chore: update badge URLs to commit 918ffe7d [skip ci]

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

.gitea/workflows/ci.yml

@@ -160,10 +160,10 @@ jobs:
     container: git.oblachno.oblachno.fyi/oblachno-oss/runner-images/ci-full:latest
     timeout-minutes: 15
     strategy:
-      fail-fast: true
-      max-parallel: 6
+      fail-fast: false
+      max-parallel: 4
       matrix:
-        runner-index: [1, 2, 3, 4, 5, 6]
+        runner-index: [1, 2, 3, 4]
     steps:
       - uses: actions/checkout@v4
       - name: Set up environment
@@ -178,25 +178,34 @@ jobs:
       - name: Discover assigned test pairs
         env:
           RUNNER_INDEX: ${{ matrix.runner-index }}
-          MAX_RUNNERS: 6
+          MAX_RUNNERS: 4
         run: |
           . .venv/bin/activate 2>/dev/null || true
           python3 -m devx.molecule.distribute_molecule \
             --runner-index "$RUNNER_INDEX" \
             --max-runners "$MAX_RUNNERS" \
             --github-env
-      - name: Run molecule tests
+      - name: Prune stale Docker data
+        id: prune
         if: env.SKIP != 'true'
+        run: |
+          docker system prune -af --volumes 2>/dev/null || true
+          disk_pct=$(df -P / | awk 'NR==2 {gsub(/%/, "", $5); print $5}')
+          echo "Disk usage after prune: ${disk_pct}%"
+          if [ "$disk_pct" -ge 85 ]; then
+            echo "should-run=false" >> "$GITHUB_OUTPUT"
+            echo "::warning::Disk usage at ${disk_pct}% after prune — skipping molecule tests to avoid ENOSPC failures"
+          else
+            echo "should-run=true" >> "$GITHUB_OUTPUT"
+          fi
+      - name: Run molecule tests
+        if: env.SKIP != 'true' && steps.prune.outputs.should-run != 'false'
+        shell: bash
         env:
-          GITEA_URL: ${{ github.server_url }}
           CI_GITEA_API_TOKEN: ${{ secrets.CI_GITEA_API_TOKEN }}
           CI_GITEA_USERNAME: ${{ vars.CI_GITEA_USERNAME }}
-          RUN_ID: ${{ github.run_id }}
-          ANSIBLE_INJECT_INVOCATION: "1"
-          JOB_NAME: ${{ github.job }}
-          MATRIX_INDEX: ${{ matrix.runner-index }}
-          GITEA_REPOSITORY: ${{ github.repository }}
           DOCKER_HOST: unix:///var/run/docker.sock
+          ANSIBLE_INJECT_INVOCATION: "1"
         run: |
           . .venv/bin/activate 2>/dev/null || true
           if [ -z "$TEST_PAIRS" ]; then exit 0; fi
@@ -207,8 +216,44 @@ jobs:
           _TOKEN="$CI_GITEA_API_TOKEN"; [ -z "$_TOKEN" ] && _TOKEN="$CI_GITEA_TOKEN"
           [ -z "$_TOKEN" ] && { echo "Gitea API token not set — skipping Docker login"; exit 0; }
           echo "$_TOKEN" | docker login git.oblachno.oblachno.fyi -u "$CI_GITEA_USERNAME" --password-stdin
-          # shellcheck disable=SC2086 # intentional word splitting for argument expansion
-          python3 -m devx.molecule.molecule_ci_guard $TEST_PAIRS
+          # Run each molecule test pair sequentially.
+          # Pairs are 4-part: scenario|platform_name|platform_image|platform_command
+          # Spaces in platform_command are encoded as __SPACE__.
+          role_dir="ansible/roles/gitea_runner"
+          # shellcheck disable=SC2086 # intentional word splitting for pair list
+          for pair in $TEST_PAIRS; do
+            IFS='|' read -r scenario platform_name platform_image platform_command <<< "$pair"
+            platform_command="${platform_command//__SPACE__/ }"
+            export MOLECULE_PLATFORM_NAME="$platform_name"
+            export MOLECULE_PLATFORM_IMAGE="$platform_image"
+            if [ -n "$platform_command" ]; then
+              export MOLECULE_PLATFORM_COMMAND="$platform_command"
+            else
+              unset MOLECULE_PLATFORM_COMMAND
+            fi
+            export ANSIBLE_ALLOW_BROKEN_CONDITIONALS=true
+            echo "--- Running: $scenario on $platform_name ---"
+            pushd "$role_dir" >/dev/null
+            if [ "$scenario" = "default" ]; then
+              molecule test || {
+                echo "FAILED: $pair — running molecule destroy"
+                molecule destroy 2>/dev/null || true
+                popd >/dev/null
+                exit 1
+              }
+            else
+              molecule test -s "$scenario" || {
+                echo "FAILED: $pair — running molecule destroy"
+                molecule destroy -s "$scenario" 2>/dev/null || true
+                popd >/dev/null
+                exit 1
+              }
+            fi
+            popd >/dev/null
+            echo "PASSED: $pair"
+            docker system prune -af --volumes 2>/dev/null || true
+          done
+          echo "All molecule tests passed."
 
