha }}" \
+#         --auto-login
+#
+# Gitea 1.27 notes:
+# - `if: failure()` is evaluated in the calling workflow's context and
+#   propagates correctly to composite action steps.
+# - `secrets` are not accessible here; the calling workflow's top-level
+#   `env:` CI_GITEA_API_TOKEN is used via `${{ env.* }}`.
+
+inputs:
+  workflow:
+    description: 'Workflow/job name used in the Gitea issue title (e.g., ci/validate)'
+    required: true
+
+runs:
+  using: 'composite'
+  steps:
+    - name: Notify on failure
+      if: failure()
+      shell: bash
+      env:
+        CI_GITEA_API_TOKEN: ${{ env.CI_GITEA_API_TOKEN }}
+      run: |
+        . .venv/bin/activate 2>/dev/null || true
+        export PATH="$HOME/.local/bin:$PATH"
+        python3 -m devx.ci.notify_failure \
+          --repo "${{ github.repository }}" \
+          --run-id "${{ github.run_id }}" \
+          --workflow "${{ inputs.workflow }}" \
+          --commit "${{ github.sha }}" \
+          --auto-login

.gitea/actions/quality-checks/action.yml

@@ -0,0 +1,89 @@
+name: 'Quality checks'
+description: 'Run lint, unit tests with coverage, test speed, docs, translations, and security scan'
+
+# Composite action for the 6-step quality check sequence used by the
+# devx validate job. Replaces the inline block:
+#   - Lint all
+#   - Unit tests with 100% coverage
+#   - Check unit test speed
+#   - Documentation gate (coverage + stale refs + lint + version refs + prose)
+#   - Translation completeness check
+#   - Dependency security scan
+#
+# Each step activates the venv defensively (`. .venv/bin/activate 2>/dev/null
+# || true`) so the action works whether or not the setup step created a
+# venv at the repo root (pre-built CI images symlink /opt/venv to .venv).
+#
+# Gitea 1.27 notes:
+# - Every `run` step needs explicit `shell:`.
+# - Inputs are string-typed; numeric thresholds are passed through as
+#   strings to `devx.tools.check_test_speed`.
+
+inputs:
+  package:
+    description: 'Package name for doc version checks (e.g., devx, grm). Empty = no DEVX_DOC_VERSIONS_PKG override.'
+    required: false
+    default: ''
+  test-speed-max:
+    description: 'Max total test seconds (passed to check_test_speed --max-seconds)'
+    required: false
+    default: '15'
+  test-speed-max-single:
+    description: 'Max single test seconds (passed to check_test_speed --max-single-seconds)'
+    required: false
+    default: '0.5'
+  translations-file:
+    description: 'Path to translations.json (empty = default location src/devx/translations.json)'
+    required: false
+    default: ''
+
+runs:
+  using: 'composite'
+  steps:
+    - name: Lint all
+      shell: bash
+      run: |
+        . .venv/bin/activate 2>/dev/null || true
+        export PATH="$HOME/.local/bin:$PATH"
+        make lint-all
+    - name: Unit tests with 100% coverage
+      shell: bash
+      run: |
+        . .venv/bin/activate 2>/dev/null || true
+        make pytest-cov
+    - name: Check unit test speed
+      shell: bash
+      run: |
+        . .venv/bin/activate 2>/dev/null || true
+        python3 -m devx.tools.check_test_speed \
+          --max-seconds "${{ inputs.test-speed-max }}" \
+          --max-single-seconds "${{ inputs.test-speed-max-single }}"
+    - name: Documentation gate (coverage + stale refs + lint + version refs + prose)
+      shell: bash
+      env:
+        DEVX_DOC_COVERAGE_STRICT: "1"
+        DEVX_VALE_LEVEL: warning
+      run: |
+        . .venv/bin/activate 2>/dev/null || true
+        export PATH="$HOME/.local/bin:$PATH"
+        if [ -n "${{ inputs.package }}" ]; then
+          export DEVX_DOC_VERSIONS_PKG="${{ inputs.package }}"
+        fi
+        make devx-docs-check
+    - name: Translation completeness check
+      shell: bash
+      run: |
+        . .venv/bin/activate 2>/dev/null || true
+        if [ -n "${{ inputs.translations-file }}" ]; then
+          python3 -m devx.ci.check_translations --translations "${{ inputs.translations-file }}"
+        else
+          python3 -m devx.ci.check_translations
+        fi
+    - name: Dependency security scan
+      shell: bash
+      run: |
+        . .venv/bin/activate 2>/dev/null || true
+        # Install pip in venv if missing (needed by pip-audit)
+        .venv/bin/python -m ensurepip 2>/dev/null || true
+        PIPAPI_PYTHON_LOCATION=$PWD/.venv/bin/python \
+          pip-audit --desc --skip-editable 2>&1 || true

.gitea/actions/setup-env/action.yml

@@ -0,0 +1,37 @@
+name: 'Set up environment'
+description: 'Set up CI environment with venv and PATH (calls make setup-image)'
+
+# Composite action for the common "Set up environment" step pattern.
+# Replaces the repeated inline:
+#   - name: Set up environment
+#     env:
+#       CI_GITEA_API_TOKEN: ${{ secrets.CI_GITEA_API_TOKEN }}
+#     run: make setup-image
+#
+# Gitea 1.27 notes:
+# - Every `run` step needs explicit `shell:`.
+# - Composite actions cannot access `secrets` directly; they read from
+#   the `env:` context which the calling workflow must populate.
+# - The calling workflow's top-level `env:` block (CI_GITEA_API_TOKEN,
+#   CI_GITEA_USERNAME) is visible here via `${{ env.* }}`.
+
+inputs:
+  extras:
+    description: 'Extra pip install groups passed to make setup-image (e.g., ci,lint,release)'
+    required: false
+    default: ''
+
+runs:
+  using: 'composite'
+  steps:
+    - name: Set up environment
+      shell: bash
+      env:
+        CI_GITEA_API_TOKEN: ${{ env.CI_GITEA_API_TOKEN }}
+        CI_GITEA_USERNAME: ${{ env.CI_GITEA_USERNAME }}
+      run: |
+        if [ -n "${{ inputs.extras }}" ]; then
+          make setup-image EXTRAS="${{ inputs.extras }}"
+        else
+          make setup-image
+        fi

.gitea/workflows/build-images.yml

@@ -29,9 +29,20 @@ concurrency:
   group: build-images
   cancel-in-progress: false
 
+env:
+  PIP_BREAK_SYSTEM_PACKAGES: "1"
+  PYTHONPATH: src
+  CI_GITEA_API_TOKEN: ${{ secrets.CI_GITEA_API_TOKEN }}
+  CI_GITEA_USERNAME: ${{ vars.CI_GITEA_USERNAME }}
+
 jobs:
   build-and-push:
     runs-on: docker
+    container:
+      image: git.oblachno.oblachno.fyi/oblachno-oss/runner-images/ci-full:latest
+      credentials:
+        username: ${{ env.CI_GITEA_USERNAME }}
+        password: ${{ env.CI_GITEA_API_TOKEN }}
     timeout-minutes: 30
     outputs:
       is-release: ${{ steps.check.outputs.is-release }}
@@ -40,13 +51,9 @@ jobs:
         with:
           fetch-depth: 1
       - name: Set up environment
-        env:
-          CI_GITEA_API_TOKEN: ${{ secrets.CI_GITEA_API_TOKEN }}
         run: make setup-release
       - name: Check if this is a release commit
         id: check
-        env:
-          PYTHONPATH: src
         run: |
           . .venv/bin/activate
           python3 -m devx.ci.detect_release_commit
@@ -54,9 +61,6 @@ jobs:
         if: >-
           github.event_name == 'workflow_dispatch' ||
           (github.event_name == 'workflow_run' && github.event.workflow_run.conclusion == 'success' && steps.check.outputs.is-release == 'false')
-        env:
-          CI_GITEA_API_TOKEN: ${{ secrets.CI_GITEA_API_TOKEN }}
-          CI_GITEA_USERNAME: ${{ vars.CI_GITEA_USERNAME }}
         run: |
           . .venv/bin/activate
           _TOKEN="$CI_GITEA_API_TOKEN"
@@ -68,10 +72,6 @@ jobs:
         if: >-
           github.event_name == 'workflow_dispatch' ||
           (github.event_name == 'workflow_run' && github.event.workflow_run.conclusion == 'success' && steps.check.outputs.is-release == 'false')
-        env:
-          CI_GITEA_API_TOKEN: ${{ secrets.CI_GITEA_API_TOKEN }}
-          CI_GITEA_USERNAME: ${{ vars.CI_GITEA_USERNAME }}
-          PYTHONPATH: src
         run: |
           . .venv/bin/activate
           export PATH="$HOME/.local/bin:$PATH"
@@ -96,38 +96,27 @@ jobs:
             --tag latest \
             --registry git.oblachno.oblachno.fyi \
             --push
-      - name: Notify on failure
-        if: failure()
-        env:
-          CI_GITEA_API_TOKEN: ${{ secrets.CI_GITEA_API_TOKEN }}
-          PYTHONPATH: src
-        run: |
-          . .venv/bin/activate 2>/dev/null || true
-          export PATH="$HOME/.local/bin:$PATH"
-          python3 -m devx.ci.notify_failure \
-            --repo "${{ github.repository }}" \
-            --run-id "${{ github.run_id }}" \
-            --workflow "build-images/build-and-push" \
-            --commit "${{ github.sha }}" \
-            --auto-login
+      - uses: ./.gitea/actions/notify-failure
+        with:
+          workflow: "build-images/build-and-push"
 
   cleanup:
     needs: [build-and-push]
     if: always() && needs.build-and-push.result == 'success'
     runs-on: docker
+    container:
+      image: git.oblachno.oblachno.fyi/oblachno-oss/runner-images/ci-base:latest
+      credentials:
+        username: ${{ env.CI_GITEA_USERNAME }}
+        password: ${{ env.CI_GITEA_API_TOKEN }}
     timeout-minutes: 10
     steps:
       - uses: actions/checkout@v4
         with:
           fetch-depth: 1
       - name: Set up environment
-        env:
-          CI_GITEA_API_TOKEN: ${{ secrets.CI_GITEA_API_TOKEN }}
         run: make setup-ci
       - name: Clean up old image versions
-        env:
-          CI_GITEA_API_TOKEN: ${{ secrets.CI_GITEA_API_TOKEN }}
-          PYTHONPATH: src
         run: |
           . .venv/bin/activate
           python3 -m devx.tools.clean_images \
@@ -136,3 +125,6 @@ jobs:
             --name oblachno-oss/runner-images/ci-quality \
             --name oblachno-oss/runner-images/ci-full \
             --keep 2
+      - uses: ./.gitea/actions/notify-failure
+        with:
+          workflow: "build-images/cleanup"

.gitea/workflows/ci.yml

@@ -18,7 +18,11 @@ jobs:
   # Saves ~4x checkout+setup overhead vs 5 separate jobs.
   validate:
     runs-on: docker
-    container: git.oblachno.oblachno.fyi/oblachno-oss/runner-images/ci-full:latest
+    container:
+      image: git.oblachno.oblachno.fyi/oblachno-oss/runner-images/ci-full:latest
+      credentials:
+        username: ${{ env.CI_GITEA_USERNAME }}
+        password: ${{ env.CI_GITEA_API_TOKEN }}
     timeout-minutes: 15
     defaults:
       run:
@@ -29,43 +33,12 @@ jobs:
       - uses: actions/checkout@v4
         with:
           fetch-depth: 0
-      - name: Set up environment
-        env:
-          CI_GITEA_API_TOKEN: ${{ secrets.CI_GITEA_API_TOKEN }}
-        run: make setup-image
-      # --- quality steps ---
-      - name: Lint all
-        run: |
-          . .venv/bin/activate 2>/dev/null || true
-          export PATH="$HOME/.local/bin:$PATH"
-          make lint-all
-      - name: Unit tests with 100% coverage
-        run: |
-          . .venv/bin/activate 2>/dev/null || true
-          make pytest-cov
-      - name: Check unit test speed
-        run: |
-          . .venv/bin/activate 2>/dev/null || true
-          python3 -m devx.tools.check_test_speed --max-seconds 8 --max-single-seconds 0.5
-      - name: Documentation gate (coverage + stale refs + lint + version refs + prose)
-        env:
-          DEVX_DOC_COVERAGE_STRICT: "1"
-          DEVX_VALE_LEVEL: warning
-        run: |
-          . .venv/bin/activate 2>/dev/null || true
-          export PATH="$HOME/.local/bin:$PATH"
-          make devx-docs-check
-      - name: Translation completeness check
-        run: |
-          . .venv/bin/activate 2>/dev/null || true
-          python3 -m devx.ci.check_translations
-      - name: Dependency security scan
-        run: |
-          . .venv/bin/activate 2>/dev/null || true
-          # Install pip in venv if missing (needed by pip-audit)
-          .venv/bin/python -m ensurepip 2>/dev/null || true
-          PIPAPI_PYTHON_LOCATION=$PWD/.venv/bin/python \
-            pip-audit --desc --skip-editable 2>&1 || true
+      - uses: ./.gitea/actions/setup-env
+      - uses: ./.gitea/actions/quality-checks
+        with:
+          package: devx
+          test-speed-max: "15"
+          test-speed-max-single: "0.5"
       - name: Workflow dry-run validation
         run: |
           . .venv/bin/activate 2>/dev/null || true
@@ -117,19 +90,9 @@ jobs:
           . .venv/bin/activate 2>/dev/null || true
           export PATH="$HOME/.local/bin:$PATH"
           python3 -m devx.ci.release --dry-run
-      - name: Notify on failure
-        if: failure()
-        env:
-          CI_GITEA_API_TOKEN: ${{ secrets.CI_GITEA_API_TOKEN }}
-        run: |
-          . .venv/bin/activate 2>/dev/null || true
-          export PATH="$HOME/.local/bin:$PATH"
-          python3 -m devx.ci.notify_failure \
-            --repo "${{ github.repository }}" \
-            --run-id "${{ github.run_id }}" \
-            --workflow "ci/validate" \
-            --commit "${{ github.sha }}" \
-            --auto-login
+      - uses: ./.gitea/actions/notify-failure
+        with:
+          workflow: "ci/validate"
 
   auto-merge:
     # Auto-merge runs after validate passes. It reads the task ID
@@ -140,7 +103,11 @@ jobs:
       github.event_name == 'pull_request' &&
       needs.validate.result == 'success'
     runs-on: docker
-    container: git.oblachno.oblachno.fyi/oblachno-oss/runner-images/ci-base:latest
+    container:
+      image: git.oblachno.oblachno.fyi/oblachno-oss/runner-images/ci-base:latest
+      credentials:
+        username: ${{ env.CI_GITEA_USERNAME }}
+        password: ${{ env.CI_GITEA_API_TOKEN }}
     timeout-minutes: 10
     defaults:
       run:
@@ -150,14 +117,10 @@ jobs:
         with:
           fetch-depth: 0
           token: ${{ secrets.CI_GITEA_API_TOKEN }}
-      - name: Set up environment
-        env:
-          CI_GITEA_API_TOKEN: ${{ secrets.CI_GITEA_API_TOKEN }}
-        run: make setup-image
+      - uses: ./.gitea/actions/setup-env
       - name: Post approval review
         env:
           REVIEWER_GITEA_API_TOKEN: ${{ secrets.REVIEWER_GITEA_API_TOKEN }}
-          CI_GITEA_API_TOKEN: ${{ secrets.CI_GITEA_API_TOKEN }}
           PR_NUMBER: ${{ github.event.number }}
           REPOSITORY: ${{ github.repository }}
         run: |
@@ -171,7 +134,6 @@ jobs:
             --body "Auto-approved: all CI checks passed (validate job)."
       - name: Squash merge with task ID
         env:
-          CI_GITEA_API_TOKEN: ${{ secrets.CI_GITEA_API_TOKEN }}
           VIKUNJA_TOKEN: ${{ secrets.VIKUNJA_TOKEN }}
           DEVX_VIKUNJA_PROJECT_ID: "8"
           HEAD_REF: ${{ github.head_ref }}
@@ -185,3 +147,6 @@ jobs:
             "$PR_TITLE" \
             "$REPOSITORY" \
             "$PR_NUMBER"
+      - uses: ./.gitea/actions/notify-failure
+        with:
+          workflow: "ci/auto-merge"

.gitea/workflows/post-merge.yml

@@ -35,7 +35,11 @@ env:
 jobs:
   detect-and-configure:
     runs-on: docker
-    container: git.oblachno.oblachno.fyi/oblachno-oss/runner-images/ci-base:latest
+    container:
+      image: git.oblachno.oblachno.fyi/oblachno-oss/runner-images/ci-base:latest
+      credentials:
+        username: ${{ env.CI_GITEA_USERNAME }}
+        password: ${{ env.CI_GITEA_API_TOKEN }}
     timeout-minutes: 10
     defaults:
       run:
@@ -48,10 +52,7 @@ jobs:
       - uses: actions/checkout@v4
         with:
           fetch-depth: 0
-      - name: Set up environment
-        env:
-          CI_GITEA_API_TOKEN: ${{ secrets.CI_GITEA_API_TOKEN }}
-        run: make setup-image
+      - uses: ./.gitea/actions/setup-env
       - name: Ensure branch protection and labels
         env:
           DEVX_REPO_NAME: devx
@@ -81,25 +82,19 @@ jobs:
             --base "HEAD~1" \
             --head "HEAD" \
             --github-output
-      - name: Notify on failure
-        if: failure()
-        env:
-          CI_GITEA_API_TOKEN: ${{ secrets.CI_GITEA_API_TOKEN }}
-        run: |
-          . .venv/bin/activate 2>/dev/null || true
-          export PATH="$HOME/.local/bin:$PATH"
-          python3 -m devx.ci.notify_failure \
-            --repo "${{ github.repository }}" \
-            --run-id "${{ github.run_id }}" \
-            --workflow "post-merge/detect-and-configure" \
-            --commit "${{ github.sha }}" \
-            --auto-login
+      - uses: ./.gitea/actions/notify-failure
+        with:
+          workflow: "post-merge/detect-and-configure"
 
   release-and-maintain:
     needs: [detect-and-configure]
     if: always() && needs.detect-and-configure.result == 'success'
     runs-on: docker
-    container: git.oblachno.oblachno.fyi/oblachno-oss/runner-images/ci-full:latest
+    container:
+      image: git.oblachno.oblachno.fyi/oblachno-oss/runner-images/ci-full:latest
+      credentials:
+        username: ${{ env.CI_GITEA_USERNAME }}
+        password: ${{ env.CI_GITEA_API_TOKEN }}
     timeout-minutes: 15
     outputs:
       tag: ${{ steps.release-tag.outputs.tag }}
@@ -112,28 +107,24 @@ jobs:
           fetch-depth: 0
           ref: master
           token: ${{ secrets.CI_GITEA_API_TOKEN }}
-      - name: Set up environment
-        env:
-          CI_GITEA_API_TOKEN: ${{ secrets.CI_GITEA_API_TOKEN }}
-        run: make setup-image EXTRAS=release
+      - uses: ./.gitea/actions/setup-env
+        with:
+          extras: "release"
       - name: Configure git
         run: |
           git config user.name "devx-ci-bot"
           git config user.email "devx-ci-bot@oblachno.fyi"
+          git remote set-url origin "https://devx-ci-bot:${CI_GITEA_API_TOKEN}@git.oblachno.oblachno.fyi/oblachno-oss/devx.git"
       # --- release + publish (only if user-facing changes, not a release commit) ---
       - name: Run release
         id: release-tag
         if: needs.detect-and-configure.outputs.is-release == 'false' && needs.detect-and-configure.outputs.user-facing-changed == 'true'
-        env:
-          CI_GITEA_API_TOKEN: ${{ secrets.CI_GITEA_API_TOKEN }}
         run: |
           . .venv/bin/activate 2>/dev/null || true
           export PATH="$HOME/.local/bin:$PATH"
           python3 -m devx.ci.release
       - name: Build and publish release
         if: steps.release-tag.outputs.tag != ''
-        env:
-          CI_GITEA_API_TOKEN: ${{ secrets.CI_GITEA_API_TOKEN }}
         run: |
           . .venv/bin/activate 2>/dev/null || true
           export PATH="$HOME/.local/bin:$PATH"
@@ -143,8 +134,6 @@ jobs:
       # --- sync-wiki + vikunja (skip on automated/release commits) ---
       - name: Sync documentation to wiki
         if: needs.detect-and-configure.outputs.is-automated == 'false'
-        env:
-          CI_GITEA_API_TOKEN: ${{ secrets.CI_GITEA_API_TOKEN }}
         run: |
           . .venv/bin/activate 2>/dev/null || true
           python3 -m devx.ci.sync_wiki --repo "${{ github.repository }}" --verify
@@ -159,7 +148,6 @@ jobs:
       # --- badges (always run — even on release commits) ---
       - name: Generate and push badges
         env:
-          CI_GITEA_API_TOKEN: ${{ secrets.CI_GITEA_API_TOKEN }}
           PRE_COMMIT_ALLOW_NO_CONFIG: "1"
         run: |
           . .venv/bin/activate 2>/dev/null || true
@@ -168,16 +156,6 @@ jobs:
           git fetch origin master
           git reset --hard origin/master
           python3 -m devx.ci.push_badges
-      - name: Notify on failure
-        if: failure()
-        env:
-          CI_GITEA_API_TOKEN: ${{ secrets.CI_GITEA_API_TOKEN }}
-        run: |
-          . .venv/bin/activate 2>/dev/null || true
-          export PATH="$HOME/.local/bin:$PATH"
-          python3 -m devx.ci.notify_failure \
-            --repo "${{ github.repository }}" \
-            --run-id "${{ github.run_id }}" \
-            --workflow "post-merge/release-and-maintain" \
-            --commit "${{ github.sha }}" \
-            --auto-login
+      - uses: ./.gitea/actions/notify-failure
+        with:
+          workflow: "post-merge/release-and-maintain"

.pre-commit-config.yaml

@@ -59,7 +59,7 @@ repos:
 
       - id: check-test-speed
         name: unit test speed check
-        entry: .venv/bin/python -m devx.tools.check_test_speed --max-seconds 6 --max-single-seconds 0.5
+        entry: .venv/bin/python -m devx.tools.check_test_speed --max-seconds 15 --max-single-seconds 0.5
         language: system
         types: [python]
         pass_filenames: false

.vale/styles/Google/Anthropomorphism.yml

@@ -0,0 +1,12 @@
+extends: existence
+message: "Don't attribute human qualities to software or hardware ('%s')."
+link: https://developers.google.com/style/anthropomorphism
+level: suggestion
+ignorecase: true
+# Limited to the two verbs the guide itself names. Broader lists (wants, knows,
+# thinks) can't tell a software subject from a human one: on a 950-file corpus
+# they produced 8 false positives ('the customer wants', 'your audience knows')
+# for every 2 real ones.
+tokens:
+  - sees
+  - tells

.vale/styles/Google/Colons.yml

@@ -1,8 +1,13 @@
 extends: existence
 message: "'%s' should be in lowercase."
 link: 'https://developers.google.com/style/colons'
-nonword: true
 level: warning
 scope: sentence
+# The match is the word itself, not ': X', and `nonword` is off. Both are
+# required for a project Vocab to work: Vale compares accept.txt entries
+# against the matched text, and `nonword: true` opts out of that entirely.
+# So a proper noun after a colon can be exempted by adding it to accept.txt.
+# The guide's other exemption, notice labels, is handled by the lookbehinds;
+# headings are already excluded by `scope: sentence`. See issue #20.
 tokens:
-  - '(?<!:[^ ]+?):\s[A-Z]'
+  - '(?<!Note: )(?<!Caution: )(?<!Warning: )(?<!Success: )(?<=:\s)[A-Z]\w+'

.vale/styles/Google/DateFormat.yml

@@ -6,4 +6,4 @@ level: error
 nonword: true
 tokens:
   - '\d{1,2}(?:\.|/)\d{1,2}(?:\.|/)\d{4}'
-  - '\d{1,2} (?:Jan(?:uary)?|Feb(?:ruary)?|Mar(?:ch)?|Apr(?:il)|May|Jun(?:e)|Jul(?:y)|Aug(?:ust)|Sep(?:tember)?|Oct(?:ober)|Nov(?:ember)?|Dec(?:ember)?) \d{4}'
+  - '\d{1,2} (?:Jan(?:uary)?|Feb(?:ruary)?|Mar(?:ch)?|Apr(?:il)?|May|Jun(?:e)?|Jul(?:y)?|Aug(?:ust)?|Sep(?:tember)?|Oct(?:ober)?|Nov(?:ember)?|Dec(?:ember)?) \d{4}'

.vale/styles/Google/ExcessiveClaims.yml

@@ -0,0 +1,14 @@
+extends: existence
+message: "Avoid the unverifiable claim '%s'."
+link: https://developers.google.com/style/excessive-claims
+level: suggestion
+ignorecase: true
+# The guide also names 'never', 'always', and 'ensure', but in technical writing
+# those are usually legitimate instructions ('never commit secrets') rather than
+# product claims: they accounted for 125 of 142 hits on a 950-file corpus.
+# 'best practices' is a fixed term, not a superlative.
+tokens:
+  - 'best(?! practices?)'
+  - simplest
+  - fastest
+  - guarantees?

.vale/styles/Google/FirstPerson.yml

@@ -3,11 +3,13 @@ message: "Avoid first-person pronouns such as '%s'."
 link: 'https://developers.google.com/style/pronouns#personal-pronouns'
 ignorecase: true
 level: warning
-nonword: true
+# The 'I' tokens use lookaround rather than consuming the surrounding
+# whitespace. Matching ' I ' made the alert span cover both spaces, which shows
+# up as a too-wide underline in editors, and read as "such as ' I '". Dropping
+# `nonword` also lets a project Vocab apply, which it can't when set. See PR #50.
 tokens:
-  - (?:^|\s)I\s
-  - (?:^|\s)I,\s
-  - \bI'm\b
+  - '(?<=^|\s)I(?=[\s,])'
+  - "\\bI'm\\b"
   - \bme\b
   - \bmy\b
   - \bmine\b

.vale/styles/Google/Headings.yml

@@ -4,8 +4,11 @@ link: "https://developers.google.com/style/capitalization#capitalization-in-titl
 level: warning
 scope: heading
 match: $sentence
-indicators:
-  - ":"
+# No `indicators: [":"]` here. That makes Vale require a capital after a colon,
+# which is the Microsoft convention this rule was originally copied from. This
+# guide says the opposite: "the first word after a colon is generally
+# lowercase" (developers.google.com/style/colons), and Colons.yml enforces
+# exactly that. See issue #58.
 exceptions:
   - Azure
   - CLI

.vale/styles/Google/Jargon.yml

@@ -0,0 +1,13 @@
+extends: existence
+message: "Avoid the jargon '%s'."
+link: https://developers.google.com/style/jargon
+level: suggestion
+ignorecase: true
+# The guide also cites 'solution', 'support', and 'workload' as overloaded
+# terms, but those have ordinary technical meanings and accounted for every hit
+# on a 950-file corpus, so only the unambiguous figurative terms are listed.
+tokens:
+  - break-glass
+  - camel ?case
+  - out-of-the-box
+  - swim ?lane

.vale/styles/Google/Latin.yml

@@ -6,6 +6,10 @@ level: error
 nonword: true
 action:
   name: replace
+# The delimiter is a lookahead so the replacement doesn't swallow the comma or
+# space that follows (issue #18). `$` is included so the abbreviation is still
+# caught at the end of a heading, table cell, or block, which accounted for 8
+# of 10 occurrences on a 950-file corpus.
 swap:
-  '\b(?:eg|e\.g\.)(?=[\s,;])': for example
-  '\b(?:ie|i\.e\.)(?=[\s,;])': that is
+  '\b(?:eg|e\.g\.)(?=[\s,;]|$)': for example
+  '\b(?:ie|i\.e\.)(?=[\s,;]|$)': that is

.vale/styles/Google/OxfordComma.yml

@@ -3,5 +3,26 @@ message: "Use the Oxford comma in '%s'."
 link: 'https://developers.google.com/style/commas'
 scope: sentence
 level: warning
+nonword: true
+# List items may be several words long, not just one. Four guards keep the
+# false-positive rate down:
+#
+#   1. The comma can't be the one closing a fronted subordinate clause
+#      ('When your alarm rings, you turn it off and tumble out of bed.') --
+#      that comma separates clauses, not list items. Only the first comma of
+#      such a sentence is exempt, so 'When it rains, apples, pears or bananas
+#      get wet.' is still caught.
+#   2. The item can't open with a clause-introducer (', which ...',
+#      ', specifically ...').
+#   3. The item can't open with a subject pronoun followed by a verb, which
+#      marks a compound predicate rather than a list ('..., you walk to the
+#      fridge and get a snack.'). A pronoun directly followed by 'and'/'or'
+#      is a real list item, so ', you and me.' still matches.
+#   4. Neither item may contain an auxiliary verb, which is another compound
+#      predicate signal (', it has some downsides and is officially
+#      discouraged.').
+#
+# The trailing anchor allows end-of-scope so list fragments ('Apples, pears
+# or bananas') are still caught.
 tokens:
-  - '(?:[^,]+,){1,}\s\w+\s(?:and|or)'
+  - '(?<!^(?i:when|whenever|while|if|unless|until|although|though|because|since|after|before|once|whereas|whether|as)\b[^,]{0,80}),\s(?!(?:which|who|whom|whose|that|where|when|while|because|since|although|though|if|unless|so|but|and|or|however|therefore|thus|specifically|especially|namely|then|take|see|note|consider|make|use|either|neither)\b)(?!(?i:i|you|we|they|he|she|it)\s+(?!(?:and|or)\b))(?:(?!\b(?:is|are|was|were|has|have|had|be|been|being|will|would|can|could|should|may|might|must|do|does|did)\b)\w+ ){0,4}\w+ (?:and|or) (?:(?!\b(?:is|are|was|were|has|have|had|be|been|being|will|would|can|could|should|may|might|must|do|does|did)\b)\w+ ){0,4}\w+(?:[.?!]|$)'

.vale/styles/Google/Parens.yml

@@ -3,5 +3,13 @@ message: "Use parentheses judiciously."
 link: 'https://developers.google.com/style/parentheses'
 nonword: true
 level: suggestion
+# `[^)]` rather than `.+`: a greedy match ran from the first '(' on a line to
+# the last ')', so 'Text (one) and more (two).' produced a single alert
+# covering everything between them. See issue #30.
+# A bare 3-5 letter acronym is skipped: Acronyms.yml requires acronyms to be
+# defined as 'Spelled Out Term (ACRONYM)', so flagging those parentheses would
+# put the two rules in direct conflict. The acronym has to be the whole
+# parenthetical — '(NASA rocket program)' is an ordinary aside and still
+# flags. Length matches the {3,5} in Acronyms.yml. See PR #59.
 tokens:
-  - '\(.+\)'
+  - '\((?![A-Z]{3,5}\))[^)]+\)'

.vale/styles/Google/Timeless.yml

@@ -0,0 +1,13 @@
+extends: existence
+message: "Avoid time-based words like '%s' in product documentation."
+link: https://developers.google.com/style/timeless-documentation
+level: suggestion
+ignorecase: true
+# The guide also names 'now' and 'new', but both have common senses that aren't
+# time-anchored ('create a new project'): adding them took a 950-file corpus of
+# technical documentation from 14 hits to 117. 'recently' is left out too — every
+# hit in that corpus was the UI idiom 'recently used'.
+tokens:
+  - currently
+  - latest
+  - soon

.vale/styles/Google/Units.yml

@@ -4,5 +4,7 @@ link: "https://developers.google.com/style/units-of-measure"
 nonword: true
 level: error
 tokens:
-  - \b\d+(?:B|kB|MB|GB|TB)
-  - \b\d+(?:ns|ms|s|min|h|d)
+  - '\b\d+(?:B|kB|MB|GB|TB)\b'
+  - '\b\d+(?:ns|ms|min|h|d)\b'
+  # Seconds are split out so a decade ('1990s') isn't read as a unit.
+  - '\b\d+s\b(?<!\b(?:19|20)\d\ds\b)'

.vale/styles/Google/WordList.yml

@@ -2,79 +2,28 @@ extends: substitution
 message: "Use '%s' instead of '%s'."
 link: "https://developers.google.com/style/word-list"
 level: warning
+# Case matters here: each key's own capitalization is what's being corrected,
+# so ignorecase would make these match their own replacements. The rest of the
+# word list lives in WordListCase.yml.
 ignorecase: false
 action:
   name: replace
 swap:
-  "(?:API Console|dev|developer) key": API key
-  "(?:cell ?phone|smart ?phone)": phone|mobile phone
-  "(?:dev|developer|APIs) console": API console
-  "(?:e-mail|Email|E-mail)": email
-  "(?:file ?path|path ?name)": path
-  "(?:kill|terminate|abort)": stop|exit|cancel|end
-  "(?:OAuth ?2|Oauth)": OAuth 2.0
-  "(?:ok|Okay)": OK|okay
-  "(?:WiFi|wifi)": Wi-Fi
-  '[\.]+apk': APK
-  '3\-D': 3D
-  'Google (?:I\-O|IO)': Google I/O
-  "tap (?:&|and) hold": touch & hold
-  "un(?:check|select)": clear
-  above: preceding
-  account name: username
-  action bar: app bar
-  admin: administrator
   Ajax: AJAX
-  a\.k\.a|aka: or|also known as
   Android device: Android-powered device
   android: Android
   API explorer: APIs Explorer
-  application: app
-  approx\.: approximately
   authN: authentication
   authZ: authorization
-  autoupdate: automatically update
-  cellular data: mobile data
-  cellular network: mobile network
-  chapter: documents|pages|sections
-  check box: checkbox
   CLI: command-line tool
-  click on: click|click in
   Cloud: Google Cloud Platform|GCP
   Container Engine: Kubernetes Engine
-  content type: media type
-  curated roles: predefined roles
-  data are: data is
   Developers Console: Google API Console|API Console
-  disabled?: turn off|off
-  ephemeral IP address: ephemeral external IP address
-  fewer data: less data
-  file name: filename
-  firewalls: firewall rules
-  functionality: capability|feature
   Google account: Google Account
   Google accounts: Google Accounts
   Googling: search with Google
-  grayed-out: unavailable
   HTTPs: HTTPS
-  in order to: to
-  ingest: import|load
   k8s: Kubernetes
-  long press: touch & hold
-  network IP address: internal IP address
-  omnibox: address bar
-  open-source: open source
-  overview screen: recents screen
-  regex: regular expression
   SHA1: SHA-1|HAS-SHA1
-  sign into: sign in to
-  sign-?on: single sign-on
-  static IP address: static external IP address
-  stylesheet: style sheet
-  synch: sync
-  tablename: table name
-  tablet: device
-  touch: tap
   url: URL
-  vs\.: versus
   World Wide Web: web

.vale/styles/Google/WordListCase.yml

@@ -0,0 +1,68 @@
+extends: substitution
+message: "Use '%s' instead of '%s'."
+link: "https://developers.google.com/style/word-list"
+level: warning
+# The case-insensitive half of the word list, so sentence-initial use is caught
+# ('Touch the screen', not only 'touch the screen'). Entries that must stay
+# case-sensitive are in WordList.yml.
+ignorecase: true
+action:
+  name: replace
+swap:
+  "(?:API Console|dev|developer) key": API key
+  "(?:cell ?phone|smart ?phone)": phone|mobile phone
+  "(?:dev|developer|APIs) console": API console
+  "(?:e-mail|Email|E-mail)": email
+  "(?:file ?path|path ?name)": path
+  "(?:kill|terminate|abort)": stop|exit|cancel|end
+  # Longest form first: with the shortest alternative leading, 'OAuth 2' matched
+  # only 'OAuth', so applying the suggestion produced 'OAuth 2.0 2'. The rule is
+  # already case-insensitive, so the inline (?i) is redundant. See issue #41.
+  '\bOauth2\.0\b|\bOAuth ?2\b(?!\.0)|\bOauth\b(?! ?2)': OAuth 2.0
+  "(?:ok|Okay)": OK|okay
+  "(?:WiFi|wifi)": Wi-Fi
+  '[\.]+apk': APK
+  '3\-D': 3D
+  'Google (?:I\-O|IO)': Google I/O
+  "tap (?:&|and) hold": touch & hold
+  "un(?:check|select)": clear
+  above: preceding
+  account name: username
+  action bar: app bar
+  admin: administrator
+  a\.k\.a|aka: or|also known as
+  application: app
+  approx\.: approximately
+  autoupdate: automatically update
+  cellular data: mobile data
+  cellular network: mobile network
+  chapter: documents|pages|sections
+  check box: checkbox
+  click on: click|click in
+  content type: media type
+  curated roles: predefined roles
+  data are: data is
+  disabled?: turn off|off
+  ephemeral IP address: ephemeral external IP address
+  fewer data: less data
+  file name: filename
+  firewalls: firewall rules
+  functionality: capability|feature
+  grayed-out: unavailable
+  in order to: to
+  ingest: import|load
+  long press: touch & hold
+  network IP address: internal IP address
+  omnibox: address bar
+  open-source: open source
+  overview screen: recents screen
+  regex: regular expression
+  sign into: sign in to
+  '(?<!single )sign-?on': single sign-on
+  static IP address: static external IP address
+  stylesheet: style sheet
+  synch: sync
+  tablename: table name
+  tablet: device
+  'touch(?! ?(?:&|and) hold)': tap
+  vs\.: versus

AGENTS.md

@@ -28,6 +28,11 @@ make workflow-check  # workflow-lint + workflow-dryrun
 make devx-check-doc-versions  # Verify docs version refs match __version__
 make devx-vale       # Run Vale prose linter on docs and README
 make clean           # Remove caches, build artifacts, coverage data
+make check-workflow-artifact-deps  # Verify artifact download jobs depend on upload jobs
+make check-workflow-tofu-init      # Verify tofu-state jobs have a tofu-init step
+make check-docker-init             # Check Docker Compose services with healthchecks have init: true
+make check-ansible-set-fact-to-json  # Check set_fact tasks don't misuse to_json
+make check-alert-rules             # Validate Prometheus alert rules with promtool
 ```
 
 `make setup` automatically installs all development tools:
@@ -53,6 +58,74 @@ The pre-commit hook runs actionlint automatically when workflow files change.
 The CI `validate` job runs `make setup-image` then `make lint-all`.
 CI also runs a best-effort `make workflow-dryrun` step (skipped if act_runner is not installed in the CI Docker image).
 
+## Composite Actions (`.gitea/actions/`)
+
+Reusable Gitea composite actions eliminate repeated multi-step sequences
+across workflows. Each action lives in its own directory under
+`.gitea/actions/<name>/action.yml` and is referenced via
+`uses: ./.gitea/actions/<name>`.
+
+### Available Composite Actions
+
+| Action | Purpose | Inputs |
+|--------|---------|--------|
+| `setup-env` | Run `make setup-image` (with optional `EXTRAS=`) | `extras` (default: `""`) |
+| `notify-failure` | Create a Gitea issue on job failure via `devx.ci.notify_failure` | `workflow` (required) |
+| `quality-checks` | 6-step quality sequence: lint, tests, speed, docs, translations, security | `package`, `test-speed-max`, `test-speed-max-single`, `translations-file` |
+
+### Gitea 1.27 Constraints
+
+- Every `run` step in a composite action MUST have explicit `shell:`.
+- Composite actions CANNOT access `secrets` directly. They read from
+  the calling workflow's `env:` context (for example, `${{ env.CI_GITEA_API_TOKEN }}`).
+  The calling workflow's top-level `env:` block must define the required
+  env vars.
+- `if: failure()` in a composite action step is evaluated in the
+  calling workflow's job-status context.
+
+### Usage Pattern
+
+```yaml
+jobs:
+  validate:
+    env:
+      CI_GITEA_API_TOKEN: ${{ secrets.CI_GITEA_API_TOKEN }}
+      CI_GITEA_USERNAME: ${{ vars.CI_GITEA_USERNAME }}
+    steps:
+      - uses: actions/checkout@v4
+      - uses: ./.gitea/actions/setup-env
+      - uses: ./.gitea/actions/quality-checks
+        with:
+          package: devx
+      - uses: ./.gitea/actions/notify-failure
+        with:
+          workflow: "ci/validate"
+```
+
+### Same-Repo Copies (No Cross-Repo References)
+
+Each repo (`devx`, `grm`, `infra`) gets its own copy of the composite
+actions under its `.gitea/actions/` directory. There is no
+`uses: oblachno-oss/devx/.gitea/actions/...@vX.Y.Z` reference. This
+avoids a single-point-of-failure where a bad devx master commit would
+break all repos' CI simultaneously. See ADR-0003 for the full
+rationale.
+
+### When NOT to Use Composite Actions
+
+- **`make setup-release` / `make setup-ci`**: the `setup-env` action
+  only wraps `make setup-image`. Workflows that use other setup targets
+  (for example, `build-images.yml` uses `make setup-release`) keep the inline
+  setup step.
+- **Deploy-specific setup**: infra deploy workflows have additional
+  steps (`install-collections`, `setup-vault`, `setup_ssh_key`) that
+  are NOT part of the common setup. The `setup-env` action only
+  replaces the `make setup-image` step; deploy-specific steps stay
+  inline.
+- **Custom notification**: `security-scan.yml` uses a Mattermost
+  webhook, not `devx.ci.notify_failure`. The `notify-failure` action
+  does not apply.
+
 ## Architecture
 
 devx is a reusable Python package providing development and CI/CD tools for oblachno-oss projects.
@@ -90,7 +163,12 @@ src/devx/
 │   ├── doc_coverage.py  # Documentation coverage check
 │   ├── lint_docs.py  # Documentation linter (structure, links, headings, code blocks, orphans)
 │   ├── validate_deploy_ref.py  # Validate git tag for deployments (--github-output)
-│   └── record_deployed_tag.py  # Record deployed tag to Gitea repo variable
+│   ├── record_deployed_tag.py  # Record deployed tag to Gitea repo variable
+│   ├── cancel_superseded_runs.py  # Cancel in-flight CI runs for the same PR branch
+│   ├── check_workflow_artifact_deps.py  # Verify artifact download jobs depend on upload jobs
+│   ├── check_workflow_tofu_init.py  # Verify tofu-state jobs have a tofu-init step
+│   ├── discover_runners.py  # Deprecated wrapper → molecule/discover_runners
+│   └── wait_for_checks.py  # Poll Gitea Actions for job completion (replaces inline shell polling)
 ├── tools/               # Developer tooling modules (run locally or by CI)
 │   ├── setup.py         # Environment setup (venv, deps, hooks)
 │   ├── install_tools.py # Install actionlint, git-cliff, act_runner, tea, hadolint, vale
@@ -113,10 +191,24 @@ src/devx/
 │   ├── pr_logs.py           # Fetch logs for failed CI jobs
 │   ├── pr_label.py          # Add labels to PRs (idempotent)
 │   ├── pre_push_check.py    # Validate Vikunja task existence before push
+│   ├── check_docker_init.py  # Check Docker Compose services with healthchecks have init: true
+│   ├── check_ansible_set_fact_to_json.py  # Thin wrapper → ansible_checks/set_fact_to_json
+│   ├── check_alert_rules.py  # Validate Prometheus alert rules with promtool
+│   ├── check_ansible_no_log.py  # Thin wrapper → ansible_checks/no_log
+│   ├── check_ansible_patterns.py  # Thin wrapper → ansible_checks/patterns
+│   ├── check_jinja_expr.py  # Thin wrapper → ansible_checks/jinja_expr
+│   ├── check_ansible_no_state_absent_on_db.py  # Thin wrapper → ansible_checks/no_state_absent_on_db
+│   ├── ansible_checks/     # Composable Ansible check subpackage (canonical implementations)
+│   │   ├── _shared.py      # AnsibleFileFinder, AnsibleYAMLParser, ViolationReporter
+│   │   ├── no_log.py       # Check missing no_log on secret-handling tasks
+│   │   ├── patterns.py     # Detect dangerous failure-masking patterns
+│   │   ├── set_fact_to_json.py  # Check set_fact tasks don't misuse to_json
+│   │   ├── no_state_absent_on_db.py  # Prevent state:absent on DB paths
+│   │   └── jinja_expr.py   # Validate Jinja2 expressions in Ansible files
 │   └── _shared.py           # Shared tool utilities
 ├── opentofu.py          # OpenTofu output helpers (get_tofu_output, get_tofu_vm_ip, get_tofu_vm_field)
 ├── utils/               # Shared utilities (reusable across projects)
-│   ├── api.py            # API response helpers (is_truthy, is_falsy)
+│   ├── api.py            # API response helpers (is_truthy, is_falsy) + APIClient base class
 │   ├── ssh.py            # SSH exec + wait_for_ssh (pure-Python socket check)
 │   ├── crypto.py         # Secret generation (shell-safe passwords)
 │   ├── vault.py          # Ansible vault encrypt/decrypt helpers
@@ -124,12 +216,15 @@ src/devx/
 │   ├── confirm.py        # Typed confirmation validation for destructive ops
 │   ├── json_registry.py  # File-locked JSON registry for local state
 │   ├── step_tracker.py   # Multi-step operation tracking with reports
-│   └── logging.py        # XDG-compliant logging configuration
+│   ├── logging.py        # XDG-compliant logging configuration
+│   ├── ui.py             # say() — unified click.echo + logging output
+│   └── jinja.py          # Jinja2 environment helpers + Ansible-compatible filters
 └── molecule/            # Optional molecule testing helpers (for Ansible projects)
-    ├── discover_runners.py    # Dynamic Gitea runner discovery
+    ├── discover_runners.py    # Dynamic Gitea runner discovery (canonical; ci/discover_runners is a deprecated wrapper)
     ├── distribute_molecule.py # Distribute molecule scenarios across runners (LPT scheduling, --roles-root for multi-role)
     ├── molecule_ci_guard.py   # Run molecule with cross-runner fail-fast (--roles-root)
     ├── molecule_all.py        # Run all molecule scenarios locally
+    ├── molecule_changed.py    # Detect which Ansible roles changed and output molecule scenarios
     ├── start_docker.py        # Ensure Docker daemon is running for molecule tests
     └── platforms.py           # Supported molecule platforms
 ```

CHANGELOG.md

@@ -2,6 +2,152 @@
 
 All notable changes to this project will be documented in this file.
 
+## [Unreleased]
+
+### Ci
+
+- Add composite actions (setup-env, notify-failure, quality-checks) in `.gitea/actions/`
+- Convert ci.yml, post-merge.yml, build-images.yml to use composite actions
+- Add notify-failure to ci/auto-merge and build-images/cleanup jobs (previously missing)
+- Fix `make workflow-dryrun` failure: use `env` context instead of
+  `vars`/`secrets` in `container.credentials` (act_runner dry-run
+  does not populate vars/secrets)
+- Remove redundant step-level `CI_GITEA_API_TOKEN`/`CI_GITEA_USERNAME`
+  env vars (now in workflow-level `env:` block)
+
+## [0.50.4] - 2026-08-12
+
+### Bug Fixes
+
+- Add tenacity retry to install_tools._download for transient network failures
+
+## [0.50.3] - 2026-08-12
+
+### Refactor
+
+- Extract wait_for_checks, consolidate ansible_checks, deprecate ci/discover_runners
+
+## [0.50.2] - 2026-08-12
+
+### Bug Fixes
+
+- Run molecule destroy on test failure to clean up containers
+
+## [0.50.1] - 2026-08-12
+
+### Bug Fixes
+
+- Configure git remote with CI token for post-merge push
+
+## [0.50.0] - 2026-08-12
+
+### Features
+
+- Sync missing features from v0.49.x line to master
+## [0.49.5] - 2026-08-07
+
+### Performance
+
+- Skip dep resolution in setup-image with --no-deps
+## [0.49.4] - 2026-08-07
+
+### Bug Fixes
+
+- Add container.credentials for private registry auth
+## [0.49.3] - 2026-08-07
+
+### Bug Fixes
+
+- Retry ansible-galaxy collection install on transient timeouts
+## [0.49.2] - 2026-08-07
+
+### Bug Fixes
+
+- Add fallback URL for tea download
+## [0.49.1] - 2026-08-07
+
+### Bug Fixes
+
+- Add container images to build-images workflow
+## [0.49.0] - 2026-08-07
+
+### Features
+
+- Add --include-roles and --exclude-roles to distribute_molecule
+## [0.48.0] - 2026-07-22
+
+### Features
+
+- Extract reusable components from infra and grm into devx
+
+## [0.49.5] - 2026-08-07
+
+### Performance
+
+- Skip dep resolution in setup-image with --no-deps
+
+## [0.49.4] - 2026-08-07
+
+### Bug Fixes
+
+- Add container.credentials for private registry auth
+
+## [0.49.3] - 2026-08-07
+
+### Bug Fixes
+
+- Retry ansible-galaxy collection install on transient timeouts
+
+## [0.49.2] - 2026-08-07
+
+### Bug Fixes
+
+- Add fallback URL for tea download
+
+## [0.49.1] - 2026-08-07
+
+### Bug Fixes
+
+- Add container images to build-images workflow
+
+## [0.49.0] - 2026-08-07
+
+### Features
+
+- Add --include-roles and --exclude-roles to distribute_molecule
+## [0.48.0] - 2026-07-22
+
+### Features
+
+- Extract reusable components from infra and grm into devx
+
+## [0.48.0] - 2026-07-22
+
+### Features
+
+- Extract reusable components from infra and grm into devx
+
+## [Unreleased]
+
+### Features
+
+- Extract reusable components from infra and grm into devx:
+  - `devx.utils.ui.say()` — unified click.echo + logging output
+  - `devx.utils.api.APIClient` — base HTTP API client class with retry logic
+  - `devx.utils.jinja` — Jinja2 environment helpers with Ansible-compatible filters
+  - `devx.i18n.configure_i18n()` — configurable `lang_env_var` and `translations_path_env_var`
+  - `devx.ci.cancel_superseded_runs` — cancel in-flight CI runs for the same PR branch
+  - `devx.ci.check_workflow_artifact_deps` — verify artifact download jobs depend on upload jobs
+  - `devx.ci.check_workflow_tofu_init` — verify tofu-state jobs have a tofu-init step
+  - `devx.tools.check_docker_init` — check Docker Compose services with healthchecks have init: true
+  - `devx.tools.check_ansible_set_fact_to_json` — check set_fact tasks don't misuse to_json
+  - `devx.tools.check_alert_rules` — validate Prometheus alert rules with promtool
+- Add `jinja2` and `pyyaml` as core dependencies (previously in `deploy` extras only)
+- Register new CLI commands: `devx ci cancel-superseded-runs`, `devx ci check-workflow-artifact-deps`,
+  `devx ci check-workflow-tofu-init`, `devx tools check-docker-init`,
+  `devx tools check-ansible-set-fact-to-json`, `devx tools check-alert-rules`
+- Add Makefile targets for all new check tools
+
 ## [0.47.3] - 2026-07-17
 
 ### Bug Fixes

Makefile

@@ -1,4 +1,5 @@
 .PHONY: all setup setup-ci setup-quality setup-release setup-image install update lint lint-all lint-dockerfiles test test-unit pytest-cov clean install-tools install-hooks activate-scripts checkmake check-mutable-globals check-dep-docs check-test-speed build-images push-images build-images-dry-run clean-images
+.PHONY: check-workflow-artifact-deps check-workflow-tofu-init check-docker-init check-ansible-set-fact-to-json check-alert-rules
 
 PYTHON := python3
 VENV := .venv
@@ -65,7 +66,7 @@ setup-release: $(VENV)/bin/activate .env
 # an older devx.mak that doesn't yet define devx-setup-image. Consumer repos
 # (grm, infra) can safely alias to devx-setup-image since they install devx from PyPI.
 setup-image:
-	@if [ -d /opt/venv ]; then ln -sf /opt/venv $(VENV); . $(VENV)/bin/activate && pip install --no-cache-dir -e . 2>/dev/null; \
+	@if [ -d /opt/venv ]; then ln -sf /opt/venv $(VENV); . $(VENV)/bin/activate && pip install --no-cache-dir --no-deps -e . 2>/dev/null; \
 	else echo "[setup-image] /opt/venv not found — falling back to setup-ci"; $(MAKE) setup-ci; fi
 
 install-hooks:
@@ -113,6 +114,31 @@ pr-rebase: devx-pr-rebase
 lint-all: lint workflow-lint lint-dockerfiles
 	@echo "[lint-all] All linting checks passed."
 
