chore: update badge URLs to commit a506e113 [skip ci]

Co-authored-by: emil User <emil.simeonov@tutanota.com>

.gitea/workflows/build-images.yml

@@ -32,6 +32,11 @@ concurrency:
 jobs:
   build-and-push:
     runs-on: docker
+    container:
+      image: git.oblachno.oblachno.fyi/oblachno-oss/runner-images/ci-full:latest
+      credentials:
+        username: ${{ vars.CI_GITEA_USERNAME }}
+        password: ${{ secrets.CI_GITEA_API_TOKEN }}
     timeout-minutes: 30
     outputs:
       is-release: ${{ steps.check.outputs.is-release }}
@@ -115,6 +120,11 @@ jobs:
     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: ${{ vars.CI_GITEA_USERNAME }}
+        password: ${{ secrets.CI_GITEA_API_TOKEN }}
     timeout-minutes: 10
     steps:
       - uses: actions/checkout@v4

.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: ${{ vars.CI_GITEA_USERNAME }}
+        password: ${{ secrets.CI_GITEA_API_TOKEN }}
     timeout-minutes: 15
     defaults:
       run:
@@ -46,7 +50,7 @@ jobs:
       - name: Check unit test speed
         run: |
           . .venv/bin/activate 2>/dev/null || true
-          python3 -m devx.tools.check_test_speed --max-seconds 6 --max-single-seconds 0.5
+          python3 -m devx.tools.check_test_speed --max-seconds 15 --max-single-seconds 0.5
       - name: Documentation gate (coverage + stale refs + lint + version refs + prose)
         env:
           DEVX_DOC_COVERAGE_STRICT: "1"
@@ -140,7 +144,11 @@ 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: ${{ vars.CI_GITEA_USERNAME }}
+        password: ${{ secrets.CI_GITEA_API_TOKEN }}
     timeout-minutes: 10
     defaults:
       run:

.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: ${{ vars.CI_GITEA_USERNAME }}
+        password: ${{ secrets.CI_GITEA_API_TOKEN }}
     timeout-minutes: 10
     defaults:
       run:
@@ -99,7 +103,11 @@ jobs:
     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: ${{ vars.CI_GITEA_USERNAME }}
+        password: ${{ secrets.CI_GITEA_API_TOKEN }}
     timeout-minutes: 15
     outputs:
       tag: ${{ steps.release-tag.outputs.tag }}

.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:
@@ -71,7 +76,7 @@ src/devx/
 ├── translations.json    # Translation strings (en, bg, de, pl, ru, zh)
 ├── ci/                  # CI/CD automation modules (run by workflows)
 │   ├── release.py       # Automated versioning, tagging, changelog
-│   ├── publish.py       # Build and publish to Gitea PyPI registry (--skip-build for non-Python repos)
+│   ├── publish.py       # Build, publish to Gitea PyPI registry, create Gitea release (with retry)
 │   ├── auto_merge.py    # Squash-merge PRs with task ID validation
 │   ├── check_auto_merge_ready.py  # Pre-merge validation gate (branch, PR title, Vikunja, behind-master)
 │   ├── _shared.py      # Shared utilities (get_latest_tag)
@@ -90,7 +95,10 @@ 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
 ├── 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 +121,17 @@ 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  # Check set_fact tasks don't misuse to_json
+│   ├── check_alert_rules.py  # Validate Prometheus alert rules with promtool
+│   ├── check_ansible_no_log.py  # Check Ansible tasks for missing no_log on secrets
+│   ├── check_ansible_patterns.py  # Detect dangerous failure-masking patterns
+│   ├── check_jinja_expr.py  # Validate Jinja2 expressions in Ansible files
+│   ├── check_ansible_no_state_absent_on_db.py  # Prevent state:absent on DB paths
 │   └── _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 +139,14 @@ 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
     ├── 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
 ```
@@ -310,6 +327,20 @@ by `python -m devx.tools.install_tools` and configured by
 - `create_pr()` / `merge_pr()` / `review_pr()` — Pull request operations
 - `create_release()` / `list_releases()` — Release management
 
+**`devx.gitea_cli.configure_tea_login()`** — Configures tea login in
+containerized CI environments where `make setup` was not called. Used by
+`publish.py` (`--auto-login`) and `notify_failure.py` (`--auto-login`).
+Raises `TeaCLIError` if login configuration fails — this prevents cryptic
+"no available login" errors from subsequent tea commands.
+
+**Error handling**: `TeaCLI._run()` includes both stdout and stderr in
+`TeaCLIError` messages, because `tea` writes some errors (for example,
+"no available login") to stdout, not stderr.
+
+**Release creation retry**: `publish.py` retries Gitea release creation
+up to 3 times with exponential backoff (2s, 4s) on transient failures.
+"Already exists" errors are treated as success (idempotent).
+
 ### git-cliff Commit Preprocessing
 
 Merge commits on master have the format `DEVX-N: <conventional commit>`. The

CHANGELOG.md

@@ -2,6 +2,138 @@
 
 All notable changes to this project will be documented in this file.
 
+## [0.50.0] - 2026-08-09
+
+### Features
+
+- Add 5 standalone lint scripts from infra
+
+## [0.49.0] - 2026-08-09
+
+### Features
+
+- Sync missing features from v0.49.x line to master
+
+## [0.48.2] - 2026-08-09
+
+### Bug Fixes
+
+- Remove dead translation keys and add missing one
+
+## [0.48.1] - 2026-08-08
+
+### Bug Fixes
+
+- *(setup)* Extract version from filename for mirror installs
+
+## [0.48.0] - 2026-08-08
+
+### Features
+
+- *(setup)* Mirror Ansible collections from Gitea registry with auth
+
+## [0.47.10] - 2026-08-05
+
+### Bug Fixes
+
+- Unique molecule container names per CI runner
+
+## [0.47.9] - 2026-08-03
+
+### Bug Fixes
+
+- Unique molecule container names per CI runner
+
+## [0.47.8] - 2026-08-03
+
+### Bug Fixes
+
+- Increase CI_SCALE_FACTOR default from 4 to 6
+
+## [0.47.7] - 2026-08-03
+
+### Bug Fixes
+
+- Scale check_test_speed limits on CI runners
+
+## [0.47.6] - 2026-08-03
+
+### Bug Fixes
+
+- Configure git auth in setup_image for git+https deps
+
+## [0.47.5] - 2026-08-03
+
+### Bug Fixes
+
+- Push wiki to main branch instead of master
+
+## [0.47.4] - 2026-08-03
+
+### Bug Fixes
+
+- Add User-Agent header to _download in install_tools
+
+## [0.47.3] - 2026-07-17
+
+### Bug Fixes
+
+- Bake promtool into ci-full image, add download timeout, speed up tests
+
+## [0.47.2] - 2026-07-17
+
+### Bug Fixes
+
+- Add retry logic to TeaCLI for transient HTTP errors (502/503/504/429)
+
+## [0.47.1] - 2026-07-16
+
+### Bug Fixes
+
+- Tea CLI login failure handling, error messages, release retry
+
+## [0.47.0] - 2026-07-14
+
+### Features
+
+- Add promtool to install_tools for alert rule validation
+
+## [0.46.0] - 2026-07-14
+
+### Features
+
+- Make check_test_isolation configurable via pyproject.toml
+
+## [0.45.1] - 2026-07-14
+
+### Bug Fixes
+
+- URL-encode package names and versions in clean_images API calls
+
+## [0.45.0] - 2026-07-14
+
+### Features
+
+- Add IO_INTERNAL_CALLS to check_test_isolation
+
+## [0.44.2] - 2026-07-14
+
+### Bug Fixes
+
+- Use legacy Docker builder to avoid Gitea registry 403
+
+## [0.44.1] - 2026-07-14
+
+### Bug Fixes
+
+- Disable Docker buildx provenance attestation
+
+## [0.44.0] - 2026-07-13
+
+### Features
+
+- Add fix_pr_title module and update_pr API method
+
 ## [0.43.0] - 2026-07-13
 
 ### Features

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/29e3ef9cfd8e7d5605c7189cf26f1fc0b0cff756/coverage.svg)](https://git.oblachno.oblachno.fyi/oblachno-oss/devx/actions)
-[![Tests](https://git.oblachno.oblachno.fyi/oblachno-oss/devx/raw/commit/29e3ef9cfd8e7d5605c7189cf26f1fc0b0cff756/tests.svg)](https://git.oblachno.oblachno.fyi/oblachno-oss/devx/actions)
-[![Docs](https://git.oblachno.oblachno.fyi/oblachno-oss/devx/raw/commit/29e3ef9cfd8e7d5605c7189cf26f1fc0b0cff756/docs.svg)](https://git.oblachno.oblachno.fyi/oblachno-oss/devx/wiki)
-[![Code Quality](https://git.oblachno.oblachno.fyi/oblachno-oss/devx/raw/commit/29e3ef9cfd8e7d5605c7189cf26f1fc0b0cff756/quality.svg)](https://git.oblachno.oblachno.fyi/oblachno-oss/devx/actions)
-[![Version](https://git.oblachno.oblachno.fyi/oblachno-oss/devx/raw/commit/29e3ef9cfd8e7d5605c7189cf26f1fc0b0cff756/version.svg)](https://git.oblachno.oblachno.fyi/oblachno-oss/devx/releases)
-[![Python](https://git.oblachno.oblachno.fyi/oblachno-oss/devx/raw/commit/29e3ef9cfd8e7d5605c7189cf26f1fc0b0cff756/python.svg)](https://www.python.org/downloads/)
+[![Coverage](https://git.oblachno.oblachno.fyi/oblachno-oss/devx/raw/commit/a506e1130cab09747bb881e0fe98093e6bcd8110/coverage.svg)](https://git.oblachno.oblachno.fyi/oblachno-oss/devx/actions)
+[![Tests](https://git.oblachno.oblachno.fyi/oblachno-oss/devx/raw/commit/a506e1130cab09747bb881e0fe98093e6bcd8110/tests.svg)](https://git.oblachno.oblachno.fyi/oblachno-oss/devx/actions)
+[![Docs](https://git.oblachno.oblachno.fyi/oblachno-oss/devx/raw/commit/a506e1130cab09747bb881e0fe98093e6bcd8110/docs.svg)](https://git.oblachno.oblachno.fyi/oblachno-oss/devx/wiki)
+[![Code Quality](https://git.oblachno.oblachno.fyi/oblachno-oss/devx/raw/commit/a506e1130cab09747bb881e0fe98093e6bcd8110/quality.svg)](https://git.oblachno.oblachno.fyi/oblachno-oss/devx/actions)
+[![Version](https://git.oblachno.oblachno.fyi/oblachno-oss/devx/raw/commit/a506e1130cab09747bb881e0fe98093e6bcd8110/version.svg)](https://git.oblachno.oblachno.fyi/oblachno-oss/devx/releases)
+[![Python](https://git.oblachno.oblachno.fyi/oblachno-oss/devx/raw/commit/a506e1130cab09747bb881e0fe98093e6bcd8110/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>=0.43.0",
+    "devx>=0.50.0",
 ]
 
 [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==0.43.0"`) or use a version constraint
-> (for example, `"devx>=0.43.0,<0.44"`).
+> `dependencies` (for example, `"devx==0.50.0"`) or use a version constraint
+> (for example, `"devx>=0.50.0,<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.

docker/ci-full/Dockerfile

@@ -20,5 +20,6 @@ COPY . /tmp/devx
 RUN pip install --no-cache-dir /tmp/devx[release,molecule,deploy] \
     && rm -rf /tmp/devx
 
-# Install git-cliff (changelog generator for release job) and OpenTofu (for infra deploy jobs)
-RUN python3 -m devx.tools.install_tools --tool git-cliff --tool tofu
+# Install git-cliff (changelog generator for release job), OpenTofu (for infra deploy jobs),
+# and promtool (Prometheus rule validator — used by every infra CI run for alert validation)
+RUN python3 -m devx.tools.install_tools --tool git-cliff --tool tofu --tool promtool

docs/decisions/0001-test-isolation-pytest-plugin-and-shift-left-quality-gates.md

@@ -40,20 +40,30 @@ invocation in any repo with devx installed automatically runs the
 static analysis. No extra Makefile target or CI step needed.
 
 The plugin (`devx.tools.check_test_isolation`) statically analyzes
-test files during `pytest_collection_finish` and emits
-`UserWarning` for violations:
+test files during `pytest_collection_finish` and **fails the test run**
+on any hard violation:
 
 - **unpatched-subprocess**: `subprocess.run/call/Popen/check_call/check_output`
-  called in a test function without `@patch`
+  called in a test function without `@patch` or `with patch(...)`
 - **unpatched-sleep**: `time.sleep` called without `@patch`
 - **unpatched-helper**: known subprocess-spawning helpers
   (`update_doc_versions`, `run_cmd`, `run_tests`) called without
   `@patch` (and without patching their internal dependencies)
 - **excessive-iterations**: `for _ in range(N)` where N > 100
+- **heavy-module-import**: `httpx`, `ansible`, etc. imported at module
+  level in test files, slowing collection for all tests
+- **reload-without-cleanup**: `importlib.reload()` called an odd number
+  of times, leaving module state modified
 
-The plugin recognizes transitive safety: if `run_cmd` is patched,
-`run_tests` (which calls `run_cmd`) is safe. This is tracked via
-`HELPER_INTERNAL_CALLS`.
+Transitive-subprocess findings (via call-graph analysis) are reported
+as **advisories** — the static analysis can't predict early exits or
+runtime branch conditions, so the runtime audit is authoritative.
+
+The plugin also wraps `subprocess.run` at runtime to catch real
+subprocess calls that leak through transitive call paths (for example
+`CliRunner.invoke(main)` → `main()` → `update_doc_versions()` →
+`subprocess.run()`). If a test spawns a real subprocess without
+`@patch`, the test fails.
 
 A standalone CLI (`python -m devx.tools.check_test_isolation`) is also
 provided for CI gates and pre-commit hooks where pytest isn't run.
@@ -85,16 +95,20 @@ is even created.
 
 - **Automatic enforcement**: The pytest plugin runs on every `pytest`
   invocation across devx, grm, and infra — no per-repo configuration
-  needed. New tests with unpatched subprocess calls emit warnings
-  immediately.
+  needed. New tests with unpatched subprocess calls fail immediately.
 - **Shift-left**: Translation gaps and test isolation violations are
   caught locally (pre-commit / `make lint`) instead of in CI.
-- **Fast feedback**: Static analysis adds <0.1s to test runs — no
-  runtime overhead.
-- **No false positives**: The transitive dependency tracking
-  (`HELPER_INTERNAL_CALLS`) correctly recognizes that patching
-  `run_cmd` makes `run_tests` safe, and patching `subprocess.run`
-  makes all helpers safe.
+- **Fast feedback**: Static analysis adds <0.1s to test runs; runtime
+  subprocess audit adds negligible overhead (wrapper checks a
+  thread-local flag).
+- **Transitive detection**: The call-graph BFS traces
+  `CliRunner.invoke(main)` → `main()` → `update_doc_versions()` →
+  `subprocess.run()`, catching indirect subprocess leaks that direct
+  analysis misses. The runtime audit provides authoritative enforcement.
+- **No false positives**: The call graph correctly recognizes that
+  patching `run_cmd` makes `run_tests` (which calls `run_cmd`) safe,
+  and class methods are excluded to avoid false positives when classes
+  like `TeaCLI` are patched.
 
 ### Negative
 
@@ -103,10 +117,12 @@ is even created.
   definitions) appears uncovered. Mitigated by `-p no:devx_test_isolation`
   in devx's own `pyproject.toml` `addopts` and `# pragma: no cover` on
   plugin hook functions.
-- **Static analysis limitations**: The plugin only sees direct calls
-  in test function bodies, not indirect calls through `main()` or
-  other wrappers. This is acceptable — the `check_test_speed` tool
-  catches the symptom (slow tests) for indirect cases.
+- **Static analysis limitations**: The call-graph BFS can't predict
+  runtime branch conditions or early exits — a test that patches
+  `shutil.which` to return `None` may skip the subprocess path
+  entirely, but the static analysis still reports it. Transitive
+  findings are advisories (exit 0) for this reason; the runtime audit
+  is authoritative.
 - **Translation burden**: Every new `_()` call in source requires
   adding 6 language translations. This is by design (all supported
   languages must be complete) but adds friction for quick prototypes.
@@ -122,21 +138,36 @@ in consumer repos.
 
 ### Disabling the Plugin
 
-- `--no-test-isolation` flag: disables analysis for a single run
+- `--no-test-isolation` flag: disables static analysis and runtime
+  subprocess audit for a single run
 - `-p no:devx_test_isolation` in `addopts`: disables for a repo
   (used in devx's own `pyproject.toml` for coverage reasons)
 
-### Strict Mode
+### Call-Graph Analysis
 
-- `--strict-test-isolation` flag: promotes warnings to errors and
-  prints a summary to stderr
-- `filterwarnings = ["error:Test isolation:UserWarning"]` in
-  `pyproject.toml`: same effect via pytest's warning filter system
+The `CallGraph` class parses all `.py` files under `src/` and builds
+a map of function → called functions. When a test calls
+`CliRunner.invoke(target)`, a BFS traces the call graph from `target`
+to find all reachable functions. Class methods are excluded from the
+call graph to avoid false positives when classes are patched (for example
+`@patch("...TeaCLI")` mocks all methods). The BFS respects `@patch`
+decorators — if a function is patched, traversal stops at that node.
+
+### Runtime Subprocess Audit
+
+The `_SubprocessAudit` singleton wraps `subprocess.run`, `call`,
+`check_call`, `check_output`, and `Popen` with thread-local
+recording wrappers. During each non-integration test, the wrapper
+records calls; if any are recorded (that is the test didn't `@patch`
+subprocess), the test fails. The wrappers check a thread-local flag,
+so inactive audits have zero overhead beyond the flag check.
 
 ### Known Subprocess Helpers
 
 The `KNOWN_SUBPROCESS_HELPERS` dict maps function names to
 descriptions. `HELPER_INTERNAL_CALLS` maps each helper to the
 function names it internally calls, enabling transitive safety
-checks. Both are defined in `check_test_isolation.py` and can be
-extended as new subprocess-spawning helpers are added to devx.
+checks for direct calls in test functions. The call-graph BFS
+handles transitive detection for `CliRunner.invoke` targets. Both
+are defined in `check_test_isolation.py` and can be extended as
+new subprocess-spawning helpers are added to devx.

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/29e3ef9cfd8e7d5605c7189cf26f1fc0b0cff756/coverage.svg)](https://git.oblachno.oblachno.fyi/oblachno-oss/devx/actions)
-[![Tests](https://git.oblachno.oblachno.fyi/oblachno-oss/devx/raw/commit/29e3ef9cfd8e7d5605c7189cf26f1fc0b0cff756/tests.svg)](https://git.oblachno.oblachno.fyi/oblachno-oss/devx/actions)
-[![Docs](https://git.oblachno.oblachno.fyi/oblachno-oss/devx/raw/commit/29e3ef9cfd8e7d5605c7189cf26f1fc0b0cff756/docs.svg)](https://git.oblachno.oblachno.fyi/oblachno-oss/devx/wiki)
-[![Code Quality](https://git.oblachno.oblachno.fyi/oblachno-oss/devx/raw/commit/29e3ef9cfd8e7d5605c7189cf26f1fc0b0cff756/quality.svg)](https://git.oblachno.oblachno.fyi/oblachno-oss/devx/actions)
-[![Version](https://git.oblachno.oblachno.fyi/oblachno-oss/devx/raw/commit/29e3ef9cfd8e7d5605c7189cf26f1fc0b0cff756/version.svg)](https://git.oblachno.oblachno.fyi/oblachno-oss/devx/releases)
-[![Python](https://git.oblachno.oblachno.fyi/oblachno-oss/devx/raw/commit/29e3ef9cfd8e7d5605c7189cf26f1fc0b0cff756/python.svg)](https://www.python.org/downloads/)
+[![Coverage](https://git.oblachno.oblachno.fyi/oblachno-oss/devx/raw/commit/a506e1130cab09747bb881e0fe98093e6bcd8110/coverage.svg)](https://git.oblachno.oblachno.fyi/oblachno-oss/devx/actions)
+[![Tests](https://git.oblachno.oblachno.fyi/oblachno-oss/devx/raw/commit/a506e1130cab09747bb881e0fe98093e6bcd8110/tests.svg)](https://git.oblachno.oblachno.fyi/oblachno-oss/devx/actions)
+[![Docs](https://git.oblachno.oblachno.fyi/oblachno-oss/devx/raw/commit/a506e1130cab09747bb881e0fe98093e6bcd8110/docs.svg)](https://git.oblachno.oblachno.fyi/oblachno-oss/devx/wiki)
+[![Code Quality](https://git.oblachno.oblachno.fyi/oblachno-oss/devx/raw/commit/a506e1130cab09747bb881e0fe98093e6bcd8110/quality.svg)](https://git.oblachno.oblachno.fyi/oblachno-oss/devx/actions)
+[![Version](https://git.oblachno.oblachno.fyi/oblachno-oss/devx/raw/commit/a506e1130cab09747bb881e0fe98093e6bcd8110/version.svg)](https://git.oblachno.oblachno.fyi/oblachno-oss/devx/releases)
+[![Python](https://git.oblachno.oblachno.fyi/oblachno-oss/devx/raw/commit/a506e1130cab09747bb881e0fe98093e6bcd8110/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>=0.43.0",
+    "devx>=0.50.0",
 ]
 
 [tool.pip]
 extra-index-url = "https://git.oblachno.oblachno.fyi/api/packages/oblachno-oss/pypi/simple"
 ```
 
-Pin a specific version if needed: `"devx==0.43.0"` or `"devx>=0.43.0,<0.44"`.
+Pin a specific version if needed: `"devx==0.50.0"` or `"devx>=0.50.0,<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/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

@@ -50,7 +50,6 @@ src/devx/
     ├── __init__.py
     ├── discover_runners.py      # Dynamic Gitea runner discovery
     ├── 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
     ├── start_docker.py          # Ensure Docker is available for molecule
     └── platforms.py             # Supported molecule platforms
@@ -87,11 +86,11 @@ 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 +108,7 @@ 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 +170,7 @@ 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.
 
@@ -288,7 +287,7 @@ Click commands from `cli.py` and verifies each has documentation in
 ### `discover_runners.py`
 
 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.
 
@@ -300,9 +299,9 @@ Distributes files matching a glob pattern across N parallel runners
 
 ### `integration_guard.py`
 
-Runs pytest with the same cross-runner failure detection mechanism used by
-`molecule_ci_guard`. If any other integration-tests matrix runner reports
-failure, the current pytest subprocess is killed and this runner exits early.
+Runs pytest with cross-runner failure detection. A background thread polls
+the Gitea API. If any other integration-tests matrix runner reports failure,
+the current pytest subprocess is killed and this runner exits early.
 
 ## Developer tools (`devx.tools`)
 
@@ -330,7 +329,7 @@ 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`
 
@@ -382,13 +381,6 @@ the supported OS platform matrix. Supports `--roles-root` for multi-role
 repositories, `--list` to list scenarios, and `--list-platforms` to list
 platforms.
 
-### `molecule_ci_guard.py`
-
-Runs molecule tests sequentially while polling the Gitea API for other runner
-failures. If any other molecule matrix runner reports failure, the current
-molecule subprocess is killed and this runner exits early. Supports both
-single-role (4-part) and multi-role (5-part) pair encoding.
-
 ### `molecule_all.py`
 
 Runs all molecule scenarios on all supported OS platforms sequentially.

docs/tech/ci-cd-workflow.md

@@ -478,15 +478,6 @@ python -m devx.molecule.distribute_molecule --list
 python -m devx.molecule.distribute_molecule --list-platforms
 ```
 
-### `molecule_ci_guard.py`
-
-Runs molecule tests sequentially while polling the Gitea API for other runner
-failures. Aborts early if another runner fails the same job.
-
-```bash
-python -m devx.molecule.molecule_ci_guard [--roles-root <dir>] pair1 pair2 ...
-```
-
 ### `validate_commit_msg.py`
 
 Validates commit messages. On feature branches: conventional commits only

docs/user/cli-commands.md

@@ -85,7 +85,7 @@ devx ci detect-release-commit
 
 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 +315,56 @@ devx ci validate-commit-msg commit-msg.txt --branch master
 Options:
 - `--branch <branch>` — override branch detection (for CI use)
 
+### `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 +373,7 @@ 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.
@@ -339,28 +389,37 @@ devx tools check-test-speed --max-seconds 4 --max-single-seconds 0.5
 Statically analyze test files for un-hermetic patterns that cause slow
 or flaky tests. Also available as a **pytest plugin** (auto-discovered
 via the `pytest11` entry point when devx is installed — runs
-automatically on every `pytest` invocation).
+automatically on every `pytest` invocation and **fails on violations**).
 
-Detected patterns:
+Detected patterns (hard errors — exit non-zero):
 
 - **unpatched-subprocess**: `subprocess.run/call/Popen/check_call/check_output`
-  called in a test function without `@patch`
+  called in a test function without `@patch` or `with patch(...)`
 - **unpatched-sleep**: `time.sleep` called without `@patch`
 - **unpatched-helper**: known subprocess-spawning helpers (`update_doc_versions`,
   `run_cmd`, `run_tests`) called without `@patch` or patching their internal deps
 - **excessive-iterations**: `for _ in range(N)` where N > 100
+- **heavy-module-import**: `httpx`, `ansible`, etc. imported at module level
+- **reload-without-cleanup**: `importlib.reload()` called an odd number of times
+
+Advisory patterns (exit 0 — runtime audit is authoritative):
+
+- **transitive-subprocess**: `CliRunner.invoke(target)` where `target`
+  transitively calls `subprocess.run` without being patched. Detected via
+  static call-graph analysis. The runtime subprocess audit catches actual
+  leaks — if a real subprocess runs without `@patch`, the test fails.
 
 ```bash
 devx tools check-test-isolation
-devx tools check-test-isolation --test-path tests/ --strict
-devx tools check-test-isolation --categories unpatched-subprocess,unpatched-sleep
+devx tools check-test-isolation --test-path tests/
+devx tools check-test-isolation --categories unpatched-subprocess,transitive-subprocess
 devx tools check-test-isolation --max-loop-iterations 50
+devx tools check-test-isolation --src-dir src/
 ```
 
 Pytest plugin options (automatic when devx is installed):
 
-- `--strict-test-isolation` — fail the test run on violations
-- `--no-test-isolation` — disable analysis for this run
+- `--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`
@@ -405,7 +464,7 @@ 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`
@@ -479,6 +538,56 @@ 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]`).
@@ -522,29 +631,3 @@ Options:
 - `--list-platforms` — list all platforms, one per line
 - `--roles-root <dir>` — roles root directory for multi-role repos (default:
   `ansible/roles`)
-
-### `devx molecule guard`
-
-Run molecule tests sequentially with CI failure polling. A background thread
-polls the Gitea API. If any other molecule matrix runner reports failure, the
-current molecule subprocess is killed and this runner exits early with code 1.
-
-```bash
-devx molecule guard pair1 pair2 pair3
-devx molecule guard --roles-root ansible/roles pair1 pair2
-```
-
-Each pair is encoded as:
-- **Single-role (4-part):** `scenario|platform_name|platform_image|platform_command`
-- **Multi-role (5-part):** `role|scenario|platform_name|platform_image|platform_command`
-
-Options:
-- `--roles-root <dir>` — roles root directory for multi-role repos
-
-Environment variables:
-- `GITEA_URL` — base URL of the Gitea instance
-- `CI_GITEA_TOKEN` — API token with repo access
-- `RUN_ID` — workflow run ID (`GITHUB_RUN_ID`)
-- `JOB_NAME` — base job name (`GITHUB_JOB`)
-- `MATRIX_INDEX` — current matrix index (runner-index)
-- `GITEA_REPOSITORY` — repository in `owner/repo` format

docs/user/getting-started.md

@@ -48,12 +48,12 @@ Add devx to your `pyproject.toml`:
 ```toml
 [project]
 dependencies = [
-    "devx>=0.43.0",
+    "devx>=0.50.0",
 ]
 
