release: v0.49.2 [skip ci]

Co-authored-by: oblachno Admin <admin@oblachno.oblachno.fyi>

.gitea/workflows/build-images.yml

@@ -32,6 +32,7 @@ concurrency:
 jobs:
   build-and-push:
     runs-on: docker
+    container: git.oblachno.oblachno.fyi/oblachno-oss/runner-images/ci-full:latest
     timeout-minutes: 30
     outputs:
       is-release: ${{ steps.check.outputs.is-release }}
@@ -115,6 +116,7 @@ jobs:
     needs: [build-and-push]
     if: always() && needs.build-and-push.result == 'success'
     runs-on: docker
+    container: git.oblachno.oblachno.fyi/oblachno-oss/runner-images/ci-base:latest
     timeout-minutes: 10
     steps:
       - uses: actions/checkout@v4

.gitea/workflows/ci.yml

@@ -46,7 +46,7 @@ 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"

.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,])'
-  - (?:^|\s)I,\s
+  - "\\bI'm\\b"
-  - \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). `$` is included so the abbreviation is still
+# caught at the end of a heading, table cell, or block, which accounted for 8
+# of 10 occurrences on a 950-file corpus.
 swap:
-  '\b(?:eg|e\.g\.)(?=[\s,;])': for example
+  '\b(?:eg|e\.g\.)(?=[\s,;]|$)': for example
-  '\b(?:ie|i\.e\.)(?=[\s,;])': that is
+  '\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+(?:B|kB|MB|GB|TB)\b'
-  - \b\d+(?:ns|ms|s|min|h|d)
+  - '\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 +121,13 @@ 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
 │   └── _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
@@ -124,7 +135,9 @@ 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)
@@ -310,6 +323,20 @@ 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 +2,92 @@
 
 All notable changes to this project will be documented in this file.
 
+## [0.49.2] - 2026-08-07
+
+### Bug Fixes
+
+- Add fallback URL for tea download
+
+## [0.49.1] - 2026-08-07
+
+### Bug Fixes
+
+- Add container images to build-images workflow
+
+## [0.49.0] - 2026-08-07
+
+### Features
+
+- Add --include-roles and --exclude-roles to distribute_molecule
+## [0.48.0] - 2026-07-22
+
+### Features
+
+- Extract reusable components from infra and grm into devx
+
+## [0.48.0] - 2026-07-22
+
+### Features
+
+- Extract reusable components from infra and grm into devx
+
+## [Unreleased]
+
+### Features
+
+- Extract reusable components from infra and grm into devx:
+  - `devx.utils.ui.say()` — unified click.echo + logging output
+  - `devx.utils.api.APIClient` — base HTTP API client class with retry logic
+  - `devx.utils.jinja` — Jinja2 environment helpers with Ansible-compatible filters
+  - `devx.i18n.configure_i18n()` — configurable `lang_env_var` and `translations_path_env_var`
+  - `devx.ci.cancel_superseded_runs` — cancel in-flight CI runs for the same PR branch
+  - `devx.ci.check_workflow_artifact_deps` — verify artifact download jobs depend on upload jobs
+  - `devx.ci.check_workflow_tofu_init` — verify tofu-state jobs have a tofu-init step
+  - `devx.tools.check_docker_init` — check Docker Compose services with healthchecks have init: true
+  - `devx.tools.check_ansible_set_fact_to_json` — check set_fact tasks don't misuse to_json
+  - `devx.tools.check_alert_rules` — validate Prometheus alert rules with promtool
+- Add `jinja2` and `pyyaml` as core dependencies (previously in `deploy` extras only)
+- Register new CLI commands: `devx ci cancel-superseded-runs`, `devx ci check-workflow-artifact-deps`,
+  `devx ci check-workflow-tofu-init`, `devx tools check-docker-init`,
+  `devx tools check-ansible-set-fact-to-json`, `devx tools check-alert-rules`
+- Add Makefile targets for all new check tools
+
+## [0.47.3] - 2026-07-17
+
+### Bug Fixes
+
+- 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