   auto-merge:
     # Auto-merge runs after validate + molecule-tests pass (or molecule is skipped).

.vale/styles/Google/Anthropomorphism.yml

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

.vale/styles/Google/Colons.yml

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

.vale/styles/Google/DateFormat.yml

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

.vale/styles/Google/ExcessiveClaims.yml

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

.vale/styles/Google/FirstPerson.yml

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

.vale/styles/Google/Headings.yml

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

.vale/styles/Google/Jargon.yml

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

.vale/styles/Google/Latin.yml

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

.vale/styles/Google/OxfordComma.yml

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

.vale/styles/Google/Parens.yml

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

.vale/styles/Google/Timeless.yml

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

.vale/styles/Google/Units.yml

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

.vale/styles/Google/WordList.yml

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

.vale/styles/Google/WordListCase.yml

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

AGENTS.md

@@ -278,9 +278,9 @@ via `[tool.devx.classify]` in `pyproject.toml`.
 - Any new file type not in the allowlist
 
 **devx module structure** (installed from git, not in this repo):
-- `devx.ci.*` — CI/CD automation (run by workflows): release, publish, auto_merge, classify_changes, detect_release_commit, push_badges, doc_coverage, sync_wiki, distribute_molecule, molecule_ci_guard, discover_runners, notify_failure, post_merge, pr_review, validate_commit_msg
+- `devx.ci.*` — CI/CD automation (run by workflows): release, publish, auto_merge, classify_changes, detect_release_commit, push_badges, doc_coverage, sync_wiki, distribute_molecule, discover_runners, notify_failure, post_merge, pr_review, validate_commit_msg
 - `devx.tools.*` — Dev tools (run locally): check_test_speed, configure_repo, install_checkmake, install_tools, setup, generate_badges, create_task, create_pr, pr_status, pr_logs, pr_label, rebase, pr_rebase
-- `devx.molecule.*` — Molecule helpers: molecule_all, platforms, discover_runners, distribute_molecule, molecule_ci_guard
+- `devx.molecule.*` — Molecule helpers: molecule_all, platforms, discover_runners, distribute_molecule
 - `devx.gitea_cli` — Tea CLI wrapper
 - `devx.i18n` — i18n translation system
 - `devx.config` — Shared configuration (DEVX_* env vars)
@@ -348,7 +348,7 @@ Since devx is installed as a package (via `pip install` from git), it is importa
 | PYTHONPATH | When to use | Example modules |
 |------------|-------------|-----------------|
 | `src` | Module imports from `grm` | `devx.ci.auto_merge`, `devx.ci.pr_review`, `devx.ci.pr_review`, `devx.ci.sync_wiki`, `devx.ci.post_merge`, `devx.ci.classify_changes`, `devx.molecule.discover_runners`, `devx.ci.doc_coverage` |
-| (none) | Module has no GRM imports | `devx.ci.detect_release_commit`, `devx.molecule.distribute_molecule`, `devx.molecule.molecule_ci_guard`, `devx.ci.push_badges`, `devx.ci.validate_commit_msg` |
+| (none) | Module has no GRM imports | `devx.ci.detect_release_commit`, `devx.molecule.distribute_molecule`, `devx.ci.push_badges`, `devx.ci.validate_commit_msg` |
 