+# ── Workflow / Ansible / Docker check tools ─────────────────────────────────
+# Generic check tools ported from infra. These targets are no-ops in devx
+# itself (no .gitea/workflows or ansible/ directory) but provide the
+# canonical entry points for consumer repos that include devx.mak.
+
+check-workflow-artifact-deps:
+	@$(BIN)/python -m devx.ci.check_workflow_artifact_deps || \
+		echo "[check-workflow-artifact-deps] No workflows directory found — skipping."
+
+check-workflow-tofu-init:
+	@$(BIN)/python -m devx.ci.check_workflow_tofu_init || \
+		echo "[check-workflow-tofu-init] No workflows directory found — skipping."
+
+check-docker-init:
+	@$(BIN)/python -m devx.tools.check_docker_init || \
+		echo "[check-docker-init] No ansible templates found — skipping."
+
+check-ansible-set-fact-to-json:
+	@$(BIN)/python -m devx.tools.check_ansible_set_fact_to_json || \
+		echo "[check-ansible-set-fact-to-json] No ansible directory found — skipping."
+
+check-alert-rules:
+	@$(BIN)/python -m devx.tools.check_alert_rules --template-path ansible/roles/observability/templates || \
+		echo "[check-alert-rules] No alert-rules template found — skipping."
+
 # Note: Not aliased to devx-lint-dockerfiles for the same reason as setup-image —
 # devx's own CI images may have an older devx.mak. Consumer repos can safely alias.
 lint-dockerfiles:

README.md

@@ -12,16 +12,16 @@ opinionated CI/CD pipeline: conventional commits, automated versioning via
 git-cliff, squash-merge automation, Vikunja task tracking, wiki sync, and
 quality badges.
 
-> An open-source project from **Oblachno** (облачно means *cloudy* in Bulgarian).
+> An open source project from **Oblachno** (облачно means *cloudy* in Bulgarian).
 
 [![CI](https://git.oblachno.oblachno.fyi/oblachno-oss/devx/actions/workflows/ci.yml/badge.svg)](https://git.oblachno.oblachno.fyi/oblachno-oss/devx/actions)
 [![License: GPL-3.0](https://img.shields.io/badge/license-GPL--3.0-blue)](https://git.oblachno.oblachno.fyi/oblachno-oss/devx/src/branch/master/LICENSE)
-[![Coverage](https://git.oblachno.oblachno.fyi/oblachno-oss/devx/raw/commit/82b4caf3bcf5fb7058654abab87cd2fea339d882/coverage.svg)](https://git.oblachno.oblachno.fyi/oblachno-oss/devx/actions)
-[![Tests](https://git.oblachno.oblachno.fyi/oblachno-oss/devx/raw/commit/82b4caf3bcf5fb7058654abab87cd2fea339d882/tests.svg)](https://git.oblachno.oblachno.fyi/oblachno-oss/devx/actions)
-[![Docs](https://git.oblachno.oblachno.fyi/oblachno-oss/devx/raw/commit/82b4caf3bcf5fb7058654abab87cd2fea339d882/docs.svg)](https://git.oblachno.oblachno.fyi/oblachno-oss/devx/wiki)
-[![Code Quality](https://git.oblachno.oblachno.fyi/oblachno-oss/devx/raw/commit/82b4caf3bcf5fb7058654abab87cd2fea339d882/quality.svg)](https://git.oblachno.oblachno.fyi/oblachno-oss/devx/actions)
-[![Version](https://git.oblachno.oblachno.fyi/oblachno-oss/devx/raw/commit/82b4caf3bcf5fb7058654abab87cd2fea339d882/version.svg)](https://git.oblachno.oblachno.fyi/oblachno-oss/devx/releases)
-[![Python](https://git.oblachno.oblachno.fyi/oblachno-oss/devx/raw/commit/82b4caf3bcf5fb7058654abab87cd2fea339d882/python.svg)](https://www.python.org/downloads/)
+[![Coverage](https://git.oblachno.oblachno.fyi/oblachno-oss/devx/raw/commit/43d0589aeee6d706356f79deef37662c9291b981/coverage.svg)](https://git.oblachno.oblachno.fyi/oblachno-oss/devx/actions)
+[![Tests](https://git.oblachno.oblachno.fyi/oblachno-oss/devx/raw/commit/43d0589aeee6d706356f79deef37662c9291b981/tests.svg)](https://git.oblachno.oblachno.fyi/oblachno-oss/devx/actions)
+[![Docs](https://git.oblachno.oblachno.fyi/oblachno-oss/devx/raw/commit/43d0589aeee6d706356f79deef37662c9291b981/docs.svg)](https://git.oblachno.oblachno.fyi/oblachno-oss/devx/wiki)
+[![Code Quality](https://git.oblachno.oblachno.fyi/oblachno-oss/devx/raw/commit/43d0589aeee6d706356f79deef37662c9291b981/quality.svg)](https://git.oblachno.oblachno.fyi/oblachno-oss/devx/actions)
+[![Version](https://git.oblachno.oblachno.fyi/oblachno-oss/devx/raw/commit/43d0589aeee6d706356f79deef37662c9291b981/version.svg)](https://git.oblachno.oblachno.fyi/oblachno-oss/devx/releases)
+[![Python](https://git.oblachno.oblachno.fyi/oblachno-oss/devx/raw/commit/43d0589aeee6d706356f79deef37662c9291b981/python.svg)](https://www.python.org/downloads/)
 
 ## Why devx?
 
@@ -87,7 +87,7 @@ extra index and list devx in your dependencies:
 ```toml
 [project]
 dependencies = [
-    "devx>=0.47.3",
+    "devx>=0.50.4",
 ]
 
 [tool.pip]
@@ -101,8 +101,8 @@ pip install -e .
 ```
 
 > **Note:** If your project requires a specific devx version, pin it in
-> `dependencies` (for example, `"devx==0.47.3"`) or use a version constraint
-> (for example, `"devx>=0.47.3,<0.48"`).
+> `dependencies` (for example, `"devx==0.50.4"`) or use a version constraint
+> (for example, `"devx>=0.50.4,<0.51"`).
 
 ### Optional extras
 
@@ -226,10 +226,6 @@ python -m devx.molecule.distribute_molecule --runner-index 1 --max-runners 3
 python -m devx.molecule.distribute_molecule --list              # list all scenarios
 python -m devx.molecule.distribute_molecule --list-platforms    # list platforms
 
-# Run molecule tests with cross-runner fail-fast
-python -m devx.molecule.molecule_ci_guard pair1 pair2
-python -m devx.molecule.molecule_ci_guard --roles-root ansible/roles pair1 pair2
-
 # Run all molecule scenarios locally (sequential)
 python -m devx.molecule.molecule_all
 python -m devx.molecule.molecule_all --bin .venv/bin
@@ -303,7 +299,6 @@ devx --version
 | `devx molecule all` | Run all molecule scenarios on all supported platforms |
 | `devx molecule discover-runners` | Discover available Gitea Actions runners |
 | `devx molecule distribute` | Distribute molecule test pairs across parallel runners |
-| `devx molecule guard` | Run molecule tests with CI failure polling |
 
 See [CLI Commands](https://git.oblachno.oblachno.fyi/oblachno-oss/devx/wiki/CLI-Commands)
 in the wiki for full command documentation with examples.
@@ -450,6 +445,17 @@ src/devx/
 └── molecule/            # Optional molecule testing helpers (for Ansible projects)
 ```
 
+### Composite Actions (`.gitea/actions/`)
+
+Reusable Gitea composite actions for CI workflow steps:
+
+- `setup-env` — runs `make setup-image` (with optional `EXTRAS=`)
+- `notify-failure` — creates a Gitea issue on job failure
+- `quality-checks` — 6-step quality gate (lint, tests, speed, docs, translations, security)
+
+Each consumer repo gets its own copy (no cross-repo references). See
+ADR-0003 for the design rationale.
+
 ### Design principles
 
 - **Self-contained package** — `src/devx/` never imports from scripts outside the package

docs/decisions/0002-ansible-check-consolidation-and-wait-for-checks.md

@@ -0,0 +1,108 @@
+# ADR-0002: Ansible Check Tool Consolidation and wait_for_checks Extraction
+
+Date: 2026-08-12
+Status: Accepted
+
+## Context
+
+The devx package had two categories of code duplication and inline
+workflow logic that were hard to test and maintain:
+
+### 1. Ansible Check Tools — Duplicated Boilerplate
+
+Five Ansible check tools (`check_ansible_no_log`,
+`check_ansible_patterns`, `check_ansible_set_fact_to_json`,
+`check_ansible_no_state_absent_on_db`, `check_jinja_expr`) each
+implemented their own file discovery, YAML parsing, task iteration, and
+violation reporting logic. While the check logic differed, the
+supporting infrastructure was copy-pasted across all five modules:
+
+- `find_task_files()` — glob YAML files, skip molecule
+- YAML multi-document parsing with error handling
+- Task iteration (bare lists, play dicts with `tasks`/`pre_tasks`/`post_tasks`/`handlers`, nested `block` tasks)
+- Violation formatting (`path:line — message`)
+
+This made it difficult to add new checks (each new tool repeated the
+boilerplate) and risky to change shared behavior (fixes had to be
+applied to all five modules independently).
+
+### 2. Inline Job Polling in Workflow YAML
+
+The `grm` repository's `ci.yml` workflow contained ~25 lines of inline
+shell + Python polling logic to wait for the `molecule-tests` job to
+complete before the auto-merge step. This logic:
+
+- Was not testable (embedded in workflow YAML)
+- Duplicated the Gitea API client pattern already used elsewhere
+- Had no timeout handling, no error reporting, no retry logic
+- Could not be reused by other repositories
+
+### 3. Duplicate discover_runners Modules
+
+`devx.ci.discover_runners` and `devx.molecule.discover_runners` were
+near-identical modules. The `ci/` version had better error logging
+(warnings on non-200 responses, 403 suppression for instance-level
+queries), while the `molecule/` version silently swallowed errors.
+Both were imported by different workflows, making it unclear which was
+canonical.
+
+## Decision
+
+### 1. Composable `ansible_checks/` Subpackage
+
+Consolidate the five Ansible check tools into a
+`devx.tools.ansible_checks/` subpackage with shared utilities:
+
+- `_shared.py` — `AnsibleFileFinder`, `AnsibleYAMLParser`,
+  `ViolationReporter` classes providing composable helpers
+- `no_log.py`, `patterns.py`, `set_fact_to_json.py`,
+  `no_state_absent_on_db.py`, `jinja_expr.py` — canonical check
+  implementations using the shared utilities
+
+The old modules (`check_ansible_*.py`, `check_jinja_expr.py`) remain as
+**thin backward-compat wrappers** that re-export the canonical
+implementation and preserve the CLI entry point. This avoids breaking
+existing Makefile targets and workflow references.
+
+**Composition over inheritance**: each check module picks the helpers it
+needs. Tools that don't parse YAML (for example line-based scanners) can skip
+`AnsibleYAMLParser` entirely.
+
+### 2. Extracted `wait_for_checks` Module
+
+Extract the inline polling logic into `devx.ci.wait_for_checks`:
+
+- Polls the Gitea API for job completion status
+- Configurable job name prefix, timeout, poll interval
+- Exit codes: 0 (success), 1 (failure), 2 (timeout), 3 (API error)
+- `--require-success/--no-require-success` flag for flexibility
+- 100% test coverage with mocked API responses
+
+This replaces the inline shell polling in `grm` `ci.yml` with a
+reusable, testable Python module.
+
+### 3. Deprecated `ci/discover_runners` Wrapper
+
+Merge the `ci/discover_runners` implementation (with its better error
+logging) into `molecule/discover_runners` as the canonical version.
+Make `ci/discover_runners` a deprecated wrapper that:
+
+- Re-exports all public symbols from `molecule.discover_runners`
+- Emits a `DeprecationWarning` when run as `__main__`
+- Preserves backward compatibility for existing workflow references
+
+New code should import from `devx.molecule.discover_runners` directly.
+
+## Consequences
+
+- **New checks are easier to write**: import `_shared` helpers, implement
+  only the check-specific logic
+- **Shared behavior can be fixed in one place**: file discovery, YAML
+  parsing, violation formatting
+- **Workflow polling is testable**: `wait_for_checks` has 26 unit tests
+  covering success, failure, timeout, and API error scenarios
+- **Backward compatibility preserved**: all existing Makefile targets,
+  workflow references, and test imports continue to work via wrappers
+- **Migration path is gradual**: new code uses the subpackage; old code
+  can migrate at its own pace; wrappers can be removed in a future
+  release once all references are updated

docs/decisions/0003-composite-actions.md

@@ -0,0 +1,155 @@
+# ADR-0003: Composite Actions for CI Workflow Reuse
+
+Date: 2026-08-12
+Status: Accepted
+
+## Context
+
+The devx repository's Gitea Actions workflows (`.gitea/workflows/ci.yml`,
+`post-merge.yml`, `build-images.yml`) repeated multi-step
+sequences across jobs:
+
+1. **Set up environment** — `make setup-image` (optionally with `EXTRAS=`).
+   Appeared verbatim in 4 jobs across `ci.yml` and `post-merge.yml`, each
+   with the same `CI_GITEA_API_TOKEN` env wiring.
+
+2. **Notify on failure** — `python3 -m devx.ci.notify_failure ... --auto-login`
+   with venv activation, PATH export, and 5 fixed CLI args. Appeared in
+   4 jobs (`ci/validate`, `post-merge/detect-and-configure`,
+   `post-merge/release-and-maintain`, `build-images/build-and-push`),
+   each differing only in the `--workflow` string.
+
+3. **Quality checks** — a 6-step sequence (lint-all, pytest-cov,
+   check-test-speed, devx-docs-check, check-translations, pip-audit)
+   with venv activation boilerplate on every step. Appeared once in
+   `ci.yml` validate job, but the same sequence is needed by `grm` and
+   `infra` (Phase 2b/2c of the cross-repo refactoring plan).
+
+This duplication had the following costs:
+
+- **Drift risk**: a fix to notify-failure (for example, new flag,
+  different env var) had to be applied to 4 places; missing one caused
+  inconsistent failure notifications.
+- **Workflow YAML noise**: the 6-step quality block obscured the
+  validate job's actual structure (detect-changes, pr-review,
+  release-dry-run).
+- **Cross-repo reuse blocked**: `grm` and `infra` could not adopt the
+  same quality-checks sequence without copy-pasting the inline steps,
+  which would amplify the drift problem across 3 repos.
+- **Gitea 1.27 constraints**: every `run` step needs explicit `shell:`;
+  composite actions cannot access `secrets` directly (only `env:`).
+  These constraints had to be re-discovered and re-applied per step.
+
+## Decision
+
+Introduce three Gitea composite actions in `.gitea/actions/`:
+
+### 1. `setup-env/action.yml`
+
+Wraps the `make setup-image` call. Single input `extras` (default empty)
+forwarded to `make setup-image EXTRAS=`. Reads `CI_GITEA_API_TOKEN` and
+`CI_GITEA_USERNAME` from the calling workflow's `env:` context.
+
+### 2. `notify-failure/action.yml`
+
+Wraps the `devx.ci.notify_failure` invocation. Single required input
+`workflow` (the workflow/job name for the Gitea issue title). Step is
+gated by `if: failure()` so it only runs on job failure. Reads
+`CI_GITEA_API_TOKEN` from the calling workflow's `env:` context.
+
+### 3. `quality-checks/action.yml`
+
+Wraps the 6-step quality sequence. Inputs:
+
+- `package` (default empty) — sets `DEVX_DOC_VERSIONS_PKG` for doc
+  version checks (for example, `devx`, `grm`).
+- `test-speed-max` (default `15`) — total test seconds threshold.
+- `test-speed-max-single` (default `0.5`) — per-test seconds threshold.
+- `translations-file` (default empty) — path to `translations.json`
+  for repos whose translations live outside `src/devx/`.
+
+Each step activates the venv defensively
+(`. .venv/bin/activate 2>/dev/null || true`) so the action works with
+both pre-built CI images (which symlink `/opt/venv` to `.venv`) and
+fresh `make setup-image` runs.
+
+### Adoption Scope
+
+- **`ci.yml` validate job**: `setup-env` + `quality-checks` +
+  `notify-failure`.
+- **`ci.yml` auto-merge job**: `setup-env` + `notify-failure` (no
+  quality checks — auto-merge only runs after validate passes).
+- **`post-merge.yml` detect-and-configure**: `setup-env` +
+  `notify-failure`.
+- **`post-merge.yml` release-and-maintain**: `setup-env` (with
+  `extras: "release"`) + `notify-failure`.
+- **`build-images.yml` build-and-push**: `notify-failure` only. The
+  setup steps use `make setup-release` (not `make setup-image`), so
+  `setup-env` does not apply.
+- **`build-images.yml` cleanup**: `notify-failure` only. The setup
+  step uses `make setup-ci` (not `make setup-image`).
+
+### Same-Repo Copies (No Cross-Repo References)
+
+Each consumer repo (`devx`, `grm`, `infra`) gets its own copy of the
+composite actions under its `.gitea/actions/` directory. There is no
+`uses: oblachno-oss/devx/.gitea/actions/...@vX.Y.Z` reference.
+
+This avoids a single-point-of-failure where a bad `devx` master commit
+would break all three repos' CI simultaneously. The cost is three
+copies of ~30 lines of YAML each, updated manually when a composite
+action changes. Given the stability of these patterns (the inline
+versions were unchanged for months), this cost is acceptable.
+
+## Consequences
+
+### Positive
+
+- **Workflow YAML is shorter and clearer**: the validate job's
+  quality block collapses from 32 lines to 5 lines. The intent
+  (`uses: ./.gitea/actions/quality-checks`) is more legible than
+  6 individually wrapped steps.
+- **Drift eliminated**: a change to notify-failure (new flag, different
+  env var) is applied in one file. All 4 calling sites pick it up.
+- **Cross-repo reuse enabled**: Phase 2b (`grm`) and Phase 2c (`infra`)
+  copy the same `action.yml` files and adopt the same `uses:` pattern.
+  The quality-checks sequence is now portable.
+- **Gitea 1.27 constraints centralized**: the `shell: bash` and
+  `env:` (not `secrets`) patterns are encoded once per action, not
+  re-derived per step.
+- **No release triggered**: changes to `.gitea/**` are classified as
+  workflow-only by `devx.ci.classify_changes`. Phase 2a does not
+  produce a new devx version. `grm`/`infra` bump to the Phase 1
+  release (v0.50.4), not a Phase 2a version.
+
+### Negative
+
+- **Three copies of each action**: when a composite action changes,
+  the change must be applied to `devx`, `grm`, and `infra`
+  independently. This is intentional (see Same-Repo Copies preceding)
+  but is a maintenance cost.
+- **Composite action debugging is harder**: Gitea's log output for
+  composite action steps is nested under the action name. Finding the
+  failing step requires reading one more level of indentation.
+- **`env:` propagation is implicit**: the calling workflow's top-level
+  `env:` block must define `CI_GITEA_API_TOKEN` for the composite
+  action to read it. A workflow that omits this will see an empty
+  token at runtime, not at lint time. actionlint does not catch this.
+- **`quality-checks` is devx-shaped**: the `package` and
+  `translations-file` inputs exist because consumer repos (for example,
+  `grm`) have translations files outside the default
+  `src/devx/translations.json` location and need doc version checks
+  targeting their own package name.
+  A repo with a different translations path or package layout would need
+  a new input or a different action. This is acceptable for the current
+  3-repo scope.
+
+### Neutral
+
+- **`if: failure()` is preserved**: the `notify-failure` composite
+  action's step has `if: failure()`, which is evaluated in the
+  calling workflow's job-status context. This is the standard Gitea
+  Actions pattern for post-failure notification.
+- **Venv activation is defensive**: `. .venv/bin/activate 2>/dev/null
+  || true` does not fail if the venv is missing (pre-built image path)
+  or already active. This matches the inline pattern's behavior.

docs/index.md

@@ -8,16 +8,16 @@ parallel test distribution, and more into a single installable package.
 It was extracted from the [GRM](https://git.oblachno.oblachno.fyi/oblachno-oss/grm)
 project to be reusable across all oblachno-oss repositories.
 
-> An open-source project from **Oblachno** (облачно means *cloudy* in Bulgarian).
+> An open source project from **Oblachno** (облачно means *cloudy* in Bulgarian).
 
 [![CI](https://git.oblachno.oblachno.fyi/oblachno-oss/devx/actions/workflows/ci.yml/badge.svg)](https://git.oblachno.oblachno.fyi/oblachno-oss/devx/actions)
 [![License: GPL-3.0](https://img.shields.io/badge/license-GPL--3.0-blue)](https://git.oblachno.oblachno.fyi/oblachno-oss/devx/src/branch/master/LICENSE)
-[![Coverage](https://git.oblachno.oblachno.fyi/oblachno-oss/devx/raw/commit/82b4caf3bcf5fb7058654abab87cd2fea339d882/coverage.svg)](https://git.oblachno.oblachno.fyi/oblachno-oss/devx/actions)
-[![Tests](https://git.oblachno.oblachno.fyi/oblachno-oss/devx/raw/commit/82b4caf3bcf5fb7058654abab87cd2fea339d882/tests.svg)](https://git.oblachno.oblachno.fyi/oblachno-oss/devx/actions)
-[![Docs](https://git.oblachno.oblachno.fyi/oblachno-oss/devx/raw/commit/82b4caf3bcf5fb7058654abab87cd2fea339d882/docs.svg)](https://git.oblachno.oblachno.fyi/oblachno-oss/devx/wiki)
-[![Code Quality](https://git.oblachno.oblachno.fyi/oblachno-oss/devx/raw/commit/82b4caf3bcf5fb7058654abab87cd2fea339d882/quality.svg)](https://git.oblachno.oblachno.fyi/oblachno-oss/devx/actions)
-[![Version](https://git.oblachno.oblachno.fyi/oblachno-oss/devx/raw/commit/82b4caf3bcf5fb7058654abab87cd2fea339d882/version.svg)](https://git.oblachno.oblachno.fyi/oblachno-oss/devx/releases)
-[![Python](https://git.oblachno.oblachno.fyi/oblachno-oss/devx/raw/commit/82b4caf3bcf5fb7058654abab87cd2fea339d882/python.svg)](https://www.python.org/downloads/)
+[![Coverage](https://git.oblachno.oblachno.fyi/oblachno-oss/devx/raw/commit/43d0589aeee6d706356f79deef37662c9291b981/coverage.svg)](https://git.oblachno.oblachno.fyi/oblachno-oss/devx/actions)
+[![Tests](https://git.oblachno.oblachno.fyi/oblachno-oss/devx/raw/commit/43d0589aeee6d706356f79deef37662c9291b981/tests.svg)](https://git.oblachno.oblachno.fyi/oblachno-oss/devx/actions)
+[![Docs](https://git.oblachno.oblachno.fyi/oblachno-oss/devx/raw/commit/43d0589aeee6d706356f79deef37662c9291b981/docs.svg)](https://git.oblachno.oblachno.fyi/oblachno-oss/devx/wiki)
+[![Code Quality](https://git.oblachno.oblachno.fyi/oblachno-oss/devx/raw/commit/43d0589aeee6d706356f79deef37662c9291b981/quality.svg)](https://git.oblachno.oblachno.fyi/oblachno-oss/devx/actions)
+[![Version](https://git.oblachno.oblachno.fyi/oblachno-oss/devx/raw/commit/43d0589aeee6d706356f79deef37662c9291b981/version.svg)](https://git.oblachno.oblachno.fyi/oblachno-oss/devx/releases)
+[![Python](https://git.oblachno.oblachno.fyi/oblachno-oss/devx/raw/commit/43d0589aeee6d706356f79deef37662c9291b981/python.svg)](https://www.python.org/downloads/)
 
 ## Overview
 
@@ -74,14 +74,14 @@ Add devx to your `pyproject.toml` dependencies and configure the registry:
 ```toml
 [project]
 dependencies = [
-    "devx>=0.47.3",
+    "devx>=0.50.4",
 ]
 
 [tool.pip]
 extra-index-url = "https://git.oblachno.oblachno.fyi/api/packages/oblachno-oss/pypi/simple"
 ```
 
-Pin a specific version if needed: `"devx==0.47.3"` or `"devx>=0.47.3,<0.48"`.
+Pin a specific version if needed: `"devx==0.50.4"` or `"devx>=0.50.4,<0.51"`.
 
 ### Optional extras
 
@@ -104,8 +104,8 @@ devx is a self-contained Python package under `src/devx/`:
 - **Dev tools** (`devx.tools`) — setup, install_tools, check_test_speed,
   configure_repo, generate_badges, generate_cliff_config, install_checkmake
 - **Molecule tools** (`devx.molecule`) — Optional, for projects with Ansible
-  roles: distribute_molecule, molecule_ci_guard, molecule_all, discover_runners,
-  start_docker, platforms
+  roles: distribute_molecule, molecule_all, discover_runners, start_docker,
+  platforms
 
 See [Architecture](Architecture) for the full package structure, module
 descriptions, design principles, and data flow diagrams.
@@ -132,7 +132,7 @@ devx provides a `devx` CLI with three command groups:
 
 - `devx ci <command>` — CI/CD automation (17 commands)
 - `devx tools <command>` — Developer tools (9 commands)
-- `devx molecule <command>` — Molecule testing (4 commands, optional)
+- `devx molecule <command>` — Molecule testing (3 commands, optional)
 
 See [CLI Commands](CLI-Commands) for full command documentation with examples.
 

docs/mapping.json

@@ -3,5 +3,7 @@
   "user/getting-started.md": "Getting-Started",
   "user/cli-commands.md": "CLI-Commands",
   "tech/architecture.md": "Architecture",
-  "tech/ci-cd-workflow.md": "CI-CD-Workflow"
+  "tech/ci-cd-workflow.md": "CI-CD-Workflow",
+  "decisions/0001-test-isolation-pytest-plugin-and-shift-left-quality-gates.md": "ADR-0001-Test-Isolation",
+  "decisions/0002-ansible-check-consolidation-and-wait-for-checks.md": "ADR-0002-Ansible-Check-Consolidation"
 }

docs/retrospectives/2026-07-12-self-approval-fallback-and-ci-consolidation.md

@@ -132,7 +132,7 @@ unblocked auto-merge across all three repos.
 ### 2. Double-Prefix Detection (MEDIUM impact)
 
 `check_auto_merge_ready.py` now detects and rejects Vikunja task titles
-that include the identifier prefix (for example, "DEVX-127: Fix...").
+that include the identifier prefix (for example, "DEVX-127: Fix").
 The validator adds the prefix automatically, so a double prefix would
 fail validation.
 

docs/tech/architecture.md

@@ -33,7 +33,8 @@ src/devx/
 │   ├── notify_failure.py    # Create Gitea issues on CI failures
 │   ├── distribute_files.py  # Distribute files across parallel runners
 │   ├── integration_guard.py # Run pytest with cross-runner fail-fast
-│   ├── discover_runners.py  # Dynamic Gitea runner discovery
+│   ├── discover_runners.py  # Deprecated wrapper → molecule/discover_runners
+│   ├── wait_for_checks.py  # Poll Gitea Actions for job completion
 │   ├── check_translations.py  # Translation completeness check
 │   └── doc_coverage.py      # Documentation coverage check
 ├── tools/                   # Developer tooling modules (run locally or by CI)
@@ -48,7 +49,7 @@ src/devx/
 │   └── install_checkmake.py # Install checkmake (Makefile linter)
 └── molecule/                # Optional molecule testing helpers (Ansible projects)
     ├── __init__.py
-    ├── discover_runners.py      # Dynamic Gitea runner discovery
+    ├── discover_runners.py      # Dynamic Gitea runner discovery (canonical)
     ├── distribute_molecule.py   # Distribute scenarios across runners
     ├── molecule_ci_guard.py     # Run molecule with cross-runner fail-fast
     ├── molecule_all.py          # Run all molecule scenarios locally
@@ -87,11 +88,11 @@ overridden via environment variables with the `DEVX_` prefix. Provides:
 
 - `GITEA_API_URL` / `VIKUNJA_API_URL` — API endpoints
 - `REPO_OWNER` — repository owner (must be set per-project)
-- `TASK_PREFIX` / `TASK_ID_RE` — task ID prefix and regex (for example, `DEVX-N`)
+- `TASK_PREFIX` / `TASK_ID_RE` — task ID prefix and regular expression (for example, `DEVX-N`)
 - `VIKUNJA_PROJECT_ID` — Vikunja project for task tracking
 - `DEFAULT_TIMEOUT`, `DEFAULT_PER_PAGE` — HTTP client defaults
 - `MAX_RETRIES`, `RETRY_BACKOFF_BASE`, `RETRY_STATUS_CODES` — retry config
-- `CONVENTIONAL_RE` — conventional commit format regex
+- `CONVENTIONAL_RE` — conventional commit format regular expression
 
 ### `exceptions.py`
 
@@ -109,7 +110,7 @@ wraps user-facing strings for translation.
 
 Projects can extend translations by setting `DEVX_TRANSLATIONS_PATH` to a
 custom JSON file. Keys from the project's file are merged on top of devx's
-built-in translations, allowing projects to override or add keys without
+built-in translations, allowing projects to override, or add keys without
 modifying the package.
 
 ### `api_clients.py`
@@ -171,7 +172,7 @@ from `devx.api_clients`, `devx.config`, `devx.gitea_cli`, and `devx.i18n`.
 
 Automated release using git-cliff. Calculates the next semver version from
 conventional commits since the last tag, updates `__version__` in
-`__init__.py` and `CHANGELOG.md`, runs lint and tests to verify the release
+`__init__.py` and `CHANGELOG.md`, runs lint, and tests to verify the release
 is healthy, commits with `release: vX.Y.Z [skip ci]`, creates an annotated
 tag, and pushes both to master.
 
@@ -285,13 +286,24 @@ Click commands from `cli.py` and verifies each has documentation in
 `architecture.md` and CI scripts in `ci-cd-workflow.md`. Supports
 `--fail-on-missing` to enforce 100% coverage.
 
-### `discover_runners.py`
+### `discover_runners.py` (deprecated wrapper)
+
+> **Deprecated:** Use `devx.molecule.discover_runners` instead. This
+> module is a thin wrapper that re-exports the canonical implementation.
 
 Discovers available Gitea Actions runners at three levels: repository,
-organization, and instance (admin). Falls back to the `MOLECULE_RUNNERS` repo
+organization, and instance (administrator). Falls back to the `MOLECULE_RUNNERS` repo
 variable or `DEFAULT_MAX_RUNNERS` (3). Outputs runner count or a JSON index
 array for use as a dynamic matrix in Gitea Actions.
 
+### `wait_for_checks.py`
+
+Polls the Gitea Actions API for job completion status. Used by auto-merge
+jobs that need to wait for parallel jobs (for example molecule-tests) before
+proceeding. Replaces inline shell polling in workflow YAML with a
+reusable, testable Python module. Exit codes: 0 (success), 1 (job
+failure), 2 (timeout), 3 (API error or no matching jobs).
+
 ### `distribute_files.py`
 
 Distributes files matching a glob pattern across N parallel runners
@@ -330,7 +342,7 @@ Supports `--tool` to install specific tools and `--list` to show status.
 Runs unit tests and enforces execution-time budgets. Two quality gates:
 total suite time must not exceed `--max-seconds` (default: 10s), and no
 individual test may exceed `--max-single-seconds` (default: 0.5s, 0 to
-disable). Runs `make test-unit` with `PYTEST_ADDOPTS=--durations=0`.
+off). Runs `make test-unit` with `PYTEST_ADDOPTS=--durations=0`.
 
 ### `check_test_isolation.py`
 
@@ -396,8 +408,13 @@ Intended for local development; CI uses the parallel matrix instead.
 
 ### `molecule/discover_runners.py`
 
-Discovers available Gitea Actions runners for molecule tests. Same logic as
-`devx.ci.discover_runners` but intended for molecule-specific workflows.
+Discovers available Gitea Actions runners for molecule tests. This is the
+canonical implementation; `devx.ci.discover_runners` is a deprecated wrapper
+that re-exports from this module. Queries runners at repository,
+organization, and instance (administrator) levels, with warnings logged
+to stderr on non-200 responses (except 403 on instance-level, which is
+expected without admin scope). Falls back to `MOLECULE_RUNNERS` env var
+or `DEFAULT_MAX_RUNNERS` (3).
 
 ### `start_docker.py`
 
@@ -436,6 +453,24 @@ v2 failures. Supports loading custom platforms from a JSON file.
 - **Secrets via environment** — secrets are passed via environment variables,
   never on the command line.
 
+## Composite Actions (`.gitea/actions/`)
+
+Reusable Gitea composite actions eliminate repeated multi-step sequences
+across workflows. Each action lives in `.gitea/actions/<name>/action.yml`
+and is referenced via `uses: ./.gitea/actions/<name>`.
+
+| Action | Purpose |
+|--------|---------|
+| `setup-env` | Run `make setup-image` (with optional `EXTRAS=`) |
+| `notify-failure` | Create a Gitea issue on job failure via `devx.ci.notify_failure` |
+| `quality-checks` | 6-step quality sequence: lint, tests, speed, docs, translations, security |
+
+Each consumer repo (`devx`, `grm`, `infra`) gets its own copy — there are
+no cross-repo composite action references. This avoids a single-point-of-failure
+where a bad devx master commit would break all repos' CI simultaneously.
+
+See ADR-0003 for the full design rationale and Gitea 1.27 constraints.
+
 ## Import rules
 
 1. **`src/devx/` is self-contained** — the package never imports from outside `src/`

docs/tech/ci-cd-workflow.md

@@ -38,22 +38,33 @@ The single validation job. Consolidates the former `quality`,
 `detect-changes`, `release-dry-run`, `pr-review`, and `pre-merge-check`
 jobs into one job to save checkout+setup overhead. Runs on every PR.
 
-**Quality steps**
+**Setup and quality steps** (composite actions)
 
-The main quality gate:
+The validate job uses three composite actions from `.gitea/actions/`:
 
-1. **Lint all** — ruff check, ruff format check, pyright, bandit, actionlint
-   (via `make lint-all`)
-2. **Unit tests with 100% coverage** — `make pytest-cov`
-3. **Check unit test speed** — `python -m devx.tools.check_test_speed
-   --max-seconds 4 --max-single-seconds 0.5`
-4. **Documentation coverage check** — `python -m devx.ci.doc_coverage
-   --fail-on-missing`
-5. **Translation completeness check** — `python -m devx.ci.check_translations`
-6. **Dependency security scan** — `pip-audit --desc --skip-editable`
-   (best-effort, non-blocking)
-7. **Workflow dry-run validation** — `make workflow-dryrun` via act_runner
-   (best-effort, skipped if act_runner is not installed)
+1. **`setup-env`** — runs `make setup-image` to link the pre-built venv
+   and install the project (no-deps mode)
+2. **`quality-checks`** — runs the 6-step quality gate:
+   - **Lint all** — ruff check, ruff format check, pyright, bandit,
+     actionlint (via `make lint-all`)
+   - **Unit tests with 100% coverage** — `make pytest-cov`
+   - **Check unit test speed** — `python -m devx.tools.check_test_speed
+     --max-seconds 15 --max-single-seconds 0.5`
+   - **Documentation gate** — `make devx-docs-check` (coverage + stale
+     refs + lint + version refs + prose)
+   - **Translation completeness check** — `python -m devx.ci.check_translations`
+   - **Dependency security scan** — `pip-audit --desc --skip-editable`
+     (best-effort, non-blocking)
+3. **`notify-failure`** — creates a Gitea issue if any step fails
+
+The quality-checks action accepts inputs (`package`, `test-speed-max`,
+`test-speed-max-single`, `translations-file`) for cross-repo reuse.
+See ADR-0003 for the composite action design rationale.
+
+**Workflow dry-run validation** (inline step, not part of composite action)
+
+`make workflow-dryrun` via act_runner (best-effort, skipped if
+act_runner is not installed).
 
 **`detect-changes` step**
 
@@ -574,8 +585,14 @@ picks up the new version number). This prevents infinite loops.
 
 ## Failure handling
 
-Every job in the CI and post-merge workflows has a `notify_failure` step
-that runs `if: failure()`. This creates a Gitea issue with the workflow name,
-run ID, and commit SHA, ensuring failures that would otherwise go unnoticed
-in the Actions tab are surfaced as issues. The issue is created via the tea
-CLI with a `bug` label if available.
+Every job in the CI, post-merge, and build-images workflows uses the
+`notify-failure` composite action (`.gitea/actions/notify-failure`),
+which runs `if: failure()`. This creates a Gitea issue with the workflow
+name, run ID, and commit SHA, ensuring failures that would otherwise go
+unnoticed in the Actions tab are surfaced as issues. The issue is created
+via the tea CLI with a `bug` label if available.
+
+Jobs with `notify-failure`:
+- `ci/validate`, `ci/auto-merge`
+- `post-merge/detect-and-configure`, `post-merge/release-and-maintain`
+- `build-images/build-and-push`, `build-images/cleanup`

docs/user/cli-commands.md

@@ -83,9 +83,14 @@ devx ci detect-release-commit
 
 ### `devx ci discover-runners`
 
+> **Deprecated:** Use `devx molecule discover-runners` instead. This
+> command is a thin wrapper that re-exports the canonical implementation
+> from `devx.molecule.discover_runners`. It will be removed in a future
+> release.
+
 Discover available Gitea Actions runners for dynamic job distribution.
 Queries the Gitea API for registered runners at repository, organization, and
-instance (admin) levels. Falls back to `MOLECULE_RUNNERS` repo variable or
+instance (administrator) levels. Falls back to `MOLECULE_RUNNERS` repo variable or
 `DEFAULT_MAX_RUNNERS` (3).
 
 ```bash
@@ -315,6 +320,82 @@ devx ci validate-commit-msg commit-msg.txt --branch master
 Options:
 - `--branch <branch>` — override branch detection (for CI use)
 
+### `devx ci wait-for-checks`
+
+Wait for Gitea Actions jobs to complete by polling the API. Used by
+auto-merge jobs that need to wait for parallel jobs (for example molecule-tests)
+before proceeding. Replaces inline shell polling in workflow YAML with
+a reusable, testable Python module.
+
+Exit codes:
+- `0` — all matching jobs completed successfully
+- `1` — one or more matching jobs failed (when `--require-success` is set)
+- `2` — timeout reached before all jobs completed
+- `3` — API error or no matching jobs found
+
+```bash
+devx ci wait-for-checks --job-name molecule-tests --repo oblachno-oss/grm
+devx ci wait-for-checks --job-name molecule-tests --timeout 1200 --poll-interval 10
+devx ci wait-for-checks --job-name molecule-tests --no-require-success
+```
+
+Options:
+- `--job-name <prefix>` — job name prefix to match (required)
+- `--repo <owner/name>` — repository (default: `$GITHUB_REPOSITORY`)
+- `--timeout <seconds>` — max wait time (default: 1200 = 20 min)
+- `--poll-interval <seconds>` — seconds between polls (default: 10)
+- `--require-success / --no-require-success` — exit 1 if a job failed (default: yes)
+
+### `devx ci cancel-superseded-runs`
+
+Cancel in-flight CI runs for the same PR branch when a new push triggers
+a new run. Uses the Gitea Actions API to list running pull_request runs
+and cancel those with a lower run ID on the same branch.
+
+```bash
+devx ci cancel-superseded-runs \
+    --repo "$REPOSITORY" \
+    --current-run-id "$GITHUB_RUN_ID" \
+    --head-branch "$HEAD_REF"
+```
+
+Options:
+- `--repo <owner/repo>` — repository (required)
+- `--current-run-id <id>` — current run ID, not cancelled (required)
+- `--head-branch <branch>` — PR head branch name (required)
+- `--dry-run` — list superseded runs without cancelling
+- `--base-url <url>` — Gitea base URL (default: `GITEA_API_URL` env var)
+
+### `devx ci check-workflow-artifact-deps`
+
+Verify that workflow jobs downloading artifacts depend on the uploading
+job. Prevents the class of bug where a download job runs in parallel
+with the upload job and fails because the artifact isn't available yet.
+
+```bash
+devx ci check-workflow-artifact-deps
+devx ci check-workflow-artifact-deps --workflow .gitea/workflows/ci.yml
+```
+
+Options:
+- `--workflow <path>` — check a specific workflow file
+- `--workflows-dir <path>` — override workflows directory
+
+### `devx ci check-workflow-tofu-init`
+
+Verify that workflow jobs using tofu state (tofu output/plan/apply or
+scripts that call them) have a tofu-init step in the same job.
+
+```bash
+devx ci check-workflow-tofu-init
+devx ci check-workflow-tofu-init --workflow .gitea/workflows/deploy.yml
+```
+
+Options:
+- `--workflow <path>` — check a specific workflow file
+- `--workflows-dir <path>` — override workflows directory
+- `--state-script <name>` — add a script that uses tofu state (repeatable)
+
 ## Tools Commands
 
 ### `devx tools check-test-speed`
@@ -323,7 +404,7 @@ Run unit tests and enforce execution-time budgets. Two quality gates:
 
 - **Total suite time** must not exceed `--max-seconds` (default: 10s)
 - **Per-test time** — no individual test may exceed `--max-single-seconds`
-  (default: 0.5s, 0 to disable)
+  (default: 0.5s, 0 to turn off)
 
 Runs `make test-unit` with `PYTEST_ADDOPTS=--durations=0` so pytest emits
 per-test timing lines.
@@ -369,7 +450,7 @@ devx tools check-test-isolation --src-dir src/
 
 Pytest plugin options (automatic when devx is installed):
 
-- `--no-test-isolation` — disable static analysis and runtime subprocess audit
+- `--no-test-isolation` — turn off static analysis and runtime subprocess audit
 - `--test-isolation-max-loop N` — max iterations per loop (default: 100)
 
 ### `devx tools configure-repo`
@@ -414,7 +495,7 @@ devx tools generate-cliff-config --prefix GRM --force  # overwrite existing
 Options:
 - `--prefix <prefix>` — task ID prefix (default: `DEVX_TASK_PREFIX` env var
   or `DEVX`)
-- `--output <file>` — output file path (default: `cliff.toml`)
+- `--output <file>` — output path (default: `cliff.toml`)
 - `--force` — overwrite existing file
 
 ### `devx tools install-checkmake`
@@ -488,6 +569,56 @@ devx tools pr-rebase                       # auto-detect PR from current branch
 Options (pass after `--`):
 - `--pr <N>` — PR number (auto-detected from current branch if omitted)
 
+### `devx tools check-docker-init`
+
+Check that Docker Compose services with healthchecks have `init: true`.
+Without `init: true`, CMD-SHELL healthchecks spawn child processes that
+become zombies when PID 1 doesn't reap them.
+
+```bash
+devx tools check-docker-init
+devx tools check-docker-init --path path/to/docker-compose.yml.j2
+```
+
+Options:
+- `--path <path>` — check a specific file or directory
+- `--templates-dir <path>` — override templates directory (default: `ansible/roles/`)
+
+### `devx tools check-ansible-set-fact-to-json`
+
+Check that Ansible `set_fact` tasks don't misuse `| to_json`. Using
+`to_json` in `set_fact` converts native Python types to JSON strings,
+causing iteration bugs (for example, iterating over characters instead
+of list items).
+
+```bash
+devx tools check-ansible-set-fact-to-json
+devx tools check-ansible-set-fact-to-json --path path/to/playbook.yml
+```
+
+Options:
+- `--path <path>` — check a specific file or directory
+- `--ansible-dir <path>` — override ansible directories (repeatable)
+
+### `devx tools check-alert-rules`
+
+Validate rendered Prometheus alert rules with `promtool check rules`.
+Renders a Jinja2 template with test values and validates the output.
+Skips (exits 0) if promtool is not on PATH.
+
+```bash
+devx tools check-alert-rules \
+    --template-path ansible/roles/observability/templates
+devx tools check-alert-rules \
+    --template-path ansible/roles/observability/templates \
+    --var grafana_base_url=https://grafana.example.com
+```
+
+Options:
+- `--template-path <path>` — path to templates directory (required)
+- `--template-name <name>` — template filename (default: `alert-rules.yml.j2`)
+- `--var key=value` — template variables (repeatable)
+
 ## Molecule Commands
 
 Molecule commands require the `molecule` extra (`pip install devx[molecule]`).

docs/user/getting-started.md

@@ -48,12 +48,12 @@ Add devx to your `pyproject.toml`:
 ```toml
 [project]
 dependencies = [
-    "devx>=0.47.3",
+    "devx>=0.50.4",
 ]
 
 [project.optional-dependencies]
 dev = [
-    "devx>=0.47.3",
+    "devx>=0.50.4",
 ]
 ```
 

pyproject.toml

@@ -20,6 +20,8 @@ dependencies = [
     "python-dotenv==1.2.2",
     "click==8.4.2",
     "tenacity==9.1.4",  # retry logic for GiteaClient/VikunjaClient
+    "jinja2==3.1.6",  # template rendering (devx.utils.jinja, check_alert_rules)
+    "pyyaml==6.0.3",  # YAML parsing (workflow checks, ansible checks)
 ]
 
 [project.scripts]
@@ -62,13 +64,16 @@ molecule = [
     "ansible-core==2.21.1",
 ]
 # Deploy tools (for infra staging/production deployments)
+# Versions aligned with infra's pyproject.toml to avoid reinstalls on every CI job.
+# bcrypt and PyJWT are infra deps not in devx core — included here so the CI
+# image has them and setup-image can use --no-deps (skip dep resolution).
 deploy = [
     "ansible-core==2.21.1",
-    "boto3==1.43.37",
+    "boto3==1.43.44",
     "docker==7.1.0",
-    "jinja2==3.1.6",
-    "pyyaml==6.0.3",
-    "cryptography==49.0.0",
+    "cryptography==50.0.0",
+    "bcrypt==5.0.0",
+    "PyJWT==2.13.0",
 ]
 # Full dev environment (local development)
 dev = [

src/devx/__init__.py

@@ -1,3 +1,3 @@
 """devx — reusable development and CI/CD tools for oblachno-oss projects."""
 