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
@@ -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/6ee532d4c43005a77f1e3dd0e62b81fe6262552b/coverage.svg)](https://git.oblachno.oblachno.fyi/oblachno-oss/devx/actions)
+[![Coverage](https://git.oblachno.oblachno.fyi/oblachno-oss/devx/raw/commit/3f33ebe6e955847867ce2ea7b9550ee549a9f966/coverage.svg)](https://git.oblachno.oblachno.fyi/oblachno-oss/devx/actions)
-[![Tests](https://git.oblachno.oblachno.fyi/oblachno-oss/devx/raw/commit/6ee532d4c43005a77f1e3dd0e62b81fe6262552b/tests.svg)](https://git.oblachno.oblachno.fyi/oblachno-oss/devx/actions)
+[![Tests](https://git.oblachno.oblachno.fyi/oblachno-oss/devx/raw/commit/3f33ebe6e955847867ce2ea7b9550ee549a9f966/tests.svg)](https://git.oblachno.oblachno.fyi/oblachno-oss/devx/actions)
-[![Docs](https://git.oblachno.oblachno.fyi/oblachno-oss/devx/raw/commit/6ee532d4c43005a77f1e3dd0e62b81fe6262552b/docs.svg)](https://git.oblachno.oblachno.fyi/oblachno-oss/devx/wiki)
+[![Docs](https://git.oblachno.oblachno.fyi/oblachno-oss/devx/raw/commit/3f33ebe6e955847867ce2ea7b9550ee549a9f966/docs.svg)](https://git.oblachno.oblachno.fyi/oblachno-oss/devx/wiki)
-[![Code Quality](https://git.oblachno.oblachno.fyi/oblachno-oss/devx/raw/commit/6ee532d4c43005a77f1e3dd0e62b81fe6262552b/quality.svg)](https://git.oblachno.oblachno.fyi/oblachno-oss/devx/actions)
+[![Code Quality](https://git.oblachno.oblachno.fyi/oblachno-oss/devx/raw/commit/3f33ebe6e955847867ce2ea7b9550ee549a9f966/quality.svg)](https://git.oblachno.oblachno.fyi/oblachno-oss/devx/actions)
-[![Version](https://git.oblachno.oblachno.fyi/oblachno-oss/devx/raw/commit/6ee532d4c43005a77f1e3dd0e62b81fe6262552b/version.svg)](https://git.oblachno.oblachno.fyi/oblachno-oss/devx/releases)
+[![Version](https://git.oblachno.oblachno.fyi/oblachno-oss/devx/raw/commit/3f33ebe6e955847867ce2ea7b9550ee549a9f966/version.svg)](https://git.oblachno.oblachno.fyi/oblachno-oss/devx/releases)
-[![Python](https://git.oblachno.oblachno.fyi/oblachno-oss/devx/raw/commit/6ee532d4c43005a77f1e3dd0e62b81fe6262552b/python.svg)](https://www.python.org/downloads/)
+[![Python](https://git.oblachno.oblachno.fyi/oblachno-oss/devx/raw/commit/3f33ebe6e955847867ce2ea7b9550ee549a9f966/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>=0.45.0",
+    "devx>=0.49.2",
 ]
 
 [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==0.45.0"`) or use a version constraint
+> `dependencies` (for example, `"devx==0.49.2"`) or use a version constraint
-> (for example, `"devx>=0.45.0,<0.46"`).
+> (for example, `"devx>=0.49.2,<0.50"`).
 