 **In workflows**, always use `env:` blocks (not inline `PYTHONPATH=value`):
 ```yaml

CHANGELOG.md

@@ -2,6 +2,55 @@
 
 All notable changes to this project will be documented in this file.
 
+## [0.20.0] - 2026-08-09
+
+### Features
+
+- *(healthcheck)* Add two-tier disk prune with critical threshold
+
+## [0.19.0] - 2026-08-08
+
+### Features
+
+- Use Gitea mirror for Ansible collection installs
+
+## [0.18.8] - 2026-08-06
+
+### Bug Fixes
+
+- Pin containerd.io to compatible version for Docker 28.x
+
+
+## [0.18.7] - 2026-08-06
+
+### Bug Fixes
+
+- Move StartLimit to [Unit] and make prune timer reload conditional
+
+## [0.18.6] - 2026-08-05
+
+### Bug Fixes
+
+- Pre-configure daemon.json before rootless setuptool + add DBUS_SESSION_BUS_ADDRESS
+
+## [0.18.5] - 2026-08-05
+
+### Bug Fixes
+
+- Pin Docker 28.x + disable containerd snapshotter + tune prune/disk
+
+## [0.18.4] - 2026-08-05
+
+### Bug Fixes
+
+- Harden rootless Docker daemon resilience on CI runners
+
+## [0.18.3] - 2026-08-04
+
+### Bug Fixes
+
+- Switch default network driver to slirp4netns (pasta TCP RST bug)
+
 ## [0.18.2] - 2026-07-16
 
 ### Bug Fixes

Makefile

@@ -88,7 +88,7 @@ setup-release: $(VENV)/bin/activate .env configure-gitea-pypi
 setup-image:
 	@if [ -d /opt/venv ]; then ln -sf /opt/venv .venv; . .venv/bin/activate; \
 		_TOKEN="$$CI_GITEA_API_TOKEN"; [ -z "$$_TOKEN" ] && _TOKEN="$$DEVELOPER_GITEA_API_TOKEN"; [ -z "$$_TOKEN" ] && _TOKEN="$$CI_GITEA_TOKEN"; \
-		if [ -n "$$_TOKEN" ]; then export PIP_EXTRA_INDEX_URL="https://$$CI_GITEA_USERNAME:$${_TOKEN}@git.oblachno.oblachno.fyi/api/packages/oblachno-oss/pypi/simple/"; fi; \
+		if [ -n "$$_TOKEN" ]; then export PIP_EXTRA_INDEX_URL="https://$$CI_GITEA_USERNAME:$${_TOKEN}@git.oblachno.oblachno.fyi/api/packages/oblachno-oss/pypi/simple/"; git config --global url."https://$$CI_GITEA_USERNAME:$${_TOKEN}@git.oblachno.oblachno.fyi/".insteadOf "https://git.oblachno.oblachno.fyi/"; fi; \
 		pip install -e .$(if $(EXTRAS),[$(EXTRAS)],); \
 	else echo "[setup-image] /opt/venv not found — falling back to setup-ci"; $(MAKE) setup-ci; fi
 

README.md

@@ -8,12 +8,12 @@ Each runner runs in an isolated **rootless Docker** environment under a dedicate
 
 [![CI](https://git.oblachno.oblachno.fyi/oblachno-oss/grm/actions/workflows/ci.yml/badge.svg)](https://git.oblachno.oblachno.fyi/oblachno-oss/grm/actions)
 [![License: GPL-3.0](https://img.shields.io/badge/license-GPL--3.0-blue)](https://git.oblachno.oblachno.fyi/oblachno-oss/grm/src/branch/master/LICENSE)
-[![Coverage](https://git.oblachno.oblachno.fyi/oblachno-oss/grm/raw/commit/bf77093ceedcbb44e60ebfdbd10ebf17643377d5/coverage.svg)](https://git.oblachno.oblachno.fyi/oblachno-oss/grm/actions)
-[![Tests](https://git.oblachno.oblachno.fyi/oblachno-oss/grm/raw/commit/bf77093ceedcbb44e60ebfdbd10ebf17643377d5/tests.svg)](https://git.oblachno.oblachno.fyi/oblachno-oss/grm/actions)
-[![Docs](https://git.oblachno.oblachno.fyi/oblachno-oss/grm/raw/commit/bf77093ceedcbb44e60ebfdbd10ebf17643377d5/docs.svg)](https://git.oblachno.oblachno.fyi/oblachno-oss/grm/wiki)