-__version__ = "0.47.3"
+__version__ = "0.50.4"

src/devx/ci/cancel_superseded_runs.py

@@ -0,0 +1,185 @@
+"""Cancel superseded CI runs for the same PR.
+
+When a new push to a PR branch triggers a new CI run, any in-flight
+runs for the same PR are wasting runner time. This script cancels
+all but the latest running CI run for each PR branch.
+
+Uses the Gitea Actions API:
+  GET  /repos/{owner}/{repo}/actions/runs?status=in_progress&event=pull_request
+  POST /repos/{owner}/{repo}/actions/runs/{run_id}/cancel
+
+Usage::
+
+  # CI (cancels superseded runs for the current PR):
+  python -m devx.ci.cancel_superseded_runs \\
+      --repo "$REPOSITORY" \\
+      --current-run-id "$GITHUB_RUN_ID" \\
+      --head-branch "$HEAD_REF"
+
+  # Dry-run (lists what would be cancelled without cancelling):
+  python -m devx.ci.cancel_superseded_runs \\
+      --repo "$REPOSITORY" \\
+      --current-run-id "$GITHUB_RUN_ID" \\
+      --head-branch "$HEAD_REF" \\
+      --dry-run
+"""
+
+from __future__ import annotations
+
+import argparse
+import json
+import os
+import sys
+import urllib.error
+import urllib.request
+
+_HTTP_NO_CONTENT = 204
+_HTTP_NOT_FOUND = 404
+_HTTP_BAD_REQUEST = 400
+_PAGE_SIZE = 50
+
+
+def _log(msg: str) -> None:
+    """Log to stderr."""
+    print(f"[cancel-superseded] {msg}", file=sys.stderr, flush=True)
+
+
+def _api_request(
+    method: str,
+    path: str,
+    token: str,
+    base_url: str,
+    body: dict | None = None,
+) -> dict | list:
+    """Make a Gitea API request."""
+    url = f"{base_url}/api/v1{path}"
+    headers = {
+        "Authorization": f"token {token}",
+        "Content-Type": "application/json",
+        "Accept": "application/json",
+    }
+    data = json.dumps(body).encode() if body else None
+    req = urllib.request.Request(url, data=data, headers=headers, method=method)
+    try:
+        with urllib.request.urlopen(req, timeout=30) as resp:  # nosec B310 — authenticated API request to known Gitea instance
+            if resp.status == _HTTP_NO_CONTENT:
+                return {}
+            return json.loads(resp.read().decode())
+    except urllib.error.HTTPError as e:
+        _log(f"API error {e.code} on {method} {path}: {e.read().decode()[:200]}")
+        raise
+    except urllib.error.URLError as e:
+        _log(f"URL error on {method} {path}: {e}")
+        raise
+
+
+def list_running_runs(repo: str, token: str, base_url: str) -> list[dict]:
+    """List all running CI runs for pull_request events."""
+    runs: list[dict] = []
+    page = 1
+    while True:
+        result = _api_request(
+            "GET",
+            f"/repos/{repo}/actions/runs?status=in_progress&event=pull_request&page={page}&limit=50",
+            token,
+            base_url,
+        )
+        # Gitea returns {"workflow_runs": [...], "total_count": N}
+        page_runs = result["workflow_runs"] if isinstance(result, dict) else result
+        if not page_runs:
+            break
+        runs.extend(page_runs)
+        if len(page_runs) < _PAGE_SIZE:
+            break
+        page += 1
+    return runs
+
+
+def cancel_run(repo: str, run_id: int, token: str, base_url: str) -> bool:
+    """Cancel a CI run. Returns True on success."""
+    try:
+        _api_request(
+            "POST",
+            f"/repos/{repo}/actions/runs/{run_id}/cancel",
+            token,
+            base_url,
+        )
+    except (urllib.error.HTTPError, urllib.error.URLError):
+        return False
+    return True
+
+
+def main() -> int:
+    parser = argparse.ArgumentParser(description="Cancel superseded CI runs for the same PR.")
+    parser.add_argument("--repo", required=True, help="owner/repo")
+    parser.add_argument("--current-run-id", required=True, help="Current run ID (not cancelled)")
+    parser.add_argument("--head-branch", required=True, help="PR head branch name")
+    parser.add_argument("--dry-run", action="store_true", help="List without cancelling")
+    parser.add_argument(
+        "--base-url",
+        default=os.environ.get("GITEA_API_URL", "https://git.oblachno.oblachno.fyi"),
+        help="Gitea base URL",
+    )
+    args = parser.parse_args()
+
+    token = os.environ.get("CI_GITEA_API_TOKEN") or os.environ.get("CI_GITEA_TOKEN")
+    if not token:
+        _log("No CI_GITEA_API_TOKEN or CI_GITEA_TOKEN set — skipping")
+        return 0
+
+    current_run_id = int(args.current_run_id)
+
+    _log(f"Listing running PR runs for {args.repo}...")
+    try:
+        runs = list_running_runs(args.repo, token, args.base_url)
+    except urllib.error.HTTPError as e:
+        if e.code in (_HTTP_NOT_FOUND, _HTTP_BAD_REQUEST):
+            _log(
+                f"Actions runs API not usable (HTTP {e.code}) — "
+                f"Gitea {args.base_url} may not support this endpoint or status filter. "
+                f"Skipping cancel-superseded (non-fatal)."
+            )
+            return 0
+        raise
+    _log(f"Found {len(runs)} running PR runs")
+
+    # Group by head_branch — only cancel runs for the SAME branch
+    # that are older than the current run
+    same_branch_runs = [
+        r
+        for r in runs
+        if r.get("head_branch") == args.head_branch
+        and int(r.get("id", 0)) != current_run_id
+        and int(r.get("id", 0)) < current_run_id
+    ]
+
+    if not same_branch_runs:
+        _log(f"No superseded runs for branch {args.head_branch}")
+        return 0
+
+    _log(f"Found {len(same_branch_runs)} superseded run(s) for branch {args.head_branch}:")
+    for r in same_branch_runs:
+        run_id = r.get("id")
+        created = r.get("created_at", "?")
+        _log(f"  Run #{run_id} (created: {created})")
+
+    if args.dry_run:
+        _log("[dry-run] Would cancel the above runs")
+        return 0
+
+    cancelled = 0
+    for r in same_branch_runs:
+        run_id = int(r["id"])
+        _log(f"Cancelling run #{run_id}...")
+        if cancel_run(args.repo, run_id, token, args.base_url):
+            cancelled += 1
+            _log(f"  Cancelled run #{run_id}")
+        else:
+            _log(f"  Failed to cancel run #{run_id}")
+
+    _log(f"Cancelled {cancelled}/{len(same_branch_runs)} superseded runs")
+    return 0
+
+
+if __name__ == "__main__":  # pragma: no cover
+    raise SystemExit(main())

src/devx/ci/check_workflow_artifact_deps.py

@@ -0,0 +1,163 @@
+"""Check that workflow jobs downloading artifacts depend on the uploading job.
+
+This prevents the class of bug where a job downloads an artifact produced by
+another job but does not declare that job in its ``needs`` list. When both
+jobs run in parallel, the download fails because the artifact hasn't been
+uploaded yet.
+
+The check scans all workflow YAML files for:
+  - ``gitea-upload-artifact`` / ``actions/upload-artifact`` steps
+  - ``gitea-download-artifact`` / ``actions/download-artifact`` steps
+
+For each download, it finds the job(s) that upload an artifact with a
+matching name and verifies that at least one uploading job is in the
+downloading job's ``needs`` list.
+
+Artifact names with ``${{ ... }}`` expressions are matched literally
+(both sides use the same expression, so they resolve to the same value
+at runtime).
+
+Usage::
+
+    python -m devx.ci.check_workflow_artifact_deps
+    python -m devx.ci.check_workflow_artifact_deps --workflow .gitea/workflows/ci.yml
+
+Exit code 0 if all artifact dependencies are satisfied, 1 otherwise.
+"""
+
+from __future__ import annotations
+
+import sys
+from pathlib import Path
+
+import click
+import yaml
+
+REPO_ROOT = Path.cwd()
+WORKFLOWS_DIR = REPO_ROOT / ".gitea" / "workflows"
+
+UPLOAD_ACTIONS = ("upload-artifact",)
+DOWNLOAD_ACTIONS = ("download-artifact",)
+
+
+def _is_artifact_action(uses: str, action_types: tuple[str, ...]) -> bool:
+    """Check if a step's ``uses`` field references an artifact action."""
+    if not uses:
+        return False
+    uses_lower = uses.lower()
+    return any(action in uses_lower for action in action_types)
+
+
+def _extract_artifact_info(workflow: dict) -> tuple[dict[str, list[str]], list[tuple[str, str, str]]]:
+    """Extract artifact upload and download info from a workflow.
+
+    Returns:
+        uploads: Mapping of artifact_name → list of job names that upload it.
+        downloads: List of (job_name, artifact_name, step_name) tuples.
+    """
+    uploads: dict[str, list[str]] = {}
+    downloads: list[tuple[str, str, str]] = []
+
+    jobs = workflow.get("jobs", {})
+    for job_name, job_def in jobs.items():
+        for step in job_def.get("steps", []):
+            uses = step.get("uses", "")
+            with_data = step.get("with", {})
+            artifact_name = with_data.get("name", "")
+            step_name = step.get("name", "")
+
+            if _is_artifact_action(uses, UPLOAD_ACTIONS):
+                if artifact_name:
+                    uploads.setdefault(artifact_name, []).append(job_name)
+            elif _is_artifact_action(uses, DOWNLOAD_ACTIONS) and artifact_name:
+                downloads.append((job_name, artifact_name, step_name))
+
+    return uploads, downloads
+
+
+def _check_workflow(filepath: Path) -> list[str]:
+    """Check a single workflow file for missing artifact dependencies.
+
+    Returns a list of error messages (empty if all OK).
+    """
+    errors: list[str] = []
+    content = filepath.read_text(encoding="utf-8")
+    try:
+        workflow = yaml.safe_load(content)
+    except yaml.YAMLError as exc:
+        return [f"{filepath}: cannot parse YAML: {exc}"]
+
+    if not isinstance(workflow, dict):
+        return [f"{filepath}: not a valid workflow (expected dict)"]
+
+    uploads, downloads = _extract_artifact_info(workflow)
+    jobs = workflow.get("jobs", {})
+
+    for dl_job, artifact_name, step_name in downloads:
+        uploading_jobs = uploads.get(artifact_name, [])
+        if not uploading_jobs:
+            # Artifact not uploaded in this workflow — may come from an
+            # external source (e.g., S3). Skip.
+            continue
+
+        dl_job_def = jobs.get(dl_job, {})
+        needs_raw = dl_job_def.get("needs", [])
+        needs = {needs_raw} if isinstance(needs_raw, str) else set(needs_raw or [])
+
+        # Check if any uploading job is in the download job's needs
+        if not any(uploader in needs for uploader in uploading_jobs):
+            # Check if the download step has continue-on-error: true
+            # (valid guard when the uploading job may be skipped due to
+            # Gitea Actions' needs skip behavior — the download will
+            # fail gracefully if the artifact doesn't exist).
+            dl_steps = dl_job_def.get("steps", [])
+            step_def = next((s for s in dl_steps if s.get("name", "") == step_name), {})
+            if step_def.get("continue-on-error") is True:
+                continue
+
+            uploaders_str = ", ".join(sorted(uploading_jobs))
+            errors.append(
+                f"{filepath.name}::{dl_job}: step '{step_name}' downloads "
+                f"artifact '{artifact_name}' produced by job(s) "
+                f"[{uploaders_str}] but none are in its 'needs' list "
+                f"(current needs: {sorted(needs) or 'none'}). "
+                f"Add the uploading job to 'needs' or guard the download "
+                f"with an if: condition checking the upload job's result."
+            )
+
+    return errors
+
+
+@click.command()
+@click.option(
+    "--workflow",
+    type=click.Path(exists=True, path_type=Path),
+    help="Check a specific workflow file (default: all in .gitea/workflows/).",
+)
+@click.option(
+    "--workflows-dir",
+    type=click.Path(exists=True, path_type=Path),
+    default=None,
+    help="Override the workflows directory (default: .gitea/workflows/).",
+)
+def main(workflow: Path | None, workflows_dir: Path | None) -> None:
+    """Check that artifact download jobs depend on upload jobs."""
+    wdir = workflows_dir or WORKFLOWS_DIR
+    files = [workflow] if workflow else sorted(wdir.glob("*.yml"))
+
+    all_errors: list[str] = []
+    for f in files:
+        errors = _check_workflow(f)
+        all_errors.extend(errors)
+
+    if all_errors:
+        click.echo("[check-workflow-artifact-deps] FAIL: missing artifact dependencies found:")
+        for err in all_errors:
+            click.echo(f"  - {err}")
+        sys.exit(1)
+    else:
+        click.echo("[check-workflow-artifact-deps] OK: all artifact downloads have upload jobs in needs.")
+
+
+if __name__ == "__main__":  # pragma: no cover
+    main()

src/devx/ci/check_workflow_tofu_init.py

@@ -0,0 +1,145 @@
+"""Check that workflow jobs using tofu state have a tofu-init step.
+
+This prevents the class of bug where a job runs ``tofu output`` or calls
+a script that uses tofu state without first running ``tofu init``,
+causing "Required plugins are not installed" errors.
+
+The check scans all workflow YAML files for jobs that:
+  - Call scripts that use ``tofu output`` (configurable via --state-scripts)
+  - Call ``tofu output`` directly
+  - Call ``tofu plan`` or ``tofu apply`` directly
+
+For each such job, it verifies the same job has a ``tofu-init`` step,
+either:
+  - Directly via ``tofu init`` in a step's run command
+  - Via ``create_staging_deployment.py --phase tofu-init``
+  - Via ``create_production_deployment.py --phase tofu-init``
+
+Usage::
+
+    python -m devx.ci.check_workflow_tofu_init
+    python -m devx.ci.check_workflow_tofu_init --workflow .gitea/workflows/deploy.yml
+
+Exit code 0 if all jobs have tofu-init, 1 otherwise.
+"""
+
+from __future__ import annotations
+
+import sys
+from pathlib import Path
+
+import click
+import yaml
+
+REPO_ROOT = Path.cwd()
+WORKFLOWS_DIR = REPO_ROOT / ".gitea" / "workflows"
+
+# Scripts that call `tofu output`, `tofu plan`, or `tofu apply` internally.
+# If a job calls any of these, it must have a tofu-init step.
+# NOTE: destroy_orphans.py reads terraform.tfstate directly from disk
+# (does not invoke `tofu output`), so it does NOT need tofu-init.
+DEFAULT_TOFU_STATE_SCRIPTS: set[str] = {
+    "preflight_deploy.py",
+}
+
+# Commands that directly use tofu state (must be preceded by tofu init).
+TOFU_STATE_COMMANDS = ("tofu output", "tofu plan", "tofu apply", "tofu show")
+
+# Commands that initialize tofu (counted as tofu-init steps).
+TOFU_INIT_COMMANDS = (
+    "tofu init",
+    "--phase tofu-init",
+    "tofu-init",
+)
+
+
+def _check_workflow(filepath: Path, state_scripts: set[str]) -> list[str]:
+    """Check a single workflow file for missing tofu-init steps.
+
+    Returns a list of error messages (empty if all OK).
+    """
+    errors: list[str] = []
+    content = filepath.read_text(encoding="utf-8")
+    try:
+        workflow = yaml.safe_load(content)
+    except yaml.YAMLError as exc:
+        return [f"{filepath}: cannot parse YAML: {exc}"]
+
+    jobs = workflow.get("jobs", {})
+    for job_name, job_def in jobs.items():
+        steps = job_def.get("steps", [])
+        if not steps:
+            continue
+
+        uses_tofu_state = False
+        has_tofu_init = False
+
+        for step in steps:
+            run_cmd = step.get("run", "")
+            if not run_cmd:
+                continue
+            # Check if this step uses tofu state
+            for script in state_scripts:
+                if script in run_cmd:
+                    uses_tofu_state = True
+            for cmd in TOFU_STATE_COMMANDS:
+                if cmd in run_cmd:
+                    uses_tofu_state = True
+            # Check if this step initializes tofu
+            for cmd in TOFU_INIT_COMMANDS:
+                if cmd in run_cmd:
+                    has_tofu_init = True
+
+        if uses_tofu_state and not has_tofu_init:
+            errors.append(
+                f"{filepath.name}::{job_name}: uses tofu state "
+                f"(tofu output/plan/apply or {state_scripts}) "
+                f"but has no tofu-init step. Add a step running "
+                f"'create_*_deployment.py --phase tofu-init' before "
+                f"the first tofu state access."
+            )
+
+    return errors
+
+
+@click.command()
+@click.option(
+    "--workflow",
+    type=click.Path(exists=True, path_type=Path),
+    help="Check a specific workflow file (default: all in .gitea/workflows/).",
+)
+@click.option(
+    "--workflows-dir",
+    type=click.Path(exists=True, path_type=Path),
+    default=None,
+    help="Override the workflows directory (default: .gitea/workflows/).",
+)
+@click.option(
+    "--state-script",
+    "state_scripts",
+    multiple=True,
+    default=None,
+    help="Add a script name that uses tofu state (can be repeated). Overrides the default list if any are specified.",
+)
+def main(workflow: Path | None, workflows_dir: Path | None, state_scripts: tuple[str, ...]) -> None:
+    """Check that workflow jobs using tofu state have a tofu-init step."""
+    scripts = set(state_scripts) if state_scripts else DEFAULT_TOFU_STATE_SCRIPTS
+    wdir = workflows_dir or WORKFLOWS_DIR
+    files = [workflow] if workflow else sorted(wdir.glob("*.yml"))
+
+    all_errors: list[str] = []
+    for f in files:
+        errors = _check_workflow(f, scripts)
+        all_errors.extend(errors)
+
+    if all_errors:
+        click.echo("[check-workflow-tofu-init] FAIL: missing tofu-init steps found:")
+        for err in all_errors:
+            click.echo(f"  - {err}")
+        sys.exit(1)
+    else:
+        click.echo("[check-workflow-tofu-init] OK: all tofu-state jobs have tofu-init.")
+
+
+if __name__ == "__main__":  # pragma: no cover
+    main()

src/devx/ci/discover_runners.py

@@ -1,19 +1,18 @@
 #!/usr/bin/env python3
 """Discover available Gitea Actions runners for dynamic job distribution.
 
-Queries the Gitea API for registered runners at three levels:
-  1. Repository level: GET /repos/{owner}/{repo}/actions/runners
-  2. Organization level: GET /orgs/{org}/actions/runners
-  3. Instance (admin) level: GET /admin/actions/runners
+.. deprecated:: Phase 1c
+    Use :mod:`devx.molecule.discover_runners` instead. This module is a
+    thin wrapper that re-exports the canonical implementation from
+    :mod:`devx.molecule.discover_runners` for backward compatibility
+    with existing workflow references and Makefile targets.
 
-Falls back to the ``MOLECULE_RUNNERS`` repo variable or environment
-variable, then to ``DEFAULT_MAX_RUNNERS`` (3).
-
-Outputs:
-  - ``--count``: prints the number of available runners
-  - ``--indices``: prints a JSON array [0, 1, ..., N-1] for use as a
-    dynamic matrix in Gitea Actions
-  - (default): prints both as ``count=N`` and ``indices=[0,1,...]``
+    The canonical implementation lives in
+    :mod:`devx.molecule.discover_runners` because runner discovery is
+    primarily used by the molecule test distribution pipeline. CI
+    workflows that still reference ``python -m devx.ci.discover_runners``
+    will continue to work via this wrapper, but new code should import
+    from :mod:`devx.molecule.discover_runners` directly.
 
 Usage:
   python3 -m devx.ci.discover_runners --owner oblachno-oss --repo devx
@@ -23,172 +22,28 @@ Usage:
 
 from __future__ import annotations
 
-import json
-import os
+import sys
+import warnings
 
-import click
-import requests
-
-from devx.config import GITEA_API_URL, REPO_NAME, REPO_OWNER
-from devx.i18n import _
-from devx.tokens import get_ci_token
-
-DEFAULT_MAX_RUNNERS = 3
-
-
-def query_runners(api_url: str, token: str, owner: str, repo: str) -> int:
-    """Query the Gitea API for registered runners at all levels.
-
-    Returns the total count of active runners.  If the API call fails
-    (e.g., no admin access for instance-level runners), falls back to
-    what we can see.  Fallbacks are logged to stderr for debugging.
-    """
-    headers = {"Authorization": f"token {token}"}
-    total = 0
-
-    # 1. Repository-level runners
-    try:
-        r = requests.get(
-            f"{api_url}/repos/{owner}/{repo}/actions/runners",
-            headers=headers,
-            timeout=10,
-        )
-        if r.status_code == 200:
-            data = r.json()
-            total += data.get("total_count", 0)
-        else:
-            click.echo(_("Warning: repo-level runners query returned HTTP {status}", status=r.status_code), err=True)
-    except (requests.RequestException, ValueError) as e:
-        click.echo(_("Warning: repo-level runners query failed: {error}", error=e), err=True)
-
-    # 2. Organization-level runners
-    try:
-        r = requests.get(
-            f"{api_url}/orgs/{owner}/actions/runners",
-            headers=headers,
-            timeout=10,
-        )
-        if r.status_code == 200:
-            data = r.json()
-            total += data.get("total_count", 0)
-        else:
-            click.echo(_("Warning: org-level runners query returned HTTP {status}", status=r.status_code), err=True)
-    except (requests.RequestException, ValueError) as e:
-        click.echo(_("Warning: org-level runners query failed: {error}", error=e), err=True)
-
-    # 3. Instance-level runners (requires admin scope)
-    try:
-        r = requests.get(
-            f"{api_url}/admin/actions/runners",
-            headers=headers,
-            timeout=10,
-        )
-        if r.status_code == 200:
-            data = r.json()
-            total += data.get("total_count", 0)
-        elif r.status_code != 403:  # 403 is expected without admin scope
-            click.echo(
-                _("Warning: instance-level runners query returned HTTP {status}", status=r.status_code),
-                err=True,
-            )
-    except (requests.RequestException, ValueError) as e:
-        click.echo(_("Warning: instance-level runners query failed: {error}", error=e), err=True)
-
-    return total
-
-
-def get_runner_count(api_url: str, token: str | None, owner: str, repo: str) -> int:
-    """Determine the number of available runners.
-
-    Tries the Gitea API first, then falls back to env vars, then default.
-    """
-    # Try API query if we have a token
-    if token:
-        api_count = query_runners(api_url, token, owner, repo)
-        if api_count > 0:
-            return api_count
-
-    # Fall back to MOLECULE_RUNNERS env var (set by CI from repo variable)
-    env_count = os.environ.get("MOLECULE_RUNNERS")
-    if env_count:
-        try:
-            count = int(env_count)
-            if count > 0:
-                return count
-        except ValueError:
-            pass
-
-    # Fall back to default
-    return DEFAULT_MAX_RUNNERS
-
-
-def generate_indices(count: int) -> list[str]:
-    """Generate a list of runner indices ["1", "2", ..., "N"].
-
-    Uses 1-based string indices because Gitea Actions renders
-    integer 0 and string "0" as empty in ${{ matrix.runner-index }}
-    expressions, causing --runner-index to be passed without a value.
-    The distribute_molecule.py script converts these back to 0-based
-    internally.
-    """
-    return [str(i + 1) for i in range(count)]
-
-
-@click.command()
-@click.option("--owner", default=None, help="Repository owner (for API query).")
-@click.option("--repo", default=None, help="Repository name (for API query).")
-@click.option("--count", "output_count", is_flag=True, help="Output only the count.")
-@click.option("--indices", "output_indices", is_flag=True, help="Output only the JSON indices array.")
-@click.option(
-    "--github-output",
-    "github_output",
-    is_flag=True,
-    default=False,
-    help="Write results to $GITHUB_OUTPUT file (for CI workflow steps).",
+from devx.molecule.discover_runners import (  # noqa: F401 — re-exported for backward compat
+    DEFAULT_MAX_RUNNERS,
+    generate_indices,
+    get_runner_count,
+    main,
+    query_runners,
 )
-def main(
-    owner: str | None,
-    repo: str | None,
-    output_count: bool,
-    output_indices: bool,
-    github_output: bool,
-) -> None:
-    try:
-        token = get_ci_token()
-    except click.ClickException:
-        token = None
 
-    if owner is None:
-        owner = os.environ.get("DEVX_REPO_OWNER", "") or REPO_OWNER
-    if repo is None:
-        repo = os.environ.get("DEVX_REPO_NAME", "") or REPO_NAME
+_DEPRECATION_MSG = (
+    "devx.ci.discover_runners is deprecated; use devx.molecule.discover_runners instead. "
+    "This wrapper will be removed in a future release."
+)
 
-    count = get_runner_count(GITEA_API_URL, token, owner, repo)
-    indices = generate_indices(count)
 
-    if github_output:
-        gh_output = os.environ.get("GITHUB_OUTPUT")
-        if not gh_output:
-            raise click.ClickException("GITHUB_OUTPUT environment variable is not set")
-        with open(gh_output, "a", encoding="utf-8") as f:  # noqa: PTH123
-            f.write(f"runner-count={count}\n")
-            f.write(f"runner-indices={json.dumps(indices)}\n")
-        click.echo(_("Runner count: {count}", count=count))
-        click.echo(_("Runner indices: {indices}", indices=indices))
-        return
-
-    if output_count:
-        click.echo(str(count))
-        return
-
-    if output_indices:
-        click.echo(json.dumps(indices))
-        return
-
-    # Default: output both as key=value pairs for CI consumption
-    click.echo(_("count={count}", count=count))
-    click.echo(_("indices={indices}", indices=json.dumps(indices)))
+def _emit_deprecation_warning() -> None:
+    """Emit a DeprecationWarning when this module is imported for CLI use."""
+    warnings.warn(_DEPRECATION_MSG, DeprecationWarning, stacklevel=2)
 
 
 if __name__ == "__main__":  # pragma: no cover
-    main()
+    _emit_deprecation_warning()
+    sys.exit(main())

src/devx/ci/wait_for_checks.py

@@ -0,0 +1,209 @@
+#!/usr/bin/env python3
+"""Wait for Gitea Actions jobs to complete.
+
+Polls the Gitea API for job completion status. Used by auto-merge
+jobs that need to wait for molecule-tests or other parallel jobs
+before proceeding.
+
+Exits:
+  0 — all matching jobs completed successfully
+  1 — one or more matching jobs failed
+  2 — timeout reached before all jobs completed
+  3 — API error or job not found
+
+Usage:
+  python3 -m devx.ci.wait_for_checks \\
+    --job-name molecule-tests \\
+    --repo oblachno-oss/grm \\
+    --timeout 1200 \\
+    --poll-interval 10
+"""
+
+from __future__ import annotations
+
+import os
+import sys
+import time
+
+import click
+import requests
+
+from devx.config import GITEA_API_URL
+from devx.i18n import _
+from devx.tokens import get_ci_token
+
+
+def query_job_status(api_url: str, token: str, repo: str, job_name_prefix: str) -> list[dict]:
+    """Query the Gitea API for the status of jobs matching *job_name_prefix*.
+
+    Fetches the most recent pull_request runs (up to 3) and inspects
+    their jobs. Returns a list of ``{"name": str, "status": str,
+    "conclusion": str | None}`` dicts for jobs whose name starts with
+    *job_name_prefix*. On API errors, logs a warning to stderr and
+    returns an empty list — callers treat this as "no information yet"
+    and retry on the next poll.
+    """
+    headers = {"Authorization": f"token {token}"}
+    matches: list[dict] = []
+    try:
+        r = requests.get(
+            f"{api_url}/repos/{repo}/actions/runs",
+            headers=headers,
+            params={"limit": 5, "event": "pull_request"},
+            timeout=10,
+        )
+        if r.status_code != 200:
+            click.echo(
+                _("Warning: actions runs query returned HTTP {status}", status=r.status_code),
+                err=True,
+            )
+            return []
+        runs = r.json()
+        if isinstance(runs, dict):
+            runs = runs.get("runs", [])
+    except (requests.RequestException, ValueError) as e:
+        click.echo(_("Warning: actions runs query failed: {error}", error=e), err=True)
+        return []
+
+    for run in runs[:3]:
+        run_id = run.get("id")
+        if run_id is None:
+            continue
+        try:
+            jr = requests.get(
+                f"{api_url}/repos/{repo}/actions/runs/{run_id}/jobs",
+                headers=headers,
+                timeout=10,
+            )
+            if jr.status_code != 200:
+                click.echo(
+                    _(
+                        "Warning: jobs query for run {run_id} returned HTTP {status}",
+                        run_id=run_id,
+                        status=jr.status_code,
+                    ),
+                    err=True,
+                )
+                continue
+            jobs = jr.json()
+            if isinstance(jobs, dict):
+                jobs = jobs.get("jobs", [])
+        except (requests.RequestException, ValueError) as e:
+            click.echo(
+                _("Warning: jobs query for run {run_id} failed: {error}", run_id=run_id, error=e),
+                err=True,
+            )
+            continue
+        for job in jobs:
+            name = job.get("name", "")
+            if name.startswith(job_name_prefix):
+                matches.append(
+                    {
+                        "name": name,
+                        "status": job.get("status", "unknown"),
+                        "conclusion": job.get("conclusion"),
+                    }
+                )
+    return matches
+
+
+def poll_until_complete(
+    api_url: str,
+    token: str,
+    repo: str,
+    job_name: str,
+    timeout: int,
+    interval: int,
+    require_success: bool = True,
+) -> int:
+    """Poll *query_job_status* until all matching jobs complete or *timeout*.
+
+    Returns:
+      0 — all matching jobs completed successfully (or any completed, when
+          *require_success* is False)
+      1 — at least one matching job completed with a non-success conclusion
+          (only when *require_success* is True)
+      2 — *timeout* reached before all matching jobs completed
+      3 — no matching jobs found at all within *timeout*
+    """
+    deadline = time.monotonic() + timeout
+    found_any = False
+
+    while time.monotonic() < deadline:
+        jobs = query_job_status(api_url, token, repo, job_name)
+        if jobs:
+            found_any = True
+            all_completed = all(j["status"] == "completed" for j in jobs)
+            if all_completed:
+                if require_success and any(j["conclusion"] != "success" for j in jobs):
+                    click.echo(
+                        _("Job(s) completed with non-success conclusion: {jobs}", jobs=jobs),
+                        err=True,
+                    )
+                    return 1
+                click.echo(_("All matching jobs completed successfully: {jobs}", jobs=jobs))
+                return 0
+        # Not all completed (or no jobs yet) — sleep and retry.
+        time.sleep(min(interval, max(0, deadline - time.monotonic())))
+
+    if not found_any:
+        click.echo(_("No matching jobs found for prefix '{prefix}' within timeout.", prefix=job_name), err=True)
+        return 3
+    click.echo(_("Timeout reached waiting for jobs matching '{prefix}'.", prefix=job_name), err=True)
+    return 2
+
+
+@click.command()
+@click.option("--job-name", required=True, help="Job name prefix to match (e.g. 'molecule-tests').")
+@click.option(
+    "--repo",
+    default=None,
+    help="Repository as owner/name (default: $GITHUB_REPOSITORY env var).",
+)
+@click.option("--timeout", type=int, default=1200, help="Max seconds to wait (default: 1200 = 20 min).")
+@click.option("--poll-interval", "interval", type=int, default=10, help="Seconds between polls (default: 10).")
+@click.option(
+    "--require-success/--no-require-success",
+    default=True,
+    help="Exit 1 if a matched job failed (default: yes).",
+)
+def main(job_name: str, repo: str | None, timeout: int, interval: int, require_success: bool) -> None:
+    """Wait for Gitea Actions jobs matching --job-name to complete."""
+    if repo is None:
+        repo = os.environ.get("GITHUB_REPOSITORY", "")
+    if not repo or "/" not in repo:
+        raise click.ClickException(_("--repo is required (or set GITHUB_REPOSITORY=owner/name)"))
+    if timeout <= 0:
+        raise click.ClickException(_("--timeout must be positive"))
+    if interval <= 0:
+        raise click.ClickException(_("--poll-interval must be positive"))
+
+    try:
+        token = get_ci_token()
+    except click.ClickException as e:
+        click.echo(str(e), err=True)
+        sys.exit(3)
+
+    click.echo(
+        _(
+            "Waiting for jobs matching '{prefix}' in {repo} (timeout={timeout}s, interval={interval}s)",
+            prefix=job_name,
+            repo=repo,
+            timeout=timeout,
+            interval=interval,
+        )
+    )
+    code = poll_until_complete(
+        GITEA_API_URL,
+        token,
+        repo,
+        job_name,
+        timeout,
+        interval,
+        require_success=require_success,
+    )
+    sys.exit(code)
+
+
+if __name__ == "__main__":  # pragma: no cover
+    main()

src/devx/cli.py

@@ -158,6 +158,13 @@ def ci_validate_commit_msg(args: tuple[str, ...]) -> None:
     _run_module("devx.ci.validate_commit_msg", list(args))
 
 
+@ci.command("wait-for-checks")
+@click.argument("args", nargs=-1)
+def ci_wait_for_checks(args: tuple[str, ...]) -> None:
+    """Wait for Gitea Actions jobs to complete (polls API)."""
+    _run_module("devx.ci.wait_for_checks", list(args))
+
+
 @ci.command("distribute-files")
 @click.argument("args", nargs=-1)
 def ci_distribute_files(args: tuple[str, ...]) -> None:
@@ -172,6 +179,27 @@ def ci_integration_guard(args: tuple[str, ...]) -> None:
     _run_module("devx.ci.integration_guard", list(args))
 
 
+@ci.command("cancel-superseded-runs")
+@click.argument("args", nargs=-1)
+def ci_cancel_superseded_runs(args: tuple[str, ...]) -> None:
+    """Cancel superseded CI runs for the same PR branch."""
+    _run_module("devx.ci.cancel_superseded_runs", list(args))
+
+
+@ci.command("check-workflow-artifact-deps")
+@click.argument("args", nargs=-1)
+def ci_check_workflow_artifact_deps(args: tuple[str, ...]) -> None:
+    """Check that artifact download jobs depend on upload jobs."""
+    _run_module("devx.ci.check_workflow_artifact_deps", list(args))
+
+
+@ci.command("check-workflow-tofu-init")
+@click.argument("args", nargs=-1)
+def ci_check_workflow_tofu_init(args: tuple[str, ...]) -> None:
+    """Check that workflow jobs using tofu state have a tofu-init step."""
+    _run_module("devx.ci.check_workflow_tofu_init", list(args))
+
+
 @cli.group()
 def tools() -> None:
     """Development tool commands."""
@@ -240,6 +268,27 @@ def tools_pr_rebase(args: tuple[str, ...]) -> None:
     _run_module("devx.tools.pr_rebase", list(args))
 
 
+@tools.command("check-docker-init")
+@click.argument("args", nargs=-1)
+def tools_check_docker_init(args: tuple[str, ...]) -> None:
+    """Check that Docker Compose services with healthchecks have init: true."""
+    _run_module("devx.tools.check_docker_init", list(args))
+
+
+@tools.command("check-ansible-set-fact-to-json")
+@click.argument("args", nargs=-1)
+def tools_check_ansible_set_fact_to_json(args: tuple[str, ...]) -> None:
+    """Check that Ansible set_fact tasks don't misuse to_json."""
+    _run_module("devx.tools.check_ansible_set_fact_to_json", list(args))
+
+
+@tools.command("check-alert-rules")
+@click.argument("args", nargs=-1)
+def tools_check_alert_rules(args: tuple[str, ...]) -> None:
+    """Validate rendered Prometheus alert rules with promtool."""
+    _run_module("devx.tools.check_alert_rules", list(args))
+
+
 @cli.group()
 def molecule() -> None:
     """Molecule testing commands (requires devx[molecule])."""

src/devx/i18n.py

@@ -6,6 +6,10 @@ Supported: en, bg, de, ru, zh, pl.
 Projects can extend translations by setting DEVX_TRANSLATIONS_PATH to a
 JSON file with additional keys. Keys from the project's file are merged
 on top of devx's built-in translations.
+
+Projects that use different env var names (e.g. GRM_LANG instead of
+DEVX_LANG) can call :func:`configure_i18n` at import time to override
+the defaults.
 """
 
 from __future__ import annotations
@@ -14,15 +18,39 @@ import json
 import os
 from pathlib import Path
 
+# Configurable env var names — projects can override via configure_i18n()
+_lang_env_var = "DEVX_LANG"
+_translations_path_env_var = "DEVX_TRANSLATIONS_PATH"
+
 # Load built-in translations
 _BUILTIN_TRANSLATIONS: dict[str, dict[str, str]] = json.loads(
     (Path(__file__).parent / "translations.json").read_text(encoding="utf-8")
 )
 
 
+def configure_i18n(
+    *,
+    lang_env_var: str = "DEVX_LANG",
+    translations_path_env_var: str = "DEVX_TRANSLATIONS_PATH",
+) -> None:
+    """Override the env var names used for language and translations path.
+
+    This allows downstream projects (e.g. grm) to use their own env var
+    names (e.g. ``GRM_LANG``) while still using devx's i18n system.
+
+    Args:
+        lang_env_var: Environment variable name for language selection.
+        translations_path_env_var: Environment variable name for the
+            path to a JSON file with project-specific translations.
+    """
+    global _lang_env_var, _translations_path_env_var
+    _lang_env_var = lang_env_var
+    _translations_path_env_var = translations_path_env_var
+
+
 def _load_project_translations() -> dict[str, dict[str, str]]:
-    """Load project-specific translations from DEVX_TRANSLATIONS_PATH if set."""
-    path = os.getenv("DEVX_TRANSLATIONS_PATH")
+    """Load project-specific translations from the configured env var if set."""
+    path = os.getenv(_translations_path_env_var)
     if not path:
         return {}
     p = Path(path)
@@ -41,10 +69,11 @@ TRANSLATIONS: dict[str, dict[str, str]] = {**_BUILTIN_TRANSLATIONS, **_load_proj
 def _(key: str, **kwargs: object) -> str:
     """Return a translated string for the given key.
 
-    Translation is opt-in via the ``DEVX_LANG`` environment variable.
-    If unset, English is always returned regardless of system locale.
+    Translation is opt-in via the configured language environment variable
+    (default ``DEVX_LANG``). If unset, English is always returned regardless
+    of system locale.
     """
-    lang = os.getenv("DEVX_LANG", "en")
+    lang = os.getenv(_lang_env_var, "en")
     if lang not in ("en", "bg", "de", "ru", "zh", "pl"):
         lang = "en"
     template = TRANSLATIONS.get(key, {}).get(lang, key)

src/devx/molecule/discover_runners.py

@@ -30,6 +30,7 @@ import click
 import requests
 
 from devx.config import GITEA_API_URL, REPO_NAME, REPO_OWNER
+from devx.i18n import _
 from devx.tokens import get_ci_token
 
 DEFAULT_MAX_RUNNERS = 3
@@ -40,7 +41,7 @@ def query_runners(api_url: str, token: str, owner: str, repo: str) -> int:
 
     Returns the total count of active runners.  If the API call fails
     (e.g., no admin access for instance-level runners), falls back to
-    what we can see.
+    what we can see.  Fallbacks are logged to stderr for debugging.
     """
     headers = {"Authorization": f"token {token}"}
     total = 0
@@ -55,8 +56,10 @@ def query_runners(api_url: str, token: str, owner: str, repo: str) -> int:
         if r.status_code == 200:
             data = r.json()
             total += data.get("total_count", 0)
-    except (requests.RequestException, ValueError):
-        pass
+        else:
+            click.echo(_("Warning: repo-level runners query returned HTTP {status}", status=r.status_code), err=True)
+    except (requests.RequestException, ValueError) as e:
+        click.echo(_("Warning: repo-level runners query failed: {error}", error=e), err=True)
 
     # 2. Organization-level runners
     try:
@@ -68,8 +71,10 @@ def query_runners(api_url: str, token: str, owner: str, repo: str) -> int:
         if r.status_code == 200:
             data = r.json()
             total += data.get("total_count", 0)
-    except (requests.RequestException, ValueError):
-        pass
+        else:
+            click.echo(_("Warning: org-level runners query returned HTTP {status}", status=r.status_code), err=True)
+    except (requests.RequestException, ValueError) as e:
+        click.echo(_("Warning: org-level runners query failed: {error}", error=e), err=True)
 
     # 3. Instance-level runners (requires admin scope)
     try:
@@ -81,8 +86,13 @@ def query_runners(api_url: str, token: str, owner: str, repo: str) -> int:
         if r.status_code == 200:
             data = r.json()
             total += data.get("total_count", 0)
-    except (requests.RequestException, ValueError):
-        pass
+        elif r.status_code != 403:  # 403 is expected without admin scope
+            click.echo(
+                _("Warning: instance-level runners query returned HTTP {status}", status=r.status_code),
+                err=True,
+            )
+    except (requests.RequestException, ValueError) as e:
+        click.echo(_("Warning: instance-level runners query failed: {error}", error=e), err=True)
 
     return total
 
@@ -163,8 +173,8 @@ def main(
         with open(gh_output, "a", encoding="utf-8") as f:  # noqa: PTH123
             f.write(f"runner-count={count}\n")
             f.write(f"runner-indices={json.dumps(indices)}\n")
-        click.echo(f"Runner count: {count}")
-        click.echo(f"Runner indices: {indices}")
+        click.echo(_("Runner count: {count}", count=count))
+        click.echo(_("Runner indices: {indices}", indices=indices))
         return
 
     if output_count:
@@ -176,8 +186,8 @@ def main(
         return
 
     # Default: output both as key=value pairs for CI consumption
-    click.echo(f"count={count}")
-    click.echo(f"indices={json.dumps(indices)}")
+    click.echo(_("count={count}", count=count))
+    click.echo(_("indices={indices}", indices=json.dumps(indices)))
 
 
 if __name__ == "__main__":  # pragma: no cover

src/devx/molecule/distribute_molecule.py

@@ -104,21 +104,36 @@ def discover_scenarios(root: Path | None = None) -> list[str]:
     return sorted(scenarios)
 
 
-def discover_multi_role_scenarios(roles_root: Path | None = None) -> list[tuple[str, str]]:
+def discover_multi_role_scenarios(
+    roles_root: Path | None = None,
+    include_roles: list[str] | None = None,
+    exclude_roles: list[str] | None = None,
+) -> list[tuple[str, str]]:
     """Discover (role, scenario) pairs across all roles under *roles_root*.
 
     Scans ``roles_root/*/molecule/*/`` for scenario directories, skipping
     ``common`` and directories starting with ``_``. Returns a sorted list of
     ``(role_name, scenario_name)`` tuples.
+
+    If *include_roles* is given, only roles whose name is in the list are
+    returned. If *exclude_roles* is given, roles whose name is in the list
+    are skipped. Both filters are case-insensitive.
     """
     if roles_root is None:
         roles_root = DEFAULT_ROLES_ROOT
     if not roles_root.is_dir():
         raise click.ClickException(_("Roles directory not found: {path}", path=str(roles_root)))
+    include_set = {r.lower() for r in include_roles} if include_roles else None
+    exclude_set = {r.lower() for r in exclude_roles} if exclude_roles else None
     pairs: list[tuple[str, str]] = []
     for role_dir in sorted(roles_root.iterdir()):
         if not role_dir.is_dir():
             continue
+        role_name = role_dir.name
+        if include_set is not None and role_name.lower() not in include_set:
+            continue
+        if exclude_set is not None and role_name.lower() in exclude_set:
+            continue
         mol_dir = role_dir / "molecule"
         if not mol_dir.is_dir():
             continue
@@ -348,6 +363,24 @@ def _write_github_env(key: str, value: str) -> None:
     help="JSON file with custom platform list (each entry: name, image, command). "
     "Overrides the default platform matrix. Useful for projects with custom test images.",
 )
+@click.option(
+    "--include-roles",
+    "include_roles",
+    type=str,
+    default=None,
+    help="Comma-separated list of role names to include (multi-role mode only). "
+    "Only scenarios from these roles are distributed. Case-insensitive. "
+    "Example: --include-roles docker_base,crowdsec,disk_cleanup,app_hardening",
+)
+@click.option(
+    "--exclude-roles",
+    "exclude_roles",
+    type=str,
+    default=None,
+    help="Comma-separated list of role names to exclude (multi-role mode only). "
+    "Scenarios from these roles are skipped. Case-insensitive. "
+    "Example: --exclude-roles docker_base,crowdsec,disk_cleanup,app_hardening",
+)
 def cli(
     runner_index: int | None,
     max_runners: int,
@@ -358,11 +391,18 @@ def cli(
     molecule_root: Path | None,
     roles_root: Path | None,
     platforms_file: Path | None,
+    include_roles: str | None,
+    exclude_roles: str | None,
 ) -> None:
     platforms = load_platforms(platforms_file)
+    # Parse role filters
+    include_list = [r.strip() for r in include_roles.split(",")] if include_roles else None
+    exclude_list = [r.strip() for r in exclude_roles.split(",")] if exclude_roles else None
     # Multi-role mode: discover (role, scenario) pairs across all roles
     if roles_root is not None:
-        role_scenarios = discover_multi_role_scenarios(roles_root)
+        role_scenarios = discover_multi_role_scenarios(
+            roles_root, include_roles=include_list, exclude_roles=exclude_list
+        )
         if list_all:
             for role, scenario in role_scenarios:
                 click.echo(f"{role}|{scenario}")

src/devx/molecule/molecule_changed.py

@@ -0,0 +1,158 @@
+"""Detect which Ansible roles changed and output their molecule scenarios.
+
+Usage::
+
+    python -m devx.molecule.molecule_changed --print-targets
+    python -m devx.molecule.molecule_changed --base origin/master --print-roles
+
+Outputs the list of make targets (e.g. molecule-docker-base) for roles
+that have changed files vs the base ref. Used by ``make molecule-changed``
+to run only the molecule scenarios affected by the current diff.
+
+Role-to-target mapping is derived from the directory structure:
+  ansible/roles/<role>/  →  molecule-<role>
+
+For roles with multiple scenarios (e.g. app_container has customer-apps,
+nextcloud, postgres-upgrade, simple-app), the base target runs all
+scenarios for that role.
+
+Playbooks that change also trigger molecule for the roles they include.
+Shared infrastructure changes (ansible.cfg, requirements.yml, molecule/)
+trigger all scenarios.
+"""
+
+from __future__ import annotations
+
+import subprocess  # nosec B404 — used to run git, a trusted binary
+from pathlib import Path
+
+import click
+
+REPO_ROOT = Path.cwd()
+
+# Map role names to make targets.
+ROLE_TARGET_MAP: dict[str, str] = {
+    "app_container": "molecule-app-container",
+    "app_hardening": "molecule-app-hardening",
+    "crowdsec": "molecule-crowdsec",
+    "disk_cleanup": "molecule-disk-cleanup",
+    "docker_base": "molecule-docker-base",
+    "observability": "molecule-observability",
+    "restore": "molecule-restore",
+    "sso_config": "molecule-sso-config",
+    "storage": "molecule-storage",
+    "zitadel": "molecule-zitadel",
+}
+
+# Playbooks that map to molecule scenarios (via roles they include).
+PLAYBOOK_ROLE_MAP: dict[str, list[str]] = {
+    "ansible/playbooks/deploy-observability.yml": ["observability", "docker_base", "zitadel", "crowdsec"],
+    "ansible/playbooks/deploy-customer.yml": ["app_container", "docker_base", "app_hardening", "sso_config"],
+    "ansible/playbooks/configure-oidc.yml": ["sso_config", "app_container"],
+    "ansible/playbooks/prepare-vms.yml": ["docker_base", "app_hardening", "storage", "disk_cleanup", "crowdsec"],
+}
+
+# Shared infrastructure that affects all molecule tests.
+SHARED_PATHS = (
+    "ansible/ansible.cfg",
+    "ansible/requirements.yml",
+    "ansible/molecule/",
+)
+
+# Minimum path parts for a role file: ansible/roles/<role> (3 parts).
+# Files inside the role have more parts, but we only need the role name.
+_MIN_ROLE_PATH_PARTS = 3
+
+
+def _run_git(args: list[str]) -> str:  # pragma: no cover
+    """Run a git command and return stdout."""
+    result = subprocess.run(  # nosec
+        ["git", *args],
+        cwd=REPO_ROOT,
+        capture_output=True,
+        text=True,
+        check=False,
+    )
+    return result.stdout
+
+
+def get_changed_files(base: str) -> list[str]:
+    """Get list of changed files vs base ref."""
+    for ref in [base, "master"]:
+        output = _run_git(["diff", "--name-only", f"{ref}...HEAD"])
+        if output.strip():
+            return sorted(output.strip().splitlines())
+    return []
+
+
+def detect_changed_roles(changed_files: list[str]) -> set[str]:
+    """Detect which roles have changed files."""
+    roles: set[str] = set()
+
+    for filepath in changed_files:
+        # Check if file is in a role directory
+        if filepath.startswith("ansible/roles/"):
+            parts = filepath.split("/")
+            if len(parts) >= _MIN_ROLE_PATH_PARTS:
+                roles.add(parts[2])
+
+        # Check if file is a playbook that maps to roles
+        if filepath in PLAYBOOK_ROLE_MAP:
+            roles.update(PLAYBOOK_ROLE_MAP[filepath])
+
+        # Check shared infrastructure — triggers all roles
+        for shared in SHARED_PATHS:
+            if filepath.startswith(shared):
+                return set(ROLE_TARGET_MAP.keys())
+
+    return roles
+
+
+def roles_to_targets(roles: set[str]) -> list[str]:
+    """Convert role names to make targets."""
+    targets = []
+    for role in sorted(roles):
+        target = ROLE_TARGET_MAP.get(role)
+        if target:
+            targets.append(target)
+    return targets
+
+
+@click.command()
+@click.option(
+    "--base",
+    default="origin/master",
+    help="Base ref to compare against (default: origin/master).",
+)
+@click.option(
+    "--print-targets",
+    is_flag=True,
+    help="Print make targets (e.g. molecule-docker-base).",
+)
+@click.option(
+    "--print-roles",
+    is_flag=True,
+    help="Print role names (default if no --print-targets).",
+)
+def main(base: str, print_targets: bool, print_roles: bool) -> None:
+    """Detect which Ansible roles changed and output molecule scenarios."""
+    changed_files = get_changed_files(base)
+    if not changed_files:
+        click.echo("No changed files detected.", err=True)
+        return
+
+    roles = detect_changed_roles(changed_files)
+    if not roles:
+        click.echo("No molecule scenarios affected by changes.", err=True)
+        return
+
+    if print_targets:
+        for target in roles_to_targets(roles):
+            click.echo(target)
+    else:
+        for role in sorted(roles):
+            click.echo(role)
+
+
+if __name__ == "__main__":  # pragma: no cover
+    main()

src/devx/molecule/molecule_ci_guard.py

@@ -246,18 +246,62 @@ def cli(pairs: tuple[str, ...], roles_root: Path | None) -> None:
                             with contextlib.suppress(ProcessLookupError):
                                 os.killpg(os.getpgid(process.pid), signal.SIGKILL)
                             process.wait()
+                        # Clean up containers left behind by the killed test.
+                        click.echo(_("Cleaning up: running molecule destroy for {scenario}", scenario=scenario))
+                        destroy_cmd = ["molecule", "destroy"]
+                        if scenario != "default":
+                            destroy_cmd.extend(["-s", scenario])
+                        with contextlib.suppress(subprocess.SubprocessError, OSError):
+                            subprocess.run(  # nosec B603, B607
+                                destroy_cmd,
+                                cwd=str(cwd),
+                                env=env,
+                                check=False,
+                                capture_output=True,
+                                timeout=120,
+                            )
                         sys.exit(1)
                     time.sleep(1)
             except KeyboardInterrupt:
                 with contextlib.suppress(ProcessLookupError):
                     os.killpg(os.getpgid(process.pid), signal.SIGTERM)
                 process.wait()
+                # Clean up containers left behind by the interrupted test.
+                click.echo(_("Cleaning up: running molecule destroy for {scenario}", scenario=scenario))
+                destroy_cmd = ["molecule", "destroy"]
+                if scenario != "default":
+                    destroy_cmd.extend(["-s", scenario])
+                with contextlib.suppress(subprocess.SubprocessError, OSError):
+                    subprocess.run(  # nosec B603, B607
+                        destroy_cmd,
+                        cwd=str(cwd),
+                        env=env,
+                        check=False,
+                        capture_output=True,
+                        timeout=120,
+                    )
                 sys.exit(1)
 
             rc = process.returncode
 
             if rc != 0:
                 click.echo(_("FAILED: {pair} exited with code {code}", pair=pair, code=rc))
+                # Run molecule destroy to clean up containers left behind by the
+                # failed test. Without this, containers stay running and accumulate
+                # on the runner, consuming disk/memory and degrading CI performance.
+                click.echo(_("Cleaning up: running molecule destroy for {scenario}", scenario=scenario))
+                destroy_cmd = ["molecule", "destroy"]
+                if scenario != "default":
+                    destroy_cmd.extend(["-s", scenario])
+                with contextlib.suppress(subprocess.SubprocessError, OSError):
+                    subprocess.run(  # nosec B603, B607
+                        destroy_cmd,
+                        cwd=str(cwd),
+                        env=env,
+                        check=False,
+                        capture_output=True,
+                        timeout=120,
+                    )
                 sys.exit(rc)
 
             click.echo(_("PASSED: {pair}", pair=pair))

src/devx/tools/ansible_checks/__init__.py

@@ -0,0 +1,34 @@
+"""Ansible check tools — composable validators for Ansible playbooks and roles.
+
+Each check module exports a ``check_*`` function that returns a list of
+violation strings. The shared utilities in :mod:`devx.tools.ansible_checks._shared`
+handle file discovery, YAML parsing, and violation reporting.
+
+The old entry points (``devx.tools.check_ansible_*``, ``devx.tools.check_jinja_expr``)
+remain as thin wrappers for backward compatibility with existing Makefile
+targets and workflow references.
+"""
+
+from devx.tools.ansible_checks._shared import (
+    DEFAULT_ANSIBLE_DIRS,
+    AnsibleFileFinder,
+    AnsibleYAMLParser,
+    ViolationReporter,
+)
+from devx.tools.ansible_checks.jinja_expr import check_jinja_expr
+from devx.tools.ansible_checks.no_log import check_no_log
+from devx.tools.ansible_checks.no_state_absent_on_db import check_no_state_absent_on_db
+from devx.tools.ansible_checks.patterns import check_patterns
+from devx.tools.ansible_checks.set_fact_to_json import check_set_fact_to_json
+
+__all__ = [
+    "DEFAULT_ANSIBLE_DIRS",
+    "AnsibleFileFinder",
+    "AnsibleYAMLParser",
+    "ViolationReporter",
+    "check_jinja_expr",
+    "check_no_log",
+    "check_no_state_absent_on_db",
+    "check_patterns",
+    "check_set_fact_to_json",
+]