 ### Optional extras
 

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)
+# Install git-cliff (changelog generator for release job), OpenTofu (for infra deploy jobs),
-RUN python3 -m devx.tools.install_tools --tool git-cliff --tool tofu
+# 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/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/6ee532d4c43005a77f1e3dd0e62b81fe6262552b/coverage.svg)](https://git.oblachno.oblachno.fyi/oblachno-oss/devx/actions)
+[![Coverage](https://git.oblachno.oblachno.fyi/oblachno-oss/devx/raw/commit/3f33ebe6e955847867ce2ea7b9550ee549a9f966/coverage.svg)](https://git.oblachno.oblachno.fyi/oblachno-oss/devx/actions)
-[![Tests](https://git.oblachno.oblachno.fyi/oblachno-oss/devx/raw/commit/6ee532d4c43005a77f1e3dd0e62b81fe6262552b/tests.svg)](https://git.oblachno.oblachno.fyi/oblachno-oss/devx/actions)
+[![Tests](https://git.oblachno.oblachno.fyi/oblachno-oss/devx/raw/commit/3f33ebe6e955847867ce2ea7b9550ee549a9f966/tests.svg)](https://git.oblachno.oblachno.fyi/oblachno-oss/devx/actions)
-[![Docs](https://git.oblachno.oblachno.fyi/oblachno-oss/devx/raw/commit/6ee532d4c43005a77f1e3dd0e62b81fe6262552b/docs.svg)](https://git.oblachno.oblachno.fyi/oblachno-oss/devx/wiki)
+[![Docs](https://git.oblachno.oblachno.fyi/oblachno-oss/devx/raw/commit/3f33ebe6e955847867ce2ea7b9550ee549a9f966/docs.svg)](https://git.oblachno.oblachno.fyi/oblachno-oss/devx/wiki)
-[![Code Quality](https://git.oblachno.oblachno.fyi/oblachno-oss/devx/raw/commit/6ee532d4c43005a77f1e3dd0e62b81fe6262552b/quality.svg)](https://git.oblachno.oblachno.fyi/oblachno-oss/devx/actions)
+[![Code Quality](https://git.oblachno.oblachno.fyi/oblachno-oss/devx/raw/commit/3f33ebe6e955847867ce2ea7b9550ee549a9f966/quality.svg)](https://git.oblachno.oblachno.fyi/oblachno-oss/devx/actions)
-[![Version](https://git.oblachno.oblachno.fyi/oblachno-oss/devx/raw/commit/6ee532d4c43005a77f1e3dd0e62b81fe6262552b/version.svg)](https://git.oblachno.oblachno.fyi/oblachno-oss/devx/releases)
+[![Version](https://git.oblachno.oblachno.fyi/oblachno-oss/devx/raw/commit/3f33ebe6e955847867ce2ea7b9550ee549a9f966/version.svg)](https://git.oblachno.oblachno.fyi/oblachno-oss/devx/releases)
-[![Python](https://git.oblachno.oblachno.fyi/oblachno-oss/devx/raw/commit/6ee532d4c43005a77f1e3dd0e62b81fe6262552b/python.svg)](https://www.python.org/downloads/)
+[![Python](https://git.oblachno.oblachno.fyi/oblachno-oss/devx/raw/commit/3f33ebe6e955847867ce2ea7b9550ee549a9f966/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>=0.45.0",
+    "devx>=0.49.2",
 ]
 
 [tool.pip]
 extra-index-url = "https://git.oblachno.oblachno.fyi/api/packages/oblachno-oss/pypi/simple"
 ```
 
-Pin a specific version if needed: `"devx==0.45.0"` or `"devx>=0.45.0,<0.46"`.
+Pin a specific version if needed: `"devx==0.49.2"` or `"devx>=0.49.2,<0.50"`.
 
 ### Optional extras
 

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

@@ -87,11 +87,11 @@ 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 +109,7 @@ 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 +171,7 @@ 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 +288,7 @@ 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.
 
@@ -330,7 +330,7 @@ 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`
 

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.
@@ -369,7 +419,7 @@ devx tools check-test-isolation --src-dir src/
 
 Pytest plugin options (automatic when devx is installed):
 
-- `--no-test-isolation` — disable static analysis and runtime subprocess audit
+- `--no-test-isolation` — turn off static analysis and runtime subprocess audit
 - `--test-isolation-max-loop N` — max iterations per loop (default: 100)
 
 ### `devx tools configure-repo`
@@ -414,7 +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`
@@ -488,6 +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]`).

docs/user/getting-started.md

@@ -48,12 +48,12 @@ Add devx to your `pyproject.toml`:
 ```toml
 [project]
 dependencies = [
-    "devx>=0.45.0",
+    "devx>=0.49.2",
 ]
 