-[![Code Quality](https://git.oblachno.oblachno.fyi/oblachno-oss/grm/raw/commit/bf77093ceedcbb44e60ebfdbd10ebf17643377d5/quality.svg)](https://git.oblachno.oblachno.fyi/oblachno-oss/grm/actions)
-[![Version](https://git.oblachno.oblachno.fyi/oblachno-oss/grm/raw/commit/bf77093ceedcbb44e60ebfdbd10ebf17643377d5/version.svg)](https://git.oblachno.oblachno.fyi/oblachno-oss/grm/releases)
-[![Python](https://git.oblachno.oblachno.fyi/oblachno-oss/grm/raw/commit/bf77093ceedcbb44e60ebfdbd10ebf17643377d5/python.svg)](https://www.python.org/downloads/)
+[![Coverage](https://git.oblachno.oblachno.fyi/oblachno-oss/grm/raw/commit/918ffe7df0c91464112f012126e3fd60a0dfa2d5/coverage.svg)](https://git.oblachno.oblachno.fyi/oblachno-oss/grm/actions)
+[![Tests](https://git.oblachno.oblachno.fyi/oblachno-oss/grm/raw/commit/918ffe7df0c91464112f012126e3fd60a0dfa2d5/tests.svg)](https://git.oblachno.oblachno.fyi/oblachno-oss/grm/actions)
+[![Docs](https://git.oblachno.oblachno.fyi/oblachno-oss/grm/raw/commit/918ffe7df0c91464112f012126e3fd60a0dfa2d5/docs.svg)](https://git.oblachno.oblachno.fyi/oblachno-oss/grm/wiki)
+[![Code Quality](https://git.oblachno.oblachno.fyi/oblachno-oss/grm/raw/commit/918ffe7df0c91464112f012126e3fd60a0dfa2d5/quality.svg)](https://git.oblachno.oblachno.fyi/oblachno-oss/grm/actions)
+[![Version](https://git.oblachno.oblachno.fyi/oblachno-oss/grm/raw/commit/918ffe7df0c91464112f012126e3fd60a0dfa2d5/version.svg)](https://git.oblachno.oblachno.fyi/oblachno-oss/grm/releases)
+[![Python](https://git.oblachno.oblachno.fyi/oblachno-oss/grm/raw/commit/918ffe7df0c91464112f012126e3fd60a0dfa2d5/python.svg)](https://www.python.org/downloads/)
 
 ## Why GRM?
 

ansible/requirements.yml

@@ -1,7 +1,11 @@
+---
 collections:
   - name: community.general
-    version: "==13.1.0"
+    type: url
+    source: https://git.oblachno.oblachno.fyi/api/packages/emil/generic/ansible-collections/13.1.0/community-general-13.1.0.tar.gz
   - name: ansible.posix
-    version: "==2.2.1"
+    type: url
+    source: https://git.oblachno.oblachno.fyi/api/packages/emil/generic/ansible-collections/2.2.1/ansible-posix-2.2.1.tar.gz
   - name: community.docker
-    version: "==5.2.1"
+    type: url
+    source: https://git.oblachno.oblachno.fyi/api/packages/emil/generic/ansible-collections/5.2.1/community-docker-5.2.1.tar.gz

ansible/roles/gitea_runner/defaults/main.yml

@@ -3,6 +3,13 @@ gitea_runner_version: "2.0.1"
 gitea_runner_labels: "docker,ubuntu-latest:docker://runner-images:ubuntu-26.04"
 gitea_runner_skip_registration: false
 
+# Force re-registration even if .runner file exists.
+# Use this when Gitea no longer recognizes the runner (e.g., after a Gitea
+# server restore/reinstall or when the runner record was deleted from the
+# admin UI). The existing .runner file is removed and a new registration is
+# performed. Requires registration_token.
+gitea_runner_force_reregister: false
+
 # Per-runner user (rootless isolation)
 gitea_runner_user_prefix: "grm-"
 gitea_runner_base_home: "/home"
@@ -18,18 +25,58 @@ gitea_runner_binary_path: "/usr/local/bin/gitea_runner"
 
 # Prune configuration
 gitea_runner_prune_until: "24h"
-gitea_runner_prune_schedule: "daily"