src/devx/tools/ansible_checks/_shared.py

@@ -0,0 +1,178 @@
+"""Shared utilities for Ansible check tools.
+
+Provides composable helpers for file discovery, YAML parsing, and
+violation reporting used by the modules in :mod:`devx.tools.ansible_checks`.
+
+Composition over inheritance: each check module picks the helpers it
+needs. Tools that don't parse YAML (e.g. line-based scanners) can skip
+:class:`AnsibleYAMLParser` entirely.
+"""
+
+from __future__ import annotations
+
+import sys
+from collections.abc import Iterator
+from pathlib import Path
+from typing import Final
+
+import click
+import yaml
+
+from devx.i18n import _
+
+#: Default Ansible directories scanned by checks that accept ``--ansible-dir``.
+#: Immutable tuple (not a list) to avoid module-level mutable globals.
+DEFAULT_ANSIBLE_DIRS: Final[tuple[str, ...]] = ("ansible/roles", "ansible/playbooks")
+
+
+class AnsibleFileFinder:
+    """File discovery helpers for Ansible YAML files."""
+
+    @staticmethod
+    def find_task_files(base: Path, skip_molecule: bool = True) -> list[Path]:
+        """Find all YAML files under *base*, recursively.
+
+        If *base* is a single YAML file, returns ``[base]``. If *base* is
+        not a file or directory, returns ``[]``. When *skip_molecule* is
+        True, files with ``molecule`` in their path parts are excluded.
+        """
+        if base.is_file() and base.suffix in (".yml", ".yaml"):
+            return [base]
+        if not base.is_dir():
+            return []
+        files: list[Path] = []
+        for f in sorted(base.rglob("*.yml")) + sorted(base.rglob("*.yaml")):
+            if skip_molecule and "molecule" in f.parts:
+                continue
+            files.append(f)
+        return files
+
+    @staticmethod
+    def find_yaml_files(base: Path, skip_molecule: bool = True) -> list[Path]:
+        """Find YAML files under *base* using ``glob`` (non-recursive rglob).
+
+        Unlike :meth:`find_task_files`, this uses ``base.glob("**/*.yml")``
+        and does not check the suffix when *base* is a single file (any
+        file is accepted). Used by the Jinja expression checker which
+        scans all YAML files including defaults/handlers.
+        """
+        if base.is_file():
+            return [base]
+        files: list[Path] = []
+        for pattern in ("**/*.yml", "**/*.yaml"):
+            files.extend(base.glob(pattern))
+        if skip_molecule:
+            return [f for f in files if "molecule" not in f.parts]
+        return files
+
+    @staticmethod
+    def find_task_and_playbook_files(base: Path, skip_molecule: bool = True) -> list[Path]:
+        """Find task files (``tasks/*.yml``) and playbook files (``playbooks/*.yml``).
+
+        Used by the no_log checker which scans role task files and
+        top-level playbook files. When *skip_molecule* is True, molecule
+        scenario files are excluded.
+        """
+        task_files = list(base.rglob("tasks/*.yml")) + list(base.rglob("tasks/*.yaml"))
+        task_files += list(base.glob("playbooks/*.yml")) + list(base.glob("playbooks/*.yaml"))
+        if skip_molecule:
+            task_files = [f for f in task_files if "molecule" not in f.parts]
+        return sorted(task_files)
+
+
+class AnsibleYAMLParser:
+    """YAML parsing helpers for Ansible files."""
+
+    @staticmethod
+    def parse_file(content: str) -> list[dict]:
+        """Parse multi-document YAML from *content*.
+
+        Returns a list of non-None documents. On ``YAMLError`` or
+        ``OSError``, returns an empty list (the caller skips the file).
+        """
+        try:
+            docs = list(yaml.safe_load_all(content))
+        except (yaml.YAMLError, OSError):
+            return []
+        return [d for d in docs if d]
+
+    @staticmethod
+    def iter_tasks(doc: dict | list) -> Iterator[tuple[dict, int]]:
+        """Yield ``(task_dict, line_number)`` tuples from a YAML document.
+
+        Handles:
+        - Bare task lists (role tasks files): ``[task1, task2, ...]``
+        - Play dicts with ``hosts`` key: iterates ``tasks``,
+          ``pre_tasks``, ``post_tasks``, ``handlers`` sections
+        - Nested ``block`` tasks
+
+        The line number is the 1-based index within the task section
+        (not the file line number — callers use it for display only).
+        """
+        if isinstance(doc, list):
+            for i, item in enumerate(doc):
+                if isinstance(item, dict):
+                    if any(k in item for k in ("tasks", "pre_tasks", "post_tasks", "handlers")):
+                        yield from AnsibleYAMLParser._iter_play_sections(item)
+                    else:
+                        yield item, i + 1
+                        block = item.get("block")
+                        if isinstance(block, list):
+                            for j, bt in enumerate(block):
+                                if isinstance(bt, dict):
+                                    yield bt, i + j + 1
+        elif isinstance(doc, dict):
+            yield from AnsibleYAMLParser._iter_play_sections(doc)
+
+    @staticmethod
+    def _iter_play_sections(doc: dict) -> Iterator[tuple[dict, int]]:
+        """Yield tasks from play sections (tasks, pre_tasks, post_tasks, handlers)."""
+        for section_key in ("tasks", "pre_tasks", "post_tasks", "handlers"):
+            section = doc.get(section_key)
+            if isinstance(section, list):
+                for i, task in enumerate(section):
+                    if isinstance(task, dict):
+                        yield task, i + 1
+                        block = task.get("block")
+                        if isinstance(block, list):
+                            for j, bt in enumerate(block):
+                                if isinstance(bt, dict):
+                                    yield bt, i + j + 1
+
+
+class ViolationReporter:
+    """Standardized violation formatting and reporting."""
+
+    @staticmethod
+    def format_violation(
+        filepath: Path,
+        repo_root: Path,
+        line_num: int | None,
+        message: str,
+    ) -> str:
+        """Format a violation as ``"{relative_path}:{line_num} — message"``.
+
+        Falls back to the full path if *filepath* is not relative to
+        *repo_root*. When *line_num* is None, omits the line number.
+        """
+        try:
+            display_path = filepath.relative_to(repo_root)
+        except ValueError:
+            display_path = filepath
+        if line_num is not None:
+            return f"{display_path}:{line_num} — {message}"
+        return f"{display_path} — {message}"
+
+    @staticmethod
+    def report(violations: list[str], tool_name: str) -> None:
+        """Print violations and exit with the appropriate code.
+
+        Prints ``[{tool_name}] FAIL`` or ``[{tool_name}] OK`` and exits
+        1 if violations are non-empty, 0 otherwise.
+        """
+        if violations:
+            click.echo(_("[{tool}] FAIL: {count} violation(s) found.", tool=tool_name, count=len(violations)))
+            for v in violations:
+                click.echo(f"  - {v}")
+            sys.exit(1)
+        click.echo(_("[{tool}] OK: no violations found.", tool=tool_name))

src/devx/tools/ansible_checks/jinja_expr.py

@@ -0,0 +1,226 @@
+"""Validate Jinja2 expressions in Ansible files by rendering them.
+
+Extracted from :mod:`devx.tools.check_jinja_expr` as part of the
+Ansible check tool consolidation. The old module remains as a thin
+wrapper for backward compatibility.
+"""
+
+from __future__ import annotations
+
+import re
+from pathlib import Path
+
+from jinja2 import Environment
+from jinja2.exceptions import TemplateSyntaxError, UndefinedError
+
+from devx.tools.ansible_checks._shared import AnsibleFileFinder, ViolationReporter
+
+REPO_ROOT = Path.cwd()
+
+MOCK_CONTEXT: dict[str, object] = {
+    "now": lambda fmt=None: (
+        "2026-01-01T00:00:00+00:00"
+        if fmt
+        else type(
+            "Now",
+            (),
+            {
+                "timestamp": lambda self: 1735689600.0,
+                "strftime": lambda self, fmt: "2026-01-01T00:00:00+00:00",
+            },
+        )()
+    ),
+    "ansible_date_time": {
+        "iso8601": "2026-01-01T00:00:00+00:00",
+        "epoch": "1735689600",
+    },
+    "ansible_facts": {
+        "service_mgr": "systemd",
+        "architecture": "x86_64",
+        "distribution_release": "noble",
+        "virtualization_type": "none",
+        "interfaces": ["eth0", "lo"],
+        "hostname": "test-host",
+    },
+    "ansible_host": "10.0.0.1",
+    "env": "staging",
+    "environment": "staging",
+    "customer_id": "test",
+    "zitadel_domain": "zitadel.test",
+    "_env_name": "staging",
+    "_observability_data_root": "/opt",
+    "skip_zitadel_stack": False,
+    "skip_htpasswd": False,
+    "skip_observability_stack": False,
+    "backup_enabled": True,
+    "app_filter": "",
+    "app_domain": "test.example.com",
+    "oidc_client_id": "test-client-id",
+    "oidc_client_secret": "test-secret",  # nosec B105 — mock value for Jinja rendering, not a real secret
+    "s3_backup_bucket": "test-bucket",
+    "s3_endpoint": "https://s3.test",
+    "s3_access_key": "test-key",
+    "s3_secret_key": "test-secret",  # nosec B105 — mock value for Jinja rendering, not a real secret
+}
+
+EXPR_PATTERN = re.compile(r"\{\{(.*?)\}\}", re.DOTALL)
+
+
+def _default_ansible_dirs() -> list[Path]:
+    """Return the default directories to scan for Ansible files."""
+    return [
+        REPO_ROOT / "ansible" / "playbooks",
+        REPO_ROOT / "ansible" / "roles",
+    ]
+
+
+def _find_yaml_files(path: Path) -> list[Path]:
+    """Find Ansible YAML files (tasks, playbooks, handlers) in a path."""
+    return AnsibleFileFinder.find_yaml_files(path, skip_molecule=True)
+
+
+def _extract_expressions(content: str) -> list[str]:
+    """Extract Jinja expressions from file content."""
+    expressions = []
+    for match in EXPR_PATTERN.finditer(content):
+        raw = match.group(1)
+        if "\n" in raw:
+            continue
+        expr = raw.strip()
+        if not expr or expr.startswith("%") or len(expr) <= 1:
+            continue
+        if expr.startswith(".") or "println" in expr:
+            continue
+        if ".State." in expr or ".NetworkSettings." in expr:
+            continue
+        if expr.count("(") != expr.count(")"):
+            continue
+        if expr.count("{") != expr.count("}"):
+            continue
+        if expr.count("[") != expr.count("]"):
+            continue
+        expressions.append(expr)
+    return expressions
+
+
+def _render_expression(expr: str) -> tuple[bool, str]:
+    """Try to render a Jinja expression. Returns (success, error_msg)."""
+    try:
+        env = Environment(autoescape=False, keep_trailing_newline=True)  # nosec B701 — Ansible Jinja, not web-facing  # noqa: S701
+
+        def _strftime(string_format: str, second: float | None = None, utc: bool = False) -> str:
+            if isinstance(string_format, (int, float)) and isinstance(second, str) and "%" in second:
+                raise ValueError(  # noqa: TRY301
+                    "Invalid value for epoch value — strftime filter arguments "
+                    "are reversed. The format string must be the piped value: "
+                    "'%format%' | strftime(epoch), not epoch | strftime('%format%')"
+                )
+            return str(string_format)
+
+        env.filters["strftime"] = _strftime
+        env.filters["b64decode"] = lambda x: x
+        env.filters["b64encode"] = lambda x: x
+        env.filters["regex_replace"] = lambda x, pattern, replacement="": x
+        env.filters["int"] = lambda x, default=0: (
+            int(x) if isinstance(x, (int, float, str)) and str(x).lstrip("-").isdigit() else default
+        )
+        env.filters["bool"] = bool
+        env.filters["basename"] = lambda x: str(x).rsplit("/", 1)[-1]
+        env.filters["dirname"] = lambda x: str(x).rsplit("/", 1)[0] if "/" in str(x) else "."
+        env.filters["combine"] = lambda *args, **kwargs: args[0]
+        env.filters["from_json"] = lambda x: x
+        env.filters["to_json"] = lambda x: x
+        env.filters["ternary"] = lambda x, true_val, false_val=None: true_val if x else false_val
+        env.filters["dict2items"] = lambda x: [
+            {"key": k, "value": v} for k, v in (x.items() if isinstance(x, dict) else [])
+        ]
+        env.filters["map"] = lambda x, attribute=None: x
+        env.filters["default"] = lambda x, default_value="", boolean=False: x if x else default_value
+        env.filters["from_yaml"] = lambda x: x
+        env.filters["difference"] = lambda x, y: x
+        env.filters["join"] = lambda x, sep="": sep.join(str(i) for i in (x if isinstance(x, list) else [x]))
+        env.filters["list"] = lambda x: list(x) if isinstance(x, (list, tuple)) else [x]
+        env.filters["length"] = lambda x: len(x) if hasattr(x, "__len__") else 0
+        env.filters["items"] = lambda x: list(x.items()) if isinstance(x, dict) else []
+        env.filters["first"] = lambda x: x[0] if isinstance(x, (list, str)) and x else x
+        env.filters["last"] = lambda x: x[-1] if isinstance(x, (list, str)) and x else x
+        env.filters["upper"] = lambda x: str(x).upper()
+        env.filters["lower"] = lambda x: str(x).lower()
+        env.filters["replace"] = lambda x, old, new: str(x).replace(old, new)
+        env.filters["split"] = lambda x, sep=None: str(x).split(sep) if sep else str(x).split()
+        env.filters["trim"] = lambda x: str(x).strip()
+        env.filters["sort"] = lambda x: sorted(x) if isinstance(x, list) else x
+        env.filters["unique"] = lambda x: list(set(x)) if isinstance(x, list) else x
+        env.filters["count"] = lambda x: len(x) if hasattr(x, "__len__") else 0
+        env.filters["float"] = lambda x, default=0.0: (
+            float(x) if isinstance(x, (int, float, str)) and str(x).replace(".", "").lstrip("-").isdigit() else default
+        )
+        env.filters["string"] = str
+        env.filters["indent"] = lambda x, width=4: str(x)
+        env.filters["to_nice_json"] = str
+        env.filters["to_nice_yaml"] = str
+        env.filters["from_yaml_all"] = lambda x: x
+        env.filters["groupby"] = lambda x: x
+        env.filters["dictsort"] = lambda x: list(x.items()) if isinstance(x, dict) else []
+        env.filters["max"] = lambda x: max(x) if isinstance(x, list) and x else x
+        env.filters["min"] = lambda x: min(x) if isinstance(x, list) and x else x
+        env.filters["reverse"] = lambda x: list(reversed(x)) if isinstance(x, list) else x
+        env.filters["flatten"] = lambda x: x
+        env.filters["product"] = lambda x: x
+        env.filters["zip"] = lambda x: x
+        env.filters["subelements"] = lambda x: x
+        env.filters["json_query"] = lambda x: x
+        env.filters["type_debug"] = lambda x: type(x).__name__
+        env.globals["lookup"] = lambda *args, **kwargs: ""
+        env.globals["query"] = lambda *args, **kwargs: []
+
+        template = env.from_string("{{ " + expr + " }}")
+        result = template.render(**MOCK_CONTEXT)
+    except TemplateSyntaxError as e:
+        return False, f"Syntax error: {e.message}"
+    except UndefinedError as e:
+        return True, f"Skipped (undefined: {e})"
+    except Exception as e:
+        error_msg = str(e)
+        if "Invalid value for epoch" in error_msg:
+            return False, f"strftime filter argument error: {error_msg}"
+        return True, f"Skipped ({type(e).__name__}: {error_msg})"
+    else:
+        return True, result
+
+
+def _check_file(filepath: Path, repo_root: Path) -> list[str]:
+    """Check all Jinja expressions in a file. Returns list of violations."""
+    violations = []
+    content = filepath.read_text()
+    expressions = _extract_expressions(content)
+    for expr in expressions:
+        success, msg = _render_expression(expr)
+        if not success:
+            display_path = ViolationReporter.format_violation(filepath, repo_root, None, "")
+            display_path = display_path.removesuffix(" — ")
+            violations.append(f"{display_path}: `{{{{ {expr} }}}}` — {msg}")
+    return violations
+
+
+def check_jinja_expr(path: Path | None, ansible_dirs: list[Path] | None = None) -> list[str]:
+    """Validate Jinja2 expressions in Ansible files.
+
+    Args:
+        path: Specific file or directory to check. If None, *ansible_dirs*
+            is used.
+        ansible_dirs: Directories to scan when *path* is None.
+
+    Returns:
+        List of violation messages (empty if all renderable expressions pass).
+    """
+    if path:
+        files = _find_yaml_files(path)
+    else:
+        files: list[Path] = []
+        for d in ansible_dirs or _default_ansible_dirs():
+            files.extend(_find_yaml_files(d))
+    all_violations: list[str] = []
+    for f in files:
+        all_violations.extend(_check_file(f, REPO_ROOT))
+    return all_violations

src/devx/tools/ansible_checks/no_log.py

@@ -0,0 +1,128 @@
+"""Check Ansible tasks for missing no_log on secret-handling tasks.
+
+Extracted from :mod:`devx.tools.check_ansible_no_log` as part of the
+Ansible check tool consolidation. The old module remains as a thin
+wrapper for backward compatibility.
+"""
+
+from __future__ import annotations
+
+import re
+from pathlib import Path
+
+from devx.tools.ansible_checks._shared import AnsibleFileFinder, AnsibleYAMLParser
+
+# Patterns that indicate a task is handling secrets.
+SECRET_PATTERNS = [
+    re.compile(r"\{\{[^}]*_secrets\.", re.IGNORECASE),
+    re.compile(r"\{\{[^}]*password", re.IGNORECASE),
+    re.compile(r"\{\{[^}]*_secret\b", re.IGNORECASE),
+    re.compile(r"\{\{[^}]*api_key", re.IGNORECASE),
+    re.compile(r"\{\{[^}]*(?:vault_token|auth_token|access_token|bot_token)", re.IGNORECASE),
+]
+
+TASK_VALUE_KEYS = {
+    "shell",
+    "command",
+    "ansible.builtin.shell",
+    "ansible.builtin.command",
+    "ansible.builtin.template",
+    "ansible.builtin.copy",
+    "ansible.builtin.debug",
+    "template",
+    "copy",
+    "debug",
+    "cmd",
+    "msg",
+    "content",
+}
+
+NON_VALUE_KEYS = {
+    "name",
+    "when",
+    "loop",
+    "loop_control",
+    "changed_when",
+    "failed_when",
+    "no_log",
+    "register",
+    "tags",
+    "vars",
+    "become",
+    "become_user",
+    "delegate_to",
+    "run_once",
+    "environment",
+    "with_items",
+    "with_dict",
+    "with_list",
+}
+
+
+def _contains_secret(value: object) -> bool:
+    """Recursively check if a value contains secret-like variable references."""
+    if isinstance(value, str):
+        return any(p.search(value) for p in SECRET_PATTERNS)
+    if isinstance(value, dict):
+        return any(_contains_secret(v) for v in value.values())
+    if isinstance(value, list):
+        return any(_contains_secret(item) for item in value)
+    return False
+
+
+def _has_no_log(task: dict) -> bool:
+    """Check if a task has no_log set to a non-False value."""
+    no_log = task.get("no_log", False)
+    return no_log is not False and no_log is not None
+
+
+def _check_task(task: dict, file_path: Path, task_num: int) -> list[str]:
+    """Check a single task for missing no_log on secret values."""
+    violations: list[str] = []
+    if _has_no_log(task):
+        return violations
+    has_secrets = False
+    for key, value in task.items():
+        if key in NON_VALUE_KEYS:
+            continue
+        if _contains_secret(value):
+            has_secrets = True
+            break
+    if has_secrets:
+        task_name = task.get("name", "<unnamed>")
+        violations.append(
+            f"{file_path}:{task_num}: Task '{task_name}' references secrets "
+            f"but has no no_log. Add `no_log: true` or "
+            f'`no_log: "{{{{ not (debug_mode | default(false) | bool) }}}}"` '
+            f"to prevent credential leakage in Ansible output."
+        )
+    return violations
+
+
+def check_no_log(path: Path, ansible_dirs: list[Path] | None = None) -> list[str]:
+    """Check all Ansible task files for missing no_log on secret-handling tasks.
+
+    Args:
+        path: The base directory to scan (or a specific file).
+        ansible_dirs: Unused — kept for API symmetry with other checks.
+            The no_log checker scans *path* directly.
+
+    Returns:
+        List of violation messages (empty if all OK).
+    """
+    all_violations: list[str] = []
+    task_files = AnsibleFileFinder.find_task_and_playbook_files(path)
+    for task_file in task_files:
+        try:
+            content = task_file.read_text(encoding="utf-8")
+        except (OSError, UnicodeDecodeError):
+            continue
+        docs = AnsibleYAMLParser.parse_file(content)
+        for doc in docs:
+            for task, task_num in AnsibleYAMLParser.iter_tasks(doc):
+                all_violations.extend(_check_task(task, task_file, task_num))
+    return all_violations
+
+
+# Backward-compat alias for the old public function name.
+check_directory = check_no_log

src/devx/tools/ansible_checks/no_state_absent_on_db.py

@@ -0,0 +1,100 @@
+"""Check Ansible tasks for ``state: absent`` on database data directories.
+
+Extracted from :mod:`devx.tools.check_ansible_no_state_absent_on_db` as
+part of the Ansible check tool consolidation. The old module remains as
+a thin wrapper for backward compatibility.
+"""
+
+from __future__ import annotations
+
+import re
+from pathlib import Path
+
+from devx.tools.ansible_checks._shared import AnsibleFileFinder, ViolationReporter
+
+REPO_ROOT = Path.cwd()
+
+DB_PATH_PATTERNS = (
+    re.compile(r"postgres/zitadel-db", re.IGNORECASE),
+    re.compile(r"postgres/\w+-db", re.IGNORECASE),
+    re.compile(r"/var/lib/postgresql/data", re.IGNORECASE),
+    re.compile(r"/var/lib/postgresql/data/\w+-db", re.IGNORECASE),
+)
+
+DESTRUCTIVE_PATTERNS = (
+    re.compile(r"state:\s*absent", re.IGNORECASE),
+    re.compile(r"rm\s+-rf.*\bdb\b", re.IGNORECASE),
+)
+
+ALLOWED_CONTEXT_KEYWORDS = (
+    "upgrade-postgres",
+    "PG_VERSION",
+    "pg_version",
+)
+
+ALLOW_MARKER = "lint:allow-state-absent"
+
+
+def _find_task_files(base: Path) -> list[Path]:
+    """Find all YAML task files under a base directory, skipping molecule."""
+    return AnsibleFileFinder.find_task_files(base, skip_molecule=True)
+
+
+def _check_file(filepath: Path, repo_root: Path) -> list[str]:
+    """Check a YAML file for state: absent on DB data directory paths."""
+    try:
+        content = filepath.read_text(encoding="utf-8")
+    except (OSError, UnicodeDecodeError):
+        return []
+    if not any(p.search(content) for p in DB_PATH_PATTERNS):
+        return []
+    display_path = ViolationReporter.format_violation(filepath, repo_root, None, "")
+    display_path = display_path.removesuffix(" — ")
+    violations: list[str] = []
+    lines = content.splitlines()
+    for i, line in enumerate(lines):
+        for db_pattern in DB_PATH_PATTERNS:
+            if not db_pattern.search(line):
+                continue
+            context_start = max(0, i - 5)
+            context_end = min(len(lines), i + 6)
+            context = "\n".join(lines[context_start:context_end])
+            if any(kw in context for kw in ALLOWED_CONTEXT_KEYWORDS):
+                continue
+            if ALLOW_MARKER in context:
+                continue
+            for dp in DESTRUCTIVE_PATTERNS:
+                if dp.search(context):
+                    violations.append(
+                        f"{display_path}:{i + 1} — destructive operation "
+                        f"({dp.pattern!r}) near DB data directory path "
+                        f"({db_pattern.pattern!r}). "
+                        f"Database directories must never be wiped automatically (ADR-0028). "
+                        f"If this is legitimate (e.g. PG upgrade), add "
+                        f"#{ALLOW_MARKER} to the task."
+                    )
+                    break
+    return violations
+
+
+def check_no_state_absent_on_db(path: Path | None, ansible_dirs: list[Path] | None = None) -> list[str]:
+    """Check that no Ansible task uses state: absent on a DB data directory.
+
+    Args:
+        path: Specific file or directory to check. If None, *ansible_dirs*
+            is used.
+        ansible_dirs: Directories to scan when *path* is None.
+
+    Returns:
+        List of violation messages (empty if clean).
+    """
+    if path:
+        files = _find_task_files(path)
+    else:
+        files: list[Path] = []
+        for d in ansible_dirs or []:
+            files.extend(_find_task_files(d))
+    all_violations: list[str] = []
+    for f in files:
+        all_violations.extend(_check_file(f, REPO_ROOT))
+    return all_violations

src/devx/tools/ansible_checks/patterns.py

@@ -0,0 +1,226 @@
+"""Check Ansible tasks for dangerous patterns that mask failures.
+
+Extracted from :mod:`devx.tools.check_ansible_patterns` as part of the
+Ansible check tool consolidation. The old module remains as a thin
+wrapper for backward compatibility.
+"""
+
+from __future__ import annotations
+
+import re
+from pathlib import Path
+
+from devx.tools.ansible_checks._shared import AnsibleFileFinder, AnsibleYAMLParser
+
+REPO_ROOT = Path.cwd()
+
+# Comment marker to explicitly allow a pattern on a specific task
+ALLOW_MARKER = "lint:allow-failure-masking"
+
+# Patterns that mask failures when used in shell/command tasks
+OR_TRUE_PATTERN = re.compile(r"\|\|\s*true\b", re.IGNORECASE)
+REDIRECT_DEVNULL_PATTERN = re.compile(r"2>/dev/null")
+
+# Module keys that accept shell/command strings
+SHELL_MODULE_KEYS = frozenset(
+    {
+        "shell",
+        "command",
+        "ansible.builtin.shell",
+        "ansible.builtin.command",
+        "cmd",
+        "ansible.builtin.raw",
+        "raw",
+    }
+)
+
+# Task keys whose values might contain shell commands
+COMMAND_VALUE_KEYS = frozenset(
+    {
+        "shell",
+        "command",
+        "ansible.builtin.shell",
+        "ansible.builtin.command",
+        "cmd",
+        "raw",
+        "ansible.builtin.raw",
+    }
+)
+
+LEGITIMATE_COMMAND_PREFIXES = (
+    "docker rm",
+    "docker stop",
+    "docker rmi",
+    "docker network rm",
+    "docker volume rm",
+    "pkill",
+    "kill",
+    "journalctl --vacuum",
+    "apt-get clean",
+    "apt-get autoremove",
+    "docker image prune",
+    "docker container prune",
+    "docker volume prune",
+    "docker builder prune",
+    "find / -name",
+    "chmod",
+    "rm -f",
+    "docker network connect",
+    "curl.*api/v2/admin/tsdb/snapshot",
+)
+
+LEGITIMATE_TASK_NAME_KEYWORDS = (
+    "remove",
+    "cleanup",
+    "clean up",
+    "prune",
+    "purge",
+    "disconnect",
+    "stop",
+    "kill",
+    "strip suid",
+    "suid",
+    "vacuum",
+    "ensure.*absent",
+    "may not exist",
+    "if exists",
+    "optional",
+    "best effort",
+    "no-op",
+    "noop",
+    "idempotent",
+    "sync",
+)
+
+CRITICAL_TASK_KEYWORDS = (
+    "password",
+    "secret",
+    "provision",
+    "oidc",
+)
+
+LEGITIMATE_FAILED_WHEN_KEYWORDS = (
+    "stop",
+    "start",
+    "check",
+    "wait",
+    "migrate",
+    "restart",
+    "rebuild",
+    "restore",
+    "remove",
+    "cleanup",
+    "sync",
+    "download",
+    "extract",
+    "verify",
+)
+
+
+def _is_legitimate_or_true(command_str: str, task_name: str) -> bool:
+    """Check if a || true in a command is in a legitimate context."""
+    name_lower = task_name.lower()
+    if any(re.search(kw, name_lower) for kw in LEGITIMATE_TASK_NAME_KEYWORDS):
+        return True
+    cmd_lower = command_str.lower()
+    return any(re.search(prefix, cmd_lower) for prefix in LEGITIMATE_COMMAND_PREFIXES)
+
+
+def _is_legitimate_devnull(command_str: str, task_name: str) -> bool:
+    """Check if a 2>/dev/null in a command is in a legitimate context."""
+    return _is_legitimate_or_true(command_str, task_name)
+
+
+def _check_task(task: dict, filepath: Path, task_num: int, repo_root: Path) -> list[str]:
+    """Check a single task for dangerous failure-masking patterns."""
+    violations: list[str] = []
+    try:
+        display_path = filepath.relative_to(repo_root)
+    except ValueError:
+        display_path = filepath
+    task_name = task.get("name", "<unnamed>")
+    if ALLOW_MARKER in task_name:
+        return violations
+    for key in COMMAND_VALUE_KEYS:
+        value = task.get(key)
+        if value is None:
+            continue
+        value_str = str(value)
+        if OR_TRUE_PATTERN.search(value_str) and not _is_legitimate_or_true(value_str, task_name):
+            violations.append(
+                f"{display_path}:{task_num} — task '{task_name}' uses "
+                f"'|| true' in {key} which may mask real failures. "
+                f"If this is a cleanup/idempotency operation, rename the "
+                f"task to include 'remove'/'cleanup'/'prune' or add "
+                f"#{ALLOW_MARKER} to the task."
+            )
+    failed_when = task.get("failed_when")
+    if failed_when is False:
+        name_lower = task_name.lower()
+        is_legitimate = any(kw in name_lower for kw in LEGITIMATE_FAILED_WHEN_KEYWORDS)
+        if not is_legitimate:
+            for kw in CRITICAL_TASK_KEYWORDS:
+                if kw in name_lower:
+                    violations.append(
+                        f"{display_path}:{task_num} — critical task '{task_name}' "
+                        f"has failed_when: false, which masks failures on "
+                        f"a {kw}-related operation. Remove failed_when: false "
+                        f"or add #{ALLOW_MARKER} if masking is intentional."
+                    )
+                    break
+    return violations
+
+
+def _check_file(filepath: Path, repo_root: Path) -> list[str]:
+    """Check a YAML file for dangerous failure-masking patterns."""
+    try:
+        content = filepath.read_text(encoding="utf-8")
+    except (OSError, UnicodeDecodeError):
+        return []
+    if not (
+        OR_TRUE_PATTERN.search(content) or "failed_when: false" in content or REDIRECT_DEVNULL_PATTERN.search(content)
+    ):
+        return []
+    has_allow_marker = ALLOW_MARKER in content
+    docs = AnsibleYAMLParser.parse_file(content)
+    violations: list[str] = []
+    for doc in docs:
+        for task, task_num in AnsibleYAMLParser.iter_tasks(doc):
+            violations.extend(_check_task(task, filepath, task_num, repo_root))
+    if has_allow_marker:
+        violations = []
+    return violations
+
+
+def _check_tasks(doc: dict, filepath: Path, errors: list[str], repo_root: Path) -> None:
+    """Check top-level tasks and nested task sections in a playbook doc."""
+    for task, task_num in AnsibleYAMLParser._iter_play_sections(doc):
+        errors.extend(_check_task(task, filepath, task_num, repo_root))
+
+
+def _find_task_files(base: Path) -> list[Path]:
+    """Find all YAML task files under a base directory, skipping molecule."""
+    return AnsibleFileFinder.find_task_files(base, skip_molecule=True)
+
+
+def check_patterns(path: Path | None, ansible_dirs: list[Path] | None = None) -> list[str]:
+    """Check Ansible tasks for dangerous failure-masking patterns.
+
+    Args:
+        path: Specific file or directory to check. If None, *ansible_dirs*
+            is used.
+        ansible_dirs: Directories to scan when *path* is None.
+
+    Returns:
+        List of violation messages (empty if clean).
+    """
+    if path:
+        files = _find_task_files(path)
+    else:
+        files: list[Path] = []
+        for d in ansible_dirs or []:
+            files.extend(_find_task_files(d))
+    all_violations: list[str] = []
+    for f in files:
+        all_violations.extend(_check_file(f, REPO_ROOT))
+    return all_violations

src/devx/tools/ansible_checks/set_fact_to_json.py

@@ -0,0 +1,134 @@
+"""Check that Ansible ``set_fact`` tasks don't misuse ``| to_json``.
+
+Extracted from :mod:`devx.tools.check_ansible_set_fact_to_json` as part
+of the Ansible check tool consolidation. The old module remains as a
+thin wrapper for backward compatibility.
+"""
+
+from __future__ import annotations
+
+from pathlib import Path
+
+import yaml
+
+from devx.tools.ansible_checks._shared import AnsibleFileFinder, ViolationReporter
+
+REPO_ROOT = Path.cwd()
+
+TO_JSON_FILTERS = ("| to_json", "| to_nice_json", "|to_json", "|to_nice_json")
+
+
+def _find_task_files(base: Path) -> list[Path]:
+    """Find all YAML task files under a base directory."""
+    return AnsibleFileFinder.find_task_files(base, skip_molecule=False)
+
+
+def _check_file(filepath: Path, repo_root: Path) -> list[str]:
+    """Check a single YAML file for set_fact + to_json misuse."""
+    errors: list[str] = []
+    try:
+        content = filepath.read_text(encoding="utf-8")
+    except (OSError, UnicodeDecodeError):
+        return errors
+    try:
+        docs = list(yaml.safe_load_all(content))
+    except yaml.YAMLError as exc:
+        return [f"{filepath}: cannot parse YAML: {exc}"]
+    for doc in docs:
+        if isinstance(doc, list):
+            for item in doc:
+                if isinstance(item, dict):
+                    if any(k in item for k in ("tasks", "pre_tasks", "post_tasks", "handlers", "roles")):
+                        _check_tasks(item, filepath, errors, repo_root)
+                    else:
+                        _check_task(item, filepath, errors, repo_root)
+                        block = item.get("block")
+                        if isinstance(block, list):
+                            _check_task_list(block, filepath, errors, repo_root)
+        elif isinstance(doc, dict):
+            _check_tasks(doc, filepath, errors, repo_root)
+    return errors
+
+
+def _check_tasks(doc: dict, filepath: Path, errors: list[str], repo_root: Path) -> None:
+    """Check top-level tasks and nested task sections in a playbook doc."""
+    tasks = doc.get("tasks")
+    if isinstance(tasks, list):
+        _check_task_list(tasks, filepath, errors, repo_root)
+    for role_key in ("pre_tasks", "post_tasks", "handlers"):
+        section = doc.get(role_key)
+        if isinstance(section, list):
+            _check_task_list(section, filepath, errors, repo_root)
+    roles = doc.get("roles")
+    if isinstance(roles, list):
+        for role_entry in roles:
+            if isinstance(role_entry, dict):
+                role_tasks = role_entry.get("tasks")
+                if isinstance(role_tasks, list):
+                    _check_task_list(role_tasks, filepath, errors, repo_root)
+
+
+def _check_task_list(tasks: list, filepath: Path, errors: list[str], repo_root: Path) -> None:
+    """Check a list of task definitions for set_fact + to_json."""
+    for task in tasks:
+        if not isinstance(task, dict):
+            continue
+        _check_task(task, filepath, errors, repo_root)
+        block = task.get("block")
+        if isinstance(block, list):
+            _check_task_list(block, filepath, errors, repo_root)
+
+
+def _check_task(task: dict, filepath: Path, errors: list[str], repo_root: Path) -> None:
+    """Check a single task for set_fact + to_json misuse."""
+    has_set_fact = False
+    for key in task:
+        if key in {"set_fact", "ansible.builtin.set_fact"}:
+            has_set_fact = True
+            break
+    if not has_set_fact:
+        return
+    set_fact_body = task.get("set_fact") or task.get("ansible.builtin.set_fact")
+    if not isinstance(set_fact_body, dict):
+        return
+    task_name = task.get("name", "(unnamed)")
+    for fact_name, fact_value in set_fact_body.items():
+        if fact_name in ("cacheable",):
+            continue
+        value_str = str(fact_value)
+        for filter_pattern in TO_JSON_FILTERS:
+            if filter_pattern in value_str:
+                display_path = ViolationReporter.format_violation(filepath, repo_root, None, "")
+                display_path = display_path.removesuffix(" — ")
+                errors.append(
+                    f"{display_path}: task '{task_name}' "
+                    f"sets fact '{fact_name}' with '{filter_pattern.strip()}' "
+                    f"— this converts native Python types to JSON strings. "
+                    f"Remove the filter to preserve the native type, or use "
+                    f"'| from_json' in the consuming task if the string "
+                    f"representation is intentional."
+                )
+                break
+
+
+def check_set_fact_to_json(path: Path | None, ansible_dirs: list[Path] | None = None) -> list[str]:
+    """Check that set_fact tasks don't misuse to_json.
+
+    Args:
+        path: Specific file or directory to check. If None, *ansible_dirs*
+            is used.
+        ansible_dirs: Directories to scan when *path* is None.
+
+    Returns:
+        List of error messages (empty if all OK).
+    """
+    if path:
+        files = _find_task_files(path)
+    else:
+        files: list[Path] = []
+        for d in ansible_dirs or []:
+            files.extend(_find_task_files(d))
+    all_errors: list[str] = []
+    for f in files:
+        all_errors.extend(_check_file(f, REPO_ROOT))
+    return all_errors

src/devx/tools/check_alert_rules.py

@@ -0,0 +1,86 @@
+"""Validate Prometheus alert rules with promtool check rules.
+
+Renders an alert-rules Jinja2 template with test values and validates
+the output with ``promtool check rules``. Exits 0 if valid, non-zero
+otherwise. Skips (exits 0) if promtool is not on PATH.
+
+Usage::
+
+    python -m devx.tools.check_alert_rules \\
+        --template-path ansible/roles/observability/templates \\
+        --template-name alert-rules.yml.j2
+
+    # With extra template variables:
+    python -m devx.tools.check_alert_rules \\
+        --template-path ansible/roles/observability/templates \\
+        --template-name alert-rules.yml.j2 \\
+        --var grafana_base_url=https://grafana.test.example.com
+"""
+
+from __future__ import annotations
+
+import shutil
+import subprocess  # nosec B404 — used to run promtool, a trusted binary
+import sys
+import tempfile
+from pathlib import Path
+
+import click
+
+from devx.utils.jinja import make_env, render_template
+
+
+@click.command()
+@click.option(
+    "--template-path",
+    type=click.Path(exists=True, path_type=Path),
+    required=True,
+    help="Path to the directory containing the Jinja2 template.",
+)
+@click.option(
+    "--template-name",
+    default="alert-rules.yml.j2",
+    help="Name of the Jinja2 template file to render.",
+)
+@click.option(
+    "--var",
+    "template_vars",
+    multiple=True,
+    help="Template variables in key=value format (can be repeated). "
+    "Example: --var grafana_base_url=https://grafana.example.com",
+)
+def main(template_path: Path, template_name: str, template_vars: tuple[str, ...]) -> None:
+    """Validate rendered alert rules with promtool."""
+    if not shutil.which("promtool"):
+        click.echo("promtool not found in PATH — skipping alert rules validation")
+        return
+
+    # Parse template variables
+    kwargs: dict[str, str] = {}
+    for v in template_vars:
+        if "=" in v:
+            key, value = v.split("=", 1)
+            kwargs[key] = value
+
+    env = make_env(str(template_path))
+    output = render_template(env, template_name, **kwargs)
+
+    with tempfile.NamedTemporaryFile(mode="w", suffix=".yml", delete=False) as f:
+        f.write(output)
+        tmp_path = f.name
+
+    click.echo("[check-alert-rules] Validating rendered rules with promtool...")
+    result = subprocess.run(  # nosec
+        ["promtool", "check", "rules", tmp_path],
+        capture_output=True,
+        text=True,
+        check=False,
+    )
+    click.echo(result.stdout, nl=False)
+    if result.returncode != 0:
+        click.echo(result.stderr, nl=False, err=True)
+    sys.exit(result.returncode)
+
+
+if __name__ == "__main__":  # pragma: no cover
+    main()

src/devx/tools/check_ansible_no_log.py

@@ -0,0 +1,71 @@
+"""Check Ansible tasks for missing no_log on secret-handling tasks.
+
+Thin wrapper around :mod:`devx.tools.ansible_checks.no_log` for
+backward compatibility. The check logic lives in the subpackage; this
+module preserves the CLI entry point and re-exports the internal
+helpers so existing tests and imports continue to work.
+
+Usage::
+
+    python -m devx.tools.check_ansible_no_log
+    python -m devx.tools.check_ansible_no_log --path ansible/roles/my_role
+    python -m devx.tools.check_ansible_no_log --ansible-dir ansible/roles
+
+Exit code 0 if all secret-handling tasks have no_log, 1 otherwise.
+"""
+
+from __future__ import annotations
+
+import sys
+from pathlib import Path
+
+import click
+
+from devx.tools.ansible_checks.no_log import (
+    NON_VALUE_KEYS,  # noqa: F401
+    SECRET_PATTERNS,  # noqa: F401 — re-exported for backward compat
+    TASK_VALUE_KEYS,  # noqa: F401
+    _check_task,  # noqa: F401
+    _contains_secret,  # noqa: F401
+    _has_no_log,  # noqa: F401
+    check_directory,  # noqa: F401
+    check_no_log,  # noqa: F401
+)
+
+REPO_ROOT = Path.cwd()
+DEFAULT_ANSIBLE_DIR = REPO_ROOT / "ansible"
+
+
+@click.command()
+@click.option(
+    "--path",
+    type=click.Path(exists=True, path_type=Path),
+    help="Check a specific file or directory (default: ansible/).",
+)
+@click.option(
+    "--ansible-dir",
+    type=click.Path(exists=True, path_type=Path),
+    default=None,
+    help="Override the default ansible directory (default: ansible/).",
+)
+def main(path: Path | None, ansible_dir: Path | None) -> None:
+    """Check that Ansible tasks handling secrets have no_log set."""
+    target = path or ansible_dir or DEFAULT_ANSIBLE_DIR
+    if not target.is_dir():
+        click.echo(f"Error: {target} is not a directory", err=True)
+        sys.exit(2)
+
+    violations = check_no_log(target)
+
+    if violations:
+        click.echo(f"Found {len(violations)} task(s) handling secrets without no_log:\n")
+        for v in violations:
+            click.echo(f"  {v}")
+        click.echo(f"\nTotal: {len(violations)} violation(s).")
+        sys.exit(1)
+
+    click.echo(f"[check-ansible-no-log] All secret-handling tasks have no_log. ({target})")
+
+
+if __name__ == "__main__":  # pragma: no cover
+    main()

src/devx/tools/check_ansible_no_state_absent_on_db.py

@@ -0,0 +1,72 @@
+"""Check Ansible tasks for ``state: absent`` on database data directories.
+
+Thin wrapper around
+:mod:`devx.tools.ansible_checks.no_state_absent_on_db` for backward
+compatibility. The check logic lives in the subpackage; this module
+preserves the CLI entry point and re-exports the internal helpers so
+existing tests and imports continue to work.
+
+Usage::
+
+    python -m devx.tools.check_ansible_no_state_absent_on_db
+    python -m devx.tools.check_ansible_no_state_absent_on_db --path ansible/roles/zitadel/tasks/main.yml
+
+Exit code 0 if no violations found, 1 otherwise.
+"""
+
+from __future__ import annotations
+
+import sys
+from pathlib import Path
+
+import click
+
+from devx.tools.ansible_checks.no_state_absent_on_db import (
+    ALLOW_MARKER,  # noqa: F401 — re-exported for backward compat
+    ALLOWED_CONTEXT_KEYWORDS,  # noqa: F401
+    DB_PATH_PATTERNS,  # noqa: F401
+    DESTRUCTIVE_PATTERNS,  # noqa: F401
+    REPO_ROOT,
+    _check_file,  # noqa: F401
+    _find_task_files,  # noqa: F401
+    check_no_state_absent_on_db,  # noqa: F401
+)
+
+DEFAULT_ANSIBLE_DIRS: list[Path] = [
+    REPO_ROOT / "ansible" / "playbooks",
+    REPO_ROOT / "ansible" / "roles",
+]
+
+
+@click.command()
+@click.option(
+    "--path",
+    type=click.Path(exists=True, path_type=Path),
+    help="Check a specific file or directory (default: ansible/playbooks + ansible/roles).",
+)
+@click.option(
+    "--ansible-dir",
+    "ansible_dirs",
+    type=click.Path(exists=True, path_type=Path),
+    multiple=True,
+    default=None,
+    help="Override the default ansible directories (can be repeated). Defaults to ansible/playbooks and ansible/roles.",
+)
+def main(path: Path | None, ansible_dirs: tuple[Path, ...]) -> None:
+    """Check that no Ansible task uses state: absent on a DB data directory."""
+    dirs = list(ansible_dirs) if ansible_dirs else DEFAULT_ANSIBLE_DIRS
+    all_violations = check_no_state_absent_on_db(path) if path else check_no_state_absent_on_db(None, dirs)
+
+    if all_violations:
+        click.echo("[check-ansible-no-state-absent-on-db] FAIL: destructive operations on DB paths:")
+        for v in all_violations:
+            click.echo(f"  - {v}")
+        click.echo(f"\nTotal: {len(all_violations)} violation(s).")
+        click.echo("Database data directories must never be wiped automatically (ADR-0028).")
+        sys.exit(1)
+    else:
+        click.echo("[check-ansible-no-state-absent-on-db] OK: no destructive operations on DB paths.")
+
+
+if __name__ == "__main__":  # pragma: no cover
+    main()

src/devx/tools/check_ansible_patterns.py

@@ -0,0 +1,79 @@
+"""Check Ansible tasks for dangerous patterns that mask failures.
+
+Thin wrapper around :mod:`devx.tools.ansible_checks.patterns` for
+backward compatibility. The check logic lives in the subpackage; this
+module preserves the CLI entry point and re-exports the internal
+helpers so existing tests and imports continue to work.
+
+Usage::
+
+    python -m devx.tools.check_ansible_patterns
+    python -m devx.tools.check_ansible_patterns --path ansible/roles/app_container/tasks/main.yml
+
+Exit code 0 if no violations found, 1 otherwise.
+"""
+
+from __future__ import annotations
+
+import sys
+from pathlib import Path
+
+import click
+
+from devx.tools.ansible_checks.patterns import (
+    ALLOW_MARKER,  # noqa: F401 — re-exported for backward compat
+    COMMAND_VALUE_KEYS,  # noqa: F401
+    CRITICAL_TASK_KEYWORDS,  # noqa: F401
+    LEGITIMATE_COMMAND_PREFIXES,  # noqa: F401
+    LEGITIMATE_FAILED_WHEN_KEYWORDS,  # noqa: F401
+    LEGITIMATE_TASK_NAME_KEYWORDS,  # noqa: F401
+    OR_TRUE_PATTERN,  # noqa: F401
+    REDIRECT_DEVNULL_PATTERN,  # noqa: F401
+    REPO_ROOT,
+    SHELL_MODULE_KEYS,  # noqa: F401
+    _check_file,  # noqa: F401
+    _check_task,  # noqa: F401
+    _check_tasks,  # noqa: F401
+    _find_task_files,  # noqa: F401
+    _is_legitimate_devnull,  # noqa: F401
+    _is_legitimate_or_true,  # noqa: F401
+    check_patterns,  # noqa: F401
+)
+
+DEFAULT_ANSIBLE_DIRS: list[Path] = [
+    REPO_ROOT / "ansible" / "playbooks",
+    REPO_ROOT / "ansible" / "roles",
+]
+
+
+@click.command()
+@click.option(
+    "--path",
+    type=click.Path(exists=True, path_type=Path),
+    help="Check a specific file or directory (default: ansible/playbooks + ansible/roles).",
+)
+@click.option(
+    "--ansible-dir",
+    "ansible_dirs",
+    type=click.Path(exists=True, path_type=Path),
+    multiple=True,
+    default=None,
+    help="Override the default ansible directories (can be repeated). Defaults to ansible/playbooks and ansible/roles.",
+)
+def main(path: Path | None, ansible_dirs: tuple[Path, ...]) -> None:
+    """Check Ansible tasks for dangerous failure-masking patterns."""
+    dirs = list(ansible_dirs) if ansible_dirs else DEFAULT_ANSIBLE_DIRS
+    all_violations = check_patterns(path) if path else check_patterns(None, dirs)
+
+    if all_violations:
+        click.echo("[check-ansible-patterns] FAIL: dangerous failure-masking patterns found:")
+        for v in all_violations:
+            click.echo(f"  - {v}")
+        click.echo(f"\nTotal: {len(all_violations)} violation(s).")
+        sys.exit(1)
+    else:
+        click.echo("[check-ansible-patterns] OK: no dangerous failure-masking patterns.")
+
+
+if __name__ == "__main__":  # pragma: no cover
+    main()

src/devx/tools/check_ansible_set_fact_to_json.py

@@ -0,0 +1,69 @@
+"""Check that Ansible ``set_fact`` tasks don't misuse ``| to_json``.
+
+Thin wrapper around :mod:`devx.tools.ansible_checks.set_fact_to_json`
+for backward compatibility. The check logic lives in the subpackage;
+this module preserves the CLI entry point and re-exports the internal
+helpers so existing tests and imports continue to work.
+
+Usage::
+
+    python -m devx.tools.check_ansible_set_fact_to_json
+    python -m devx.tools.check_ansible_set_fact_to_json --path ansible/playbooks/deploy.yml
+
+Exit code 0 if no misuses found, 1 otherwise.
+"""
+
+from __future__ import annotations
+
+import sys
+from pathlib import Path
+
+import click
+
+from devx.tools.ansible_checks.set_fact_to_json import (
+    REPO_ROOT,
+    TO_JSON_FILTERS,  # noqa: F401 — re-exported for backward compat
+    _check_file,  # noqa: F401
+    _check_task,  # noqa: F401
+    _check_task_list,  # noqa: F401
+    _check_tasks,  # noqa: F401
+    _find_task_files,  # noqa: F401
+    check_set_fact_to_json,  # noqa: F401
+)
+
+DEFAULT_ANSIBLE_DIRS: list[Path] = [
+    REPO_ROOT / "ansible" / "playbooks",
+    REPO_ROOT / "ansible" / "roles",
+]
+
+
+@click.command()
+@click.option(
+    "--path",
+    type=click.Path(exists=True, path_type=Path),
+    help="Check a specific file or directory (default: ansible/playbooks + ansible/roles).",
+)
+@click.option(
+    "--ansible-dir",
+    "ansible_dirs",
+    type=click.Path(exists=True, path_type=Path),
+    multiple=True,
+    default=None,
+    help="Override the default ansible directories (can be repeated). Defaults to ansible/playbooks and ansible/roles.",
+)
+def main(path: Path | None, ansible_dirs: tuple[Path, ...]) -> None:
+    """Check that set_fact tasks don't misuse to_json."""
+    dirs = list(ansible_dirs) if ansible_dirs else DEFAULT_ANSIBLE_DIRS
+    all_errors = check_set_fact_to_json(path) if path else check_set_fact_to_json(None, dirs)
+
+    if all_errors:
+        click.echo("[check-ansible-set-fact-to-json] FAIL: set_fact with to_json found:")
+        for err in all_errors:
+            click.echo(f"  - {err}")
+        sys.exit(1)
+    else:
+        click.echo("[check-ansible-set-fact-to-json] OK: no set_fact tasks misuse to_json.")
+
+
+if __name__ == "__main__":  # pragma: no cover
+    main()