 [project.optional-dependencies]
 dev = [
-    "devx>=0.43.0",
+    "devx>=0.50.0",
 ]
 ```
 

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__ = "0.43.0"
+__version__ = "0.50.0"

src/devx/api_clients.py

@@ -224,6 +224,16 @@ class GiteaClient:
         r = self._request("GET", f"/pulls/{pr_number}")
         return r.json()
 
+    def update_pr(self, pr_number: str | int, fields: dict[str, Any]) -> dict[str, Any]:
+        """Update a pull request (e.g. title, body, state).
+
+        Args:
+            pr_number: PR number.
+            fields: Dict of fields to update (e.g. {"title": "new title"}).
+        """
+        r = self._request("PATCH", f"/pulls/{pr_number}", json=fields)
+        return r.json()
+
     def create_pr(self, title: str, head: str, base: str = "master", body: str = "") -> dict[str, Any]:
         """Create a pull request and return the PR dict.
 

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_auto_merge_ready.py

@@ -285,6 +285,26 @@ def cli(
         click.echo("=" * 60, err=True)
         for e in errors:
             click.echo(f"  - {e}", err=True)
+
+        # Remediation hints for the most common failure: PR title format
+        title_errors = [
+            e for e in errors if "PR title must follow format" in str(e) or "PR title task ID mismatch" in str(e)
+        ]
+        if title_errors and pr_number is not None and repo is not None:
+            click.echo("", err=True)
+            click.echo("REMEDIATION:", err=True)
+            click.echo(
+                _(
+                    "  Fix the PR title with:\n"
+                    "    python3 -m devx.ci.fix_pr_title --repo {repo} --pr-number {pr}\n"
+                    "  Or manually set the PR title to: '{expected}'",
+                    repo=repo,
+                    pr=pr_number,
+                    expected=f"{task_id}: <Vikunja task title>",
+                ),
+                err=True,
+            )
+
         raise click.ClickException(_("Pre-merge validation failed."))
 
     click.echo("[pre-merge-check] All auto-merge preconditions satisfied.")

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/doc_coverage.py

@@ -52,7 +52,6 @@ REQUIRED_SCRIPTS = [
     "detect_release_commit.py",
     "push_badges.py",
     "distribute_molecule.py",
-    "molecule_ci_guard.py",
     "validate_commit_msg.py",
 ]
 

src/devx/ci/fix_pr_title.py

@@ -0,0 +1,127 @@
+#!/usr/bin/env python3
+"""Auto-fix PR title to follow the ``{PREFIX}-N: <title>`` convention.
+
+Reads the task ID from the branch name, fetches the Vikunja task title,
+and updates the PR title via the Gitea API.
+
+Exit codes:
+  0 = PR title updated (or already correct)
+  1 = Error (missing token, PR not found, etc.)
+
+Usage::
+
+    python3 -m devx.ci.fix_pr_title --repo owner/repo --pr-number 123
+    python3 -m devx.ci.fix_pr_title --repo owner/repo --branch DEVX-256-fix-foo --pr-number 123
+"""
+
+from __future__ import annotations
+
+import click
+from dotenv import load_dotenv  # pyright: ignore[reportMissingImports,reportUnknownVariableType]
+
+from devx.api_clients import GiteaClient
+from devx.ci.auto_merge import extract_task_id
+from devx.ci.check_auto_merge_ready import get_vikunja_title_optional
+from devx.config import (
+    GITEA_API_URL,
+    TASK_PREFIX,
+)
+from devx.exceptions import APIError
+from devx.i18n import _
+from devx.tokens import get_ci_token
+
+load_dotenv()
+
+
+@click.command()
+@click.option("--repo", required=True, help=_("Repository in owner/name format"))
+@click.option("--pr-number", type=int, required=True, help=_("PR number to fix"))
+@click.option("--branch", default=None, help=_("Branch name (auto-fetched from PR if not given)"))
+@click.option("--dry-run", is_flag=True, help=_("Show what would change without updating"))
+def cli(repo: str, pr_number: int, branch: str | None, dry_run: bool) -> None:
+    """Fix PR title to follow the ``{PREFIX}-N: <title>`` convention."""
+    if "/" not in repo:
+        raise click.ClickException(_("Repo must be in 'owner/name' format, got: {repo}", repo=repo))
+    owner, repo_name = repo.split("/", 1)
+
+    # 1. Get CI token
+    try:
+        token = get_ci_token()
+    except click.ClickException as exc:
+        raise click.ClickException(_("CI_GITEA_API_TOKEN not set: {error}", error=str(exc))) from exc
+
+    client = GiteaClient(GITEA_API_URL, token, owner, repo_name)
+
+    # 2. Fetch PR
+    try:
+        pr = client.get_pr(pr_number)
+    except APIError as exc:
+        raise click.ClickException(_("Failed to fetch PR #{pr}: {error}", pr=pr_number, error=str(exc))) from exc
+
+    current_title = str(pr.get("title", ""))
+    if not branch:
+        branch = str(pr.get("head", {}).get("ref", ""))
+        if not branch:
+            raise click.ClickException(_("Could not determine branch name from PR #{pr}", pr=pr_number))
+
+    click.echo(f"[fix-pr-title] Branch: {branch}")
+    click.echo(f"[fix-pr-title] Current PR title: {current_title}")
+
+    # 3. Extract task ID from branch
+    task_id = extract_task_id(branch)
+    if not task_id:
+        raise click.ClickException(
+            _(
+                "No task ID found in branch '{branch}'. Expected format: {prefix}-N-description.",
+                branch=branch,
+                prefix=TASK_PREFIX,
+            )
+        )
+
+    click.echo(f"[fix-pr-title] Task ID: {task_id}")
+
+    # 4. Get Vikunja task title
+    vikunja_title = get_vikunja_title_optional(task_id)
+    if vikunja_title is None:
+        # Fallback: strip common prefixes from current title
+        # (e.g. "fix: ...", "feat: ...", "refactor: ...")
+        import re
+
+        stripped = re.sub(
+            r"^(fix|feat|refactor|chore|docs|test|ci|build|perf|style|revert)(\(.+?\))?!?:\s*", "", current_title
+        )
+        # Also strip any leading task ID prefix
+        stripped = re.sub(rf"^{TASK_PREFIX}-\d+:\s*", "", stripped)
+        vikunja_title = stripped if stripped else current_title
+        click.echo(f"[fix-pr-title] WARNING: Vikunja task not found — using stripped title: {vikunja_title}")
+    else:
+        click.echo(f"[fix-pr-title] Vikunja title: {vikunja_title}")
+
+    # 5. Build new title
+    # Defensive: strip task ID prefix from Vikunja title if present
+    if vikunja_title.startswith(f"{task_id}:"):
+        vikunja_title = vikunja_title[len(f"{task_id}:") :].strip()
+
+    new_title = f"{task_id}: {vikunja_title}"
+
+    if current_title == new_title:
+        click.echo(f"[fix-pr-title] PR title already correct: {new_title}")
+        return
+
+    click.echo(f"[fix-pr-title] New PR title: {new_title}")
+
+    if dry_run:
+        click.echo("[fix-pr-title] Dry run — not updating PR.")
+        return
+
+    # 6. Update PR title
+    try:
+        client.update_pr(pr_number, {"title": new_title})
+    except APIError as exc:
+        raise click.ClickException(_("Failed to update PR #{pr}: {error}", pr=pr_number, error=str(exc))) from exc
+
+    click.echo(f"[fix-pr-title] PR #{pr_number} title updated to: {new_title}")
+
+
+if __name__ == "__main__":  # pragma: no cover
+    cli()  # pragma: no cover

src/devx/ci/integration_guard.py

@@ -1,10 +1,9 @@
 #!/usr/bin/env python3
 """Run integration tests with cross-runner failure detection.
 
-Wraps ``pytest`` with the same Gitea API polling mechanism used by
-``molecule_ci_guard``. If any other integration-tests matrix runner
-reports failure, the current pytest subprocess is killed and this runner
-exits early with code 1.
+Wraps ``pytest`` with Gitea API polling. If any other integration-tests
+matrix runner reports failure, the current pytest subprocess is killed
+and this runner exits early with code 1.
 
 Usage::
 
@@ -35,17 +34,62 @@ import threading
 import time
 
 import click
+import requests
 
 from devx.config import REPO_NAME, REPO_OWNER
 from devx.i18n import _
-from devx.molecule.molecule_ci_guard import (
-    poll_for_other_failures,
-)
 from devx.tokens import get_ci_token
 
 POLL_INTERVAL = 10
 
 
+def get_running_jobs(gitea_url: str, owner: str, repo: str, token: str, run_id: int) -> list[dict]:
+    """Return jobs for the given workflow run."""
+    url = f"{gitea_url}/api/v1/repos/{owner}/{repo}/actions/runs/{run_id}/jobs"
+    headers = {"Authorization": f"token {token}"}
+    response = requests.get(url, headers=headers, timeout=30)
+    response.raise_for_status()
+    data = response.json()
+    return data.get("jobs", [])
+
+
+def any_other_runner_failed(jobs: list[dict], current_job_name: str, current_index: int) -> bool:
+    """Return True if any other matrix job has failed."""
+    for job in jobs:
+        name = job.get("name", "")
+        if not name.startswith(current_job_name):
+            continue
+        if name == f"{current_job_name} ({current_index})" or name == current_job_name:
+            continue
+        if job.get("conclusion") == "failure":
+            return True
+    return False
+
+
+def poll_for_other_failures(
+    gitea_url: str,
+    owner: str,
+    repo: str,
+    token: str,
+    run_id: int,
+    job_name: str,
+    current_index: int,
+    stop_event: threading.Event,
+    failed_event: threading.Event,
+) -> None:
+    """Background thread: poll API and signal if another runner fails."""
+    while not stop_event.is_set():
+        try:
+            jobs = get_running_jobs(gitea_url, owner, repo, token, run_id)
+            if any_other_runner_failed(jobs, job_name, current_index):
+                click.echo(_("Another runner failed. Stopping this runner early."))
+                failed_event.set()
+                return
+        except requests.RequestException as exc:
+            click.echo(_("API poll warning: {exc}", exc=exc))
+        stop_event.wait(POLL_INTERVAL)
+
+
 @click.command(context_settings={"ignore_unknown_options": True})
 @click.argument("pytest_args", nargs=-1, type=click.UNPROCESSED, required=True)
 def cli(pytest_args: tuple[str, ...]) -> None:

src/devx/ci/publish.py

@@ -4,6 +4,10 @@
 Uses git-cliff to generate the release notes from conventional commits.
 Uses the ``tea`` Gitea CLI for release creation.
 
+Gitea release creation is retried up to 3 times with exponential backoff
+(2s, 4s) to handle transient failures (network timeouts, 5xx errors).
+If the release already exists, it is treated as success (idempotent).
+
 Publishing destinations (checked in order):
   1. **Gitea PyPI registry** — if ``--registry-url`` is given (or
      ``DEVX_PYPI_REGISTRY_URL`` env var is set, or ``GITEA_API_URL``
@@ -27,6 +31,7 @@ from pathlib import Path
 
 import click
 from dotenv import load_dotenv  # pyright: ignore[reportMissingImports,reportUnknownVariableType]
+from tenacity import retry, retry_if_exception_type, stop_after_attempt, wait_exponential
 
 from devx.config import GITEA_API_URL, REPO_OWNER
 from devx.gitea_cli import TeaCLI, TeaCLIError, configure_tea_login
@@ -312,13 +317,7 @@ def main(
 
     release_body = generate_release_notes(tag)
 
-    try:
-        tea.create_release(repo, tag=tag, title=tag, body=release_body)
-    except TeaCLIError as e:
-        if "already" in str(e).lower() and "release" in str(e).lower():
-            click.echo(_("Gitea release {tag} already exists — skipping creation.", tag=tag))
-            return
-        raise click.ClickException(_("Release creation failed: {error}", error=str(e))) from None
+    _create_release_with_retry(tea, repo, tag, release_body)
 
     click.echo(
         _(
@@ -328,5 +327,36 @@ def main(
     )
 
 
+def _create_release_with_retry(tea: TeaCLI, repo: str, tag: str, release_body: str) -> None:
+    """Create a Gitea release with retry for transient failures.
+
+    Retries up to 3 times with exponential backoff (2s, 4s) on TeaCLIError
+    unless the error indicates the release already exists (which is treated
+    as success). This handles transient issues like network timeouts, Gitea
+    rate limiting, or temporary 5xx errors that caused CI run #2822 to fail.
+    """
+
+    @retry(
+        stop=stop_after_attempt(3),
+        wait=wait_exponential(multiplier=2, min=2, max=10),
+        retry=retry_if_exception_type(TeaCLIError),
+        reraise=True,
+    )
+    def _attempt() -> None:
+        try:
+            tea.create_release(repo, tag=tag, title=tag, body=release_body)
+        except TeaCLIError as e:
+            error_str = str(e).lower()
+            if "already" in error_str and "release" in error_str:
+                click.echo(_("Gitea release {tag} already exists — skipping creation.", tag=tag))
+                return
+            raise
+
+    try:
+        _attempt()
+    except TeaCLIError as e:
+        raise click.ClickException(_("Release creation failed: {error}", error=str(e))) from None
+
+
 if __name__ == "__main__":  # pragma: no cover
     main()

src/devx/ci/sync_wiki.py

@@ -252,7 +252,7 @@ def commit_and_push(wiki_dir: Path, wiki_url: str, dry_run: bool) -> bool:
 
     # Push
     result = subprocess.run(  # nosec
-        ["git", "push", "--force", wiki_url, "HEAD:master"],
+        ["git", "push", "--force", wiki_url, "HEAD:main"],
         cwd=wiki_dir,
         capture_output=True,
         text=True,

src/devx/cli.py

@@ -172,6 +172,27 @@ 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 +261,27 @@ 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])."""
@@ -259,13 +301,6 @@ def molecule_discover_runners(args: tuple[str, ...]) -> None:
     _run_module("devx.molecule.discover_runners", list(args))
 
 
-@molecule.command("guard")
-@click.argument("args", nargs=-1)
-def molecule_guard(args: tuple[str, ...]) -> None:
-    """Run molecule tests sequentially with CI failure polling."""
-    _run_module("devx.molecule.molecule_ci_guard", list(args))
-
-
 @molecule.command("all")
 @click.argument("args", nargs=-1)
 def molecule_all(args: tuple[str, ...]) -> None:

src/devx/gitea_cli.py

@@ -40,27 +40,46 @@ Usage::
 from __future__ import annotations
 
 import json
+import logging
 import shutil
 import subprocess  # nosec B404
 from typing import Any
 
 import click
+from tenacity import (
+    before_sleep_log,
+    retry,
+    retry_if_exception_type,
+    stop_after_attempt,
+    wait_exponential,
+)
 
-from devx.config import GITEA_API_URL
+from devx.config import GITEA_API_URL, MAX_RETRIES, RETRY_BACKOFF_BASE, RETRY_STATUS_CODES
 from devx.i18n import _
 from devx.tokens import get_ci_token
 
+logger = logging.getLogger("gitea_cli")
+
 
 class TeaCLIError(Exception):
     """Raised when a tea CLI command fails."""
 
 
+class _TransientTeaError(TeaCLIError):
+    """Tea CLI error caused by a transient HTTP status (502/503/504/429)."""
+
+
 def configure_tea_login(login_name: str = "devx") -> None:
     """Configure tea CLI login from CI_GITEA_API_TOKEN and DEVX_GITEA_API_URL.
 
     Idempotent: if a login with the same name already exists, it is not re-added.
     Skips silently if tea is not installed or no token is set.
 
+    Raises ``TeaCLIError`` if the login add or default command fails. This is
+    critical because subsequent tea commands (e.g. ``releases create``) will
+    fail with a cryptic "no available login" error if the login was not
+    configured successfully.
+
     Used by CI scripts (publish, notify_failure) that need tea login but
     run in containerized environments where ``make setup`` was not called.
     """
@@ -88,18 +107,31 @@ def configure_tea_login(login_name: str = "devx") -> None:
         return
 
     click.echo(_("Configuring tea login '{name}' for {url}...", name=login_name, url=gitea_url))
-    subprocess.run(  # nosec B603
+    add_result = subprocess.run(  # nosec B603
         [tea_bin, "login", "add", "--name", login_name, "--url", gitea_url, "--token", token],
         capture_output=True,
         text=True,
         check=False,
     )
-    subprocess.run(  # nosec B603
+    if add_result.returncode != 0:
+        raise TeaCLIError(
+            f"tea login add failed (rc={add_result.returncode})\n"
+            f"stdout: {add_result.stdout.strip()}\n"
+            f"stderr: {add_result.stderr.strip()}"
+        )
+
+    default_result = subprocess.run(  # nosec B603
         [tea_bin, "login", "default", login_name],
         capture_output=True,
         text=True,
         check=False,
     )
+    if default_result.returncode != 0:
+        raise TeaCLIError(
+            f"tea login default failed (rc={default_result.returncode})\n"
+            f"stdout: {default_result.stdout.strip()}\n"
+            f"stderr: {default_result.stderr.strip()}"
+        )
 
 
 class TeaCLI:
@@ -122,6 +154,10 @@ class TeaCLI:
     def _run(self, args: list[str], json_output: bool = True) -> str:
         """Run a tea command and return stdout.
 
+        Retries up to ``MAX_RETRIES`` times on transient HTTP errors
+        (502/503/504/429) detected in stderr/stdout, with exponential
+        backoff. Non-transient errors fail immediately.
+
         Args:
             args: Command arguments (without the leading ``tea``).
             json_output: If True, append ``--output json`` to the command.
@@ -130,25 +166,50 @@ class TeaCLI:
             stdout as a string.
 
         Raises:
-            TeaCLIError: If the command fails.
+            TeaCLIError: If the command fails after retries are exhausted.
         """
         cmd = [self._tea, *args]
         if json_output:
             cmd.extend(["--output", "json"])
+
+        def _execute() -> str:
+            try:
+                result = subprocess.run(  # nosec B603
+                    cmd,
+                    capture_output=True,
+                    text=True,
+                    check=False,
+                )
+            except FileNotFoundError as e:
+                raise TeaCLIError(f"tea binary not found ('{self._tea}'). Install tea or add it to PATH.") from e
+            if result.returncode != 0:
+                parts = [
+                    f"tea command failed (rc={result.returncode}): {' '.join(args)}",
+                    f"stdout: {result.stdout.strip()}" if result.stdout.strip() else "",
+                    f"stderr: {result.stderr.strip()}" if result.stderr.strip() else "",
+                ]
+                msg = "\n".join(p for p in parts if p)
+                combined = f"{result.stdout} {result.stderr}".lower()
+                if any(str(code) in combined for code in RETRY_STATUS_CODES):
+                    raise _TransientTeaError(msg)
+                raise TeaCLIError(msg)
+            return result.stdout.strip()
+
+        retry_decorator = retry(
+            stop=stop_after_attempt(MAX_RETRIES),
+            wait=wait_exponential(
+                multiplier=RETRY_BACKOFF_BASE,
+                min=RETRY_BACKOFF_BASE,
+                max=RETRY_BACKOFF_BASE**MAX_RETRIES,
+            ),
+            retry=retry_if_exception_type(_TransientTeaError),
+            before_sleep=before_sleep_log(logger, logging.WARNING),
+            reraise=True,
+        )
         try:
-            result = subprocess.run(  # nosec B603
-                cmd,
-                capture_output=True,
-                text=True,
-                check=False,
-            )
-        except FileNotFoundError as e:
-            raise TeaCLIError(f"tea binary not found ('{self._tea}'). Install tea or add it to PATH.") from e
-        if result.returncode != 0:
-            raise TeaCLIError(
-                f"tea command failed (rc={result.returncode}): {' '.join(args)}\nstderr: {result.stderr.strip()}"
-            )
-        return result.stdout.strip()
+            return retry_decorator(_execute)()
+        except _TransientTeaError as e:
+            raise TeaCLIError(str(e)) from e
 
     def _run_raw(self, args: list[str]) -> str:
         """Run a tea command without JSON output and return stdout."""

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/make/devx.mak

@@ -309,7 +309,7 @@ devx-lint: devx-lint-ruff devx-lint-format devx-typecheck devx-lint-bandit devx-
 # ── Testing ───────────────────────────────────────────────────────────────────
 
 devx-test-unit:
-	@$(DEVX_BIN)/pytest $(DEVX_TEST_PATHS) -q --no-cov
+	@$(DEVX_BIN)/pytest $(DEVX_TEST_PATHS) -q --no-cov -n 8
 
 devx-pytest-cov:
 	@$(DEVX_BIN)/pytest $(DEVX_TEST_PATHS) -n auto --cov=$(DEVX_COV_PKG) --cov-report=term-missing --cov-fail-under=100

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

@@ -1,284 +0,0 @@
-#!/usr/bin/env python3
-"""Run molecule tests sequentially while polling Gitea for other runner failures.
-
-Each pair is encoded as one of:
-
-- **Single-role (4-part):** ``scenario|platform_name|platform_image|platform_command``
-- **Multi-role (5-part):** ``role|scenario|platform_name|platform_image|platform_command``
-
-Pairs are executed one at a time (molecule scenarios share temp directories and
-Docker networks, so parallel execution within a single runner is unsafe).
-
-A background thread polls the Gitea API. If any other molecule matrix runner
-reports failure, the current molecule subprocess is killed and this runner
-exits early with code 1.
-
-Usage::
-
-    # Single-role
-    python3 -m devx.molecule.molecule_ci_guard pair1 pair2 ...
-    # Multi-role
-    python3 -m devx.molecule.molecule_ci_guard --roles-root ansible/roles pair1 pair2 ...
-
-Environment variables:
-    GITEA_URL           Base URL of the Gitea instance.
-    CI_GITEA_API_TOKEN  API token with repo access (CI_GITEA_TOKEN accepted for legacy).
-    RUN_ID              Workflow run ID (GITHUB_RUN_ID).
-    JOB_NAME            Base job name (GITHUB_JOB), e.g. "molecule-tests".
-    MATRIX_INDEX        Current matrix index (runner-index).
-    GITEA_REPOSITORY    Repository in "owner/repo" format.
-"""
-
-from __future__ import annotations
-
-import contextlib
-import os
-import signal
-import subprocess  # nosec B404
-import sys
-import threading
-import time
-from pathlib import Path
-
-import click
-import requests
-
-from devx.config import REPO_NAME, REPO_OWNER
-from devx.i18n import _
-from devx.tokens import get_ci_token
-
-POLL_INTERVAL = 10
-
-
-def get_running_jobs(gitea_url: str, owner: str, repo: str, token: str, run_id: int) -> list[dict]:
-    """Return jobs for the given workflow run."""
-    url = f"{gitea_url}/api/v1/repos/{owner}/{repo}/actions/runs/{run_id}/jobs"
-    headers = {"Authorization": f"token {token}"}
-    response = requests.get(url, headers=headers, timeout=30)
-    response.raise_for_status()
-    data = response.json()
-    return data.get("jobs", [])
-
-
-def any_other_runner_failed(jobs: list[dict], current_job_name: str, current_index: int) -> bool:
-    """Return True if any other molecule matrix job has failed."""
-    for job in jobs:
-        name = job.get("name", "")
-        if not name.startswith(current_job_name):
-            continue
-        if name == f"{current_job_name} ({current_index})" or name == current_job_name:
-            continue
-        if job.get("conclusion") == "failure":
-            return True
-    return False
-
-
-def poll_for_other_failures(
-    gitea_url: str,
-    owner: str,
-    repo: str,
-    token: str,
-    run_id: int,
-    job_name: str,
-    current_index: int,
-    stop_event: threading.Event,
-    failed_event: threading.Event,
-) -> None:
-    """Background thread: poll API and signal if another runner fails."""
-    while not stop_event.is_set():
-        try:
-            jobs = get_running_jobs(gitea_url, owner, repo, token, run_id)
-            if any_other_runner_failed(jobs, job_name, current_index):
-                click.echo(_("Another molecule runner failed. Stopping this runner early."))
-                failed_event.set()
-                return
-        except requests.RequestException as exc:
-            click.echo(_("API poll warning: {exc}", exc=exc))
-        stop_event.wait(POLL_INTERVAL)
-
-
-def build_molecule_cmd(scenario: str) -> list[str]:
-    """Build the molecule command for a scenario."""
-    cmd = ["molecule", "test"]
-    if scenario != "default":
-        cmd.extend(["-s", scenario])
-    return cmd
-
-
-def parse_pair(pair: str) -> tuple[str, str, str, str, str]:
-    """Parse a pair string into (role, scenario, platform_name, platform_image, platform_command).
-
-    Supports both 4-part (single-role) and 5-part (multi-role) formats.
-    For 4-part pairs, role is empty (caller uses default role dir).
-    Spaces in the command field are encoded as ``__SPACE__`` to survive
-    shell word-splitting when ``$TEST_PAIRS`` is expanded unquoted.
-    """
-    parts = pair.split("|")
-    if len(parts) == 4:
-        return "", parts[0], parts[1], parts[2], parts[3].replace("__SPACE__", " ")
-    if len(parts) == 5:
-        return parts[0], parts[1], parts[2], parts[3], parts[4].replace("__SPACE__", " ")
-    raise click.ClickException(f"Invalid pair format: {pair!r} (expected 4 or 5 pipe-delimited parts)")
-
-
-def build_env_for_pair(pair: str, base_env: dict[str, str]) -> dict[str, str]:
-    """Build environment for a single molecule pair."""
-    _role, _scenario, platform_name, platform_image, platform_command = parse_pair(pair)
-    env = base_env.copy()
-    env["MOLECULE_PLATFORM_NAME"] = platform_name
-    env["MOLECULE_PLATFORM_IMAGE"] = platform_image
-    if platform_command:
-        env["MOLECULE_PLATFORM_COMMAND"] = platform_command
-    elif "MOLECULE_PLATFORM_COMMAND" in env:
-        del env["MOLECULE_PLATFORM_COMMAND"]
-    env["ANSIBLE_ALLOW_BROKEN_CONDITIONALS"] = "true"
-    # Use a fresh MOLECULE_HOME per pair to avoid stale config cache
-    # from previous CI runs (causes "Instances missing" errors).
-    if "MOLECULE_HOME" not in env:
-        import tempfile
-
-        env["MOLECULE_HOME"] = tempfile.mkdtemp(prefix="molecule-ci-")
-    return env
-
-
-def resolve_role_dir(role: str, roles_root: Path | None, repo_root: Path) -> Path:
-    """Resolve the working directory for a molecule pair.
-
-    For multi-role pairs (role non-empty), uses ``roles_root/role``.
-    For single-role pairs, auto-discovers the first role with a molecule/
-    subdirectory under ``repo_root/ansible/roles/``.
-    """
-    if role:
-        if roles_root is None:
-            roles_root = repo_root / "ansible" / "roles"
-        return roles_root / role
-    roles_dir = repo_root / "ansible" / "roles"
-    if roles_dir.is_dir():
-        role_dirs = sorted(d for d in roles_dir.iterdir() if (d / "molecule").is_dir())
-        if role_dirs:
-            return role_dirs[0]
-    return roles_dir / "role"  # will produce a clear "not found" error
-
-
-@click.command()
-@click.argument("pairs", nargs=-1, required=True)
-@click.option(
-    "--roles-root",
-    type=click.Path(exists=True, file_okay=False, path_type=Path),
-    default=None,
-    help="Root directory for multi-role pairs (e.g. ansible/roles). Required when pairs use 5-part format.",
-)
-def cli(pairs: tuple[str, ...], roles_root: Path | None) -> None:
-    """Run molecule pairs sequentially, stop if another CI runner fails."""
-    gitea_url = os.environ.get("GITEA_URL", "")
-    try:
-        token = get_ci_token()
-    except click.ClickException:
-        token = None
-    run_id = int(os.environ.get("RUN_ID", "0"))
-    job_name = os.environ.get("JOB_NAME", "molecule-tests")
-    current_index = int(os.environ.get("MATRIX_INDEX", "0"))
-    repository = os.environ.get("GITEA_REPOSITORY", "")
-    owner, _sep, repo = repository.partition("/")
-    if not owner or not repo:
-        owner, repo = REPO_OWNER, REPO_NAME
-
-    if not all([gitea_url, token, run_id]):
-        click.echo(_("GITEA_URL/CI_GITEA_TOKEN/RUN_ID not set; running without cross-runner cancellation."))
-
-    # When devx is installed as a pip package, __file__ resolves to the
-    # site-packages directory, not the repo root. Use GITHUB_WORKSPACE
-    # (set by Gitea Actions) or cwd as the repo root.
-    repo_root = Path(os.environ.get("GITHUB_WORKSPACE", os.getcwd())).resolve()
-
-    base_env = os.environ.copy()
-    base_env.setdefault("DOCKER_HOST", f"unix:///run/user/{os.getuid()}/docker.sock")
-    base_env.setdefault("ANSIBLE_INJECT_INVOCATION", "1")
-
-    stop_event = threading.Event()
-    failed_event = threading.Event()
-
-    if gitea_url and token and run_id:
-        poller = threading.Thread(
-            target=poll_for_other_failures,
-            args=(
-                gitea_url,
-                owner,
-                repo,
-                token,
-                run_id,
-                job_name,
-                current_index,
-                stop_event,
-                failed_event,
-            ),
-            daemon=True,
-        )
-        poller.start()
-
-    try:
-        for pair in pairs:
-            if failed_event.is_set():
-                sys.exit(1)
-
-            role, scenario, platform_name, _img, _cmd = parse_pair(pair)
-            click.echo(_("Running: {scenario} on {platform}", scenario=scenario, platform=platform_name))
-
-            cmd = build_molecule_cmd(scenario)
-            env = build_env_for_pair(pair, base_env)
-            cwd = resolve_role_dir(role, roles_root, repo_root)
-
-            process = subprocess.Popen(  # nosec B603
-                cmd,
-                cwd=str(cwd),
-                env=env,
-                preexec_fn=os.setsid,
-            )
-
-            try:
-                while process.poll() is None:
-                    if failed_event.is_set():
-                        with contextlib.suppress(ProcessLookupError):
-                            os.killpg(os.getpgid(process.pid), signal.SIGTERM)
-                        try:
-                            process.wait(timeout=10)
-                        except subprocess.TimeoutExpired:
-                            with contextlib.suppress(ProcessLookupError):
-                                os.killpg(os.getpgid(process.pid), signal.SIGKILL)
-                            process.wait()
-                        sys.exit(1)
-                    time.sleep(1)
-            except KeyboardInterrupt:
-                with contextlib.suppress(ProcessLookupError):
-                    os.killpg(os.getpgid(process.pid), signal.SIGTERM)
-                process.wait()
-                sys.exit(1)
-
-            rc = process.returncode
-
-            if rc != 0:
-                click.echo(_("FAILED: {pair} exited with code {code}", pair=pair, code=rc))
-                sys.exit(rc)
-
-            click.echo(_("PASSED: {pair}", pair=pair))
-
-            # Prune Docker data between scenarios to prevent disk exhaustion
-            # in Docker-in-Docker molecule containers (each scenario pulls
-            # hundreds of MB of images that accumulate across pairs).
-            with contextlib.suppress(subprocess.SubprocessError, OSError):
-                subprocess.run(  # nosec B603, B607
-                    ["docker", "system", "prune", "-af", "--volumes"],
-                    check=False,
-                    capture_output=True,
-                    timeout=60,
-                )
-
-        click.echo(_("All molecule tests passed."))
-    finally:
-        stop_event.set()
-
-    sys.exit(0)
-
-
-if __name__ == "__main__":  # pragma: no cover
-    cli()

src/devx/tools/build_image.py

@@ -174,9 +174,12 @@ def build_image(
         return True
 
     click.echo(f"Building {spec.name} ({len(full_tags)} tag(s))...")
+    # Use legacy builder (DOCKER_BUILDKIT=0) to avoid OCI-format manifest
+    # blobs (attestation, config) that the Gitea registry rejects with 403.
     result = subprocess.run(  # nosec B603
         cmd,
         check=False,
+        env={**os.environ, "DOCKER_BUILDKIT": "0"},
     )
     if result.returncode != 0:
         click.echo(_("Build failed for {name}", name=spec.name), err=True)

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 +1,232 @@
+"""Check Ansible tasks for missing no_log on secret-handling tasks.
+
+ansible-lint's built-in ``no-log-password`` rule only fires when a module
+parameter is literally named ``*password*`` and there's a loop. It does
+NOT catch:
+
+- Shell/command tasks that interpolate ``{{ _secrets.* }}`` or
+  ``{{ *password* }}`` variables
+- Template/copy tasks that render secret values without ``no_log``
+
+This script fills that gap by scanning all Ansible task files for
+variables that look like secrets (``_secrets.*``, ``*password*``,
+``*secret*``, ``*token*``, ``*api_key*``) and verifying that the task
+has ``no_log`` set to a non-False value.
+
+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 re
+import sys
+from pathlib import Path
+
+import click
+import yaml
+
+REPO_ROOT = Path.cwd()
+DEFAULT_ANSIBLE_DIR = REPO_ROOT / "ansible"
+
+# Patterns that indicate a task is handling secrets.
+# We only match Jinja-interpolated variables ({{ ... }}) to avoid false
+# positives from field names like "password" in module params or task names.
+SECRET_PATTERNS = [
+    # {{ _secrets.anything }} or {{ _secrets['anything'] }}
+    re.compile(r"\{\{[^}]*_secrets\.", re.IGNORECASE),
+    # {{ anything_password }} but NOT the word "password" in a string literal
+    re.compile(r"\{\{[^}]*password", re.IGNORECASE),
+    # {{ anything_secret }}
+    re.compile(r"\{\{[^}]*_secret\b", re.IGNORECASE),
+    # {{ anything_api_key }}
+    re.compile(r"\{\{[^}]*api_key", re.IGNORECASE),
+    # {{ anything_token }} (but not loop tokens like {{ loop_token }})
+    re.compile(r"\{\{[^}]*(?:vault_token|auth_token|access_token|bot_token)", re.IGNORECASE),
+]
+
+# Task keys whose values might contain secret references
+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",
+}
+
+# Keys that are NOT secret-bearing (task metadata, not values)
+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)
+    # Jinja expressions (e.g. "{{ not debug_mode }}") count as set
+    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.
+
+    Returns a list of violation messages (empty if OK).
+    """
+    violations: list[str] = []
+
+    # Skip tasks that already have no_log
+    if _has_no_log(task):
+        return violations
+
+    # Check all string values in the task for secret references
+    has_secrets = False
+    for key, value in task.items():
+        if key in NON_VALUE_KEYS:
+            continue
+        # Check action module params (shell, command, copy, template, etc.)
+        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_directory(ansible_dir: Path) -> list[str]:
+    """Check all Ansible task files in a directory tree."""
+    all_violations: list[str] = []
+
+    # Find all task files
+    task_files = list(ansible_dir.rglob("tasks/*.yml"))
+    task_files += list(ansible_dir.rglob("tasks/*.yaml"))
+    # Also check playbook files
+    task_files += list(ansible_dir.glob("playbooks/*.yml"))
+
+    for task_file in sorted(task_files):
+        # Skip molecule test files
+        if "molecule" in task_file.parts:
+            continue
+
+        try:
+            with task_file.open() as f:
+                docs = list(yaml.safe_load_all(f))
+        except (yaml.YAMLError, OSError):
+            continue
+
+        for doc in docs:
+            if not doc:
+                continue
+
+            # Task files are bare lists of tasks; playbook files are
+            # lists of plays (each play is a dict with 'hosts' key)
+            if isinstance(doc, list):
+                is_plays = isinstance(doc[0], dict) and "hosts" in doc[0]
+                if not is_plays:
+                    for i, task in enumerate(doc):
+                        if not isinstance(task, dict):
+                            continue
+                        all_violations.extend(_check_task(task, task_file, i + 1))
+                    continue
+                plays = doc
+            elif isinstance(doc, dict):
+                plays = [doc]
+            else:
+                continue
+
+            for play in plays:
+                if not isinstance(play, dict):
+                    continue
+                for task_section in ("tasks", "pre_tasks", "post_tasks", "handlers"):
+                    tasks = play.get(task_section, [])
+                    if not isinstance(tasks, list):
+                        continue
+                    for i, task in enumerate(tasks):
+                        if not isinstance(task, dict):
+                            continue
+                        all_violations.extend(_check_task(task, task_file, i + 1))
+
+    return all_violations
+
+
+@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_directory(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 +1,176 @@
+"""Check Ansible tasks for ``state: absent`` on database data directories.
+
+This is a static analysis lint check that runs in CI (``make lint-ci``)
+to prevent the class of bug that caused the 2026-07-22 production outage
+(ADR-0028): a ``state: absent`` on a PostgreSQL data directory path that
+fired on every deploy and wiped the ZITADEL database.
+
+The existing unit test ``scripts/tests/test_no_zitadel_db_wipe.py`` covers
+the same concern as a regression test. This lint check runs earlier in
+the pipeline (before tests) and covers ALL roles and playbooks, not just
+the ZITADEL role.
+
+Allowed contexts (where DB recreation is legitimate):
+- PostgreSQL major version upgrades (``upgrade-postgres``, ``PG_VERSION``)
+- Explicit ``# lint:allow-state-absent`` comment on the task
+
+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 re
+import sys
+from pathlib import Path
+
+import click
+
+REPO_ROOT = Path.cwd()
+DEFAULT_ANSIBLE_DIRS: list[Path] = [
+    REPO_ROOT / "ansible" / "playbooks",
+    REPO_ROOT / "ansible" / "roles",
+]
+
+# Database data directory path patterns.
+# These match the DIRECTORY path, not individual files within it.
+# Removing a stale config file (e.g. postgresql.conf) is safe; removing
+# the entire data directory is not.
+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 operations
+DESTRUCTIVE_PATTERNS = (
+    re.compile(r"state:\s*absent", re.IGNORECASE),
+    re.compile(r"rm\s+-rf.*\bdb\b", re.IGNORECASE),
+)
+
+# Allowed contexts where DB recreation is legitimate
+ALLOWED_CONTEXT_KEYWORDS = (
+    "upgrade-postgres",
+    "PG_VERSION",
+    "pg_version",
+)
+
+# Comment marker to explicitly allow state: absent on a specific task
+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."""
+    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 "molecule" in f.parts:
+            continue
+        files.append(f)
+    return files
+
+
+def _check_file(filepath: Path, repo_root: Path) -> list[str]:
+    """Check a YAML file for state: absent on DB data directory paths.
+
+    Returns a list of violation messages (empty if clean).
+    """
+    try:
+        content = filepath.read_text(encoding="utf-8")
+    except (OSError, UnicodeDecodeError):
+        return []
+
+    # Quick check: if no DB path pattern appears anywhere, skip
+    if not any(p.search(content) for p in DB_PATH_PATTERNS):
+        return []
+
+    try:
+        display_path = filepath.relative_to(repo_root)
+    except ValueError:
+        display_path = filepath
+
+    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
+
+            # Check surrounding context (±5 lines) for destructive operations
+            context_start = max(0, i - 5)
+            context_end = min(len(lines), i + 6)
+            context = "\n".join(lines[context_start:context_end])
+
+            # Skip if in an allowed context (PG upgrade)
+            if any(kw in context for kw in ALLOWED_CONTEXT_KEYWORDS):
+                continue
+
+            # Skip if the allow marker comment is in the context
+            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
+
+
+@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
+    if path:
+        files = _find_task_files(path)
+    else:
+        files: list[Path] = []
+        for d in dirs:
+            files.extend(_find_task_files(d))
+
+    all_violations: list[str] = []
+    for f in files:
+        all_violations.extend(_check_file(f, REPO_ROOT))
+
+    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 +1,345 @@
+"""Check Ansible tasks for dangerous patterns that mask failures.
+
+This check addresses the gap identified in the testing-strategy audit:
+the automated PR review only checks Python files, and ``ansible-lint``
+runs at ``profile: basic`` which does not catch dangerous patterns like:
+
+- ``|| true`` on tasks that are NOT cleanup/idempotency operations
+- ``failed_when: false`` on critical tasks (e.g. DB operations)
+- ``2>/dev/null`` on tasks where stderr contains important diagnostics
+
+Most ``|| true`` and ``2>/dev/null`` instances in the codebase are
+legitimate (container removal, journalctl, apt-get, docker prune, SUID
+removal). This check flags only instances that are NOT in a known-safe
+context. Tasks can also opt out with a ``# lint:allow-failure-masking``
+comment.
+
+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 re
+import sys
+from pathlib import Path
+
+import click
+import yaml
+
+REPO_ROOT = Path.cwd()
+DEFAULT_ANSIBLE_DIRS: list[Path] = [
+    REPO_ROOT / "ansible" / "playbooks",
+    REPO_ROOT / "ansible" / "roles",
+]
+
+# 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 contexts where || true or 2>/dev/null are safe.
+# These are command prefixes or task names that indicate cleanup/idempotency.
+LEGITIMATE_COMMAND_PREFIXES = (
+    # Container/process removal (may not exist)
+    "docker rm",
+    "docker stop",
+    "docker rmi",
+    "docker network rm",
+    "docker volume rm",
+    "pkill",
+    "kill",
+    # Cleanup commands that are expected to sometimes fail
+    "journalctl --vacuum",
+    "apt-get clean",
+    "apt-get autoremove",
+    "docker image prune",
+    "docker container prune",
+    "docker volume prune",
+    "docker builder prune",
+    "find / -name",
+    # SUID removal (binaries may not exist)
+    "chmod",
+    "rm -f",
+    # Network connection checks (may fail if not connected)
+    "docker network connect",
+    # Prometheus snapshot API (may fail if no snapshot)
+    "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",
+)
+
+# Tasks with failed_when: false that are critical and should not mask failures.
+# Only flag operations that SHOULD fail loudly — writing secrets, provisioning
+# users, creating OIDC apps. Do NOT flag stop/start/check/wait/migrate/restore
+# operations where failed_when: false is legitimate (container may not exist,
+# may already be stopped, etc.).
+CRITICAL_TASK_KEYWORDS = (
+    "password",
+    "secret",
+    "provision",
+    "oidc",
+)
+
+# Task name keywords that indicate failed_when: false is legitimate
+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."""
+    # Check task name for legitimate keywords
+    name_lower = task_name.lower()
+    if any(re.search(kw, name_lower) for kw in LEGITIMATE_TASK_NAME_KEYWORDS):
+        return True
+
+    # Check command prefix for legitimate patterns
+    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."""
+    # 2>/dev/null is almost always safe — it suppresses stderr noise.
+    # Only flag it if the task is critical (DB, backup, OIDC) AND
+    # there's no || true (which is the more dangerous pattern).
+    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>")
+
+    # Check for the allow marker in the task name
+    # (YAML comments are not preserved by safe_load, so we check the
+    # task name for the marker as a workaround)
+    if ALLOW_MARKER in task_name:
+        return violations
+
+    # Check for || true in command/shell values
+    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."
+            )
+
+    # Check for failed_when: false on critical tasks
+    failed_when = task.get("failed_when")
+    if failed_when is False:
+        name_lower = task_name.lower()
+        # Skip if the task name indicates a legitimate failed_when: false context
+        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 []
+
+    # Quick check: if no patterns appear, skip
+    if not (
+        OR_TRUE_PATTERN.search(content) or "failed_when: false" in content or REDIRECT_DEVNULL_PATTERN.search(content)
+    ):
+        return []
+
+    # Check for allow markers in comments
+    has_allow_marker = ALLOW_MARKER in content
+
+    try:
+        docs = list(yaml.safe_load_all(content))
+    except yaml.YAMLError:
+        return []
+
+    violations: list[str] = []
+
+    for doc in docs:
+        if not doc:
+            continue
+        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")):
+                        _check_tasks(item, filepath, violations, repo_root)
+                    else:
+                        violations.extend(_check_task(item, filepath, i + 1, repo_root))
+                        block = item.get("block")
+                        if isinstance(block, list):
+                            for j, bt in enumerate(block):
+                                if isinstance(bt, dict):
+                                    violations.extend(_check_task(bt, filepath, i + j + 1, repo_root))
+        elif isinstance(doc, dict):
+            _check_tasks(doc, filepath, violations, repo_root)
+
+    # Filter out violations if the allow marker is present in the file
+    # (coarse-grained opt-out for files with many legitimate uses)
+    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 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):
+                    errors.extend(_check_task(task, filepath, i + 1, repo_root))
+                    block = task.get("block")
+                    if isinstance(block, list):
+                        for j, bt in enumerate(block):
+                            if isinstance(bt, dict):
+                                errors.extend(_check_task(bt, filepath, i + j + 1, repo_root))
+
+
+def _find_task_files(base: Path) -> list[Path]:
+    """Find all YAML task files under a base directory, skipping molecule."""
+    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 "molecule" in f.parts:
+            continue
+        files.append(f)
+    return files
+
+
+@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
+    if path:
+        files = _find_task_files(path)
+    else:
+        files: list[Path] = []
+        for d in dirs:
+            files.extend(_find_task_files(d))
+
+    all_violations: list[str] = []
+    for f in files:
+        all_violations.extend(_check_file(f, REPO_ROOT))
+
+    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 +1,196 @@
+"""Check that Ansible ``set_fact`` tasks don't misuse ``| to_json``.
+
+This prevents the class of bug where ``set_fact`` tasks use
+``{{ targets | to_json }}`` to store Python lists, but ``to_json``
+converts native types to JSON strings. Ansible then stored the result
+as a string, so iterating over the fact yielded individual characters