+# Every 6 hours — daily is insufficient for CI runners that build dozens
+# of images per day. Accumulation between daily runs can trigger Docker
+# daemon instability (containerd snapshotter GC holds locks, blocking
+# container operations).
+gitea_runner_prune_schedule: "*-*-* 00/6:00:00"
 gitea_runner_prune_label: "gitea-runner=true"
 
 # Service configuration
 gitea_runner_service_restart_sec: "5"
 
 # Health check configuration
-gitea_runner_healthcheck_interval: "5min"
+# 2min interval — catches hung daemons before multiple CI jobs fail between checks.
+# The previous 5min interval was too coarse: a stuck daemon could fail 3+ molecule
+# jobs in the window between healthcheck runs.
+gitea_runner_healthcheck_interval: "2min"
 gitea_runner_healthcheck_boot_delay: "2min"
-gitea_runner_healthcheck_disk_threshold: 85
+gitea_runner_healthcheck_disk_threshold: 70
+# When disk reaches this level, prune EVERYTHING (no until-filter) — the
+# runner is dangerously full and the gentle until=1h prune isn't enough.
+# This removes all stopped containers and unused images regardless of age.
+# At 75%+, molecule containers fail with "container is not running" because
+# overlay2 runs out of space under parallel DinD load.
+gitea_runner_healthcheck_disk_critical: 75
 gitea_runner_healthcheck_script_path: "{{ gitea_runner_config_dir }}/healthcheck.sh"
 
+# Auto-recovery: when the healthcheck detects an unregistered runner, it
+# can automatically re-register if a Gitea API token is provided.
+# The token needs admin or org-level access to fetch registration tokens.
+# Stored in a file readable by the runner user (mode 0400).
+# Set to empty string to disable auto-recovery (manual re-registration required).
+gitea_runner_auto_recover_api_token: ""
+
+# Cooldown file to prevent auto-recovery loops (e.g., if Gitea is down).
+# The healthcheck writes a timestamp to this file after a re-registration
+# attempt and skips further attempts for the cooldown period.
+gitea_runner_auto_recover_cooldown_sec: 300
+
+# Docker daemon resilience settings (applied to daemon.json).
+# live-restore: containers survive daemon restarts — prevents stuck container
+#   states when the healthcheck restarts a hung daemon.
+# shutdown-timeout: grace period (seconds) for containers to stop on daemon
+#   shutdown/restart. Default 15s is too short for DinD containers with nested
+#   processes (molecule tests). 30s gives SIGTERM time to propagate.
+# max-concurrent-downloads/uploads: limits parallel transfers to reduce daemon
+#   memory pressure when multiple CI jobs pull images simultaneously.
+# default-ulimits: prevents FD exhaustion in container processes.
+gitea_runner_docker_live_restore: true
+gitea_runner_docker_shutdown_timeout: 30
+gitea_runner_docker_max_concurrent_downloads: 3
+gitea_runner_docker_max_concurrent_uploads: 3
+gitea_runner_docker_default_nofile: 65536
+
 # Admin token for runner deregistration via Gitea API.
 # If not set, falls back to registration_token (which likely lacks admin scope).
 # Set this to a token with admin scope to enable automatic runner cleanup on removal.
@@ -44,6 +91,15 @@ gitea_runner_log_level: "info"