 [project.optional-dependencies]
 dev = [
-    "devx>=0.45.0",
+    "devx>=0.49.2",
 ]
 ```
 

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]
@@ -66,8 +68,6 @@ deploy = [
     "ansible-core==2.21.1",
     "boto3==1.43.37",
     "docker==7.1.0",
-    "jinja2==3.1.6",
-    "pyyaml==6.0.3",
     "cryptography==49.0.0",
 ]
 # Full dev environment (local development)

src/devx/__init__.py

@@ -1,3 +1,3 @@
 """devx — reusable development and CI/CD tools for oblachno-oss projects."""
 
-__version__ = "0.45.0"
+__version__ = "0.49.2"

src/devx/ci/cancel_superseded_runs.py

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

src/devx/ci/check_workflow_artifact_deps.py

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

src/devx/ci/check_workflow_tofu_init.py

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

src/devx/ci/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:
+    _create_release_with_retry(tea, repo, tag, release_body)
-        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
 
     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/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])."""

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
+            return retry_decorator(_execute)()
-                cmd,
+        except _TransientTeaError as e:
-                capture_output=True,
+            raise TeaCLIError(str(e)) from e
-                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()
 
     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."""
+    """Load project-specific translations from the configured env var if set."""
-    path = os.getenv("DEVX_TRANSLATIONS_PATH")
+    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.
+    Translation is opt-in via the configured language environment variable
-    If unset, English is always returned regardless of system locale.
+    (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/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_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_test_isolation.py

@@ -25,6 +25,25 @@ This module is used in two ways:
    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
@@ -60,6 +79,7 @@ from pathlib import Path
 
 import click
 
+from devx.config import _load_pyproject_devx
 from devx.i18n import _
 
 # ── Configuration ─────────────────────────────────────────────────────────────
@@ -71,7 +91,7 @@ DEFAULT_MAX_LOOP_ITERATIONS = 100
 # 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.
-HEAVY_MODULE_IMPORTS: dict[str, float] = {
+_DEFAULT_HEAVY_MODULE_IMPORTS: dict[str, float] = {
     "httpx": 80.0,
     "aiohttp": 120.0,
     "docker": 90.0,
@@ -96,7 +116,7 @@ HEAVY_MODULE_IMPORTS: dict[str, float] = {
 # 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",
@@ -105,7 +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",
@@ -124,7 +144,7 @@ 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"},
@@ -133,7 +153,7 @@ HELPER_INTERNAL_CALLS: dict[str, set[str]] = {
 # 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.
-IO_INTERNAL_CALLS: dict[str, set[str]] = {
+_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": {
@@ -150,6 +170,76 @@ IO_INTERNAL_CALLS: dict[str, set[str]] = {
     "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")
 

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 +65,28 @@ def _ensure_target_dir() -> Path:
 
 
 def _download(url: str, dest: Path) -> None:
-    """Download a file from ``url`` to ``dest``."""
+    """Download a file from ``url`` to ``dest`` with a 60s timeout."""
-    urllib.request.urlretrieve(url, dest)  # nosec B310
+    with urllib.request.urlopen(url, timeout=60) as resp, open(dest, "wb") as f:  # nosec B310
+        shutil.copyfileobj(resp, f)
+
+
+def _download_with_fallback(urls: list[str], binary_name: str) -> Path:
+    """Try downloading a binary from a list of URLs, falling back on failure.
+
+    Returns the path to the installed binary. Raises if all URLs fail.
+    """
+    target_dir = _ensure_target_dir()
+    dest = target_dir / binary_name
+    errors: list[str] = []
+    for url in urls:
+        try:
+            _download(url, dest)
+            dest.chmod(0o755)
+            return dest
+        except Exception as exc:  # noqa: BLE001
+            errors.append(f"{url}: {exc}")
+            click.echo(f"  {binary_name}: retrying — {exc}")
+    raise click.ClickException(f"Failed to download {binary_name} from all URLs: {'; '.join(errors)}")
 
 
 def _download_and_extract_tarball(url: str, binary_name: str) -> Path:
@@ -160,8 +183,13 @@ 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}"
+    # dl.gitea.com is the primary CDN, but it can return 403 from some networks.
-    dest = _download_binary(url, "tea")
+    # 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 +240,26 @@ 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 +278,8 @@ 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/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"``)