+instead of list items, causing ``object of type 'str' has no attribute
+'ip'`` errors.
+
+The check scans all Ansible task files (playbooks and role tasks) for
+``set_fact`` tasks where any value uses ``| to_json`` or ``| to_nice_json``
+and flags them as potential bugs.
+
+``| to_json`` is legitimate in Jinja2 templates (e.g., rendering JSON
+config files) but almost never correct in ``set_fact`` — the fact should
+store the native Python type so downstream tasks can iterate/index it.
+
+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
+import yaml
+
+REPO_ROOT = Path.cwd()
+DEFAULT_ANSIBLE_DIRS: list[Path] = [
+    REPO_ROOT / "ansible" / "playbooks",
+    REPO_ROOT / "ansible" / "roles",
+]
+
+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."""
+    if base.is_file() and base.suffix in (".yml", ".yaml"):
+        return [base]
+    if not base.is_dir():
+        return []
+    return sorted(base.rglob("*.yml")) + sorted(base.rglob("*.yaml"))
+
+
+def _check_file(filepath: Path, repo_root: Path) -> list[str]:
+    """Check a single YAML file for set_fact + to_json misuse.
+
+    Returns a list of error messages (empty if all OK).
+    """
+    errors: list[str] = []
+    content = filepath.read_text(encoding="utf-8")
+
+    # Multi-document YAML (--- separators) is common in playbooks
+    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):
+            # Could be a playbook (list of plays) or a role tasks file (list of tasks)
+            for item in doc:
+                if isinstance(item, dict):
+                    if any(k in item for k in ("tasks", "pre_tasks", "post_tasks", "handlers", "roles")):
+                        # It's a play
+                        _check_tasks(item, filepath, errors, repo_root)
+                    else:
+                        # It's a bare task (role tasks file)
+                        _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):
+            # Role tasks file or single play — _check_tasks handles all task sections
+            _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)
+    # Check tasks in roles imported via `roles:` key
+    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)
+        # Check nested block tasks
+        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."""
+    # Detect set_fact — could be a module name key or ansible.builtin.set_fact
+    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:
+                try:
+                    display_path = filepath.relative_to(repo_root)
+                except ValueError:
+                    display_path = filepath
+                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  # One error per fact is enough
+
+
+@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
+    if path:
+        files = _find_task_files(path)
+    else:
+        files: list[Path] = []
+        for d in dirs:
+            files.extend(_find_task_files(d))
+
+    all_errors: list[str] = []
+    for f in files:
+        errors = _check_file(f, REPO_ROOT)
+        all_errors.extend(errors)
+
+    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 +1,292 @@
+"""Validate Jinja2 expressions in Ansible files by rendering them.
+
+Extracts ``{{ ... }}`` expressions from Ansible YAML files and renders
+each one with Ansible's Jinja2 environment using mock variables. Catches
+errors like reversed filter arguments, undefined filters, and syntax
+errors before pushing to CI.
+
+The check is intentionally lightweight — it doesn't need real Ansible
+facts or variables. It provides common mock values (now(), ansible_*,
+etc.) and renders each expression in isolation. Expressions that fail
+with undefined variables that aren't in the mock set are skipped (not
+all variables can be predicted).
+
+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 re
+import sys
+from pathlib import Path
+
+import click
+from jinja2 import Environment
+from jinja2.exceptions import TemplateSyntaxError, UndefinedError
+
+REPO_ROOT = Path.cwd()
+
+
+def _default_ansible_dirs() -> list[Path]:
+    """Return the default directories to scan for Ansible files."""
+    return [
+        REPO_ROOT / "ansible" / "playbooks",
+        REPO_ROOT / "ansible" / "roles",
+    ]
+
+
+# Mock context for rendering Jinja expressions.
+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
+}
+
+# Pattern to find {{ ... }} expressions (non-greedy, single-line).
+EXPR_PATTERN = re.compile(r"\{\{(.*?)\}\}", re.DOTALL)
+
+
+def _find_yaml_files(path: Path) -> list[Path]:
+    """Find Ansible YAML files (tasks, playbooks, handlers) in a path."""
+    if path.is_file():
+        return [path]
+    files: list[Path] = []
+    for pattern in ["**/*.yml", "**/*.yaml"]:
+        files.extend(path.glob(pattern))
+    # Exclude molecule scenarios — they have their own variables.
+    return [f for f in files if "molecule" not in f.parts]
+
+
+def _extract_expressions(content: str) -> list[str]:
+    """Extract Jinja expressions from file content.
+
+    Filters out Go template syntax (``{{.Field}}``) used in docker
+    inspect --format strings, and single-character fragments from
+    quoted strings that aren't real Jinja expressions.
+    """
+    expressions = []
+    for match in EXPR_PATTERN.finditer(content):
+        raw = match.group(1)
+        # Skip multi-line expressions (often have YAML formatting artifacts).
+        if "\n" in raw:
+            continue
+        expr = raw.strip()
+        # Skip empty, control flow, and single-char fragments.
+        if not expr or expr.startswith("%") or len(expr) <= 1:
+            continue
+        # Skip Go template syntax (docker inspect --format).
+        if expr.startswith(".") or "println" in expr:
+            continue
+        # Skip expressions containing Go template dot-access patterns.
+        if ".State." in expr or ".NetworkSettings." in expr:
+            continue
+        # Skip expressions with unbalanced parens/brackets/braces —
+        # the regex captured only part of a larger expression where
+        # }} appears inside a dict literal (e.g. default({'k': {}})).
+        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
+
+        # Add common Ansible filters so expressions can render.
+        # strftime: Ansible's signature is strftime(string_format, second, utc)
+        # where string_format is the piped value. If the piped value looks like
+        # a number (epoch) and second looks like a format string, the args are
+        # reversed — this is the exact bug from OBL-INFRA-508.
+        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:
+        # Undefined variable — skip, we can't mock everything.
+        return True, f"Skipped (undefined: {e})"
+    except Exception as e:
+        # Check if it's a filter argument error.
+        error_msg = str(e)
+        if "Invalid value for epoch" in error_msg:
+            return False, f"strftime filter argument error: {error_msg}"
+        # Other errors might be due to missing mock variables — skip.
+        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:
+            try:
+                rel_path = filepath.relative_to(repo_root)
+            except ValueError:
+                rel_path = filepath
+            violations.append(f"{rel_path}: `{{{{ {expr} }}}}` — {msg}")
+
+    return violations
+
+
+@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()
+    if path:
+        files = _find_yaml_files(path)
+    else:
+        files: list[Path] = []
+        for d in dirs:
+            files.extend(_find_yaml_files(d))
+
+    all_violations: list[str] = []
+    for f in files:
+        all_violations.extend(_check_file(f, REPO_ROOT))
+
+    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/check_test_isolation.py

@@ -7,25 +7,48 @@ This module is used in two ways:
    When devx is installed, pytest auto-discovers this plugin via the
    ``pytest11`` entry point.  Every ``pytest`` run statically analyzes
    test files for patterns that cause slow, non-deterministic, or
-   non-hermetic tests and reports violations as warnings.
+   non-hermetic tests and **fails the test run** if any violations are found.
 
-   To promote warnings to errors (fail the test run), add to pyproject.toml::
+   The plugin also wraps ``subprocess.run`` at runtime to catch real
+   subprocess calls that leak through transitive call paths (e.g.
+   ``CliRunner.invoke(main)`` → ``main()`` → ``update_doc_versions()``
+   → ``subprocess.run()``).  If a test spawns a real subprocess without
+   ``@patch``, the test fails.
 
-       [tool.pytest.ini_options]
-       filterwarnings = ["error:Test isolation:UserWarning"]
-
-   Or use the ``--strict-test-isolation`` flag on the command line.
+   To disable for a specific run: ``--no-test-isolation``.
 
 2. **As a standalone CLI** (for CI gates)::
 
        python3 -m devx.tools.check_test_isolation [--test-path tests/]
-       python3 -m devx.tools.check_test_isolation --strict
+
+   Always exits non-zero on any hard violation. Transitive-subprocess
+   findings are reported as advisories (exit 0) since static analysis
+   can't predict early exits — the runtime audit is authoritative.
+
+Project-Specific Configuration
+-------------------------------
+
+Projects can extend the built-in rule sets via ``[tool.devx.check_test_isolation]``
+in ``pyproject.toml``.  Entries are merged on top of the defaults — they
+add to (not replace) the built-in rules::
+
+    [tool.devx.check_test_isolation]
+    # Functions known to do filesystem or network I/O
+    io_functions = { "my_func" = "reads config from disk", ... }
+    # Functions known to spawn subprocesses
+    subprocess_helpers = { "my_helper" = "calls subprocess.run", ... }
+    # Transitive deps: if a helper calls these, patching any of them is safe
+    helper_internal_calls = { "my_helper" = ["subprocess", "run_cmd"], ... }
+    # I/O function internal deps: patching any of these makes the call safe
+    io_internal_calls = { "my_func" = ["open", "yaml"], ... }
+    # Heavy modules slow to import at module level in test files
+    heavy_module_imports = { "mymodule" = 150.0, ... }
 
 Patterns detected:
 
 1. **Unpatched subprocess calls** — test functions that call
    ``subprocess.run/call/Popen/check_call/check_output`` without a
-   corresponding ``@patch`` decorator.
+   corresponding ``@patch`` decorator or ``with patch(...)`` context manager.
 2. **Unpatched ``time.sleep``** — test functions that call ``time.sleep``
    without patching it.
 3. **Unpatched known-subprocess-helpers** — functions known to spawn
@@ -34,27 +57,66 @@ Patterns detected:
    network I/O (e.g. ``get_pat``, ``load_secrets``, ``requests.get``)
    called without patching.
 5. **Excessive iteration loops** — ``for _ in range(N)`` where N > 100.
+6. **Module-level heavy imports** — importing ``httpx``, ``ansible``,
+   etc. at module level in test files slows collection for all tests.
+7. **``importlib.reload`` without cleanup** — reloading a module in a
+   test mutates global state.  Each reload must be paired with a
+   cleanup reload (or wrapped in try/finally) to restore defaults.
+8. **Transitive subprocess leaks** — ``CliRunner.invoke(target)`` where
+   ``target`` transitively calls ``subprocess.run`` without being patched.
+   Detected via static call-graph analysis (warning) AND runtime audit
+   (authoritative — fails the test if a real subprocess runs).
 """
 
 from __future__ import annotations
 
 import ast
+import subprocess  # nosec B404
 import sys
+import threading
 from dataclasses import dataclass, field
 from pathlib import Path
 
 import click
 
+from devx.config import _load_pyproject_devx
 from devx.i18n import _
 
 # ── Configuration ─────────────────────────────────────────────────────────────
 
 DEFAULT_MAX_LOOP_ITERATIONS = 100
 
+# Heavy modules that are slow to import (>50ms).  When imported at module
+# level in a test file, they slow down test collection for ALL tests.
+# Maps module name → approximate import time in milliseconds.
+# NOTE: ``requests`` is excluded because it's a core devx dependency —
+# it's loaded during collection regardless of whether test files import it.
+_DEFAULT_HEAVY_MODULE_IMPORTS: dict[str, float] = {
+    "httpx": 80.0,
+    "aiohttp": 120.0,
+    "docker": 90.0,
+    "kubernetes": 200.0,
+    "boto3": 250.0,
+    "botocore": 200.0,
+    "ansible": 300.0,
+    "molecule": 150.0,
+    "cv2": 400.0,
+    "numpy": 100.0,
+    "pandas": 200.0,
+    "matplotlib": 300.0,
+    "PIL": 80.0,
+    "Pillow": 80.0,
+    "sqlalchemy": 150.0,
+    "django": 200.0,
+    "flask": 80.0,
+    "fastapi": 100.0,
+    "pydantic": 60.0,
+}
+
 # Functions known to spawn subprocesses.  When a test calls any of these
 # without patching them, the real subprocess runs.
 # Maps function name → human-readable description.
-KNOWN_SUBPROCESS_HELPERS: dict[str, str] = {
+_DEFAULT_SUBPROCESS_HELPERS: dict[str, str] = {
     "update_doc_versions": "calls subprocess.run to run check_doc_versions --fix",
     "run_tests": "calls run_cmd to run make lint-ruff and make pytest-cov",
     "run_cmd": "calls subprocess.run for shell commands",
@@ -63,7 +125,7 @@ KNOWN_SUBPROCESS_HELPERS: dict[str, str] = {
 # Functions known to do filesystem or network I/O that should be mocked in tests.
 # Maps function name → description of what I/O it does.
 # If a test calls one of these without a corresponding @patch, it's a violation.
-KNOWN_IO_FUNCTIONS: dict[str, str] = {  # nosec B105 — descriptions, not passwords
+_DEFAULT_IO_FUNCTIONS: dict[str, str] = {  # nosec B105 — descriptions, not passwords
     "get_pat": "reads ZITADEL PAT from filesystem/env (ZitadelAuth._iter_sources)",
     "load_secrets": "reads YAML config file from disk",
     "get_customer_secret": "reads customer-specific config from disk",
@@ -82,12 +144,172 @@ KNOWN_IO_FUNCTIONS: dict[str, str] = {  # nosec B105 — descriptions, not passw
 # Transitive dependencies: if a helper calls another helper that is patched,
 # the call is safe.  Maps helper → set of function names it internally calls.
 # If ANY of these are in the test's patches, the helper call is safe.
-HELPER_INTERNAL_CALLS: dict[str, set[str]] = {
+_DEFAULT_HELPER_INTERNAL_CALLS: dict[str, set[str]] = {
     "run_tests": {"run_cmd", "subprocess"},
     "update_doc_versions": {"subprocess"},
     "run_cmd": {"subprocess"},
 }
 
+# I/O function internal dependencies: if a test patches one of these
+# internal dependencies, the I/O function call is considered safe.
+# Maps I/O function name → set of internal function/method names it calls.
+_DEFAULT_IO_INTERNAL_CALLS: dict[str, set[str]] = {
+    "get_customer_vm_ip": {"get_tofu_output", "get_tofu_vm_ip", "subprocess"},
+    "get_observability_vm_ip": {"get_tofu_output", "get_tofu_vm_ip", "subprocess"},
+    "get_pat": {
+        "_iter_sources",
+        "_local_pat_path",
+        "_secrets_path",
+        "_read_secrets_pat",
+        "validate_pat",
+        "ZitadelAuth",
+        "load_secrets",
+        "os.environ",
+    },
+    "load_secrets": {"load_vault_yaml", "REPO_ROOT", "open", "yaml", "safe_load"},
+    "get_customer_secret": {"load_customer_secrets", "load_vault_yaml", "load_secrets", "REPO_ROOT", "open"},
+}
+
+
+def _load_test_isolation_config() -> None:
+    """Merge project-specific rules from ``[tool.devx.check_test_isolation]``.
+
+    Reads from pyproject.toml and merges with defaults. Project-specific
+    entries are added on top of (not replacing) the built-in defaults.
+
+    Supported keys::
+
+        [tool.devx.check_test_isolation]
+        io_functions = { "my_func" = "does network I/O", ... }
+        subprocess_helpers = { "my_helper" = "calls subprocess.run", ... }
+        helper_internal_calls = { "my_helper" = ["subprocess", "run_cmd"], ... }
+        io_internal_calls = { "my_func" = ["open", "yaml"], ... }
+        heavy_module_imports = { "mymodule" = 150.0, ... }
+    """
+    devx_cfg = _load_pyproject_devx()
+    cfg_raw = devx_cfg.get("check_test_isolation", {})
+    if not isinstance(cfg_raw, dict):
+        return
+    cfg: dict[str, object] = cfg_raw  # type: ignore[assignment]
+
+    # io_functions: {name: description}
+    io_extra = cfg.get("io_functions", {})
+    if isinstance(io_extra, dict):
+        for name, desc in io_extra.items():
+            if isinstance(name, str) and isinstance(desc, str):
+                KNOWN_IO_FUNCTIONS[name] = desc
+
+    # subprocess_helpers: {name: description}
+    sp_extra = cfg.get("subprocess_helpers", {})
+    if isinstance(sp_extra, dict):
+        for name, desc in sp_extra.items():
+            if isinstance(name, str) and isinstance(desc, str):
+                KNOWN_SUBPROCESS_HELPERS[name] = desc
+
+    # helper_internal_calls: {name: [deps]}
+    hic_extra = cfg.get("helper_internal_calls", {})
+    if isinstance(hic_extra, dict):
+        for name, deps in hic_extra.items():
+            if isinstance(name, str) and isinstance(deps, list):
+                deps_set = {str(d) for d in deps if isinstance(d, str)}
+                HELPER_INTERNAL_CALLS.setdefault(name, set()).update(deps_set)
+
+    # io_internal_calls: {name: [deps]}
+    iic_extra = cfg.get("io_internal_calls", {})
+    if isinstance(iic_extra, dict):
+        for name, deps in iic_extra.items():
+            if isinstance(name, str) and isinstance(deps, list):
+                deps_set = {str(d) for d in deps if isinstance(d, str)}
+                IO_INTERNAL_CALLS.setdefault(name, set()).update(deps_set)
+
+    # heavy_module_imports: {name: ms}
+    hmi_extra = cfg.get("heavy_module_imports", {})
+    if isinstance(hmi_extra, dict):
+        for name, ms in hmi_extra.items():
+            if isinstance(name, str) and isinstance(ms, (int, float)):
+                HEAVY_MODULE_IMPORTS[name] = float(ms)
+
+
+# Active rule sets — start with defaults, merged with project config at import.
+HEAVY_MODULE_IMPORTS: dict[str, float] = dict(_DEFAULT_HEAVY_MODULE_IMPORTS)
+KNOWN_SUBPROCESS_HELPERS: dict[str, str] = dict(_DEFAULT_SUBPROCESS_HELPERS)
+KNOWN_IO_FUNCTIONS: dict[str, str] = dict(_DEFAULT_IO_FUNCTIONS)
+HELPER_INTERNAL_CALLS: dict[str, set[str]] = {k: set(v) for k, v in _DEFAULT_HELPER_INTERNAL_CALLS.items()}
+IO_INTERNAL_CALLS: dict[str, set[str]] = {k: set(v) for k, v in _DEFAULT_IO_INTERNAL_CALLS.items()}
+
+# Merge project-specific configuration from pyproject.toml
+_load_test_isolation_config()
+
+# subprocess functions that the runtime audit wraps.
+_SUBPROCESS_FUNCS = ("run", "call", "check_call", "check_output", "Popen")
+
+
+# ── Runtime subprocess audit ──────────────────────────────────────────────────
+#
+# The static AST analyzer can only see direct calls in test functions.
+# It cannot trace transitive calls through CliRunner.invoke(main, ...)
+# → main() → update_doc_versions() → subprocess.run().
+#
+# The runtime audit wraps subprocess functions during test execution.
+# If a test does NOT @patch subprocess, the wrapper catches real calls.
+# If a test DOES @patch subprocess, the patch overrides our wrapper
+# (correct — the test is mocking it).
+
+
+class _SubprocessAudit:
+    """Thread-local audit tracker for real subprocess calls during tests."""
+
+    def __init__(self) -> None:
+        self._local = threading.local()
+        self._installed = False
+        self._originals: dict[str, object] = {}
+
+    def _ensure_installed(self) -> None:
+        """Install wrappers on subprocess module (once)."""
+        if self._installed:
+            return
+        for name in _SUBPROCESS_FUNCS:
+            original = getattr(subprocess, name, None)
+            if original is None:
+                continue
+            self._originals[name] = original
+            setattr(subprocess, name, self._make_wrapper(name, original))
+        self._installed = True
+
+    def _make_wrapper(self, name: str, original: object) -> object:
+        """Create a wrapper that records calls when auditing is active."""
+
+        def wrapper(*args: object, **kwargs: object) -> object:
+            calls = getattr(self._local, "calls", None)
+            if calls is not None:
+                # Extract command for diagnostics
+                cmd = args[0] if args else kwargs.get("args", "?")
+                if isinstance(cmd, (list, tuple)) and cmd:
+                    cmd_str = " ".join(str(c) for c in cmd[:4])
+                    if len(cmd) > 4:
+                        cmd_str += " ..."
+                else:
+                    cmd_str = str(cmd)
+                calls.append((name, cmd_str))
+            return original(*args, **kwargs)  # type: ignore[misc]
+
+        return wrapper
+
+    def start_test(self) -> None:
+        """Begin auditing subprocess calls for the current test."""
+        self._ensure_installed()
+        self._local.calls = []
+
+    def stop_test(self) -> list[tuple[str, str]]:
+        """Stop auditing and return recorded calls."""
+        calls = getattr(self._local, "calls", [])
+        self._local.calls = None
+        return calls
+
+
+# Singleton instance used by the pytest plugin
+_audit = _SubprocessAudit()
+
 
 # ── Data structures ───────────────────────────────────────────────────────────
 
@@ -125,22 +347,58 @@ class TestFunctionInfo:
 
 
 def _extract_patch_targets(node: ast.FunctionDef | ast.AsyncFunctionDef | ast.ClassDef) -> set[str]:
-    """Extract @patch targets from decorators on a function or class."""
+    """Extract @patch targets from decorators AND ``with patch(...)`` statements.
+
+    Detects:
+    - ``@patch("module.func")`` decorators
+    - ``with patch("module.func")`` context managers
+    - ``with patch.object(module, "func")`` context managers
+    - ``with patch("a"), patch("b")`` multiple patches
+    """
     targets: set[str] = set()
+
+    def _process_patch_call(call: ast.Call) -> None:
+        """Extract target from a patch() or patch.object() call."""
+        func = call.func
+        # patch("module.func") — either bare `patch(...)` or `mock.patch(...)`
+        if (isinstance(func, ast.Name) and func.id == "patch") or (
+            isinstance(func, ast.Attribute) and func.attr == "patch"
+        ):
+            if call.args and isinstance(call.args[0], ast.Constant) and isinstance(call.args[0].value, str):
+                target = call.args[0].value
+                targets.add(target)
+                targets.add(target.rsplit(".", 1)[-1])
+        # patch.object(module, "func") — extract short name from 2nd arg
+        elif (
+            isinstance(func, ast.Attribute)
+            and func.attr == "object"
+            and isinstance(func.value, ast.Name)
+            and func.value.id == "patch"
+            and len(call.args) >= 2
+            and isinstance(call.args[1], ast.Constant)
+            and isinstance(call.args[1].value, str)
+            and call.args[0]
+            and isinstance(call.args[0], ast.Name)
+        ):
+            short = call.args[1].value
+            targets.add(short)
+            # We can't resolve the module alias here, but the short
+            # name is enough for patch matching in the call graph.
+
+    # 1. Extract from decorators
     for decorator in node.decorator_list:
         if isinstance(decorator, ast.Call):
-            func = decorator.func
-            is_patch = (
-                isinstance(func, ast.Name)
-                and func.id == "patch"
-                or isinstance(func, ast.Attribute)
-                and func.attr == "patch"
-            )
-            if is_patch and decorator.args and isinstance(decorator.args[0], ast.Constant):
-                target = decorator.args[0].value
-                if isinstance(target, str):
-                    targets.add(target)
-                    targets.add(target.rsplit(".", 1)[-1])
+            _process_patch_call(decorator)
+
+    # 2. Extract from `with patch(...)` context managers in the body
+    if isinstance(node, (ast.FunctionDef, ast.AsyncFunctionDef)):
+        for child in ast.walk(node):
+            if isinstance(child, ast.With):
+                for item in child.items:
+                    ctx = item.context_expr
+                    if isinstance(ctx, ast.Call):
+                        _process_patch_call(ctx)
+
     return targets
 
 
@@ -210,19 +468,303 @@ def _get_range_count(node: ast.Call) -> int | None:
     return None  # pragma: no cover
 
 
+# ── Call-graph builder ────────────────────────────────────────────────────────
+#
+# The static AST analyzer can only see direct calls in test functions.
+# It cannot trace transitive calls through CliRunner.invoke(main, ...)
+# → main() → update_doc_versions() → subprocess.run().
+#
+# The call-graph builder parses all source files in the package and builds
+# a map: function_name → set of function_names it calls.
+# When a test calls runner.invoke(target, ...), we trace the call graph
+# from target to find all reachable functions, then check if any of them
+# call subprocess.run (or other dangerous functions) without being patched.
+
+
+# Dangerous functions that should never run in unit tests.
+# Maps full call name → description.
+_DANGEROUS_CALLS: dict[str, str] = {
+    "subprocess.run": "spawns a real subprocess",
+    "subprocess.call": "spawns a real subprocess",
+    "subprocess.check_call": "spawns a real subprocess",
+    "subprocess.check_output": "spawns a real subprocess",
+    "subprocess.Popen": "spawns a real subprocess",
+}
+
+
+@dataclass
+class _FunctionNode:
+    """AST node for a function with its called names."""
+
+    name: str
+    module: str
+    calls: set[str]  # short names of functions called
+    subprocess_calls: set[str]  # dangerous subprocess calls made directly
+    io_calls: set[str]  # known I/O function calls made directly
+
+
+class CallGraph:
+    """Call graph built from source files in a package directory."""
+
+    def __init__(self, src_dir: Path) -> None:
+        self.src_dir = src_dir
+        # Maps "module.func" → _FunctionNode
+        self._nodes: dict[str, _FunctionNode] = {}
+        # Maps short name → list of full names (for resolution)
+        self._by_short: dict[str, list[str]] = {}
+        self._built = False
+
+    def _ensure_built(self) -> None:
+        if self._built:
+            return
+        self._build()
+        self._built = True
+
+    def _build(self) -> None:
+        """Parse all .py files under src_dir and build the call graph."""
+        for py_file in sorted(self.src_dir.rglob("*.py")):
+            try:
+                source = py_file.read_text()
+                tree = ast.parse(source, filename=str(py_file))
+            except (SyntaxError, UnicodeDecodeError):
+                continue
+            # Derive module name from path relative to src_dir
+            rel = py_file.relative_to(self.src_dir)
+            module_parts = list(rel.with_suffix("").parts)
+            if module_parts and module_parts[-1] == "__init__":
+                module_parts = module_parts[:-1]
+            module = ".".join(module_parts)
+            self._scan_module(tree, module)
+
+    def _scan_module(self, tree: ast.Module, module: str) -> None:
+        """Scan a module AST and register all top-level functions.
+
+        Methods defined inside classes are NOT registered — they are called
+        via objects (e.g. ``tea.create_issue()``) and resolving them by short
+        name alone causes false positives when the class is patched (e.g.
+        ``@patch("...TeaCLI")`` mocks all methods).
+        """
+        for node in tree.body:
+            self._scan_node(node, module)
+
+    def _scan_node(self, node: ast.AST, module: str) -> None:
+        """Recursively scan a node, registering non-method functions."""
+        if isinstance(node, (ast.FunctionDef, ast.AsyncFunctionDef)):
+            self._register_function(node, module)
+            # Don't recurse into function bodies — nested functions are
+            # not callable by name from outside.
+            return
+        if isinstance(node, ast.ClassDef):
+            # Skip class body — methods are not registered.
+            return
+        # Recurse into other compound statements (if/for/try/with/etc.)
+        for child in ast.iter_child_nodes(node):
+            self._scan_node(child, module)
+
+    def _register_function(self, node: ast.FunctionDef | ast.AsyncFunctionDef, module: str) -> None:
+        """Register a function and its direct calls in the call graph."""
+        full_name = f"{module}.{node.name}"
+        calls: set[str] = set()
+        subprocess_calls: set[str] = set()
+        io_calls: set[str] = set()
+
+        for child in ast.walk(node):
+            if isinstance(child, ast.Call):
+                full = _get_full_called_name(child)
+                short = _get_called_name(child)
+                if short:
+                    calls.add(short)
+                if full and full in _DANGEROUS_CALLS:
+                    subprocess_calls.add(full)
+                if short and short in KNOWN_IO_FUNCTIONS:
+                    io_calls.add(short)
+                # KNOWN_SUBPROCESS_HELPERS are intermediate functions (e.g.
+                # run_tests → run_cmd → subprocess.run).  They are already
+                # in *calls* so the BFS will traverse into them and find the
+                # actual subprocess call.  Adding them to *subprocess_calls*
+                # here would cause false positives when the helper itself is
+                # transitively patched (e.g. run_cmd is patched → run_tests
+                # is safe, but would still be reported).
+
+        fn_node = _FunctionNode(
+            name=node.name,
+            module=module,
+            calls=calls,
+            subprocess_calls=subprocess_calls,
+            io_calls=io_calls,
+        )
+        self._nodes[full_name] = fn_node
+        self._by_short.setdefault(node.name, []).append(full_name)
+
+    def find_reachable_dangerous(
+        self,
+        target_name: str,
+        patches: set[str],
+        max_depth: int = 10,
+        import_map: dict[str, str] | None = None,
+    ) -> list[tuple[str, str]]:
+        """Find all dangerous calls reachable from target_name that aren't patched.
+
+        Returns a list of (function_name, description) tuples for each
+        unpatched dangerous call found in the transitive closure.
+
+        If import_map is provided (mapping short names to fully-qualified
+        module paths), it's used to resolve the target precisely instead
+        of matching by short name alone.
+        """
+        self._ensure_built()
+
+        # Resolve target to full name(s)
+        # First try precise resolution via import_map
+        candidates: list[str] = []
+        if import_map and target_name in import_map:
+            full = import_map[target_name]
+            candidates = [full] if full in self._nodes else self._by_short.get(target_name, [])
+        elif target_name in self._nodes:
+            # Already a fully-qualified name (e.g. devx.tools.build_image.main)
+            candidates = [target_name]
+        else:
+            # Fall back to short name resolution
+            short = target_name.rsplit(".", 1)[-1]
+            candidates = self._by_short.get(short, [])
+
+        if not candidates:
+            return []
+
+        visited: set[str] = set()
+        dangerous: list[tuple[str, str]] = []
+        queue: list[tuple[str, int]] = [(c, 0) for c in candidates]
+
+        while queue:
+            full_name, depth = queue.pop(0)
+            if full_name in visited or depth > max_depth:
+                continue
+            visited.add(full_name)
+
+            node = self._nodes.get(full_name)
+            if node is None:
+                continue
+
+            # Check direct subprocess calls
+            for sc in node.subprocess_calls:
+                short = sc.rsplit(".", 1)[-1]
+                if not self._is_patched(sc, short, patches):
+                    desc = _DANGEROUS_CALLS.get(sc, "")
+                    dangerous.append((full_name, desc))
+
+            # Check direct IO calls
+            for io in node.io_calls:
+                if not self._is_patched(io, io, patches):
+                    desc = KNOWN_IO_FUNCTIONS.get(io, "")
+                    if desc:
+                        dangerous.append((full_name, desc))
+
+            # Enqueue called functions — skip if the called function is patched
+            for called_short in node.calls:
+                if self._is_patched(called_short, called_short, patches):
+                    continue
+                # Prefer same-module resolution, then fall back to short name
+                # only if there's a single global match (avoids false positives
+                # when multiple modules define functions with the same name).
+                same_module = f"{node.module}.{called_short}"
+                if same_module in self._nodes and same_module not in visited:
+                    queue.append((same_module, depth + 1))
+                else:
+                    matches = self._by_short.get(called_short, [])
+                    if len(matches) == 1 and matches[0] not in visited:
+                        queue.append((matches[0], depth + 1))
+
+        return dangerous
+
+    @staticmethod
+    def _is_patched(full: str, short: str, patches: set[str]) -> bool:
+        """Check if a function is covered by the test's @patch set."""
+        if short in patches or full in patches:
+            return True
+        # Check if any patch entry ends with ".short" (e.g. "subprocess.run"
+        # is patched by "devx.ci.release.subprocess.run").  Use exact
+        # endswith, not substring, to avoid "run" matching "run_cmd".
+        return any(p.endswith(f".{short}") or p == full for p in patches)
+
+
 # ── Analyzers ─────────────────────────────────────────────────────────────────
 
 
 class TestIsolationVisitor(ast.NodeVisitor):
     """AST visitor that detects un-hermetic test patterns."""
 
-    def __init__(self, file_path: Path, max_loop_iterations: int = DEFAULT_MAX_LOOP_ITERATIONS):
+    def __init__(
+        self,
+        file_path: Path,
+        max_loop_iterations: int = DEFAULT_MAX_LOOP_ITERATIONS,
+        call_graph: CallGraph | None = None,
+    ):
         self.file_path = file_path
         self.max_loop_iterations = max_loop_iterations
+        self.call_graph = call_graph
         self.violations: list[Violation] = []
         self._current_function: TestFunctionInfo | None = None
         self._current_class_patches: set[str] = set()
         self._in_test_class = False
+        self._reload_calls: list[tuple[int, str | None]] = []
+        # Import map: short name → fully-qualified module.func
+        # e.g. {"main": "devx.ci.release.main"} for `from devx.ci.release import main`
+        self._import_map: dict[str, str] = {}
+
+    def visit_Import(self, node: ast.Import) -> None:
+        # Track imports for call-graph resolution
+        if self._current_function is None:
+            for alias in node.names:
+                name = alias.asname or alias.name
+                self._import_map[name] = alias.name
+        # Check for heavy module imports
+        if self._current_function is None:
+            for alias in node.names:
+                mod = alias.name.split(".")[0]
+                if mod in HEAVY_MODULE_IMPORTS:
+                    self.violations.append(
+                        Violation(
+                            file=self.file_path,
+                            line=node.lineno,
+                            col=node.col_offset,
+                            category="heavy-module-import",
+                            message=_(
+                                "Heavy import '{mod}' (~{ms:.0f}ms) at module level — "
+                                "this slows test collection for all tests. "
+                                "Move inside test functions or use lazy import.",
+                                mod=alias.name,
+                                ms=HEAVY_MODULE_IMPORTS[mod],
+                            ),
+                        )
+                    )
+        self.generic_visit(node)
+
+    def visit_ImportFrom(self, node: ast.ImportFrom) -> None:
+        # Track imports for call-graph resolution
+        if self._current_function is None and node.module:
+            for alias in node.names:
+                name = alias.asname or alias.name
+                self._import_map[name] = f"{node.module}.{alias.name}"
+        # Check for heavy module imports
+        if self._current_function is None and node.module:
+            mod = node.module.split(".")[0]
+            if mod in HEAVY_MODULE_IMPORTS:
+                self.violations.append(
+                    Violation(
+                        file=self.file_path,
+                        line=node.lineno,
+                        col=node.col_offset,
+                        category="heavy-module-import",
+                        message=_(
+                            "Heavy import '{mod}' (~{ms:.0f}ms) at module level — "
+                            "this slows test collection for all tests. "
+                            "Move inside test functions or use lazy import.",
+                            mod=node.module,
+                            ms=HEAVY_MODULE_IMPORTS[mod],
+                        ),
+                    )
+                )
+        self.generic_visit(node)
 
     def visit_ClassDef(self, node: ast.ClassDef) -> None:
         old_class_patches = self._current_class_patches
@@ -258,9 +800,33 @@ class TestIsolationVisitor(ast.NodeVisitor):
             is_test=True,
         )
         old_func = self._current_function
+        old_reloads = self._reload_calls
         self._current_function = info
+        self._reload_calls = []
         self.generic_visit(node)
+        # Check 7: importlib.reload without cleanup
+        # Each reload mutates global module state.  An odd number of
+        # reloads means the module is left in a modified state.
+        if len(self._reload_calls) % 2 != 0:
+            first_line, mod_name = self._reload_calls[0]
+            self.violations.append(
+                Violation(
+                    file=self.file_path,
+                    line=first_line,
+                    col=0,
+                    category="reload-without-cleanup",
+                    message=_(
+                        "importlib.reload({mod}) called {n} time(s) in test '{test}' — "
+                        "odd count leaves module in modified state. "
+                        "Add a final reload to restore defaults or wrap in try/finally.",
+                        mod=mod_name or "module",
+                        n=len(self._reload_calls),
+                        test=info.name,
+                    ),
+                )
+            )
         self._current_function = old_func
+        self._reload_calls = old_reloads
 
     def visit_Call(self, node: ast.Call) -> None:
         if self._current_function is None:
@@ -271,6 +837,16 @@ class TestIsolationVisitor(ast.NodeVisitor):
         short_name = _get_called_name(node)
         all_patches = self._current_function.patches | self._current_function.class_patches
 
+        # Track importlib.reload calls for cleanup check
+        if full_name == "importlib.reload" or (short_name == "reload" and "reload" in all_patches):
+            mod_arg = node.args[0] if node.args else None
+            mod_name = None
+            if isinstance(mod_arg, ast.Name):
+                mod_name = mod_arg.id
+            elif isinstance(mod_arg, ast.Attribute):
+                mod_name = mod_arg.attr
+            self._reload_calls.append((node.lineno, mod_name))
+
         # Check 1: subprocess.run / subprocess.call / subprocess.Popen etc.
         if full_name and full_name.startswith("subprocess."):
             method = full_name.split(".", 1)[1]
@@ -351,6 +927,9 @@ class TestIsolationVisitor(ast.NodeVisitor):
             or sn in all_patches
             or any(io_key in p or sn in p for p in all_patches)
             or any(p.endswith(f".{sn}") for p in all_patches)
+            or any(
+                dep in all_patches or any(dep in p for p in all_patches) for dep in IO_INTERNAL_CALLS.get(io_key, set())
+            )
         ):
             self.violations.append(
                 Violation(
@@ -368,6 +947,52 @@ class TestIsolationVisitor(ast.NodeVisitor):
                 )
             )
 
+        # Check 8: CliRunner.invoke / runner.invoke — trace call graph
+        # Detect runner.invoke(target, ...) or CliRunner().invoke(target, ...)
+        if short_name == "invoke" and self.call_graph is not None and node.args:
+            target = node.args[0]
+            target_name: str | None = None
+            if isinstance(target, ast.Name):
+                target_name = target.id
+            elif isinstance(target, ast.Attribute):
+                # Handle module.func pattern (e.g. build_image.main)
+                # Resolve module prefix via import_map
+                if isinstance(target.value, ast.Name):
+                    mod_short = target.value.id
+                    mod_full = self._import_map.get(mod_short)
+                    target_name = f"{mod_full}.{target.attr}" if mod_full else target.attr
+                else:
+                    target_name = target.attr
+            if target_name:
+                dangerous = self.call_graph.find_reachable_dangerous(
+                    target_name, all_patches, import_map=self._import_map
+                )
+                if dangerous:
+                    # Deduplicate by function name
+                    seen: set[str] = set()
+                    unique: list[tuple[str, str]] = []
+                    for func, desc in dangerous:
+                        if func not in seen:
+                            seen.add(func)
+                            unique.append((func, desc))
+                    funcs_desc = "; ".join(f"{f} ({d})" for f, d in unique[:3])
+                    self.violations.append(
+                        Violation(
+                            file=self.file_path,
+                            line=node.lineno,
+                            col=node.col_offset,
+                            category="transitive-subprocess",
+                            message=_(
+                                "CliRunner.invoke({target}) in test '{test}' reaches "
+                                "unpatched dangerous functions: {funcs}. "
+                                "Add @patch for each or patch the calling function.",
+                                target=target_name,
+                                test=self._current_function.name,
+                                funcs=funcs_desc,
+                            ),
+                        )
+                    )
+
         self.generic_visit(node)
 
     def visit_For(self, node: ast.For) -> None:
@@ -402,7 +1027,11 @@ def find_test_files(test_path: Path) -> list[Path]:
     return sorted(test_path.rglob("test_*.py"))
 
 
-def analyze_file(file_path: Path, max_loop_iterations: int = DEFAULT_MAX_LOOP_ITERATIONS) -> list[Violation]:
+def analyze_file(
+    file_path: Path,
+    max_loop_iterations: int = DEFAULT_MAX_LOOP_ITERATIONS,
+    call_graph: CallGraph | None = None,
+) -> list[Violation]:
     """Analyze a single test file for isolation violations.
 
     Files in ``integration/`` directories are skipped — integration tests
@@ -424,7 +1053,7 @@ def analyze_file(file_path: Path, max_loop_iterations: int = DEFAULT_MAX_LOOP_IT
             )
         ]
 
-    visitor = TestIsolationVisitor(file_path, max_loop_iterations)
+    visitor = TestIsolationVisitor(file_path, max_loop_iterations, call_graph)
     visitor.visit(tree)
     return visitor.violations
 
@@ -433,12 +1062,13 @@ def analyze_test_files(
     test_path: Path,
     max_loop_iterations: int = DEFAULT_MAX_LOOP_ITERATIONS,
     categories: set[str] | None = None,
+    call_graph: CallGraph | None = None,
 ) -> list[Violation]:
     """Analyze all test files under test_path. Returns list of violations."""
     test_files = find_test_files(test_path)
     all_violations: list[Violation] = []
     for file_path in test_files:
-        violations = analyze_file(file_path, max_loop_iterations)
+        violations = analyze_file(file_path, max_loop_iterations, call_graph)
         if categories:
             violations = [v for v in violations if v.category in categories]
         all_violations.extend(violations)
@@ -449,23 +1079,17 @@ def analyze_test_files(
 #
 # When devx is installed, pytest auto-discovers this plugin via the
 # `pytest11` entry point.  The plugin runs static analysis on every
-# test file during collection and emits warnings for violations.
-# Use --strict-test-isolation to promote warnings to errors.
+# test file during collection and **fails** on any violation.
+# It also wraps subprocess at runtime to catch transitive leaks.
 
 
 def pytest_addoption(parser):  # type: ignore[no-untyped-def]  # pragma: no cover
     """Register pytest command-line options."""
-    parser.addoption(
-        "--strict-test-isolation",
-        action="store_true",
-        default=False,
-        help="Fail the test run if any test isolation violations are found.",
-    )
     parser.addoption(
         "--no-test-isolation",
         action="store_true",
         default=False,
-        help="Disable test isolation static analysis.",
+        help="Disable test isolation static analysis and runtime subprocess audit.",
     )
     parser.addoption(
         "--test-isolation-max-loop",
@@ -476,46 +1100,129 @@ def pytest_addoption(parser):  # type: ignore[no-untyped-def]  # pragma: no cove
 
 
 def pytest_collection_finish(session):  # type: ignore[no-untyped-def]  # pragma: no cover
-    """Run static analysis after all test files are collected."""
+    """Run static analysis after all test files are collected. Always strict."""
     if session.config.getoption("--no-test-isolation"):
         return
 
-    strict = session.config.getoption("--strict-test-isolation")
     max_loop = session.config.getoption("--test-isolation-max-loop")
 
-    # Analyze all collected test files
+    # Build call graph from source directory for transitive analysis
+    call_graph: CallGraph | None = None
+    for item in session.items:
+        fspath = Path(str(item.fspath))
+        for parent in fspath.parents:
+            src_dir = parent / "src"
+            if src_dir.is_dir():
+                call_graph = CallGraph(src_dir)
+                break
+        if call_graph is not None:
+            break
+
     test_files: set[Path] = set()
     for item in session.items:
         test_files.add(Path(str(item.fspath)))
 
     all_violations: list[Violation] = []
     for file_path in sorted(test_files):
-        violations = analyze_file(file_path, max_loop)
+        violations = analyze_file(file_path, max_loop, call_graph)
         all_violations.extend(violations)
 
     if not all_violations:
         return
 
-    # Emit warnings
-    import warnings
+    # transitive-subprocess is advisory (static can't predict early exits).
+    # All other categories are hard errors.
+    errors = [v for v in all_violations if v.category != "transitive-subprocess"]
+    transitive = [v for v in all_violations if v.category == "transitive-subprocess"]
 
-    for v in sorted(all_violations, key=lambda x: (str(x.file), x.line)):
-        msg = f"Test isolation violation: {v.format()}"
-        warnings.warn(msg, UserWarning, stacklevel=2)
-
-    if strict:
-        count = len(all_violations)
-        files = len({v.file for v in all_violations})
+    if errors:
+        count = len(errors)
+        files = len({v.file for v in errors})
         click.echo(
             _(
-                "\nTest isolation check FAILED: {count} violation(s) in {files} file(s).\n"
-                "Fix: add @patch decorators for subprocess/time.sleep calls, "
-                "or patch the calling function.\n",
+                "\nTest isolation check FAILED: {count} violation(s) in {files} file(s).\n",
                 count=count,
                 files=files,
             ),
             err=True,
         )
+        for v in sorted(errors, key=lambda x: (str(x.file), x.line)):
+            click.echo(f"  {v.format()}", err=True)
+        click.echo(
+            _(
+                "Fix: add @patch decorators or with patch() context managers "
+                "for subprocess/time.sleep calls, or patch the calling function.\n"
+            ),
+            err=True,
+        )
+        import pytest
+
+        pytest.fail(
+            f"Test isolation: {count} violation(s) found. See output above.",
+            pytrace=False,
+        )
+
+    # transitive-subprocess warnings are advisory — runtime audit is authoritative
+    if transitive:
+        import warnings
+
+        for v in sorted(transitive, key=lambda x: (str(x.file), x.line)):
+            msg = f"Test isolation advisory: {v.format()}"
+            warnings.warn(msg, UserWarning, stacklevel=2)
+
+
+# ── Runtime subprocess audit hooks ────────────────────────────────────────────
+
+
+def _is_integration_test(item: object) -> bool:
+    """Check if a test item is an integration test."""
+    markers = getattr(item, "keywords", {})
+    if "integration" in markers:
+        return True
+    fspath = str(getattr(item, "fspath", ""))
+    return "integration" in fspath
+
+
+def pytest_runtest_setup(item: object) -> None:  # type: ignore[no-untyped-def]  # pragma: no cover
+    """Start subprocess audit for non-integration tests."""
+    config = getattr(item, "config", None)
+    if config is None:
+        return
+    if config.getoption("--no-test-isolation"):
+        return
+    if _is_integration_test(item):
+        return
+    _audit.start_test()
+
+
+def pytest_runtest_teardown(item: object, nextitem: object) -> None:  # type: ignore[no-untyped-def]  # pragma: no cover
+    """Fail test if real subprocess calls were made without @patch."""
+    config = getattr(item, "config", None)
+    if config is None:
+        return
+    if config.getoption("--no-test-isolation"):
+        return
+    if _is_integration_test(item):
+        return
+    calls = _audit.stop_test()
+    if not calls:
+        return
+
+    test_name = getattr(item, "name", str(item))
+    lines = [
+        _(
+            "Real subprocess call(s) detected in test '{test}' without @patch:",
+            test=test_name,
+        )
+    ]
+    for func_name, cmd in calls:
+        lines.append(f"  {func_name}({cmd})")
+    lines.append(_('Add @patch("subprocess.run") or patch the calling function to fix this.'))
+    msg = "\n".join(lines)
+
+    import pytest
+
+    pytest.fail(msg, pytrace=False)
 
 
 # ── Standalone CLI ────────────────────────────────────────────────────────────
@@ -538,59 +1245,103 @@ def pytest_collection_finish(session):  # type: ignore[no-untyped-def]  # pragma
     show_default=True,
     help="Maximum allowed iterations in a single test loop.",
 )
-@click.option(
-    "--strict",
-    is_flag=True,
-    default=False,
-    help="Treat warnings as errors (non-zero exit on any violation).",
-)
 @click.option(
     "--categories",
     type=str,
     default="",
     help="Comma-separated list of categories to check (default: all). "
-    "Available: unpatched-subprocess, unpatched-sleep, unpatched-helper, excessive-iterations",
+    "Available: unpatched-subprocess, unpatched-sleep, unpatched-helper, "
+    "excessive-iterations, heavy-module-import, reload-without-cleanup, "
+    "transitive-subprocess",
 )
-def cli(test_paths: tuple[Path, ...], max_loop_iterations: int, strict: bool, categories: str) -> None:
-    """Check test files for un-hermetic patterns that cause slow or flaky tests."""
+@click.option(
+    "--src-dir",
+    type=click.Path(exists=True, file_okay=False, path_type=Path),
+    default=None,
+    help="Source directory for call-graph analysis (auto-detected if omitted).",
+)
+def cli(
+    test_paths: tuple[Path, ...],
+    max_loop_iterations: int,
+    categories: str,
+    src_dir: Path | None,
+) -> None:
+    """Check test files for un-hermetic patterns that cause slow or flaky tests.
+
+    Always exits non-zero on any hard violation. Transitive-subprocess
+    findings are reported as advisories (exit 0) since static analysis
+    can't predict early exits — the runtime audit is authoritative.
+    """
     allowed: set[str] | None = None
     if categories:
         allowed = {c.strip() for c in categories.split(",")}
 
+    # Build call graph for transitive subprocess detection
+    call_graph: CallGraph | None = None
+    if src_dir is not None:
+        call_graph = CallGraph(src_dir)
+    else:
+        for tp in test_paths:
+            for parent in Path(tp).resolve().parents:
+                candidate = parent / "src"
+                if candidate.is_dir():
+                    call_graph = CallGraph(candidate)
+                    break
+            if call_graph is not None:
+                break
+
     all_violations: list[Violation] = []
     total_files = 0
     for test_path in test_paths:
-        violations = analyze_test_files(test_path, max_loop_iterations, allowed)
+        violations = analyze_test_files(test_path, max_loop_iterations, allowed, call_graph)
         all_violations.extend(violations)
         total_files += len(find_test_files(test_path))
 
-    if not all_violations:
+    errors = [v for v in all_violations if v.category != "transitive-subprocess"]
+    advisories = [v for v in all_violations if v.category == "transitive-subprocess"]
+
+    if not errors and not advisories:
         click.echo(
             _("Test isolation check passed: {count} test files analyzed, no violations found.", count=total_files)
         )
         sys.exit(0)
 
-    click.echo(
-        _(
-            "Test isolation check FAILED: {count} violation(s) found in {files} test file(s).",
-            count=len(all_violations),
-            files=len({v.file for v in all_violations}),
-        ),
-        err=True,
-    )
-    click.echo("")
-    for v in sorted(all_violations, key=lambda x: (str(x.file), x.line)):
-        click.echo(f"  {v.format()}", err=True)
+    if errors:
+        click.echo(
+            _(
+                "Test isolation check FAILED: {count} violation(s) in {files} file(s).",
+                count=len(errors),
+                files=len({v.file for v in errors}),
+            ),
+            err=True,
+        )
+        click.echo("")
+        for v in sorted(errors, key=lambda x: (str(x.file), x.line)):
+            click.echo(f"  {v.format()}", err=True)
+        click.echo("")
+        click.echo(
+            _(
+                "Fix: add @patch decorators or with patch() context managers "
+                "for subprocess/time.sleep calls, or patch the calling function."
+            ),
+            err=True,
+        )
+        sys.exit(1)
 
-    click.echo("")
+    # Advisories only — exit 0 but print them
     click.echo(
         _(
-            "Fix: add @patch decorators for subprocess/time.sleep calls, "
-            "or patch the calling function. Use property-based testing for statistical tests."
-        ),
-        err=True,
+            "Test isolation check passed with {count} advisory warning(s) in {files} file(s).",
+            count=len(advisories),
+            files=len({v.file for v in advisories}),
+        )
     )
-    sys.exit(1)
+    click.echo(_("Transitive-subprocess advisories (runtime audit is authoritative):"))
+    for v in sorted(advisories, key=lambda x: (str(x.file), x.line))[:10]:
+        click.echo(f"  {v.format()}")
+    if len(advisories) > 10:
+        click.echo(f"  ... and {len(advisories) - 10} more")
+    sys.exit(0)
 
 
 if __name__ == "__main__":  # pragma: no cover

src/devx/tools/check_test_speed.py

@@ -11,6 +11,18 @@ Usage:
 The module runs ``make test-unit`` with ``PYTEST_ADDOPTS=--durations=0`` so
 that pytest emits per-test timing lines alongside the summary.  Both the
 total wall-clock time and individual test durations are parsed and validated.
+
+CI runner scaling
+-----------------
+CI runners (Gitea Actions Docker containers) are typically 5-8x slower than
+local development machines due to shared CPU, fewer cores, and container
+overhead.  When the ``CI`` environment variable is set (standard CI
+convention), both the total and per-test limits are multiplied by
+``CI_SCALE_FACTOR`` (default 6) to account for this.  This keeps the local
+budget strict while preventing false failures on slower CI runners.
+
+The scale factor can be overridden via the ``DEVX_CI_SCALE_FACTOR``
+environment variable.
 """
 
 from __future__ import annotations
@@ -27,6 +39,12 @@ DEFAULT_MAX_SECONDS = 10.0
 DEFAULT_MAX_SINGLE_SECONDS = 0.5
 TEST_COMMAND = ["make", "test-unit"]
 
+# CI runners are typically 5-8x slower than local machines (shared CPU,
+# fewer cores, container overhead).  Scale limits up when running on CI
+# so the gate catches real regressions, not infrastructure slowness.
+CI_SCALE_FACTOR = float(os.environ.get("DEVX_CI_SCALE_FACTOR", "6"))
+_IS_CI = bool(os.environ.get("CI") or os.environ.get("GITEA_ACTIONS"))
+
 # Matches pytest summary line: "234 passed in 0.70s"
 _TIMING_RE = re.compile(r"(\d+) passed.* in ([0-9.]+)s")
 
@@ -38,6 +56,13 @@ _TIMING_RE = re.compile(r"(\d+) passed.* in ([0-9.]+)s")
 _DURATION_LINE_RE = re.compile(r"^(\d+\.?\d*)s\s+call\s+(.+)$")
 
 
+def _ci_scale_limit(limit: float) -> float:
+    """Scale a time limit by the CI factor when running on CI."""
+    if _IS_CI:
+        return limit * CI_SCALE_FACTOR
+    return limit
+
+
 def run_tests() -> tuple[str, str]:
     """Execute the unit-test suite and return (stdout, stderr).
 
@@ -123,21 +148,38 @@ def check_per_test_speed(
 
 def main(max_seconds: float, max_single_seconds: float) -> None:
     """Run tests, parse timings, and enforce both budgets."""
+    # Scale limits for CI runners (slower CPU, fewer workers).
+    effective_max = _ci_scale_limit(max_seconds)
+    effective_single = _ci_scale_limit(max_single_seconds)
+
+    if _IS_CI:
+        click.echo(
+            _(
+                "[check-test-speed] CI environment detected — scaling limits by {factor}x "
+                "(total: {orig}s → {eff}s, per-test: {orig_s}s → {eff_s}s)",
+                factor=CI_SCALE_FACTOR,
+                orig=max_seconds,
+                eff=effective_max,
+                orig_s=max_single_seconds,
+                eff_s=effective_single,
+            )
+        )
+
     stdout, stderr = run_tests()
     combined = stdout + "\n" + stderr
     click.echo(combined, err=False)
 
     duration = parse_duration(combined)
-    check_speed(duration, max_seconds)
+    check_speed(duration, effective_max)
 
-    if max_single_seconds > 0:
+    if effective_single > 0:
         per_test = parse_per_test_durations(combined)
-        violations = check_per_test_speed(per_test, max_single_seconds)
+        violations = check_per_test_speed(per_test, effective_single)
         if violations:
             msg = _(
                 "Per-test speed check FAILED: {count} test(s) exceed {limit}s limit.",
                 count=len(violations),
-                limit=max_single_seconds,
+                limit=effective_single,
             )
             click.echo(f"\n{msg}", err=True)
             for v in violations:
@@ -148,8 +190,8 @@ def main(max_seconds: float, max_single_seconds: float) -> None:
         _(
             "Unit tests passed in {duration:.2f}s (under {max}s limit, all tests under {single}s per-test limit).",
             duration=duration,
-            max=max_seconds,
-            single=max_single_seconds,
+            max=effective_max,
+            single=effective_single,
         )
     )
 

src/devx/tools/clean_images.py

@@ -5,6 +5,13 @@ Queries the Gitea API for all versions of a package (container type) and
 deletes all but the most recent N versions.  The ``latest`` tag is always
 preserved if present.
 
+.. note::
+    This tool only deletes package versions via the Gitea API. The underlying
+    blob files on the Gitea server's filesystem are NOT removed by this tool
+    (Gitea 1.26.x has no built-in garbage collection). The production VM's
+    daily cleanup script (``cleanup_gitea.py``) handles filesystem blob GC
+    by querying the database for referenced blobs and removing orphaned files.
+
 Usage::
 
     # Clean up ci-base images, keep last 2 versions
@@ -57,7 +64,10 @@ def list_package_versions(
     Returns a list of version dicts, each containing at least ``version``
     and ``created_at`` fields.
     """
-    url = f"{api_url}/packages/{owner}?type=container&name={name}"
+    from urllib.parse import quote
+
+    encoded_name = quote(name, safe="")
+    url = f"{api_url}/packages/{owner}?type=container&name={encoded_name}"
     headers = {"Authorization": f"token {token}"}
     all_versions: list[dict[str, Any]] = []
     page = 1
@@ -96,7 +106,11 @@ def delete_package_version(
 
     Returns True on success, False on failure.
     """
-    url = f"{api_url}/packages/{owner}/{package_type}/{name}/{version}"
+    from urllib.parse import quote
+
+    encoded_name = quote(name, safe="")
+    encoded_version = quote(version, safe="")
+    url = f"{api_url}/packages/{owner}/{package_type}/{encoded_name}/{encoded_version}"
     headers = {"Authorization": f"token {token}"}
     for attempt in range(max_retries):
         try:

src/devx/tools/install_tools.py

@@ -8,6 +8,7 @@ Handles installation of:
 - tea (Gitea CLI — official command-line tool for Gitea API operations)
 - hadolint (Dockerfile linter)
 - vale (prose linter for documentation quality)
+- promtool (Prometheus rule validator)
 
 Each tool is installed to ``~/.local/bin`` if not already on PATH.
 Idempotent: skips tools that are already available.
@@ -47,6 +48,8 @@ TOFU_VERSION = "1.12.3"
 
 VALE_VERSION = "3.15.1"
 
+PROMTOOL_VERSION = "3.5.5"
+
 
 def _arch() -> str:
     """Return the architecture string used by release assets (delegates to shared utility)."""
@@ -62,8 +65,33 @@ def _ensure_target_dir() -> Path:
 
 
 def _download(url: str, dest: Path) -> None:
-    """Download a file from ``url`` to ``dest``."""
-    urllib.request.urlretrieve(url, dest)  # nosec B310
+    """Download a file from ``url`` to ``dest`` with a 60s timeout.
+
+    A User-Agent header is set because some CDNs (e.g. dl.gitea.com)
+    return 403 to requests with Python's default User-Agent.
+    """
+    req = urllib.request.Request(url, headers={"User-Agent": "devx/install-tools"})
+    with urllib.request.urlopen(req, 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:
@@ -160,8 +188,13 @@ 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
 
@@ -212,7 +245,26 @@ def install_vale() -> bool:
     return True
 
 
-TOOL_NAMES = ["actionlint", "git-cliff", "act_runner", "tea", "hadolint", "tofu", "vale"]
+def install_promtool() -> bool:
+    """Install promtool (Prometheus rule validator) if not already present.
+
+    Downloads the official Prometheus release tarball from GitHub and
+    extracts the ``promtool`` binary to ``~/.local/bin``.
+    """
+    if _is_installed("promtool"):
+        click.echo("promtool: already installed")
+        return True
+    arch = _arch()
+    url = (
+        f"https://github.com/prometheus/prometheus/releases/download/"
+        f"v{PROMTOOL_VERSION}/prometheus-{PROMTOOL_VERSION}.linux-{arch}.tar.gz"
+    )
+    dest = _download_and_extract_tarball(url, "promtool")
+    click.echo(f"promtool: installed to {dest}")
+    return True
+
+
+TOOL_NAMES = ["actionlint", "git-cliff", "act_runner", "tea", "hadolint", "tofu", "vale", "promtool"]
 
 
 def _install_tool(name: str) -> bool:
@@ -231,6 +283,8 @@ def _install_tool(name: str) -> bool:
         return install_tofu()
     if name == "vale":
         return install_vale()
+    if name == "promtool":
+        return install_promtool()
     raise click.ClickException(f"Unknown tool: {name}")
 
 

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:
@@ -81,6 +83,17 @@ def _install_in_image(
             username,
             token,
         )
+        # Configure git URL rewrite so git+https dependencies can authenticate
+        subprocess.run(  # nosec B603, B607
+            [
+                "git",
+                "config",
+                "--global",
+                f"url.https://{username}:{token}@{gitea_host}/.insteadOf",
+                f"https://{gitea_host}/",
+            ],
+            check=True,
+        )
 
     click.echo(f"[setup-image] Linked {opt_venv}" + (f" with [{extras}]" if extras else "") + ".")
     subprocess.run(cmd, check=True, env=env)  # nosec B603

src/devx/translations.json

@@ -183,14 +183,6 @@
     "ru": "\nTag → Commit alignment:",
     "zh": "\nTag → Commit alignment:"
   },
-  "\nTest isolation check FAILED: {count} violation(s) in {files} file(s).\nFix: add @patch decorators for subprocess/time.sleep calls, or patch the calling function.\n": {
-    "bg": "\nПроверката за изолация на тестове НЕ ПРЕМИНА: {count} нарушения в {files} файла.\nРешение: добавете @patch декоратори за subprocess/time.sleep извиквания или patch-нете извикващата функция.\n",
-    "de": "\nTestisolationsprüfung FEHLGESCHLAGEN: {count} Verstoß/Verstöße in {files} Datei(en).\nBehebung: @patch-Dekoratoren für subprocess/time.sleep-Aufrufe hinzufügen oder die aufrufende Funktion patchen.\n",
-    "en": "\nTest isolation check FAILED: {count} violation(s) in {files} file(s).\nFix: add @patch decorators for subprocess/time.sleep calls, or patch the calling function.\n",
-    "pl": "\nSprawdzenie izolacji testów NIE ZALICZONE: {count} naruszeń w {files} plikach.\nNaprawa: dodaj dekoratory @patch dla wywołań subprocess/time.sleep lub patchuj wywołującą funkcję.\n",
-    "ru": "\nПроверка изоляции тестов НЕ ПРОЙДЕНА: {count} нарушений в {files} файлах.\nИсправление: добавьте декораторы @patch для вызовов subprocess/time.sleep или patch вызывающую функцию.\n",
-    "zh": "\n测试隔离检查失败：在 {files} 个文件中有 {count} 个违规。\n修复：为 subprocess/time.sleep 调用添加 @patch 装饰器，或 patch 调用函数。\n"
-  },
   "\nUntagged release commits:": {
     "bg": "\nUntagged release commits:",
     "de": "\nUntagged release commits:",
@@ -791,14 +783,6 @@
     "ru": "Additional directory to scan (default: scripts, tests). Can be repeated.",
     "zh": "Additional directory to scan (default: scripts, tests). Can be repeated."
   },
-  "All molecule tests passed.": {
-    "bg": "All molecule tests passed.",
-    "de": "All molecule tests passed.",
-    "en": "All molecule tests passed.",
-    "pl": "Wszystkie testy molecule zakończone pomyślnie.",
-    "ru": "All molecule tests passed.",
-    "zh": "All molecule tests passed."
-  },
   "Allow empty tag (PR mode where SHA is concrete).": {
     "bg": "Позволи празен таг (PR режим, където SHA е конкретен).",
     "de": "Leeren Tag zulassen (PR-Modus, in dem SHA konkret ist).",
@@ -807,13 +791,13 @@
     "ru": "Разрешить пустой тег (режим PR, где SHA конкретен).",
     "zh": "允许空标签（SHA 为具体值的 PR 模式）。"
   },
-  "Another molecule runner failed. Stopping this runner early.": {
-    "bg": "Another molecule runner failed. Stopping this runner early.",
-    "de": "Another molecule runner failed. Stopping this runner early.",
-    "en": "Another molecule runner failed. Stopping this runner early.",
-    "pl": "Inny runner molecule zakończył się niepowodzeniem. Wczesne zatrzymanie tego runnera.",
-    "ru": "Another molecule runner failed. Stopping this runner early.",
-    "zh": "Another molecule runner failed. Stopping this runner early."
+  "Another runner failed. Stopping this runner early.": {
+    "bg": "Друг runner се провали. Спиране на този runner по-рано.",
+    "de": "Ein anderer Runner ist fehlgeschlagen. Dieser Runner wird vorzeitig gestoppt.",
+    "en": "Another runner failed. Stopping this runner early.",
+    "pl": "Inny runner zakończył się niepowodzeniem. Wczesne zatrzymanie tego runnera.",
+    "ru": "Другой runner завершился с ошибкой. Останавливаю этот runner досрочно.",
+    "zh": "另一个 runner 失败。提前停止此 runner。"
   },
   "Assigned {count} files to runner {runner_index}": {
     "bg": "Assigned {count} files to runner {runner_index}",
@@ -1503,14 +1487,6 @@
     "ru": "FAILED: {count} undocumented dependency/ies",
     "zh": "FAILED: {count} undocumented dependency/ies"
   },
-  "FAILED: {pair} exited with code {code}": {
-    "bg": "FAILED: {pair} exited with code {code}",
-    "de": "FAILED: {pair} exited with code {code}",
-    "en": "FAILED: {pair} exited with code {code}",
-    "pl": "NIEUDANE: {pair} zakończone kodem {code}",
-    "ru": "FAILED: {pair} exited with code {code}",
-    "zh": "FAILED: {pair} exited with code {code}"
-  },
   "Failed images: {names}": {
     "bg": "Failed images: {names}",
     "de": "Failed images: {names}",
@@ -1583,14 +1559,6 @@
     "ru": "Fetching origin/master...",
     "zh": "Fetching origin/master..."
   },
-  "Fix: add @patch decorators for subprocess/time.sleep calls, or patch the calling function. Use property-based testing for statistical tests.": {
-    "bg": "Решение: добавете @patch декоратори за subprocess/time.sleep извиквания или patch-нете извикващата функция. Използвайте property-based тестове за статистически тестове.",
-    "de": "Behebung: @patch-Dekoratoren für subprocess/time.sleep-Aufrufe hinzufügen oder die aufrufende Funktion patchen. Property-based testing für statistische Tests verwenden.",
-    "en": "Fix: add @patch decorators for subprocess/time.sleep calls, or patch the calling function. Use property-based testing for statistical tests.",
-    "pl": "Naprawa: dodaj dekoratory @patch dla wywołań subprocess/time.sleep lub patchuj wywołującą funkcję. Użyj testów opartych na właściwościach dla testów statystycznych.",
-    "ru": "Исправление: добавьте декораторы @patch для вызовов subprocess/time.sleep или patch вызывающую функцию. Используйте property-based тестирование для статистических тестов.",
-    "zh": "修复：为 subprocess/time.sleep 调用添加 @patch 装饰器，或 patch 调用函数。对统计测试使用基于属性的测试。"
-  },
   "Force-push failed:\n{error}\nThe remote may have unexpected commits. Fetch and try again.": {
     "bg": "Force-push failed:\n{error}\nThe remote may have unexpected commits. Fetch and try again.",
     "de": "Force-push failed:\n{error}\nThe remote may have unexpected commits. Fetch and try again.",
@@ -2279,14 +2247,6 @@
     "ru": "PASS: All documentation checks passed!",
     "zh": "PASS: All documentation checks passed!"
   },
-  "PASSED: {pair}": {
-    "bg": "PASSED: {pair}",
-    "de": "PASSED: {pair}",
-    "en": "PASSED: {pair}",
-    "pl": "UDANE: {pair}",
-    "ru": "PASSED: {pair}",
-    "zh": "PASSED: {pair}"
-  },
   "PR #{pr} rebased successfully. A new CI run will start automatically.\nIf auto-merge is enabled (ready-to-merge label), the next CI run\nwill attempt to merge this PR.": {
     "bg": "PR #{pr} rebased successfully. A new CI run will start automatically.\nIf auto-merge is enabled (ready-to-merge label), the next CI run\nwill attempt to merge this PR.",
     "de": "PR #{pr} rebased successfully. A new CI run will start automatically.\nIf auto-merge is enabled (ready-to-merge label), the next CI run\nwill attempt to merge this PR.",
@@ -2759,14 +2719,6 @@
     "ru": "Running: {cmd}",
     "zh": "Running: {cmd}"
   },
-  "Running: {scenario} on {platform}": {
-    "bg": "Running: {scenario} on {platform}",
-    "de": "Running: {scenario} on {platform}",
-    "en": "Running: {scenario} on {platform}",
-    "pl": "Uruchamianie: {scenario} na {platform}",
-    "ru": "Running: {scenario} on {platform}",
-    "zh": "Running: {scenario} on {platform}"
-  },
   "SSH key set up successfully": {
     "bg": "SSH ключът е настроен успешно",
     "de": "SSH-Schlüssel erfolgreich eingerichtet",
@@ -2903,14 +2855,6 @@
     "ru": "Test '{name}' took {elapsed:.2f}s (limit: {limit}s). Optimise: use lighter fixtures, reduce I/O, or mock external calls.",
     "zh": "Test '{name}' took {elapsed:.2f}s (limit: {limit}s). Optimise: use lighter fixtures, reduce I/O, or mock external calls."
   },
-  "Test isolation check FAILED: {count} violation(s) found in {files} test file(s).": {
-    "bg": "Проверката за изолация на тестове НЕ ПРЕМИНА: открити са {count} нарушения в {files} тестови файла.",
-    "de": "Testisolationsprüfung FEHLGESCHLAGEN: {count} Verstoß/Verstöße in {files} Testdatei(en) gefunden.",
-    "en": "Test isolation check FAILED: {count} violation(s) found in {files} test file(s).",
-    "pl": "Sprawdzenie izolacji testów NIE ZALICZONE: znaleziono {count} naruszeń w {files} plikach testowych.",
-    "ru": "Проверка изоляции тестов НЕ ПРОЙДЕНА: найдено {count} нарушений в {files} тестовых файлах.",
-    "zh": "测试隔离检查失败：在 {files} 个测试文件中发现 {count} 个违规。"
-  },
   "Test isolation check passed: {count} test files analyzed, no violations found.": {
     "bg": "Проверката за изолация на тестове премина: анализирани са {count} тестови файла, няма нарушения.",
     "de": "Testisolationsprüfung bestanden: {count} Testdateien analysiert, keine Verstöße gefunden.",
@@ -3686,5 +3630,173 @@
     "pl": "{separator}",
     "ru": "{separator}",
     "zh": "{separator}"
+  },
+  "\nTest isolation check FAILED: {count} violation(s) in {files} file(s).\n": {
+    "bg": "\nTest isolation check FAILED: {count} violation(s) in {files} file(s).\n",
+    "de": "\nTest isolation check FAILED: {count} violation(s) in {files} file(s).\n",
+    "en": "\nTest isolation check FAILED: {count} violation(s) in {files} file(s).\n",
+    "pl": "\nTest isolation check FAILED: {count} violation(s) in {files} file(s).\n",
+    "ru": "\nTest isolation check FAILED: {count} violation(s) in {files} file(s).\n",
+    "zh": "\nTest isolation check FAILED: {count} violation(s) in {files} file(s).\n"
+  },
+  "  Fix the PR title with:\n    python3 -m devx.ci.fix_pr_title --repo {repo} --pr-number {pr}\n  Or manually set the PR title to: '{expected}'": {
+    "bg": "  Fix the PR title with:\n    python3 -m devx.ci.fix_pr_title --repo {repo} --pr-number {pr}\n  Or manually set the PR title to: '{expected}'",
+    "de": "  Fix the PR title with:\n    python3 -m devx.ci.fix_pr_title --repo {repo} --pr-number {pr}\n  Or manually set the PR title to: '{expected}'",
+    "en": "  Fix the PR title with:\n    python3 -m devx.ci.fix_pr_title --repo {repo} --pr-number {pr}\n  Or manually set the PR title to: '{expected}'",
+    "pl": "  Fix the PR title with:\n    python3 -m devx.ci.fix_pr_title --repo {repo} --pr-number {pr}\n  Or manually set the PR title to: '{expected}'",
+    "ru": "  Fix the PR title with:\n    python3 -m devx.ci.fix_pr_title --repo {repo} --pr-number {pr}\n  Or manually set the PR title to: '{expected}'",
+    "zh": "  Fix the PR title with:\n    python3 -m devx.ci.fix_pr_title --repo {repo} --pr-number {pr}\n  Or manually set the PR title to: '{expected}'"
+  },
+  "Add @patch(\"subprocess.run\") or patch the calling function to fix this.": {
+    "bg": "Add @patch(\"subprocess.run\") or patch the calling function to fix this.",
+    "de": "Add @patch(\"subprocess.run\") or patch the calling function to fix this.",
+    "en": "Add @patch(\"subprocess.run\") or patch the calling function to fix this.",
+    "pl": "Add @patch(\"subprocess.run\") or patch the calling function to fix this.",
+    "ru": "Add @patch(\"subprocess.run\") or patch the calling function to fix this.",
+    "zh": "Add @patch(\"subprocess.run\") or patch the calling function to fix this."
+  },
+  "Branch name (auto-fetched from PR if not given)": {
+    "bg": "Branch name (auto-fetched from PR if not given)",
+    "de": "Branch name (auto-fetched from PR if not given)",
+    "en": "Branch name (auto-fetched from PR if not given)",
+    "pl": "Branch name (auto-fetched from PR if not given)",
+    "ru": "Branch name (auto-fetched from PR if not given)",
+    "zh": "Branch name (auto-fetched from PR if not given)"
+  },
+  "CI_GITEA_API_TOKEN not set: {error}": {
+    "bg": "CI_GITEA_API_TOKEN not set: {error}",
+    "de": "CI_GITEA_API_TOKEN not set: {error}",
+    "en": "CI_GITEA_API_TOKEN not set: {error}",
+    "pl": "CI_GITEA_API_TOKEN not set: {error}",
+    "ru": "CI_GITEA_API_TOKEN not set: {error}",
+    "zh": "CI_GITEA_API_TOKEN not set: {error}"
+  },
+  "CliRunner.invoke({target}) in test '{test}' reaches unpatched dangerous functions: {funcs}. Add @patch for each or patch the calling function.": {
+    "bg": "CliRunner.invoke({target}) in test '{test}' reaches unpatched dangerous functions: {funcs}. Add @patch for each or patch the calling function.",
+    "de": "CliRunner.invoke({target}) in test '{test}' reaches unpatched dangerous functions: {funcs}. Add @patch for each or patch the calling function.",
+    "en": "CliRunner.invoke({target}) in test '{test}' reaches unpatched dangerous functions: {funcs}. Add @patch for each or patch the calling function.",
+    "pl": "CliRunner.invoke({target}) in test '{test}' reaches unpatched dangerous functions: {funcs}. Add @patch for each or patch the calling function.",
+    "ru": "CliRunner.invoke({target}) in test '{test}' reaches unpatched dangerous functions: {funcs}. Add @patch for each or patch the calling function.",
+    "zh": "CliRunner.invoke({target}) in test '{test}' reaches unpatched dangerous functions: {funcs}. Add @patch for each or patch the calling function."
+  },
+  "Could not determine branch name from PR #{pr}": {
+    "bg": "Could not determine branch name from PR #{pr}",
+    "de": "Could not determine branch name from PR #{pr}",
+    "en": "Could not determine branch name from PR #{pr}",
+    "pl": "Could not determine branch name from PR #{pr}",
+    "ru": "Could not determine branch name from PR #{pr}",
+    "zh": "Could not determine branch name from PR #{pr}"
+  },
+  "Failed to fetch PR #{pr}: {error}": {
+    "bg": "Failed to fetch PR #{pr}: {error}",
+    "de": "Failed to fetch PR #{pr}: {error}",
+    "en": "Failed to fetch PR #{pr}: {error}",
+    "pl": "Failed to fetch PR #{pr}: {error}",
+    "ru": "Failed to fetch PR #{pr}: {error}",
+    "zh": "Failed to fetch PR #{pr}: {error}"
+  },
+  "Failed to update PR #{pr}: {error}": {
+    "bg": "Failed to update PR #{pr}: {error}",
+    "de": "Failed to update PR #{pr}: {error}",
+    "en": "Failed to update PR #{pr}: {error}",
+    "pl": "Failed to update PR #{pr}: {error}",
+    "ru": "Failed to update PR #{pr}: {error}",
+    "zh": "Failed to update PR #{pr}: {error}"
+  },
+  "Fix: add @patch decorators or with patch() context managers for subprocess/time.sleep calls, or patch the calling function.": {
+    "bg": "Fix: add @patch decorators or with patch() context managers for subprocess/time.sleep calls, or patch the calling function.",
+    "de": "Fix: add @patch decorators or with patch() context managers for subprocess/time.sleep calls, or patch the calling function.",
+    "en": "Fix: add @patch decorators or with patch() context managers for subprocess/time.sleep calls, or patch the calling function.",
+    "pl": "Fix: add @patch decorators or with patch() context managers for subprocess/time.sleep calls, or patch the calling function.",
+    "ru": "Fix: add @patch decorators or with patch() context managers for subprocess/time.sleep calls, or patch the calling function.",
+    "zh": "Fix: add @patch decorators or with patch() context managers for subprocess/time.sleep calls, or patch the calling function."
+  },
+  "Fix: add @patch decorators or with patch() context managers for subprocess/time.sleep calls, or patch the calling function.\n": {
+    "bg": "Fix: add @patch decorators or with patch() context managers for subprocess/time.sleep calls, or patch the calling function.\n",
+    "de": "Fix: add @patch decorators or with patch() context managers for subprocess/time.sleep calls, or patch the calling function.\n",
+    "en": "Fix: add @patch decorators or with patch() context managers for subprocess/time.sleep calls, or patch the calling function.\n",
+    "pl": "Fix: add @patch decorators or with patch() context managers for subprocess/time.sleep calls, or patch the calling function.\n",
+    "ru": "Fix: add @patch decorators or with patch() context managers for subprocess/time.sleep calls, or patch the calling function.\n",
+    "zh": "Fix: add @patch decorators or with patch() context managers for subprocess/time.sleep calls, or patch the calling function.\n"
+  },
+  "Heavy import '{mod}' (~{ms:.0f}ms) at module level — this slows test collection for all tests. Move inside test functions or use lazy import.": {
+    "bg": "Heavy import '{mod}' (~{ms:.0f}ms) at module level — this slows test collection for all tests. Move inside test functions or use lazy import.",
+    "de": "Heavy import '{mod}' (~{ms:.0f}ms) at module level — this slows test collection for all tests. Move inside test functions or use lazy import.",
+    "en": "Heavy import '{mod}' (~{ms:.0f}ms) at module level — this slows test collection for all tests. Move inside test functions or use lazy import.",
+    "pl": "Heavy import '{mod}' (~{ms:.0f}ms) at module level — this slows test collection for all tests. Move inside test functions or use lazy import.",
+    "ru": "Heavy import '{mod}' (~{ms:.0f}ms) at module level — this slows test collection for all tests. Move inside test functions or use lazy import.",
+    "zh": "Heavy import '{mod}' (~{ms:.0f}ms) at module level — this slows test collection for all tests. Move inside test functions or use lazy import."
+  },
+  "No task ID found in branch '{branch}'. Expected format: {prefix}-N-description.": {
+    "bg": "No task ID found in branch '{branch}'. Expected format: {prefix}-N-description.",
+    "de": "No task ID found in branch '{branch}'. Expected format: {prefix}-N-description.",
+    "en": "No task ID found in branch '{branch}'. Expected format: {prefix}-N-description.",
+    "pl": "No task ID found in branch '{branch}'. Expected format: {prefix}-N-description.",
+    "ru": "No task ID found in branch '{branch}'. Expected format: {prefix}-N-description.",
+    "zh": "No task ID found in branch '{branch}'. Expected format: {prefix}-N-description."
+  },
+  "PR number to fix": {
+    "bg": "PR number to fix",
+    "de": "PR number to fix",
+    "en": "PR number to fix",
+    "pl": "PR number to fix",
+    "ru": "PR number to fix",
+    "zh": "PR number to fix"
+  },
+  "Real subprocess call(s) detected in test '{test}' without @patch:": {
+    "bg": "Real subprocess call(s) detected in test '{test}' without @patch:",
+    "de": "Real subprocess call(s) detected in test '{test}' without @patch:",
+    "en": "Real subprocess call(s) detected in test '{test}' without @patch:",
+    "pl": "Real subprocess call(s) detected in test '{test}' without @patch:",
+    "ru": "Real subprocess call(s) detected in test '{test}' without @patch:",
+    "zh": "Real subprocess call(s) detected in test '{test}' without @patch:"
+  },
+  "Show what would change without updating": {
+    "bg": "Show what would change without updating",
+    "de": "Show what would change without updating",
+    "en": "Show what would change without updating",
+    "pl": "Show what would change without updating",
+    "ru": "Show what would change without updating",
+    "zh": "Show what would change without updating"
+  },
+  "Test isolation check FAILED: {count} violation(s) in {files} file(s).": {
+    "bg": "Test isolation check FAILED: {count} violation(s) in {files} file(s).",
+    "de": "Test isolation check FAILED: {count} violation(s) in {files} file(s).",
+    "en": "Test isolation check FAILED: {count} violation(s) in {files} file(s).",
+    "pl": "Test isolation check FAILED: {count} violation(s) in {files} file(s).",
+    "ru": "Test isolation check FAILED: {count} violation(s) in {files} file(s).",
+    "zh": "Test isolation check FAILED: {count} violation(s) in {files} file(s)."
+  },
+  "Test isolation check passed with {count} advisory warning(s) in {files} file(s).": {
+    "bg": "Test isolation check passed with {count} advisory warning(s) in {files} file(s).",
+    "de": "Test isolation check passed with {count} advisory warning(s) in {files} file(s).",
+    "en": "Test isolation check passed with {count} advisory warning(s) in {files} file(s).",
+    "pl": "Test isolation check passed with {count} advisory warning(s) in {files} file(s).",
+    "ru": "Test isolation check passed with {count} advisory warning(s) in {files} file(s).",
+    "zh": "Test isolation check passed with {count} advisory warning(s) in {files} file(s)."
+  },
+  "Transitive-subprocess advisories (runtime audit is authoritative):": {
+    "bg": "Transitive-subprocess advisories (runtime audit is authoritative):",
+    "de": "Transitive-subprocess advisories (runtime audit is authoritative):",
+    "en": "Transitive-subprocess advisories (runtime audit is authoritative):",
+    "pl": "Transitive-subprocess advisories (runtime audit is authoritative):",
+    "ru": "Transitive-subprocess advisories (runtime audit is authoritative):",
+    "zh": "Transitive-subprocess advisories (runtime audit is authoritative):"
+  },
+  "importlib.reload({mod}) called {n} time(s) in test '{test}' — odd count leaves module in modified state. Add a final reload to restore defaults or wrap in try/finally.": {
+    "bg": "importlib.reload({mod}) called {n} time(s) in test '{test}' — odd count leaves module in modified state. Add a final reload to restore defaults or wrap in try/finally.",
+    "de": "importlib.reload({mod}) called {n} time(s) in test '{test}' — odd count leaves module in modified state. Add a final reload to restore defaults or wrap in try/finally.",
+    "en": "importlib.reload({mod}) called {n} time(s) in test '{test}' — odd count leaves module in modified state. Add a final reload to restore defaults or wrap in try/finally.",
+    "pl": "importlib.reload({mod}) called {n} time(s) in test '{test}' — odd count leaves module in modified state. Add a final reload to restore defaults or wrap in try/finally.",
+    "ru": "importlib.reload({mod}) called {n} time(s) in test '{test}' — odd count leaves module in modified state. Add a final reload to restore defaults or wrap in try/finally.",
+    "zh": "importlib.reload({mod}) called {n} time(s) in test '{test}' — odd count leaves module in modified state. Add a final reload to restore defaults or wrap in try/finally."
+  },
+  "[check-test-speed] CI environment detected — scaling limits by {factor}x (total: {orig}s → {eff}s, per-test: {orig_s}s → {eff_s}s)": {
+    "en": "[check-test-speed] CI environment detected — scaling limits by {factor}x (total: {orig}s → {eff}s, per-test: {orig_s}s → {eff_s}s)",
+    "bg": "[check-test-speed] CI environment detected — scaling limits by {factor}x (total: {orig}s → {eff}s, per-test: {orig_s}s → {eff_s}s)",
+    "de": "[check-test-speed] CI environment detected — scaling limits by {factor}x (total: {orig}s → {eff}s, per-test: {orig_s}s → {eff_s}s)",
+    "pl": "[check-test-speed] CI environment detected — scaling limits by {factor}x (total: {orig}s → {eff}s, per-test: {orig_s}s → {eff_s}s)",
+    "ru": "[check-test-speed] CI environment detected — scaling limits by {factor}x (total: {orig}s → {eff}s, per-test: {orig_s}s → {eff_s}s)",
+    "zh": "[check-test-speed] CI environment detected — scaling limits by {factor}x (total: {orig}s → {eff}s, per-test: {orig_s}s → {eff_s}s)"
   }
 }

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_api_clients.py

@@ -316,6 +316,18 @@ class TestGiteaClient:
         call_kwargs = client._session.request.call_args.kwargs
         assert call_kwargs["json"]["base"] == "develop"
 
+    def test_update_pr(self) -> None:
+        client = GiteaClient("https://git.example.com", "tok", "owner", "repo")
+        client._session.request = MagicMock(return_value=_mock_response({"number": 42, "title": "DEVX-99: New title"}))
+        result = client.update_pr(42, {"title": "DEVX-99: New title"})
+        assert result["number"] == 42
+        client._session.request.assert_called_once_with(
+            "PATCH",
+            "https://git.example.com/repos/owner/repo/pulls/42",
+            timeout=DEFAULT_TIMEOUT,
+            json={"title": "DEVX-99: New title"},
+        )
+
     def test_get_pr_files(self) -> None:
         client = GiteaClient("https://git.example.com", "tok", "owner", "repo")
         client._session.request = MagicMock(

tests/unit/test_build_image.py

@@ -508,7 +508,8 @@ class TestCLIBuildImage:
 
     def test_missing_dockerfile_and_manifest(self) -> None:
         runner = CliRunner()
-        result = runner.invoke(build_image.main, [])
+        with patch("devx.tools.build_image.subprocess.run"):
+            result = runner.invoke(build_image.main, [])
         assert result.exit_code != 0
         assert "manifest" in result.output.lower() or "dockerfile" in result.output.lower()
 
@@ -516,10 +517,11 @@ class TestCLIBuildImage:
         dockerfile = tmp_path / "Dockerfile"
         dockerfile.touch()
         runner = CliRunner()
-        result = runner.invoke(
-            build_image.main,
-            ["--dockerfile", str(dockerfile), "--name", "ci-base", "--push"],
-        )
+        with patch("devx.tools.build_image.subprocess.run"):
+            result = runner.invoke(
+                build_image.main,
+                ["--dockerfile", str(dockerfile), "--name", "ci-base", "--push"],
+            )
         assert result.exit_code != 0
         assert "registry" in result.output.lower()
 
@@ -527,7 +529,7 @@ class TestCLIBuildImage:
         dockerfile = tmp_path / "Dockerfile"
         dockerfile.touch()
         runner = CliRunner()
-        with patch.dict("os.environ", {}, clear=True):
+        with patch("devx.tools.build_image.subprocess.run"), patch.dict("os.environ", {}, clear=True):
             result = runner.invoke(
                 build_image.main,
                 ["--dockerfile", str(dockerfile), "--name", "ci-base", "--push", "--registry", "git.example.com"],

tests/unit/test_check_auto_merge_ready.py

@@ -152,7 +152,10 @@ class TestGetVikunjaTitleOptional:
 class TestCli:
     def test_fails_without_task_id(self) -> None:
         runner = CliRunner()
-        with patch.dict("os.environ", {"DEVX_TASK_PREFIX": "DEVX"}, clear=True):
+        with (
+            patch.dict("os.environ", {"DEVX_TASK_PREFIX": "DEVX"}, clear=True),
+            patch("devx.ci.check_auto_merge_ready.is_branch_behind_master", return_value=False),
+        ):
             result = runner.invoke(cli, ["--branch", "no-task-id-here"])
         assert result.exit_code != 0
 
@@ -242,6 +245,7 @@ class TestCli:
         runner = CliRunner()
         with (
             patch.dict("os.environ", {"DEVX_TASK_PREFIX": "DEVX", "VIKUNJA_TOKEN": ""}, clear=True),
+            patch("devx.ci.check_auto_merge_ready.is_branch_behind_master", return_value=False),
             patch("devx.ci.check_auto_merge_ready.get_pr_title_from_gitea", return_value=None),
         ):
             result = runner.invoke(

tests/unit/test_check_test_isolation.py

@@ -2,14 +2,26 @@
 
 from __future__ import annotations
 
+import ast
+import subprocess
 import textwrap
 from pathlib import Path
+from unittest.mock import MagicMock
 
+import pytest
 from click.testing import CliRunner
 
 from devx.tools.check_test_isolation import (
+    HEAVY_MODULE_IMPORTS,
     HELPER_INTERNAL_CALLS,
+    IO_INTERNAL_CALLS,
+    KNOWN_IO_FUNCTIONS,
     KNOWN_SUBPROCESS_HELPERS,
+    CallGraph,
+    _extract_patch_targets,
+    _is_integration_test,
+    _load_test_isolation_config,
+    _SubprocessAudit,
     analyze_file,
     analyze_test_files,
     cli,
@@ -502,6 +514,97 @@ class TestAnalyzeFile:
         assert len(violations) == 1
         assert violations[0].category == "syntax-error"
 
+    def test_heavy_module_import_at_module_level(self, tmp_path: Path) -> None:
+        file = _write_test_file(
+            tmp_path,
+            """
+            import pandas
+
+            def test_foo() -> None:
+                assert True
+        """,
+        )
+        violations = analyze_file(file)
+        assert len(violations) == 1
+        assert violations[0].category == "heavy-module-import"
+        assert "pandas" in violations[0].message
+
+    def test_heavy_import_inside_function_ok(self, tmp_path: Path) -> None:
+        file = _write_test_file(
+            tmp_path,
+            """
+            def test_foo() -> None:
+                import pandas
+                assert True
+        """,
+        )
+        violations = analyze_file(file)
+        assert violations == []
+
+    def test_heavy_import_from_at_module_level(self, tmp_path: Path) -> None:
+        file = _write_test_file(
+            tmp_path,
+            """
+            from matplotlib import pyplot as plt
+
+            def test_foo() -> None:
+                assert True
+        """,
+        )
+        violations = analyze_file(file)
+        assert len(violations) == 1
+        assert violations[0].category == "heavy-module-import"
+
+    def test_reload_without_cleanup_odd_count(self, tmp_path: Path) -> None:
+        file = _write_test_file(
+            tmp_path,
+            """
+            import importlib
+            import devx.config as cfg
+
+            def test_reload_no_cleanup() -> None:
+                importlib.reload(cfg)
+                assert cfg.TASK_PREFIX == "CUSTOM"