src/devx/tools/check_docker_init.py

@@ -0,0 +1,166 @@
+"""Check that Docker Compose services with healthchecks have ``init: true``.
+
+This prevents zombie process accumulation on production VMs. Without
+``init: true``, Docker uses the container's PID 1 process to reap
+child processes. Many images (especially those using CMD-SHELL
+healthchecks with ``wget``) don't call ``wait()`` on children, causing
+zombies to accumulate.
+
+The check scans all Jinja2 docker-compose templates for services that
+have a ``healthcheck:`` key but no ``init: true`` key. Since the
+templates use Jinja2 syntax (not pure YAML), the check uses text-based
+parsing to identify service blocks and their properties.
+
+Usage::
+
+    python -m devx.tools.check_docker_init
+    python -m devx.tools.check_docker_init --path ansible/roles/observability/templates/docker-compose.yml.j2
+
+Exit code 0 if all services with healthchecks have init: true, 1 otherwise.
+"""
+
+from __future__ import annotations
+
+import re
+import sys
+from pathlib import Path
+
+import click
+
+REPO_ROOT = Path.cwd()
+DEFAULT_TEMPLATES_DIR = REPO_ROOT / "ansible" / "roles"
+
+
+def _find_compose_templates(base: Path) -> list[Path]:
+    """Find all Jinja2 docker-compose templates under a base directory."""
+    if base.is_file():
+        return [base]
+    if not base.is_dir():
+        return []
+    results: list[Path] = []
+    for pattern in ("*docker-compose*", "*compose*"):
+        results.extend(base.rglob(f"{pattern}.yml.j2"))
+        results.extend(base.rglob(f"{pattern}.yaml.j2"))
+    # Also check exporters-compose
+    results.extend(base.rglob("exporters-compose*.j2"))
+    # Deduplicate while preserving order
+    seen: set[Path] = set()
+    unique: list[Path] = []
+    for p in sorted(results):
+        if p not in seen:
+            seen.add(p)
+            unique.append(p)
+    return unique
+
+
+def _parse_services(content: str) -> dict[str, list[str]]:
+    """Parse service blocks from a docker-compose Jinja2 template.
+
+    Returns a mapping of service_name → list of lines in that service block.
+    """
+    lines = content.splitlines()
+    in_services = False
+    services: dict[str, list[str]] = {}
+    current_svc: str | None = None
+    current_lines: list[str] = []
+
+    for line in lines:
+        if line.startswith("services:"):
+            in_services = True
+            continue
+        if not in_services:
+            continue
+        # Top-level keys (networks:, volumes:) end the services section
+        if re.match(r"^(networks|volumes):\s*$", line):
+            if current_svc is not None:
+                services[current_svc] = current_lines
+            current_svc = None
+            in_services = False
+            continue
+        # Service definition: exactly 2-space indent, ends with :
+        # Service names can contain Jinja2 variables like {{ app_name }}
+        # or {{ app_name }}-db. Match: 2-space indent + non-whitespace
+        # chars (including {{ }}, -, _, .) + optional spaces inside {{ }} + :
+        m = re.match(r"^  (\{\{.*?\}\}[a-zA-Z0-9_-]*|[a-zA-Z0-9_().-]+):\s*$", line)
+        if m:
+            if current_svc is not None:
+                services[current_svc] = current_lines
+            current_svc = m.group(1)
+            current_lines = []
+        elif current_svc is not None:
+            current_lines.append(line)
+
+    if current_svc is not None:
+        services[current_svc] = current_lines
+
+    return services
+
+
+def _check_template(filepath: Path, repo_root: Path) -> list[str]:
+    """Check a single docker-compose template for missing init: true.
+
+    Returns a list of error messages (empty if all OK).
+    """
+    errors: list[str] = []
+    content = filepath.read_text(encoding="utf-8")
+
+    if "services:" not in content:
+        return errors
+
+    services = _parse_services(content)
+
+    for svc_name, svc_lines in services.items():
+        svc_text = "\n".join(svc_lines)
+        has_init = "init: true" in svc_text
+        has_healthcheck = "healthcheck:" in svc_text
+        # Skip services that are conditionally included (Jinja2 if blocks)
+        # but still check them — the healthcheck is inside the conditional
+        if has_healthcheck and not has_init:
+            try:
+                display_path = filepath.relative_to(repo_root)
+            except ValueError:
+                display_path = filepath
+            errors.append(
+                f"{display_path}: service '{svc_name}' has a healthcheck "
+                f"but no 'init: true'. Without init: true, CMD-SHELL "
+                f"healthchecks (wget, pgrep) spawn children that become "
+                f"zombies when PID 1 doesn't reap them. Add 'init: true' "
+                f"to enable Docker's built-in tini as PID 1."
+            )
+
+    return errors
+
+
+@click.command()
+@click.option(
+    "--path",
+    type=click.Path(exists=True, path_type=Path),
+    help="Check a specific file or directory (default: ansible/roles/).",
+)
+@click.option(
+    "--templates-dir",
+    type=click.Path(exists=True, path_type=Path),
+    default=None,
+    help="Override the default templates directory (default: ansible/roles/).",
+)
+def main(path: Path | None, templates_dir: Path | None) -> None:
+    """Check that Docker Compose services with healthchecks have init: true."""
+    tdir = templates_dir or DEFAULT_TEMPLATES_DIR
+    files = _find_compose_templates(path) if path else _find_compose_templates(tdir)
+
+    all_errors: list[str] = []
+    for f in files:
+        errors = _check_template(f, tdir)
+        all_errors.extend(errors)
+
+    if all_errors:
+        click.echo("[check-docker-init] FAIL: services with healthchecks missing init: true:")
+        for err in all_errors:
+            click.echo(f"  - {err}")
+        sys.exit(1)
+    else:
+        click.echo("[check-docker-init] OK: all services with healthchecks have init: true.")
+
+
+if __name__ == "__main__":  # pragma: no cover
+    main()

src/devx/tools/check_jinja_expr.py

@@ -0,0 +1,65 @@
+"""Validate Jinja2 expressions in Ansible files by rendering them.
+
+Thin wrapper around :mod:`devx.tools.ansible_checks.jinja_expr` for
+backward compatibility. The check logic lives in the subpackage; this
+module preserves the CLI entry point and re-exports the internal
+helpers so existing tests and imports continue to work.
+
+Usage::
+
+    python -m devx.tools.check_jinja_expr
+    python -m devx.tools.check_jinja_expr --path ansible/playbooks/deploy-observability.yml
+
+Exit code 0 if all renderable expressions pass, 1 if any fail.
+"""
+
+from __future__ import annotations
+
+import sys
+from pathlib import Path
+
+import click
+
+from devx.tools.ansible_checks.jinja_expr import (
+    EXPR_PATTERN,  # noqa: F401 — re-exported for backward compat
+    MOCK_CONTEXT,  # noqa: F401
+    _check_file,  # noqa: F401
+    _default_ansible_dirs,  # noqa: F401
+    _extract_expressions,  # noqa: F401
+    _find_yaml_files,  # noqa: F401
+    _render_expression,  # noqa: F401
+    check_jinja_expr,  # noqa: F401
+)
+
+
+@click.command()
+@click.option(
+    "--path",
+    type=click.Path(exists=True, path_type=Path),
+    help="Check a specific file or directory (default: ansible/playbooks + ansible/roles).",
+)
+@click.option(
+    "--ansible-dir",
+    "ansible_dirs",
+    type=click.Path(exists=True, path_type=Path),
+    multiple=True,
+    default=None,
+    help="Override the default ansible directories (can be repeated). Defaults to ansible/playbooks and ansible/roles.",
+)
+def main(path: Path | None, ansible_dirs: tuple[Path, ...]) -> None:
+    """Validate Jinja2 expressions in Ansible files."""
+    dirs = list(ansible_dirs) if ansible_dirs else _default_ansible_dirs()
+    all_violations = check_jinja_expr(path) if path else check_jinja_expr(None, dirs)
+
+    if all_violations:
+        click.echo("[check-jinja-expr] FAIL: invalid Jinja expressions found:")
+        for v in all_violations:
+            click.echo(f"  - {v}")
+        click.echo("\nFix: test expressions with `ansible localhost -m debug -a 'msg={{ <expr> }}'`")
+        sys.exit(1)
+    else:
+        click.echo("[check-jinja-expr] OK: all Jinja expressions render correctly.")
+
+
+if __name__ == "__main__":  # pragma: no cover
+    main()

src/devx/tools/install_tools.py

@@ -22,18 +22,37 @@ Usage::
 
 from __future__ import annotations
 
+import logging
 import os
 import platform
 import shutil
 import tarfile
 import tempfile
+import time
+import urllib.error
 import urllib.request
 from pathlib import Path
 
 import click
+from tenacity import (
+    Retrying,
+    before_sleep_log,
+    retry_if_exception_type,
+    stop_after_attempt,
+    wait_exponential,
+)
 
 TARGET_DIR = Path.home() / ".local" / "bin"
 
+logger = logging.getLogger(__name__)
+
+# Retry configuration for transient network failures during download.
+# GitHub releases occasionally drops connections ("Remote end closed
+# connection without response"). Retrying with backoff before falling
+# through to the next fallback URL makes the build resilient to
+# momentary network blips.
+MAX_DOWNLOAD_RETRIES = 3
+
 ACTIONLINT_VERSION = "1.7.12"
 
 GIT_CLIFF_VERSION = "2.13.1"
@@ -64,12 +83,53 @@ def _ensure_target_dir() -> Path:
     return TARGET_DIR
 
 
-def _download(url: str, dest: Path) -> None:
-    """Download a file from ``url`` to ``dest`` with a 60s timeout."""
+def _download(url: str, dest: Path, *, _sleep=None) -> None:
+    """Download a file from ``url`` to ``dest`` with retry and 60s timeout.
+
+    Retries up to ``MAX_DOWNLOAD_RETRIES`` times on transient network
+    errors (``URLError``, ``OSError`` from connection resets) using
+    exponential backoff. This handles momentary GitHub releases
+    connection drops that were causing CI image builds to fail.
+
+    The ``_sleep`` kwarg is for tests to avoid real sleeping; production
+    code should leave it as ``None`` (uses ``time.sleep``).
+    """
+    retrying = Retrying(
+        stop=stop_after_attempt(MAX_DOWNLOAD_RETRIES),
+        wait=wait_exponential(multiplier=2, min=2, max=10),
+        retry=retry_if_exception_type((urllib.error.URLError, OSError, ConnectionError)),
+        before_sleep=before_sleep_log(logger, logging.WARNING),
+        sleep=_sleep if _sleep is not None else time.sleep,
+        reraise=True,
+    )
+    retrying(_do_download, url, dest)
+
+
+def _do_download(url: str, dest: Path) -> None:
+    """Single download attempt — called by :func:`_download` retry wrapper."""
     with urllib.request.urlopen(url, timeout=60) as resp, open(dest, "wb") as f:  # nosec B310
         shutil.copyfileobj(resp, f)
 
 
+def _download_with_fallback(urls: list[str], binary_name: str) -> Path:
+    """Try downloading a binary from a list of URLs, falling back on failure.
+
+    Returns the path to the installed binary. Raises if all URLs fail.
+    """
+    target_dir = _ensure_target_dir()
+    dest = target_dir / binary_name
+    errors: list[str] = []
+    for url in urls:
+        try:
+            _download(url, dest)
+            dest.chmod(0o755)
+            return dest
+        except Exception as exc:  # noqa: BLE001
+            errors.append(f"{url}: {exc}")
+            click.echo(f"  {binary_name}: retrying — {exc}")
+    raise click.ClickException(f"Failed to download {binary_name} from all URLs: {'; '.join(errors)}")
+
+
 def _download_and_extract_tarball(url: str, binary_name: str) -> Path:
     """Download a tarball, extract the binary, and install it to TARGET_DIR.
 
@@ -164,8 +224,13 @@ def install_tea() -> bool:
         click.echo("tea: already installed")
         return True
     arch = _arch()
-    url = f"https://dl.gitea.com/tea/{TEA_VERSION}/tea-{TEA_VERSION}-linux-{arch}"
-    dest = _download_binary(url, "tea")
+    # dl.gitea.com is the primary CDN, but it can return 403 from some networks.
+    # Fall back to the gitea.com release downloads URL.
+    urls = [
+        f"https://dl.gitea.com/tea/{TEA_VERSION}/tea-{TEA_VERSION}-linux-{arch}",
+        f"https://gitea.com/gitea/tea/releases/download/v{TEA_VERSION}/tea-{TEA_VERSION}-linux-{arch}",
+    ]
+    dest = _download_with_fallback(urls, "tea")
     click.echo(f"tea: installed to {dest}")
     return True
 

src/devx/tools/setup.py

@@ -15,6 +15,7 @@ from pathlib import Path
 
 import click
 from dotenv import load_dotenv  # pyright: ignore[reportMissingImports,reportUnknownVariableType]
+from tenacity import retry, stop_after_attempt, wait_exponential
 
 from devx.tokens import get_developer_token
 
@@ -56,13 +57,22 @@ def _install_pre_commit_hooks(bin_dir: str) -> None:
 
 
 def _install_ansible_collections(bin_dir: str) -> None:
-    """Install required Ansible Galaxy collections if requirements exist."""
+    """Install required Ansible Galaxy collections if requirements exist.
+
+    Retries up to 3 times with exponential backoff to handle transient
+    network timeouts when contacting galaxy.ansible.com.
+    """
     galaxy = shutil.which("ansible-galaxy") or str(Path(bin_dir) / "ansible-galaxy")
     requirements = Path("ansible/requirements.yml")
     if not requirements.exists():
         click.echo("  ansible/requirements.yml not found — skipping collections.")
         return
-    _run([galaxy, "collection", "install", "-r", str(requirements)])
+
+    @retry(stop=stop_after_attempt(3), wait=wait_exponential(multiplier=2, min=2, max=10), reraise=True)
+    def _do_install() -> None:
+        _run([galaxy, "collection", "install", "-r", str(requirements)])
+
+    _do_install()
 
 
 def _configure_tea_login() -> None:

src/devx/tools/setup_image.py

@@ -64,9 +64,11 @@ def _install_in_image(
     link.symlink_to(opt_venv)
 
     # Build pip install command
+    # --no-deps: the CI image already has all dependencies pre-installed.
+    # We only need to install the project itself in editable mode.
     spec = f".[{extras}]" if extras else "."
     pip_bin = str(Path(venv_link) / "bin" / "pip")
-    cmd = [pip_bin, "install", "--no-cache-dir", "-e", spec]
+    cmd = [pip_bin, "install", "--no-cache-dir", "--no-deps", "-e", spec]
 
     env = os.environ.copy()
     try:

src/devx/utils/api.py

@@ -1,14 +1,26 @@
 #!/usr/bin/env python3
-"""Utilities for handling API response values.
+"""Utilities for handling API response values and base HTTP API client.
 
-Many APIs return boolean values as strings (``"true"``, ``"false"``)
-rather than native JSON booleans.  The Mattermost ``/api/v4/config/client``
-endpoint is a notable example.  These helpers handle both string and
-boolean responses safely.
+This module provides two categories of utilities:
+
+1. **Response helpers** — :func:`is_truthy` and :func:`is_falsy` handle
+   APIs that return boolean values as strings (``"true"``, ``"false"``)
+   rather than native JSON booleans.
+
+2. **Base API client** — :class:`APIClient` provides a reusable base
+   class for HTTP API clients with consistent timeout handling, header
+   propagation, and automatic raising on 4xx/5xx responses.
 
 Usage::
 
-    from devx.utils.api import is_truthy, is_falsy
+    from devx.utils.api import APIClient, is_truthy
+
+    class MyClient(APIClient):
+        def __init__(self):
+            super().__init__(
+                base_url="https://api.example.com",
+                headers={"Authorization": "Bearer token"},
+            )
 
     if not is_truthy(config.get("EnableOpenServer")):
         raise ValueError("EnableOpenServer not enabled")
@@ -16,6 +28,82 @@ Usage::
 
 from __future__ import annotations
 
+import requests
+
+
+class APIClient:
+    """Base class for HTTP API clients.
+
+    Subclasses set ``base_url``, ``headers``, and optionally ``auth`` in
+    their constructor, then use :meth:`_request` or the convenience
+    methods (:meth:`get`, :meth:`post`, etc.) to make requests.
+
+    All requests raise :class:`requests.HTTPError` on 4xx/5xx responses
+    via :meth:`requests.Response.raise_for_status`.
+    """
+
+    def __init__(
+        self,
+        base_url: str,
+        headers: dict,
+        timeout: int = 30,
+        verify: bool = True,
+        auth: tuple[str, str] | None = None,
+    ) -> None:
+        """Initialize the API client.
+
+        Args:
+            base_url: Base URL for the API (trailing slash stripped).
+            headers: Default headers sent with every request.
+            timeout: Request timeout in seconds.
+            verify: Whether to verify TLS certificates.
+            auth: Optional ``(username, password)`` tuple for basic auth.
+        """
+        self.base_url = base_url.rstrip("/")
+        self.headers = headers
+        self.timeout = timeout
+        self.verify = verify
+        self.auth = auth
+
+    def _request(self, method: str, path: str, **kwargs) -> requests.Response:
+        """Execute an HTTP request against the API.
+
+        The URL is constructed as ``{base_url}{path}``. Default timeout,
+        verify, auth, and headers are applied but can be overridden via
+        ``kwargs``.
+
+        Raises:
+            requests.HTTPError: On 4xx/5xx response status codes.
+        """
+        url = f"{self.base_url}{path}"
+        kwargs.setdefault("timeout", self.timeout)
+        kwargs.setdefault("verify", self.verify)
+        if self.auth is not None:
+            kwargs.setdefault("auth", self.auth)
+        resp = requests.request(method, url, headers=self.headers, **kwargs)  # noqa: S113
+        resp.raise_for_status()
+        return resp
+
+    def get(self, path: str, **kwargs) -> requests.Response:
+        """Send a GET request."""
+        return self._request("GET", path, **kwargs)
+
+    def post(self, path: str, **kwargs) -> requests.Response:
+        """Send a POST request."""
+        return self._request("POST", path, **kwargs)
+
+    def put(self, path: str, **kwargs) -> requests.Response:
+        """Send a PUT request."""
+        return self._request("PUT", path, **kwargs)
+
+    def delete(self, path: str, **kwargs) -> requests.Response:
+        """Send a DELETE request."""
+        return self._request("DELETE", path, **kwargs)
+
+    def patch(self, path: str, **kwargs) -> requests.Response:
+        """Send a PATCH request."""
+        return self._request("PATCH", path, **kwargs)
+
 
 def is_truthy(value: str | bool | None) -> bool:
     """Check if an API config value is truthy.

src/devx/utils/jinja.py

@@ -0,0 +1,133 @@
+"""Shared Jinja2 environment helpers for unit tests and template rendering.
+
+Creating a Jinja2 Environment is expensive (filesystem scanning, template
+compilation).  These helpers create cached environments with
+``auto_reload=False`` to skip stat() calls on every ``get_template``,
+which is the single biggest speedup for template-heavy test suites.
+
+The filters mimic Ansible builtins not available in plain Jinja2,
+making it possible to render Ansible templates outside of Ansible
+(e.g. in unit tests or config generation scripts).
+
+Usage::
+
+    from devx.utils.jinja import make_env, render_template
+
+    env = make_env("/path/to/templates")
+    output = render_template(env, "alert-rules.yml.j2", grafana_base_url="https://grafana.example.com")
+"""
+
+from __future__ import annotations
+
+import functools
+import json
+import re
+
+import jinja2
+
+# ---------------------------------------------------------------------------
+# Filters (mimic Ansible builtins not available in plain Jinja2)
+# ---------------------------------------------------------------------------
+
+
+def to_json(value) -> str:
+    return json.dumps(value)
+
+
+def to_bool(value) -> bool:
+    """Mimic Ansible's |bool filter for plain Jinja2 tests."""
+    if isinstance(value, bool):
+        return value
+    if isinstance(value, str):
+        return value.lower() not in ("", "false", "0", "no", "off", "null", "none")
+    return bool(value)
+
+
+def regex_replace(value, pattern: str, replacement: str) -> str:
+    """Mimic Ansible's |regex_replace filter."""
+    return re.sub(pattern, replacement, str(value))
+
+
+def regex_escape(value) -> str:
+    """Mimic Ansible's |regex_escape filter."""
+    return re.escape(str(value))
+
+
+def regex_search(value, pattern: str) -> str | None:
+    """Mimic Ansible's |regex_search filter.
+
+    Returns the first match (group 0) or None if no match.
+    Ansible returns the full match string or None.
+    """
+    m = re.search(pattern, str(value))
+    return m.group(0) if m else None
+
+
+# ---------------------------------------------------------------------------
+# Environment factory
+# ---------------------------------------------------------------------------
+
+_FILTERS = {
+    "to_json": to_json,
+    "bool": to_bool,
+    "regex_replace": regex_replace,
+    "regex_escape": regex_escape,
+    "regex_search": regex_search,
+}
+
+
+@functools.cache
+def make_env(loader_path: str) -> jinja2.Environment:
+    """Create a cached Jinja2 Environment with standard filters.
+
+    ``auto_reload=False`` skips stat() on every get_template call —
+    templates don't change during a test run so this is safe and
+    cuts ~40% off render time.
+    """
+    env = jinja2.Environment(  # nosec B701 — renders YAML/config templates, not HTML
+        loader=jinja2.FileSystemLoader(loader_path),
+        undefined=jinja2.StrictUndefined,
+        auto_reload=False,
+        cache_size=400,
+    )
+    env.filters.update(_FILTERS)
+    return env
+
+
+@functools.cache
+def make_value_env() -> jinja2.Environment:
+    """Cached environment for rendering individual manifest string values."""
+    env = jinja2.Environment(  # nosec B701 — renders config values, not HTML
+        undefined=jinja2.ChainableUndefined,
+        auto_reload=False,
+    )
+    env.filters.update(_FILTERS)
+    return env
+
+
+# ---------------------------------------------------------------------------
+# Render helpers
+# ---------------------------------------------------------------------------
+
+
+def render_template(env: jinja2.Environment, template_name: str, **kwargs) -> str:
+    """Render a named template from a FileSystemLoader-backed env."""
+    return env.get_template(template_name).render(**kwargs)
+
+
+def render_value(value, ctx: dict):
+    """Render a single string value as a Jinja2 template if it contains expressions."""
+    if not isinstance(value, str):
+        return value
+    if "{{" not in value and "{%" not in value:
+        return value
+    return make_value_env().from_string(value).render(**ctx)
+
+
+def render_manifest_values(obj, ctx: dict):
+    """Recursively render all Jinja2 expressions in manifest string values."""
+    if isinstance(obj, dict):
+        return {k: render_manifest_values(v, ctx) for k, v in obj.items()}
+    if isinstance(obj, list):
+        return [render_manifest_values(v, ctx) for v in obj]
+    return render_value(obj, ctx)

src/devx/utils/ui.py

@@ -0,0 +1,79 @@
+"""User-facing output utilities combining console and log output.
+
+Console messages are colorised via ``click.style`` for visual feedback.
+The persistent log file always receives plain text (no ANSI codes).
+
+This is a generalisation of grm's ``ui.say()`` function, extracted so
+that any CLI tool can use the same pattern.  The logger name and
+console-level env var are configurable.
+
+Usage::
+
+    from devx.utils.ui import say
+
+    say("Starting deployment...")
+    say("Error occurred", level=logging.ERROR, err=True, color="red")
+"""
+
+from __future__ import annotations
+
+import logging
+import os
+
+import click
+
+# Configurable env var for console verbosity — projects can override
+# via :func:`configure_ui`.
+_LOG_LEVEL_ENV_VAR = "DEVX_LOG_LEVEL"
+_LOGGER_NAME = "devx"
+
+
+def configure_ui(*, log_level_env_var: str = "DEVX_LOG_LEVEL", logger_name: str = "devx") -> None:
+    """Override the env var name and logger name used by :func:`say`.
+
+    This allows downstream projects (e.g. grm) to use their own env var
+    names (e.g. ``GRM_LOG_LEVEL``) and logger names while still using
+    devx's ui module.
+
+    Args:
+        log_level_env_var: Environment variable name for console log level.
+        logger_name: Logger name for persistent log file output.
+    """
+    global _LOG_LEVEL_ENV_VAR, _LOGGER_NAME
+    _LOG_LEVEL_ENV_VAR = log_level_env_var
+    _LOGGER_NAME = logger_name
+
+
+def _console_level() -> int:
+    """Return the minimum level for console output from the configured env var."""
+    value = os.getenv(_LOG_LEVEL_ENV_VAR, "INFO")
+    try:
+        return getattr(logging, value.upper())
+    except AttributeError:
+        return logging.INFO
+
+
+def say(
+    msg: str,
+    level: int = logging.INFO,
+    err: bool = False,
+    color: str | None = None,
+) -> None:
+    """Output a message to the user and also log it for auditing.
+
+    Console output goes via ``click.echo`` (handles encoding, CliRunner,
+    Windows colorama) only when *level* is at least the configured
+    console log level (default ``DEVX_LOG_LEVEL``, falls back to INFO).
+    The same message is always sent to the configured logger so it
+    appears in the persistent log file regardless of console verbosity.
+
+    Args:
+        msg: Message to display.
+        level: Logging level (e.g. ``logging.INFO``, ``logging.ERROR``).
+        err: If True, output to stderr instead of stdout.
+        color: Optional ``click.style`` fg color (e.g. ``"green"``, ``"red"``).
+    """
+    if level >= _console_level():
+        styled = click.style(msg, fg=color) if color else msg
+        click.echo(styled, err=err)
+    logging.getLogger(_LOGGER_NAME).log(level, msg)

tests/unit/test_ansible_checks_shared.py

@@ -0,0 +1,231 @@
+"""Unit tests for devx.tools.ansible_checks._shared."""
+
+from pathlib import Path
+
+import pytest
+
+from devx.tools.ansible_checks._shared import (
+    DEFAULT_ANSIBLE_DIRS,
+    AnsibleFileFinder,
+    AnsibleYAMLParser,
+    ViolationReporter,
+)
+
+
+class TestAnsibleFileFinder:
+    def test_find_task_files_single_yaml(self, tmp_path: Path) -> None:
+        f = tmp_path / "test.yml"
+        f.write_text("tasks: []")
+        assert AnsibleFileFinder.find_task_files(f) == [f]
+
+    def test_find_task_files_single_non_yaml(self, tmp_path: Path) -> None:
+        f = tmp_path / "test.txt"
+        f.write_text("hello")
+        assert AnsibleFileFinder.find_task_files(f) == []
+
+    def test_find_task_files_dir(self, tmp_path: Path) -> None:
+        (tmp_path / "a.yml").write_text("tasks: []")
+        (tmp_path / "b.yaml").write_text("tasks: []")
+        (tmp_path / "c.txt").write_text("hello")
+        result = AnsibleFileFinder.find_task_files(tmp_path)
+        assert len(result) == 2
+        assert all(f.suffix in (".yml", ".yaml") for f in result)
+
+    def test_find_task_files_skip_molecule(self, tmp_path: Path) -> None:
+        (tmp_path / "a.yml").write_text("tasks: []")
+        mol = tmp_path / "molecule" / "default"
+        mol.mkdir(parents=True)
+        (mol / "main.yml").write_text("tasks: []")
+        result = AnsibleFileFinder.find_task_files(tmp_path, skip_molecule=True)
+        assert len(result) == 1
+        assert "molecule" not in result[0].parts
+
+    def test_find_task_files_include_molecule(self, tmp_path: Path) -> None:
+        (tmp_path / "a.yml").write_text("tasks: []")
+        mol = tmp_path / "molecule" / "default"
+        mol.mkdir(parents=True)
+        (mol / "main.yml").write_text("tasks: []")
+        result = AnsibleFileFinder.find_task_files(tmp_path, skip_molecule=False)
+        assert len(result) == 2
+
+    def test_find_task_files_nonexistent(self, tmp_path: Path) -> None:
+        assert AnsibleFileFinder.find_task_files(tmp_path / "nonexistent") == []
+
+    def test_find_yaml_files_single_file(self, tmp_path: Path) -> None:
+        f = tmp_path / "test.txt"
+        f.write_text("hello")
+        # find_yaml_files accepts any single file (no suffix check)
+        assert AnsibleFileFinder.find_yaml_files(f) == [f]
+
+    def test_find_yaml_files_dir(self, tmp_path: Path) -> None:
+        (tmp_path / "a.yml").write_text("tasks: []")
+        (tmp_path / "sub").mkdir()
+        (tmp_path / "sub" / "b.yaml").write_text("tasks: []")
+        result = AnsibleFileFinder.find_yaml_files(tmp_path)
+        assert len(result) == 2
+
+    def test_find_yaml_files_skip_molecule(self, tmp_path: Path) -> None:
+        (tmp_path / "a.yml").write_text("tasks: []")
+        mol = tmp_path / "molecule" / "default"
+        mol.mkdir(parents=True)
+        (mol / "main.yml").write_text("tasks: []")
+        result = AnsibleFileFinder.find_yaml_files(tmp_path, skip_molecule=True)
+        assert len(result) == 1
+
+    def test_find_yaml_files_include_molecule(self, tmp_path: Path) -> None:
+        (tmp_path / "a.yml").write_text("tasks: []")
+        mol = tmp_path / "molecule" / "default"
+        mol.mkdir(parents=True)
+        (mol / "main.yml").write_text("tasks: []")
+        result = AnsibleFileFinder.find_yaml_files(tmp_path, skip_molecule=False)
+        assert len(result) == 2
+
+    def test_find_task_and_playbook_files(self, tmp_path: Path) -> None:
+        role = tmp_path / "roles" / "myrole"
+        (role / "tasks").mkdir(parents=True)
+        (role / "tasks" / "main.yml").write_text("tasks: []")
+        pb = tmp_path / "playbooks"
+        pb.mkdir()
+        (pb / "deploy.yml").write_text("tasks: []")
+        (tmp_path / "random.yml").write_text("tasks: []")
+        result = AnsibleFileFinder.find_task_and_playbook_files(tmp_path)
+        # Should find tasks/main.yml and playbooks/deploy.yml, not random.yml
+        names = [f.name for f in result]
+        assert "main.yml" in names
+        assert "deploy.yml" in names
+        assert "random.yml" not in names
+
+    def test_find_task_and_playbook_files_skip_molecule(self, tmp_path: Path) -> None:
+        role = tmp_path / "roles" / "myrole"
+        (role / "tasks").mkdir(parents=True)
+        (role / "tasks" / "main.yml").write_text("tasks: []")
+        mol = role / "molecule" / "default" / "tasks"
+        mol.mkdir(parents=True)
+        (mol / "main.yml").write_text("tasks: []")
+        result = AnsibleFileFinder.find_task_and_playbook_files(tmp_path, skip_molecule=True)
+        assert len(result) == 1
+        assert "molecule" not in result[0].parts
+
+
+class TestAnsibleYAMLParser:
+    def test_parse_file_valid(self) -> None:
+        content = "---\n- name: test\n  shell: echo hi\n"
+        docs = AnsibleYAMLParser.parse_file(content)
+        assert len(docs) == 1
+        assert isinstance(docs[0], list)
+
+    def test_parse_file_multi_doc(self) -> None:
+        content = "---\n- a\n---\n- b\n"
+        docs = AnsibleYAMLParser.parse_file(content)
+        assert len(docs) == 2
+
+    def test_parse_file_empty_docs_filtered(self) -> None:
+        content = "---\n- a\n---\n\n"
+        docs = AnsibleYAMLParser.parse_file(content)
+        assert len(docs) == 1
+
+    def test_parse_file_yaml_error(self) -> None:
+        content = "{{ invalid: ["
+        docs = AnsibleYAMLParser.parse_file(content)
+        assert docs == []
+
+    def test_iter_tasks_bare_list(self) -> None:
+        doc = [{"name": "task1", "shell": "echo hi"}, {"name": "task2", "shell": "echo bye"}]
+        tasks = list(AnsibleYAMLParser.iter_tasks(doc))
+        assert len(tasks) == 2
+        assert tasks[0][0]["name"] == "task1"
+        assert tasks[0][1] == 1
+        assert tasks[1][1] == 2
+
+    def test_iter_tasks_play_dict(self) -> None:
+        doc = {"hosts": "all", "tasks": [{"name": "task1", "shell": "echo hi"}]}
+        tasks = list(AnsibleYAMLParser.iter_tasks(doc))
+        assert len(tasks) == 1
+        assert tasks[0][0]["name"] == "task1"
+
+    def test_iter_tasks_play_with_pre_post_handlers(self) -> None:
+        doc = {
+            "hosts": "all",
+            "pre_tasks": [{"name": "pre", "shell": "echo pre"}],
+            "tasks": [{"name": "main", "shell": "echo main"}],
+            "post_tasks": [{"name": "post", "shell": "echo post"}],
+            "handlers": [{"name": "handler", "shell": "echo handler"}],
+        }
+        tasks = list(AnsibleYAMLParser.iter_tasks(doc))
+        assert len(tasks) == 4
+        names = [t[0]["name"] for t in tasks]
+        # Order: tasks, pre_tasks, post_tasks, handlers (as defined in _iter_play_sections)
+        assert names == ["main", "pre", "post", "handler"]
+
+    def test_iter_tasks_block(self) -> None:
+        doc = [{"name": "outer", "block": [{"name": "inner", "shell": "echo hi"}]}]
+        tasks = list(AnsibleYAMLParser.iter_tasks(doc))
+        # outer is not a play (no task sections) → yielded as bare task
+        # inner is yielded from block
+        assert len(tasks) == 2
+        assert tasks[0][0]["name"] == "outer"
+        assert tasks[1][0]["name"] == "inner"
+
+    def test_iter_tasks_block_in_play_section(self) -> None:
+        """Block tasks within a play's tasks section are yielded."""
+        doc = {
+            "hosts": "all",
+            "tasks": [
+                {"name": "outer", "block": [{"name": "inner", "shell": "echo hi"}]},
+            ],
+        }
+        tasks = list(AnsibleYAMLParser.iter_tasks(doc))
+        assert len(tasks) == 2
+        assert tasks[0][0]["name"] == "outer"
+        assert tasks[1][0]["name"] == "inner"
+
+    def test_iter_tasks_play_list(self) -> None:
+        doc = [{"hosts": "all", "tasks": [{"name": "task1", "shell": "echo hi"}]}]
+        tasks = list(AnsibleYAMLParser.iter_tasks(doc))
+        assert len(tasks) == 1
+        assert tasks[0][0]["name"] == "task1"
+
+    def test_iter_tasks_non_dict_items_skipped(self) -> None:
+        doc = ["string", 42, {"name": "task1", "shell": "echo hi"}]
+        tasks = list(AnsibleYAMLParser.iter_tasks(doc))
+        assert len(tasks) == 1
+
+
+class TestViolationReporter:
+    def test_format_violation_with_line(self, tmp_path: Path) -> None:
+        result = ViolationReporter.format_violation(tmp_path / "foo.yml", tmp_path, 42, "bad")
+        assert result == "foo.yml:42 — bad"
+
+    def test_format_violation_without_line(self, tmp_path: Path) -> None:
+        result = ViolationReporter.format_violation(tmp_path / "foo.yml", tmp_path, None, "bad")
+        assert result == "foo.yml — bad"
+
+    def test_format_violation_not_relative(self, tmp_path: Path) -> None:
+        other = Path("/other/path")
+        result = ViolationReporter.format_violation(other, tmp_path, 1, "bad")
+        assert str(other) in result
+        assert "bad" in result
+
+    def test_report_no_violations(self, capsys: pytest.CaptureFixture[str]) -> None:
+        ViolationReporter.report([], "test-tool")
+        captured = capsys.readouterr()
+        assert "OK" in captured.out
+        assert "test-tool" in captured.out
+
+    def test_report_with_violations(self, capsys: pytest.CaptureFixture[str]) -> None:
+        with pytest.raises(SystemExit) as exc_info:
+            ViolationReporter.report(["v1", "v2"], "test-tool")
+        assert exc_info.value.code == 1
+        captured = capsys.readouterr()
+        assert "FAIL" in captured.out
+        assert "v1" in captured.out
+        assert "v2" in captured.out
+
+
+class TestDefaultAnsibleDirs:
+    def test_is_tuple(self) -> None:
+        assert isinstance(DEFAULT_ANSIBLE_DIRS, tuple)
+
+    def test_contains_expected(self) -> None:
+        assert "ansible/roles" in DEFAULT_ANSIBLE_DIRS
+        assert "ansible/playbooks" in DEFAULT_ANSIBLE_DIRS

tests/unit/test_ci_cancel_superseded_runs.py

@@ -0,0 +1,172 @@
+"""Unit tests for devx.ci.cancel_superseded_runs."""
+
+from __future__ import annotations
+
+import json
+import urllib.error
+from unittest.mock import MagicMock, patch
+
+import pytest
+
+import devx.ci.cancel_superseded_runs as mod
+from devx.ci.cancel_superseded_runs import _api_request, cancel_run, list_running_runs, main
+
+_HTTP_NO_CONTENT = mod._HTTP_NO_CONTENT
+_PAGE_SIZE = mod._PAGE_SIZE
+
+
+class TestConstants:
+    def test_http_no_content_is_204(self) -> None:
+        assert _HTTP_NO_CONTENT == 204
+
+    def test_page_size_is_50(self) -> None:
+        assert _PAGE_SIZE == 50
+
+
+class TestApiRequest:
+    def test_returns_empty_for_204(self) -> None:
+        mock_resp = MagicMock()
+        mock_resp.status = _HTTP_NO_CONTENT
+        mock_resp.read.return_value = b""
+        mock_resp.__enter__ = MagicMock(return_value=mock_resp)
+        mock_resp.__exit__ = MagicMock(return_value=None)
+        with patch("urllib.request.urlopen", return_value=mock_resp):
+            result = _api_request("POST", "/repos/test/actions/runs/1/cancel", "tok", "https://x")
+        assert result == {}
+
+    def test_returns_json_for_200(self) -> None:
+        mock_resp = MagicMock()
+        mock_resp.status = 200
+        mock_resp.read.return_value = json.dumps({"id": 1}).encode()
+        mock_resp.__enter__ = MagicMock(return_value=mock_resp)
+        mock_resp.__exit__ = MagicMock(return_value=None)
+        with patch("urllib.request.urlopen", return_value=mock_resp):
+            result = _api_request("GET", "/repos/test/actions/runs", "tok", "https://x")
+        assert result == {"id": 1}
+
+    def test_http_error_raises(self) -> None:
+        err = urllib.error.HTTPError("x", 500, "err", {}, None)
+        err.read = MagicMock(return_value=b"error body")
+        with patch("urllib.request.urlopen", side_effect=err):
+            with pytest.raises(urllib.error.HTTPError):
+                _api_request("GET", "/repos/test/actions/runs", "tok", "https://x")
+
+    def test_url_error_raises(self) -> None:
+        with patch("urllib.request.urlopen", side_effect=urllib.error.URLError("fail")):
+            with pytest.raises(urllib.error.URLError):
+                _api_request("GET", "/repos/test/actions/runs", "tok", "https://x")
+
+
+class TestListRunningRuns:
+    def test_paginates_until_empty(self) -> None:
+        page1 = {"workflow_runs": [{"id": 1}, {"id": 2}], "total_count": 2}
+        page2 = {"workflow_runs": [], "total_count": 2}
+        responses = iter([page1, page2])
+        with patch.object(mod, "_api_request", side_effect=lambda *a, **k: next(responses)):
+            runs = list_running_runs("owner/repo", "tok", "https://x")
+        assert len(runs) == 2
+
+    def test_empty_first_page(self) -> None:
+        with patch.object(mod, "_api_request", return_value={"workflow_runs": [], "total_count": 0}):
+            runs = list_running_runs("owner/repo", "tok", "https://x")
+        assert runs == []
+
+    def test_stops_at_page_size(self) -> None:
+        full_page = {"workflow_runs": [{"id": i} for i in range(_PAGE_SIZE)], "total_count": _PAGE_SIZE + 1}
+        half_page = {"workflow_runs": [{"id": 99}], "total_count": _PAGE_SIZE + 1}
+        responses = iter([full_page, half_page])
+        with patch.object(mod, "_api_request", side_effect=lambda *a, **k: next(responses)):
+            runs = list_running_runs("owner/repo", "tok", "https://x")
+        assert len(runs) == _PAGE_SIZE + 1
+
+    def test_uses_in_progress_status(self) -> None:
+        with patch.object(mod, "_api_request", return_value={"workflow_runs": [], "total_count": 0}) as mock_req:
+            list_running_runs("owner/repo", "tok", "https://x")
+        path = mock_req.call_args.args[1]
+        assert "status=in_progress" in path
+        assert "status=running" not in path
+
+    def test_accepts_bare_list(self) -> None:
+        with patch.object(mod, "_api_request", return_value=[{"id": 1}, {"id": 2}]):
+            runs = list_running_runs("owner/repo", "tok", "https://x")
+        assert len(runs) == 2
+
+
+class TestCancelRun:
+    def test_success_returns_true(self) -> None:
+        with patch.object(mod, "_api_request", return_value={}):
+            assert cancel_run("owner/repo", 123, "tok", "https://x") is True
+
+    def test_http_error_returns_false(self) -> None:
+        with patch.object(mod, "_api_request", side_effect=urllib.error.HTTPError("x", 500, "err", {}, None)):
+            assert cancel_run("owner/repo", 123, "tok", "https://x") is False
+
+
+class TestMain:
+    def test_no_token_exits_zero(self, monkeypatch: pytest.MonkeyPatch) -> None:
+        monkeypatch.delenv("CI_GITEA_API_TOKEN", raising=False)
+        monkeypatch.delenv("CI_GITEA_TOKEN", raising=False)
+        monkeypatch.setattr("sys.argv", ["cancel", "--repo", "o/r", "--current-run-id", "1", "--head-branch", "feat"])
+        assert main() == 0
+
+    def test_no_superseded_runs(self, monkeypatch: pytest.MonkeyPatch) -> None:
+        monkeypatch.setenv("CI_GITEA_API_TOKEN", "tok")
+        monkeypatch.setattr("sys.argv", ["cancel", "--repo", "o/r", "--current-run-id", "10", "--head-branch", "feat"])
+        with patch.object(mod, "list_running_runs", return_value=[]):
+            assert main() == 0
+
+    def test_cancels_superseded(self, monkeypatch: pytest.MonkeyPatch) -> None:
+        monkeypatch.setenv("CI_GITEA_API_TOKEN", "tok")
+        runs = [
+            {"id": 5, "head_branch": "feat"},
+            {"id": 8, "head_branch": "feat"},
+            {"id": 12, "head_branch": "other"},
+        ]
+        monkeypatch.setattr("sys.argv", ["cancel", "--repo", "o/r", "--current-run-id", "10", "--head-branch", "feat"])
+        with patch.object(mod, "list_running_runs", return_value=runs):
+            with patch.object(mod, "cancel_run", return_value=True) as mock_cancel:
+                assert main() == 0
+        cancelled_ids = [call.args[1] for call in mock_cancel.call_args_list]
+        assert cancelled_ids == [5, 8]
+
+    def test_dry_run_does_not_cancel(self, monkeypatch: pytest.MonkeyPatch) -> None:
+        monkeypatch.setenv("CI_GITEA_API_TOKEN", "tok")
+        runs = [{"id": 5, "head_branch": "feat"}]
+        monkeypatch.setattr(
+            "sys.argv",
+            ["cancel", "--repo", "o/r", "--current-run-id", "10", "--head-branch", "feat", "--dry-run"],
+        )
+        with patch.object(mod, "list_running_runs", return_value=runs):
+            with patch.object(mod, "cancel_run", return_value=True) as mock_cancel:
+                assert main() == 0
+        assert mock_cancel.call_count == 0
+
+    def test_cancel_failure_continues(self, monkeypatch: pytest.MonkeyPatch) -> None:
+        monkeypatch.setenv("CI_GITEA_API_TOKEN", "tok")
+        runs = [{"id": 5, "head_branch": "feat"}, {"id": 8, "head_branch": "feat"}]
+        monkeypatch.setattr("sys.argv", ["cancel", "--repo", "o/r", "--current-run-id", "10", "--head-branch", "feat"])
+        with patch.object(mod, "list_running_runs", return_value=runs):
+            with patch.object(mod, "cancel_run", side_effect=[False, True]):
+                assert main() == 0
+
+    def test_404_returns_zero(self, monkeypatch: pytest.MonkeyPatch) -> None:
+        monkeypatch.setenv("CI_GITEA_API_TOKEN", "tok")
+        monkeypatch.setattr("sys.argv", ["cancel", "--repo", "o/r", "--current-run-id", "10", "--head-branch", "feat"])
+        err = urllib.error.HTTPError("x", 404, "Not Found", {}, None)
+        with patch.object(mod, "list_running_runs", side_effect=err):
+            assert main() == 0
+
+    def test_400_returns_zero(self, monkeypatch: pytest.MonkeyPatch) -> None:
+        monkeypatch.setenv("CI_GITEA_API_TOKEN", "tok")
+        monkeypatch.setattr("sys.argv", ["cancel", "--repo", "o/r", "--current-run-id", "10", "--head-branch", "feat"])
+        err = urllib.error.HTTPError("x", 400, "Bad Request", {}, None)
+        with patch.object(mod, "list_running_runs", side_effect=err):
+            assert main() == 0
+
+    def test_500_raises(self, monkeypatch: pytest.MonkeyPatch) -> None:
+        monkeypatch.setenv("CI_GITEA_API_TOKEN", "tok")
+        monkeypatch.setattr("sys.argv", ["cancel", "--repo", "o/r", "--current-run-id", "10", "--head-branch", "feat"])
+        err = urllib.error.HTTPError("x", 500, "Server Error", {}, None)
+        with patch.object(mod, "list_running_runs", side_effect=err):
+            with pytest.raises(urllib.error.HTTPError):
+                main()

tests/unit/test_ci_check_workflow_artifact_deps.py

@@ -0,0 +1,419 @@
+"""Unit tests for devx.ci.check_workflow_artifact_deps."""
+
+from __future__ import annotations
+
+import textwrap
+from pathlib import Path
+
+from click.testing import CliRunner
+
+from devx.ci.check_workflow_artifact_deps import (
+    _check_workflow,
+    _extract_artifact_info,
+    _is_artifact_action,
+    main,
+)
+
+
+class TestIsArtifactAction:
+    def test_upload_action_gitea(self):
+        assert _is_artifact_action("christopherhx/gitea-upload-artifact@v4", ("upload-artifact",))
+
+    def test_upload_action_github(self):
+        assert _is_artifact_action("actions/upload-artifact@v4", ("upload-artifact",))
+
+    def test_download_action(self):
+        assert _is_artifact_action("christopherhx/gitea-download-artifact@v4", ("download-artifact",))
+
+    def test_non_artifact_action(self):
+        assert not _is_artifact_action("actions/checkout@v4", ("upload-artifact",))
+
+    def test_empty_string(self):
+        assert not _is_artifact_action("", ("upload-artifact",))
+
+    def test_case_insensitive(self):
+        assert _is_artifact_action("Actions/Upload-Artifact@v4", ("upload-artifact",))
+
+
+class TestExtractArtifactInfo:
+    def test_uploads_and_downloads(self):
+        import yaml
+
+        workflow_yaml = textwrap.dedent("""
+            jobs:
+              producer:
+                steps:
+                  - name: Upload config
+                    uses: christopherhx/gitea-upload-artifact@v4
+                    with:
+                      name: config-${{ github.run_id }}
+              consumer:
+                needs: [producer]
+                steps:
+                  - name: Download config
+                    uses: christopherhx/gitea-download-artifact@v4
+                    with:
+                      name: config-${{ github.run_id }}
+        """).strip()
+        wf = yaml.safe_load(workflow_yaml)
+        uploads, downloads = _extract_artifact_info(wf)
+        assert uploads == {"config-${{ github.run_id }}": ["producer"]}
+        assert downloads == [("consumer", "config-${{ github.run_id }}", "Download config")]
+
+    def test_no_artifacts(self):
+        import yaml
+
+        workflow_yaml = textwrap.dedent("""
+            jobs:
+              build:
+                steps:
+                  - name: Checkout
+                    uses: actions/checkout@v4
+        """).strip()
+        wf = yaml.safe_load(workflow_yaml)
+        uploads, downloads = _extract_artifact_info(wf)
+        assert uploads == {}
+        assert downloads == []
+
+    def test_multiple_uploaders_same_artifact(self):
+        import yaml
+
+        workflow_yaml = textwrap.dedent("""
+            jobs:
+              producer-a:
+                steps:
+                  - uses: christopherhx/gitea-upload-artifact@v4
+                    with:
+                      name: shared
+              producer-b:
+                steps:
+                  - uses: christopherhx/gitea-upload-artifact@v4
+                    with:
+                      name: shared
+        """).strip()
+        wf = yaml.safe_load(workflow_yaml)
+        uploads, downloads = _extract_artifact_info(wf)
+        assert uploads == {"shared": ["producer-a", "producer-b"]}
+
+    def test_step_without_name(self):
+        import yaml
+
+        workflow_yaml = textwrap.dedent("""
+            jobs:
+              producer:
+                steps:
+                  - uses: christopherhx/gitea-upload-artifact@v4
+                    with:
+                      name: data
+              consumer:
+                needs: [producer]
+                steps:
+                  - uses: christopherhx/gitea-download-artifact@v4
+                    with:
+                      name: data
+        """).strip()
+        wf = yaml.safe_load(workflow_yaml)
+        uploads, downloads = _extract_artifact_info(wf)
+        assert downloads == [("consumer", "data", "")]
+
+    def test_upload_without_name_skipped(self):
+        import yaml
+
+        workflow_yaml = textwrap.dedent("""
+            jobs:
+              producer:
+                steps:
+                  - uses: christopherhx/gitea-upload-artifact@v4
+                    with:
+                      path: ./dist
+        """).strip()
+        wf = yaml.safe_load(workflow_yaml)
+        uploads, downloads = _extract_artifact_info(wf)
+        assert uploads == {}
+
+
+class TestCheckWorkflow:
+    def test_valid_dependency(self, tmp_path: Path):
+        workflow_yaml = textwrap.dedent("""
+            jobs:
+              producer:
+                steps:
+                  - name: Upload config
+                    uses: christopherhx/gitea-upload-artifact@v4
+                    with:
+                      name: config
+              consumer:
+                needs: [producer]
+                steps:
+                  - name: Download config
+                    uses: christopherhx/gitea-download-artifact@v4
+                    with:
+                      name: config
+        """).strip()
+        f = tmp_path / "test.yml"
+        f.write_text(workflow_yaml)
+        assert _check_workflow(f) == []
+
+    def test_missing_dependency(self, tmp_path: Path):
+        workflow_yaml = textwrap.dedent("""
+            jobs:
+              producer:
+                steps:
+                  - name: Upload config
+                    uses: christopherhx/gitea-upload-artifact@v4
+                    with:
+                      name: config
+              consumer:
+                needs: [other-job]
+                steps:
+                  - name: Download config
+                    uses: christopherhx/gitea-download-artifact@v4
+                    with:
+                      name: config
+        """).strip()
+        f = tmp_path / "test.yml"
+        f.write_text(workflow_yaml)
+        errors = _check_workflow(f)
+        assert len(errors) == 1
+        assert "consumer" in errors[0]
+        assert "producer" in errors[0]
+
+    def test_no_needs_at_all(self, tmp_path: Path):
+        workflow_yaml = textwrap.dedent("""
+            jobs:
+              producer:
+                steps:
+                  - uses: christopherhx/gitea-upload-artifact@v4
+                    with:
+                      name: data
+              consumer:
+                steps:
+                  - uses: christopherhx/gitea-download-artifact@v4
+                    with:
+                      name: data
+        """).strip()
+        f = tmp_path / "test.yml"
+        f.write_text(workflow_yaml)
+        errors = _check_workflow(f)
+        assert len(errors) == 1
+        assert "consumer" in errors[0]
+
+    def test_artifact_not_uploaded_in_workflow(self, tmp_path: Path):
+        workflow_yaml = textwrap.dedent("""
+            jobs:
+              consumer:
+                steps:
+                  - name: Download external
+                    uses: christopherhx/gitea-download-artifact@v4
+                    with:
+                      name: external-artifact
+        """).strip()
+        f = tmp_path / "test.yml"
+        f.write_text(workflow_yaml)
+        assert _check_workflow(f) == []
+
+    def test_multiple_uploaders_one_in_needs(self, tmp_path: Path):
+        workflow_yaml = textwrap.dedent("""
+            jobs:
+              producer-a:
+                steps:
+                  - uses: christopherhx/gitea-upload-artifact@v4
+                    with:
+                      name: shared
+              producer-b:
+                steps:
+                  - uses: christopherhx/gitea-upload-artifact@v4
+                    with:
+                      name: shared
+              consumer:
+                needs: [producer-a, other]
+                steps:
+                  - uses: christopherhx/gitea-download-artifact@v4
+                    with:
+                      name: shared
+        """).strip()
+        f = tmp_path / "test.yml"
+        f.write_text(workflow_yaml)
+        assert _check_workflow(f) == []
+
+    def test_string_needs(self, tmp_path: Path):
+        workflow_yaml = textwrap.dedent("""
+            jobs:
+              producer:
+                steps:
+                  - uses: christopherhx/gitea-upload-artifact@v4
+                    with:
+                      name: data
+              consumer:
+                needs: producer
+                steps:
+                  - uses: christopherhx/gitea-download-artifact@v4
+                    with:
+                      name: data
+        """).strip()
+        f = tmp_path / "test.yml"
+        f.write_text(workflow_yaml)
+        assert _check_workflow(f) == []
+
+    def test_needs_null(self, tmp_path: Path):
+        workflow_yaml = textwrap.dedent("""
+            jobs:
+              producer:
+                steps:
+                  - uses: christopherhx/gitea-upload-artifact@v4
+                    with:
+                      name: data
+              consumer:
+                needs: null
+                steps:
+                  - uses: christopherhx/gitea-download-artifact@v4
+                    with:
+                      name: data
+        """).strip()
+        f = tmp_path / "test.yml"
+        f.write_text(workflow_yaml)
+        errors = _check_workflow(f)
+        assert len(errors) == 1
+        assert "consumer" in errors[0]
+
+    def test_invalid_yaml(self, tmp_path: Path):
+        f = tmp_path / "test.yml"
+        f.write_text("jobs: [invalid yaml: {")
+        errors = _check_workflow(f)
+        assert len(errors) == 1
+        assert "cannot parse YAML" in errors[0]
+
+    def test_not_a_dict(self, tmp_path: Path):
+        f = tmp_path / "test.yml"
+        f.write_text("just a string")
+        errors = _check_workflow(f)
+        assert len(errors) == 1
+        assert "not a valid workflow" in errors[0]
+
+    def test_no_jobs(self, tmp_path: Path):
+        f = tmp_path / "test.yml"
+        f.write_text("name: empty\non: push\n")
+        assert _check_workflow(f) == []
+
+    def test_continue_on_error_guard(self, tmp_path: Path):
+        workflow_yaml = textwrap.dedent("""
+            jobs:
+              producer:
+                steps:
+                  - name: Upload config
+                    uses: christopherhx/gitea-upload-artifact@v4
+                    with:
+                      name: config
+              consumer:
+                needs: [other-job]
+                steps:
+                  - name: Download config
+                    continue-on-error: true
+                    uses: christopherhx/gitea-download-artifact@v4
+                    with:
+                      name: config
+        """).strip()
+        f = tmp_path / "test.yml"
+        f.write_text(workflow_yaml)
+        assert _check_workflow(f) == []
+
+    def test_continue_on_error_false_still_errors(self, tmp_path: Path):
+        workflow_yaml = textwrap.dedent("""
+            jobs:
+              producer:
+                steps:
+                  - name: Upload config
+                    uses: christopherhx/gitea-upload-artifact@v4
+                    with:
+                      name: config
+              consumer:
+                needs: [other-job]
+                steps:
+                  - name: Download config
+                    continue-on-error: false
+                    uses: christopherhx/gitea-download-artifact@v4
+                    with:
+                      name: config
+        """).strip()
+        f = tmp_path / "test.yml"
+        f.write_text(workflow_yaml)
+        errors = _check_workflow(f)
+        assert len(errors) == 1
+        assert "consumer" in errors[0]
+
+    def test_job_with_no_steps(self, tmp_path: Path):
+        workflow_yaml = textwrap.dedent("""
+            jobs:
+              empty:
+                runs-on: docker
+        """).strip()
+        f = tmp_path / "test.yml"
+        f.write_text(workflow_yaml)
+        assert _check_workflow(f) == []
+
+
+class TestMain:
+    def test_passes_when_valid(self, tmp_path: Path):
+        workflow_yaml = textwrap.dedent("""
+            jobs:
+              producer:
+                steps:
+                  - uses: christopherhx/gitea-upload-artifact@v4
+                    with:
+                      name: data
+              consumer:
+                needs: [producer]
+                steps:
+                  - uses: christopherhx/gitea-download-artifact@v4
+                    with:
+                      name: data
+        """).strip()
+        f = tmp_path / "test.yml"
+        f.write_text(workflow_yaml)
+        runner = CliRunner()
+        result = runner.invoke(main, ["--workflows-dir", str(tmp_path)])
+        assert result.exit_code == 0
+        assert "OK" in result.output
+
+    def test_fails_when_missing_dep(self, tmp_path: Path):
+        workflow_yaml = textwrap.dedent("""
+            jobs:
+              producer:
+                steps:
+                  - uses: christopherhx/gitea-upload-artifact@v4
+                    with:
+                      name: data
+              consumer:
+                steps:
+                  - uses: christopherhx/gitea-download-artifact@v4
+                    with:
+                      name: data
+        """).strip()
+        f = tmp_path / "test.yml"
+        f.write_text(workflow_yaml)
+        runner = CliRunner()
+        result = runner.invoke(main, ["--workflows-dir", str(tmp_path)])
+        assert result.exit_code == 1
+        assert "FAIL" in result.output
+        assert "consumer" in result.output
+
+    def test_specific_workflow_file(self, tmp_path: Path):
+        workflow_yaml = textwrap.dedent("""
+            jobs:
+              producer:
+                steps:
+                  - uses: christopherhx/gitea-upload-artifact@v4
+                    with:
+                      name: data
+              consumer:
+                needs: [producer]
+                steps:
+                  - uses: christopherhx/gitea-download-artifact@v4
+                    with:
+                      name: data
+        """).strip()
+        f = tmp_path / "test.yml"
+        f.write_text(workflow_yaml)
+        runner = CliRunner()
+        result = runner.invoke(main, ["--workflow", str(f)])
+        assert result.exit_code == 0