+This module provides two categories of utilities:
-rather than native JSON booleans.  The Mattermost ``/api/v4/config/client``
+
-endpoint is a notable example.  These helpers handle both string and
+1. **Response helpers** — :func:`is_truthy` and :func:`is_falsy` handle
-boolean responses safely.
+   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_check_test_isolation.py

@@ -8,14 +8,19 @@ 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,
@@ -1667,3 +1672,110 @@ class TestIsIntegrationTest:
         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_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_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_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_tools.py

@@ -47,13 +47,25 @@ 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]:
+        class _FakeResponse:
-            Path(path).write_bytes(b"data")
+            def __init__(self) -> None:
-            return str(path), 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()
         assert dest.read_bytes() == b"data"
 
 
@@ -221,6 +233,33 @@ 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 +336,47 @@ 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 +421,11 @@ 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 +444,7 @@ 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_publish.py

@@ -387,8 +387,10 @@ class TestMain:
     @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_sleep: MagicMock,
         mock_build: MagicMock,
         mock_publish: MagicMock,
         mock_tea_cls: MagicMock,
@@ -397,6 +399,7 @@ class TestMain:
         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")
@@ -405,6 +408,8 @@ 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")
@@ -496,8 +501,10 @@ class TestMain:
     @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,
@@ -507,7 +514,7 @@ class TestMain:
         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")
@@ -516,6 +523,8 @@ 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")
@@ -526,8 +535,10 @@ class TestMain:
     @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,
@@ -537,7 +548,7 @@ class TestMain:
         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")
@@ -546,6 +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:

tests/unit/test_tools_check_alert_rules.py

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

tests/unit/test_tools_check_ansible_set_fact_to_json.py

@@ -0,0 +1,346 @@
+"""Unit tests for devx.tools.check_ansible_set_fact_to_json."""
+
+from __future__ import annotations
+
+import textwrap
+from pathlib import Path
+
+from click.testing import CliRunner
+
+from devx.tools.check_ansible_set_fact_to_json import (
+    _check_file,
+    _check_task,
+    _check_task_list,
+    _find_task_files,
+    main,
+)
+
+
+class TestFindTaskFiles:
+    def test_single_file(self, tmp_path: Path):
+        f = tmp_path / "tasks.yml"
+        f.write_text("tasks: []")
+        assert _find_task_files(f) == [f]
+
+    def test_directory_recursive(self, tmp_path: Path):
+        (tmp_path / "sub").mkdir()
+        f1 = tmp_path / "a.yml"
+        f2 = tmp_path / "sub" / "b.yml"
+        f1.write_text("tasks: []")
+        f2.write_text("tasks: []")
+        result = _find_task_files(tmp_path)
+        assert f1 in result
+        assert f2 in result
+
+    def test_nonexistent_path(self, tmp_path: Path):
+        assert _find_task_files(tmp_path / "nonexistent") == []
+
+    def test_non_yaml_file_skipped(self, tmp_path: Path):
+        f = tmp_path / "readme.txt"
+        f.write_text("not yaml")
+        assert _find_task_files(f) == []
+
+
+class TestCheckTask:
+    def test_set_fact_with_to_json_flagged(self, tmp_path: Path):
+        task = {"name": "Set targets", "set_fact": {"customer_hosts": "{{ targets | to_json }}"}}
+        errors: list[str] = []
+        _check_task(task, tmp_path / "test.yml", errors, tmp_path)
+        assert len(errors) == 1
+        assert "customer_hosts" in errors[0]
+        assert "to_json" in errors[0]
+
+    def test_set_fact_without_to_json_ok(self, tmp_path: Path):
+        task = {"name": "Set targets", "set_fact": {"customer_hosts": "{{ targets }}"}}
+        errors: list[str] = []
+        _check_task(task, tmp_path / "test.yml", errors, tmp_path)
+        assert errors == []
+
+    def test_ansible_builtin_set_fact(self, tmp_path: Path):
+        task = {"name": "Set targets", "ansible.builtin.set_fact": {"my_list": "{{ items | to_nice_json }}"}}
+        errors: list[str] = []
+        _check_task(task, tmp_path / "test.yml", errors, tmp_path)
+        assert len(errors) == 1
+        assert "to_nice_json" in errors[0]
+
+    def test_non_set_fact_task_ignored(self, tmp_path: Path):
+        task = {"name": "Render config", "copy": {"content": "{{ data | to_json }}"}}
+        errors: list[str] = []
+        _check_task(task, tmp_path / "test.yml", errors, tmp_path)