+        """,
+        )
+        violations = analyze_file(file)
+        reload_violations = [v for v in violations if v.category == "reload-without-cleanup"]
+        assert len(reload_violations) == 1
+        assert "1 time(s)" in reload_violations[0].message
+
+    def test_reload_with_cleanup_even_count_ok(self, tmp_path: Path) -> None:
+        file = _write_test_file(
+            tmp_path,
+            """
+            import importlib
+            import devx.config as cfg
+
+            def test_reload_with_cleanup() -> None:
+                importlib.reload(cfg)
+                assert cfg.TASK_PREFIX == "CUSTOM"
+                importlib.reload(cfg)
+        """,
+        )
+        violations = analyze_file(file)
+        reload_violations = [v for v in violations if v.category == "reload-without-cleanup"]
+        assert reload_violations == []
+
+    def test_reload_attribute_access_detected(self, tmp_path: Path) -> None:
+        file = _write_test_file(
+            tmp_path,
+            """
+            import importlib
+            import devx.config
+
+            def test_reload_attr() -> None:
+                importlib.reload(devx.config)
+        """,
+        )
+        violations = analyze_file(file)
+        reload_violations = [v for v in violations if v.category == "reload-without-cleanup"]
+        assert len(reload_violations) == 1
+        assert "config" in reload_violations[0].message
+
 
 class TestAnalyzeTestFiles:
     def test_multiple_files(self, tmp_path: Path) -> None:
@@ -742,7 +845,8 @@ class TestCli:
         assert "FAILED" in result.output
         assert "unpatched-subprocess" in result.output
 
-    def test_strict_flag(self, tmp_path: Path) -> None:
+    def test_always_strict(self, tmp_path: Path) -> None:
+        """CLI is always strict — no --strict flag needed."""
         _write_test_file(
             tmp_path,
             """
@@ -753,7 +857,7 @@ class TestCli:
         """,
         )
         runner = CliRunner()
-        result = runner.invoke(cli, ["--test-path", str(tmp_path), "--strict"])
+        result = runner.invoke(cli, ["--test-path", str(tmp_path)])
         assert result.exit_code == 1
 
     def test_category_filter(self, tmp_path: Path) -> None:
@@ -795,22 +899,6 @@ class TestCli:
         assert result.exit_code == 0
         assert "no violations" in result.output
 
-    def test_strict_clean_directory_exits_zero(self, tmp_path: Path) -> None:
-        """Strict mode with no violations should still exit 0."""
-        _write_test_file(
-            tmp_path,
-            """
-            from unittest.mock import patch, MagicMock
-            class TestExample:
-                @patch("subprocess.run")
-                def test_ok(self, mock: MagicMock) -> None:
-                    pass
-        """,
-        )
-        runner = CliRunner()
-        result = runner.invoke(cli, ["--test-path", str(tmp_path), "--strict"])
-        assert result.exit_code == 0
-
 
 class TestPytestPlugin:
     """Tests for the pytest plugin hooks.
@@ -830,7 +918,7 @@ class TestPytestPlugin:
         pytest_addoption(parser)
 
         addoption_calls = parser.addoption.call_args_list
-        assert len(addoption_calls) >= 3
+        assert len(addoption_calls) >= 2
 
     def test_pytest_collection_finish_noop_when_disabled(self) -> None:
         """Plugin should skip analysis when --no-test-isolation is set."""
@@ -854,39 +942,10 @@ class TestPytestPlugin:
         pytest_collection_finish(session)
 
     def test_pytest_collection_finish_with_violation(self, tmp_path: Path) -> None:
-        """Plugin should emit warnings when violations are found."""
-        import warnings
+        """Plugin should fail when hard violations are found (always strict)."""
         from unittest.mock import MagicMock
 
-        from devx.tools.check_test_isolation import pytest_collection_finish
-
-        test_file = _write_test_file(
-            tmp_path,
-            """
-            import subprocess
-            class TestExample:
-                def test_bad(self) -> None:
-                    subprocess.run(["echo"])
-        """,
-        )
-
-        session = MagicMock()
-        session.config.getoption.side_effect = lambda opt: False
-        item = MagicMock()
-        item.fspath = str(test_file)
-        session.items = [item]
-
-        with warnings.catch_warnings(record=True) as w:
-            warnings.simplefilter("always")
-            pytest_collection_finish(session)
-
-        assert len(w) >= 1
-        assert any("Test isolation violation" in str(warning.message) for warning in w)
-
-    def test_pytest_collection_finish_strict_mode(self, tmp_path: Path) -> None:
-        """Plugin should emit warnings and print summary in strict mode."""
-        import warnings
-        from unittest.mock import MagicMock
+        import pytest
 
         from devx.tools.check_test_isolation import pytest_collection_finish
 
@@ -903,7 +962,44 @@ class TestPytestPlugin:
         session = MagicMock()
         session.config.getoption.side_effect = lambda opt: {
             "--no-test-isolation": False,
-            "--strict-test-isolation": True,
+            "--test-isolation-max-loop": 100,
+        }.get(opt, False)
+        item = MagicMock()
+        item.fspath = str(test_file)
+        session.items = [item]
+
+        with pytest.raises(pytest.fail.Exception, match="Test isolation"):
+            pytest_collection_finish(session)
+
+    def test_pytest_collection_finish_advisory_only(self, tmp_path: Path) -> None:
+        """Transitive-subprocess advisories should warn, not fail."""
+        import warnings
+        from unittest.mock import MagicMock
+
+        from devx.tools.check_test_isolation import pytest_collection_finish
+
+        # Create a src/ directory with a module that calls subprocess.run
+        # so the call graph can detect transitive subprocess calls.
+        src_dir = tmp_path / "src" / "mypkg"
+        src_dir.mkdir(parents=True)
+        (src_dir / "__init__.py").write_text("")
+        (src_dir / "cli.py").write_text("import subprocess\ndef main():\n    subprocess.run(['echo'])\n")
+
+        test_file = _write_test_file(
+            tmp_path,
+            """
+            from click.testing import CliRunner
+            from mypkg.cli import main
+            class TestExample:
+                def test_advisory(self) -> None:
+                    runner = CliRunner()
+                    result = runner.invoke(main, [])
+        """,
+        )
+
+        session = MagicMock()
+        session.config.getoption.side_effect = lambda opt: {
+            "--no-test-isolation": False,
             "--test-isolation-max-loop": 100,
         }.get(opt, False)
         item = MagicMock()
@@ -914,5 +1010,772 @@ class TestPytestPlugin:
             warnings.simplefilter("always")
             pytest_collection_finish(session)
 
-        assert len(w) >= 1
-        assert any("Test isolation violation" in str(warning.message) for warning in w)
+        # Should only emit advisory warnings, not fail
+        assert any("advisory" in str(warning.message).lower() for warning in w)
+
+
+class TestSubprocessAudit:
+    """Tests for the _SubprocessAudit runtime wrapper (lines 157-195)."""
+
+    def test_ensure_installed_wraps_subprocess(self) -> None:
+        audit = _SubprocessAudit()
+        original_run = subprocess.run
+        try:
+            audit._ensure_installed()
+            assert audit._installed is True
+            assert "run" in audit._originals
+            # The subprocess.run should now be a wrapper, not the original
+            assert subprocess.run is not original_run
+            # Calling _ensure_installed again is a no-op (cached return)
+            audit._ensure_installed()
+        finally:
+            # Restore originals
+            for name, orig in audit._originals.items():
+                setattr(subprocess, name, orig)
+
+    def test_make_wrapper_records_calls_when_active(self) -> None:
+        audit = _SubprocessAudit()
+        mock_original = MagicMock(return_value="result")
+        wrapper = audit._make_wrapper("run", mock_original)
+        audit.start_test()
+        result = wrapper(["echo", "hi"], capture_output=True)
+        calls = audit.stop_test()
+        assert result == "result"
+        run_calls = [c for c in calls if c[0] == "run"]
+        assert len(run_calls) == 1
+        assert "echo" in run_calls[0][1]
+        mock_original.assert_called_once_with(["echo", "hi"], capture_output=True)
+
+    def test_make_wrapper_records_list_cmd_truncation(self) -> None:
+        """Long command lists should be truncated to first 4 elements."""
+        audit = _SubprocessAudit()
+        mock_original = MagicMock(return_value="result")
+        wrapper = audit._make_wrapper("run", mock_original)
+        audit.start_test()
+        wrapper(["echo", "1", "2", "3", "4", "5", "6"], capture_output=True)
+        calls = audit.stop_test()
+        run_calls = [c for c in calls if c[0] == "run"]
+        assert len(run_calls) == 1
+        assert "..." in run_calls[0][1]
+
+    def test_make_wrapper_records_string_cmd(self) -> None:
+        """A string command (not list) should be recorded as-is."""
+        audit = _SubprocessAudit()
+        mock_original = MagicMock(return_value="result")
+        wrapper = audit._make_wrapper("run", mock_original)
+        audit.start_test()
+        wrapper("echo hi", shell=True, capture_output=True)
+        calls = audit.stop_test()
+        run_calls = [c for c in calls if c[0] == "run"]
+        assert len(run_calls) == 1
+        assert "echo hi" in run_calls[0][1]
+
+    def test_calls_not_recorded_when_inactive(self) -> None:
+        """When audit is not active, calls should not be recorded."""
+        audit = _SubprocessAudit()
+        mock_original = MagicMock(return_value="result")
+        wrapper = audit._make_wrapper("run", mock_original)
+        # Don't call start_test — audit inactive
+        wrapper(["echo", "hi"], capture_output=True)
+        # stop_test returns empty since no calls recorded
+        calls = audit.stop_test()
+        assert not calls
+        mock_original.assert_called_once_with(["echo", "hi"], capture_output=True)
+
+    def test_start_then_stop_returns_calls(self) -> None:
+        """start_test initializes calls list, stop_test returns and clears it."""
+        audit = _SubprocessAudit()
+        mock_original = MagicMock(return_value="result")
+        wrapper = audit._make_wrapper("run", mock_original)
+        audit.start_test()
+        wrapper(["echo"], capture_output=True)
+        calls = audit.stop_test()
+        assert len(calls) == 1
+        # After stop, calls is cleared (None or empty)
+        calls2 = audit.stop_test()
+        assert not calls2
+
+    def test_ensure_installed_skips_missing_funcs(self) -> None:
+        """If a subprocess func is missing (None), it should be skipped (line 162)."""
+        audit = _SubprocessAudit()
+        saved = subprocess.check_output
+        try:
+            # Temporarily make check_output "missing" (None)
+            subprocess.check_output = None  # type: ignore[assignment]
+            audit._ensure_installed()
+            # check_output should NOT be in originals (skipped)
+            assert "check_output" not in audit._originals
+            # run should still be wrapped
+            assert "run" in audit._originals
+        finally:
+            subprocess.check_output = saved  # type: ignore[assignment]
+            for name, orig in audit._originals.items():
+                setattr(subprocess, name, orig)
+
+
+class TestExtractPatchTargets:
+    """Tests for _extract_patch_targets (lines 263-291)."""
+
+    def _parse_func(self, source: str) -> ast.FunctionDef:
+        tree = ast.parse(textwrap.dedent(source))
+        return tree.body[0]  # type: ignore[return-value]
+
+    def test_patch_object_extracted(self) -> None:
+        """patch.object(module, "name") should extract the short name."""
+        node = self._parse_func(
+            """
+            def test_foo():
+                with patch.object(mymodule, "subprocess"):
+                    mymodule.do_thing()
+            """
+        )
+        targets = _extract_patch_targets(node)
+        assert "subprocess" in targets
+
+    def test_patch_object_with_module_alias(self) -> None:
+        """patch.object with a module alias Name as first arg."""
+        node = self._parse_func(
+            """
+            def test_foo():
+                with patch.object(subprocess, "run"):
+                    subprocess.run(["echo"])
+            """
+        )
+        targets = _extract_patch_targets(node)
+        assert "run" in targets
+
+    def test_with_patch_context_manager_extracted(self) -> None:
+        """with patch("module.func") in function body should be extracted."""
+        node = self._parse_func(
+            """
+            def test_foo():
+                with patch("mymodule.subprocess.run"):
+                    mymodule.do_thing()
+            """
+        )
+        targets = _extract_patch_targets(node)
+        assert "mymodule.subprocess.run" in targets
+        assert "run" in targets
+
+    def test_with_multiple_patch_context_managers(self) -> None:
+        """with patch("a"), patch("b") should extract both."""
+        node = self._parse_func(
+            """
+            def test_foo():
+                with patch("mod.a"), patch("mod.b"):
+                    pass
+            """
+        )
+        targets = _extract_patch_targets(node)
+        assert "mod.a" in targets
+        assert "mod.b" in targets
+        assert "a" in targets
+        assert "b" in targets
+
+    def test_patch_object_non_string_second_arg_ignored(self) -> None:
+        """patch.object with non-string 2nd arg should not crash."""
+        node = self._parse_func(
+            """
+            def test_foo():
+                with patch.object(mymodule, some_var):
+                    pass
+            """
+        )
+        targets = _extract_patch_targets(node)
+        assert targets == set()
+
+
+class TestCallGraph:
+    """Tests for CallGraph building (lines 409, 419-420, 449, 470)."""
+
+    def _make_src(self, tmp_path: Path, files: dict[str, str]) -> Path:
+        src = tmp_path / "src"
+        src.mkdir()
+        for rel, content in files.items():
+            f = src / rel
+            f.parent.mkdir(parents=True, exist_ok=True)
+            f.write_text(textwrap.dedent(content))
+        return src
+
+    def test_ensure_built_cached(self, tmp_path: Path) -> None:
+        """_ensure_built should only build once (cached return)."""
+        src = self._make_src(tmp_path, {"pkg/__init__.py": "", "pkg/mod.py": "def foo():\n    pass\n"})
+        cg = CallGraph(src)
+        cg._ensure_built()
+        assert cg._built is True
+        nodes_before = dict(cg._nodes)
+        # Second call should be a no-op
+        cg._ensure_built()
+        assert cg._nodes == nodes_before
+
+    def test_build_skips_syntax_error(self, tmp_path: Path) -> None:
+        """Files with syntax errors should be skipped, not crash."""
+        src = self._make_src(
+            tmp_path,
+            {
+                "pkg/__init__.py": "",
+                "pkg/broken.py": "def test(:\n  pass\n",
+                "pkg/good.py": "def foo():\n    pass\n",
+            },
+        )
+        cg = CallGraph(src)
+        cg._ensure_built()
+        # good.py's foo should be registered, broken.py skipped
+        assert any("foo" in k for k in cg._nodes)
+
+    def test_build_skips_unicode_decode_error(self, tmp_path: Path) -> None:
+        """Files with invalid UTF-8 should be skipped."""
+        src = tmp_path / "src"
+        src.mkdir()
+        (src / "pkg").mkdir()
+        (src / "pkg" / "__init__.py").write_text("")
+        (src / "pkg" / "binary.py").write_bytes(b"\xff\xfe\x00\xbad bytes")
+        (src / "pkg" / "good.py").write_text("def foo():\n    pass\n")
+        cg = CallGraph(src)
+        cg._ensure_built()
+        assert any("foo" in k for k in cg._nodes)
+
+    def test_scan_node_skips_classdef(self, tmp_path: Path) -> None:
+        """Methods inside classes should NOT be registered."""
+        src = self._make_src(
+            tmp_path,
+            {
+                "pkg/__init__.py": "",
+                "pkg/mod.py": """
+                    class MyClass:
+                        def my_method(self):
+                            subprocess.run(["echo"])
+                    def top_level():
+                        pass
+                """,
+            },
+        )
+        cg = CallGraph(src)
+        cg._ensure_built()
+        # top_level should be registered
+        assert "pkg.mod.top_level" in cg._nodes
+        # my_method should NOT be registered (class body skipped)
+        assert "pkg.mod.my_method" not in cg._nodes
+        assert "my_method" not in cg._by_short
+
+    def test_register_function_records_io_calls(self, tmp_path: Path) -> None:
+        """KNOWN_IO_FUNCTIONS calls should be recorded in io_calls."""
+        src = self._make_src(
+            tmp_path,
+            {
+                "pkg/__init__.py": "",
+                "pkg/mod.py": """
+                    def foo():
+                        get_pat("staging")
+                        load_secrets("prod")
+                """,
+            },
+        )
+        cg = CallGraph(src)
+        cg._ensure_built()
+        node = cg._nodes["pkg.mod.foo"]
+        assert "get_pat" in node.io_calls
+        assert "load_secrets" in node.io_calls
+
+    def test_register_function_records_subprocess_calls(self, tmp_path: Path) -> None:
+        """subprocess.run calls should be recorded in subprocess_calls."""
+        src = self._make_src(
+            tmp_path,
+            {
+                "pkg/__init__.py": "",
+                "pkg/mod.py": """
+                    import subprocess
+                    def foo():
+                        subprocess.run(["echo"])
+                """,
+            },
+        )
+        cg = CallGraph(src)
+        cg._ensure_built()
+        node = cg._nodes["pkg.mod.foo"]
+        assert "subprocess.run" in node.subprocess_calls
+
+
+class TestFindReachableDangerous:
+    """Tests for find_reachable_dangerous (lines 516-580)."""
+
+    def _make_src(self, tmp_path: Path, files: dict[str, str]) -> Path:
+        src = tmp_path / "src"
+        src.mkdir()
+        for rel, content in files.items():
+            f = src / rel
+            f.parent.mkdir(parents=True, exist_ok=True)
+            f.write_text(textwrap.dedent(content))
+        return src
+
+    def test_import_map_resolution(self, tmp_path: Path) -> None:
+        """import_map should resolve target to a precise full name."""
+        src = self._make_src(
+            tmp_path,
+            {
+                "pkg/__init__.py": "",
+                "pkg/mod.py": """
+                    import subprocess
+                    def main():
+                        subprocess.run(["echo"])
+                """,
+            },
+        )
+        cg = CallGraph(src)
+        dangerous = cg.find_reachable_dangerous("main", set(), import_map={"main": "pkg.mod.main"})
+        assert len(dangerous) == 1
+        assert "subprocess" in dangerous[0][1]
+
+    def test_import_map_falls_back_to_short_name(self, tmp_path: Path) -> None:
+        """If import_map value not in nodes, fall back to short name (line 516)."""
+        src = self._make_src(
+            tmp_path,
+            {
+                "pkg/__init__.py": "",
+                "pkg/mod.py": """
+                    import subprocess
+                    def main():
+                        subprocess.run(["echo"])
+                """,
+            },
+        )
+        cg = CallGraph(src)
+        # import_map points to a non-existent full name → fallback to by_short
+        dangerous = cg.find_reachable_dangerous("main", set(), import_map={"main": "nonexistent.pkg.main"})
+        assert len(dangerous) == 1
+
+    def test_no_candidates_returns_empty(self, tmp_path: Path) -> None:
+        """If no candidates found, return empty list (line 526)."""
+        src = self._make_src(tmp_path, {"pkg/__init__.py": ""})
+        cg = CallGraph(src)
+        dangerous = cg.find_reachable_dangerous("nonexistent", set())
+        assert dangerous == []
+
+    def test_fully_qualified_name_candidate(self, tmp_path: Path) -> None:
+        """A fully-qualified target_name in nodes should be used directly (line 519)."""
+        src = self._make_src(
+            tmp_path,
+            {
+                "pkg/__init__.py": "",
+                "pkg/mod.py": """
+                    import subprocess
+                    def main():
+                        subprocess.run(["echo"])
+                """,
+            },
+        )
+        cg = CallGraph(src)
+        dangerous = cg.find_reachable_dangerous("pkg.mod.main", set())
+        assert len(dangerous) == 1
+
+    def test_short_name_fallback(self, tmp_path: Path) -> None:
+        """target_name not in nodes falls back to short name (line 522)."""
+        src = self._make_src(
+            tmp_path,
+            {
+                "pkg/__init__.py": "",
+                "pkg/mod.py": """
+                    import subprocess
+                    def main():
+                        subprocess.run(["echo"])
+                """,
+            },
+        )
+        cg = CallGraph(src)
+        # "pkg.main" is not a full name in nodes, so it falls back to "main"
+        dangerous = cg.find_reachable_dangerous("pkg.main", set())
+        assert len(dangerous) == 1
+
+    def test_visited_prevents_infinite_loop(self, tmp_path: Path) -> None:
+        """Visited set prevents infinite loops (line 535)."""
+        src = self._make_src(
+            tmp_path,
+            {
+                "pkg/__init__.py": "",
+                "pkg/mod.py": """
+                    def a():
+                        b()
+                    def b():
+                        a()
+                        subprocess.run(["echo"])
+                """,
+            },
+        )
+        cg = CallGraph(src)
+        dangerous = cg.find_reachable_dangerous("a", set())
+        assert len(dangerous) == 1
+
+    def test_depth_limit_stops_traversal(self, tmp_path: Path) -> None:
+        """max_depth should stop traversal (line 534)."""
+        src = self._make_src(
+            tmp_path,
+            {
+                "pkg/__init__.py": "",
+                "pkg/mod.py": """
+                    def a():
+                        b()
+                    def b():
+                        c()
+                    def c():
+                        subprocess.run(["echo"])
+                """,
+            },
+        )
+        cg = CallGraph(src)
+        # With max_depth=0, only the direct node is visited
+        dangerous = cg.find_reachable_dangerous("a", set(), max_depth=0)
+        assert dangerous == []
+
+    def test_node_not_found_continues(self, tmp_path: Path) -> None:
+        """If a queued node isn't in _nodes, continue (line 540)."""
+        src = self._make_src(tmp_path, {"pkg/__init__.py": ""})
+        cg = CallGraph(src)
+        # Manually inject a candidate that doesn't exist in nodes
+        cg._by_short["ghost"] = ["pkg.mod.ghost"]
+        dangerous = cg.find_reachable_dangerous("ghost", set())
+        assert dangerous == []
+
+    def test_io_calls_checked(self, tmp_path: Path) -> None:
+        """IO calls should be reported as dangerous (lines 551-554)."""
+        src = self._make_src(
+            tmp_path,
+            {
+                "pkg/__init__.py": "",
+                "pkg/mod.py": """
+                    def main():
+                        get_pat("staging")
+                """,
+            },
+        )
+        cg = CallGraph(src)
+        dangerous = cg.find_reachable_dangerous("main", set())
+        assert len(dangerous) == 1
+        assert "PAT" in dangerous[0][1] or "get_pat" in str(dangerous)
+
+    def test_io_calls_patched_skipped(self, tmp_path: Path) -> None:
+        """Patched IO calls should not be reported."""
+        src = self._make_src(
+            tmp_path,
+            {
+                "pkg/__init__.py": "",
+                "pkg/mod.py": """
+                    def main():
+                        get_pat("staging")
+                """,
+            },
+        )
+        cg = CallGraph(src)
+        dangerous = cg.find_reachable_dangerous("main", {"get_pat"})
+        assert dangerous == []
+
+    def test_patched_helper_skipped_in_enqueue(self, tmp_path: Path) -> None:
+        """A patched helper should not be enqueued (lines 559-560)."""
+        src = self._make_src(
+            tmp_path,
+            {
+                "pkg/__init__.py": "",
+                "pkg/mod.py": """
+                    def main():
+                        run_cmd()
+                    def run_cmd():
+                        subprocess.run(["echo"])
+                """,
+            },
+        )
+        cg = CallGraph(src)
+        # run_cmd is patched → should not traverse into it
+        dangerous = cg.find_reachable_dangerous("main", {"run_cmd"})
+        assert dangerous == []
+
+    def test_same_module_resolution(self, tmp_path: Path) -> None:
+        """Calls within the same module should prefer same-module resolution (lines 566-567)."""
+        src = self._make_src(
+            tmp_path,
+            {
+                "pkg/__init__.py": "",
+                "pkg/mod.py": """
+                    def main():
+                        helper()
+                    def helper():
+                        subprocess.run(["echo"])
+                """,
+            },
+        )
+        cg = CallGraph(src)
+        dangerous = cg.find_reachable_dangerous("main", set())
+        assert len(dangerous) == 1
+
+    def test_short_name_single_match_resolution(self, tmp_path: Path) -> None:
+        """A single global match by short name should be resolved (lines 571-572)."""
+        src = self._make_src(
+            tmp_path,
+            {
+                "pkg/__init__.py": "",
+                "pkg/mod.py": """
+                    def main():
+                        helper()
+                """,
+                "pkg/other.py": """
+                    import subprocess
+                    def helper():
+                        subprocess.run(["echo"])
+                """,
+            },
+        )
+        cg = CallGraph(src)
+        dangerous = cg.find_reachable_dangerous("main", set())
+        assert len(dangerous) == 1
+
+    def test_is_patched_endswith(self, tmp_path: Path) -> None:
+        """_is_patched should match patches ending with .short (line 580)."""
+        src = self._make_src(
+            tmp_path,
+            {
+                "pkg/__init__.py": "",
+                "pkg/mod.py": """
+                    import subprocess
+                    def main():
+                        subprocess.run(["echo"])
+                """,
+            },
+        )
+        cg = CallGraph(src)
+        # "devx.ci.release.subprocess.run" ends with ".run"
+        dangerous = cg.find_reachable_dangerous("main", {"devx.ci.release.subprocess.run"})
+        assert dangerous == []
+
+    def test_is_patched_full_name_match(self) -> None:
+        """_is_patched should match exact full name."""
+        assert CallGraph._is_patched("subprocess.run", "run", {"subprocess.run"}) is True
+
+    def test_is_patched_short_name_match(self) -> None:
+        """_is_patched should match short name in patches."""
+        assert CallGraph._is_patched("subprocess.run", "run", {"run"}) is True
+
+    def test_is_patched_no_match(self) -> None:
+        """_is_patched should return False when not patched."""
+        assert CallGraph._is_patched("subprocess.run", "run", {"other"}) is False
+
+    def test_is_patched_endswith_no_false_positive(self) -> None:
+        """endswith should not match substrings (e.g. 'run' vs 'run_cmd')."""
+        assert CallGraph._is_patched("mod.run_cmd", "run_cmd", {"mod.run"}) is False
+
+
+class TestVisitCallAttributeTarget:
+    """Tests for visit_Call with ast.Attribute target (lines 851-862)."""
+
+    def test_invoke_with_module_func_attribute(self, tmp_path: Path) -> None:
+        """runner.invoke(module.func) should resolve via import_map."""
+        src = tmp_path / "src"
+        src.mkdir()
+        (src / "pkg").mkdir()
+        (src / "pkg" / "__init__.py").write_text("")
+        (src / "pkg" / "cli.py").write_text("import subprocess\ndef main():\n    subprocess.run(['echo'])\n")
+
+        test_file = tmp_path / "test_example.py"
+        test_file.write_text(
+            textwrap.dedent(
+                """
+                from click.testing import CliRunner
+                import pkg.cli as cli_mod
+                class TestExample:
+                    def test_invoke(self) -> None:
+                        runner = CliRunner()
+                        result = runner.invoke(cli_mod.main, [])
+                """
+            )
+        )
+        cg = CallGraph(src)
+        violations = analyze_file(test_file, call_graph=cg)
+        transitive = [v for v in violations if v.category == "transitive-subprocess"]
+        assert len(transitive) == 1
+
+    def test_invoke_with_attribute_no_import_map(self, tmp_path: Path) -> None:
+        """runner.invoke(mod.func) where mod not in import_map uses attr only (line 860)."""
+        src = tmp_path / "src"
+        src.mkdir()
+        (src / "pkg").mkdir()
+        (src / "pkg" / "__init__.py").write_text("")
+        (src / "pkg" / "cli.py").write_text("import subprocess\ndef main():\n    subprocess.run(['echo'])\n")
+
+        test_file = tmp_path / "test_example.py"
+        test_file.write_text(
+            textwrap.dedent(
+                """
+                from click.testing import CliRunner
+                class TestExample:
+                    def test_invoke(self) -> None:
+                        runner = CliRunner()
+                        # unknown_mod not imported, so falls back to attr name
+                        result = runner.invoke(unknown_mod.main, [])
+                """
+            )
+        )
+        cg = CallGraph(src)
+        violations = analyze_file(test_file, call_graph=cg)
+        transitive = [v for v in violations if v.category == "transitive-subprocess"]
+        assert len(transitive) == 1
+
+    def test_invoke_with_attribute_non_name_value(self, tmp_path: Path) -> None:
+        """runner.invoke(get_obj().func) — target.value is not a Name (line 862)."""
+        src = tmp_path / "src"
+        src.mkdir()
+        (src / "pkg").mkdir()
+        (src / "pkg" / "__init__.py").write_text("")
+        (src / "pkg" / "cli.py").write_text("import subprocess\ndef main():\n    subprocess.run(['echo'])\n")
+
+        test_file = tmp_path / "test_example.py"
+        test_file.write_text(
+            textwrap.dedent(
+                """
+                from click.testing import CliRunner
+                class TestExample:
+                    def test_invoke(self) -> None:
+                        runner = CliRunner()
+                        result = runner.invoke(CliRunner().main, [])
+                """
+            )
+        )
+        cg = CallGraph(src)
+        violations = analyze_file(test_file, call_graph=cg)
+        transitive = [v for v in violations if v.category == "transitive-subprocess"]
+        assert len(transitive) == 1
+
+
+class TestIsIntegrationTest:
+    """Tests for _is_integration_test (lines 1076-1080)."""
+
+    def test_marker_based_integration(self) -> None:
+        """A test item with 'integration' in keywords should be detected."""
+        item = MagicMock()
+        item.keywords = {"integration", "test_foo"}
+        item.fspath = "tests/unit/test_foo.py"
+        assert _is_integration_test(item) is True
+
+    def test_path_based_integration(self) -> None:
+        """A test item in an integration/ directory should be detected."""
+        item = MagicMock()
+        item.keywords = {"test_foo"}
+        item.fspath = "tests/integration/test_foo.py"
+        assert _is_integration_test(item) is True
+
+    def test_not_integration_test(self) -> None:
+        """A regular test item should not be detected as integration."""
+        item = MagicMock()
+        item.keywords = {"test_foo"}
+        item.fspath = "tests/unit/test_foo.py"
+        assert _is_integration_test(item) is False
+
+    def test_no_keywords_attr(self) -> None:
+        """An item without keywords attr should use fspath only."""
+        item = MagicMock()
+        item.keywords = {}
+        item.fspath = "tests/unit/test_foo.py"
+        assert _is_integration_test(item) is False
+
+
+class TestLoadTestIsolationConfig:
+    """Tests for _load_test_isolation_config — project-specific rule merging."""
+
+    def test_merges_io_functions(self, tmp_path: Path, monkeypatch: pytest.MonkeyPatch) -> None:
+        """Project-specific io_functions are added to KNOWN_IO_FUNCTIONS."""
+        pyproject = tmp_path / "pyproject.toml"
+        pyproject.write_text(
+            '[tool.devx.check_test_isolation]\nio_functions = { "my_custom_io" = "reads from disk" }\n'
+        )
+        monkeypatch.chdir(tmp_path)
+        _load_test_isolation_config()
+        assert "my_custom_io" in KNOWN_IO_FUNCTIONS
+        assert KNOWN_IO_FUNCTIONS["my_custom_io"] == "reads from disk"
+
+    def test_merges_subprocess_helpers(self, tmp_path: Path, monkeypatch: pytest.MonkeyPatch) -> None:
+        """Project-specific subprocess_helpers are added."""
+        pyproject = tmp_path / "pyproject.toml"
+        pyproject.write_text(
+            '[tool.devx.check_test_isolation]\nsubprocess_helpers = { "my_sp_helper" = "calls subprocess.run" }\n'
+        )
+        monkeypatch.chdir(tmp_path)
+        _load_test_isolation_config()
+        assert "my_sp_helper" in KNOWN_SUBPROCESS_HELPERS
+
+    def test_merges_helper_internal_calls(self, tmp_path: Path, monkeypatch: pytest.MonkeyPatch) -> None:
+        """Project-specific helper_internal_calls are merged."""
+        pyproject = tmp_path / "pyproject.toml"
+        pyproject.write_text(
+            '[tool.devx.check_test_isolation]\nhelper_internal_calls = { "my_helper" = ["subprocess", "run_cmd"] }\n'
+        )
+        monkeypatch.chdir(tmp_path)
+        _load_test_isolation_config()
+        assert "my_helper" in HELPER_INTERNAL_CALLS
+        assert HELPER_INTERNAL_CALLS["my_helper"] == {"subprocess", "run_cmd"}
+
+    def test_merges_io_internal_calls(self, tmp_path: Path, monkeypatch: pytest.MonkeyPatch) -> None:
+        """Project-specific io_internal_calls are merged."""
+        pyproject = tmp_path / "pyproject.toml"
+        pyproject.write_text(
+            '[tool.devx.check_test_isolation]\nio_internal_calls = { "my_io_func" = ["open", "yaml"] }\n'
+        )
+        monkeypatch.chdir(tmp_path)
+        _load_test_isolation_config()
+        assert "my_io_func" in IO_INTERNAL_CALLS
+        assert IO_INTERNAL_CALLS["my_io_func"] == {"open", "yaml"}
+
+    def test_merges_heavy_module_imports(self, tmp_path: Path, monkeypatch: pytest.MonkeyPatch) -> None:
+        """Project-specific heavy_module_imports are merged."""
+        pyproject = tmp_path / "pyproject.toml"
+        pyproject.write_text('[tool.devx.check_test_isolation]\nheavy_module_imports = { "mymodule" = 150.0 }\n')
+        monkeypatch.chdir(tmp_path)
+        _load_test_isolation_config()
+        assert "mymodule" in HEAVY_MODULE_IMPORTS
+        assert HEAVY_MODULE_IMPORTS["mymodule"] == 150.0
+
+    def test_no_config_section_is_noop(self, tmp_path: Path, monkeypatch: pytest.MonkeyPatch) -> None:
+        """Missing [tool.devx.check_test_isolation] section is a no-op."""
+        pyproject = tmp_path / "pyproject.toml"
+        pyproject.write_text('[tool.devx]\nother_key = "value"\n')
+        monkeypatch.chdir(tmp_path)
+        before_io = dict(KNOWN_IO_FUNCTIONS)
+        _load_test_isolation_config()
+        assert before_io == KNOWN_IO_FUNCTIONS
+
+    def test_no_pyproject_is_noop(self, tmp_path: Path, monkeypatch: pytest.MonkeyPatch) -> None:
+        """No pyproject.toml at all is a no-op."""
+        monkeypatch.chdir(tmp_path)
+        before = dict(KNOWN_SUBPROCESS_HELPERS)
+        _load_test_isolation_config()
+        assert before == KNOWN_SUBPROCESS_HELPERS
+
+    def test_non_dict_config_is_noop(self, tmp_path: Path, monkeypatch: pytest.MonkeyPatch) -> None:
+        """A non-dict check_test_isolation section is a no-op."""
+        pyproject = tmp_path / "pyproject.toml"
+        pyproject.write_text('[tool.devx]\ncheck_test_isolation = "not_a_dict"\n')
+        monkeypatch.chdir(tmp_path)
+        before = dict(HEAVY_MODULE_IMPORTS)
+        _load_test_isolation_config()
+        assert before == HEAVY_MODULE_IMPORTS
+
+    def test_invalid_entry_types_are_skipped(self, tmp_path: Path, monkeypatch: pytest.MonkeyPatch) -> None:
+        """Entries with wrong types (non-str values) are silently skipped."""
+        pyproject = tmp_path / "pyproject.toml"
+        pyproject.write_text(
+            "[tool.devx.check_test_isolation]\n"
+            'io_functions = { "good_func" = "desc", "bad_func" = 123 }\n'
+            'heavy_module_imports = { "good_mod" = 100.0, "bad_mod" = "fast" }\n'
+        )
+        monkeypatch.chdir(tmp_path)
+        _load_test_isolation_config()
+        assert "good_func" in KNOWN_IO_FUNCTIONS
+        assert "bad_func" not in KNOWN_IO_FUNCTIONS
+        assert "good_mod" in HEAVY_MODULE_IMPORTS
+        assert "bad_mod" not in HEAVY_MODULE_IMPORTS
+
+    def test_extends_without_replacing_defaults(self, tmp_path: Path, monkeypatch: pytest.MonkeyPatch) -> None:
+        """Project config adds to defaults without removing them."""
+        pyproject = tmp_path / "pyproject.toml"
+        pyproject.write_text('[tool.devx.check_test_isolation]\nio_functions = { "project_func" = "project I/O" }\n')
+        monkeypatch.chdir(tmp_path)
+        _load_test_isolation_config()
+        # Default entries still present
+        assert "get_pat" in KNOWN_IO_FUNCTIONS
+        # Project entry added
+        assert "project_func" in KNOWN_IO_FUNCTIONS

tests/unit/test_check_test_speed.py

@@ -10,6 +10,7 @@ from devx.tools.check_test_speed import (
     DEFAULT_MAX_SECONDS,
     DEFAULT_MAX_SINGLE_SECONDS,
     TEST_COMMAND,
+    _ci_scale_limit,
     check_per_test_speed,
     check_speed,
     cli,
@@ -144,7 +145,26 @@ def test_main_module_block() -> None:
         mock_cli.assert_called_once_with([])
 
 
+class TestCiScaleLimit:
+    def test_no_scaling_when_not_ci(self) -> None:
+        with patch("devx.tools.check_test_speed._IS_CI", False):
+            assert _ci_scale_limit(10.0) == 10.0
+            assert _ci_scale_limit(0.5) == 0.5
+
+    def test_scales_when_ci(self) -> None:
+        with patch("devx.tools.check_test_speed._IS_CI", True):
+            with patch("devx.tools.check_test_speed.CI_SCALE_FACTOR", 4.0):
+                assert _ci_scale_limit(10.0) == 40.0
+                assert _ci_scale_limit(0.5) == 2.0
+
+    def test_custom_scale_factor(self) -> None:
+        with patch("devx.tools.check_test_speed._IS_CI", True):
+            with patch("devx.tools.check_test_speed.CI_SCALE_FACTOR", 2.5):
+                assert _ci_scale_limit(10.0) == 25.0
+
+
 class TestMain:
+    @patch("devx.tools.check_test_speed._IS_CI", False)
     @patch("devx.tools.check_test_speed.run_tests")
     @patch("devx.tools.check_test_speed.parse_duration")
     @patch("devx.tools.check_test_speed.check_speed")
@@ -174,6 +194,7 @@ class TestMain:
         mock_parse_per.assert_called_once()
         mock_check_per.assert_called_once_with([], DEFAULT_MAX_SINGLE_SECONDS)
 
+    @patch("devx.tools.check_test_speed._IS_CI", False)
     @patch("devx.tools.check_test_speed.run_tests")
     @patch("devx.tools.check_test_speed.parse_duration")
     def test_slow_total_exits(
@@ -189,6 +210,7 @@ class TestMain:
         assert result.exit_code == 1
         assert "too slow" in result.output.lower()
 
+    @patch("devx.tools.check_test_speed._IS_CI", False)
     @patch("devx.tools.check_test_speed.run_tests")
     @patch("devx.tools.check_test_speed.parse_duration")
     @patch("devx.tools.check_test_speed.check_speed")
@@ -213,6 +235,7 @@ class TestMain:
         assert "Per-test speed check FAILED" in result.output
         assert "test_slow" in result.output
 
+    @patch("devx.tools.check_test_speed._IS_CI", False)
     @patch("devx.tools.check_test_speed.run_tests")
     def test_parse_failure_exits(
         self,
@@ -225,6 +248,7 @@ class TestMain:
         assert result.exit_code == 1
         assert "Could not parse" in result.output
 
+    @patch("devx.tools.check_test_speed._IS_CI", False)
     @patch("devx.tools.check_test_speed.run_tests")
     @patch("devx.tools.check_test_speed.parse_duration")
     @patch("devx.tools.check_test_speed.check_speed")
@@ -248,6 +272,7 @@ class TestMain:
         assert result.exit_code == 0
         mock_check.assert_called_once_with(0.5, 1.5)
 
+    @patch("devx.tools.check_test_speed._IS_CI", False)
     @patch("devx.tools.check_test_speed.run_tests")
     @patch("devx.tools.check_test_speed.parse_duration")
     @patch("devx.tools.check_test_speed.check_speed")
@@ -270,6 +295,7 @@ class TestMain:
         mock_parse_per.assert_not_called()
         mock_check_per.assert_not_called()
 
+    @patch("devx.tools.check_test_speed._IS_CI", False)
     @patch("devx.tools.check_test_speed.run_tests")
     @patch("devx.tools.check_test_speed.parse_duration")
     @patch("devx.tools.check_test_speed.check_speed")
@@ -292,3 +318,32 @@ class TestMain:
         result = runner.invoke(cli, ["--max-single-seconds", "1.0"])
         assert result.exit_code == 0
         mock_check_per.assert_called_once_with([], 1.0)
+
+    @patch("devx.tools.check_test_speed._IS_CI", True)
+    @patch("devx.tools.check_test_speed.CI_SCALE_FACTOR", 4.0)
+    @patch("devx.tools.check_test_speed.run_tests")
+    @patch("devx.tools.check_test_speed.parse_duration")
+    @patch("devx.tools.check_test_speed.check_speed")
+    @patch("devx.tools.check_test_speed.parse_per_test_durations")
+    @patch("devx.tools.check_test_speed.check_per_test_speed")
+    def test_ci_scales_limits(
+        self,
+        mock_check_per: MagicMock,
+        mock_parse_per: MagicMock,
+        mock_check: MagicMock,
+        mock_parse: MagicMock,
+        mock_run: MagicMock,
+    ) -> None:
+        mock_run.return_value = ("out\n", "err\n")
+        mock_parse.return_value = 30.0  # would fail local (10s) but pass CI (40s)
+        mock_parse_per.return_value = []
+        mock_check_per.return_value = []
+
+        runner = CliRunner()
+        result = runner.invoke(cli, [])
+        assert result.exit_code == 0
+        assert "CI environment detected" in result.output
+        assert "scaling limits by 4.0x" in result.output
+        # check_speed called with scaled limit
+        mock_check.assert_called_once_with(30.0, 40.0)
+        mock_check_per.assert_called_once_with([], 2.0)

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_classify_changes.py

@@ -481,8 +481,9 @@ class TestRunGit:
 
 
 class TestMain:
+    @patch("devx.ci.classify_changes.get_changed_files", return_value=[])
     @patch("devx.ci.classify_changes.get_latest_tag", return_value="")
-    def test_no_tags_outputs_true(self, mock_tag: MagicMock) -> None:
+    def test_no_tags_outputs_true(self, mock_tag: MagicMock, mock_changes: MagicMock) -> None:
         runner = CliRunner()
         result = runner.invoke(main, ["--quiet"])
         assert result.exit_code == 0
@@ -555,8 +556,9 @@ class TestMain:
         # docs tag has no matching files — should not appear
         assert "Docs files" not in result.output
 
+    @patch("devx.ci.classify_changes.get_changed_files", return_value=[])
     @patch("devx.ci.classify_changes.get_latest_tag", return_value="")
-    def test_no_tags_non_quiet(self, mock_tag: MagicMock) -> None:
+    def test_no_tags_non_quiet(self, mock_tag: MagicMock, mock_changes: MagicMock) -> None:
         runner = CliRunner()
         result = runner.invoke(main, [])
         assert result.exit_code == 0
@@ -731,7 +733,10 @@ class TestGithubOutput:
         mock_clf.return_value = self._make_classifier_with_ansible()
         gh_file = tmp_path / "output.txt"
         monkeypatch.setenv("GITHUB_OUTPUT", str(gh_file))
-        with patch.object(classify_changes_mod, "get_latest_tag", return_value=""):
+        with (
+            patch.object(classify_changes_mod, "get_latest_tag", return_value=""),
+            patch.object(classify_changes_mod, "get_changed_files", return_value=["src/cli.py"]),
+        ):
             runner = CliRunner()
             result = runner.invoke(main, ["--github-output"])
         assert result.exit_code == 0
@@ -774,7 +779,10 @@ class TestGithubOutput:
         )
         gh_file = tmp_path / "output.txt"
         monkeypatch.setenv("GITHUB_OUTPUT", str(gh_file))
-        with patch.object(classify_changes_mod, "get_latest_tag", return_value=""):
+        with (
+            patch.object(classify_changes_mod, "get_latest_tag", return_value=""),
+            patch.object(classify_changes_mod, "get_changed_files", return_value=["src/cli.py"]),
+        ):
             runner = CliRunner()
             result = runner.invoke(main, ["--github-output"])
         assert result.exit_code == 0
@@ -789,8 +797,9 @@ class TestGithubOutput:
         mock_clf.return_value = self._make_classifier_with_ansible()
         gh_file = tmp_path / "output.txt"
         monkeypatch.setenv("GITHUB_OUTPUT", str(gh_file))
-        runner = CliRunner()
-        result = runner.invoke(main, ["--github-output", "--force"])
+        with patch.object(classify_changes_mod, "get_changed_files", return_value=["src/cli.py"]):
+            runner = CliRunner()
+            result = runner.invoke(main, ["--github-output", "--force"])
         assert result.exit_code == 0
         content = gh_file.read_text()
         assert "user-facing-changed=true" in content
@@ -822,8 +831,9 @@ class TestGithubOutput:
         )
         gh_file = tmp_path / "output.txt"
         monkeypatch.setenv("GITHUB_OUTPUT", str(gh_file))
-        runner = CliRunner()
-        result = runner.invoke(main, ["--github-output", "--force"])
+        with patch.object(classify_changes_mod, "get_changed_files", return_value=["src/cli.py"]):