tests/unit/test_ci_check_workflow_tofu_init.py

@@ -0,0 +1,356 @@
+"""Unit tests for devx.ci.check_workflow_tofu_init."""
+
+from __future__ import annotations
+
+import textwrap
+from pathlib import Path
+
+from click.testing import CliRunner
+
+import devx.ci.check_workflow_tofu_init as mod
+from devx.ci.check_workflow_tofu_init import _check_workflow, main
+
+
+def _write_workflow(tmp_path: Path, content: str) -> Path:
+    filepath = tmp_path / "test.yml"
+    filepath.write_text(textwrap.dedent(content), encoding="utf-8")
+    return filepath
+
+
+class TestCheckWorkflow:
+    def test_passes_when_tofu_init_present(self, tmp_path: Path) -> None:
+        filepath = _write_workflow(
+            tmp_path,
+            """
+            name: Test
+            on: push
+            jobs:
+              deploy:
+                runs-on: docker
+                steps:
+                  - run: python3 scripts/create_production_deployment.py --phase tofu-init
+                  - run: python3 scripts/preflight_deploy.py --env production
+        """,
+        )
+        assert _check_workflow(filepath, mod.DEFAULT_TOFU_STATE_SCRIPTS) == []
+
+    def test_fails_when_tofu_init_missing(self, tmp_path: Path) -> None:
+        filepath = _write_workflow(
+            tmp_path,
+            """
+            name: Test
+            on: push
+            jobs:
+              preflight:
+                runs-on: docker
+                steps:
+                  - run: python3 scripts/preflight_deploy.py --env production
+        """,
+        )
+        errors = _check_workflow(filepath, mod.DEFAULT_TOFU_STATE_SCRIPTS)
+        assert len(errors) == 1
+        assert "preflight" in errors[0]
+        assert "tofu-init" in errors[0]
+
+    def test_passes_when_direct_tofu_init(self, tmp_path: Path) -> None:
+        filepath = _write_workflow(
+            tmp_path,
+            """
+            name: Test
+            on: push
+            jobs:
+              deploy:
+                runs-on: docker
+                steps:
+                  - run: tofu init
+                  - run: tofu output -json
+        """,
+        )
+        assert _check_workflow(filepath, mod.DEFAULT_TOFU_STATE_SCRIPTS) == []
+
+    def test_fails_when_direct_tofu_output_without_init(self, tmp_path: Path) -> None:
+        filepath = _write_workflow(
+            tmp_path,
+            """
+            name: Test
+            on: push
+            jobs:
+              check:
+                runs-on: docker
+                steps:
+                  - run: tofu output -json
+        """,
+        )
+        errors = _check_workflow(filepath, mod.DEFAULT_TOFU_STATE_SCRIPTS)
+        assert len(errors) == 1
+        assert "check" in errors[0]
+
+    def test_passes_when_no_tofu_usage(self, tmp_path: Path) -> None:
+        filepath = _write_workflow(
+            tmp_path,
+            """
+            name: Test
+            on: push
+            jobs:
+              lint:
+                runs-on: docker
+                steps:
+                  - run: make lint
+        """,
+        )
+        assert _check_workflow(filepath, mod.DEFAULT_TOFU_STATE_SCRIPTS) == []
+
+    def test_passes_with_staging_deployment_tofu_init(self, tmp_path: Path) -> None:
+        filepath = _write_workflow(
+            tmp_path,
+            """
+            name: Test
+            on: push
+            jobs:
+              deploy:
+                runs-on: docker
+                steps:
+                  - run: python3 scripts/create_staging_deployment.py --phase tofu-init
+                  - run: python3 scripts/create_staging_deployment.py --phase deploy
+        """,
+        )
+        assert _check_workflow(filepath, mod.DEFAULT_TOFU_STATE_SCRIPTS) == []
+
+    def test_fails_with_tofu_plan_without_init(self, tmp_path: Path) -> None:
+        filepath = _write_workflow(
+            tmp_path,
+            """
+            name: Test
+            on: push
+            jobs:
+              plan:
+                runs-on: docker
+                steps:
+                  - run: tofu plan
+        """,
+        )
+        errors = _check_workflow(filepath, mod.DEFAULT_TOFU_STATE_SCRIPTS)
+        assert len(errors) == 1
+        assert "plan" in errors[0]
+
+    def test_fails_with_tofu_apply_without_init(self, tmp_path: Path) -> None:
+        filepath = _write_workflow(
+            tmp_path,
+            """
+            name: Test
+            on: push
+            jobs:
+              apply:
+                runs-on: docker
+                steps:
+                  - run: tofu apply -auto-approve
+        """,
+        )
+        errors = _check_workflow(filepath, mod.DEFAULT_TOFU_STATE_SCRIPTS)
+        assert len(errors) == 1
+        assert "apply" in errors[0]
+
+    def test_multiple_jobs_one_missing(self, tmp_path: Path) -> None:
+        filepath = _write_workflow(
+            tmp_path,
+            """
+            name: Test
+            on: push
+            jobs:
+              good:
+                runs-on: docker
+                steps:
+                  - run: python3 scripts/create_production_deployment.py --phase tofu-init
+                  - run: python3 scripts/preflight_deploy.py --env production
+              bad:
+                runs-on: docker
+                steps:
+                  - run: python3 scripts/preflight_deploy.py --env production
+        """,
+        )
+        errors = _check_workflow(filepath, mod.DEFAULT_TOFU_STATE_SCRIPTS)
+        assert len(errors) == 1
+        assert "bad" in errors[0]
+
+    def test_no_steps_passes(self, tmp_path: Path) -> None:
+        filepath = _write_workflow(
+            tmp_path,
+            """
+            name: Test
+            on: push
+            jobs:
+              empty:
+                runs-on: docker
+        """,
+        )
+        assert _check_workflow(filepath, mod.DEFAULT_TOFU_STATE_SCRIPTS) == []
+
+    def test_destroy_orphans_does_not_require_init(self, tmp_path: Path) -> None:
+        filepath = _write_workflow(
+            tmp_path,
+            """
+            name: Test
+            on: push
+            jobs:
+              cleanup:
+                runs-on: docker
+                steps:
+                  - run: python3 scripts/destroy_orphans.py
+        """,
+        )
+        assert _check_workflow(filepath, mod.DEFAULT_TOFU_STATE_SCRIPTS) == []
+
+    def test_invalid_yaml_returns_error(self, tmp_path: Path) -> None:
+        filepath = tmp_path / "bad.yml"
+        filepath.write_text("jobs: [invalid yaml: {", encoding="utf-8")
+        errors = _check_workflow(filepath, mod.DEFAULT_TOFU_STATE_SCRIPTS)
+        assert len(errors) == 1
+        assert "cannot parse YAML" in errors[0]
+
+    def test_tofu_show_requires_init(self, tmp_path: Path) -> None:
+        filepath = _write_workflow(
+            tmp_path,
+            """
+            name: Test
+            on: push
+            jobs:
+              show:
+                runs-on: docker
+                steps:
+                  - run: tofu show -json
+        """,
+        )
+        errors = _check_workflow(filepath, mod.DEFAULT_TOFU_STATE_SCRIPTS)
+        assert len(errors) == 1
+        assert "show" in errors[0]
+
+    def test_custom_state_scripts(self, tmp_path: Path) -> None:
+        filepath = _write_workflow(
+            tmp_path,
+            """
+            name: Test
+            on: push
+            jobs:
+              custom:
+                runs-on: docker
+                steps:
+                  - run: python3 scripts/my_custom_script.py
+        """,
+        )
+        errors = _check_workflow(filepath, {"my_custom_script.py"})
+        assert len(errors) == 1
+        assert "custom" in errors[0]
+
+    def test_step_with_no_run_skipped(self, tmp_path: Path) -> None:
+        """A step with no 'run' key should be skipped (line 80 continue)."""
+        filepath = _write_workflow(
+            tmp_path,
+            """
+            name: Test
+            on: push
+            jobs:
+              deploy:
+                runs-on: docker
+                steps:
+                  - name: Checkout
+                    uses: actions/checkout@v4
+                  - run: tofu init
+                  - run: tofu output
+        """,
+        )
+        assert _check_workflow(filepath, mod.DEFAULT_TOFU_STATE_SCRIPTS) == []
+
+
+class TestCli:
+    def test_passes_with_specific_workflow(self, tmp_path: Path) -> None:
+        filepath = _write_workflow(
+            tmp_path,
+            """
+            name: Test
+            on: push
+            jobs:
+              deploy:
+                runs-on: docker
+                steps:
+                  - run: tofu init
+                  - run: tofu output
+        """,
+        )
+        runner = CliRunner()
+        result = runner.invoke(main, ["--workflow", str(filepath)])
+        assert result.exit_code == 0
+        assert "OK" in result.output
+
+    def test_fails_with_missing_tofu_init(self, tmp_path: Path) -> None:
+        filepath = _write_workflow(
+            tmp_path,
+            """
+            name: Test
+            on: push
+            jobs:
+              preflight:
+                runs-on: docker
+                steps:
+                  - run: python3 scripts/preflight_deploy.py --env production
+        """,
+        )
+        runner = CliRunner()
+        result = runner.invoke(main, ["--workflow", str(filepath)])
+        assert result.exit_code == 1
+        assert "FAIL" in result.output
+        assert "preflight" in result.output
+
+    def test_checks_all_workflows_by_default(self, tmp_path: Path) -> None:
+        workflows_dir = tmp_path / "workflows"
+        workflows_dir.mkdir()
+        (workflows_dir / "good.yml").write_text(
+            textwrap.dedent("""
+            name: Good
+            on: push
+            jobs:
+              deploy:
+                runs-on: docker
+                steps:
+                  - run: tofu init
+                  - run: tofu output
+        """),
+            encoding="utf-8",
+        )
+        (workflows_dir / "bad.yml").write_text(
+            textwrap.dedent("""
+            name: Bad
+            on: push
+            jobs:
+              check:
+                runs-on: docker
+                steps:
+                  - run: tofu output
+        """),
+            encoding="utf-8",
+        )
+        runner = CliRunner()
+        result = runner.invoke(main, ["--workflows-dir", str(workflows_dir)])
+        assert result.exit_code == 1
+        assert "bad.yml" in result.output
+        assert "check" in result.output
+
+    def test_all_workflows_pass(self, tmp_path: Path) -> None:
+        workflows_dir = tmp_path / "workflows"
+        workflows_dir.mkdir()
+        (workflows_dir / "ok.yml").write_text(
+            textwrap.dedent("""
+            name: OK
+            on: push
+            jobs:
+              deploy:
+                runs-on: docker
+                steps:
+                  - run: tofu init
+                  - run: tofu plan
+        """),
+            encoding="utf-8",
+        )
+        runner = CliRunner()
+        result = runner.invoke(main, ["--workflows-dir", str(workflows_dir)])
+        assert result.exit_code == 0
+        assert "OK" in result.output

tests/unit/test_cli.py

@@ -150,6 +150,13 @@ class TestCiCommands:
         assert result.exit_code == 0
         mock_run.assert_called_once_with("devx.ci.validate_commit_msg", ["msg"])
 
+    @patch("devx.cli._run_module")
+    def test_ci_wait_for_checks(self, mock_run: MagicMock) -> None:
+        runner = CliRunner()
+        result = runner.invoke(cli, ["ci", "wait-for-checks", "--", "--job-name", "molecule-tests"])
+        assert result.exit_code == 0
+        mock_run.assert_called_once_with("devx.ci.wait_for_checks", ["--job-name", "molecule-tests"])
+
 
 class TestToolsCommands:
     @patch("devx.cli._run_module")

tests/unit/test_discover_runners.py

@@ -1,4 +1,9 @@
-"""Unit tests for scripts/ci/discover_runners.py."""
+"""Unit tests for devx.ci.discover_runners (deprecated wrapper).
+
+The wrapper re-exports from devx.molecule.discover_runners; these tests
+verify backward compatibility by importing through the wrapper and
+patching the canonical implementation's requests module.
+"""
 
 import json
 from pathlib import Path
@@ -32,7 +37,7 @@ class TestGenerateIndices:
 
 
 class TestQueryRunners:
-    @patch("devx.ci.discover_runners.requests.get")
+    @patch("devx.molecule.discover_runners.requests.get")
     def test_returns_total_from_all_levels(self, mock_get: MagicMock) -> None:
         """Runners from repo, org, and admin levels are summed."""
         responses = [
@@ -44,7 +49,7 @@ class TestQueryRunners:
         result = query_runners("https://api.example.com", "token", "owner", "repo")
         assert result == 6
 
-    @patch("devx.ci.discover_runners.requests.get")
+    @patch("devx.molecule.discover_runners.requests.get")
     def test_skips_non_200(self, mock_get: MagicMock) -> None:
         """Non-200 responses (e.g., 403 for admin) are skipped."""
         responses = [
@@ -56,7 +61,7 @@ class TestQueryRunners:
         result = query_runners("https://api.example.com", "token", "owner", "repo")
         assert result == 3
 
-    @patch("devx.ci.discover_runners.requests.get")
+    @patch("devx.molecule.discover_runners.requests.get")
     def test_handles_request_exception(self, mock_get: MagicMock) -> None:
         """Network errors are caught and don't crash."""
         mock_get.side_effect = [
@@ -67,7 +72,7 @@ class TestQueryRunners:
         result = query_runners("https://api.example.com", "token", "owner", "repo")
         assert result == 3
 
-    @patch("devx.ci.discover_runners.requests.get")
+    @patch("devx.molecule.discover_runners.requests.get")
     def test_all_failures_return_zero(self, mock_get: MagicMock) -> None:
         """When all API calls fail, returns 0."""
         mock_get.side_effect = [
@@ -78,7 +83,7 @@ class TestQueryRunners:
         result = query_runners("https://api.example.com", "token", "owner", "repo")
         assert result == 0
 
-    @patch("devx.ci.discover_runners.requests.get")
+    @patch("devx.molecule.discover_runners.requests.get")
     def test_value_error_on_repo_level(self, mock_get: MagicMock) -> None:
         """JSON parse error on repo level is caught."""
         responses = [
@@ -90,7 +95,7 @@ class TestQueryRunners:
         result = query_runners("https://api.example.com", "token", "owner", "repo")
         assert result == 3
 
-    @patch("devx.ci.discover_runners.requests.get")
+    @patch("devx.molecule.discover_runners.requests.get")
     def test_value_error_on_org_level(self, mock_get: MagicMock) -> None:
         """JSON parse error on org level is caught."""
         responses = [
@@ -102,7 +107,7 @@ class TestQueryRunners:
         result = query_runners("https://api.example.com", "token", "owner", "repo")
         assert result == 3
 
-    @patch("devx.ci.discover_runners.requests.get")
+    @patch("devx.molecule.discover_runners.requests.get")
     def test_value_error_on_admin_level(self, mock_get: MagicMock) -> None:
         """JSON parse error on admin level is caught."""
         responses = [
@@ -114,14 +119,14 @@ class TestQueryRunners:
         result = query_runners("https://api.example.com", "token", "owner", "repo")
         assert result == 3
 
-    @patch("devx.ci.discover_runners.requests.get")
+    @patch("devx.molecule.discover_runners.requests.get")
     def test_request_exception_on_all_levels(self, mock_get: MagicMock) -> None:
         """Network errors on all levels return 0."""
         mock_get.side_effect = __import__("requests").RequestException("network error")
         result = query_runners("https://api.example.com", "token", "owner", "repo")
         assert result == 0
 
-    @patch("devx.ci.discover_runners.requests.get")
+    @patch("devx.molecule.discover_runners.requests.get")
     def test_query_runners_403_no_warning(self, mock_get: MagicMock, capsys: pytest.CaptureFixture[str]) -> None:
         """403 on instance-level runners should not produce a warning (expected without admin scope)."""
         responses = [
@@ -135,7 +140,7 @@ class TestQueryRunners:
         captured = capsys.readouterr()
         assert "instance-level" not in captured.err
 
-    @patch("devx.ci.discover_runners.requests.get")
+    @patch("devx.molecule.discover_runners.requests.get")
     def test_instance_level_non_403_warns(self, mock_get: MagicMock, capsys: pytest.CaptureFixture[str]) -> None:
         """Non-200, non-403 status on instance-level runners should produce a warning."""
         responses = [
@@ -152,37 +157,37 @@ class TestQueryRunners:
 
 
 class TestGetRunnerCount:
-    @patch("devx.ci.discover_runners.query_runners", return_value=5)
+    @patch("devx.molecule.discover_runners.query_runners", return_value=5)
     def test_uses_api_count_when_positive(self, mock_query: MagicMock) -> None:
         result = get_runner_count("https://api.example.com", "token", "owner", "repo")
         assert result == 5
 
-    @patch("devx.ci.discover_runners.query_runners", return_value=0)
+    @patch("devx.molecule.discover_runners.query_runners", return_value=0)
     @patch.dict("os.environ", {"MOLECULE_RUNNERS": "4"})
     def test_falls_back_to_env_var(self, mock_query: MagicMock) -> None:
         result = get_runner_count("https://api.example.com", "token", "owner", "repo")
         assert result == 4
 
-    @patch("devx.ci.discover_runners.query_runners", return_value=0)
+    @patch("devx.molecule.discover_runners.query_runners", return_value=0)
     @patch.dict("os.environ", {"MOLECULE_RUNNERS": "invalid"})
     def test_falls_back_to_default_on_invalid_env(self, mock_query: MagicMock) -> None:
         result = get_runner_count("https://api.example.com", "token", "owner", "repo")
         assert result == DEFAULT_MAX_RUNNERS
 
-    @patch("devx.ci.discover_runners.query_runners", return_value=0)
+    @patch("devx.molecule.discover_runners.query_runners", return_value=0)
     @patch.dict("os.environ", {}, clear=True)
     def test_falls_back_to_default_when_no_env(self, mock_query: MagicMock) -> None:
         result = get_runner_count("https://api.example.com", "token", "owner", "repo")
         assert result == DEFAULT_MAX_RUNNERS
 
-    @patch("devx.ci.discover_runners.query_runners", return_value=0)
+    @patch("devx.molecule.discover_runners.query_runners", return_value=0)
     @patch.dict("os.environ", {"MOLECULE_RUNNERS": "0"})
     def test_env_var_zero_falls_back_to_default(self, mock_query: MagicMock) -> None:
         """MOLECULE_RUNNERS=0 is invalid, falls back to default."""
         result = get_runner_count("https://api.example.com", "token", "owner", "repo")
         assert result == DEFAULT_MAX_RUNNERS
 
-    @patch("devx.ci.discover_runners.query_runners", return_value=0)
+    @patch("devx.molecule.discover_runners.query_runners", return_value=0)
     @patch.dict("os.environ", {}, clear=True)
     def test_no_token_uses_env_var(self, mock_query: MagicMock) -> None:
         """When no token, skips API and uses env/default."""
@@ -192,7 +197,7 @@ class TestGetRunnerCount:
 
 
 class TestMain:
-    @patch("devx.ci.discover_runners.get_runner_count", return_value=3)
+    @patch("devx.molecule.discover_runners.get_runner_count", return_value=3)
     def test_default_output(self, mock_count: MagicMock) -> None:
         runner = CliRunner()
         result = runner.invoke(main, [])
@@ -200,28 +205,28 @@ class TestMain:
         assert "count=3" in result.output
         assert 'indices=["1", "2", "3"]' in result.output
 
-    @patch("devx.ci.discover_runners.get_runner_count", return_value=5)
+    @patch("devx.molecule.discover_runners.get_runner_count", return_value=5)
     def test_count_only(self, mock_count: MagicMock) -> None:
         runner = CliRunner()
         result = runner.invoke(main, ["--count"])
         assert result.exit_code == 0
         assert result.output.strip() == "5"
 
-    @patch("devx.ci.discover_runners.get_runner_count", return_value=4)
+    @patch("devx.molecule.discover_runners.get_runner_count", return_value=4)
     def test_indices_only(self, mock_count: MagicMock) -> None:
         runner = CliRunner()
         result = runner.invoke(main, ["--indices"])
         assert result.exit_code == 0
         assert json.loads(result.output.strip()) == ["1", "2", "3", "4"]
 
-    @patch("devx.ci.discover_runners.get_runner_count", return_value=1)
+    @patch("devx.molecule.discover_runners.get_runner_count", return_value=1)
     def test_single_runner(self, mock_count: MagicMock) -> None:
         runner = CliRunner()
         result = runner.invoke(main, ["--indices"])
         assert result.exit_code == 0
         assert json.loads(result.output.strip()) == ["1"]
 
-    @patch("devx.ci.discover_runners.get_runner_count", return_value=3)
+    @patch("devx.molecule.discover_runners.get_runner_count", return_value=3)
     def test_github_output(self, mock_count: MagicMock, tmp_path: Path, monkeypatch: pytest.MonkeyPatch) -> None:
         gh_file = tmp_path / "output.txt"
         monkeypatch.setenv("GITHUB_OUTPUT", str(gh_file))
@@ -232,14 +237,14 @@ class TestMain:
         assert "runner-count=3" in content
         assert "runner-indices=" in content
 
-    @patch("devx.ci.discover_runners.get_runner_count", return_value=3)
+    @patch("devx.molecule.discover_runners.get_runner_count", return_value=3)
     def test_github_output_no_env(self, mock_count: MagicMock, monkeypatch: pytest.MonkeyPatch) -> None:
         monkeypatch.delenv("GITHUB_OUTPUT", raising=False)
         runner = CliRunner()
         result = runner.invoke(main, ["--github-output"])
         assert result.exit_code != 0
 
-    @patch("devx.ci.discover_runners.get_runner_count", return_value=2)
+    @patch("devx.molecule.discover_runners.get_runner_count", return_value=2)
     def test_explicit_owner_and_repo(self, mock_count: MagicMock) -> None:
         """When --owner and --repo are provided, env vars are not used."""
         runner = CliRunner()
@@ -251,8 +256,8 @@ class TestMain:
         assert "myorg" in args
         assert "myrepo" in args
 
-    @patch("devx.ci.discover_runners.get_ci_token", side_effect=click.ClickException("no token"))
-    @patch("devx.ci.discover_runners.get_runner_count", return_value=3)
+    @patch("devx.molecule.discover_runners.get_ci_token", side_effect=click.ClickException("no token"))
+    @patch("devx.molecule.discover_runners.get_runner_count", return_value=3)
     def test_missing_token_runs_without_api(self, mock_count: MagicMock, mock_token: MagicMock) -> None:
         """When no token is available, runner discovery falls back to env/default."""
         runner = CliRunner()
@@ -261,3 +266,29 @@ class TestMain:
         assert result.output.strip() == "3"
         args, _ = mock_count.call_args
         assert args[1] is None  # token passed as None when missing
+
+
+class TestDeprecationWrapper:
+    def test_re_exports_canonical_symbols(self) -> None:
+        """The wrapper re-exports the canonical implementation's symbols."""
+        from devx.ci import discover_runners as ci_mod
+        from devx.molecule import discover_runners as mol_mod
+
+        assert ci_mod.query_runners is mol_mod.query_runners
+        assert ci_mod.get_runner_count is mol_mod.get_runner_count
+        assert ci_mod.generate_indices is mol_mod.generate_indices
+        assert ci_mod.main is mol_mod.main
+        assert ci_mod.DEFAULT_MAX_RUNNERS is mol_mod.DEFAULT_MAX_RUNNERS
+
+    def test_emit_deprecation_warning(self) -> None:
+        """_emit_deprecation_warning issues a DeprecationWarning."""
+        import warnings
+
+        from devx.ci.discover_runners import _emit_deprecation_warning
+
+        with warnings.catch_warnings(record=True) as caught:
+            warnings.simplefilter("always")
+            _emit_deprecation_warning()
+        assert len(caught) == 1
+        assert issubclass(caught[0].category, DeprecationWarning)
+        assert "deprecated" in str(caught[0].message)

tests/unit/test_distribute_molecule.py

@@ -311,6 +311,61 @@ class TestDiscoverMultiRole:
         with pytest.raises(click.ClickException):
             discover_multi_role_scenarios()
 
+    def test_include_roles_filters_to_subset(self, tmp_path: Path) -> None:
+        roles = tmp_path / "roles"
+        for scenario in ["default"]:
+            (roles / "docker_base" / "molecule" / scenario).mkdir(parents=True)
+            (roles / "crowdsec" / "molecule" / scenario).mkdir(parents=True)
+            (roles / "app_container" / "molecule" / scenario).mkdir(parents=True)
+        result = discover_multi_role_scenarios(roles, include_roles=["docker_base", "crowdsec"])
+        assert ("docker_base", "default") in result
+        assert ("crowdsec", "default") in result
+        assert ("app_container", "default") not in result
+        assert len(result) == 2
+
+    def test_include_roles_case_insensitive(self, tmp_path: Path) -> None:
+        roles = tmp_path / "roles"
+        (roles / "Docker_Base" / "molecule" / "default").mkdir(parents=True)
+        (roles / "other" / "molecule" / "default").mkdir(parents=True)
+        result = discover_multi_role_scenarios(roles, include_roles=["docker_base"])
+        assert ("Docker_Base", "default") in result
+        assert len(result) == 1
+
+    def test_exclude_roles_skips_subset(self, tmp_path: Path) -> None:
+        roles = tmp_path / "roles"
+        for scenario in ["default"]:
+            (roles / "docker_base" / "molecule" / scenario).mkdir(parents=True)
+            (roles / "crowdsec" / "molecule" / scenario).mkdir(parents=True)
+            (roles / "app_container" / "molecule" / scenario).mkdir(parents=True)
+        result = discover_multi_role_scenarios(roles, exclude_roles=["docker_base", "crowdsec"])
+        assert ("docker_base", "default") not in result
+        assert ("crowdsec", "default") not in result
+        assert ("app_container", "default") in result
+        assert len(result) == 1
+
+    def test_exclude_roles_case_insensitive(self, tmp_path: Path) -> None:
+        roles = tmp_path / "roles"
+        (roles / "Docker_Base" / "molecule" / "default").mkdir(parents=True)
+        (roles / "other" / "molecule" / "default").mkdir(parents=True)
+        result = discover_multi_role_scenarios(roles, exclude_roles=["docker_base"])
+        assert ("Docker_Base", "default") not in result
+        assert ("other", "default") in result
+        assert len(result) == 1
+
+    def test_include_and_exclude_combined(self, tmp_path: Path) -> None:
+        roles = tmp_path / "roles"
+        for scenario in ["default"]:
+            (roles / "docker_base" / "molecule" / scenario).mkdir(parents=True)
+            (roles / "crowdsec" / "molecule" / scenario).mkdir(parents=True)
+            (roles / "app_container" / "molecule" / scenario).mkdir(parents=True)
+        result = discover_multi_role_scenarios(
+            roles, include_roles=["docker_base", "crowdsec", "app_container"], exclude_roles=["crowdsec"]
+        )
+        assert ("docker_base", "default") in result
+        assert ("crowdsec", "default") not in result
+        assert ("app_container", "default") in result
+        assert len(result) == 2
+
     def test_default_roles_root_constant(self) -> None:
         assert Path("ansible/roles") == DEFAULT_ROLES_ROOT
 

tests/unit/test_i18n.py

@@ -0,0 +1,100 @@
+"""Unit tests for devx.i18n."""
+
+from __future__ import annotations
+
+import pytest
+
+import devx.i18n as i18n_mod
+from devx.i18n import _, configure_i18n
+
+
+class TestTranslate:
+    def test_returns_english_by_default(self) -> None:
+        with pytest.MonkeyPatch().context() as mp:
+            mp.delenv("DEVX_LANG", raising=False)
+            assert _("Running tests") == "Running tests"
+
+    def test_returns_key_when_missing(self) -> None:
+        with pytest.MonkeyPatch().context() as mp:
+            mp.delenv("DEVX_LANG", raising=False)
+            assert _("nonexistent.key.xyz") == "nonexistent.key.xyz"
+
+    def test_formats_kwargs(self) -> None:
+        # Find a key with format placeholders
+        for key, translations in i18n_mod.TRANSLATIONS.items():
+            en = translations.get("en", "")
+            if "{" in en:
+                with pytest.MonkeyPatch().context() as mp:
+                    mp.delenv("DEVX_LANG", raising=False)
+                    result = _(key, **dict.fromkeys(_extract_format_keys(en), "x"))
+                    assert "{" not in result
+                return
+        pytest.skip("No key with format placeholders found")
+
+    def test_invalid_lang_falls_back_to_english(self) -> None:
+        with pytest.MonkeyPatch().context() as mp:
+            mp.setenv("DEVX_LANG", "fr")
+            assert _("Running tests") == "Running tests"
+
+    def test_bulgarian_translation(self) -> None:
+        with pytest.MonkeyPatch().context() as mp:
+            mp.setenv("DEVX_LANG", "bg")
+            # Find a key that has a Bulgarian translation
+            for key, translations in i18n_mod.TRANSLATIONS.items():
+                if "bg" in translations:
+                    result = _(key)
+                    assert result == translations["bg"]
+                    return
+        pytest.skip("No Bulgarian translation found")
+
+
+class TestConfigureI18n:
+    def test_custom_lang_env_var(self) -> None:
+        configure_i18n(lang_env_var="GRM_LANG")
+        try:
+            with pytest.MonkeyPatch().context() as mp:
+                mp.setenv("GRM_LANG", "bg")
+                mp.delenv("DEVX_LANG", raising=False)
+                # Find a key with Bulgarian translation
+                for key, translations in i18n_mod.TRANSLATIONS.items():
+                    if "bg" in translations:
+                        assert _(key) == translations["bg"]
+                        return
+            pytest.skip("No Bulgarian translation found")
+        finally:
+            configure_i18n()  # Reset to defaults
+
+    def test_custom_translations_path_env_var(self, tmp_path) -> None:
+        custom_translations = {"custom.key": {"en": "Custom Value", "bg": "Персонализирано"}}
+        custom_file = tmp_path / "custom.json"
+        custom_file.write_text(__import__("json").dumps(custom_translations))
+
+        configure_i18n(translations_path_env_var="GRM_TRANSLATIONS_PATH")
+        try:
+            # Use i18n_mod.TRANSLATIONS (not a stale import) — other tests
+            # may call importlib.reload(devx.i18n), replacing the dict object.
+            translations = i18n_mod.TRANSLATIONS
+            original = dict(translations)
+            translations.update(custom_translations)
+            try:
+                with pytest.MonkeyPatch().context() as mp:
+                    mp.setenv("GRM_TRANSLATIONS_PATH", str(custom_file))
+                    assert _("custom.key") == "Custom Value"
+            finally:
+                translations.clear()
+                translations.update(original)
+        finally:
+            configure_i18n()  # Reset to defaults
+
+    def test_reset_to_defaults(self) -> None:
+        configure_i18n(lang_env_var="GRM_LANG")
+        configure_i18n()  # Reset
+        assert i18n_mod._lang_env_var == "DEVX_LANG"
+        assert i18n_mod._translations_path_env_var == "DEVX_TRANSLATIONS_PATH"
+
+
+def _extract_format_keys(template: str) -> list[str]:
+    """Extract {key} format placeholders from a template string."""
+    import re
+
+    return re.findall(r"\{(\w+)\}", template)

tests/unit/test_install_tools.py

@@ -1,6 +1,7 @@
 from __future__ import annotations
 
 import platform
+import urllib.error
 from pathlib import Path
 from unittest.mock import patch
 
@@ -68,6 +69,67 @@ class TestDownload:
         mock_urlopen.assert_called_once()
         assert dest.read_bytes() == b"data"
 
+    def test_download_retries_on_transient_error(self, tmp_path: Path) -> None:
+        """Download retries on URLError then succeeds."""
+        dest = tmp_path / "file.bin"
+        call_count = [0]
+
+        class _FakeResponse:
+            def __init__(self) -> None:
+                self._sent = False
+
+            def __enter__(self) -> _FakeResponse:
+                return self
+
+            def __exit__(self, *args: object) -> None:
+                pass
+
+            def read(self, n: int = -1) -> bytes:
+                if self._sent:
+                    return b""
+                self._sent = True
+                return b"data"
+
+        def _flaky_urlopen(url: str, timeout: int = 60):
+            call_count[0] += 1
+            if call_count[0] < 2:
+                raise urllib.error.URLError("Remote end closed connection")
+            return _FakeResponse()
+
+        with patch("urllib.request.urlopen", side_effect=_flaky_urlopen):
+            install_tools._download("https://example.com/file", dest, _sleep=lambda _: None)
+        assert call_count[0] == 2
+        assert dest.read_bytes() == b"data"
+
+    def test_download_fails_after_max_retries(self, tmp_path: Path) -> None:
+        """Download raises after MAX_DOWNLOAD_RETRIES attempts."""
+        dest = tmp_path / "file.bin"
+        call_count = [0]
+
+        def _always_fail(url: str, timeout: int = 60):
+            call_count[0] += 1
+            raise urllib.error.URLError("Remote end closed connection")
+
+        with patch("urllib.request.urlopen", side_effect=_always_fail):
+            with pytest.raises(urllib.error.URLError):
+                install_tools._download("https://example.com/file", dest, _sleep=lambda _: None)
+        assert call_count[0] == install_tools.MAX_DOWNLOAD_RETRIES
+        assert not dest.exists()
+
+    def test_download_no_retry_on_non_transient_error(self, tmp_path: Path) -> None:
+        """Download does not retry on non-network errors (e.g. ValueError)."""
+        dest = tmp_path / "file.bin"
+        call_count = [0]
+
+        def _fail_with_value_error(url: str, timeout: int = 60):
+            call_count[0] += 1
+            raise ValueError("not a network error")
+
+        with patch("urllib.request.urlopen", side_effect=_fail_with_value_error):
+            with pytest.raises(ValueError):
+                install_tools._download("https://example.com/file", dest, _sleep=lambda _: None)
+        assert call_count[0] == 1
+
 
 class TestDownloadBinary:
     def test_download(self, tmp_path: Path) -> None:
@@ -233,6 +295,33 @@ class TestInstallTea:
                         assert install_tools.install_tea() is True
         assert (tmp_path / "tea").exists()
 
+    def test_install_fallback_to_second_url(self, tmp_path: Path) -> None:
+        """First URL fails (403), second URL succeeds."""
+        call_count = [0]
+
+        def _download_side_effect(url: str, dest: Path) -> None:
+            call_count[0] += 1
+            if call_count[0] == 1:
+                raise OSError("HTTP Error 403: Forbidden")
+            Path(dest).write_bytes(b"binary")
+
+        with patch.object(install_tools, "_is_installed", return_value=False):
+            with patch.object(install_tools, "TARGET_DIR", tmp_path):
+                with patch.object(platform, "machine", return_value="x86_64"):
+                    with patch.object(install_tools, "_download", side_effect=_download_side_effect):
+                        assert install_tools.install_tea() is True
+        assert (tmp_path / "tea").exists()
+        assert call_count[0] == 2
+
+    def test_install_all_urls_fail(self, tmp_path: Path) -> None:
+        """All URLs fail — should raise ClickException."""
+        with patch.object(install_tools, "_is_installed", return_value=False):
+            with patch.object(install_tools, "TARGET_DIR", tmp_path):
+                with patch.object(platform, "machine", return_value="x86_64"):
+                    with patch.object(install_tools, "_download", side_effect=OSError("403 Forbidden")):
+                        with pytest.raises(ClickException, match="Failed to download tea"):
+                            install_tools.install_tea()
+
 
 class TestInstallHadolint:
     def test_already_installed(self) -> None:

tests/unit/test_molecule_changed.py

@@ -0,0 +1,192 @@
+"""Unit tests for devx.molecule.molecule_changed.
+
+Verifies that the script correctly detects changed roles and maps
+them to make targets.
+"""
+
+from __future__ import annotations
+
+from unittest.mock import patch
+
+from click.testing import CliRunner
+
+from devx.molecule.molecule_changed import (
+    detect_changed_roles,
+    get_changed_files,
+    main,
+    roles_to_targets,
+)
+
+
+def test_detect_role_change():
+    """A file in ansible/roles/<role>/ maps to that role."""
+    files = ["ansible/roles/docker_base/tasks/main.yml"]
+    roles = detect_changed_roles(files)
+    assert "docker_base" in roles
+
+
+def test_detect_playbook_change():
+    """A playbook change maps to its included roles."""
+    files = ["ansible/playbooks/deploy-observability.yml"]
+    roles = detect_changed_roles(files)
+    assert "observability" in roles
+    assert "docker_base" in roles
+    assert "zitadel" in roles
+
+
+def test_detect_shared_infra_triggers_all():
+    """ansible.cfg change triggers all roles."""
+    files = ["ansible/ansible.cfg"]
+    roles = detect_changed_roles(files)
+    assert len(roles) == 10  # all roles
+
+
+def test_detect_no_ansible_changes():
+    """Non-Ansible files don't trigger any roles."""
+    files = ["scripts/molecule_changed.py", "Makefile"]
+    roles = detect_changed_roles(files)
+    assert len(roles) == 0
+
+
+def test_roles_to_targets():
+    """Role names map to make targets."""
+    targets = roles_to_targets({"docker_base", "zitadel"})
+    assert "molecule-docker-base" in targets
+    assert "molecule-zitadel" in targets
+
+
+def test_roles_to_targets_unknown_role():
+    """Unknown roles are silently skipped."""
+    targets = roles_to_targets({"docker_base", "unknown_role"})
+    assert targets == ["molecule-docker-base"]
+
+
+def test_main_no_changes():
+    """When no files changed, outputs message to stderr."""
+    with patch("devx.molecule.molecule_changed.get_changed_files", return_value=[]):
+        runner = CliRunner()
+        result = runner.invoke(main, ["--print-targets"])
+        assert result.exit_code == 0
+        assert "No changed files" in result.output
+
+
+def test_main_print_targets():
+    """--print-targets outputs make targets."""
+    with patch(
+        "devx.molecule.molecule_changed.get_changed_files",
+        return_value=["ansible/roles/docker_base/tasks/main.yml"],
+    ):
+        runner = CliRunner()
+        result = runner.invoke(main, ["--print-targets"])
+        assert result.exit_code == 0
+        assert "molecule-docker-base" in result.output
+
+
+def test_main_print_roles():
+    """--print-roles outputs role names."""
+    with patch(
+        "devx.molecule.molecule_changed.get_changed_files",
+        return_value=["ansible/roles/zitadel/tasks/main.yml"],
+    ):
+        runner = CliRunner()
+        result = runner.invoke(main, ["--print-roles"])
+        assert result.exit_code == 0
+        assert "zitadel" in result.output
+
+
+def test_main_no_ansible_changes():
+    """When only non-Ansible files changed, outputs no scenarios message."""
+    with patch(
+        "devx.molecule.molecule_changed.get_changed_files",
+        return_value=["scripts/molecule_changed.py"],
+    ):
+        runner = CliRunner()
+        result = runner.invoke(main, ["--print-targets"])
+        assert result.exit_code == 0
+        assert "No molecule scenarios" in result.output
+
+
+def test_get_changed_files_with_mock():
+    """get_changed_files returns files from git diff."""
+    with patch("devx.molecule.molecule_changed._run_git", return_value="file1\nfile2\n"):
+        files = get_changed_files("origin/master")
+        assert files == ["file1", "file2"]
+
+
+def test_get_changed_files_falls_back_to_master():
+    """When base ref has no diff, falls back to master."""
+    calls: list[list[str]] = []
+
+    def mock_git(args):
+        calls.append(args)
+        # First call (origin/master) returns empty, second (master) returns files
+        if "origin/master...HEAD" in args[2]:
+            return ""
+        return "ansible/roles/docker_base/tasks/main.yml\n"
+
+    with patch("devx.molecule.molecule_changed._run_git", side_effect=mock_git):
+        files = get_changed_files("origin/master")
+        assert files == ["ansible/roles/docker_base/tasks/main.yml"]
+        assert len(calls) == 2
+
+
+def test_get_changed_files_empty():
+    """When no changes in either ref, returns empty list."""
+    with patch("devx.molecule.molecule_changed._run_git", return_value=""):
+        files = get_changed_files("origin/master")
+        assert files == []
+
+
+def test_detect_molecule_shared_path():
+    """ansible/molecule/ change triggers all roles."""
+    files = ["ansible/molecule/Dockerfile"]
+    roles = detect_changed_roles(files)
+    assert len(roles) == 10
+
+
+def test_detect_requirements_yml_triggers_all():
+    """ansible/requirements.yml change triggers all roles."""
+    files = ["ansible/requirements.yml"]
+    roles = detect_changed_roles(files)
+    assert len(roles) == 10
+
+
+def test_detect_configure_oidc_playbook():
+    """configure-oidc.yml maps to sso_config and app_container."""
+    files = ["ansible/playbooks/configure-oidc.yml"]
+    roles = detect_changed_roles(files)
+    assert "sso_config" in roles
+    assert "app_container" in roles
+
+
+def test_detect_prepare_vms_playbook():
+    """prepare-vms.yml maps to all base roles."""
+    files = ["ansible/playbooks/prepare-vms.yml"]
+    roles = detect_changed_roles(files)
+    assert "docker_base" in roles
+    assert "app_hardening" in roles
+    assert "storage" in roles
+    assert "disk_cleanup" in roles
+    assert "crowdsec" in roles
+
+
+def test_detect_deploy_customer_playbook():
+    """deploy-customer.yml maps to its roles."""
+    files = ["ansible/playbooks/deploy-customer.yml"]
+    roles = detect_changed_roles(files)
+    assert "app_container" in roles
+    assert "docker_base" in roles
+    assert "app_hardening" in roles
+    assert "sso_config" in roles
+
+
+def test_main_default_base():
+    """main() with no --base uses origin/master."""
+    with patch(
+        "devx.molecule.molecule_changed.get_changed_files",
+        return_value=["ansible/roles/zitadel/tasks/main.yml"],
+    ) as mock:
+        runner = CliRunner()
+        result = runner.invoke(main, ["--print-roles"])
+        assert result.exit_code == 0
+        mock.assert_called_once_with("origin/master")

tests/unit/test_setup.py

@@ -114,6 +114,49 @@ class TestInstallAnsibleCollections:
         _install_ansible_collections(".venv/bin")
         mock_run.assert_not_called()
 
+    @patch("tenacity.nap.time.sleep")
+    @patch("devx.tools.setup.shutil.which", return_value="/usr/local/bin/ansible-galaxy")
+    @patch("devx.tools.setup._run")
+    def test_retries_on_transient_failure(
+        self, mock_run: MagicMock, mock_which: MagicMock, mock_sleep: MagicMock, tmp_path: Path
+    ) -> None:
+        """ansible-galaxy install should retry on transient network errors."""
+        import subprocess as _subprocess
+
+        req = tmp_path / "ansible" / "requirements.yml"
+        req.parent.mkdir(parents=True)
+        req.write_text("collections: []")
+        # First call fails (timeout), second succeeds
+        mock_run.side_effect = [
+            _subprocess.CalledProcessError(1, ["ansible-galaxy", "collection", "install"]),
+            None,
+        ]
+        with patch("devx.tools.setup.Path") as mock_path:
+            mock_path.return_value.exists.return_value = True
+            mock_path.return_value.__str__ = lambda _: str(req)
+            _install_ansible_collections(".venv/bin")
+        assert mock_run.call_count == 2
+
+    @patch("tenacity.nap.time.sleep")
+    @patch("devx.tools.setup.shutil.which", return_value="/usr/local/bin/ansible-galaxy")
+    @patch("devx.tools.setup._run")
+    def test_exhausts_retries_then_raises(
+        self, mock_run: MagicMock, mock_which: MagicMock, mock_sleep: MagicMock, tmp_path: Path
+    ) -> None:
+        """After 3 attempts, the error should propagate."""
+        import subprocess as _subprocess
+
+        req = tmp_path / "ansible" / "requirements.yml"
+        req.parent.mkdir(parents=True)
+        req.write_text("collections: []")
+        mock_run.side_effect = _subprocess.CalledProcessError(1, ["ansible-galaxy"])
+        with patch("devx.tools.setup.Path") as mock_path:
+            mock_path.return_value.exists.return_value = True
+            mock_path.return_value.__str__ = lambda _: str(req)
+            with pytest.raises(_subprocess.CalledProcessError):
+                _install_ansible_collections(".venv/bin")
+        assert mock_run.call_count == 3
+
 
 class TestConfigureTeaLogin:
     @patch("devx.tools.setup.shutil.which", return_value=None)

tests/unit/test_setup_image.py

@@ -52,6 +52,7 @@ class TestInstallInImage:
         mock_run.assert_called_once()
         cmd = mock_run.call_args[0][0]
         assert "--no-cache-dir" in cmd
+        assert "--no-deps" in cmd
         assert "-e" in cmd
         assert "." in cmd
         # No extras → spec is "."