+        assert errors == []
+
+    def test_cacheable_key_ignored(self, tmp_path: Path):
+        task = {"name": "Set fact", "set_fact": {"my_var": "{{ value }}", "cacheable": True}}
+        errors: list[str] = []
+        _check_task(task, tmp_path / "test.yml", errors, tmp_path)
+        assert errors == []
+
+    def test_unnamed_task(self, tmp_path: Path):
+        task = {"set_fact": {"my_var": "{{ value | to_json }}"}}
+        errors: list[str] = []
+        _check_task(task, tmp_path / "test.yml", errors, tmp_path)
+        assert len(errors) == 1
+        assert "(unnamed)" in errors[0]
+
+    def test_set_fact_not_dict_ignored(self, tmp_path: Path):
+        task = {"set_fact": "not a dict"}
+        errors: list[str] = []
+        _check_task(task, tmp_path / "test.yml", errors, tmp_path)
+        assert errors == []
+
+    def test_to_json_no_spaces(self, tmp_path: Path):
+        task = {"set_fact": {"my_var": "{{ items|to_json }}"}}
+        errors: list[str] = []
+        _check_task(task, tmp_path / "test.yml", errors, tmp_path)
+        assert len(errors) == 1
+
+
+class TestCheckTaskList:
+    def test_block_tasks_checked(self, tmp_path: Path):
+        tasks = [{"name": "Block", "block": [{"name": "Set in block", "set_fact": {"x": "{{ y | to_json }}"}}]}]
+        errors: list[str] = []
+        _check_task_list(tasks, tmp_path / "test.yml", errors, tmp_path)
+        assert len(errors) == 1
+        assert "x" in errors[0]
+
+    def test_non_dict_task_ignored(self, tmp_path: Path):
+        tasks = ["just a string", 42, None]
+        errors: list[str] = []
+        _check_task_list(tasks, tmp_path / "test.yml", errors, tmp_path)
+        assert errors == []
+
+
+class TestCheckFile:
+    def test_playbook_with_set_fact_to_json(self, tmp_path: Path):
+        content = textwrap.dedent("""
+            - name: Deploy
+              hosts: all
+              tasks:
+                - name: Set targets
+                  ansible.builtin.set_fact:
+                    customer_hosts: "{{ targets | to_json }}"
+        """).strip()
+        f = tmp_path / "playbook.yml"
+        f.write_text(content)
+        errors = _check_file(f, tmp_path)
+        assert len(errors) == 1
+        assert "customer_hosts" in errors[0]
+
+    def test_playbook_without_set_fact(self, tmp_path: Path):
+        content = textwrap.dedent("""
+            - name: Deploy
+              hosts: all
+              tasks:
+                - name: Debug
+                  ansible.builtin.debug:
+                    msg: "hello"
+        """).strip()
+        f = tmp_path / "playbook.yml"
+        f.write_text(content)
+        assert _check_file(f, tmp_path) == []
+
+    def test_role_tasks_file(self, tmp_path: Path):
+        content = textwrap.dedent("""
+            - name: Set config
+              set_fact:
+                my_data: "{{ data | to_json }}"
+            - name: Copy config
+              copy:
+                content: "{{ config | to_json }}"
+                dest: /etc/config.json
+        """).strip()
+        f = tmp_path / "main.yml"
+        f.write_text(content)
+        errors = _check_file(f, tmp_path)
+        assert len(errors) == 1
+        assert "my_data" in errors[0]
+
+    def test_pre_tasks_and_post_tasks(self, tmp_path: Path):
+        content = textwrap.dedent("""
+            - name: Play
+              hosts: all
+              pre_tasks:
+                - name: Pre set
+                  set_fact:
+                    pre_var: "{{ x | to_json }}"
+              post_tasks:
+                - name: Post set
+                  set_fact:
+                    post_var: "{{ y | to_json }}"
+        """).strip()
+        f = tmp_path / "playbook.yml"
+        f.write_text(content)
+        errors = _check_file(f, tmp_path)
+        assert len(errors) == 2
+
+    def test_handlers_checked(self, tmp_path: Path):
+        content = textwrap.dedent("""
+            - name: Play
+              hosts: all
+              handlers:
+                - name: Restart service
+                  set_fact:
+                    restart_data: "{{ data | to_json }}"
+        """).strip()
+        f = tmp_path / "playbook.yml"
+        f.write_text(content)
+        errors = _check_file(f, tmp_path)
+        assert len(errors) == 1
+
+    def test_invalid_yaml(self, tmp_path: Path):
+        f = tmp_path / "bad.yml"
+        f.write_text("tasks: [invalid: {")
+        errors = _check_file(f, tmp_path)
+        assert len(errors) == 1
+        assert "cannot parse YAML" in errors[0]
+
+    def test_non_dict_doc_skipped(self, tmp_path: Path):
+        f = tmp_path / "list.yml"
+        f.write_text("- just\n- a\n- list\n")
+        assert _check_file(f, tmp_path) == []
+
+    def test_multi_doc_yaml(self, tmp_path: Path):
+        content = textwrap.dedent("""
+            ---
+            - name: Play 1
+              hosts: all
+              tasks:
+                - name: Set in play 1
+                  set_fact:
+                    var1: "{{ x | to_json }}"
+            ---
+            - name: Play 2
+              hosts: all
+              tasks:
+                - name: Set in play 2
+                  set_fact:
+                    var2: "{{ y }}"
+        """).strip()
+        f = tmp_path / "multi.yml"
+        f.write_text(content)
+        errors = _check_file(f, tmp_path)
+        assert len(errors) == 1
+        assert "var1" in errors[0]
+
+    def test_dict_doc_role_tasks_file(self, tmp_path: Path):
+        content = textwrap.dedent("""
+            tasks:
+              - name: Set var
+                set_fact:
+                  my_var: "{{ value | to_json }}"
+        """).strip()
+        f = tmp_path / "main.yml"
+        f.write_text(content)
+        errors = _check_file(f, tmp_path)
+        assert len(errors) == 1
+        assert "my_var" in errors[0]
+
+    def test_play_with_roles_key(self, tmp_path: Path):
+        content = textwrap.dedent("""
+            - name: Play
+              hosts: all
+              roles:
+                - role: my_role
+                  tasks:
+                    - name: Set in role
+                      set_fact:
+                        role_var: "{{ x | to_json }}"
+        """).strip()
+        f = tmp_path / "playbook.yml"
+        f.write_text(content)
+        errors = _check_file(f, tmp_path)
+        assert len(errors) == 1
+        assert "role_var" in errors[0]
+
+    def test_bare_task_in_list_with_block(self, tmp_path: Path):
+        content = textwrap.dedent("""
+            - name: Outer task
+              set_fact:
+                outer: "{{ x | to_json }}"
+            - name: Block
+              block:
+                - name: Inner task
+                  set_fact:
+                    inner: "{{ y | to_json }}"
+        """).strip()
+        f = tmp_path / "tasks.yml"
+        f.write_text(content)
+        errors = _check_file(f, tmp_path)
+        assert len(errors) == 2
+
+
+class TestMain:
+    def test_passes_when_clean(self, tmp_path: Path):
+        content = textwrap.dedent("""
+            - name: Play
+              hosts: all
+              tasks:
+                - name: Set var
+                  set_fact:
+                    my_var: "{{ value }}"
+        """).strip()
+        f = tmp_path / "playbook.yml"
+        f.write_text(content)
+        runner = CliRunner()
+        result = runner.invoke(main, ["--path", str(f)])
+        assert result.exit_code == 0
+        assert "OK" in result.output
+
+    def test_fails_when_to_json_found(self, tmp_path: Path):
+        content = textwrap.dedent("""
+            - name: Play
+              hosts: all
+              tasks:
+                - name: Set var
+                  set_fact:
+                    my_var: "{{ value | to_json }}"
+        """).strip()
+        f = tmp_path / "playbook.yml"
+        f.write_text(content)
+        runner = CliRunner()
+        result = runner.invoke(main, ["--path", str(f)])
+        assert result.exit_code == 1
+        assert "FAIL" in result.output
+        assert "my_var" in result.output
+
+    def test_directory_scan(self, tmp_path: Path):
+        (tmp_path / "good.yml").write_text(
+            textwrap.dedent("""
+                - name: Play
+                  hosts: all
+                  tasks:
+                    - name: Set
+                      set_fact:
+                        x: "{{ y }}"
+            """).strip()
+        )
+        (tmp_path / "bad.yml").write_text(
+            textwrap.dedent("""
+                - name: Play
+                  hosts: all
+                  tasks:
+                    - name: Set
+                      set_fact:
+                        x: "{{ y | to_json }}"
+            """).strip()
+        )
+        runner = CliRunner()
+        result = runner.invoke(main, ["--path", str(tmp_path)])
+        assert result.exit_code == 1
+        assert "bad.yml" in result.output
+
+    def test_custom_ansible_dirs(self, tmp_path: Path):
+        (tmp_path / "playbook.yml").write_text(
+            textwrap.dedent("""
+                - name: Play
+                  hosts: all
+                  tasks:
+                    - name: Set
+                      set_fact:
+                        x: "{{ y | to_json }}"
+            """).strip()
+        )
+        runner = CliRunner()
+        result = runner.invoke(main, ["--ansible-dir", str(tmp_path)])
+        assert result.exit_code == 1
+        assert "playbook.yml" in result.output

tests/unit/test_tools_check_docker_init.py

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

tests/unit/test_utils_api.py

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

tests/unit/test_utils_jinja.py

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

tests/unit/test_utils_ui.py

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