 gitea_runner_container_label: "gitea-runner=true"
 gitea_runner_file: ".runner"
 
+# Containerd version pinning — Docker 28.x vendors containerd v2.1.x internally.
+# containerd.io >= 2.3 ships a shim that returns a protobuf BootstrapResult which
+# Docker 28.x's vendored containerd code cannot parse, causing:
+#   "failed to create TTRPC connection: unsupported protocol: \b\x03\x12Yunix"
+# When Docker 29+ is installed (it vendors containerd 2.3+), this pin is not needed.
+# Set to "" to skip the compatibility check and allow any containerd.io version.
+gitea_runner_containerd_max_compatible_major: 2
+gitea_runner_containerd_max_compatible_minor: 2
+
 # Docker installation (for rootless dependencies)
 gitea_runner_docker_gpg_key_path: "/etc/apt/keyrings/docker.gpg"
 gitea_runner_docker_apt_arch: "{{ 'amd64' if ansible_facts['architecture'] == 'x86_64' else ansible_facts['architecture'] }}"
@@ -64,9 +120,18 @@ gitea_runner_rootless_scripts_ref: "v28.5.1"
 # that dockerd-rootless-setuptool.sh (which derives BIN from its own dirname) finds them co-located.
 gitea_runner_rootless_scripts_install_dir: "/usr/bin"
 
-# Rootless Docker network driver: "pasta" (IPv6 support) or "slirp4netns" (IPv4 only)
-# pasta has proper outgoing IPv6 support; slirp4netns does not (known limitation).
-gitea_runner_docker_rootless_net_driver: "pasta"
+# Rootless Docker network driver: "slirp4netns" (default) or "pasta" (IPv6 support)
+# slirp4netns is the default because pasta has a TCP proxy bug that sends RST
+# packets with wrong sequence numbers, breaking TCP connections from Docker
+# containers to external hosts. slirp4netns doesn't have IPv6 support.
+# See: https://bugs.passt.top/show_bug.cgi?id=52
+gitea_runner_docker_rootless_net_driver: "slirp4netns"
 
 # IPv6 subnet for rootless Docker containers (ULA range, not routable on internet)
 gitea_runner_docker_ipv6_cidr: "fd00:dead:beef::/48"
+
+# Pre-pull Docker images that CI runners need (avoids pulling on every CI run).
+# The runner container image (ci-full) is large (~3.3GB) and the healthcheck's
+# disk-space prune only removes dangling images, so pre-pulled tagged images persist.
+# Set to [] to skip pre-pulling. Images are pulled as the runner user via rootless Docker.
+gitea_runner_pre_pull_images: []

ansible/roles/gitea_runner/molecule/template-content/verify.yml

@@ -47,8 +47,11 @@
       ansible.builtin.assert:
         that:
           - "'Type=oneshot' in prune_service.content | b64decode"
-          - "'docker system prune' in prune_service.content | b64decode"
-          - "'docker volume prune' in prune_service.content | b64decode"
+          - "'docker rm -f' in prune_service.content | b64decode"
+          - "'GITEA-ACTIONS-TASK' in prune_service.content | b64decode"
+          - "'docker system prune -af' in prune_service.content | b64decode"
+          - "'docker network prune' in prune_service.content | b64decode"
+          - "'docker builder prune' in prune_service.content | b64decode"
         fail_msg: "Prune service template is missing expected directives"
 
     - name: Read rendered prune timer template