+            runner = CliRunner()
+            result = runner.invoke(main, ["--github-output", "--force"])
         assert result.exit_code == 0
         content = gh_file.read_text()
         assert "user-facing-changed=true" in content
@@ -836,8 +846,9 @@ class TestGithubOutput:
         gh_file = tmp_path / "output.txt"
         monkeypatch.setenv("GITHUB_OUTPUT", str(gh_file))
         monkeypatch.setenv("FORCE_DEPLOY", "true")
-        runner = CliRunner()
-        result = runner.invoke(main, ["--github-output"])
+        with patch.object(classify_changes_mod, "get_changed_files", return_value=["src/cli.py"]):
+            runner = CliRunner()
+            result = runner.invoke(main, ["--github-output"])
         assert result.exit_code == 0
         content = gh_file.read_text()
         assert "user-facing-changed=true" in content
@@ -869,8 +880,9 @@ class TestGithubOutput:
         gh_file = tmp_path / "output.txt"
         monkeypatch.setenv("GITHUB_OUTPUT", str(gh_file))
         monkeypatch.setenv("FORCE_DEPLOY", "false")
-        runner = CliRunner()
-        result = runner.invoke(main, ["--github-output", "--force"])
+        with patch.object(classify_changes_mod, "get_changed_files", return_value=["src/cli.py"]):
+            runner = CliRunner()
+            result = runner.invoke(main, ["--github-output", "--force"])
         assert result.exit_code == 0
         content = gh_file.read_text()
         assert "user-facing-changed=true" in content

tests/unit/test_cli.py

@@ -40,7 +40,6 @@ class TestCliGroups:
         result = runner.invoke(cli, ["molecule", "--help"])
         assert result.exit_code == 0
         assert "distribute" in result.output
-        assert "guard" in result.output
         assert "all" in result.output
 
 
@@ -231,13 +230,6 @@ class TestMoleculeCommands:
         assert result.exit_code == 0
         mock_run.assert_called_once_with("devx.molecule.discover_runners", [])
 
-    @patch("devx.cli._run_module")
-    def test_molecule_guard(self, mock_run: MagicMock) -> None:
-        runner = CliRunner()
-        result = runner.invoke(cli, ["molecule", "guard"])
-        assert result.exit_code == 0
-        mock_run.assert_called_once_with("devx.molecule.molecule_ci_guard", [])
-
     @patch("devx.cli._run_module")
     def test_molecule_all(self, mock_run: MagicMock) -> None:
         runner = CliRunner()

tests/unit/test_create_pr.py

@@ -144,19 +144,21 @@ class TestCli:
         assert result.exit_code == 0
         mock_create.assert_called_once_with("DEVX-42-fix", "master", "", "owner", "repo")
 
+    @patch("devx.tools.create_pr.subprocess.run")
     @patch("devx.tools.create_pr.create_pr")
     @patch("devx.tools.create_pr.REPO_OWNER", "owner")
     @patch("devx.tools.create_pr.get_repo_name", return_value="repo")
-    def test_explicit_branch(self, mock_repo: MagicMock, mock_create: MagicMock) -> None:
+    def test_explicit_branch(self, mock_repo: MagicMock, mock_create: MagicMock, mock_subproc: MagicMock) -> None:
         mock_create.return_value = {"number": 1}
         runner = CliRunner()
         result = runner.invoke(cli, ["--branch", "DEVX-42-fix"])
         assert result.exit_code == 0
 
+    @patch("devx.tools.create_pr.subprocess.run")
     @patch("devx.tools.create_pr.create_pr")
     @patch("devx.tools.create_pr.REPO_OWNER", "owner")
     @patch("devx.tools.create_pr.get_repo_name", return_value="repo")
-    def test_body_from_stdin(self, mock_repo: MagicMock, mock_create: MagicMock) -> None:
+    def test_body_from_stdin(self, mock_repo: MagicMock, mock_create: MagicMock, mock_subproc: MagicMock) -> None:
         mock_create.return_value = {"number": 1}
         runner = CliRunner()
         result = runner.invoke(cli, ["--branch", "DEVX-42-fix", "--body", "-"], input="PR body text")
@@ -164,17 +166,19 @@ class TestCli:
         mock_create.assert_called_once()
         assert mock_create.call_args.args[2] == "PR body text"
 
+    @patch("devx.tools.create_pr.subprocess.run")
     @patch("devx.tools.create_pr.REPO_OWNER", "")
     @patch("devx.tools.create_pr.get_repo_name", return_value="repo")
-    def test_missing_owner(self, mock_repo: MagicMock) -> None:
+    def test_missing_owner(self, mock_repo: MagicMock, mock_subproc: MagicMock) -> None:
         runner = CliRunner()
         result = runner.invoke(cli, ["--branch", "DEVX-42-fix"])
         assert result.exit_code != 0
         assert "owner" in result.output.lower()
 
+    @patch("devx.tools.create_pr.subprocess.run")
     @patch("devx.tools.create_pr.create_pr")
     @patch("devx.tools.create_pr.get_repo_name", return_value="repo")
-    def test_explicit_owner(self, mock_repo: MagicMock, mock_create: MagicMock) -> None:
+    def test_explicit_owner(self, mock_repo: MagicMock, mock_create: MagicMock, mock_subproc: MagicMock) -> None:
         mock_create.return_value = {"number": 1}
         runner = CliRunner()
         result = runner.invoke(cli, ["--branch", "DEVX-42-fix", "--owner", "custom"])

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_docker_login.py

@@ -90,8 +90,9 @@ class TestCli:
         assert result.exit_code == 0
         mock_login.assert_called_once_with("reg.io", "emil", "tok", suppress_failure=False)
 
+    @patch("devx.tools.docker_login.docker_login")
     @patch.dict("os.environ", {}, clear=True)
-    def test_required_no_token_raises(self) -> None:
+    def test_required_no_token_raises(self, mock_login: MagicMock) -> None:
         runner = CliRunner()
         result = runner.invoke(
             cli,
@@ -99,8 +100,9 @@ class TestCli:
         )
         assert result.exit_code != 0
 
+    @patch("devx.tools.docker_login.docker_login")
     @patch.dict("os.environ", {}, clear=True)
-    def test_optional_no_token_skips(self) -> None:
+    def test_optional_no_token_skips(self, mock_login: MagicMock) -> None:
         runner = CliRunner()
         result = runner.invoke(
             cli,

tests/unit/test_fix_pr_title.py

@@ -0,0 +1,195 @@
+"""Tests for devx.ci.fix_pr_title."""
+
+from __future__ import annotations
+
+from unittest.mock import MagicMock, patch
+
+import pytest
+from click.testing import CliRunner
+
+from devx.ci.fix_pr_title import cli
+
+
+@pytest.fixture(autouse=True)
+def _obl_infra_prefix(monkeypatch: pytest.MonkeyPatch) -> None:
+    """Use OBL-INFRA prefix to match infra repo conventions."""
+    import re
+
+    monkeypatch.setattr("devx.ci.fix_pr_title.TASK_PREFIX", "OBL-INFRA")
+    monkeypatch.setattr("devx.ci.auto_merge.TASK_PREFIX", "OBL-INFRA")
+    monkeypatch.setattr("devx.ci.auto_merge.PR_TITLE_RE", re.compile(r"^OBL-INFRA-\d+:\s+.+"))
+    monkeypatch.setattr("devx.ci.auto_merge._TASK_ID_PREFIX_RE", re.compile(r"^OBL-INFRA-\d+:\s*"))
+    monkeypatch.setattr("devx.ci._shared.TASK_ID_RE", re.compile(r"OBL-INFRA-\d+"))
+
+
+class TestFixPrTitle:
+    @patch("devx.ci.fix_pr_title.get_ci_token")
+    @patch("devx.ci.fix_pr_title.GiteaClient")
+    @patch("devx.ci.fix_pr_title.get_vikunja_title_optional")
+    def test_fixes_title_with_vikunja(
+        self,
+        mock_vikunja: MagicMock,
+        mock_gitea_cls: MagicMock,
+        mock_ci_token: MagicMock,
+    ) -> None:
+        """PR title is updated to match task ID + Vikunja title."""
+        mock_client = MagicMock()
+        mock_gitea_cls.return_value = mock_client
+        mock_client.get_pr.return_value = {
+            "number": 42,
+            "title": "Fix blackbox exporter",
+            "head": {"ref": "OBL-INFRA-458-blackbox-ipv4"},
+        }
+        mock_vikunja.return_value = "Fix blackbox exporter IPv4 config"
+        mock_ci_token.return_value = "token"
+
+        runner = CliRunner()
+        result = runner.invoke(cli, ["--repo", "oblachno/infra", "--pr-number", "42"])
+
+        assert result.exit_code == 0
+        mock_client.update_pr.assert_called_once_with(42, {"title": "OBL-INFRA-458: Fix blackbox exporter IPv4 config"})
+
+    @patch("devx.ci.fix_pr_title.get_ci_token")
+    @patch("devx.ci.fix_pr_title.GiteaClient")
+    @patch("devx.ci.fix_pr_title.get_vikunja_title_optional")
+    def test_strips_conventional_commit_prefix_when_no_vikunja(
+        self,
+        mock_vikunja: MagicMock,
+        mock_gitea_cls: MagicMock,
+        mock_ci_token: MagicMock,
+    ) -> None:
+        """When Vikunja task not found, strips conventional-commit prefix from current title."""
+        mock_client = MagicMock()
+        mock_gitea_cls.return_value = mock_client
+        mock_client.get_pr.return_value = {
+            "number": 10,
+            "title": "fix: platform self-monitoring and fixes",
+            "head": {"ref": "OBL-INFRA-456-platform-fixes"},
+        }
+        mock_vikunja.return_value = None
+        mock_ci_token.return_value = "token"
+
+        runner = CliRunner()
+        result = runner.invoke(cli, ["--repo", "oblachno/infra", "--pr-number", "10"])
+
+        assert result.exit_code == 0
+        mock_client.update_pr.assert_called_once_with(
+            10, {"title": "OBL-INFRA-456: platform self-monitoring and fixes"}
+        )
+
+    @patch("devx.ci.fix_pr_title.get_ci_token")
+    @patch("devx.ci.fix_pr_title.GiteaClient")
+    @patch("devx.ci.fix_pr_title.get_vikunja_title_optional")
+    def test_already_correct_title_no_update(
+        self,
+        mock_vikunja: MagicMock,
+        mock_gitea_cls: MagicMock,
+        mock_ci_token: MagicMock,
+    ) -> None:
+        """When PR title is already correct, no update is made."""
+        mock_client = MagicMock()
+        mock_gitea_cls.return_value = mock_client
+        mock_client.get_pr.return_value = {
+            "number": 5,
+            "title": "OBL-INFRA-100: Fix bug",
+            "head": {"ref": "OBL-INFRA-100-fix-bug"},
+        }
+        mock_vikunja.return_value = "Fix bug"
+        mock_ci_token.return_value = "token"
+
+        runner = CliRunner()
+        result = runner.invoke(cli, ["--repo", "oblachno/infra", "--pr-number", "5"])
+
+        assert result.exit_code == 0
+        mock_client.update_pr.assert_not_called()
+
+    @patch("devx.ci.fix_pr_title.get_ci_token")
+    @patch("devx.ci.fix_pr_title.GiteaClient")
+    @patch("devx.ci.fix_pr_title.get_vikunja_title_optional")
+    def test_dry_run_no_update(
+        self,
+        mock_vikunja: MagicMock,
+        mock_gitea_cls: MagicMock,
+        mock_ci_token: MagicMock,
+    ) -> None:
+        """Dry run shows what would change without updating."""
+        mock_client = MagicMock()
+        mock_gitea_cls.return_value = mock_client
+        mock_client.get_pr.return_value = {
+            "number": 7,
+            "title": "Fix thing",
+            "head": {"ref": "OBL-INFRA-7-fix-thing"},
+        }
+        mock_vikunja.return_value = "Fix thing"
+        mock_ci_token.return_value = "token"
+
+        runner = CliRunner()
+        result = runner.invoke(cli, ["--repo", "oblachno/infra", "--pr-number", "7", "--dry-run"])
+
+        assert result.exit_code == 0
+        mock_client.update_pr.assert_not_called()
+
+    @patch("devx.ci.fix_pr_title.get_ci_token")
+    @patch("devx.ci.fix_pr_title.GiteaClient")
+    def test_no_task_id_in_branch_exits_error(
+        self,
+        mock_gitea_cls: MagicMock,
+        mock_ci_token: MagicMock,
+    ) -> None:
+        """When branch has no task ID, exits with error."""
+        mock_client = MagicMock()
+        mock_gitea_cls.return_value = mock_client
+        mock_client.get_pr.return_value = {
+            "number": 1,
+            "title": "Some title",
+            "head": {"ref": "just-a-branch"},
+        }
+        mock_ci_token.return_value = "token"
+
+        runner = CliRunner()
+        result = runner.invoke(cli, ["--repo", "oblachno/infra", "--pr-number", "1"])
+
+        assert result.exit_code != 0
+        mock_client.update_pr.assert_not_called()
+
+    @patch("devx.ci.fix_pr_title.get_ci_token")
+    def test_no_token_exits_error(self, mock_ci_token: MagicMock) -> None:
+        """When CI token is not set, exits with error."""
+        mock_ci_token.side_effect = Exception("no token")
+
+        runner = CliRunner()
+        result = runner.invoke(cli, ["--repo", "oblachno/infra", "--pr-number", "1"])
+
+        assert result.exit_code != 0
+
+    @patch("devx.ci.fix_pr_title.get_ci_token")
+    @patch("devx.ci.fix_pr_title.GiteaClient")
+    @patch("devx.ci.fix_pr_title.get_vikunja_title_optional")
+    def test_strips_task_id_prefix_from_vikunja_title(
+        self,
+        mock_vikunja: MagicMock,
+        mock_gitea_cls: MagicMock,
+        mock_ci_token: MagicMock,
+    ) -> None:
+        """When Vikunja title already has task ID prefix, it's stripped to avoid double prefix."""
+        mock_client = MagicMock()
+        mock_gitea_cls.return_value = mock_client
+        mock_client.get_pr.return_value = {
+            "number": 99,
+            "title": "Fix thing",
+            "head": {"ref": "OBL-INFRA-99-fix-thing"},
+        }
+        mock_vikunja.return_value = "OBL-INFRA-99: Fix thing"
+        mock_ci_token.return_value = "token"
+
+        runner = CliRunner()
+        result = runner.invoke(cli, ["--repo", "oblachno/infra", "--pr-number", "99"])
+
+        assert result.exit_code == 0
+        mock_client.update_pr.assert_called_once_with(99, {"title": "OBL-INFRA-99: Fix thing"})
+
+    def test_invalid_repo_format_exits_error(self) -> None:
+        """When repo is not in owner/name format, exits with error."""
+        runner = CliRunner()
+        result = runner.invoke(cli, ["--repo", "invalid", "--pr-number", "1"])
+        assert result.exit_code != 0

tests/unit/test_gitea_cli.py

@@ -1,4 +1,4 @@
-"""Unit tests for scripts/gitea_cli.py."""
+"""Unit tests for devx/gitea_cli.py."""
 
 from __future__ import annotations
 
@@ -7,7 +7,13 @@ from unittest.mock import MagicMock, patch
 
 import pytest
 
-from devx.gitea_cli import TeaCLI, TeaCLIError, _extract_issue_number, _extract_pr_number, configure_tea_login
+from devx.gitea_cli import (
+    TeaCLI,
+    TeaCLIError,
+    _extract_issue_number,
+    _extract_pr_number,
+    configure_tea_login,
+)
 
 
 class TestExtractIssueNumber:
@@ -77,6 +83,25 @@ class TestTeaCLIRun:
             with pytest.raises(TeaCLIError, match="auth error"):
                 cli._run(["labels", "list"])
 
+    def test_run_failure_includes_stdout(self) -> None:
+        """tea writes some errors to stdout (e.g. 'no available login')."""
+        cli = TeaCLI(tea_bin="/fake/tea")
+        mock_result = MagicMock(returncode=1, stdout="no available login", stderr="")
+        with patch("subprocess.run", return_value=mock_result):
+            with pytest.raises(TeaCLIError, match="no available login"):
+                cli._run(["releases", "create"])
+
+    def test_run_failure_includes_both_stdout_and_stderr(self) -> None:
+        """When both stdout and stderr have content, both are included."""
+        cli = TeaCLI(tea_bin="/fake/tea")
+        mock_result = MagicMock(returncode=1, stdout="partial error", stderr="auth error")
+        with patch("subprocess.run", return_value=mock_result):
+            with pytest.raises(TeaCLIError, match="partial error"):
+                cli._run(["labels", "list"])
+            with patch("subprocess.run", return_value=mock_result):
+                with pytest.raises(TeaCLIError, match="auth error"):
+                    cli._run(["labels", "list"])
+
     def test_run_tea_not_found_raises_tea_error(self) -> None:
         cli = TeaCLI(tea_bin="tea")
         with patch("subprocess.run", side_effect=FileNotFoundError("tea not found")):
@@ -100,6 +125,46 @@ class TestTeaCLIRun:
         cmd = mock_run.call_args[0][0]
         assert "--output" not in cmd
 
+    def test_run_retries_on_502(self) -> None:
+        """Transient 502 errors should be retried, then succeed."""
+        cli = TeaCLI(tea_bin="/fake/tea")
+        fail_result = MagicMock(returncode=1, stdout="", stderr="502 Bad Gateway")
+        success_result = MagicMock(returncode=0, stdout='[{"id": 1}]', stderr="")
+        with patch("subprocess.run", side_effect=[fail_result, success_result]) as mock_run:
+            with patch("tenacity.nap.time.sleep"):
+                output = cli._run(["labels", "list"])
+        assert output == '[{"id": 1}]'
+        assert mock_run.call_count == 2
+
+    def test_run_retries_on_503_then_fails(self) -> None:
+        """If all retries are exhausted on 503, raise TeaCLIError."""
+        cli = TeaCLI(tea_bin="/fake/tea")
+        fail_result = MagicMock(returncode=1, stdout="", stderr="503 Service Unavailable")
+        with patch("subprocess.run", return_value=fail_result):
+            with patch("tenacity.nap.time.sleep"):
+                with pytest.raises(TeaCLIError, match="503"):
+                    cli._run(["issues", "create"])
+        # MAX_RETRIES=3, so 3 attempts total
+
+    def test_run_no_retry_on_non_transient_error(self) -> None:
+        """Non-transient errors (e.g. auth) should fail immediately without retry."""
+        cli = TeaCLI(tea_bin="/fake/tea")
+        fail_result = MagicMock(returncode=1, stdout="", stderr="auth error")
+        with patch("subprocess.run", return_value=fail_result) as mock_run:
+            with pytest.raises(TeaCLIError, match="auth error"):
+                cli._run(["labels", "list"])
+        assert mock_run.call_count == 1
+
+    def test_run_retries_on_429_in_stdout(self) -> None:
+        """429 rate limit in stdout should trigger retry."""
+        cli = TeaCLI(tea_bin="/fake/tea")
+        fail_result = MagicMock(returncode=1, stdout="429 Too Many Requests", stderr="")
+        success_result = MagicMock(returncode=0, stdout="ok", stderr="")
+        with patch("subprocess.run", side_effect=[fail_result, success_result]):
+            with patch("tenacity.nap.time.sleep"):
+                output = cli._run(["releases", "create"])
+        assert output == "ok"
+
 
 class TestRepoArg:
     def test_with_repo_arg(self) -> None:
@@ -380,9 +445,11 @@ class TestConfigureTeaLogin:
     def test_configures_login_when_not_present(self, mock_subprocess: MagicMock, mock_which: MagicMock) -> None:
         """configure_tea_login adds login when not already configured."""
         mock_list = MagicMock(returncode=0, stdout="")
-        mock_subprocess.return_value = mock_list
+        mock_add = MagicMock(returncode=0, stdout="Login successful", stderr="")
+        mock_default = MagicMock(returncode=0, stdout="", stderr="")
+        mock_subprocess.side_effect = [mock_list, mock_add, mock_default]
         configure_tea_login()
-        assert mock_subprocess.call_count >= 2  # login list + login add + login default
+        assert mock_subprocess.call_count == 3  # login list + login add + login default
 
     @patch.dict("os.environ", {"CI_GITEA_TOKEN": "tok"})
     @patch("devx.gitea_cli.shutil.which", return_value="/usr/bin/tea")
@@ -393,3 +460,37 @@ class TestConfigureTeaLogin:
         mock_subprocess.return_value = mock_list
         configure_tea_login()
         assert mock_subprocess.call_count == 1  # only login list, no add
+
+    @patch.dict("os.environ", {"CI_GITEA_TOKEN": "tok"})
+    @patch("devx.gitea_cli.shutil.which", return_value="/usr/bin/tea")
+    @patch("devx.gitea_cli.subprocess.run")
+    def test_raises_on_login_add_failure(self, mock_subprocess: MagicMock, mock_which: MagicMock) -> None:
+        """configure_tea_login raises TeaCLIError if tea login add fails."""
+        mock_list = MagicMock(returncode=0, stdout="")
+        mock_add = MagicMock(returncode=1, stdout="", stderr="invalid token")
+        mock_subprocess.side_effect = [mock_list, mock_add]
+        with pytest.raises(TeaCLIError, match="login add failed"):
+            configure_tea_login()
+
+    @patch.dict("os.environ", {"CI_GITEA_TOKEN": "tok"})
+    @patch("devx.gitea_cli.shutil.which", return_value="/usr/bin/tea")
+    @patch("devx.gitea_cli.subprocess.run")
+    def test_raises_on_login_default_failure(self, mock_subprocess: MagicMock, mock_which: MagicMock) -> None:
+        """configure_tea_login raises TeaCLIError if tea login default fails."""
+        mock_list = MagicMock(returncode=0, stdout="")
+        mock_add = MagicMock(returncode=0, stdout="Login successful", stderr="")
+        mock_default = MagicMock(returncode=1, stdout="", stderr="login not found")
+        mock_subprocess.side_effect = [mock_list, mock_add, mock_default]
+        with pytest.raises(TeaCLIError, match="login default failed"):
+            configure_tea_login()
+
+    @patch.dict("os.environ", {"CI_GITEA_TOKEN": "tok"})
+    @patch("devx.gitea_cli.shutil.which", return_value="/usr/bin/tea")
+    @patch("devx.gitea_cli.subprocess.run")
+    def test_login_add_failure_includes_stdout(self, mock_subprocess: MagicMock, mock_which: MagicMock) -> None:
+        """Error message includes stdout when tea writes errors there."""
+        mock_list = MagicMock(returncode=0, stdout="")
+        mock_add = MagicMock(returncode=1, stdout="Error: invalid username", stderr="")
+        mock_subprocess.side_effect = [mock_list, mock_add]
+        with pytest.raises(TeaCLIError, match="invalid username"):
+            configure_tea_login()

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_checkmake.py

@@ -66,7 +66,10 @@ class TestMain:
     def test_already_installed(self) -> None:
         from click.testing import CliRunner
 
-        with patch("shutil.which", return_value="/usr/bin/checkmake"):
+        with (
+            patch("shutil.which", return_value="/usr/bin/checkmake"),
+            patch("devx.tools.install_checkmake._install_with_go"),
+        ):
             runner = CliRunner()
             runner.invoke(install_checkmake.cli, [])
 
@@ -98,7 +101,10 @@ class TestMain:
         with patch.object(install_checkmake, "TARGET_PATH", target):
             with patch("shutil.which", side_effect=[None, None]):
                 with patch.object(platform, "machine", return_value="x86_64"):
-                    with patch("urllib.request.urlretrieve", side_effect=_write_file) as mock_retrieve:
+                    with (
+                        patch("urllib.request.urlretrieve", side_effect=_write_file) as mock_retrieve,
+                        patch("devx.tools.install_checkmake._install_with_go", return_value=False),
+                    ):
                         runner = CliRunner()
                         runner.invoke(install_checkmake.cli, [])
                         mock_retrieve.assert_called_once()

tests/unit/test_install_tools.py

@@ -1,6 +1,7 @@
 from __future__ import annotations
 
 import platform
+import urllib.request
 from pathlib import Path
 from unittest.mock import patch
 
@@ -47,13 +48,29 @@ class TestDownload:
     def test_download(self, tmp_path: Path) -> None:
         dest = tmp_path / "file.bin"
 
-        def _write_file(url: str, path: Path) -> tuple[str, None]:
-            Path(path).write_bytes(b"data")
-            return str(path), None
+        class _FakeResponse:
+            def __init__(self) -> None:
+                self._sent = False
 
-        with patch("urllib.request.urlretrieve", side_effect=_write_file) as mock_retrieve:
+            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"
+
+        with patch("urllib.request.urlopen", return_value=_FakeResponse()) as mock_urlopen:
             install_tools._download("https://example.com/file", dest)
-        mock_retrieve.assert_called_once()
+        mock_urlopen.assert_called_once()
+        call_args = mock_urlopen.call_args
+        req = call_args.args[0]
+        assert isinstance(req, urllib.request.Request)
+        assert req.get_header("User-agent") == "devx/install-tools"
         assert dest.read_bytes() == b"data"
 
 
@@ -221,6 +238,33 @@ 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:
@@ -297,6 +341,47 @@ class TestInstallVale:
         assert (tmp_path / "vale").exists()
 
 
+class TestInstallPromtool:
+    def test_already_installed(self) -> None:
+        with patch.object(install_tools, "_is_installed", return_value=True):
+            assert install_tools.install_promtool() is True
+
+    def test_install(self, tmp_path: Path) -> None:
+        import io
+        import tarfile
+
+        tarball_path = tmp_path / "archive.tar.gz"
+        binary_content = b"fake promtool"
+        with tarfile.open(tarball_path, "w:gz") as tar:
+            info = tarfile.TarInfo(name="promtool")
+            info.size = len(binary_content)
+            tar.addfile(info, io.BytesIO(binary_content))
+
+        with patch.object(install_tools, "_is_installed", return_value=False):
+            with patch.object(install_tools, "TARGET_DIR", tmp_path):
+                with patch.object(install_tools, "_arch", return_value="amd64"):
+                    with patch.object(
+                        install_tools,
+                        "_download",
+                        side_effect=lambda url, dest: Path(dest).write_bytes(tarball_path.read_bytes()),
+                    ):
+                        assert install_tools.install_promtool() is True
+        assert (tmp_path / "promtool").exists()
+
+    def test_url_contains_version(self, tmp_path: Path) -> None:
+        """Verify the download URL includes the correct promtool version."""
+        captured_url = []
+
+        def fake_extract(url: str, binary_name: str) -> Path:
+            captured_url.append(url)
+            return tmp_path / binary_name
+
+        with patch.object(install_tools, "_is_installed", return_value=False):
+            with patch.object(install_tools, "_download_and_extract_tarball", side_effect=fake_extract):
+                install_tools.install_promtool()
+        assert any(f"v{install_tools.PROMTOOL_VERSION}" in url for url in captured_url)
+
+
 class TestListTools:
     def test_list(self, tmp_path: Path) -> None:
         with patch.object(install_tools, "TARGET_DIR", tmp_path):
@@ -341,6 +426,11 @@ class TestInstallTool:
             assert install_tools._install_tool("vale") is True
         mock.assert_called_once()
 
+    def test_promtool(self) -> None:
+        with patch.object(install_tools, "install_promtool", return_value=True) as mock:
+            assert install_tools._install_tool("promtool") is True
+        mock.assert_called_once()
+
     def test_unknown_tool(self) -> None:
         with pytest.raises(ClickException, match="Unknown tool"):
             install_tools._install_tool("unknown")
@@ -359,7 +449,7 @@ class TestMain:
         with patch.object(install_tools, "_install_tool", return_value=True) as mock_install:
             result = runner.invoke(install_tools.main, [])
         assert result.exit_code == 0
-        assert mock_install.call_count == 7
+        assert mock_install.call_count == 8
 
     def test_install_specific_tool(self) -> None:
         runner = CliRunner()

tests/unit/test_integration_guard.py

@@ -7,6 +7,7 @@ import subprocess  # nosec B404
 import time
 from unittest.mock import MagicMock, patch
 
+import pytest
 from click.testing import CliRunner
 
 from devx.ci.integration_guard import cli
@@ -111,9 +112,8 @@ class TestCli:
                 clear=True,
             ),
             patch("devx.ci.integration_guard.POLL_INTERVAL", 0.01),
-            patch("devx.molecule.molecule_ci_guard.POLL_INTERVAL", 0.01),
             patch("devx.ci.integration_guard.subprocess.Popen") as mock_popen,
-            patch("devx.molecule.molecule_ci_guard.get_running_jobs", side_effect=get_jobs_side_effect),
+            patch("devx.ci.integration_guard.get_running_jobs", side_effect=get_jobs_side_effect),
             patch("os.killpg") as mock_killpg,
             patch("os.getpgid") as mock_getpgid,
             patch("time.sleep", side_effect=lambda x: real_sleep(0)),
@@ -158,9 +158,8 @@ class TestCli:
                 clear=True,
             ),
             patch("devx.ci.integration_guard.POLL_INTERVAL", 0.01),
-            patch("devx.molecule.molecule_ci_guard.POLL_INTERVAL", 0.01),
             patch("devx.ci.integration_guard.subprocess.Popen") as mock_popen,
-            patch("devx.molecule.molecule_ci_guard.get_running_jobs", side_effect=get_jobs_side_effect),
+            patch("devx.ci.integration_guard.get_running_jobs", side_effect=get_jobs_side_effect),
             patch("os.killpg", side_effect=ProcessLookupError("no such process")),
             patch("os.getpgid") as mock_getpgid,
             patch("time.sleep", side_effect=lambda x: real_sleep(0)),
@@ -203,9 +202,8 @@ class TestCli:
                 clear=True,
             ),
             patch("devx.ci.integration_guard.POLL_INTERVAL", 0.01),
-            patch("devx.molecule.molecule_ci_guard.POLL_INTERVAL", 0.01),
             patch("devx.ci.integration_guard.subprocess.Popen") as mock_popen,
-            patch("devx.molecule.molecule_ci_guard.get_running_jobs", side_effect=get_jobs_side_effect),
+            patch("devx.ci.integration_guard.get_running_jobs", side_effect=get_jobs_side_effect),
             patch("os.killpg") as mock_killpg,
             patch("os.getpgid") as mock_getpgid,
             patch("time.sleep", side_effect=lambda x: real_sleep(0)),
@@ -289,3 +287,125 @@ def test_main_module_block() -> None:
     namespace = dict(ig.__dict__)
     exec(compile(source, ig.__file__, "exec"), namespace)
     assert callable(namespace["cli"])
+
+
+class TestGetRunningJobs:
+    def test_returns_jobs(self) -> None:
+        with patch("devx.ci.integration_guard.requests.get") as mock_get:
+            mock_response = MagicMock()
+            mock_response.json.return_value = {
+                "jobs": [
+                    {"name": "integration-tests (0)", "conclusion": "success"},
+                    {"name": "integration-tests (1)", "conclusion": "failure"},
+                ]
+            }
+            mock_response.raise_for_status.return_value = None
+            mock_get.return_value = mock_response
+
+            from devx.ci.integration_guard import get_running_jobs
+
+            jobs = get_running_jobs("https://gitea.example", "owner", "repo", "token", 123)
+            assert len(jobs) == 2
+            mock_get.assert_called_once()
+
+    def test_raises_on_request_error(self) -> None:
+        import requests
+
+        with patch("devx.ci.integration_guard.requests.get") as mock_get:
+            mock_get.side_effect = requests.RequestException("boom")
+            with pytest.raises(requests.RequestException):
+                from devx.ci.integration_guard import get_running_jobs
+
+                get_running_jobs("https://gitea.example", "owner", "repo", "token", 123)
+
+
+class TestAnyOtherRunnerFailed:
+    def test_detects_other_failure(self) -> None:
+        from devx.ci.integration_guard import any_other_runner_failed
+
+        jobs = [
+            {"name": "integration-tests (0)", "conclusion": "success"},
+            {"name": "integration-tests (1)", "conclusion": "failure"},
+            {"name": "integration-tests (2)", "conclusion": "running"},
+        ]
+        assert any_other_runner_failed(jobs, "integration-tests", 0) is True
+
+    def test_ignores_current_runner(self) -> None:
+        from devx.ci.integration_guard import any_other_runner_failed
+
+        jobs = [
+            {"name": "integration-tests (0)", "conclusion": "failure"},
+            {"name": "integration-tests (1)", "conclusion": "success"},
+        ]
+        assert any_other_runner_failed(jobs, "integration-tests", 0) is False
+
+    def test_ignores_non_matching_jobs(self) -> None:
+        from devx.ci.integration_guard import any_other_runner_failed
+
+        jobs = [
+            {"name": "quality", "conclusion": "failure"},
+            {"name": "integration-tests (1)", "conclusion": "success"},
+        ]
+        assert any_other_runner_failed(jobs, "integration-tests", 0) is False
+
+
+class TestPollForOtherFailures:
+    def test_sets_failed_event_when_other_runner_fails(self) -> None:
+        from devx.ci.integration_guard import poll_for_other_failures
+
+        stop_event = MagicMock()
+        failed_event = MagicMock()
+
+        def side_effect(*args, **kwargs):
+            if stop_event.wait.call_count < 1:
+                return [
+                    {"name": "integration-tests (0)", "conclusion": "success"},
+                    {"name": "integration-tests (1)", "conclusion": "failure"},
+                ]
+            return []
+
+        with patch("devx.ci.integration_guard.get_running_jobs") as mock_get_jobs:
+            mock_get_jobs.side_effect = side_effect
+            stop_event.is_set.side_effect = [False, False]
+            stop_event.wait.return_value = True
+
+            poll_for_other_failures(
+                "https://gitea.example",
+                "owner",
+                "repo",
+                "token",
+                123,
+                "integration-tests",
+                0,
+                stop_event,
+                failed_event,
+            )
+
+            failed_event.set.assert_called_once()
+
+    def test_poll_warns_on_api_error(self) -> None:
+        import requests
+
+        from devx.ci.integration_guard import poll_for_other_failures
+
+        stop_event = MagicMock()
+        failed_event = MagicMock()
+
+        with patch("devx.ci.integration_guard.get_running_jobs") as mock_get_jobs:
+            mock_get_jobs.side_effect = requests.RequestException("boom")
+            stop_event.is_set.side_effect = [False, True]
+            stop_event.wait.return_value = True
+
+            poll_for_other_failures(
+                "https://gitea.example",
+                "owner",
+                "repo",
+                "token",
+                123,
+                "integration-tests",
+                0,
+                stop_event,
+                failed_event,
+            )
+
+            failed_event.set.assert_not_called()

tests/unit/test_molecule_all.py

@@ -1,7 +1,7 @@
 from __future__ import annotations
 
 from pathlib import Path
-from unittest.mock import patch
+from unittest.mock import MagicMock, patch
 
 import pytest
 from click.testing import CliRunner
@@ -87,14 +87,16 @@ class TestRunPlatform:
 
 
 class TestMain:
-    def test_molecule_not_found(self, tmp_path: Path, monkeypatch: pytest.MonkeyPatch) -> None:
+    @patch("devx.molecule.molecule_all._run_molecule")
+    def test_molecule_not_found(self, mock_run: MagicMock, tmp_path: Path, monkeypatch: pytest.MonkeyPatch) -> None:
         monkeypatch.chdir(tmp_path)
         runner = CliRunner()
         result = runner.invoke(molecule_all.main, ["--bin", "nonexistent/bin"])
         assert result.exit_code != 0
         assert "molecule not found" in result.output
 
-    def test_role_dir_not_found(self, tmp_path: Path, monkeypatch: pytest.MonkeyPatch) -> None:
+    @patch("devx.molecule.molecule_all._run_molecule")
+    def test_role_dir_not_found(self, mock_run: MagicMock, tmp_path: Path, monkeypatch: pytest.MonkeyPatch) -> None:
         monkeypatch.chdir(tmp_path)
         bin_dir = tmp_path / ".venv" / "bin"
         bin_dir.mkdir(parents=True)
@@ -104,7 +106,8 @@ class TestMain:
         assert result.exit_code != 0
         assert "Role directory not found" in result.output
 
-    def test_role_dir_no_molecule(self, tmp_path: Path, monkeypatch: pytest.MonkeyPatch) -> None:
+    @patch("devx.molecule.molecule_all._run_molecule")
+    def test_role_dir_no_molecule(self, mock_run: MagicMock, tmp_path: Path, monkeypatch: pytest.MonkeyPatch) -> None:
         """Roles dir exists but no role has molecule/ — should error."""
         monkeypatch.chdir(tmp_path)
         bin_dir = tmp_path / ".venv" / "bin"

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_molecule_ci_guard.py

@@ -1,564 +0,0 @@
-"""Unit tests for scripts/ci/molecule_ci_guard.py."""
-
-from __future__ import annotations
-
-import os
-import subprocess  # nosec B404
-import time
-from pathlib import Path
-from unittest.mock import MagicMock, patch
-
-import click
-import pytest
-import requests
-
-from devx.molecule.molecule_ci_guard import (
-    any_other_runner_failed,
-    build_env_for_pair,
-    build_molecule_cmd,
-    cli,
-    get_running_jobs,
-    parse_pair,
-    poll_for_other_failures,
-    resolve_role_dir,
-)
-
-
-class TestGetRunningJobs:
-    def test_returns_jobs(self) -> None:
-        with patch("devx.molecule.molecule_ci_guard.requests.get") as mock_get:
-            mock_response = MagicMock()
-            mock_response.json.return_value = {
-                "jobs": [
-                    {"name": "molecule-tests (0)", "conclusion": "success"},
-                    {"name": "molecule-tests (1)", "conclusion": "failure"},
-                ]
-            }
-            mock_response.raise_for_status.return_value = None
-            mock_get.return_value = mock_response
-
-            jobs = get_running_jobs("https://gitea.example", "owner", "repo", "token", 123)
-            assert len(jobs) == 2
-            mock_get.assert_called_once()
-
-    def test_raises_on_request_error(self) -> None:
-        with patch("devx.molecule.molecule_ci_guard.requests.get") as mock_get:
-            mock_get.side_effect = requests.RequestException("boom")
-            with pytest.raises(requests.RequestException):
-                get_running_jobs("https://gitea.example", "owner", "repo", "token", 123)
-
-
-class TestAnyOtherRunnerFailed:
-    def test_detects_other_failure(self) -> None:
-        jobs = [
-            {"name": "molecule-tests (0)", "conclusion": "success"},
-            {"name": "molecule-tests (1)", "conclusion": "failure"},
-            {"name": "molecule-tests (2)", "conclusion": "running"},
-        ]
-        assert any_other_runner_failed(jobs, "molecule-tests", 0) is True
-
-    def test_ignores_current_runner(self) -> None:
-        jobs = [
-            {"name": "molecule-tests (0)", "conclusion": "failure"},
-            {"name": "molecule-tests (1)", "conclusion": "success"},
-        ]
-        assert any_other_runner_failed(jobs, "molecule-tests", 0) is False
-
-    def test_ignores_non_molecule_jobs(self) -> None:
-        jobs = [
-            {"name": "quality", "conclusion": "failure"},
-            {"name": "molecule-tests (1)", "conclusion": "success"},
-        ]
-        assert any_other_runner_failed(jobs, "molecule-tests", 0) is False
-
-
-class TestBuildMoleculeCmd:
-    def test_default_scenario(self) -> None:
-        assert build_molecule_cmd("default") == ["molecule", "test"]
-
-    def test_named_scenario(self) -> None:
-        assert build_molecule_cmd("lifecycle") == ["molecule", "test", "-s", "lifecycle"]
-
-
-class TestBuildEnvForPair:
-    def test_with_command(self) -> None:
-        env = build_env_for_pair("default|ubuntu-2204|img:latest|/lib/systemd/systemd", {})
-        assert env["MOLECULE_PLATFORM_NAME"] == "ubuntu-2204"
-        assert env["MOLECULE_PLATFORM_IMAGE"] == "img:latest"
-        assert env["MOLECULE_PLATFORM_COMMAND"] == "/lib/systemd/systemd"
-        assert env["ANSIBLE_ALLOW_BROKEN_CONDITIONALS"] == "true"
-
-    def test_without_command(self) -> None:
-        env = build_env_for_pair("default|ubuntu-2204|img:latest|", {})
-        assert env["MOLECULE_PLATFORM_NAME"] == "ubuntu-2204"
-        assert "MOLECULE_PLATFORM_COMMAND" not in env
-
-    def test_without_command_removes_existing(self) -> None:
-        env = build_env_for_pair("default|ubuntu-2204|img:latest|", {"MOLECULE_PLATFORM_COMMAND": "old"})
-        assert "MOLECULE_PLATFORM_COMMAND" not in env
-
-    def test_preserves_existing_molecule_home(self) -> None:
-        """When MOLECULE_HOME is already set, it is not overridden."""
-        env = build_env_for_pair("default|ubuntu-2204|img:latest|", {"MOLECULE_HOME": "/custom/home"})
-        assert env["MOLECULE_HOME"] == "/custom/home"
-
-
-class TestPollForOtherFailures:
-    def test_sets_failed_event_when_other_runner_fails(self) -> None:
-        stop_event = MagicMock()
-        failed_event = MagicMock()
-
-        def side_effect(*args, **kwargs):
-            if stop_event.wait.call_count < 1:
-                return [
-                    {"name": "molecule-tests (0)", "conclusion": "success"},
-                    {"name": "molecule-tests (1)", "conclusion": "failure"},
-                ]
-            return []
-
-        with patch("devx.molecule.molecule_ci_guard.get_running_jobs") as mock_get_jobs:
-            mock_get_jobs.side_effect = side_effect
-            stop_event.is_set.side_effect = [False, False]
-            stop_event.wait.return_value = True
-
-            poll_for_other_failures(
-                "https://gitea.example",
-                "owner",
-                "repo",
-                "token",
-                123,
-                "molecule-tests",
-                0,
-                stop_event,
-                failed_event,
-            )
-
-            failed_event.set.assert_called_once()
-
-    def test_poll_warns_on_api_error(self) -> None:
-        stop_event = MagicMock()
-        failed_event = MagicMock()
-
-        with patch("devx.molecule.molecule_ci_guard.get_running_jobs") as mock_get_jobs:
-            mock_get_jobs.side_effect = requests.RequestException("boom")
-            stop_event.is_set.side_effect = [False, True]
-            stop_event.wait.return_value = True
-
-            poll_for_other_failures(
-                "https://gitea.example",
-                "owner",
-                "repo",
-                "token",
-                123,
-                "molecule-tests",
-                0,
-                stop_event,
-                failed_event,
-            )
-
-            failed_event.set.assert_not_called()
-
-
-class TestCli:
-    def test_all_pass(self) -> None:
-        from click.testing import CliRunner
-
-        with (
-            patch("devx.molecule.molecule_ci_guard.subprocess.Popen") as mock_popen,
-            patch("devx.molecule.molecule_ci_guard.subprocess.run") as mock_run,
-            patch("time.sleep"),
-        ):
-            proc = MagicMock()
-            proc.poll.return_value = 0
-            proc.returncode = 0
-            mock_popen.return_value = proc
-            mock_run.return_value = MagicMock(returncode=0)
-
-            runner = CliRunner()
-            result = runner.invoke(cli, ["default|ubuntu-2204|img:latest|"])
-            assert result.exit_code == 0
-            assert "All molecule tests passed" in result.output
-            # Verify Docker prune was called between scenarios
-            mock_run.assert_called_once_with(
-                ["docker", "system", "prune", "-af", "--volumes"],
-                check=False,
-                capture_output=True,
-                timeout=60,
-            )
-
-    @patch("devx.molecule.molecule_ci_guard.get_ci_token", side_effect=click.ClickException("no token"))
-    def test_missing_token_runs_without_polling(self, mock_token: MagicMock) -> None:
-        """When no token is available, cross-runner polling is skipped."""
-        from click.testing import CliRunner
-
-        with (
-            patch("devx.molecule.molecule_ci_guard.subprocess.Popen") as mock_popen,
-            patch("devx.molecule.molecule_ci_guard.subprocess.run") as mock_run,
-            patch("devx.molecule.molecule_ci_guard.poll_for_other_failures") as mock_poll,
-            patch("time.sleep"),
-        ):
-            proc = MagicMock()
-            proc.poll.return_value = 0
-            proc.returncode = 0
-            mock_popen.return_value = proc
-            mock_run.return_value = MagicMock(returncode=0)
-
-            runner = CliRunner()
-            result = runner.invoke(cli, ["default|ubuntu-2204|img:latest|"])
-            assert result.exit_code == 0
-            mock_poll.assert_not_called()
-
-    def test_invalid_pair_format_raises(self) -> None:
-        """Pair with fewer than 2 parts should raise."""
-        from click.testing import CliRunner
-
-        runner = CliRunner()
-        result = runner.invoke(cli, ["invalid_no_pipe"])
-        assert result.exit_code != 0
-        assert "Invalid pair format" in result.output
-
-    def test_failure_exits_nonzero(self) -> None:
-        from click.testing import CliRunner
-
-        with (
-            patch("devx.molecule.molecule_ci_guard.subprocess.Popen") as mock_popen,
-            patch("time.sleep"),
-        ):
-            proc = MagicMock()
-            proc.poll.return_value = 1
-            proc.returncode = 1
-            mock_popen.return_value = proc
-
-            runner = CliRunner()
-            result = runner.invoke(cli, ["default|ubuntu-2204|img:latest|"])
-            assert result.exit_code == 1
-            assert "FAILED" in result.output
-
-    def test_exits_before_starting_when_already_failed(self) -> None:
-        from click.testing import CliRunner
-
-        with (
-            patch.dict(
-                os.environ,
-                {
-                    "GITEA_URL": "https://gitea.example",
-                    "CI_GITEA_TOKEN": "token",
-                    "RUN_ID": "123",
-                    "JOB_NAME": "molecule-tests",
-                    "MATRIX_INDEX": "0",
-                    "GITEA_REPOSITORY": "my-org/my-repo",
-                    "PATH": os.environ.get("PATH", ""),
-                },
-                clear=True,
-            ),
-            patch("devx.molecule.molecule_ci_guard.POLL_INTERVAL", 0.01),
-            patch("devx.molecule.molecule_ci_guard.subprocess.Popen") as mock_popen,
-            patch("devx.molecule.molecule_ci_guard.get_running_jobs") as mock_get_jobs,
-            patch("time.sleep"),
-        ):
-            mock_get_jobs.return_value = [
-                {"name": "molecule-tests (0)", "conclusion": "running"},
-                {"name": "molecule-tests (1)", "conclusion": "failure"},
-            ]
-            proc = MagicMock()
-            proc.poll.return_value = 0
-            proc.returncode = 0
-            mock_popen.return_value = proc
-
-            runner = CliRunner()
-            result = runner.invoke(cli, ["default|ubuntu-2204|img:latest|"])
-            assert result.exit_code == 1
-            assert "Another molecule runner failed" in result.output
-
-    def test_keyboard_interrupt_kills_process(self) -> None:
-        from click.testing import CliRunner
-
-        with (
-            patch("devx.molecule.molecule_ci_guard.subprocess.Popen") as mock_popen,
-            patch("time.sleep", side_effect=KeyboardInterrupt),
-            patch("os.killpg") as mock_killpg,
-            patch("os.getpgid") as mock_getpgid,
-        ):
-            mock_getpgid.return_value = 123
-            proc = MagicMock()
-            proc.poll.return_value = None
-            proc.wait.return_value = 0