tests/unit/test_tools_check_alert_rules.py

@@ -0,0 +1,103 @@
+"""Unit tests for devx.tools.check_alert_rules."""
+
+from __future__ import annotations
+
+from pathlib import Path
+from unittest.mock import MagicMock, patch
+
+from click.testing import CliRunner
+
+from devx.tools.check_alert_rules import main
+
+
+class TestMain:
+    def test_skip_when_promtool_not_found(self, tmp_path: Path):
+        """Should exit 0 and print skip message when promtool is not on PATH."""
+        with patch("shutil.which", return_value=None):
+            runner = CliRunner()
+            result = runner.invoke(main, ["--template-path", str(tmp_path)])
+        assert result.exit_code == 0
+        assert "promtool not found" in result.output
+
+    def test_validates_rules_successfully(self, tmp_path: Path):
+        """Should exit 0 when promtool reports SUCCESS."""
+        (tmp_path / "alert-rules.yml.j2").write_text("groups: []")
+        mock_result = MagicMock()
+        mock_result.returncode = 0
+        mock_result.stdout = "Checking /tmp/test.yml\n  SUCCESS: 60 rules found\n"
+        mock_result.stderr = ""
+        with patch("shutil.which", return_value="/usr/bin/promtool"):
+            with patch("subprocess.run", return_value=mock_result):
+                runner = CliRunner()
+                result = runner.invoke(main, ["--template-path", str(tmp_path)])
+        assert result.exit_code == 0
+
+    def test_fails_on_promtool_error(self, tmp_path: Path):
+        """Should exit non-zero when promtool reports an error."""
+        (tmp_path / "alert-rules.yml.j2").write_text("groups: []")
+        mock_result = MagicMock()
+        mock_result.returncode = 1
+        mock_result.stdout = ""
+        mock_result.stderr = "Error: invalid template function 'default'\n"
+        with patch("shutil.which", return_value="/usr/bin/promtool"):
+            with patch("subprocess.run", return_value=mock_result):
+                runner = CliRunner()
+                result = runner.invoke(main, ["--template-path", str(tmp_path)])
+        assert result.exit_code != 0
+
+    def test_uses_correct_template_path(self, tmp_path: Path):
+        """Should render the specified template from the given path."""
+        (tmp_path / "alert-rules.yml.j2").write_text("groups: []")
+        captured_args = []
+
+        def fake_run(args, **kwargs):
+            captured_args.append(args)
+            mock = MagicMock()
+            mock.returncode = 0
+            mock.stdout = "SUCCESS"
+            mock.stderr = ""
+            return mock
+
+        with patch("shutil.which", return_value="/usr/bin/promtool"):
+            with patch("subprocess.run", side_effect=fake_run):
+                runner = CliRunner()
+                runner.invoke(main, ["--template-path", str(tmp_path)])
+        assert captured_args[0][0] == "promtool"
+        assert captured_args[0][1] == "check"
+        assert captured_args[0][2] == "rules"
+
+    def test_custom_template_name(self, tmp_path: Path):
+        """Should render a custom template name."""
+        (tmp_path / "custom-rules.yml.j2").write_text("groups: []")
+        mock_result = MagicMock()
+        mock_result.returncode = 0
+        mock_result.stdout = "SUCCESS"
+        mock_result.stderr = ""
+        with patch("shutil.which", return_value="/usr/bin/promtool"):
+            with patch("subprocess.run", return_value=mock_result):
+                runner = CliRunner()
+                result = runner.invoke(
+                    main, ["--template-path", str(tmp_path), "--template-name", "custom-rules.yml.j2"]
+                )
+        assert result.exit_code == 0
+
+    def test_template_vars_passed(self, tmp_path: Path):
+        """Should pass template variables to the render call."""
+        (tmp_path / "alert-rules.yml.j2").write_text("grafana: {{ grafana_base_url }}\ngroups: []")
+        mock_result = MagicMock()
+        mock_result.returncode = 0
+        mock_result.stdout = "SUCCESS"
+        mock_result.stderr = ""
+        with patch("shutil.which", return_value="/usr/bin/promtool"):
+            with patch("subprocess.run", return_value=mock_result):
+                runner = CliRunner()
+                result = runner.invoke(
+                    main,
+                    [
+                        "--template-path",
+                        str(tmp_path),
+                        "--var",
+                        "grafana_base_url=https://grafana.test.example.com",
+                    ],
+                )
+        assert result.exit_code == 0

tests/unit/test_tools_check_ansible_no_log.py

@@ -0,0 +1,367 @@
+"""Unit tests for devx.tools.check_ansible_no_log."""
+
+from __future__ import annotations
+
+from pathlib import Path
+
+from click.testing import CliRunner
+
+from devx.tools.check_ansible_no_log import _check_task, check_directory, main
+
+
+def _make_task(name: str, action: str, value: str, **extra: object) -> dict:
+    """Build a minimal task dict for testing."""
+    task: dict = {"name": name, action: value}
+    task.update(extra)
+    return task
+
+
+class TestCheckTask:
+    def test_task_with_secret_and_no_log_passes(self):
+        task = _make_task(
+            "Safe task",
+            "ansible.builtin.shell",
+            "echo {{ _secrets.mattermost_admin_password }}",
+            no_log=True,
+        )
+        assert _check_task(task, Path("test.yml"), 1) == []
+
+    def test_task_with_secret_and_no_no_log_fails(self):
+        task = _make_task(
+            "Unsafe task",
+            "ansible.builtin.shell",
+            "echo {{ _secrets.mattermost_admin_password }}",
+        )
+        violations = _check_task(task, Path("test.yml"), 1)
+        assert len(violations) == 1
+        assert "no_log" in violations[0]
+
+    def test_task_without_secret_passes(self):
+        task = _make_task(
+            "Normal task",
+            "ansible.builtin.shell",
+            "echo hello world",
+        )
+        assert _check_task(task, Path("test.yml"), 1) == []
+
+    def test_task_with_jinja_no_log_passes(self):
+        task = _make_task(
+            "Safe task with jinja no_log",
+            "ansible.builtin.shell",
+            "echo {{ _secrets.mattermost_admin_password }}",
+            no_log="{{ not (debug_mode | default(false) | bool) }}",
+        )
+        assert _check_task(task, Path("test.yml"), 1) == []
+
+    def test_task_with_password_in_name_only_no_false_positive(self):
+        """Task name contains 'password' but no secret value — should not flag."""
+        task = _make_task(
+            "Configure passwdqc in common-password",
+            "ansible.builtin.lineinfile",
+            "password required pam_passwdqc.so min=disabled,disabled,16,12,8",
+        )
+        assert _check_task(task, Path("test.yml"), 1) == []
+
+    def test_task_with_password_in_module_param_no_false_positive(self):
+        """Module param named 'password' but value is a literal — no Jinja."""
+        task = {
+            "name": "Set user password",
+            "ansible.builtin.user": {
+                "name": "deploy",
+                "password_lock": True,
+            },
+        }
+        assert _check_task(task, Path("test.yml"), 1) == []
+
+    def test_task_with_vault_password_variable_fails(self):
+        task = _make_task(
+            "Unsafe vault task",
+            "ansible.builtin.shell",
+            "echo {{ vault_zitadel_db_password }}",
+        )
+        violations = _check_task(task, Path("test.yml"), 1)
+        assert len(violations) == 1
+
+    def test_task_with_nested_dict_secret_fails(self):
+        """Secrets in nested dict values (e.g. set_fact) should be caught."""
+        task = {
+            "name": "Set secrets",
+            "ansible.builtin.set_fact": {
+                "db_password": "{{ vault_db_password }}",
+                "api_key": "{{ vault_api_key }}",
+            },
+        }
+        violations = _check_task(task, Path("test.yml"), 1)
+        assert len(violations) == 1
+
+    def test_task_with_no_log_none_passes(self):
+        """no_log: None should count as not set (flagged)."""
+        task = _make_task(
+            "Unsafe task",
+            "ansible.builtin.shell",
+            "echo {{ _secrets.db_password }}",
+            no_log=None,
+        )
+        violations = _check_task(task, Path("test.yml"), 1)
+        assert len(violations) == 1
+
+    def test_task_with_secret_in_list_value_fails(self):
+        """Secrets inside list values should be caught."""
+        task = {
+            "name": "Task with list secret",
+            "ansible.builtin.set_fact": {
+                "items": ["{{ _secrets.api_key }}", "normal_value"],
+            },
+        }
+        violations = _check_task(task, Path("test.yml"), 1)
+        assert len(violations) == 1
+
+    def test_task_with_api_key_secret_fails(self):
+        """api_key in Jinja expression should be caught."""
+        task = _make_task(
+            "Unsafe task",
+            "ansible.builtin.shell",
+            "echo {{ my_api_key }}",
+        )
+        violations = _check_task(task, Path("test.yml"), 1)
+        assert len(violations) == 1
+
+    def test_task_with_secret_in_jinja_fails(self):
+        """_secret in Jinja expression should be caught."""
+        task = _make_task(
+            "Unsafe task",
+            "ansible.builtin.shell",
+            "echo {{ my_secret }}",
+        )
+        violations = _check_task(task, Path("test.yml"), 1)
+        assert len(violations) == 1
+
+    def test_task_with_access_token_fails(self):
+        """access_token in Jinja expression should be caught."""
+        task = _make_task(
+            "Unsafe task",
+            "ansible.builtin.shell",
+            "echo {{ my_access_token }}",
+        )
+        violations = _check_task(task, Path("test.yml"), 1)
+        assert len(violations) == 1
+
+    def test_task_with_non_secret_non_dict_non_list_value(self):
+        """Non-str, non-dict, non-list values (e.g. int) should not crash."""
+        task = _make_task(
+            "Task with int",
+            "ansible.builtin.shell",
+            "echo hello",
+            some_int=42,
+        )
+        assert _check_task(task, Path("test.yml"), 1) == []
+
+
+class TestCheckDirectory:
+    def test_clean_directory_passes(self, tmp_path: Path):
+        """A directory with no secret-handling tasks should pass."""
+        role_dir = tmp_path / "roles" / "test_role"
+        (role_dir / "tasks").mkdir(parents=True)
+        (role_dir / "tasks" / "main.yml").write_text(
+            "- name: Normal task\n  ansible.builtin.shell: echo hello\n  changed_when: false\n"
+        )
+        assert check_directory(role_dir) == []
+
+    def test_unsafe_task_is_caught(self, tmp_path: Path):
+        """A task with secrets but no no_log should be flagged."""
+        role_dir = tmp_path / "roles" / "test_role"
+        (role_dir / "tasks").mkdir(parents=True)
+        (role_dir / "tasks" / "main.yml").write_text(
+            "- name: Unsafe task\n  ansible.builtin.shell: echo {{ _secrets.db_password }}\n  changed_when: false\n"
+        )
+        violations = check_directory(role_dir)
+        assert len(violations) == 1
+        assert "Unsafe task" in violations[0]
+
+    def test_molecule_files_are_skipped(self, tmp_path: Path):
+        """Molecule test files should not be scanned."""
+        role_dir = tmp_path / "roles" / "test_role"
+        mol_dir = role_dir / "molecule" / "default" / "tasks"
+        mol_dir.mkdir(parents=True)
+        (mol_dir / "main.yml").write_text(
+            "- name: Unsafe task in molecule\n  ansible.builtin.shell: echo {{ _secrets.db_password }}\n"
+        )
+        assert check_directory(role_dir) == []
+
+    def test_playbook_format_is_parsed(self, tmp_path: Path):
+        """Playbook files (list of plays with 'hosts') should be parsed."""
+        pb_dir = tmp_path / "playbooks"
+        pb_dir.mkdir(parents=True)
+        (pb_dir / "test.yml").write_text(
+            "---\n"
+            "- name: Test play\n"
+            "  hosts: all\n"
+            "  tasks:\n"
+            "    - name: Unsafe task\n"
+            "      ansible.builtin.shell: echo {{ _secrets.db_password }}\n"
+        )
+        violations = check_directory(tmp_path)
+        assert len(violations) == 1
+        assert "Unsafe task" in violations[0]
+
+    def test_invalid_yaml_is_skipped(self, tmp_path: Path):
+        """Invalid YAML files should be skipped, not crash."""
+        role_dir = tmp_path / "roles" / "test_role"
+        (role_dir / "tasks").mkdir(parents=True)
+        (role_dir / "tasks" / "main.yml").write_text("{{ invalid yaml: [")
+        assert check_directory(role_dir) == []
+
+    def test_empty_yaml_doc_is_skipped(self, tmp_path: Path):
+        """Empty YAML documents (None) should be skipped."""
+        role_dir = tmp_path / "roles" / "test_role"
+        (role_dir / "tasks").mkdir(parents=True)
+        (role_dir / "tasks" / "main.yml").write_text("---\n")
+        assert check_directory(role_dir) == []
+
+    def test_non_dict_non_list_doc_is_skipped(self, tmp_path: Path):
+        """YAML docs that are neither dict nor list should be skipped."""
+        role_dir = tmp_path / "roles" / "test_role"
+        (role_dir / "tasks").mkdir(parents=True)
+        (role_dir / "tasks" / "main.yml").write_text("just a string\n")
+        assert check_directory(role_dir) == []
+
+    def test_task_file_with_non_dict_task_skipped(self, tmp_path: Path):
+        """Non-dict items in a task list should be skipped."""
+        role_dir = tmp_path / "roles" / "test_role"
+        (role_dir / "tasks").mkdir(parents=True)
+        (role_dir / "tasks" / "main.yml").write_text(
+            "- just a string\n- name: Safe task\n  ansible.builtin.shell: echo hello\n"
+        )
+        assert check_directory(role_dir) == []
+
+    def test_secret_in_list_value_is_caught(self, tmp_path: Path):
+        """Secrets inside list values should be caught."""
+        role_dir = tmp_path / "roles" / "test_role"
+        (role_dir / "tasks").mkdir(parents=True)
+        (role_dir / "tasks" / "main.yml").write_text(
+            "- name: Task with list secret\n"
+            "  ansible.builtin.set_fact:\n"
+            "    items:\n"
+            '      - "{{ _secrets.api_key }}"\n'
+            "      - normal_value\n"
+        )
+        violations = check_directory(role_dir)
+        assert len(violations) == 1
+
+    def test_single_play_dict_format(self, tmp_path: Path):
+        """A playbook that's a bare dict (not list of plays) should be parsed."""
+        pb_dir = tmp_path / "playbooks"
+        pb_dir.mkdir(parents=True)
+        (pb_dir / "test.yml").write_text(
+            "---\n"
+            "name: Single play\n"
+            "hosts: all\n"
+            "tasks:\n"
+            "  - name: Unsafe task\n"
+            "    ansible.builtin.shell: echo {{ _secrets.db_password }}\n"
+        )
+        violations = check_directory(tmp_path)
+        assert len(violations) == 1
+
+    def test_play_with_non_dict_play_skipped(self, tmp_path: Path):
+        """Non-dict plays in a playbook list should be skipped."""
+        pb_dir = tmp_path / "playbooks"
+        pb_dir.mkdir(parents=True)
+        # First play is valid (makes is_plays=True), second is a non-dict
+        (pb_dir / "test.yml").write_text(
+            "---\n"
+            "- name: Safe play\n"
+            "  hosts: all\n"
+            "  tasks:\n"
+            "    - name: Safe task\n"
+            "      ansible.builtin.shell: echo hello\n"
+            '- "just a string as second play"\n'
+        )
+        assert check_directory(tmp_path) == []
+
+    def test_play_with_non_list_tasks_skipped(self, tmp_path: Path):
+        """Plays where tasks is not a list should be skipped."""
+        pb_dir = tmp_path / "playbooks"
+        pb_dir.mkdir(parents=True)
+        (pb_dir / "test.yml").write_text('---\n- name: Play with bad tasks\n  hosts: all\n  tasks: "not a list"\n')
+        assert check_directory(tmp_path) == []
+
+    def test_play_with_non_dict_task_in_playbook(self, tmp_path: Path):
+        """Non-dict tasks in a playbook should be skipped."""
+        pb_dir = tmp_path / "playbooks"
+        pb_dir.mkdir(parents=True)
+        (pb_dir / "test.yml").write_text(
+            "---\n"
+            "- name: Play\n"
+            "  hosts: all\n"
+            "  tasks:\n"
+            '    - "just a string"\n'
+            "    - name: Safe task\n"
+            "      ansible.builtin.shell: echo hello\n"
+        )
+        assert check_directory(tmp_path) == []
+
+    def test_yaml_file_with_oserror_skipped(self, tmp_path: Path):
+        """YAML files that can't be opened should be skipped."""
+        role_dir = tmp_path / "roles" / "test_role"
+        (role_dir / "tasks").mkdir(parents=True)
+        # Create a file that will cause OSError when opened
+        # (use a directory with .yml extension)
+        bad_file = role_dir / "tasks" / "main.yml"
+        bad_file.mkdir()
+        assert check_directory(role_dir) == []
+
+
+class TestMain:
+    def test_main_passes_on_clean_dir(self, tmp_path: Path):
+        """main() should exit 0 on a clean directory."""
+        role_dir = tmp_path / "roles" / "test_role"
+        (role_dir / "tasks").mkdir(parents=True)
+        (role_dir / "tasks" / "main.yml").write_text(
+            "- name: Normal task\n  ansible.builtin.shell: echo hello\n  changed_when: false\n"
+        )
+        runner = CliRunner()
+        result = runner.invoke(main, ["--path", str(role_dir)])
+        assert result.exit_code == 0
+        assert "OK" in result.output or "no_log" in result.output
+
+    def test_main_fails_on_unsafe_dir(self, tmp_path: Path):
+        """main() should exit 1 when violations are found."""
+        role_dir = tmp_path / "roles" / "test_role"
+        (role_dir / "tasks").mkdir(parents=True)
+        (role_dir / "tasks" / "main.yml").write_text(
+            "- name: Unsafe task\n  ansible.builtin.shell: echo {{ _secrets.db_password }}\n"
+        )
+        runner = CliRunner()
+        result = runner.invoke(main, ["--path", str(role_dir)])
+        assert result.exit_code == 1
+        assert "Unsafe task" in result.output
+
+    def test_main_returns_2_on_missing_dir(self, tmp_path: Path):
+        """main() should exit 2 when the directory doesn't exist."""
+        runner = CliRunner()
+        result = runner.invoke(main, ["--path", str(tmp_path / "nonexistent")])
+        assert result.exit_code == 2
+
+    def test_main_with_ansible_dir_option(self, tmp_path: Path):
+        """main() --ansible-dir should work like --path."""
+        role_dir = tmp_path / "roles" / "test_role"
+        (role_dir / "tasks").mkdir(parents=True)
+        (role_dir / "tasks" / "main.yml").write_text(
+            "- name: Unsafe task\n  ansible.builtin.shell: echo {{ _secrets.db_password }}\n"
+        )
+        runner = CliRunner()
+        result = runner.invoke(main, ["--ansible-dir", str(tmp_path)])
+        assert result.exit_code == 1
+
+    def test_main_no_path_no_ansible_dir_uses_default(self, tmp_path: Path, monkeypatch):
+        """main() with no args uses DEFAULT_ANSIBLE_DIR."""
+        import devx.tools.check_ansible_no_log as mod
+
+        role_dir = tmp_path / "roles" / "test_role"
+        (role_dir / "tasks").mkdir(parents=True)
+        (role_dir / "tasks" / "main.yml").write_text("- name: Normal task\n  ansible.builtin.shell: echo hello\n")
+        monkeypatch.setattr(mod, "DEFAULT_ANSIBLE_DIR", tmp_path)
+        runner = CliRunner()
+        result = runner.invoke(main, [])
+        assert result.exit_code == 0

tests/unit/test_tools_check_ansible_no_state_absent_on_db.py

@@ -0,0 +1,198 @@
+"""Unit tests for devx.tools.check_ansible_no_state_absent_on_db."""
+
+from __future__ import annotations
+
+from pathlib import Path
+
+from click.testing import CliRunner
+
+from devx.tools.check_ansible_no_state_absent_on_db import _check_file, _find_task_files, main
+
+
+class TestCheckFile:
+    def test_clean_file_no_db_paths(self, tmp_path: Path):
+        """A file with no DB paths should produce no violations."""
+        p = tmp_path / "test.yml"
+        p.write_text("- name: Safe task\n  ansible.builtin.file:\n    path: /opt/app/data\n    state: directory\n")
+        assert _check_file(p, tmp_path) == []
+
+    def test_state_absent_on_zitadel_db_fails(self, tmp_path: Path):
+        """state: absent on zitadel-db path should be flagged."""
+        p = tmp_path / "test.yml"
+        p.write_text(
+            "- name: Dangerous wipe\n  ansible.builtin.file:\n    path: /opt/postgres/zitadel-db\n    state: absent\n"
+        )
+        violations = _check_file(p, tmp_path)
+        assert len(violations) >= 1
+        assert "state" in violations[0].lower() or "absent" in violations[0].lower()
+
+    def test_state_absent_on_var_lib_postgresql_fails(self, tmp_path: Path):
+        """state: absent on /var/lib/postgresql/data should be flagged."""
+        p = tmp_path / "test.yml"
+        p.write_text(
+            "- name: Dangerous wipe\n  ansible.builtin.file:\n    path: /var/lib/postgresql/data\n    state: absent\n"
+        )
+        violations = _check_file(p, tmp_path)
+        assert len(violations) >= 1
+
+    def test_state_absent_on_app_db_fails(self, tmp_path: Path):
+        """state: absent on any *-db path should be flagged."""
+        p = tmp_path / "test.yml"
+        p.write_text(
+            "- name: Dangerous wipe\n  ansible.builtin.file:\n    path: /opt/postgres/gitea-db\n    state: absent\n"
+        )
+        violations = _check_file(p, tmp_path)
+        assert len(violations) >= 1
+
+    def test_state_absent_with_pg_upgrade_context_passes(self, tmp_path: Path):
+        """state: absent near DB path with upgrade-postgres context should pass."""
+        p = tmp_path / "test.yml"
+        p.write_text(
+            "- name: PG upgrade — remove old data\n"
+            "  ansible.builtin.file:\n"
+            "    path: /opt/postgres/zitadel-db\n"
+            "    state: absent\n"
+            "  when: pg_version_changed | default(false)\n"
+        )
+        violations = _check_file(p, tmp_path)
+        assert violations == []
+
+    def test_state_absent_with_pg_version_context_passes(self, tmp_path: Path):
+        """state: absent near DB path with PG_VERSION context should pass."""
+        p = tmp_path / "test.yml"
+        p.write_text(
+            "- name: PG upgrade\n"
+            "  ansible.builtin.file:\n"
+            "    path: /opt/postgres/zitadel-db\n"
+            "    state: absent\n"
+            "  when: PG_VERSION is defined\n"
+        )
+        violations = _check_file(p, tmp_path)
+        assert violations == []
+
+    def test_state_absent_with_allow_marker_passes(self, tmp_path: Path):
+        """state: absent with lint:allow-state-absent comment should pass."""
+        p = tmp_path / "test.yml"
+        p.write_text(
+            "# lint:allow-state-absent\n"
+            "- name: Intentional wipe\n"
+            "  ansible.builtin.file:\n"
+            "    path: /opt/postgres/zitadel-db\n"
+            "    state: absent\n"
+        )
+        violations = _check_file(p, tmp_path)
+        assert violations == []
+
+    def test_state_present_on_db_path_passes(self, tmp_path: Path):
+        """state: present (not absent) on DB path should pass."""
+        p = tmp_path / "test.yml"
+        p.write_text(
+            "- name: Safe task\n  ansible.builtin.file:\n    path: /opt/postgres/zitadel-db\n    state: directory\n"
+        )
+        assert _check_file(p, tmp_path) == []
+
+    def test_nonexistent_file_returns_empty(self):
+        """A nonexistent file should return no violations."""
+        assert _check_file(Path("/nonexistent/path/file.yml"), Path.cwd()) == []
+
+    def test_rm_rf_db_fails(self, tmp_path: Path):
+        """rm -rf on a DB path should be flagged."""
+        p = tmp_path / "test.yml"
+        p.write_text("- name: Dangerous wipe\n  ansible.builtin.shell: rm -rf /opt/postgres/zitadel-db\n")
+        violations = _check_file(p, tmp_path)
+        assert len(violations) >= 1
+
+    def test_relative_path_outside_repo(self, tmp_path: Path):
+        """Files outside repo_root use the full path in display."""
+        p = tmp_path / "test.yml"
+        p.write_text(
+            "- name: Dangerous wipe\n  ansible.builtin.file:\n    path: /opt/postgres/zitadel-db\n    state: absent\n"
+        )
+        violations = _check_file(p, Path("/other/repo"))
+        assert len(violations) >= 1
+        assert str(tmp_path) in violations[0] or "test.yml" in violations[0]
+
+
+class TestFindTaskFiles:
+    def test_find_yml_files_in_directory(self, tmp_path: Path):
+        """Should find .yml files in a directory."""
+        (tmp_path / "tasks").mkdir()
+        (tmp_path / "tasks" / "main.yml").write_text("[]")
+        (tmp_path / "tasks" / "other.yaml").write_text("[]")
+        files = _find_task_files(tmp_path)
+        assert len(files) == 2
+
+    def test_skip_molecule_files(self, tmp_path: Path):
+        """Should skip files in molecule directories."""
+        (tmp_path / "molecule").mkdir()
+        (tmp_path / "molecule" / "test.yml").write_text("[]")
+        (tmp_path / "main.yml").write_text("[]")
+        files = _find_task_files(tmp_path)
+        assert len(files) == 1
+        assert "molecule" not in files[0].parts
+
+    def test_single_file_input(self, tmp_path: Path):
+        """Should return the file itself if it's a .yml file."""
+        f = tmp_path / "test.yml"
+        f.write_text("[]")
+        files = _find_task_files(f)
+        assert files == [f]
+
+    def test_nonexistent_path_returns_empty(self):
+        """A path that is neither a file nor a dir should return []."""
+        files = _find_task_files(Path("/nonexistent/path/that/does/not/exist"))
+        assert files == []
+
+    def test_non_yaml_file_skipped(self, tmp_path: Path):
+        """Non-YAML files should not be included."""
+        f = tmp_path / "readme.txt"
+        f.write_text("not yaml")
+        assert _find_task_files(f) == []
+
+
+class TestMain:
+    def test_main_no_violations_exit_zero(self, tmp_path: Path):
+        """main() with a clean file should exit 0."""
+        f = tmp_path / "clean.yml"
+        f.write_text("- name: Safe task\n  ansible.builtin.file:\n    path: /opt/app\n    state: directory\n")
+        result = CliRunner().invoke(main, ["--path", str(f)])
+        assert result.exit_code == 0
+        assert "OK" in result.output
+
+    def test_main_with_violations_exit_one(self, tmp_path: Path):
+        """main() with a state: absent on a DB path should exit 1."""
+        f = tmp_path / "dangerous.yml"
+        f.write_text(
+            "- name: Dangerous wipe\n  ansible.builtin.file:\n    path: /opt/postgres/zitadel-db\n    state: absent\n"
+        )
+        result = CliRunner().invoke(main, ["--path", str(f)])
+        assert result.exit_code == 1
+        assert "FAIL" in result.output
+
+    def test_main_path_to_clean_file(self, tmp_path: Path):
+        """main() --path pointing to a specific clean file should exit 0."""
+        f = tmp_path / "tasks.yml"
+        f.write_text("- name: Safe\n  ansible.builtin.file:\n    path: /opt/app\n    state: directory\n")
+        result = CliRunner().invoke(main, ["--path", str(f)])
+        assert result.exit_code == 0
+
+    def test_main_default_dirs_no_violations(self, tmp_path: Path, monkeypatch):
+        """main() with no --path scans default dirs and exits 0."""
+        import devx.tools.check_ansible_no_state_absent_on_db as mod
+
+        (tmp_path / "clean.yml").write_text(
+            "- name: Safe\n  ansible.builtin.file:\n    path: /opt/app\n    state: directory\n"
+        )
+        monkeypatch.setattr(mod, "DEFAULT_ANSIBLE_DIRS", [tmp_path])
+        result = CliRunner().invoke(main, [])
+        assert result.exit_code == 0
+        assert "OK" in result.output
+
+    def test_main_custom_ansible_dirs(self, tmp_path: Path):
+        """main() --ansible-dir should work."""
+        f = tmp_path / "dangerous.yml"
+        f.write_text(
+            "- name: Dangerous wipe\n  ansible.builtin.file:\n    path: /opt/postgres/zitadel-db\n    state: absent\n"
+        )
+        result = CliRunner().invoke(main, ["--ansible-dir", str(tmp_path)])
+        assert result.exit_code == 1

tests/unit/test_tools_check_ansible_patterns.py

@@ -0,0 +1,340 @@
+"""Unit tests for devx.tools.check_ansible_patterns."""
+
+from __future__ import annotations
+
+from pathlib import Path
+
+from click.testing import CliRunner
+
+from devx.tools.check_ansible_patterns import (
+    _check_file,
+    _check_task,
+    _check_tasks,
+    _find_task_files,
+    _is_legitimate_devnull,
+    _is_legitimate_or_true,
+    main,
+)
+
+
+def _make_task(name: str, action: str, value: str, **extra: object) -> dict:
+    """Build a minimal task dict for testing."""
+    task: dict = {"name": name, action: value}
+    task.update(extra)
+    return task
+
+
+class TestIsLegitimateOrTrue:
+    def test_cleanup_task_name_is_legitimate(self):
+        assert _is_legitimate_or_true("docker rm old-container", "Remove old container")
+
+    def test_prune_task_name_is_legitimate(self):
+        assert _is_legitimate_or_true("docker image prune -f", "Prune unused images")
+
+    def test_docker_rm_command_is_legitimate(self):
+        assert _is_legitimate_or_true("docker rm -f mycontainer", "Some task")
+
+    def test_provision_task_is_not_legitimate(self):
+        assert not _is_legitimate_or_true("curl -X POST https://api/app || true", "Provision OIDC client")
+
+    def test_sync_task_name_is_legitimate(self):
+        assert _is_legitimate_or_true("psql -c 'ALTER USER' || true", "Sync PostgreSQL password")
+
+
+class TestCheckTask:
+    def test_or_true_on_provision_task_fails(self, tmp_path: Path):
+        task = _make_task(
+            "Provision OIDC client",
+            "ansible.builtin.shell",
+            "curl -X POST https://zitadel/api || true",
+        )
+        violations = _check_task(task, tmp_path / "test.yml", 1, tmp_path)
+        assert len(violations) >= 1
+        assert "|| true" in violations[0]
+
+    def test_or_true_on_cleanup_task_passes(self, tmp_path: Path):
+        task = _make_task(
+            "Remove old container",
+            "ansible.builtin.shell",
+            "docker rm -f old-container || true",
+        )
+        assert _check_task(task, tmp_path / "test.yml", 1, tmp_path) == []
+
+    def test_failed_when_false_on_provision_fails(self, tmp_path: Path):
+        task = _make_task(
+            "Provision OIDC client",
+            "ansible.builtin.shell",
+            "curl -X POST https://zitadel/api",
+            failed_when=False,
+        )
+        violations = _check_task(task, tmp_path / "test.yml", 1, tmp_path)
+        assert any("failed_when" in v for v in violations)
+
+    def test_failed_when_false_on_stop_passes(self, tmp_path: Path):
+        task = _make_task(
+            "Stop ZITADEL containers",
+            "ansible.builtin.shell",
+            "docker stop zitadel",
+            failed_when=False,
+        )
+        assert _check_task(task, tmp_path / "test.yml", 1, tmp_path) == []
+
+    def test_failed_when_false_on_check_passes(self, tmp_path: Path):
+        task = _make_task(
+            "Check if ZITADEL is running",
+            "ansible.builtin.shell",
+            "docker inspect zitadel",
+            failed_when=False,
+        )
+        assert _check_task(task, tmp_path / "test.yml", 1, tmp_path) == []
+
+    def test_allow_marker_in_name_passes(self, tmp_path: Path):
+        task = _make_task(
+            "Provision OIDC #lint:allow-failure-masking",
+            "ansible.builtin.shell",
+            "curl -X POST https://zitadel/api || true",
+            failed_when=False,
+        )
+        assert _check_task(task, tmp_path / "test.yml", 1, tmp_path) == []
+
+    def test_safe_task_no_violations(self, tmp_path: Path):
+        task = _make_task(
+            "Create directory",
+            "ansible.builtin.file",
+            "path=/opt/app state=directory",
+        )
+        assert _check_task(task, tmp_path / "test.yml", 1, tmp_path) == []
+
+    def test_relative_path_outside_repo(self, tmp_path: Path):
+        """Files outside repo_root use the full path in display."""
+        task = _make_task(
+            "Provision OIDC",
+            "ansible.builtin.shell",
+            "curl || true",
+        )
+        other_dir = Path("/tmp/other")
+        violations = _check_task(task, other_dir / "test.yml", 1, tmp_path)
+        assert len(violations) >= 1
+
+
+class TestCheckFile:
+    def test_clean_file_passes(self, tmp_path: Path):
+        p = tmp_path / "test.yml"
+        p.write_text("- name: Safe task\n  ansible.builtin.file:\n    path: /opt/app\n    state: directory\n")
+        assert _check_file(p, tmp_path) == []
+
+    def test_dangerous_pattern_detected(self, tmp_path: Path):
+        p = tmp_path / "test.yml"
+        p.write_text(
+            "- name: Provision OIDC\n"
+            "  ansible.builtin.shell: |\n"
+            "    curl -X POST https://api/app || true\n"
+            "  failed_when: false\n"
+        )
+        violations = _check_file(p, tmp_path)
+        assert len(violations) >= 1
+
+    def test_file_level_allow_marker_passes(self, tmp_path: Path):
+        p = tmp_path / "test.yml"
+        p.write_text(
+            "# lint:allow-failure-masking\n"
+            "- name: Provision OIDC\n"
+            "  ansible.builtin.shell: |\n"
+            "    curl -X POST https://api/app || true\n"
+            "  failed_when: false\n"
+        )
+        assert _check_file(p, tmp_path) == []
+
+    def test_nonexistent_file_returns_empty(self):
+        assert _check_file(Path("/nonexistent/path/file.yml"), Path.cwd()) == []
+
+    def test_yaml_parse_error_returns_empty(self, tmp_path: Path):
+        p = tmp_path / "test.yml"
+        p.write_text("name: Provision OIDC\n  shell: curl || true\n: invalid: [")
+        assert _check_file(p, tmp_path) == []
+
+    def test_dict_doc_playbook_with_tasks(self, tmp_path: Path):
+        p = tmp_path / "playbook.yml"
+        p.write_text(
+            "- hosts: all\n"
+            "  tasks:\n"
+            "    - name: Provision OIDC\n"
+            "      ansible.builtin.shell: curl -X POST https://api/app || true\n"
+        )
+        violations = _check_file(p, tmp_path)
+        assert any("|| true" in v for v in violations)
+
+    def test_dict_doc_with_pre_tasks_and_post_tasks(self, tmp_path: Path):
+        p = tmp_path / "playbook.yml"
+        p.write_text(
+            "- hosts: all\n"
+            "  pre_tasks:\n"
+            "    - name: Provision secret\n"
+            "      ansible.builtin.shell: curl -X POST https://api/app || true\n"
+            "  post_tasks:\n"
+            "    - name: Provision OIDC\n"
+            "      ansible.builtin.shell: curl -X POST https://api/app || true\n"
+            "  handlers:\n"
+            "    - name: Provision password\n"
+            "      ansible.builtin.shell: curl -X POST https://api/app || true\n"
+        )
+        violations = _check_file(p, tmp_path)
+        assert len(violations) >= 3
+
+    def test_block_tasks_in_list_item(self, tmp_path: Path):
+        p = tmp_path / "tasks.yml"
+        p.write_text(
+            "- name: Outer task\n"
+            "  block:\n"
+            "    - name: Provision OIDC\n"
+            "      ansible.builtin.shell: curl -X POST https://api/app || true\n"
+            "    - name: Provision secret\n"
+            "      ansible.builtin.shell: curl -X POST https://api/app || true\n"
+        )
+        violations = _check_file(p, tmp_path)
+        assert any("|| true" in v for v in violations)
+
+    def test_empty_doc_skipped(self, tmp_path: Path):
+        p = tmp_path / "test.yml"
+        p.write_text("---\nnull\n---\n- name: Provision OIDC\n  ansible.builtin.shell: curl || true\n")
+        violations = _check_file(p, tmp_path)
+        assert any("|| true" in v for v in violations)
+
+    def test_pure_dict_doc_with_tasks(self, tmp_path: Path):
+        p = tmp_path / "playbook.yml"
+        p.write_text(
+            "hosts: all\n"
+            "tasks:\n"
+            "  - name: Provision OIDC\n"
+            "    ansible.builtin.shell: curl -X POST https://api/app || true\n"
+        )
+        violations = _check_file(p, tmp_path)
+        assert any("|| true" in v for v in violations)
+
+
+class TestIsLegitimateDevnull:
+    def test_cleanup_task_is_legitimate(self):
+        assert _is_legitimate_devnull("docker rm old-container 2>/dev/null", "Remove old container")
+
+    def test_provision_task_is_not_legitimate(self):
+        assert not _is_legitimate_devnull("curl -X POST https://api/app 2>/dev/null", "Provision OIDC client")
+
+
+class TestCheckTasks:
+    def test_tasks_section_checked(self, tmp_path: Path):
+        doc = {
+            "tasks": [
+                {"name": "Provision OIDC", "ansible.builtin.shell": "curl || true"},
+            ],
+        }
+        errors: list[str] = []
+        _check_tasks(doc, tmp_path / "test.yml", errors, tmp_path)
+        assert any("|| true" in e for e in errors)
+
+    def test_block_inside_tasks_section(self, tmp_path: Path):
+        doc = {
+            "tasks": [
+                {
+                    "name": "Outer",
+                    "block": [
+                        {"name": "Provision secret", "ansible.builtin.shell": "curl || true"},
+                    ],
+                },
+            ],
+        }
+        errors: list[str] = []
+        _check_tasks(doc, tmp_path / "test.yml", errors, tmp_path)
+        assert any("|| true" in e for e in errors)
+
+    def test_non_list_section_ignored(self, tmp_path: Path):
+        doc = {"tasks": "not a list"}
+        errors: list[str] = []
+        _check_tasks(doc, tmp_path / "test.yml", errors, tmp_path)
+        assert errors == []
+
+    def test_non_dict_task_ignored(self, tmp_path: Path):
+        doc = {"tasks": ["just a string"]}
+        errors: list[str] = []
+        _check_tasks(doc, tmp_path / "test.yml", errors, tmp_path)
+        assert errors == []
+
+
+class TestFindTaskFiles:
+    def test_single_file(self, tmp_path: Path):
+        p = tmp_path / "main.yml"
+        p.write_text("- name: test\n")
+        assert _find_task_files(p) == [p]
+
+    def test_single_yaml_file(self, tmp_path: Path):
+        p = tmp_path / "main.yaml"
+        p.write_text("- name: test\n")
+        assert _find_task_files(p) == [p]
+
+    def test_non_yaml_file_returns_empty(self, tmp_path: Path):
+        p = tmp_path / "main.txt"
+        p.write_text("hello\n")
+        assert _find_task_files(p) == []
+
+    def test_directory_finds_yaml_files(self, tmp_path: Path):
+        (tmp_path / "a.yml").write_text("- name: a\n")
+        (tmp_path / "sub").mkdir()
+        (tmp_path / "sub" / "b.yaml").write_text("- name: b\n")
+        (tmp_path / "ignore.txt").write_text("nope\n")
+        result = _find_task_files(tmp_path)
+        names = {f.name for f in result}
+        assert names == {"a.yml", "b.yaml"}
+
+    def test_directory_skips_molecule(self, tmp_path: Path):
+        (tmp_path / "a.yml").write_text("- name: a\n")
+        (tmp_path / "molecule").mkdir()
+        (tmp_path / "molecule" / "scenario.yml").write_text("- name: mol\n")
+        result = _find_task_files(tmp_path)
+        assert all("molecule" not in f.parts for f in result)
+
+    def test_nonexistent_path_returns_empty(self):
+        assert _find_task_files(Path("/nonexistent/path/xyz")) == []
+
+
+class TestMain:
+    def test_main_clean_file_exit_zero(self, tmp_path: Path):
+        p = tmp_path / "clean.yml"
+        p.write_text("- name: Safe task\n  ansible.builtin.file:\n    path: /opt/app\n    state: directory\n")
+        result = CliRunner().invoke(main, ["--path", str(p)])
+        assert result.exit_code == 0
+        assert "OK" in result.output
+
+    def test_main_violation_exit_one(self, tmp_path: Path):
+        p = tmp_path / "bad.yml"
+        p.write_text(
+            "- name: Provision OIDC\n"
+            "  ansible.builtin.shell: curl -X POST https://api/app || true\n"
+            "  failed_when: false\n"
+        )
+        result = CliRunner().invoke(main, ["--path", str(p)])
+        assert result.exit_code == 1
+        assert "FAIL" in result.output
+
+    def test_main_directory(self, tmp_path: Path):
+        (tmp_path / "clean.yml").write_text(
+            "- name: Safe task\n  ansible.builtin.file:\n    path: /opt\n    state: directory\n"
+        )
+        result = CliRunner().invoke(main, ["--path", str(tmp_path)])
+        assert result.exit_code == 0
+
+    def test_main_default_dirs(self, tmp_path: Path, monkeypatch):
+        import devx.tools.check_ansible_patterns as mod
+
+        (tmp_path / "clean.yml").write_text(
+            "- name: Safe task\n  ansible.builtin.file:\n    path: /opt\n    state: directory\n"
+        )
+        monkeypatch.setattr(mod, "DEFAULT_ANSIBLE_DIRS", [tmp_path])
+        result = CliRunner().invoke(main, [])
+        assert result.exit_code == 0
+        assert "OK" in result.output
+
+    def test_main_custom_ansible_dirs(self, tmp_path: Path):
+        (tmp_path / "bad.yml").write_text(
+            "- name: Provision OIDC\n  ansible.builtin.shell: curl -X POST https://api/app || true\n"
+        )
+        result = CliRunner().invoke(main, ["--ansible-dir", str(tmp_path)])
+        assert result.exit_code == 1

tests/unit/test_tools_check_ansible_set_fact_to_json.py

@@ -0,0 +1,358 @@
+"""Unit tests for devx.tools.check_ansible_set_fact_to_json."""
+
+from __future__ import annotations
+
+import textwrap
+from pathlib import Path
+
+from click.testing import CliRunner
+
+from devx.tools.check_ansible_set_fact_to_json import (
+    _check_file,
+    _check_task,
+    _check_task_list,
+    _find_task_files,
+    main,
+)
+
+
+class TestFindTaskFiles:
+    def test_single_file(self, tmp_path: Path):
+        f = tmp_path / "tasks.yml"
+        f.write_text("tasks: []")
+        assert _find_task_files(f) == [f]
+
+    def test_directory_recursive(self, tmp_path: Path):
+        (tmp_path / "sub").mkdir()
+        f1 = tmp_path / "a.yml"
+        f2 = tmp_path / "sub" / "b.yml"
+        f1.write_text("tasks: []")
+        f2.write_text("tasks: []")
+        result = _find_task_files(tmp_path)
+        assert f1 in result
+        assert f2 in result
+
+    def test_nonexistent_path(self, tmp_path: Path):
+        assert _find_task_files(tmp_path / "nonexistent") == []
+
+    def test_non_yaml_file_skipped(self, tmp_path: Path):
+        f = tmp_path / "readme.txt"
+        f.write_text("not yaml")
+        assert _find_task_files(f) == []
+
+
+class TestCheckTask:
+    def test_set_fact_with_to_json_flagged(self, tmp_path: Path):
+        task = {"name": "Set targets", "set_fact": {"customer_hosts": "{{ targets | to_json }}"}}
+        errors: list[str] = []
+        _check_task(task, tmp_path / "test.yml", errors, tmp_path)
+        assert len(errors) == 1
+        assert "customer_hosts" in errors[0]
+        assert "to_json" in errors[0]
+
+    def test_set_fact_without_to_json_ok(self, tmp_path: Path):
+        task = {"name": "Set targets", "set_fact": {"customer_hosts": "{{ targets }}"}}
+        errors: list[str] = []
+        _check_task(task, tmp_path / "test.yml", errors, tmp_path)
+        assert errors == []
+
+    def test_ansible_builtin_set_fact(self, tmp_path: Path):
+        task = {"name": "Set targets", "ansible.builtin.set_fact": {"my_list": "{{ items | to_nice_json }}"}}
+        errors: list[str] = []
+        _check_task(task, tmp_path / "test.yml", errors, tmp_path)
+        assert len(errors) == 1
+        assert "to_nice_json" in errors[0]
+
+    def test_non_set_fact_task_ignored(self, tmp_path: Path):
+        task = {"name": "Render config", "copy": {"content": "{{ data | to_json }}"}}
+        errors: list[str] = []
+        _check_task(task, tmp_path / "test.yml", errors, tmp_path)
+        assert errors == []
+
+    def test_cacheable_key_ignored(self, tmp_path: Path):
+        task = {"name": "Set fact", "set_fact": {"my_var": "{{ value }}", "cacheable": True}}
+        errors: list[str] = []
+        _check_task(task, tmp_path / "test.yml", errors, tmp_path)
+        assert errors == []
+
+    def test_unnamed_task(self, tmp_path: Path):
+        task = {"set_fact": {"my_var": "{{ value | to_json }}"}}
+        errors: list[str] = []
+        _check_task(task, tmp_path / "test.yml", errors, tmp_path)
+        assert len(errors) == 1
+        assert "(unnamed)" in errors[0]
+
+    def test_set_fact_not_dict_ignored(self, tmp_path: Path):
+        task = {"set_fact": "not a dict"}
+        errors: list[str] = []
+        _check_task(task, tmp_path / "test.yml", errors, tmp_path)
+        assert errors == []
+
+    def test_to_json_no_spaces(self, tmp_path: Path):
+        task = {"set_fact": {"my_var": "{{ items|to_json }}"}}
+        errors: list[str] = []
+        _check_task(task, tmp_path / "test.yml", errors, tmp_path)
+        assert len(errors) == 1
+
+
+class TestCheckTaskList:
+    def test_block_tasks_checked(self, tmp_path: Path):
+        tasks = [{"name": "Block", "block": [{"name": "Set in block", "set_fact": {"x": "{{ y | to_json }}"}}]}]
+        errors: list[str] = []
+        _check_task_list(tasks, tmp_path / "test.yml", errors, tmp_path)
+        assert len(errors) == 1
+        assert "x" in errors[0]
+
+    def test_non_dict_task_ignored(self, tmp_path: Path):
+        tasks = ["just a string", 42, None]
+        errors: list[str] = []
+        _check_task_list(tasks, tmp_path / "test.yml", errors, tmp_path)
+        assert errors == []
+
+
+class TestCheckFile:
+    def test_playbook_with_set_fact_to_json(self, tmp_path: Path):
+        content = textwrap.dedent("""
+            - name: Deploy
+              hosts: all
+              tasks:
+                - name: Set targets
+                  ansible.builtin.set_fact:
+                    customer_hosts: "{{ targets | to_json }}"
+        """).strip()
+        f = tmp_path / "playbook.yml"
+        f.write_text(content)
+        errors = _check_file(f, tmp_path)
+        assert len(errors) == 1
+        assert "customer_hosts" in errors[0]
+
+    def test_playbook_without_set_fact(self, tmp_path: Path):
+        content = textwrap.dedent("""
+            - name: Deploy
+              hosts: all
+              tasks:
+                - name: Debug
+                  ansible.builtin.debug:
+                    msg: "hello"
+        """).strip()
+        f = tmp_path / "playbook.yml"
+        f.write_text(content)
+        assert _check_file(f, tmp_path) == []
+
+    def test_role_tasks_file(self, tmp_path: Path):
+        content = textwrap.dedent("""
+            - name: Set config
+              set_fact:
+                my_data: "{{ data | to_json }}"
+            - name: Copy config
+              copy:
+                content: "{{ config | to_json }}"
+                dest: /etc/config.json
+        """).strip()
+        f = tmp_path / "main.yml"
+        f.write_text(content)
+        errors = _check_file(f, tmp_path)
+        assert len(errors) == 1
+        assert "my_data" in errors[0]
+
+    def test_pre_tasks_and_post_tasks(self, tmp_path: Path):
+        content = textwrap.dedent("""
+            - name: Play
+              hosts: all
+              pre_tasks:
+                - name: Pre set
+                  set_fact:
+                    pre_var: "{{ x | to_json }}"
+              post_tasks:
+                - name: Post set
+                  set_fact:
+                    post_var: "{{ y | to_json }}"
+        """).strip()
+        f = tmp_path / "playbook.yml"
+        f.write_text(content)
+        errors = _check_file(f, tmp_path)
+        assert len(errors) == 2
+
+    def test_handlers_checked(self, tmp_path: Path):
+        content = textwrap.dedent("""
+            - name: Play
+              hosts: all
+              handlers:
+                - name: Restart service
+                  set_fact:
+                    restart_data: "{{ data | to_json }}"
+        """).strip()
+        f = tmp_path / "playbook.yml"
+        f.write_text(content)
+        errors = _check_file(f, tmp_path)
+        assert len(errors) == 1
+
+    def test_invalid_yaml(self, tmp_path: Path):
+        f = tmp_path / "bad.yml"
+        f.write_text("tasks: [invalid: {")
+        errors = _check_file(f, tmp_path)
+        assert len(errors) == 1
+        assert "cannot parse YAML" in errors[0]
+
+    def test_non_dict_doc_skipped(self, tmp_path: Path):
+        f = tmp_path / "list.yml"
+        f.write_text("- just\n- a\n- list\n")
+        assert _check_file(f, tmp_path) == []
+
+    def test_multi_doc_yaml(self, tmp_path: Path):
+        content = textwrap.dedent("""
+            ---
+            - name: Play 1
+              hosts: all
+              tasks:
+                - name: Set in play 1
+                  set_fact:
+                    var1: "{{ x | to_json }}"
+            ---
+            - name: Play 2
+              hosts: all
+              tasks:
+                - name: Set in play 2
+                  set_fact:
+                    var2: "{{ y }}"
+        """).strip()
+        f = tmp_path / "multi.yml"
+        f.write_text(content)
+        errors = _check_file(f, tmp_path)
+        assert len(errors) == 1
+        assert "var1" in errors[0]
+
+    def test_dict_doc_role_tasks_file(self, tmp_path: Path):
+        content = textwrap.dedent("""
+            tasks:
+              - name: Set var
+                set_fact:
+                  my_var: "{{ value | to_json }}"
+        """).strip()
+        f = tmp_path / "main.yml"
+        f.write_text(content)
+        errors = _check_file(f, tmp_path)
+        assert len(errors) == 1
+        assert "my_var" in errors[0]
+
+    def test_play_with_roles_key(self, tmp_path: Path):
+        content = textwrap.dedent("""
+            - name: Play
+              hosts: all
+              roles:
+                - role: my_role
+                  tasks:
+                    - name: Set in role
+                      set_fact:
+                        role_var: "{{ x | to_json }}"
+        """).strip()
+        f = tmp_path / "playbook.yml"
+        f.write_text(content)
+        errors = _check_file(f, tmp_path)
+        assert len(errors) == 1
+        assert "role_var" in errors[0]
+
+    def test_bare_task_in_list_with_block(self, tmp_path: Path):
+        content = textwrap.dedent("""
+            - name: Outer task
+              set_fact:
+                outer: "{{ x | to_json }}"
+            - name: Block
+              block:
+                - name: Inner task
+                  set_fact:
+                    inner: "{{ y | to_json }}"
+        """).strip()
+        f = tmp_path / "tasks.yml"
+        f.write_text(content)
+        errors = _check_file(f, tmp_path)
+        assert len(errors) == 2
+
+    def test_check_file_os_error(self, tmp_path: Path, monkeypatch) -> None:
+        """OSError reading a file returns empty errors (not a crash)."""
+        f = tmp_path / "playbook.yml"
+        f.write_text("- name: ok\n  set_fact:\n    x: 1\n")
+
+        def _raise(*args, **kwargs):
+            raise OSError("disk error")
+
+        monkeypatch.setattr(Path, "read_text", _raise)
+        errors = _check_file(f, tmp_path)
+        assert errors == []
+
+
+class TestMain:
+    def test_passes_when_clean(self, tmp_path: Path):
+        content = textwrap.dedent("""
+            - name: Play
+              hosts: all
+              tasks:
+                - name: Set var
+                  set_fact:
+                    my_var: "{{ value }}"
+        """).strip()
+        f = tmp_path / "playbook.yml"
+        f.write_text(content)
+        runner = CliRunner()
+        result = runner.invoke(main, ["--path", str(f)])
+        assert result.exit_code == 0
+        assert "OK" in result.output
+
+    def test_fails_when_to_json_found(self, tmp_path: Path):
+        content = textwrap.dedent("""
+            - name: Play
+              hosts: all
+              tasks:
+                - name: Set var
+                  set_fact:
+                    my_var: "{{ value | to_json }}"
+        """).strip()
+        f = tmp_path / "playbook.yml"
+        f.write_text(content)
+        runner = CliRunner()
+        result = runner.invoke(main, ["--path", str(f)])
+        assert result.exit_code == 1
+        assert "FAIL" in result.output
+        assert "my_var" in result.output
+
+    def test_directory_scan(self, tmp_path: Path):
+        (tmp_path / "good.yml").write_text(
+            textwrap.dedent("""
+                - name: Play
+                  hosts: all
+                  tasks:
+                    - name: Set
+                      set_fact:
+                        x: "{{ y }}"
+            """).strip()
+        )
+        (tmp_path / "bad.yml").write_text(
+            textwrap.dedent("""
+                - name: Play
+                  hosts: all
+                  tasks:
+                    - name: Set
+                      set_fact:
+                        x: "{{ y | to_json }}"
+            """).strip()
+        )
+        runner = CliRunner()
+        result = runner.invoke(main, ["--path", str(tmp_path)])
+        assert result.exit_code == 1
+        assert "bad.yml" in result.output
+
+    def test_custom_ansible_dirs(self, tmp_path: Path):
+        (tmp_path / "playbook.yml").write_text(
+            textwrap.dedent("""
+                - name: Play
+                  hosts: all
+                  tasks:
+                    - name: Set
+                      set_fact:
+                        x: "{{ y | to_json }}"
+            """).strip()
+        )
+        runner = CliRunner()
+        result = runner.invoke(main, ["--ansible-dir", str(tmp_path)])
+        assert result.exit_code == 1
+        assert "playbook.yml" in result.output

tests/unit/test_tools_check_docker_init.py

@@ -0,0 +1,291 @@
+"""Unit tests for devx.tools.check_docker_init."""
+
+from __future__ import annotations
+
+import textwrap
+from pathlib import Path
+
+from click.testing import CliRunner
+
+from devx.tools.check_docker_init import _check_template, _find_compose_templates, _parse_services, main
+
+
+class TestFindComposeTemplates:
+    def test_finds_docker_compose_templates(self, tmp_path: Path):
+        (tmp_path / "docker-compose.observability.yml.j2").write_text("services:")
+        (tmp_path / "docker-compose.service.yml.j2").write_text("services:")
+        result = _find_compose_templates(tmp_path)
+        assert len(result) == 2
+
+    def test_finds_exporters_compose(self, tmp_path: Path):
+        (tmp_path / "exporters-compose.yml.j2").write_text("services:")
+        result = _find_compose_templates(tmp_path)
+        assert len(result) == 1
+        assert "exporters-compose" in str(result[0])
+
+    def test_finds_compose_yaml_templates(self, tmp_path: Path):
+        (tmp_path / "compose.yaml.j2").write_text("services:")
+        result = _find_compose_templates(tmp_path)
+        assert len(result) == 1
+
+    def test_single_file(self, tmp_path: Path):
+        f = tmp_path / "docker-compose.test.yml.j2"
+        f.write_text("services:")
+        result = _find_compose_templates(f)
+        assert result == [f]
+
+    def test_nonexistent_path(self, tmp_path: Path):
+        assert _find_compose_templates(tmp_path / "nonexistent") == []
+
+    def test_deduplicates(self, tmp_path: Path):
+        (tmp_path / "docker-compose.yml.j2").write_text("services:")
+        result = _find_compose_templates(tmp_path)
+        assert len(result) == 1
+
+    def test_recursive(self, tmp_path: Path):
+        (tmp_path / "sub").mkdir()
+        (tmp_path / "sub" / "docker-compose.yml.j2").write_text("services:")
+        result = _find_compose_templates(tmp_path)
+        assert len(result) == 1
+
+
+class TestParseServices:
+    def test_basic_services(self):
+        content = textwrap.dedent("""
+            services:
+              web:
+                image: nginx
+                healthcheck:
+                  test: ["CMD", "curl", "localhost"]
+              db:
+                image: postgres
+            networks:
+              default:
+        """).strip()
+        services = _parse_services(content)
+        assert "web" in services
+        assert "db" in services
+        assert any("image: nginx" in line for line in services["web"])
+
+    def test_jinja2_service_names(self):
+        content = textwrap.dedent("""
+            services:
+              {{ app_name }}:
+                image: {{ app_image }}
+                healthcheck:
+                  test: ["CMD", "curl"]
+              {{ app_name }}-db:
+                image: postgres
+            networks:
+              traefik:
+        """).strip()
+        services = _parse_services(content)
+        assert "{{ app_name }}" in services
+        assert "{{ app_name }}-db" in services
+
+    def test_no_services_section(self):
+        content = "version: '3'\nvolumes:\n  data:"
+        assert _parse_services(content) == {}
+
+    def test_service_at_end_of_file(self):
+        content = textwrap.dedent("""
+            services:
+              web:
+                image: nginx
+        """).strip()
+        services = _parse_services(content)
+        assert "web" in services
+
+    def test_volumes_ends_services(self):
+        content = textwrap.dedent("""
+            services:
+              web:
+                image: nginx
+            volumes:
+              data:
+        """).strip()
+        services = _parse_services(content)
+        assert "web" in services
+        assert "data" not in services
+
+
+class TestCheckTemplate:
+    def test_service_with_healthcheck_and_init_ok(self, tmp_path: Path):
+        content = textwrap.dedent("""
+            services:
+              web:
+                image: nginx
+                init: true
+                healthcheck:
+                  test: ["CMD", "curl", "localhost"]
+            networks:
+              default:
+        """).strip()
+        f = tmp_path / "docker-compose.yml.j2"
+        f.write_text(content)
+        assert _check_template(f, tmp_path) == []
+
+    def test_service_with_healthcheck_no_init_flagged(self, tmp_path: Path):
+        content = textwrap.dedent("""
+            services:
+              web:
+                image: nginx
+                healthcheck:
+                  test: ["CMD", "curl", "localhost"]
+            networks:
+              default:
+        """).strip()
+        f = tmp_path / "docker-compose.yml.j2"
+        f.write_text(content)
+        errors = _check_template(f, tmp_path)
+        assert len(errors) == 1
+        assert "web" in errors[0]
+        assert "init: true" in errors[0]
+
+    def test_service_without_healthcheck_ok(self, tmp_path: Path):
+        content = textwrap.dedent("""
+            services:
+              web:
+                image: nginx
+            networks:
+              default:
+        """).strip()
+        f = tmp_path / "docker-compose.yml.j2"
+        f.write_text(content)
+        assert _check_template(f, tmp_path) == []
+
+    def test_multiple_services_some_missing(self, tmp_path: Path):
+        content = textwrap.dedent("""
+            services:
+              good:
+                image: nginx
+                init: true
+                healthcheck:
+                  test: ["CMD", "curl"]
+              bad:
+                image: redis
+                healthcheck:
+                  test: ["CMD", "redis-cli", "ping"]
+            networks:
+              default:
+        """).strip()
+        f = tmp_path / "docker-compose.yml.j2"
+        f.write_text(content)
+        errors = _check_template(f, tmp_path)
+        assert len(errors) == 1
+        assert "bad" in errors[0]
+        assert "good" not in errors[0]
+
+    def test_no_services_section(self, tmp_path: Path):
+        content = "version: '3'\nvolumes:\n  data:"
+        f = tmp_path / "docker-compose.yml.j2"
+        f.write_text(content)
+        assert _check_template(f, tmp_path) == []
+
+    def test_jinja2_conditional_service(self, tmp_path: Path):
+        content = textwrap.dedent("""
+            services:
+            {% if backup_enabled %}
+              backup:
+                image: backup
+                healthcheck:
+                  test: ["CMD-SHELL", "pgrep backup"]
+            {% endif %}
+            networks:
+              default:
+        """).strip()
+        f = tmp_path / "docker-compose.yml.j2"
+        f.write_text(content)
+        errors = _check_template(f, tmp_path)
+        assert len(errors) == 1
+        assert "backup" in errors[0]
+
+    def test_relative_path_in_error(self, tmp_path: Path):
+        content = textwrap.dedent("""
+            services:
+              web:
+                image: nginx
+                healthcheck:
+                  test: ["CMD"]
+            networks:
+              default:
+        """).strip()
+        f = tmp_path / "docker-compose.yml.j2"
+        f.write_text(content)
+        errors = _check_template(f, tmp_path)
+        assert len(errors) == 1
+        assert "docker-compose.yml.j2" in errors[0]
+        assert str(tmp_path) not in errors[0]
+
+
+class TestMain:
+    def test_passes_when_all_ok(self, tmp_path: Path):
+        content = textwrap.dedent("""
+            services:
+              web:
+                image: nginx
+                init: true
+                healthcheck:
+                  test: ["CMD"]
+            networks:
+              default:
+        """).strip()
+        f = tmp_path / "docker-compose.yml.j2"
+        f.write_text(content)
+        runner = CliRunner()
+        result = runner.invoke(main, ["--path", str(f)])
+        assert result.exit_code == 0
+        assert "OK" in result.output
+
+    def test_fails_when_missing_init(self, tmp_path: Path):
+        content = textwrap.dedent("""
+            services:
+              web:
+                image: nginx
+                healthcheck:
+                  test: ["CMD"]
+            networks:
+              default:
+        """).strip()
+        f = tmp_path / "docker-compose.yml.j2"
+        f.write_text(content)
+        runner = CliRunner()
+        result = runner.invoke(main, ["--path", str(f)])
+        assert result.exit_code == 1
+        assert "FAIL" in result.output
+        assert "web" in result.output
+
+    def test_default_dir(self, tmp_path: Path):
+        (tmp_path / "docker-compose.good.yml.j2").write_text(
+            textwrap.dedent("""
+                services:
+                  web:
+                    image: nginx
+                    init: true
+                    healthcheck:
+                      test: ["CMD"]
+                networks:
+                  default:
+            """).strip()
+        )
+        (tmp_path / "docker-compose.bad.yml.j2").write_text(
+            textwrap.dedent("""
+                services:
+                  db:
+                    image: postgres
+                    healthcheck:
+                      test: ["CMD"]
+                networks:
+                  default:
+            """).strip()
+        )
+        runner = CliRunner()
+        result = runner.invoke(main, ["--templates-dir", str(tmp_path)])
+        assert result.exit_code == 1
+        assert "db" in result.output
+
+    def test_no_templates_found(self, tmp_path: Path):
+        runner = CliRunner()
+        result = runner.invoke(main, ["--templates-dir", str(tmp_path)])
+        assert result.exit_code == 0
+        assert "OK" in result.output

tests/unit/test_tools_check_jinja_expr.py

@@ -0,0 +1,264 @@
+"""Unit tests for devx.tools.check_jinja_expr.
+
+Verifies that the check correctly validates Jinja2 expressions,
+catches reversed strftime filter arguments (the OBL-INFRA-508 bug),
+and passes on valid expressions.
+"""
+
+from __future__ import annotations
+
+from pathlib import Path
+from unittest.mock import patch
+
+from click.testing import CliRunner
+
+from devx.tools.check_jinja_expr import (
+    _check_file,
+    _default_ansible_dirs,
+    _extract_expressions,
+    _render_expression,
+    main,
+)
+
+
+def test_render_valid_expression():
+    """Valid Jinja expression renders without error."""
+    ok, _ = _render_expression("'%Y-%m-%dT%H:%M:%S+00:00' | strftime(1735689600)")
+    assert ok
+
+
+def test_render_reversed_strftime_args():
+    """Reversed strftime filter args are detected as an error."""
+    ok, msg = _render_expression("(now().timestamp() | int + 3600) | strftime('%Y-%m-%dT%H:%M:%S+00:00')")
+    assert not ok
+    assert "reversed" in msg.lower()
+
+
+def test_render_correct_strftime_args():
+    """Correct strftime filter args pass."""
+    ok, _ = _render_expression("'%Y-%m-%dT%H:%M:%S+00:00' | strftime((now().timestamp() | int) + 3600)")
+    assert ok
+
+
+def test_render_unknown_filter():
+    """Unknown filter is reported as an error."""
+    ok, msg = _render_expression("'test' | nonexistent_filter")
+    assert not ok
+    assert "filter" in msg.lower()
+
+
+def test_extract_skips_go_templates():
+    """Go template syntax ({{.Field}}) is not extracted."""
+    content = "cmd: docker inspect --format '{{.State.Running}}' container"
+    expressions = _extract_expressions(content)
+    assert len(expressions) == 0
+
+
+def test_extract_skips_single_char():
+    """Single-character fragments are not extracted."""
+    content = 'value: "{{ \' }}"'
+    expressions = _extract_expressions(content)
+    assert len(expressions) == 0
+
+
+def test_extract_skips_multiline():
+    """Multi-line expressions are skipped."""
+    content = 'value: "{{\n  something\n}}"'
+    expressions = _extract_expressions(content)
+    assert len(expressions) == 0
+
+
+def test_extract_skips_unbalanced():
+    """Expressions with unbalanced braces (from partial capture) are skipped."""
+    content = "value: \"{{ default({'k': {}}, true) }}\""
+    expressions = _extract_expressions(content)
+    # The regex captures {{ default({'k': {}} — unbalanced parens
+    # because the inner }} terminates the match early.
+    # All extracted expressions should have balanced braces.
+    for expr in expressions:
+        assert expr.count("{") == expr.count("}")
+
+
+def test_extract_valid_expression():
+    """Valid Jinja expressions are extracted."""
+    content = "value: \"{{ my_var | default('x') }}\""
+    expressions = _extract_expressions(content)
+    assert "my_var | default('x')" in expressions
+
+
+def test_main_passes_on_clean_file(tmp_path: Path) -> None:
+    """A file with valid expressions passes."""
+    test_file = tmp_path / "tasks.yml"
+    test_file.write_text("value: \"{{ my_var | default('x') }}\"\nother: \"{{ '%Y' | strftime(1735689600) }}\"\n")
+    runner = CliRunner()
+    result = runner.invoke(main, ["--path", str(test_file)])
+    assert result.exit_code == 0
+
+
+def test_main_no_violations_empty_dir(tmp_path: Path) -> None:
+    """An empty directory passes."""
+    runner = CliRunner()
+    result = runner.invoke(main, ["--path", str(tmp_path)])
+    assert result.exit_code == 0
+
+
+def test_main_catches_reversed_strftime(tmp_path: Path) -> None:
+    """A file with reversed strftime args is flagged."""
+    test_file = tmp_path / "test.yml"
+    test_file.write_text("value: \"{{ (now().timestamp() | int + 3600) | strftime('%Y-%m-%dT%H:%M:%S+00:00') }}\"\n")
+    runner = CliRunner()
+    result = runner.invoke(main, ["--path", str(test_file)])
+    assert result.exit_code == 1
+    assert "reversed" in result.output.lower()
+
+
+def test_render_skips_undefined_var():
+    """Undefined variables are skipped (MockDict returns mock for missing keys)."""
+    ok, _ = _render_expression("nonexistent_var_in_mock | upper")
+    assert ok
+
+
+def test_render_skips_other_errors():
+    """Non-filter errors from missing mocks are skipped."""
+    ok, _ = _render_expression("some_undefined.attr.method()")
+    assert ok
+
+
+def test_extract_skips_backtick():
+    """Backtick fragments are skipped (caught by single-char check)."""
+    content = 'value: "{{ ` }}"'
+    expressions = _extract_expressions(content)
+    assert len(expressions) == 0
+
+
+def test_extract_skips_network_settings():
+    """Expressions with .NetworkSettings. patterns are skipped."""
+    content = 'value: "{{ foo.NetworkSettings.IPAddress }}"'
+    expressions = _extract_expressions(content)
+    assert len(expressions) == 0
+
+
+def test_extract_skips_unbalanced_parens():
+    """Expressions with unbalanced parens are skipped."""
+    content = 'value: "{{ foo(bar }}"'
+    expressions = _extract_expressions(content)
+    assert len(expressions) == 0
+
+
+def test_extract_skips_unbalanced_braces():
+    """Expressions with unbalanced braces are skipped."""
+    content = 'value: "{{ foo{bar }}"'
+    expressions = _extract_expressions(content)
+    assert len(expressions) == 0
+
+
+def test_extract_skips_unbalanced_brackets():
+    """Expressions with unbalanced brackets are skipped."""
+    content = 'value: "{{ foo[0 }}"'
+    expressions = _extract_expressions(content)
+    assert len(expressions) == 0
+
+
+def test_extract_skips_control_flow():
+    """Control flow fragments starting with % are skipped."""
+    content = 'value: "{{ % if x }}"'
+    expressions = _extract_expressions(content)
+    assert len(expressions) == 0
+
+
+def test_check_file_outside_repo(tmp_path: Path) -> None:
+    """Files outside REPO_ROOT are handled (no relative_to error)."""
+    test_file = tmp_path / "test.yml"
+    test_file.write_text("value: \"{{ (now().timestamp() | int + 3600) | strftime('%Y-%m-%dT%H:%M:%S+00:00') }}\"\n")
+    violations = _check_file(test_file, Path("/other/repo"))
+    assert len(violations) == 1
+    assert "reversed" in violations[0].lower()
+
+
+def test_render_mock_dict_missing_key():
+    """MockDict returns a mock for missing keys (no UndefinedError)."""
+    ok, _ = _render_expression("undefined_var.some_attr | upper")
+    assert ok
+
+
+def test_render_syntax_error():
+    """Syntax errors are reported as failures."""
+    ok, msg = _render_expression("{{ invalid syntax +")
+    assert not ok
+    assert "Syntax error" in msg
+
+
+def test_render_unknown_filter_error():
+    """Unknown filters are reported as failures (not skipped)."""
+    ok, msg = _render_expression("'test' | nonexistent_filter")
+    assert not ok
+    assert "filter" in msg.lower()
+
+
+def test_render_generic_exception_skipped():
+    """Non-filter exceptions from missing mocks are skipped."""
+    # replace() with no args triggers TypeError (missing required args)
+    # which is not a filter-not-found or strftime error — should be skipped.
+    ok, msg = _render_expression("my_var | replace")
+    assert ok
+    assert "Skipped" in msg
+
+
+def test_default_ansible_dirs():
+    """_default_ansible_dirs returns playbooks and roles paths."""
+    dirs = _default_ansible_dirs()
+    assert Path.cwd() / "ansible" / "playbooks" in dirs
+    assert Path.cwd() / "ansible" / "roles" in dirs
+
+
+def test_main_default_dirs(tmp_path: Path) -> None:
+    """Running with no --path scans default dirs (uses small temp fixture)."""
+    (tmp_path / "playbooks").mkdir()
+    (tmp_path / "roles").mkdir()
+    (tmp_path / "playbooks" / "test.yml").write_text("value: \"{{ my_var | default('x') }}\"\n")
+    with patch(
+        "devx.tools.check_jinja_expr._default_ansible_dirs",
+        return_value=[tmp_path / "playbooks", tmp_path / "roles"],
+    ):
+        runner = CliRunner()
+        result = runner.invoke(main, [])
+        assert result.exit_code == 0
+
+
+def test_main_custom_ansible_dirs(tmp_path: Path) -> None:
+    """--ansible-dir option works."""
+    (tmp_path / "test.yml").write_text("value: \"{{ my_var | default('x') }}\"\n")
+    runner = CliRunner()
+    result = runner.invoke(main, ["--ansible-dir", str(tmp_path)])
+    assert result.exit_code == 0
+
+
+def test_extract_skips_println():
+    """Expressions with 'println' (Go template) are skipped."""
+    content = 'value: "{{ println something }}"'
+    expressions = _extract_expressions(content)
+    assert len(expressions) == 0
+
+
+def test_extract_skips_state_dot():
+    """Expressions with .State. patterns are skipped."""
+    content = 'value: "{{ foo.State.Running }}"'
+    expressions = _extract_expressions(content)
+    assert len(expressions) == 0
+
+
+def test_render_now_with_format():
+    """now() with a format argument works."""
+    ok, _ = _render_expression("now('%Y-%m-%d')")
+    assert ok
+
+
+def test_find_yaml_files_skips_molecule(tmp_path: Path) -> None:
+    """Molecule directories are excluded from file search."""
+    from devx.tools.check_jinja_expr import _find_yaml_files
+
+    (tmp_path / "tasks.yml").write_text("value: test\n")
+    (tmp_path / "molecule").mkdir()
+    (tmp_path / "molecule" / "test.yml").write_text("value: test\n")
+    files = _find_yaml_files(tmp_path)
+    assert all("molecule" not in f.parts for f in files)

tests/unit/test_utils_api.py

@@ -0,0 +1,171 @@
+"""Unit tests for devx.utils.api.APIClient."""
+
+from __future__ import annotations
+
+from unittest.mock import MagicMock, patch
+
+import pytest
+import requests
+
+from devx.utils.api import APIClient
+
+
+class TestAPIClient:
+    @patch("devx.utils.api.requests.request")
+    def test_get(self, mock_req):
+        mock_resp = MagicMock()
+        mock_resp.raise_for_status.return_value = None
+        mock_req.return_value = mock_resp
+        client = APIClient("https://api.example.com", {"Authorization": "Bearer token"})
+        result = client.get("/users")
+        assert result is mock_resp
+        mock_req.assert_called_once_with(
+            "GET",
+            "https://api.example.com/users",
+            headers={"Authorization": "Bearer token"},
+            timeout=30,
+            verify=True,
+        )
+
+    @patch("devx.utils.api.requests.request")
+    def test_post(self, mock_req):
+        mock_resp = MagicMock()
+        mock_resp.raise_for_status.return_value = None
+        mock_req.return_value = mock_resp
+        client = APIClient("https://api.example.com", {})
+        client.post("/users", json={"name": "alice"})
+        mock_req.assert_called_once_with(
+            "POST",
+            "https://api.example.com/users",
+            headers={},
+            timeout=30,
+            verify=True,
+            json={"name": "alice"},
+        )
+
+    @patch("devx.utils.api.requests.request")
+    def test_put(self, mock_req):
+        mock_resp = MagicMock()
+        mock_resp.raise_for_status.return_value = None
+        mock_req.return_value = mock_resp
+        client = APIClient("https://api.example.com", {})
+        client.put("/users/1", json={"name": "bob"})
+        mock_req.assert_called_once_with(
+            "PUT",
+            "https://api.example.com/users/1",
+            headers={},
+            timeout=30,
+            verify=True,
+            json={"name": "bob"},
+        )
+
+    @patch("devx.utils.api.requests.request")
+    def test_delete(self, mock_req):
+        mock_resp = MagicMock()
+        mock_resp.raise_for_status.return_value = None
+        mock_req.return_value = mock_resp
+        client = APIClient("https://api.example.com", {})
+        client.delete("/users/1")
+        mock_req.assert_called_once_with(
+            "DELETE",
+            "https://api.example.com/users/1",
+            headers={},
+            timeout=30,
+            verify=True,
+        )
+
+    @patch("devx.utils.api.requests.request")
+    def test_patch(self, mock_req):
+        mock_resp = MagicMock()
+        mock_resp.raise_for_status.return_value = None
+        mock_req.return_value = mock_resp
+        client = APIClient("https://api.example.com", {})
+        client.patch("/users/1", json={"name": "carol"})
+        mock_req.assert_called_once_with(
+            "PATCH",
+            "https://api.example.com/users/1",
+            headers={},
+            timeout=30,
+            verify=True,
+            json={"name": "carol"},
+        )
+
+    @patch("devx.utils.api.requests.request")
+    def test_auth_tuple(self, mock_req):
+        mock_resp = MagicMock()
+        mock_resp.raise_for_status.return_value = None
+        mock_req.return_value = mock_resp
+        client = APIClient("https://api.example.com", {}, auth=("admin", "pass"))
+        client.get("/data")
+        mock_req.assert_called_once_with(
+            "GET",
+            "https://api.example.com/data",
+            headers={},
+            timeout=30,
+            verify=True,
+            auth=("admin", "pass"),
+        )
+
+    @patch("devx.utils.api.requests.request")
+    def test_custom_timeout_and_verify(self, mock_req):
+        mock_resp = MagicMock()
+        mock_resp.raise_for_status.return_value = None
+        mock_req.return_value = mock_resp
+        client = APIClient("https://api.example.com", {}, timeout=60, verify=False)
+        client.get("/data")
+        mock_req.assert_called_once_with(
+            "GET",
+            "https://api.example.com/data",
+            headers={},
+            timeout=60,
+            verify=False,
+        )
+
+    @patch("devx.utils.api.requests.request")
+    def test_raises_on_error(self, mock_req):
+        mock_resp = MagicMock()
+        mock_resp.raise_for_status.side_effect = requests.HTTPError("500")
+        mock_req.return_value = mock_resp
+        client = APIClient("https://api.example.com", {})
+        with pytest.raises(requests.HTTPError):
+            client.get("/fail")
+
+    @patch("devx.utils.api.requests.request")
+    def test_strips_trailing_slash(self, mock_req):
+        mock_resp = MagicMock()
+        mock_resp.raise_for_status.return_value = None
+        mock_req.return_value = mock_resp
+        client = APIClient("https://api.example.com/", {})
+        client.get("/users")
+        mock_req.assert_called_once_with(
+            "GET",
+            "https://api.example.com/users",
+            headers={},
+            timeout=30,
+            verify=True,
+        )
+
+    @patch("devx.utils.api.requests.request")
+    def test_kwargs_override_defaults(self, mock_req):
+        mock_resp = MagicMock()
+        mock_resp.raise_for_status.return_value = None
+        mock_req.return_value = mock_resp
+        client = APIClient("https://api.example.com", {}, timeout=30)
+        client.get("/slow", timeout=120)
+        mock_req.assert_called_once_with(
+            "GET",
+            "https://api.example.com/slow",
+            headers={},
+            timeout=120,
+            verify=True,
+        )
+
+    @patch("devx.utils.api.requests.request")
+    def test_no_auth_when_not_set(self, mock_req):
+        mock_resp = MagicMock()
+        mock_resp.raise_for_status.return_value = None
+        mock_req.return_value = mock_resp
+        client = APIClient("https://api.example.com", {})
+        client.get("/data")
+        call_kwargs = mock_req.call_args.kwargs
+        assert "auth" not in call_kwargs

tests/unit/test_utils_jinja.py

@@ -0,0 +1,161 @@
+"""Unit tests for devx.utils.jinja."""
+
+from __future__ import annotations
+
+import jinja2
+
+from devx.utils.jinja import (
+    make_env,
+    make_value_env,
+    regex_escape,
+    regex_replace,
+    regex_search,
+    render_manifest_values,
+    render_template,
+    render_value,
+    to_bool,
+    to_json,
+)
+
+
+class TestFilters:
+    def test_to_json(self):
+        assert to_json({"a": 1}) == '{"a": 1}'
+
+    def test_to_json_list(self):
+        assert to_json([1, 2]) == "[1, 2]"
+
+    def test_to_bool_true(self):
+        assert to_bool(True) is True
+
+    def test_to_bool_false(self):
+        assert to_bool(False) is False
+
+    def test_to_bool_string_true(self):
+        assert to_bool("yes") is True
+
+    def test_to_bool_string_false(self):
+        assert to_bool("false") is False
+
+    def test_to_bool_empty_string(self):
+        assert to_bool("") is False
+
+    def test_to_bool_none(self):
+        assert to_bool(None) is False
+
+    def test_to_bool_int(self):
+        assert to_bool(1) is True
+        assert to_bool(0) is False
+
+    def test_regex_replace(self):
+        assert regex_replace("hello world", "world", "there") == "hello there"
+
+    def test_regex_replace_with_pattern(self):
+        assert regex_replace("abc123", r"\d+", "X") == "abcX"
+
+    def test_regex_escape(self):
+        assert regex_escape("a.b*c") == "a\\.b\\*c"
+
+    def test_regex_search_found(self):
+        assert regex_search("hello world", r"world") == "world"
+
+    def test_regex_search_not_found(self):
+        assert regex_search("hello", r"world") is None
+
+    def test_regex_search_group(self):
+        assert regex_search("abc123", r"\d+") == "123"
+
+
+class TestMakeEnv:
+    def test_returns_environment(self, tmp_path):
+        (tmp_path / "test.j2").write_text("hello {{ name }}")
+        env = make_env(str(tmp_path))
+        assert isinstance(env, jinja2.Environment)
+
+    def test_has_filters(self, tmp_path):
+        env = make_env(str(tmp_path))
+        assert "to_json" in env.filters
+        assert "bool" in env.filters
+        assert "regex_replace" in env.filters
+        assert "regex_escape" in env.filters
+        assert "regex_search" in env.filters
+
+    def test_cached(self, tmp_path):
+        env1 = make_env(str(tmp_path))
+        env2 = make_env(str(tmp_path))
+        assert env1 is env2
+
+    def test_auto_reload_disabled(self, tmp_path):
+        env = make_env(str(tmp_path))
+        assert env.auto_reload is False
+
+    def test_strict_undefined(self, tmp_path):
+        env = make_env(str(tmp_path))
+        assert env.undefined is jinja2.StrictUndefined
+
+
+class TestMakeValueEnv:
+    def test_returns_environment(self):
+        env = make_value_env()
+        assert isinstance(env, jinja2.Environment)
+
+    def test_chainable_undefined(self):
+        env = make_value_env()
+        assert env.undefined is jinja2.ChainableUndefined
+
+    def test_cached(self):
+        assert make_value_env() is make_value_env()
+
+    def test_has_filters(self):
+        env = make_value_env()
+        assert "to_json" in env.filters
+
+
+class TestRenderTemplate:
+    def test_renders_named_template(self, tmp_path):
+        (tmp_path / "test.j2").write_text("hello {{ name }}")
+        env = make_env(str(tmp_path))
+        assert render_template(env, "test.j2", name="world") == "hello world"
+
+    def test_renders_with_filters(self, tmp_path):
+        (tmp_path / "test.j2").write_text("{{ data | to_json }}")
+        env = make_env(str(tmp_path))
+        assert render_template(env, "test.j2", data={"a": 1}) == '{"a": 1}'
+
+
+class TestRenderValue:
+    def test_renders_string_with_expressions(self):
+        assert render_value("hello {{ name }}", {"name": "world"}) == "hello world"
+
+    def test_passes_through_non_string(self):
+        assert render_value(42, {}) == 42
+
+    def test_passes_through_string_without_expressions(self):
+        assert render_value("plain text", {}) == "plain text"
+
+    def test_passes_through_none(self):
+        assert render_value(None, {}) is None
+
+
+class TestRenderManifestValues:
+    def test_renders_dict_values(self):
+        result = render_manifest_values({"key": "{{ value }}"}, {"value": "rendered"})
+        assert result == {"key": "rendered"}
+
+    def test_renders_list_values(self):
+        result = render_manifest_values(["{{ a }}", "{{ b }}"], {"a": "1", "b": "2"})
+        assert result == ["1", "2"]
+
+    def test_renders_nested(self):
+        result = render_manifest_values({"outer": {"inner": "{{ x }}"}}, {"x": "yes"})
+        assert result == {"outer": {"inner": "yes"}}
+
+    def test_passes_through_non_string(self):
+        result = render_manifest_values({"n": 42, "b": True, "l": [1, 2]}, {})
+        assert result == {"n": 42, "b": True, "l": [1, 2]}
+
+    def test_empty_dict(self):
+        assert render_manifest_values({}, {}) == {}
+
+    def test_empty_list(self):
+        assert render_manifest_values([], {}) == []

tests/unit/test_utils_ui.py

@@ -0,0 +1,101 @@
+"""Unit tests for devx.utils.ui."""
+
+from __future__ import annotations
+
+import logging
+from unittest.mock import patch
+
+import pytest
+
+import devx.utils.ui as ui_mod
+from devx.utils.ui import _console_level, configure_ui, say
+
+
+class TestConsoleLevel:
+    def test_default_is_info(self) -> None:
+        with patch.dict("os.environ", {}, clear=True):
+            assert _console_level() == logging.INFO
+
+    def test_env_override(self, monkeypatch: pytest.MonkeyPatch) -> None:
+        monkeypatch.setenv("DEVX_LOG_LEVEL", "DEBUG")
+        assert _console_level() == logging.DEBUG
+
+    def test_invalid_fallback(self, monkeypatch: pytest.MonkeyPatch) -> None:
+        monkeypatch.setenv("DEVX_LOG_LEVEL", "VERBOSE")
+        assert _console_level() == logging.INFO
+
+    def test_custom_env_var(self, monkeypatch: pytest.MonkeyPatch) -> None:
+        configure_ui(log_level_env_var="GRM_LOG_LEVEL")
+        try:
+            monkeypatch.setenv("GRM_LOG_LEVEL", "DEBUG")
+            monkeypatch.delenv("DEVX_LOG_LEVEL", raising=False)
+            assert _console_level() == logging.DEBUG
+        finally:
+            configure_ui()
+
+
+class TestSay:
+    def test_echoes_to_console(self) -> None:
+        with patch("devx.utils.ui.click.echo") as mock_echo:
+            say("hello")
+        mock_echo.assert_called_once_with("hello", err=False)
+
+    def test_logs_at_info_level(self) -> None:
+        with (
+            patch("devx.utils.ui.click.echo"),
+            patch("devx.utils.ui.logging.getLogger") as mock_get_logger,
+        ):
+            mock_logger = mock_get_logger.return_value
+            say("hello")
+        mock_logger.log.assert_called_once_with(logging.INFO, "hello")
+
+    def test_passes_level_and_err(self) -> None:
+        with (
+            patch("devx.utils.ui.click.echo") as mock_echo,
+            patch("devx.utils.ui.logging.getLogger") as mock_get_logger,
+        ):
+            mock_logger = mock_get_logger.return_value
+            say("error msg", level=logging.ERROR, err=True)
+        mock_echo.assert_called_once_with("error msg", err=True)
+        mock_logger.log.assert_called_once_with(logging.ERROR, "error msg")
+
+    def test_suppresses_console_below_level(self, monkeypatch: pytest.MonkeyPatch) -> None:
+        monkeypatch.setenv("DEVX_LOG_LEVEL", "WARNING")
+        with (
+            patch("devx.utils.ui.click.echo") as mock_echo,
+            patch("devx.utils.ui.logging.getLogger") as mock_get_logger,
+        ):
+            mock_logger = mock_get_logger.return_value
+            say("debug msg", level=logging.DEBUG)
+        mock_echo.assert_not_called()
+        mock_logger.log.assert_called_once_with(logging.DEBUG, "debug msg")
+
+    def test_color_applied(self) -> None:
+        with (
+            patch("devx.utils.ui.click.echo") as mock_echo,
+            patch("devx.utils.ui.click.style") as mock_style,
+        ):
+            mock_style.return_value = "styled-output"
+            say("success", color="green")
+        mock_style.assert_called_once_with("success", fg="green")
+        mock_echo.assert_called_once_with("styled-output", err=False)
+
+    def test_custom_logger_name(self) -> None:
+        configure_ui(logger_name="grm")
+        try:
+            with (
+                patch("devx.utils.ui.click.echo"),
+                patch("devx.utils.ui.logging.getLogger") as mock_get_logger,
+            ):
+                say("hello")
+            mock_get_logger.assert_called_with("grm")
+        finally:
+            configure_ui()
+
+
+class TestConfigureUi:
+    def test_reset_to_defaults(self) -> None:
+        configure_ui(log_level_env_var="GRM_LOG_LEVEL", logger_name="grm")
+        configure_ui()
+        assert ui_mod._LOG_LEVEL_ENV_VAR == "DEVX_LOG_LEVEL"
+        assert ui_mod._LOGGER_NAME == "devx"

tests/unit/test_wait_for_checks.py

@@ -0,0 +1,272 @@
+"""Unit tests for devx.ci.wait_for_checks."""
+
+from unittest.mock import MagicMock, patch
+
+import pytest
+from click.testing import CliRunner
+
+from devx.ci.wait_for_checks import (
+    main,
+    poll_until_complete,
+    query_job_status,
+)
+
+
+def _mock_response(status_code: int = 200, json_data: object | None = None) -> MagicMock:
+    m = MagicMock()
+    m.status_code = status_code
+    if json_data is None:
+        m.json.side_effect = ValueError("no json")
+    else:
+        m.json.return_value = json_data
+    return m
+
+
+class TestQueryJobStatus:
+    @patch("devx.ci.wait_for_checks.requests.get")
+    def test_returns_matching_jobs(self, mock_get: MagicMock) -> None:
+        """Jobs whose name starts with the prefix are returned."""
+        mock_get.side_effect = [
+            _mock_response(200, [{"id": 1}, {"id": 2}]),
+            _mock_response(200, [{"name": "molecule-tests (1)", "status": "completed", "conclusion": "success"}]),
+            _mock_response(200, [{"name": "other-job", "status": "completed", "conclusion": "success"}]),
+        ]
+        result = query_job_status("https://api", "tok", "o/r", "molecule-tests")
+        assert len(result) == 1
+        assert result[0]["name"] == "molecule-tests (1)"
+        assert result[0]["status"] == "completed"
+        assert result[0]["conclusion"] == "success"
+
+    @patch("devx.ci.wait_for_checks.requests.get")
+    def test_no_matching_jobs(self, mock_get: MagicMock) -> None:
+        """When no job names match the prefix, returns empty list."""
+        mock_get.side_effect = [
+            _mock_response(200, [{"id": 1}]),
+            _mock_response(200, [{"name": "other-job", "status": "completed", "conclusion": "success"}]),
+        ]
+        result = query_job_status("https://api", "tok", "o/r", "molecule-tests")
+        assert result == []
+
+    @patch("devx.ci.wait_for_checks.requests.get")
+    def test_api_error_returns_empty(self, mock_get: MagicMock) -> None:
+        """Network errors on the runs endpoint return an empty list."""
+        import requests
+
+        mock_get.side_effect = requests.ConnectionError("down")
+        result = query_job_status("https://api", "tok", "o/r", "molecule-tests")
+        assert result == []
+
+    @patch("devx.ci.wait_for_checks.requests.get")
+    def test_non_200_returns_empty(self, mock_get: MagicMock) -> None:
+        """Non-200 on runs endpoint returns empty list."""
+        mock_get.side_effect = [_mock_response(500, {"message": "err"})]
+        result = query_job_status("https://api", "tok", "o/r", "molecule-tests")
+        assert result == []
+
+    @patch("devx.ci.wait_for_checks.requests.get")
+    def test_jobs_as_dict_with_jobs_key(self, mock_get: MagicMock) -> None:
+        """Jobs endpoint returning {'jobs': [...]} dict is handled."""
+        mock_get.side_effect = [
+            _mock_response(200, [{"id": 1}]),
+            _mock_response(
+                200, {"jobs": [{"name": "molecule-tests (1)", "status": "in_progress", "conclusion": None}]}
+            ),
+        ]
+        result = query_job_status("https://api", "tok", "o/r", "molecule-tests")
+        assert len(result) == 1
+        assert result[0]["status"] == "in_progress"
+
+    @patch("devx.ci.wait_for_checks.requests.get")
+    def test_runs_as_dict_with_runs_key(self, mock_get: MagicMock) -> None:
+        """Runs endpoint returning {'runs': [...]} dict is handled."""
+        mock_get.side_effect = [
+            _mock_response(200, {"runs": [{"id": 1}]}),
+            _mock_response(200, [{"name": "molecule-tests (1)", "status": "completed", "conclusion": "success"}]),
+        ]
+        result = query_job_status("https://api", "tok", "o/r", "molecule-tests")
+        assert len(result) == 1
+
+    @patch("devx.ci.wait_for_checks.requests.get")
+    def test_jobs_endpoint_error_skips_run(self, mock_get: MagicMock) -> None:
+        """A failed jobs query for one run doesn't abort the whole call."""
+        mock_get.side_effect = [
+            _mock_response(200, [{"id": 1}, {"id": 2}]),
+            _mock_response(500, {"message": "err"}),
+            _mock_response(200, [{"name": "molecule-tests (1)", "status": "completed", "conclusion": "success"}]),
+        ]
+        result = query_job_status("https://api", "tok", "o/r", "molecule-tests")
+        assert len(result) == 1
+
+    @patch("devx.ci.wait_for_checks.requests.get")
+    def test_run_without_id_skipped(self, mock_get: MagicMock) -> None:
+        """Runs missing an 'id' field are skipped."""
+        mock_get.side_effect = [
+            _mock_response(200, [{"foo": "bar"}, {"id": 1}]),
+            _mock_response(200, [{"name": "molecule-tests (1)", "status": "completed", "conclusion": "success"}]),
+        ]
+        result = query_job_status("https://api", "tok", "o/r", "molecule-tests")
+        assert len(result) == 1
+
+    @patch("devx.ci.wait_for_checks.requests.get")
+    def test_jobs_query_exception_skips_run(self, mock_get: MagicMock) -> None:
+        """A ConnectionError on the jobs endpoint for one run is skipped."""
+        import requests
+
+        mock_get.side_effect = [
+            _mock_response(200, [{"id": 1}, {"id": 2}]),
+            requests.ConnectionError("down"),
+            _mock_response(200, [{"name": "molecule-tests (1)", "status": "completed", "conclusion": "success"}]),
+        ]
+        result = query_job_status("https://api", "tok", "o/r", "molecule-tests")
+        assert len(result) == 1
+
+    @patch("devx.ci.wait_for_checks.requests.get")
+    def test_jobs_json_value_error_skips_run(self, mock_get: MagicMock) -> None:
+        """A ValueError (bad JSON) on the jobs endpoint is skipped."""
+        mock_get.side_effect = [
+            _mock_response(200, [{"id": 1}]),
+            _mock_response(200),  # json raises ValueError by default
+        ]
+        result = query_job_status("https://api", "tok", "o/r", "molecule-tests")
+        assert result == []
+
+
+class TestPollUntilComplete:
+    @patch("devx.ci.wait_for_checks.time.sleep")
+    @patch("devx.ci.wait_for_checks.time.monotonic")
+    @patch("devx.ci.wait_for_checks.query_job_status")
+    def test_all_jobs_succeed(self, mock_query: MagicMock, mock_mono: MagicMock, mock_sleep: MagicMock) -> None:
+        """All jobs completed with success → returns 0."""
+        mock_query.return_value = [{"name": "molecule-tests (1)", "status": "completed", "conclusion": "success"}]
+        mock_mono.side_effect = [0.0, 0.0]
+        code = poll_until_complete("https://api", "tok", "o/r", "molecule-tests", timeout=100, interval=10)
+        assert code == 0
+
+    @patch("devx.ci.wait_for_checks.time.sleep")
+    @patch("devx.ci.wait_for_checks.time.monotonic")
+    @patch("devx.ci.wait_for_checks.query_job_status")
+    def test_job_fails(self, mock_query: MagicMock, mock_mono: MagicMock, mock_sleep: MagicMock) -> None:
+        """A job with non-success conclusion → returns 1."""
+        mock_query.return_value = [{"name": "molecule-tests (1)", "status": "completed", "conclusion": "failure"}]
+        mock_mono.side_effect = [0.0, 0.0]
+        code = poll_until_complete("https://api", "tok", "o/r", "molecule-tests", timeout=100, interval=10)
+        assert code == 1
+
+    @patch("devx.ci.wait_for_checks.time.sleep")
+    @patch("devx.ci.wait_for_checks.time.monotonic")
+    @patch("devx.ci.wait_for_checks.query_job_status")
+    def test_no_require_success(self, mock_query: MagicMock, mock_mono: MagicMock, mock_sleep: MagicMock) -> None:
+        """With require_success=False, a failed job returns 0."""
+        mock_query.return_value = [{"name": "molecule-tests (1)", "status": "completed", "conclusion": "failure"}]
+        mock_mono.side_effect = [0.0, 0.0]
+        code = poll_until_complete(
+            "https://api", "tok", "o/r", "molecule-tests", timeout=100, interval=10, require_success=False
+        )
+        assert code == 0
+
+    @patch("devx.ci.wait_for_checks.time.sleep")
+    @patch("devx.ci.wait_for_checks.time.monotonic")
+    @patch("devx.ci.wait_for_checks.query_job_status")
+    def test_timeout(self, mock_query: MagicMock, mock_mono: MagicMock, mock_sleep: MagicMock) -> None:
+        """Jobs never complete → returns 2 after timeout."""
+        mock_query.return_value = [{"name": "molecule-tests (1)", "status": "in_progress", "conclusion": None}]
+        # monotonic calls: deadline=0, while-check=0 (enter), sleep-calc=0, while-check=200 (exit)
+        mock_mono.side_effect = [0.0, 0.0, 0.0, 200.0]
+        code = poll_until_complete("https://api", "tok", "o/r", "molecule-tests", timeout=100, interval=10)
+        assert code == 2
+
+    @patch("devx.ci.wait_for_checks.time.sleep")
+    @patch("devx.ci.wait_for_checks.time.monotonic")
+    @patch("devx.ci.wait_for_checks.query_job_status")
+    def test_no_jobs_found_timeout(self, mock_query: MagicMock, mock_mono: MagicMock, mock_sleep: MagicMock) -> None:
+        """No matching jobs at all → returns 3."""
+        mock_query.return_value = []
+        # monotonic calls: deadline=0, while-check=0 (enter), sleep-calc=0, while-check=200 (exit)
+        mock_mono.side_effect = [0.0, 0.0, 0.0, 200.0]
+        code = poll_until_complete("https://api", "tok", "o/r", "molecule-tests", timeout=100, interval=10)
+        assert code == 3
+
+    @patch("devx.ci.wait_for_checks.time.sleep")
+    @patch("devx.ci.wait_for_checks.time.monotonic")
+    @patch("devx.ci.wait_for_checks.query_job_status")
+    def test_in_progress_then_success(self, mock_query: MagicMock, mock_mono: MagicMock, mock_sleep: MagicMock) -> None:
+        """First poll in_progress, second poll success → returns 0."""
+        mock_query.side_effect = [
+            [{"name": "molecule-tests (1)", "status": "in_progress", "conclusion": None}],
+            [{"name": "molecule-tests (1)", "status": "completed", "conclusion": "success"}],
+        ]
+        # monotonic: deadline=0, while=0 (enter), sleep-calc=0, while=5 (enter), success→return
+        mock_mono.side_effect = [0.0, 0.0, 0.0, 5.0]
+        code = poll_until_complete("https://api", "tok", "o/r", "molecule-tests", timeout=100, interval=10)
+        assert code == 0
+
+
+class TestMain:
+    @patch("devx.ci.wait_for_checks.get_ci_token", return_value="tok")
+    @patch("devx.ci.wait_for_checks.poll_until_complete", return_value=0)
+    def test_success_exit_code(self, mock_poll: MagicMock, mock_token: MagicMock) -> None:
+        runner = CliRunner()
+        result = runner.invoke(main, ["--job-name", "molecule-tests", "--repo", "o/r"])
+        assert result.exit_code == 0
+
+    @patch("devx.ci.wait_for_checks.get_ci_token", return_value="tok")
+    @patch("devx.ci.wait_for_checks.poll_until_complete", return_value=1)
+    def test_failure_exit_code(self, mock_poll: MagicMock, mock_token: MagicMock) -> None:
+        runner = CliRunner()
+        result = runner.invoke(main, ["--job-name", "molecule-tests", "--repo", "o/r"])
+        assert result.exit_code == 1
+
+    @patch("devx.ci.wait_for_checks.get_ci_token", return_value="tok")
+    @patch("devx.ci.wait_for_checks.poll_until_complete", return_value=2)
+    def test_timeout_exit_code(self, mock_poll: MagicMock, mock_token: MagicMock) -> None:
+        runner = CliRunner()
+        result = runner.invoke(main, ["--job-name", "molecule-tests", "--repo", "o/r"])
+        assert result.exit_code == 2
+
+    @patch("devx.ci.wait_for_checks.get_ci_token", return_value="tok")
+    @patch("devx.ci.wait_for_checks.poll_until_complete", return_value=3)
+    def test_api_error_exit_code(self, mock_poll: MagicMock, mock_token: MagicMock) -> None:
+        runner = CliRunner()
+        result = runner.invoke(main, ["--job-name", "molecule-tests", "--repo", "o/r"])
+        assert result.exit_code == 3
+
+    def test_missing_job_name(self) -> None:
+        runner = CliRunner()
+        result = runner.invoke(main, ["--repo", "o/r"])
+        assert result.exit_code != 0
+
+    def test_missing_repo(self, monkeypatch: pytest.MonkeyPatch) -> None:
+        monkeypatch.delenv("GITHUB_REPOSITORY", raising=False)
+        runner = CliRunner()
+        result = runner.invoke(main, ["--job-name", "molecule-tests"])
+        assert result.exit_code != 0
+
+    @patch("devx.ci.wait_for_checks.get_ci_token", return_value="tok")
+    @patch("devx.ci.wait_for_checks.poll_until_complete", return_value=0)
+    def test_repo_from_env(self, mock_poll: MagicMock, mock_token: MagicMock, monkeypatch: pytest.MonkeyPatch) -> None:
+        monkeypatch.setenv("GITHUB_REPOSITORY", "oblachno-oss/grm")
+        runner = CliRunner()
+        result = runner.invoke(main, ["--job-name", "molecule-tests"])
+        assert result.exit_code == 0
+        args, kwargs = mock_poll.call_args
+        assert args[2] == "oblachno-oss/grm"
+
+    @patch("devx.ci.wait_for_checks.get_ci_token", return_value="tok")
+    @patch("devx.ci.wait_for_checks.poll_until_complete", return_value=0)
+    def test_invalid_timeout(self, mock_poll: MagicMock, mock_token: MagicMock) -> None:
+        runner = CliRunner()
+        result = runner.invoke(main, ["--job-name", "molecule-tests", "--repo", "o/r", "--timeout", "0"])
+        assert result.exit_code != 0
+
+    @patch("devx.ci.wait_for_checks.get_ci_token", return_value="tok")
+    @patch("devx.ci.wait_for_checks.poll_until_complete", return_value=0)
+    def test_invalid_interval(self, mock_poll: MagicMock, mock_token: MagicMock) -> None:
+        runner = CliRunner()
+        result = runner.invoke(main, ["--job-name", "molecule-tests", "--repo", "o/r", "--poll-interval", "0"])
+        assert result.exit_code != 0
+
+    @patch("devx.ci.wait_for_checks.get_ci_token", side_effect=__import__("click").ClickException("no token"))
+    def test_no_token_exit_3(self, mock_token: MagicMock) -> None:
+        runner = CliRunner()
+        result = runner.invoke(main, ["--job-name", "molecule-tests", "--repo", "o/r"])
+        assert result.exit_code == 3