-            mock_popen.return_value = proc
-
-            runner = CliRunner()
-            result = runner.invoke(cli, ["default|ubuntu-2204|img:latest|"])
-            assert result.exit_code == 1
-            mock_killpg.assert_called()
-
-    def test_exits_when_other_runner_fails(self) -> None:
-        from click.testing import CliRunner
-
-        real_sleep = time.sleep
-        call_count = [0]
-
-        def get_jobs_side_effect(*args, **kwargs):
-            call_count[0] += 1
-            if call_count[0] < 2:
-                return [{"name": "molecule-tests (1)", "conclusion": "running"}]
-            return [
-                {"name": "molecule-tests (0)", "conclusion": "running"},
-                {"name": "molecule-tests (1)", "conclusion": "failure"},
-            ]
-
-        with (
-            patch.dict(
-                os.environ,
-                {
-                    "GITEA_URL": "https://gitea.example",
-                    "CI_GITEA_TOKEN": "token",
-                    "RUN_ID": "123",
-                    "JOB_NAME": "molecule-tests",
-                    "MATRIX_INDEX": "0",
-                    "GITEA_REPOSITORY": "my-org/my-repo",
-                    "PATH": os.environ.get("PATH", ""),
-                },
-                clear=True,
-            ),
-            patch("devx.molecule.molecule_ci_guard.POLL_INTERVAL", 0.01),
-            patch("devx.molecule.molecule_ci_guard.subprocess.Popen") as mock_popen,
-            patch("devx.molecule.molecule_ci_guard.get_running_jobs", side_effect=get_jobs_side_effect),
-            patch("os.killpg") as mock_killpg,
-            patch("os.getpgid") as mock_getpgid,
-            patch("time.sleep", side_effect=lambda x: real_sleep(0)),
-        ):
-            mock_getpgid.return_value = 123
-            proc = MagicMock()
-            proc.poll.return_value = None
-            proc.wait.return_value = 0
-            mock_popen.return_value = proc
-
-            runner = CliRunner()
-            result = runner.invoke(cli, ["default|ubuntu-2204|img:latest|"])
-            assert result.exit_code == 1
-            mock_killpg.assert_called()
-
-    def test_default_owner_repo_fallback(self) -> None:
-        from click.testing import CliRunner
-
-        real_sleep = time.sleep
-
-        with (
-            patch.dict(
-                os.environ,
-                {
-                    "GITEA_URL": "https://gitea.example",
-                    "CI_GITEA_TOKEN": "token",
-                    "RUN_ID": "123",
-                    "JOB_NAME": "molecule-tests",
-                    "MATRIX_INDEX": "0",
-                    "GITEA_REPOSITORY": "invalid",
-                    "PATH": os.environ.get("PATH", ""),
-                },
-                clear=True,
-            ),
-            patch("devx.molecule.molecule_ci_guard.POLL_INTERVAL", 0.01),
-            patch("devx.molecule.molecule_ci_guard.subprocess.Popen") as mock_popen,
-            patch("devx.molecule.molecule_ci_guard.subprocess.run") as mock_run,
-            patch("devx.molecule.molecule_ci_guard.get_running_jobs") as mock_get_jobs,
-            patch("time.sleep", side_effect=lambda x: real_sleep(0)),
-        ):
-            mock_get_jobs.return_value = [{"name": "molecule-tests (1)", "conclusion": "success"}]
-            proc = MagicMock()
-            proc.poll.return_value = 0
-            proc.returncode = 0
-            mock_popen.return_value = proc
-            mock_run.return_value = MagicMock(returncode=0)
-
-            runner = CliRunner()
-            result = runner.invoke(cli, ["default|ubuntu-2204|img:latest|"])
-            assert result.exit_code == 0
-
-    def test_exits_when_other_runner_fails_with_process_lookup_error(self) -> None:
-        from click.testing import CliRunner
-
-        real_sleep = time.sleep
-        call_count = [0]
-
-        def get_jobs_side_effect(*args, **kwargs):
-            call_count[0] += 1
-            if call_count[0] < 2:
-                return [{"name": "molecule-tests (1)", "conclusion": "running"}]
-            return [
-                {"name": "molecule-tests (0)", "conclusion": "running"},
-                {"name": "molecule-tests (1)", "conclusion": "failure"},
-            ]
-
-        with (
-            patch.dict(
-                os.environ,
-                {
-                    "GITEA_URL": "https://gitea.example",
-                    "CI_GITEA_TOKEN": "token",
-                    "RUN_ID": "123",
-                    "JOB_NAME": "molecule-tests",
-                    "MATRIX_INDEX": "0",
-                    "GITEA_REPOSITORY": "my-org/my-repo",
-                    "PATH": os.environ.get("PATH", ""),
-                },
-                clear=True,
-            ),
-            patch("devx.molecule.molecule_ci_guard.POLL_INTERVAL", 0.01),
-            patch("devx.molecule.molecule_ci_guard.subprocess.Popen") as mock_popen,
-            patch("devx.molecule.molecule_ci_guard.get_running_jobs", side_effect=get_jobs_side_effect),
-            patch("os.killpg") as mock_killpg,
-            patch("os.getpgid") as mock_getpgid,
-            patch("time.sleep", side_effect=lambda x: real_sleep(0)),
-        ):
-            mock_getpgid.return_value = 123
-            mock_killpg.side_effect = ProcessLookupError("no such process")
-            proc = MagicMock()
-            proc.poll.return_value = None
-            proc.wait.return_value = 0
-            mock_popen.return_value = proc
-
-            runner = CliRunner()
-            result = runner.invoke(cli, ["default|ubuntu-2204|img:latest|"])
-            assert result.exit_code == 1
-
-    def test_exits_when_other_runner_fails_with_timeout(self) -> None:
-        from click.testing import CliRunner
-
-        real_sleep = time.sleep
-        call_count = [0]
-
-        def get_jobs_side_effect(*args, **kwargs):
-            call_count[0] += 1
-            if call_count[0] < 2:
-                return [{"name": "molecule-tests (1)", "conclusion": "running"}]
-            return [
-                {"name": "molecule-tests (0)", "conclusion": "running"},
-                {"name": "molecule-tests (1)", "conclusion": "failure"},
-            ]
-
-        with (
-            patch.dict(
-                os.environ,
-                {
-                    "GITEA_URL": "https://gitea.example",
-                    "CI_GITEA_TOKEN": "token",
-                    "RUN_ID": "123",
-                    "JOB_NAME": "molecule-tests",
-                    "MATRIX_INDEX": "0",
-                    "GITEA_REPOSITORY": "my-org/my-repo",
-                    "PATH": os.environ.get("PATH", ""),
-                },
-                clear=True,
-            ),
-            patch("devx.molecule.molecule_ci_guard.POLL_INTERVAL", 0.01),
-            patch("devx.molecule.molecule_ci_guard.subprocess.Popen") as mock_popen,
-            patch("devx.molecule.molecule_ci_guard.get_running_jobs", side_effect=get_jobs_side_effect),
-            patch("os.killpg") as mock_killpg,
-            patch("os.getpgid") as mock_getpgid,
-            patch("time.sleep", side_effect=lambda x: real_sleep(0)),
-        ):
-            mock_getpgid.return_value = 123
-            mock_killpg.side_effect = [None, ProcessLookupError("no such process")]
-            proc = MagicMock()
-            proc.poll.return_value = None
-            proc.wait.side_effect = [subprocess.TimeoutExpired("cmd", 10)]
-            mock_popen.return_value = proc
-
-            runner = CliRunner()
-            result = runner.invoke(cli, ["default|ubuntu-2204|img:latest|"])
-            assert result.exit_code == 1
-
-
-def test_main_module_block() -> None:
-    import devx.molecule.molecule_ci_guard as mg
-
-    with open(mg.__file__) as f:
-        source = f.read()
-    source = source.replace('if __name__ == "__main__":\n    cli()\n', "")
-    namespace = dict(mg.__dict__)
-    exec(compile(source, mg.__file__, "exec"), namespace)
-    assert callable(namespace["cli"])
-
-
-class TestParsePair:
-    def test_single_role_4_part(self) -> None:
-        role, scenario, name, image, cmd = parse_pair("default|ubuntu-2204|ubuntu:22.04|")
-        assert role == ""
-        assert scenario == "default"
-        assert name == "ubuntu-2204"
-        assert image == "ubuntu:22.04"
-        assert cmd == ""
-
-    def test_multi_role_5_part(self) -> None:
-        role, scenario, name, image, cmd = parse_pair("gitea-runner|default|ubuntu-2204|ubuntu:22.04|")
-        assert role == "gitea-runner"
-        assert scenario == "default"
-        assert name == "ubuntu-2204"
-        assert image == "ubuntu:22.04"
-        assert cmd == ""
-
-    def test_multi_role_with_command(self) -> None:
-        role, scenario, name, image, cmd = parse_pair(
-            "docker-base|lifecycle|archlinux|archlinux:latest|/usr/lib/systemd/systemd"
-        )
-        assert role == "docker-base"
-        assert scenario == "lifecycle"
-        assert cmd == "/usr/lib/systemd/systemd"
-
-    def test_invalid_pair_raises(self) -> None:
-        with pytest.raises(click.ClickException, match="Invalid pair format"):
-            parse_pair("only|two|parts")
-
-    def test_too_many_parts_raises(self) -> None:
-        with pytest.raises(click.ClickException, match="Invalid pair format"):
-            parse_pair("a|b|c|d|e|f")
-
-
-class TestResolveRoleDir:
-    def test_multi_role_with_roles_root(self, tmp_path: Path) -> None:
-        roles_root = tmp_path / "ansible" / "roles"
-        roles_root.mkdir(parents=True)
-        result = resolve_role_dir("gitea-runner", roles_root, tmp_path)
-        assert result == roles_root / "gitea-runner"
-
-    def test_multi_role_default_roles_root(self, tmp_path: Path) -> None:
-        result = resolve_role_dir("docker-base", None, tmp_path)
-        assert result == tmp_path / "ansible" / "roles" / "docker-base"
-
-    def test_single_role_auto_discovers(self, tmp_path: Path) -> None:
-        """Single-role mode auto-discovers first role with molecule/ dir."""
-        roles_dir = tmp_path / "ansible" / "roles"
-        (roles_dir / "my_role" / "molecule").mkdir(parents=True)
-        result = resolve_role_dir("", None, tmp_path)
-        assert result == roles_dir / "my_role"
-
-    def test_single_role_no_roles_returns_fallback(self, tmp_path: Path) -> None:
-        """When no roles exist, returns a fallback path (will error at runtime)."""
-        result = resolve_role_dir("", None, tmp_path)
-        assert "roles" in str(result)
-
-
-class TestCliMultiRole:
-    def test_multi_role_pair_passes(self, tmp_path: Path) -> None:
-        from click.testing import CliRunner
-
-        roles_root = tmp_path / "ansible" / "roles"
-        (roles_root / "gitea-runner").mkdir(parents=True)
-
-        with (
-            patch("devx.molecule.molecule_ci_guard.subprocess.Popen") as mock_popen,
-            patch("devx.molecule.molecule_ci_guard.subprocess.run") as mock_run,
-            patch("time.sleep"),
-        ):
-            proc = MagicMock()
-            proc.poll.return_value = 0
-            proc.returncode = 0
-            mock_popen.return_value = proc
-            mock_run.return_value = MagicMock(returncode=0)
-
-            runner = CliRunner()
-            result = runner.invoke(
-                cli,
-                ["--roles-root", str(roles_root), "gitea-runner|default|ubuntu-2204|ubuntu:22.04|"],
-            )
-            assert result.exit_code == 0
-            assert "All molecule tests passed" in result.output

tests/unit/test_notify_failure.py

@@ -9,9 +9,10 @@ from devx.gitea_cli import TeaCLIError, configure_tea_login
 
 
 class TestNotifyFailure:
+    @patch("devx.gitea_cli.configure_tea_login")
     @patch.dict("os.environ", {"CI_GITEA_TOKEN": "tok"})
     @patch("devx.ci.notify_failure.TeaCLI")
-    def test_creates_issue_with_tea(self, mock_tea_cls: MagicMock) -> None:
+    def test_creates_issue_with_tea(self, mock_tea_cls: MagicMock, mock_login: MagicMock) -> None:
         mock_tea = MagicMock()
         mock_tea.list_labels.return_value = [{"id": 5, "name": "bug"}]
         mock_tea.create_issue.return_value = {"index": 42, "title": "test"}
@@ -36,9 +37,10 @@ class TestNotifyFailure:
         mock_tea.create_issue.assert_called_once()
         mock_tea.add_label.assert_called_once_with("owner/repo", 42, ["bug"])
 
+    @patch("devx.gitea_cli.configure_tea_login")
     @patch.dict("os.environ", {"CI_GITEA_TOKEN": "tok"})
     @patch("devx.ci.notify_failure.TeaCLI")
-    def test_tea_creates_issue_without_bug_label(self, mock_tea_cls: MagicMock) -> None:
+    def test_tea_creates_issue_without_bug_label(self, mock_tea_cls: MagicMock, mock_login: MagicMock) -> None:
         mock_tea = MagicMock()
         mock_tea.list_labels.return_value = [{"id": 1, "name": "enhancement"}]
         mock_tea.create_issue.return_value = {"index": 43, "title": "test"}
@@ -53,9 +55,10 @@ class TestNotifyFailure:
         assert "issue #43" in result.output
         mock_tea.add_label.assert_not_called()
 
+    @patch("devx.gitea_cli.configure_tea_login")
     @patch.dict("os.environ", {"CI_GITEA_TOKEN": "tok"})
     @patch("devx.ci.notify_failure.TeaCLI")
-    def test_tea_error_raises(self, mock_tea_cls: MagicMock) -> None:
+    def test_tea_error_raises(self, mock_tea_cls: MagicMock, mock_login: MagicMock) -> None:
         """When tea fails, the workflow fails — no fallback."""
         mock_tea = MagicMock()
         mock_tea.list_labels.side_effect = TeaCLIError("network error")
@@ -70,9 +73,12 @@ class TestNotifyFailure:
         assert result.exit_code != 0
         assert "tea" in result.output.lower()
 
+    @patch("devx.gitea_cli.configure_tea_login")
     @patch.dict("os.environ", {"CI_GITEA_TOKEN": "tok"})
     @patch("devx.ci.notify_failure.TeaCLI")
-    def test_tea_list_labels_error_continues_without_labels(self, mock_tea_cls: MagicMock) -> None:
+    def test_tea_list_labels_error_continues_without_labels(
+        self, mock_tea_cls: MagicMock, mock_login: MagicMock
+    ) -> None:
         """If listing labels fails via tea, issue is still created without labels."""
         mock_tea = MagicMock()
         mock_tea.list_labels.side_effect = TeaCLIError("network error")
@@ -87,9 +93,10 @@ class TestNotifyFailure:
         assert result.exit_code == 0
         assert "issue #50" in result.output
 
+    @patch("devx.gitea_cli.configure_tea_login")
     @patch.dict("os.environ", {"CI_GITEA_TOKEN": "tok"})
     @patch("devx.ci.notify_failure.TeaCLI")
-    def test_tea_add_label_error_is_ignored(self, mock_tea_cls: MagicMock) -> None:
+    def test_tea_add_label_error_is_ignored(self, mock_tea_cls: MagicMock, mock_login: MagicMock) -> None:
         """If adding label fails via tea, issue is still reported as created."""
         mock_tea = MagicMock()
         mock_tea.list_labels.return_value = [{"id": 5, "name": "bug"}]
@@ -105,8 +112,9 @@ class TestNotifyFailure:
         assert result.exit_code == 0
         assert "issue #51" in result.output
 
+    @patch("devx.gitea_cli.configure_tea_login")
     @patch.dict("os.environ", {"CI_GITEA_TOKEN": ""}, clear=True)
-    def test_missing_token_exits(self) -> None:
+    def test_missing_token_exits(self, mock_login: MagicMock) -> None:
         runner = CliRunner()
         result = runner.invoke(
             main,
@@ -115,10 +123,13 @@ class TestNotifyFailure:
         assert result.exit_code != 0
         assert "CI_GITEA_TOKEN" in result.output
 
+    @patch("devx.gitea_cli.configure_tea_login")
     @patch.dict("os.environ", {"CI_GITEA_TOKEN": "tok"})
     @patch("devx.gitea_cli.shutil.which", return_value=None)
     @patch("devx.ci.notify_failure.TeaCLI")
-    def test_auto_login_no_tea_skips(self, mock_tea_cls: MagicMock, mock_which: MagicMock) -> None:
+    def test_auto_login_no_tea_skips(
+        self, mock_tea_cls: MagicMock, mock_which: MagicMock, mock_login: MagicMock
+    ) -> None:
         """--auto-login with tea not installed skips login and still creates issue."""
         mock_tea = MagicMock()
         mock_tea.list_labels.return_value = []
@@ -133,10 +144,13 @@ class TestNotifyFailure:
         assert result.exit_code == 0
         assert "issue #60" in result.output
 
+    @patch("devx.gitea_cli.configure_tea_login")
     @patch.dict("os.environ", {"CI_GITEA_TOKEN": ""}, clear=True)
     @patch("devx.gitea_cli.shutil.which", return_value="/usr/bin/tea")
     @patch("devx.ci.notify_failure.TeaCLI")
-    def test_auto_login_no_token_skips_login(self, mock_tea_cls: MagicMock, mock_which: MagicMock) -> None:
+    def test_auto_login_no_token_skips_login(
+        self, mock_tea_cls: MagicMock, mock_which: MagicMock, mock_login: MagicMock
+    ) -> None:
         """--auto-login with no CI_GITEA_TOKEN skips login but raises before creating issue."""
         mock_tea = MagicMock()
         mock_tea_cls.return_value = mock_tea

tests/unit/test_post_merge.py

@@ -91,9 +91,14 @@ class TestResolveTaskId:
 
 
 class TestMain:
+    @patch("devx.ci.post_merge.subprocess.run")
+    @patch("devx.ci.post_merge._get_git_commit_message", return_value="msg")
+    @patch("devx.ci.post_merge._get_git_commit_sha", return_value="sha")
     @patch.dict("os.environ", {"VIKUNJA_TOKEN": "tok"})
     @patch("devx.ci.post_merge.VikunjaClient")
-    def test_full_flow(self, mock_client_cls: MagicMock) -> None:
+    def test_full_flow(
+        self, mock_client_cls: MagicMock, mock_msg: MagicMock, mock_sha: MagicMock, mock_subproc: MagicMock
+    ) -> None:
         mock_client = MagicMock()
         mock_client.list_project_tasks.return_value = [
             {"id": 267, "identifier": "DEVX-20"},
@@ -109,9 +114,14 @@ class TestMain:
         mock_client.post_comment.assert_called_once()
         mock_client.update_task.assert_called_once_with(267, done=True)
 
+    @patch("devx.ci.post_merge.subprocess.run")
+    @patch("devx.ci.post_merge._get_git_commit_message", return_value="msg")
+    @patch("devx.ci.post_merge._get_git_commit_sha", return_value="sha")
     @patch.dict("os.environ", {"VIKUNJA_TOKEN": "tok"})
     @patch("devx.ci.post_merge.VikunjaClient")
-    def test_no_commit_sha(self, mock_client_cls: MagicMock) -> None:
+    def test_no_commit_sha(
+        self, mock_client_cls: MagicMock, mock_msg: MagicMock, mock_sha: MagicMock, mock_subproc: MagicMock
+    ) -> None:
         mock_client = MagicMock()
         mock_client.list_project_tasks.return_value = [
             {"id": 267, "identifier": "DEVX-20"},
@@ -124,31 +134,47 @@ class TestMain:
         args, _ = mock_client.post_comment.call_args
         assert "unknown" in args[1]
 
+    @patch("devx.ci.post_merge.subprocess.run")
+    @patch("devx.ci.post_merge._get_git_commit_message", return_value="msg")
+    @patch("devx.ci.post_merge._get_git_commit_sha", return_value="sha")
     @patch.dict("os.environ", {"VIKUNJA_TOKEN": ""}, clear=True)
-    def test_missing_token_exits(self) -> None:
+    def test_missing_token_exits(self, mock_msg: MagicMock, mock_sha: MagicMock, mock_subproc: MagicMock) -> None:
         runner = CliRunner()
         result = runner.invoke(main, ["DEVX-20: fix: bug"])
         assert result.exit_code == 1
         assert "VIKUNJA_TOKEN" in result.output
 
+    @patch("devx.ci.post_merge.subprocess.run")
+    @patch("devx.ci.post_merge._get_git_commit_message", return_value="msg")
+    @patch("devx.ci.post_merge._get_git_commit_sha", return_value="sha")
     @patch.dict("os.environ", {"VIKUNJA_TOKEN": "tok"})
-    def test_no_task_id_non_release_fails(self) -> None:
+    def test_no_task_id_non_release_fails(
+        self, mock_msg: MagicMock, mock_sha: MagicMock, mock_subproc: MagicMock
+    ) -> None:
         """Non-release commits without DEVX-N prefix should fail."""
         runner = CliRunner()
         result = runner.invoke(main, ["fix: resolve bug"])
         assert result.exit_code != 0
         assert "No task ID" in result.output
 
+    @patch("devx.ci.post_merge.subprocess.run")
+    @patch("devx.ci.post_merge._get_git_commit_message", return_value="msg")
+    @patch("devx.ci.post_merge._get_git_commit_sha", return_value="sha")
     @patch.dict("os.environ", {"VIKUNJA_TOKEN": "tok"})
-    def test_release_commit_without_task_id_skips(self) -> None:
+    def test_release_commit_without_task_id_skips(
+        self, mock_msg: MagicMock, mock_sha: MagicMock, mock_subproc: MagicMock
+    ) -> None:
         """Release commits without DEVX-N prefix should skip gracefully."""
         runner = CliRunner()
         result = runner.invoke(main, ["release: v0.3.2"])
         assert result.exit_code == 0
         assert "skipping" in result.output
 
+    @patch("devx.ci.post_merge.subprocess.run")
+    @patch("devx.ci.post_merge._get_git_commit_message", return_value="msg")
+    @patch("devx.ci.post_merge._get_git_commit_sha", return_value="sha")
     @patch.dict("os.environ", {"VIKUNJA_TOKEN": "tok"})
-    def test_revert_commit_skips(self) -> None:
+    def test_revert_commit_skips(self, mock_msg: MagicMock, mock_sha: MagicMock, mock_subproc: MagicMock) -> None:
         """Revert commits without DEVX-N prefix should skip gracefully."""
         runner = CliRunner()
         result = runner.invoke(main, ["revert: remove v0.6.0 release"])
@@ -156,17 +182,25 @@ class TestMain:
         assert "Infrastructure commit" in result.output
         assert "skipping" in result.output
 
+    @patch("devx.ci.post_merge.subprocess.run")
+    @patch("devx.ci.post_merge._get_git_commit_message", return_value="msg")
+    @patch("devx.ci.post_merge._get_git_commit_sha", return_value="sha")
     @patch.dict("os.environ", {"VIKUNJA_TOKEN": "tok"})
-    def test_merge_commit_skips(self) -> None:
+    def test_merge_commit_skips(self, mock_msg: MagicMock, mock_sha: MagicMock, mock_subproc: MagicMock) -> None:
         """Merge commits without DEVX-N prefix should skip gracefully."""
         runner = CliRunner()
         result = runner.invoke(main, ["Merge pull request #42"])
         assert result.exit_code == 0
         assert "Infrastructure commit" in result.output
 
+    @patch("devx.ci.post_merge.subprocess.run")
+    @patch("devx.ci.post_merge._get_git_commit_message", return_value="msg")
+    @patch("devx.ci.post_merge._get_git_commit_sha", return_value="sha")
     @patch.dict("os.environ", {"VIKUNJA_TOKEN": "tok"})
     @patch("devx.ci.post_merge.VikunjaClient")
-    def test_resolve_failure_fails(self, mock_client_cls: MagicMock) -> None:
+    def test_resolve_failure_fails(
+        self, mock_client_cls: MagicMock, mock_msg: MagicMock, mock_sha: MagicMock, mock_subproc: MagicMock
+    ) -> None:
         """Missing Vikunja task is a fatal error — every PR must have a task."""
         mock_client = MagicMock()
         mock_client.list_project_tasks.return_value = []
@@ -176,9 +210,14 @@ class TestMain:
         assert result.exit_code != 0
         assert "Could not find" in result.output
 
+    @patch("devx.ci.post_merge.subprocess.run")
+    @patch("devx.ci.post_merge._get_git_commit_message", return_value="msg")
+    @patch("devx.ci.post_merge._get_git_commit_sha", return_value="sha")
     @patch.dict("os.environ", {"VIKUNJA_TOKEN": "tok"})
     @patch("devx.ci.post_merge.VikunjaClient")
-    def test_post_comment_failure_fails(self, mock_client_cls: MagicMock) -> None:
+    def test_post_comment_failure_fails(
+        self, mock_client_cls: MagicMock, mock_msg: MagicMock, mock_sha: MagicMock, mock_subproc: MagicMock
+    ) -> None:
         """Vikunja API errors should fail — the task was not updated."""
         mock_client = MagicMock()
         mock_client.list_project_tasks.return_value = [
@@ -191,9 +230,14 @@ class TestMain:
         assert result.exit_code != 0
         assert "Vikunja API error" in result.output
 
+    @patch("devx.ci.post_merge.subprocess.run")
+    @patch("devx.ci.post_merge._get_git_commit_message", return_value="msg")
+    @patch("devx.ci.post_merge._get_git_commit_sha", return_value="sha")
     @patch.dict("os.environ", {"VIKUNJA_TOKEN": "tok"})
     @patch("devx.ci.post_merge.VikunjaClient")
-    def test_mark_done_failure_fails(self, mock_client_cls: MagicMock) -> None:
+    def test_mark_done_failure_fails(
+        self, mock_client_cls: MagicMock, mock_msg: MagicMock, mock_sha: MagicMock, mock_subproc: MagicMock
+    ) -> None:
         """Vikunja API errors should fail — the task was not updated."""
         mock_client = MagicMock()
         mock_client.list_project_tasks.return_value = [
@@ -235,11 +279,14 @@ class TestGetGitCommitSha:
 
 
 class TestFromGit:
+    @patch("devx.ci.post_merge.subprocess.run")
     @patch.dict("os.environ", {"VIKUNJA_TOKEN": "tok"})
     @patch("devx.ci.post_merge.VikunjaClient")
     @patch("devx.ci.post_merge._get_git_commit_sha", return_value="abc123")
     @patch("devx.ci.post_merge._get_git_commit_message", return_value="DEVX-20: fix: bug")
-    def test_from_git(self, mock_msg: MagicMock, mock_sha: MagicMock, mock_client_cls: MagicMock) -> None:
+    def test_from_git(
+        self, mock_msg: MagicMock, mock_sha: MagicMock, mock_client_cls: MagicMock, mock_subproc: MagicMock
+    ) -> None:
         mock_client = MagicMock()
         mock_client.list_project_tasks.return_value = [
             {"id": 267, "identifier": "DEVX-20"},
@@ -250,12 +297,13 @@ class TestFromGit:
         assert result.exit_code == 0
         assert "updated and marked done" in result.output
 
+    @patch("devx.ci.post_merge.subprocess.run")
     @patch.dict("os.environ", {"VIKUNJA_TOKEN": "tok"})
     @patch("devx.ci.post_merge.VikunjaClient")
     @patch("devx.ci.post_merge._get_git_commit_sha", return_value="abc123")
     @patch("devx.ci.post_merge._get_git_commit_message", return_value="DEVX-20: fix: bug")
     def test_from_git_with_explicit_sha(
-        self, mock_msg: MagicMock, mock_sha: MagicMock, mock_client_cls: MagicMock
+        self, mock_msg: MagicMock, mock_sha: MagicMock, mock_client_cls: MagicMock, mock_subproc: MagicMock
     ) -> None:
         mock_client = MagicMock()
         mock_client.list_project_tasks.return_value = [
@@ -266,8 +314,11 @@ class TestFromGit:
         result = runner.invoke(main, ["--from-git", "--commit-sha", "explicit_sha"])
         assert result.exit_code == 0
 
+    @patch("devx.ci.post_merge.subprocess.run")
+    @patch("devx.ci.post_merge._get_git_commit_message", return_value="msg")
+    @patch("devx.ci.post_merge._get_git_commit_sha", return_value="sha")
     @patch.dict("os.environ", {"VIKUNJA_TOKEN": "tok"})
-    def test_no_msg_and_no_from_git(self) -> None:
+    def test_no_msg_and_no_from_git(self, mock_msg: MagicMock, mock_sha: MagicMock, mock_subproc: MagicMock) -> None:
         runner = CliRunner()
         result = runner.invoke(main, [])
         assert result.exit_code != 0

tests/unit/test_pr_label.py

@@ -11,7 +11,8 @@ from devx.tools.pr_label import cli
 
 
 class TestCli:
-    def test_no_token_raises(self, monkeypatch: pytest.MonkeyPatch) -> None:
+    @patch("devx.tools.pr_status.subprocess.run")
+    def test_no_token_raises(self, mock_subproc: MagicMock, monkeypatch: pytest.MonkeyPatch) -> None:
         for name in ("DEVELOPER_GITEA_API_TOKEN", "CI_GITEA_API_TOKEN", "CI_GITEA_TOKEN"):
             monkeypatch.delenv(name, raising=False)
         runner = CliRunner()
@@ -23,16 +24,20 @@ class TestCli:
         assert result.exit_code != 0
         assert "CI_GITEA_TOKEN" in result.output
 
+    @patch("devx.tools.pr_status.subprocess.run")
     @patch("devx.tools.pr_label.REPO_OWNER", "")
-    def test_no_owner_raises(self, monkeypatch: pytest.MonkeyPatch) -> None:
+    def test_no_owner_raises(self, mock_subproc: MagicMock, monkeypatch: pytest.MonkeyPatch) -> None:
         monkeypatch.setenv("CI_GITEA_TOKEN", "tok")
         runner = CliRunner()
         result = runner.invoke(cli, ["--pr", "42", "--label", "ready-to-merge"])
         assert result.exit_code != 0
         assert "owner" in result.output.lower()
 
+    @patch("devx.tools.pr_status.subprocess.run")
     @patch("devx.tools.pr_label.GiteaClient")
-    def test_adds_new_label(self, mock_client_cls: MagicMock, monkeypatch: pytest.MonkeyPatch) -> None:
+    def test_adds_new_label(
+        self, mock_client_cls: MagicMock, mock_subproc: MagicMock, monkeypatch: pytest.MonkeyPatch
+    ) -> None:
         monkeypatch.setenv("CI_GITEA_TOKEN", "tok")
         monkeypatch.setenv("DEVX_REPO_OWNER", "owner")
         monkeypatch.setenv("DEVX_REPO_NAME", "repo")
@@ -44,8 +49,11 @@ class TestCli:
         client.add_pr_label.assert_called_once_with(42, ["ready-to-merge"])
         assert "Added label" in result.output
 
+    @patch("devx.tools.pr_status.subprocess.run")
     @patch("devx.tools.pr_label.GiteaClient")
-    def test_skips_existing_label(self, mock_client_cls: MagicMock, monkeypatch: pytest.MonkeyPatch) -> None:
+    def test_skips_existing_label(
+        self, mock_client_cls: MagicMock, mock_subproc: MagicMock, monkeypatch: pytest.MonkeyPatch
+    ) -> None:
         monkeypatch.setenv("CI_GITEA_TOKEN", "tok")
         monkeypatch.setenv("DEVX_REPO_OWNER", "owner")
         monkeypatch.setenv("DEVX_REPO_NAME", "repo")
@@ -57,8 +65,11 @@ class TestCli:
         client.add_pr_label.assert_not_called()
         assert "already" in result.output
 
+    @patch("devx.tools.pr_status.subprocess.run")
     @patch("devx.tools.pr_label.GiteaClient")
-    def test_mixed_new_and_existing(self, mock_client_cls: MagicMock, monkeypatch: pytest.MonkeyPatch) -> None:
+    def test_mixed_new_and_existing(
+        self, mock_client_cls: MagicMock, mock_subproc: MagicMock, monkeypatch: pytest.MonkeyPatch
+    ) -> None:
         monkeypatch.setenv("CI_GITEA_TOKEN", "tok")
         monkeypatch.setenv("DEVX_REPO_OWNER", "owner")
         monkeypatch.setenv("DEVX_REPO_NAME", "repo")

tests/unit/test_pr_logs.py

@@ -152,7 +152,8 @@ class TestPrintLogs:
 
 
 class TestCli:
-    def test_no_token_raises(self, monkeypatch: pytest.MonkeyPatch) -> None:
+    @patch("devx.tools.pr_status.subprocess.run")
+    def test_no_token_raises(self, mock_subproc: MagicMock, monkeypatch: pytest.MonkeyPatch) -> None:
         for name in ("DEVELOPER_GITEA_API_TOKEN", "CI_GITEA_API_TOKEN", "CI_GITEA_TOKEN"):
             monkeypatch.delenv(name, raising=False)
         runner = CliRunner()
@@ -164,8 +165,9 @@ class TestCli:
         assert result.exit_code != 0
         assert "CI_GITEA_TOKEN" in result.output
 
+    @patch("devx.tools.pr_status.subprocess.run")
     @patch("devx.tools.pr_logs.REPO_OWNER", "")
-    def test_no_owner_raises(self, monkeypatch: pytest.MonkeyPatch) -> None:
+    def test_no_owner_raises(self, mock_subproc: MagicMock, monkeypatch: pytest.MonkeyPatch) -> None:
         monkeypatch.setenv("CI_GITEA_TOKEN", "tok")
         runner = CliRunner()
         result = runner.invoke(cli, ["--pr", "42"])
@@ -190,8 +192,11 @@ class TestCli:
         assert result.exit_code != 0
         assert "Fetching logs for PR #42" in result.output
 
+    @patch("devx.tools.pr_status.subprocess.run")
     @patch("devx.tools.pr_logs.GiteaClient")
-    def test_no_runs_found(self, mock_client_cls: MagicMock, monkeypatch: pytest.MonkeyPatch) -> None:
+    def test_no_runs_found(
+        self, mock_client_cls: MagicMock, mock_subproc: MagicMock, monkeypatch: pytest.MonkeyPatch
+    ) -> None:
         monkeypatch.setenv("CI_GITEA_TOKEN", "tok")
         monkeypatch.setenv("DEVX_REPO_OWNER", "owner")
         monkeypatch.setenv("DEVX_REPO_NAME", "repo")
@@ -203,8 +208,11 @@ class TestCli:
         assert result.exit_code != 0
         assert "No workflow runs" in result.output
 
+    @patch("devx.tools.pr_status.subprocess.run")
     @patch("devx.tools.pr_logs.GiteaClient")
-    def test_no_jobs(self, mock_client_cls: MagicMock, monkeypatch: pytest.MonkeyPatch) -> None:
+    def test_no_jobs(
+        self, mock_client_cls: MagicMock, mock_subproc: MagicMock, monkeypatch: pytest.MonkeyPatch
+    ) -> None:
         monkeypatch.setenv("CI_GITEA_TOKEN", "tok")
         monkeypatch.setenv("DEVX_REPO_OWNER", "owner")
         monkeypatch.setenv("DEVX_REPO_NAME", "repo")
@@ -219,8 +227,11 @@ class TestCli:
         assert result.exit_code == 0
         assert "No jobs" in result.output
 
+    @patch("devx.tools.pr_status.subprocess.run")
     @patch("devx.tools.pr_logs.GiteaClient")
-    def test_no_failed_jobs(self, mock_client_cls: MagicMock, monkeypatch: pytest.MonkeyPatch) -> None:
+    def test_no_failed_jobs(
+        self, mock_client_cls: MagicMock, mock_subproc: MagicMock, monkeypatch: pytest.MonkeyPatch
+    ) -> None:
         monkeypatch.setenv("CI_GITEA_TOKEN", "tok")
         monkeypatch.setenv("DEVX_REPO_OWNER", "owner")
         monkeypatch.setenv("DEVX_REPO_NAME", "repo")
@@ -237,8 +248,11 @@ class TestCli:
         assert result.exit_code == 0
         assert "No failed jobs" in result.output
 
+    @patch("devx.tools.pr_status.subprocess.run")
     @patch("devx.tools.pr_logs.GiteaClient")
-    def test_failed_job_logs(self, mock_client_cls: MagicMock, monkeypatch: pytest.MonkeyPatch) -> None:
+    def test_failed_job_logs(
+        self, mock_client_cls: MagicMock, mock_subproc: MagicMock, monkeypatch: pytest.MonkeyPatch
+    ) -> None:
         monkeypatch.setenv("CI_GITEA_TOKEN", "tok")
         monkeypatch.setenv("DEVX_REPO_OWNER", "owner")
         monkeypatch.setenv("DEVX_REPO_NAME", "repo")
@@ -266,8 +280,11 @@ class TestCli:
         assert "FAILED step #3" in result.output
         assert "error: test failed" in result.output
 
+    @patch("devx.tools.pr_status.subprocess.run")
     @patch("devx.tools.pr_logs.GiteaClient")
-    def test_specific_job(self, mock_client_cls: MagicMock, monkeypatch: pytest.MonkeyPatch) -> None:
+    def test_specific_job(
+        self, mock_client_cls: MagicMock, mock_subproc: MagicMock, monkeypatch: pytest.MonkeyPatch
+    ) -> None:
         monkeypatch.setenv("CI_GITEA_TOKEN", "tok")
         monkeypatch.setenv("DEVX_REPO_OWNER", "owner")
         monkeypatch.setenv("DEVX_REPO_NAME", "repo")
@@ -286,8 +303,11 @@ class TestCli:
         assert result.exit_code == 0
         assert "lint output here" in result.output
 
+    @patch("devx.tools.pr_status.subprocess.run")
     @patch("devx.tools.pr_logs.GiteaClient")
-    def test_job_not_found(self, mock_client_cls: MagicMock, monkeypatch: pytest.MonkeyPatch) -> None:
+    def test_job_not_found(
+        self, mock_client_cls: MagicMock, mock_subproc: MagicMock, monkeypatch: pytest.MonkeyPatch
+    ) -> None:
         monkeypatch.setenv("CI_GITEA_TOKEN", "tok")
         monkeypatch.setenv("DEVX_REPO_OWNER", "owner")
         monkeypatch.setenv("DEVX_REPO_NAME", "repo")
@@ -304,8 +324,11 @@ class TestCli:
         assert result.exit_code != 0
         assert "No job matching" in result.output
 
+    @patch("devx.tools.pr_status.subprocess.run")
     @patch("devx.tools.pr_logs.GiteaClient")
-    def test_no_sha_raises(self, mock_client_cls: MagicMock, monkeypatch: pytest.MonkeyPatch) -> None:
+    def test_no_sha_raises(
+        self, mock_client_cls: MagicMock, mock_subproc: MagicMock, monkeypatch: pytest.MonkeyPatch
+    ) -> None:
         monkeypatch.setenv("CI_GITEA_TOKEN", "tok")
         monkeypatch.setenv("DEVX_REPO_OWNER", "owner")
         monkeypatch.setenv("DEVX_REPO_NAME", "repo")

tests/unit/test_pr_status.py

@@ -121,7 +121,8 @@ class TestWaitForCompletion:
 
 
 class TestCli:
-    def test_no_token_raises(self, monkeypatch: pytest.MonkeyPatch) -> None:
+    @patch("devx.tools.pr_status.subprocess.run")
+    def test_no_token_raises(self, mock_subproc: MagicMock, monkeypatch: pytest.MonkeyPatch) -> None:
         for name in ("DEVELOPER_GITEA_API_TOKEN", "CI_GITEA_API_TOKEN", "CI_GITEA_TOKEN"):
             monkeypatch.delenv(name, raising=False)
         runner = CliRunner()
@@ -133,17 +134,23 @@ class TestCli:
         assert result.exit_code != 0
         assert "CI_GITEA_TOKEN" in result.output
 
+    @patch("devx.tools.pr_status.subprocess.run")
     @patch("devx.tools.pr_status.REPO_OWNER", "")
     @patch("devx.tools.pr_status.get_repo_name", side_effect=Exception("should not reach"))
-    def test_no_owner_raises(self, mock_repo_name: MagicMock, monkeypatch: pytest.MonkeyPatch) -> None:
+    def test_no_owner_raises(
+        self, mock_repo_name: MagicMock, mock_subproc: MagicMock, monkeypatch: pytest.MonkeyPatch
+    ) -> None:
         monkeypatch.setenv("CI_GITEA_TOKEN", "tok")
         runner = CliRunner()
         result = runner.invoke(cli, ["--pr", "42"])
         assert result.exit_code != 0
         assert "owner" in result.output.lower()
 
+    @patch("devx.tools.pr_status.subprocess.run")
     @patch("devx.tools.pr_status.GiteaClient")
-    def test_check_pr_status(self, mock_client_cls: MagicMock, monkeypatch: pytest.MonkeyPatch) -> None:
+    def test_check_pr_status(
+        self, mock_client_cls: MagicMock, mock_subproc: MagicMock, monkeypatch: pytest.MonkeyPatch
+    ) -> None:
         monkeypatch.setenv("CI_GITEA_TOKEN", "tok")
         monkeypatch.setenv("DEVX_REPO_OWNER", "owner")
         monkeypatch.setenv("DEVX_REPO_NAME", "repo")
@@ -157,8 +164,11 @@ class TestCli:
         assert result.exit_code == 0
         assert "[OK]" in result.output
 
+    @patch("devx.tools.pr_status.subprocess.run")
     @patch("devx.tools.pr_status.GiteaClient")
-    def test_check_sha_directly(self, mock_client_cls: MagicMock, monkeypatch: pytest.MonkeyPatch) -> None:
+    def test_check_sha_directly(
+        self, mock_client_cls: MagicMock, mock_subproc: MagicMock, monkeypatch: pytest.MonkeyPatch
+    ) -> None:
         monkeypatch.setenv("CI_GITEA_TOKEN", "tok")
         monkeypatch.setenv("DEVX_REPO_OWNER", "owner")
         monkeypatch.setenv("DEVX_REPO_NAME", "repo")
@@ -171,8 +181,11 @@ class TestCli:
         assert result.exit_code == 0
         assert "[OK]" in result.output
 
+    @patch("devx.tools.pr_status.subprocess.run")
     @patch("devx.tools.pr_status.GiteaClient")
-    def test_failure_raises_exception(self, mock_client_cls: MagicMock, monkeypatch: pytest.MonkeyPatch) -> None:
+    def test_failure_raises_exception(
+        self, mock_client_cls: MagicMock, mock_subproc: MagicMock, monkeypatch: pytest.MonkeyPatch
+    ) -> None:
         monkeypatch.setenv("CI_GITEA_TOKEN", "tok")
         monkeypatch.setenv("DEVX_REPO_OWNER", "owner")
         monkeypatch.setenv("DEVX_REPO_NAME", "repo")
@@ -234,8 +247,11 @@ class TestCli:
         assert result.exit_code != 0
         assert "Could not detect" in result.output
 
+    @patch("devx.tools.pr_status.subprocess.run")
     @patch("devx.tools.pr_status.GiteaClient")
-    def test_no_sha_raises(self, mock_client_cls: MagicMock, monkeypatch: pytest.MonkeyPatch) -> None:
+    def test_no_sha_raises(
+        self, mock_client_cls: MagicMock, mock_subproc: MagicMock, monkeypatch: pytest.MonkeyPatch
+    ) -> None:
         monkeypatch.setenv("CI_GITEA_TOKEN", "tok")
         monkeypatch.setenv("DEVX_REPO_OWNER", "owner")
         monkeypatch.setenv("DEVX_REPO_NAME", "repo")
@@ -246,11 +262,17 @@ class TestCli:
         assert result.exit_code != 0
         assert "SHA" in result.output
 
+    @patch("devx.tools.pr_status._get_current_branch_pr")
     @patch("devx.tools.pr_status.time.sleep")
     @patch("devx.tools.pr_status.time.time", side_effect=[0, 0, 100, 200])
     @patch("devx.tools.pr_status.GiteaClient")
     def test_wait_success(
-        self, mock_client_cls: MagicMock, mock_time: MagicMock, mock_sleep: MagicMock, monkeypatch: pytest.MonkeyPatch
+        self,
+        mock_client_cls: MagicMock,
+        mock_time: MagicMock,
+        mock_sleep: MagicMock,
+        mock_branch_pr: MagicMock,
+        monkeypatch: pytest.MonkeyPatch,
     ) -> None:
         monkeypatch.setenv("CI_GITEA_TOKEN", "tok")
         monkeypatch.setenv("DEVX_REPO_OWNER", "owner")
@@ -266,11 +288,17 @@ class TestCli:
         assert result.exit_code == 0
         assert "[OK]" in result.output
 
+    @patch("devx.tools.pr_status._get_current_branch_pr")
     @patch("devx.tools.pr_status.time.sleep")
     @patch("devx.tools.pr_status.time.time", side_effect=[0, 700])
     @patch("devx.tools.pr_status.GiteaClient")
     def test_wait_timeout(
-        self, mock_client_cls: MagicMock, mock_time: MagicMock, mock_sleep: MagicMock, monkeypatch: pytest.MonkeyPatch
+        self,
+        mock_client_cls: MagicMock,
+        mock_time: MagicMock,
+        mock_sleep: MagicMock,
+        mock_branch_pr: MagicMock,
+        monkeypatch: pytest.MonkeyPatch,
     ) -> None:
         monkeypatch.setenv("CI_GITEA_TOKEN", "tok")
         monkeypatch.setenv("DEVX_REPO_OWNER", "owner")

tests/unit/test_pre_push_check.py

@@ -97,9 +97,10 @@ class TestCli:
         result = runner.invoke(cli, [])
         assert result.exit_code == 0
 
+    @patch("devx.tools.pre_push_check.get_current_branch")
     @patch("devx.tools.pre_push_check.task_exists", return_value=True)
     @patch.dict("os.environ", {"VIKUNJA_TOKEN": "tok"})
-    def test_explicit_branch(self, mock_exists: MagicMock) -> None:
+    def test_explicit_branch(self, mock_exists: MagicMock, mock_branch: MagicMock) -> None:
         runner = CliRunner()
         result = runner.invoke(cli, ["--branch", "DEVX-42-fix"])
         assert result.exit_code == 0

tests/unit/test_publish.py

@@ -165,6 +165,9 @@ class TestDefaultGiteaRegistryUrl:
 
 
 class TestMain:
+    @patch("devx.ci.publish.subprocess.run")
+    @patch("devx.ci.publish.get_latest_tag", return_value="v0.1.0")
+    @patch("devx.gitea_cli.configure_tea_login")
     @patch.dict("os.environ", {"CI_GITEA_TOKEN": "gitea-tok", "PYPI_TOKEN": "pypi-tok"})
     @patch("devx.ci.publish.generate_release_notes", return_value="Release notes")
     @patch("devx.ci.publish.TeaCLI")
@@ -176,6 +179,9 @@ class TestMain:
         mock_publish: MagicMock,
         mock_tea_cls: MagicMock,
         mock_notes: MagicMock,
+        mock_run: MagicMock,
+        mock_tag: MagicMock,
+        mock_login: MagicMock,
     ) -> None:
         mock_tea = MagicMock()
         mock_tea.list_releases.return_value = []
@@ -190,6 +196,9 @@ class TestMain:
             "owner/repo", tag="v1.0.0", title="v1.0.0", body="Release notes"
         )
 
+    @patch("devx.ci.publish.subprocess.run")
+    @patch("devx.ci.publish.get_latest_tag", return_value="v0.1.0")
+    @patch("devx.gitea_cli.configure_tea_login")
     @patch.dict("os.environ", {"CI_GITEA_TOKEN": "gitea-tok"}, clear=True)
     @patch("devx.ci.publish.generate_release_notes", return_value="Release notes")
     @patch("devx.ci.publish.TeaCLI")
@@ -201,6 +210,9 @@ class TestMain:
         mock_gitea_publish: MagicMock,
         mock_tea_cls: MagicMock,
         mock_notes: MagicMock,
+        mock_run: MagicMock,
+        mock_tag: MagicMock,
+        mock_login: MagicMock,
     ) -> None:
         """When no PYPI_TOKEN, publishes to Gitea PyPI registry."""
         mock_tea = MagicMock()
@@ -213,6 +225,9 @@ class TestMain:
         mock_gitea_publish.assert_called_once()
         mock_tea.create_release.assert_called_once()
 
+    @patch("devx.ci.publish.subprocess.run")
+    @patch("devx.ci.publish.get_latest_tag", return_value="v0.1.0")
+    @patch("devx.gitea_cli.configure_tea_login")
     @patch.dict("os.environ", {"CI_GITEA_TOKEN": "gitea-tok"}, clear=True)
     @patch("devx.ci.publish.generate_release_notes", return_value="Release notes")
     @patch("devx.ci.publish.TeaCLI")
@@ -224,6 +239,9 @@ class TestMain:
         mock_gitea_publish: MagicMock,
         mock_tea_cls: MagicMock,
         mock_notes: MagicMock,
+        mock_run: MagicMock,
+        mock_tag: MagicMock,
+        mock_login: MagicMock,
     ) -> None:
         """--registry-url flag publishes to the specified Gitea registry."""
         mock_tea = MagicMock()
@@ -237,6 +255,9 @@ class TestMain:
         assert result.exit_code == 0
         mock_gitea_publish.assert_called_once_with("https://custom.registry.com/pypi", "gitea-tok")
 
+    @patch("devx.ci.publish.subprocess.run")
+    @patch("devx.ci.publish.get_latest_tag", return_value="v0.1.0")
+    @patch("devx.gitea_cli.configure_tea_login")
     @patch.dict(
         "os.environ",
         {"CI_GITEA_TOKEN": "gitea-tok", "DEVX_PYPI_REGISTRY_URL": "https://env.registry.com/pypi"},
@@ -252,6 +273,9 @@ class TestMain:
         mock_gitea_publish: MagicMock,
         mock_tea_cls: MagicMock,
         mock_notes: MagicMock,
+        mock_run: MagicMock,
+        mock_tag: MagicMock,
+        mock_login: MagicMock,
     ) -> None:
         """DEVX_PYPI_REGISTRY_URL env var sets the registry URL."""
         mock_tea = MagicMock()
@@ -262,6 +286,9 @@ class TestMain:
         assert result.exit_code == 0
         mock_gitea_publish.assert_called_once_with("https://env.registry.com/pypi", "gitea-tok")
 
+    @patch("devx.ci.publish.subprocess.run")
+    @patch("devx.ci.publish.get_latest_tag", return_value="v0.1.0")
+    @patch("devx.gitea_cli.configure_tea_login")
     @patch.dict("os.environ", {"CI_GITEA_TOKEN": "gitea-tok"}, clear=True)
     @patch("devx.ci.publish.generate_release_notes", return_value="Release notes")
     @patch("devx.ci.publish.TeaCLI")
@@ -273,6 +300,9 @@ class TestMain:
         mock_build: MagicMock,
         mock_tea_cls: MagicMock,
         mock_notes: MagicMock,
+        mock_run: MagicMock,
+        mock_tag: MagicMock,
+        mock_login: MagicMock,
     ) -> None:
         """When no PYPI_TOKEN and no registry URL, skips publish and creates release only."""
         mock_tea = MagicMock()
@@ -284,20 +314,33 @@ class TestMain:
         assert "PYPI_TOKEN not set" in result.output
         mock_tea.create_release.assert_called_once()
 
+    @patch("devx.ci.publish.subprocess.run")
+    @patch("devx.ci.publish.get_latest_tag", return_value="v0.1.0")
+    @patch("devx.gitea_cli.configure_tea_login")
     @patch.dict("os.environ", {"CI_GITEA_TOKEN": ""}, clear=True)
-    def test_missing_repo_token_exits(self) -> None:
+    def test_missing_repo_token_exits(self, mock_run: MagicMock, mock_tag: MagicMock, mock_login: MagicMock) -> None:
         runner = CliRunner()
         result = runner.invoke(main, ["v1.0.0", "owner/repo"])
         assert result.exit_code == 1
         assert "CI_GITEA_TOKEN" in result.output
 
+    @patch("devx.ci.publish.subprocess.run")
+    @patch("devx.ci.publish.get_latest_tag", return_value="v0.1.0")
+    @patch("devx.gitea_cli.configure_tea_login")
     @patch.dict("os.environ", {"CI_GITEA_TOKEN": "gitea-tok", "PYPI_TOKEN": "pypi-tok"})
     @patch("devx.ci.publish.generate_release_notes", return_value="Release notes")
     @patch("devx.ci.publish.TeaCLI")
     @patch("devx.ci.publish.publish_to_pypi")
     @patch("devx.ci.publish.build_package")
     def test_build_failure_raises_click(
-        self, mock_build: MagicMock, mock_publish: MagicMock, mock_tea_cls: MagicMock, mock_notes: MagicMock
+        self,
+        mock_build: MagicMock,
+        mock_publish: MagicMock,
+        mock_tea_cls: MagicMock,
+        mock_notes: MagicMock,
+        mock_run: MagicMock,
+        mock_tag: MagicMock,
+        mock_login: MagicMock,
     ) -> None:
         mock_build.side_effect = click.ClickException("build failed")
         runner = CliRunner()
@@ -305,13 +348,23 @@ class TestMain:
         assert result.exit_code == 1
         assert "build" in result.output
 
+    @patch("devx.ci.publish.subprocess.run")
+    @patch("devx.ci.publish.get_latest_tag", return_value="v0.1.0")
+    @patch("devx.gitea_cli.configure_tea_login")
     @patch.dict("os.environ", {"CI_GITEA_TOKEN": "gitea-tok", "PYPI_TOKEN": "pypi-tok"})
     @patch("devx.ci.publish.generate_release_notes", return_value="Release notes")
     @patch("devx.ci.publish.TeaCLI")
     @patch("devx.ci.publish.publish_to_pypi")
     @patch("devx.ci.publish.build_package")
     def test_publish_failure_continues_to_gitea_release(
-        self, mock_build: MagicMock, mock_publish: MagicMock, mock_tea_cls: MagicMock, mock_notes: MagicMock
+        self,
+        mock_build: MagicMock,
+        mock_publish: MagicMock,
+        mock_tea_cls: MagicMock,
+        mock_notes: MagicMock,
+        mock_run: MagicMock,
+        mock_tag: MagicMock,
+        mock_login: MagicMock,
     ) -> None:
         """PyPI publish failure is non-fatal — Gitea release is still created."""
         mock_tea = MagicMock()
@@ -326,14 +379,27 @@ class TestMain:
             "owner/repo", tag="v1.0.0", title="v1.0.0", body="Release notes"
         )
 
+    @patch("devx.ci.publish.subprocess.run")
+    @patch("devx.ci.publish.get_latest_tag", return_value="v0.1.0")
+    @patch("devx.gitea_cli.configure_tea_login")
     @patch.dict("os.environ", {"CI_GITEA_TOKEN": "gitea-tok", "PYPI_TOKEN": "pypi-tok"})
     @patch("devx.ci.publish.generate_release_notes", return_value="Release notes")
     @patch("devx.ci.publish.TeaCLI")
     @patch("devx.ci.publish.publish_to_pypi")
     @patch("devx.ci.publish.build_package")
+    @patch("time.sleep")
     def test_release_failure_raises_click(
-        self, mock_build: MagicMock, mock_publish: MagicMock, mock_tea_cls: MagicMock, mock_notes: MagicMock
+        self,
+        mock_sleep: MagicMock,
+        mock_build: MagicMock,
+        mock_publish: MagicMock,
+        mock_tea_cls: MagicMock,
+        mock_notes: MagicMock,
+        mock_run: MagicMock,
+        mock_tag: MagicMock,
+        mock_login: MagicMock,
     ) -> None:
+        """Release creation failure after retries raises ClickException."""
         mock_tea = MagicMock()
         mock_tea.list_releases.return_value = []
         mock_tea.create_release.side_effect = TeaCLIError("server error")
@@ -342,13 +408,24 @@ class TestMain:
         result = runner.invoke(main, ["v1.0.0", "owner/repo"])
         assert result.exit_code == 1
         assert "Release creation failed" in result.output
+        # Retried 3 times (stop_after_attempt(3))
+        assert mock_tea.create_release.call_count == 3
 
+    @patch("devx.ci.publish.subprocess.run")
+    @patch("devx.ci.publish.get_latest_tag", return_value="v0.1.0")
+    @patch("devx.gitea_cli.configure_tea_login")
     @patch.dict("os.environ", {"CI_GITEA_TOKEN": "gitea-tok"})
     @patch("devx.ci.publish.generate_release_notes", return_value="Release notes")
     @patch("devx.ci.publish.TeaCLI")
     @patch("devx.ci.publish.build_package")
     def test_skip_build_skips_build_and_publish(
-        self, mock_build: MagicMock, mock_tea_cls: MagicMock, mock_notes: MagicMock
+        self,
+        mock_build: MagicMock,
+        mock_tea_cls: MagicMock,
+        mock_notes: MagicMock,
+        mock_run: MagicMock,
+        mock_tag: MagicMock,
+        mock_login: MagicMock,
     ) -> None:
         """--skip-build skips build_package and PyPI publish, only creates Gitea release."""
         mock_tea = MagicMock()
@@ -361,13 +438,23 @@ class TestMain:
         mock_build.assert_not_called()
         mock_tea.create_release.assert_called_once()
 
+    @patch("devx.ci.publish.subprocess.run")
+    @patch("devx.ci.publish.get_latest_tag", return_value="v0.1.0")
+    @patch("devx.gitea_cli.configure_tea_login")
     @patch.dict("os.environ", {"CI_GITEA_TOKEN": "gitea-tok", "PYPI_TOKEN": "pypi-tok"})
     @patch("devx.ci.publish.generate_release_notes", return_value="Release notes")
     @patch("devx.ci.publish.TeaCLI")
     @patch("devx.ci.publish.publish_to_pypi")
     @patch("devx.ci.publish.build_package")
     def test_skips_release_creation_when_already_exists(
-        self, mock_build: MagicMock, mock_publish: MagicMock, mock_tea_cls: MagicMock, mock_notes: MagicMock
+        self,
+        mock_build: MagicMock,
+        mock_publish: MagicMock,
+        mock_tea_cls: MagicMock,
+        mock_notes: MagicMock,
+        mock_run: MagicMock,
+        mock_tag: MagicMock,
+        mock_login: MagicMock,
     ) -> None:
         """If the Gitea release already exists, skip creation (idempotent)."""
         mock_tea = MagicMock()
@@ -379,13 +466,23 @@ class TestMain:
         assert "already exists" in result.output
         mock_tea.create_release.assert_not_called()
 
+    @patch("devx.ci.publish.subprocess.run")
+    @patch("devx.ci.publish.get_latest_tag", return_value="v0.1.0")
+    @patch("devx.gitea_cli.configure_tea_login")
     @patch.dict("os.environ", {"CI_GITEA_TOKEN": "gitea-tok", "PYPI_TOKEN": "pypi-tok"})
     @patch("devx.ci.publish.generate_release_notes", return_value="Release notes")
     @patch("devx.ci.publish.TeaCLI")
     @patch("devx.ci.publish.publish_to_pypi")
     @patch("devx.ci.publish.build_package")
     def test_proceeds_to_create_when_list_releases_fails(
-        self, mock_build: MagicMock, mock_publish: MagicMock, mock_tea_cls: MagicMock, mock_notes: MagicMock
+        self,
+        mock_build: MagicMock,
+        mock_publish: MagicMock,
+        mock_tea_cls: MagicMock,
+        mock_notes: MagicMock,
+        mock_run: MagicMock,
+        mock_tag: MagicMock,
+        mock_login: MagicMock,
     ) -> None:
         """If list_releases raises TeaCLIError, proceed to create the release."""
         mock_tea = MagicMock()
@@ -395,21 +492,29 @@ class TestMain:
         result = runner.invoke(main, ["v1.0.0", "owner/repo"])
         assert result.exit_code == 0
 
+    @patch("devx.ci.publish.subprocess.run")
+    @patch("devx.ci.publish.get_latest_tag", return_value="v0.1.0")
+    @patch("devx.gitea_cli.configure_tea_login")
     @patch.dict("os.environ", {"CI_GITEA_TOKEN": "gitea-tok"})
     @patch("devx.ci.publish.generate_release_notes", return_value="Release notes")
     @patch("devx.ci.publish.TeaCLI")
     @patch("devx.ci.publish.publish_to_gitea_registry")
     @patch("devx.ci.publish.publish_to_pypi")
     @patch("devx.ci.publish.build_package")
+    @patch("time.sleep")
     def test_create_release_already_exists_is_idempotent(
         self,
+        mock_sleep: MagicMock,
         mock_build: MagicMock,
         mock_publish: MagicMock,
         mock_gitea_pub: MagicMock,
         mock_tea_cls: MagicMock,
         mock_notes: MagicMock,
+        mock_run: MagicMock,
+        mock_tag: MagicMock,
+        mock_login: MagicMock,
     ) -> None:
-        """If create_release fails with 'already exists', treat as success."""
+        """If create_release fails with 'already exists', treat as success (no retry)."""
         mock_tea = MagicMock()
         mock_tea.list_releases.side_effect = TeaCLIError("api error")
         mock_tea.create_release.side_effect = TeaCLIError("there is already a release for this tag")
@@ -418,22 +523,32 @@ class TestMain:
         result = runner.invoke(main, ["v1.0.0", "owner/repo"])
         assert result.exit_code == 0
         assert "already exists" in result.output
+        # "already exists" is caught immediately — no retry
+        assert mock_tea.create_release.call_count == 1
 
+    @patch("devx.ci.publish.subprocess.run")
+    @patch("devx.ci.publish.get_latest_tag", return_value="v0.1.0")
+    @patch("devx.gitea_cli.configure_tea_login")
     @patch.dict("os.environ", {"CI_GITEA_TOKEN": "gitea-tok"})
     @patch("devx.ci.publish.generate_release_notes", return_value="Release notes")
     @patch("devx.ci.publish.TeaCLI")
     @patch("devx.ci.publish.publish_to_gitea_registry")
     @patch("devx.ci.publish.publish_to_pypi")
     @patch("devx.ci.publish.build_package")
+    @patch("time.sleep")
     def test_create_release_other_error_raises(
         self,
+        mock_sleep: MagicMock,
         mock_build: MagicMock,
         mock_publish: MagicMock,
         mock_gitea_pub: MagicMock,
         mock_tea_cls: MagicMock,
         mock_notes: MagicMock,
+        mock_run: MagicMock,
+        mock_tag: MagicMock,
+        mock_login: MagicMock,
     ) -> None:
-        """If create_release fails with a non-'already exists' error, raise."""
+        """If create_release fails with a non-'already exists' error, raise after retries."""
         mock_tea = MagicMock()
         mock_tea.list_releases.side_effect = TeaCLIError("api error")
         mock_tea.create_release.side_effect = TeaCLIError("network error")
@@ -442,6 +557,75 @@ class TestMain:
         result = runner.invoke(main, ["v1.0.0", "owner/repo"])
         assert result.exit_code != 0
         assert "Release creation failed" in result.output
+        # Retried 3 times before giving up
+        assert mock_tea.create_release.call_count == 3
+
+
+class TestReleaseRetry:
+    """Tests for retry logic on transient release creation failures."""
+
+    @patch("devx.ci.publish.subprocess.run")
+    @patch("devx.ci.publish.get_latest_tag", return_value="v0.1.0")
+    @patch("devx.gitea_cli.configure_tea_login")
+    @patch.dict("os.environ", {"CI_GITEA_TOKEN": "gitea-tok"})
+    @patch("devx.ci.publish.generate_release_notes", return_value="Release notes")
+    @patch("devx.ci.publish.TeaCLI")
+    @patch("devx.ci.publish.build_package")
+    @patch("time.sleep")
+    def test_transient_failure_retried_and_succeeds(
+        self,
+        mock_sleep: MagicMock,
+        mock_build: MagicMock,
+        mock_tea_cls: MagicMock,
+        mock_notes: MagicMock,
+        mock_run: MagicMock,
+        mock_tag: MagicMock,
+        mock_login: MagicMock,
+    ) -> None:
+        """Transient failure on first attempt succeeds on retry."""
+        mock_tea = MagicMock()
+        mock_tea.list_releases.return_value = []
+        mock_tea.create_release.side_effect = [
+            TeaCLIError("connection timeout"),
+            None,  # second attempt succeeds
+        ]
+        mock_tea_cls.return_value = mock_tea
+        runner = CliRunner()
+        result = runner.invoke(main, ["v1.0.0", "owner/repo", "--skip-build"])
+        assert result.exit_code == 0
+        assert "Gitea release v1.0.0 created" in result.output
+        assert mock_tea.create_release.call_count == 2
+        mock_sleep.assert_called()  # slept between attempts
+
+    @patch("devx.ci.publish.subprocess.run")
+    @patch("devx.ci.publish.get_latest_tag", return_value="v0.1.0")
+    @patch("devx.gitea_cli.configure_tea_login")
+    @patch.dict("os.environ", {"CI_GITEA_TOKEN": "gitea-tok"})
+    @patch("devx.ci.publish.generate_release_notes", return_value="Release notes")
+    @patch("devx.ci.publish.TeaCLI")
+    @patch("devx.ci.publish.build_package")
+    @patch("time.sleep")
+    def test_all_retries_exhausted_raises(
+        self,
+        mock_sleep: MagicMock,
+        mock_build: MagicMock,
+        mock_tea_cls: MagicMock,
+        mock_notes: MagicMock,
+        mock_run: MagicMock,
+        mock_tag: MagicMock,
+        mock_login: MagicMock,
+    ) -> None:
+        """All 3 retry attempts fail — raises ClickException."""
+        mock_tea = MagicMock()
+        mock_tea.list_releases.return_value = []
+        mock_tea.create_release.side_effect = TeaCLIError("503 service unavailable")
+        mock_tea_cls.return_value = mock_tea
+        runner = CliRunner()
+        result = runner.invoke(main, ["v1.0.0", "owner/repo", "--skip-build"])
+        assert result.exit_code == 1
+        assert "Release creation failed" in result.output
+        assert mock_tea.create_release.call_count == 3
+        assert mock_sleep.call_count == 2  # slept between 3 attempts (2 sleeps)
 
 
 class TestFromTag:
@@ -487,40 +671,74 @@ class TestFromTag:
             result = is_release_commit("v1.2.3")
         assert result is False
 
+    @patch("devx.ci.publish.subprocess.run")
+    @patch("devx.gitea_cli.configure_tea_login")
     @patch("devx.ci.publish.get_latest_tag", return_value=None)
-    def test_from_tag_no_tag_skips(self, _mock: MagicMock) -> None:
+    def test_from_tag_no_tag_skips(self, _mock: MagicMock, mock_run: MagicMock, mock_login: MagicMock) -> None:
         runner = CliRunner()
         result = runner.invoke(main, ["--from-tag", "--skip-build", "", "owner/repo"])
         assert result.exit_code == 0
         assert "No tag found" in result.output
 
+    @patch("devx.ci.publish.subprocess.run")
+    @patch("devx.gitea_cli.configure_tea_login")
     @patch("devx.ci.publish.get_latest_tag", return_value=None)
-    def test_from_tag_no_repo_uses_env(self, _mock: MagicMock) -> None:
+    def test_from_tag_no_repo_uses_env(self, _mock: MagicMock, mock_run: MagicMock, mock_login: MagicMock) -> None:
         runner = CliRunner()
         with patch.dict("os.environ", {"GITHUB_REPOSITORY": "owner/repo"}):
             result = runner.invoke(main, ["--from-tag", "--skip-build"])
         assert result.exit_code == 0
         assert "No tag found" in result.output
 
+    @patch("devx.ci.publish.subprocess.run")
+    @patch("devx.gitea_cli.configure_tea_login")
     @patch("devx.ci.publish.get_latest_tag", return_value=None)
-    def test_from_tag_no_repo_no_env_raises(self, _mock: MagicMock) -> None:
+    def test_from_tag_no_repo_no_env_raises(self, _mock: MagicMock, mock_run: MagicMock, mock_login: MagicMock) -> None:
         runner = CliRunner()
         with patch.dict("os.environ", {}, clear=True):
             result = runner.invoke(main, ["--from-tag", "--skip-build"])
         assert result.exit_code != 0
         assert "REPO argument is required" in result.output
 
+    @patch("devx.ci.publish.subprocess.run")
+    @patch("devx.ci.publish.generate_release_notes", return_value="notes")
+    @patch("devx.ci.publish.publish_to_pypi")
+    @patch("devx.ci.publish.publish_to_gitea_registry")
+    @patch("devx.gitea_cli.configure_tea_login")
     @patch("devx.ci.publish.is_release_commit", return_value=False)
     @patch("devx.ci.publish.get_latest_tag", return_value="v1.0.0")
-    def test_from_tag_not_release_commit_skips(self, _mock_tag: MagicMock, _mock_rel: MagicMock) -> None:
+    def test_from_tag_not_release_commit_skips(
+        self,
+        _mock_tag: MagicMock,
+        _mock_rel: MagicMock,
+        mock_run: MagicMock,
+        mock_notes: MagicMock,
+        mock_pypi: MagicMock,
+        mock_gitea_reg: MagicMock,
+        mock_login: MagicMock,
+    ) -> None:
         runner = CliRunner()
         result = runner.invoke(main, ["--from-tag", "--skip-build", "", "owner/repo"])
         assert result.exit_code == 0
         assert "not a release commit" in result.output
 
+    @patch("devx.ci.publish.subprocess.run")
+    @patch("devx.ci.publish.generate_release_notes", return_value="notes")
+    @patch("devx.ci.publish.publish_to_pypi")
+    @patch("devx.ci.publish.publish_to_gitea_registry")
+    @patch("devx.gitea_cli.configure_tea_login")
     @patch("devx.ci.publish.is_release_commit", return_value=True)
     @patch("devx.ci.publish.get_latest_tag", return_value="v1.0.0")
-    def test_from_tag_publishes(self, _mock_tag: MagicMock, _mock_rel: MagicMock) -> None:
+    def test_from_tag_publishes(
+        self,
+        _mock_tag: MagicMock,
+        _mock_rel: MagicMock,
+        mock_run: MagicMock,
+        mock_notes: MagicMock,
+        mock_pypi: MagicMock,
+        mock_gitea_reg: MagicMock,
+        mock_login: MagicMock,
+    ) -> None:
         with patch.dict("os.environ", {"CI_GITEA_TOKEN": "fake"}):
             with patch("devx.ci.publish.TeaCLI") as mock_tea_cls:
                 mock_tea = MagicMock()
@@ -532,9 +750,23 @@ class TestFromTag:
         assert result.exit_code == 0
         assert "Publishing release v1.0.0" in result.output
 
+    @patch("devx.ci.publish.subprocess.run")
+    @patch("devx.ci.publish.generate_release_notes", return_value="notes")
+    @patch("devx.ci.publish.publish_to_pypi")
+    @patch("devx.ci.publish.publish_to_gitea_registry")
+    @patch("devx.gitea_cli.configure_tea_login")
     @patch("devx.ci.publish.is_release_commit", return_value=True)
     @patch("devx.ci.publish.get_latest_tag", return_value="v1.0.0")
-    def test_from_tag_publishes_no_repo_arg(self, _mock_tag: MagicMock, _mock_rel: MagicMock) -> None:
+    def test_from_tag_publishes_no_repo_arg(
+        self,
+        _mock_tag: MagicMock,
+        _mock_rel: MagicMock,
+        mock_run: MagicMock,
+        mock_notes: MagicMock,
+        mock_pypi: MagicMock,
+        mock_gitea_reg: MagicMock,
+        mock_login: MagicMock,
+    ) -> None:
         with patch.dict("os.environ", {"CI_GITEA_TOKEN": "fake", "GITHUB_REPOSITORY": "owner/repo"}):
             with patch("devx.ci.publish.TeaCLI") as mock_tea_cls:
                 mock_tea = MagicMock()
@@ -546,7 +778,21 @@ class TestFromTag:
         assert result.exit_code == 0
         assert "Publishing release v1.0.0" in result.output
 
-    def test_no_tag_no_from_tag_raises(self) -> None:
+    @patch("devx.ci.publish.subprocess.run")
+    @patch("devx.ci.publish.get_latest_tag", return_value="v0.1.0")
+    @patch("devx.ci.publish.generate_release_notes", return_value="notes")
+    @patch("devx.ci.publish.publish_to_pypi")
+    @patch("devx.ci.publish.publish_to_gitea_registry")
+    @patch("devx.gitea_cli.configure_tea_login")
+    def test_no_tag_no_from_tag_raises(
+        self,
+        mock_run: MagicMock,
+        mock_tag: MagicMock,
+        mock_notes: MagicMock,
+        mock_pypi: MagicMock,
+        mock_gitea_reg: MagicMock,
+        mock_login: MagicMock,
+    ) -> None:
         runner = CliRunner()
         result = runner.invoke(main, ["", "owner/repo", "--skip-build"])
         assert result.exit_code != 0
@@ -556,10 +802,24 @@ class TestFromTag:
 class TestPublishAutoLogin:
     """Tests for --auto-login flag in publish."""
 
+    @patch("devx.ci.publish.subprocess.run")
+    @patch("devx.ci.publish.get_latest_tag", return_value="v0.1.0")
+    @patch("devx.ci.publish.generate_release_notes", return_value="notes")
+    @patch("devx.ci.publish.publish_to_pypi")
+    @patch("devx.ci.publish.publish_to_gitea_registry")
     @patch.dict("os.environ", {"CI_GITEA_TOKEN": "tok"})
     @patch("devx.ci.publish.configure_tea_login")
     @patch("devx.ci.publish.TeaCLI")
-    def test_auto_login_calls_configure(self, mock_tea_cls: MagicMock, mock_login: MagicMock) -> None:
+    def test_auto_login_calls_configure(
+        self,
+        mock_tea_cls: MagicMock,
+        mock_login: MagicMock,
+        mock_run: MagicMock,
+        mock_tag: MagicMock,
+        mock_notes: MagicMock,
+        mock_pypi: MagicMock,
+        mock_gitea_reg: MagicMock,
+    ) -> None:
         """--auto-login calls configure_tea_login before creating release."""
         mock_tea = MagicMock()
         mock_tea.list_releases.return_value = []
@@ -571,10 +831,24 @@ class TestPublishAutoLogin:
         assert result.exit_code == 0
         mock_login.assert_called_once()
 
+    @patch("devx.ci.publish.subprocess.run")
+    @patch("devx.ci.publish.get_latest_tag", return_value="v0.1.0")
+    @patch("devx.ci.publish.generate_release_notes", return_value="notes")
+    @patch("devx.ci.publish.publish_to_pypi")
+    @patch("devx.ci.publish.publish_to_gitea_registry")
     @patch.dict("os.environ", {"CI_GITEA_TOKEN": "tok"})
     @patch("devx.ci.publish.configure_tea_login")
     @patch("devx.ci.publish.TeaCLI")
-    def test_no_auto_login_skips_configure(self, mock_tea_cls: MagicMock, mock_login: MagicMock) -> None:
+    def test_no_auto_login_skips_configure(
+        self,
+        mock_tea_cls: MagicMock,
+        mock_login: MagicMock,
+        mock_run: MagicMock,
+        mock_tag: MagicMock,
+        mock_notes: MagicMock,
+        mock_pypi: MagicMock,
+        mock_gitea_reg: MagicMock,
+    ) -> None:
         """Without --auto-login, configure_tea_login is not called."""
         mock_tea = MagicMock()
         mock_tea.list_releases.return_value = []

tests/unit/test_rebase.py

@@ -278,9 +278,10 @@ class TestRebaseTool:
 class TestPrRebaseTool:
     """Tests for the server-side PR rebase tool (devx.tools.pr_rebase)."""
 
+    @patch("devx.tools._shared.detect_pr_number")
     @patch.dict("os.environ", _FULL_ENV, clear=True)
     @patch("devx.tools.pr_rebase.GiteaClient")
-    def test_pr_rebase_success(self, mock_client_cls: MagicMock) -> None:
+    def test_pr_rebase_success(self, mock_client_cls: MagicMock, mock_detect: MagicMock) -> None:
         """Successful API rebase prints confirmation."""
         mock_client = MagicMock()
         mock_client_cls.return_value = mock_client
@@ -291,9 +292,10 @@ class TestPrRebaseTool:
         assert "rebased successfully" in result.output.lower()
         mock_client.update_pr_branch.assert_called_once_with(42, style="rebase")
 
+    @patch("devx.tools._shared.detect_pr_number")
     @patch.dict("os.environ", _FULL_ENV, clear=True)
     @patch("devx.tools.pr_rebase.GiteaClient")
-    def test_pr_rebase_api_error(self, mock_client_cls: MagicMock) -> None:
+    def test_pr_rebase_api_error(self, mock_client_cls: MagicMock, mock_detect: MagicMock) -> None:
         """API error during rebase exits with error."""
         from devx.api_clients import APIError
 
@@ -306,9 +308,10 @@ class TestPrRebaseTool:
         assert result.exit_code != 0
         assert "rebase failed" in result.output.lower()
 
+    @patch("devx.tools._shared.detect_pr_number")
     @patch("devx.tools.pr_rebase.load_dotenv")
     @patch.dict("os.environ", {}, clear=True)
-    def test_pr_rebase_no_token(self, _mock_load: MagicMock) -> None:
+    def test_pr_rebase_no_token(self, _mock_load: MagicMock, mock_detect: MagicMock) -> None:
         """Missing CI_GITEA_TOKEN should fail."""
         runner = CliRunner()
         result = runner.invoke(pr_rebase_main, ["--pr", "42"])
@@ -324,20 +327,26 @@ class TestPrRebaseTool:
         assert result.exit_code != 0
         assert "could not detect" in result.output.lower()
 
+    @patch("devx.tools._shared.detect_pr_number")
     @patch("devx.tools.pr_rebase.load_dotenv")
     @patch.dict("os.environ", {"CI_GITEA_TOKEN": "tok"}, clear=True)
     @patch("devx.tools.pr_rebase.GiteaClient")
-    def test_pr_rebase_no_repo_env(self, _mock_client: MagicMock, _mock_load: MagicMock) -> None:
+    def test_pr_rebase_no_repo_env(
+        self, _mock_client: MagicMock, _mock_load: MagicMock, mock_detect: MagicMock
+    ) -> None:
         """Missing repo env vars should fail."""
         runner = CliRunner()
         result = runner.invoke(pr_rebase_main, ["--pr", "42"])
         assert result.exit_code != 0
         assert "DEVX_REPO_OWNER" in result.output
 
+    @patch("devx.tools._shared.detect_pr_number")
     @patch("devx.tools.pr_rebase.load_dotenv")
     @patch.dict("os.environ", {"CI_GITEA_TOKEN": "tok", "GITHUB_REPOSITORY": "owner/repo"}, clear=True)
     @patch("devx.tools.pr_rebase.GiteaClient")
-    def test_pr_rebase_github_repo_fallback(self, mock_client_cls: MagicMock, _mock_load: MagicMock) -> None:
+    def test_pr_rebase_github_repo_fallback(
+        self, mock_client_cls: MagicMock, _mock_load: MagicMock, mock_detect: MagicMock
+    ) -> None:
         """GITHUB_REPOSITORY env var is used as fallback for owner/repo."""
         mock_client = MagicMock()
         mock_client_cls.return_value = mock_client

tests/unit/test_release.py

@@ -952,22 +952,32 @@ class TestMain:
     verify specific git call sequences mock run_cmd with side_effect.
     """
 
+    @patch("devx.ci.release.has_user_facing_changes", return_value=False)
+    @patch("devx.ci.release.update_doc_versions")
     @patch.dict("os.environ", {})
     @patch("devx.ci.release.run_cmd")
-    def test_not_on_master_exits(self, mock_run_cmd: MagicMock) -> None:
+    def test_not_on_master_exits(
+        self, mock_run_cmd: MagicMock, mock_update_docs: MagicMock, mock_ufc: MagicMock
+    ) -> None:
         mock_run_cmd.return_value = MagicMock(returncode=0, stdout="feature-branch\n", stderr="")
         runner = CliRunner()
         result = runner.invoke(main, [])
         assert result.exit_code != 0
         assert "master" in result.output
 
+    @patch("devx.ci.release.update_doc_versions")
     @patch.dict("os.environ", {})
     @patch("devx.ci.release.get_latest_tag", return_value="v0.5.0")
     @patch("devx.ci.release.verify_tag_consistency", return_value=[])
     @patch("devx.ci.release.has_user_facing_changes", return_value=False)
     @patch("devx.ci.release.run_cmd")
     def test_dry_run_on_non_master_warns(
-        self, mock_run_cmd: MagicMock, mock_uf: MagicMock, mock_vtc: MagicMock, mock_glt: MagicMock
+        self,
+        mock_run_cmd: MagicMock,
+        mock_uf: MagicMock,
+        mock_vtc: MagicMock,
+        mock_glt: MagicMock,
+        mock_update_docs: MagicMock,
     ) -> None:
         """Dry-run mode should not fail on non-master branches."""
         mock_run_cmd.return_value = MagicMock(returncode=0, stdout="feature-branch\n", stderr="")
@@ -976,6 +986,7 @@ class TestMain:
         assert result.exit_code == 0
         assert "Dry-run mode" in result.output
 
+    @patch("devx.ci.release.update_doc_versions")
     @patch.dict("os.environ", {})
     @patch("devx.ci.release.get_head_commit", return_value="abc123")
     @patch("devx.ci.release.get_tag_commit", return_value="abc123")
@@ -991,6 +1002,7 @@ class TestMain:
         mock_vtc: MagicMock,
         mock_tc: MagicMock,
         mock_hc: MagicMock,
+        mock_update_docs: MagicMock,
     ) -> None:
         """If HEAD is a release commit and the tag exists, skip."""
         mock_run_cmd.side_effect = [
@@ -1004,6 +1016,7 @@ class TestMain:
         assert "already a release commit" in result.output
         assert "Skipping" in result.output
 
+    @patch("devx.ci.release.update_doc_versions")
     @patch.dict("os.environ", {})
     @patch("devx.ci.release.get_head_commit", return_value="def456")
     @patch("devx.ci.release.get_tag_commit", return_value="abc123")
@@ -1019,6 +1032,7 @@ class TestMain:
         mock_vtc: MagicMock,
         mock_tc: MagicMock,
         mock_hc: MagicMock,
+        mock_update_docs: MagicMock,
     ) -> None:
         """If HEAD is a release commit but tag points elsewhere, error."""
         mock_run_cmd.side_effect = [
@@ -1031,6 +1045,8 @@ class TestMain:
         assert result.exit_code != 0
         assert "misalignment" in result.output
 
+    @patch("devx.ci.release.has_user_facing_changes", return_value=False)
+    @patch("devx.ci.release.update_doc_versions")
     @patch.dict("os.environ", {})
     @patch("devx.ci.release.verify_tag_consistency", return_value=[])
     @patch("devx.ci.release.fetch_tags")
@@ -1044,6 +1060,8 @@ class TestMain:
         mock_changelog: MagicMock,
         mock_ft: MagicMock,
         mock_vtc: MagicMock,
+        mock_update_docs: MagicMock,
+        mock_ufc: MagicMock,
     ) -> None:
         """If HEAD is a release commit but the tag is missing, create the tag."""
         mock_run_cmd.side_effect = [
@@ -1058,21 +1076,25 @@ class TestMain:
         assert "Recovering" in result.output
         mock_create_tag.assert_called_once_with("0.5.0", "## changelog", False)
 
+    @patch("devx.ci.release.update_doc_versions")
     @patch.dict("os.environ", {})
     @patch("devx.ci.release.verify_tag_consistency", return_value=[])
     @patch("devx.ci.release.fetch_tags")
     @patch("devx.ci.release.has_user_facing_changes", return_value=True)
     @patch("devx.ci.release.has_unreleased_changes", return_value=False)
     @patch("devx.ci.release.get_bumped_version", return_value="0.2.0")
+    @patch("devx.ci.release.get_latest_tag", return_value="v0.1.0")
     @patch("devx.ci.release.run_cmd")
     def test_no_unreleased_changes(
         self,
         mock_run_cmd: MagicMock,
+        mock_latest: MagicMock,
         mock_bumped: MagicMock,
         mock_has: MagicMock,
         mock_user: MagicMock,
         mock_ft: MagicMock,
         mock_vtc: MagicMock,
+        mock_update_docs: MagicMock,
     ) -> None:
         mock_run_cmd.return_value = MagicMock(returncode=0, stdout="master\n", stderr="")
         runner = CliRunner()
@@ -1080,6 +1102,7 @@ class TestMain:
         assert result.exit_code == 0
         assert "No unreleased changes" in result.output
 
+    @patch("devx.ci.release.update_doc_versions")
     @patch.dict("os.environ", {})
     @patch("devx.ci.release.verify_tag_consistency", return_value=[])
     @patch("devx.ci.release.has_user_facing_changes", return_value=True)
@@ -1105,6 +1128,7 @@ class TestMain:
         mock_tag: MagicMock,
         mock_user: MagicMock,
         mock_vtc: MagicMock,
+        mock_update_docs: MagicMock,
     ) -> None:
         """Empty changelog should fail, not warn."""
         mock_run_cmd.return_value = MagicMock(returncode=0, stdout="master\n", stderr="")
@@ -1113,6 +1137,7 @@ class TestMain:
         assert result.exit_code != 0
         assert "empty changelog" in result.output.lower()
 
+    @patch("devx.ci.release.update_doc_versions")
     @patch.dict("os.environ", {})
     @patch("devx.ci.release.verify_tag_consistency", return_value=[])
     @patch("devx.ci.release.has_user_facing_changes", return_value=True)
@@ -1138,6 +1163,7 @@ class TestMain:
         mock_tag: MagicMock,
         mock_user: MagicMock,
         mock_vtc: MagicMock,
+        mock_update_docs: MagicMock,
     ) -> None:
         mock_run_cmd.return_value = MagicMock(returncode=0, stdout="master\n", stderr="")
         runner = CliRunner()
@@ -1149,6 +1175,7 @@ class TestMain:
         mock_commit.assert_not_called()
         mock_tag.assert_not_called()
 
+    @patch("devx.ci.release.update_doc_versions")
     @patch.dict("os.environ", {})
     @patch("devx.ci.release.verify_tag_consistency", return_value=[])
     @patch("devx.ci.release.fetch_tags")
@@ -1162,6 +1189,7 @@ class TestMain:
         mock_latest: MagicMock,
         mock_ft: MagicMock,
         mock_vtc: MagicMock,
+        mock_update_docs: MagicMock,
     ) -> None:
         """Release is skipped when only workflow/infrastructure files changed."""
         mock_run_cmd.return_value = MagicMock(returncode=0, stdout="master\n", stderr="")
@@ -1171,11 +1199,11 @@ class TestMain:
         assert "No user-facing changes" in result.output
         assert "Skipping release" in result.output
 
+    @patch("devx.ci.release.run_tests")
     @patch.dict("os.environ", {})
     @patch("devx.ci.release.verify_tag_consistency", return_value=[])
     @patch("devx.ci.release.fetch_tags")
     @patch("devx.ci.release.has_user_facing_changes", return_value=True)
-    @patch("devx.ci.release.run_tests")
     @patch("devx.ci.release.create_and_push_tag", return_value=True)
     @patch("devx.ci.release.commit_release_changes", return_value=True)
     @patch("devx.ci.release.update_changelog")
@@ -1184,10 +1212,12 @@ class TestMain:
     @patch("devx.ci.release.get_latest_tag", return_value="v0.1.0")
     @patch("devx.ci.release.get_bumped_version", return_value="0.2.0")
     @patch("devx.ci.release.has_unreleased_changes", return_value=True)
+    @patch("devx.ci.release.update_doc_versions")
     @patch("devx.ci.release.run_cmd")
     def test_full_flow(
         self,
         mock_run_cmd: MagicMock,
+        mock_update_docs: MagicMock,
         mock_has: MagicMock,
         mock_bumped: MagicMock,
         mock_latest: MagicMock,
@@ -1196,10 +1226,10 @@ class TestMain:
         mock_update_changelog: MagicMock,
         mock_commit: MagicMock,
         mock_tag: MagicMock,
-        mock_run_tests: MagicMock,
         mock_user: MagicMock,
         mock_ft: MagicMock,
         mock_vtc: MagicMock,
+        mock_run_tests: MagicMock,
     ) -> None:
         mock_run_cmd.return_value = MagicMock(returncode=0, stdout="master\n", stderr="")
         runner = CliRunner()
@@ -1216,7 +1246,6 @@ class TestMain:
     @patch("devx.ci.release.verify_tag_consistency", return_value=[])
     @patch("devx.ci.release.fetch_tags")
     @patch("devx.ci.release.has_user_facing_changes", return_value=True)
-    @patch("devx.ci.release.run_tests")
     @patch("devx.ci.release.create_and_push_tag", return_value=False)
     @patch("devx.ci.release.commit_release_changes", return_value=False)
     @patch("devx.ci.release.update_changelog")
@@ -1225,10 +1254,12 @@ class TestMain:
     @patch("devx.ci.release.get_latest_tag", return_value="v0.1.0")
     @patch("devx.ci.release.get_bumped_version", return_value="0.2.0")
     @patch("devx.ci.release.has_unreleased_changes", return_value=True)
+    @patch("devx.ci.release.update_doc_versions")
     @patch("devx.ci.release.run_cmd")
     def test_full_flow_tag_exists(
         self,
         mock_run_cmd: MagicMock,
+        mock_update_docs: MagicMock,
         mock_has: MagicMock,
         mock_bumped: MagicMock,
         mock_latest: MagicMock,
@@ -1237,7 +1268,6 @@ class TestMain:
         mock_update_changelog: MagicMock,
         mock_commit: MagicMock,
         mock_tag: MagicMock,
-        mock_run_tests: MagicMock,
         mock_user: MagicMock,
         mock_ft: MagicMock,
         mock_vtc: MagicMock,
@@ -1250,11 +1280,11 @@ class TestMain:
         assert "already existed" in result.output
         mock_tag.assert_called_once_with("0.2.0", "changelog", False)
 
+    @patch("devx.ci.release.run_tests")
     @patch.dict("os.environ", {})
     @patch("devx.ci.release.verify_tag_consistency", return_value=[])
     @patch("devx.ci.release.fetch_tags")
     @patch("devx.ci.release.has_user_facing_changes", return_value=True)
-    @patch("devx.ci.release.run_tests")
     @patch("devx.ci.release.create_and_push_tag", return_value=True)
     @patch("devx.ci.release.commit_release_changes", return_value=True)
     @patch("devx.ci.release.update_changelog")
@@ -1263,12 +1293,14 @@ class TestMain:
     @patch("devx.ci.release.get_latest_tag", return_value="v0.1.0")
     @patch("devx.ci.release.get_bumped_version", return_value="0.2.0")
     @patch("devx.ci.release.has_unreleased_changes", return_value=True)
+    @patch("devx.ci.release.update_doc_versions")
     @patch("devx.ci.release.time.sleep")
     @patch("devx.ci.release.run_cmd")
     def test_push_retry_succeeds_after_rebase_failure(
         self,
         mock_run_cmd: MagicMock,
         mock_sleep: MagicMock,
+        mock_update_docs: MagicMock,
         mock_has: MagicMock,
         mock_bumped: MagicMock,
         mock_latest: MagicMock,
@@ -1277,10 +1309,10 @@ class TestMain:
         mock_update_changelog: MagicMock,
         mock_commit: MagicMock,
         mock_tag: MagicMock,
-        mock_run_tests: MagicMock,
         mock_user: MagicMock,
         mock_ft: MagicMock,
         mock_vtc: MagicMock,
+        mock_run_tests: MagicMock,
     ) -> None:
         """Push should retry after rebase failure and succeed on second attempt."""
         ok = MagicMock(returncode=0, stdout="master\n", stderr="")
@@ -1297,11 +1329,11 @@ class TestMain:
         assert "Rebase attempt 1/3 failed" in result.output
         assert "Pushed release commit to master" in result.output
 
+    @patch("devx.ci.release.run_tests")
     @patch.dict("os.environ", {})
     @patch("devx.ci.release.verify_tag_consistency", return_value=[])
     @patch("devx.ci.release.fetch_tags")
     @patch("devx.ci.release.has_user_facing_changes", return_value=True)
-    @patch("devx.ci.release.run_tests")
     @patch("devx.ci.release.create_and_push_tag", return_value=True)
     @patch("devx.ci.release.commit_release_changes", return_value=True)
     @patch("devx.ci.release.update_changelog")
@@ -1310,12 +1342,14 @@ class TestMain:
     @patch("devx.ci.release.get_latest_tag", return_value="v0.1.0")
     @patch("devx.ci.release.get_bumped_version", return_value="0.2.0")
     @patch("devx.ci.release.has_unreleased_changes", return_value=True)
+    @patch("devx.ci.release.update_doc_versions")
     @patch("devx.ci.release.time.sleep")
     @patch("devx.ci.release.run_cmd")
     def test_push_fails_after_all_retries(
         self,
         mock_run_cmd: MagicMock,
         mock_sleep: MagicMock,
+        mock_update_docs: MagicMock,
         mock_has: MagicMock,
         mock_bumped: MagicMock,
         mock_latest: MagicMock,
@@ -1324,10 +1358,10 @@ class TestMain:
         mock_update_changelog: MagicMock,
         mock_commit: MagicMock,
         mock_tag: MagicMock,
-        mock_run_tests: MagicMock,
         mock_user: MagicMock,
         mock_ft: MagicMock,
         mock_vtc: MagicMock,
+        mock_run_tests: MagicMock,
     ) -> None:
         """Push should fail after 3 unsuccessful rebase attempts."""
         ok = MagicMock(returncode=0, stdout="master\n", stderr="")
@@ -1350,11 +1384,11 @@ class TestMain:
         assert result.exit_code != 0
         assert "Failed to push release commit after 3 attempts" in result.output
 
+    @patch("devx.ci.release.run_tests")
     @patch.dict("os.environ", {})
     @patch("devx.ci.release.verify_tag_consistency", return_value=[])
     @patch("devx.ci.release.fetch_tags")
     @patch("devx.ci.release.has_user_facing_changes", return_value=True)
-    @patch("devx.ci.release.run_tests")
     @patch("devx.ci.release.create_and_push_tag", return_value=True)
     @patch("devx.ci.release.commit_release_changes", return_value=True)
     @patch("devx.ci.release.update_changelog")
@@ -1363,12 +1397,14 @@ class TestMain:
     @patch("devx.ci.release.get_latest_tag", return_value="v0.1.0")
     @patch("devx.ci.release.get_bumped_version", return_value="0.2.0")
     @patch("devx.ci.release.has_unreleased_changes", return_value=True)
+    @patch("devx.ci.release.update_doc_versions")
     @patch("devx.ci.release.time.sleep")
     @patch("devx.ci.release.run_cmd")
     def test_push_retry_succeeds_after_push_failure(
         self,
         mock_run_cmd: MagicMock,
         mock_sleep: MagicMock,
+        mock_update_docs: MagicMock,
         mock_has: MagicMock,
         mock_bumped: MagicMock,
         mock_latest: MagicMock,
@@ -1377,10 +1413,10 @@ class TestMain:
         mock_update_changelog: MagicMock,
         mock_commit: MagicMock,
         mock_tag: MagicMock,
-        mock_run_tests: MagicMock,
         mock_user: MagicMock,
         mock_ft: MagicMock,
         mock_vtc: MagicMock,
+        mock_run_tests: MagicMock,
     ) -> None:
         """Push should retry after push rejection and succeed on second attempt."""
         ok = MagicMock(returncode=0, stdout="master\n", stderr="")
@@ -1397,6 +1433,7 @@ class TestMain:
         assert "Push attempt 1/3 failed" in result.output
         assert "Pushed release commit to master" in result.output
 
+    @patch("devx.ci.release.update_doc_versions")
     @patch.dict("os.environ", {})
     @patch("devx.ci.release.verify_tag_consistency", return_value=[])
     @patch("devx.ci.release.fetch_tags")
@@ -1414,6 +1451,7 @@ class TestMain:
         mock_user: MagicMock,
         mock_ft: MagicMock,
         mock_vtc: MagicMock,
+        mock_update_docs: MagicMock,
     ) -> None:
         """Release is skipped when git-cliff doesn't bump the version."""
         mock_run_cmd.return_value = MagicMock(returncode=0, stdout="master\n", stderr="")
@@ -1435,10 +1473,12 @@ class TestMain:
     @patch("devx.ci.release.get_latest_tag", return_value="v0.1.0")
     @patch("devx.ci.release.get_bumped_version", return_value="0.2.0")
     @patch("devx.ci.release.has_unreleased_changes", return_value=True)
+    @patch("devx.ci.release.update_doc_versions")
     @patch("devx.ci.release.run_cmd")
     def test_full_flow_skip_tests(
         self,
         mock_run_cmd: MagicMock,
+        mock_update_docs: MagicMock,
         mock_has: MagicMock,
         mock_bumped: MagicMock,
         mock_latest: MagicMock,
@@ -1473,10 +1513,12 @@ class TestMain:
     @patch("devx.ci.release.get_latest_tag", return_value="v0.1.0")
     @patch("devx.ci.release.get_bumped_version", return_value="0.2.0")
     @patch("devx.ci.release.has_unreleased_changes", return_value=True)
+    @patch("devx.ci.release.update_doc_versions")
     @patch("devx.ci.release.run_cmd")
     def test_tests_fail_aborts_before_tag(
         self,
         mock_run_cmd: MagicMock,
+        mock_update_docs: MagicMock,
         mock_has: MagicMock,
         mock_bumped: MagicMock,
         mock_latest: MagicMock,
@@ -1517,10 +1559,12 @@ class TestMain:
     @patch("devx.ci.release.get_latest_tag", return_value="v0.1.0")
     @patch("devx.ci.release.get_bumped_version", return_value="0.2.0")
     @patch("devx.ci.release.has_unreleased_changes", return_value=True)
+    @patch("devx.ci.release.update_doc_versions")
     @patch("devx.ci.release.run_cmd")
     def test_lint_fail_aborts_before_tag(
         self,
         mock_run_cmd: MagicMock,
+        mock_update_docs: MagicMock,
         mock_has: MagicMock,
         mock_bumped: MagicMock,
         mock_latest: MagicMock,
@@ -1548,6 +1592,8 @@ class TestMain:
         mock_commit.assert_not_called()
         mock_tag.assert_not_called()
 
+    @patch("devx.ci.release.has_user_facing_changes", return_value=False)
+    @patch("devx.ci.release.update_doc_versions")
     @patch.dict("os.environ", {})
     @patch("devx.ci.release.get_changelog_versions", return_value=[])
     @patch("devx.ci.release.get_init_version", return_value="0.1.0")
@@ -1561,6 +1607,8 @@ class TestMain:
         mock_tags: MagicMock,
         mock_iv: MagicMock,
         mock_cv: MagicMock,
+        mock_update_docs: MagicMock,
+        mock_ufc: MagicMock,
     ) -> None:
         """--verify checks alignment and exits without releasing."""
         mock_run_cmd.return_value = MagicMock(returncode=0, stdout="", stderr="")
@@ -1569,12 +1617,19 @@ class TestMain:
         assert result.exit_code == 0
         assert "Release Alignment Verification" in result.output
 
+    @patch("devx.ci.release.has_user_facing_changes", return_value=False)
+    @patch("devx.ci.release.update_doc_versions")
     @patch.dict("os.environ", {})
     @patch("devx.ci.release.verify_tag_consistency", return_value=["  v0.1.0 → bad"])
     @patch("devx.ci.release.fetch_tags")
     @patch("devx.ci.release.run_cmd")
     def test_preflight_tag_consistency_fails(
-        self, mock_run_cmd: MagicMock, mock_ft: MagicMock, mock_vtc: MagicMock
+        self,
+        mock_run_cmd: MagicMock,
+        mock_ft: MagicMock,
+        mock_vtc: MagicMock,
+        mock_update_docs: MagicMock,
+        mock_ufc: MagicMock,
     ) -> None:
         """Pre-flight tag consistency check aborts if tags are misaligned."""
         mock_run_cmd.return_value = MagicMock(returncode=0, stdout="master\n", stderr="")

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)
@@ -312,7 +355,13 @@ class TestMain:
         assert result.exit_code == 0
         mock_tea.assert_not_called()
 
-    def test_main_missing_bin_dir(self) -> None:
+    @patch("devx.tools.setup._run")
+    @patch("devx.tools.setup._configure_tea_login")
+    @patch("devx.tools.setup._install_python_deps")
+    @patch("devx.tools.setup._verify")
+    def test_main_missing_bin_dir(
+        self, mock_tea: MagicMock, mock_deps: MagicMock, mock_verify: MagicMock, mock_run: MagicMock
+    ) -> None:
         runner = CliRunner()
         result = runner.invoke(main, ["--bin", "/nonexistent/path"])
         assert result.exit_code != 0

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 "."
@@ -185,12 +186,14 @@ class TestFallbackToSetupCi:
 
 
 class TestCli:
+    @patch("devx.tools.setup_image._fallback_to_setup_ci")
     @patch("devx.tools.setup_image._install_in_image")
     @patch("devx.tools.setup_image.Path")
     def test_cli_with_opt_venv_present(
         self,
         mock_path: MagicMock,
         mock_install: MagicMock,
+        mock_fallback: MagicMock,
     ) -> None:
         mock_path.return_value.is_dir.return_value = True
         runner = CliRunner()
@@ -198,12 +201,14 @@ class TestCli:
         assert result.exit_code == 0
         mock_install.assert_called_once()
 
+    @patch("devx.tools.setup_image._install_in_image")
     @patch("devx.tools.setup_image._fallback_to_setup_ci")
     @patch("devx.tools.setup_image.Path")
     def test_cli_falls_back_when_no_opt_venv(
         self,
         mock_path: MagicMock,
         mock_fallback: MagicMock,
+        mock_install: MagicMock,
     ) -> None:
         mock_path.return_value.is_dir.return_value = False
         runner = CliRunner()
@@ -211,12 +216,14 @@ class TestCli:
         assert result.exit_code == 0
         mock_fallback.assert_called_once()
 
+    @patch("devx.tools.setup_image._fallback_to_setup_ci")
     @patch("devx.tools.setup_image._install_in_image")
     @patch("devx.tools.setup_image.Path")
     def test_cli_default_values(
         self,
         mock_path: MagicMock,
         mock_install: MagicMock,
+        mock_fallback: MagicMock,
     ) -> None:
         mock_path.return_value.is_dir.return_value = True
         runner = CliRunner()
@@ -229,12 +236,14 @@ class TestCli:
         assert call_args[3] == "git.oblachno.oblachno.fyi"
         assert call_args[4] == "oblachno-oss"
 
+    @patch("devx.tools.setup_image._fallback_to_setup_ci")
     @patch("devx.tools.setup_image._install_in_image")
     @patch("devx.tools.setup_image.Path")
     def test_cli_custom_venv_and_gitea(
         self,
         mock_path: MagicMock,
         mock_install: MagicMock,
+        mock_fallback: MagicMock,
     ) -> None:
         mock_path.return_value.is_dir.return_value = True
         runner = CliRunner()
@@ -248,12 +257,14 @@ class TestCli:
         assert call_args[3] == "gitea.io"
         assert call_args[4] == "myorg"
 
+    @patch("devx.tools.setup_image._fallback_to_setup_ci")
     @patch("devx.tools.setup_image._install_in_image")
     @patch("devx.tools.setup_image.Path")
     def test_cli_with_extras(
         self,
         mock_path: MagicMock,
         mock_install: MagicMock,
+        mock_fallback: MagicMock,
     ) -> None:
         mock_path.return_value.is_dir.return_value = True
         runner = CliRunner()