@@ -99,8 +102,15 @@
       ansible.builtin.assert:
         that:
           - "'docker info' in healthcheck_script.content | b64decode"
+          - "'timeout 10 docker info' in healthcheck_script.content | b64decode"
           - "'systemctl --user restart docker.service' in healthcheck_script.content | b64decode"
           - "'systemctl --user restart gitea-runner.service' in healthcheck_script.content | b64decode"
-          - "'docker system prune' in healthcheck_script.content | b64decode"
+          - "'docker rm -f' in healthcheck_script.content | b64decode"
+          - "'GITEA-ACTIONS-TASK' in healthcheck_script.content | b64decode"
+          - "'docker system prune -af' in healthcheck_script.content | b64decode"
+          - "'docker network prune' in healthcheck_script.content | b64decode"
+          - "'status=removing' in healthcheck_script.content | b64decode"
+          - "'status=stopping' in healthcheck_script.content | b64decode"
           - "gitea_runner_healthcheck_disk_threshold | string in healthcheck_script.content | b64decode"
+          - "gitea_runner_healthcheck_disk_critical | string in healthcheck_script.content | b64decode"
         fail_msg: "Healthcheck script template is missing expected content"

ansible/roles/gitea_runner/tasks/deregister.yml

@@ -29,6 +29,7 @@
   become_user: "{{ gitea_runner_service_user }}"
   environment:
     XDG_RUNTIME_DIR: "/run/user/{{ gitea_runner_uid | default(0) }}"
+    DBUS_SESSION_BUS_ADDRESS: "unix:path=/run/user/{{ gitea_runner_uid | default(0) }}/bus"
     DOCKER_HOST: "unix:///run/user/{{ gitea_runner_uid | default(0) }}/docker.sock"
   when:
     - gitea_runner_file_stat.stat.exists | default(false) | bool

ansible/roles/gitea_runner/tasks/healthcheck.yml

@@ -7,6 +7,22 @@
     group: "{{ gitea_runner_service_user }}"
     mode: "0755"
 
+- name: Write auto-recovery API token file
+  ansible.builtin.copy:
+    content: "{{ gitea_runner_auto_recover_api_token }}"
+    dest: "{{ gitea_runner_config_dir }}/auto-recover.token"
+    owner: "{{ gitea_runner_service_user }}"
+    group: "{{ gitea_runner_service_user }}"
+    mode: "0400"
+  no_log: true
+  when: gitea_runner_auto_recover_api_token | length > 0
+
+- name: Remove stale auto-recovery token file (if auto-recovery disabled)
+  ansible.builtin.file:
+    path: "{{ gitea_runner_config_dir }}/auto-recover.token"
+    state: absent
+  when: gitea_runner_auto_recover_api_token | length == 0
+
 - name: Create healthcheck user service file
   ansible.builtin.template:
     src: runner-healthcheck.service.j2
@@ -29,6 +45,7 @@
   become_user: "{{ gitea_runner_service_user }}"
   environment:
     XDG_RUNTIME_DIR: "/run/user/{{ gitea_runner_uid }}"
+    DBUS_SESSION_BUS_ADDRESS: "unix:path=/run/user/{{ gitea_runner_uid | default(0) }}/bus"
   changed_when: true
   when:
     - gitea_runner_systemd_available.stat.exists
@@ -40,6 +57,7 @@
   become_user: "{{ gitea_runner_service_user }}"
   environment:
     XDG_RUNTIME_DIR: "/run/user/{{ gitea_runner_uid }}"
+    DBUS_SESSION_BUS_ADDRESS: "unix:path=/run/user/{{ gitea_runner_uid | default(0) }}/bus"
   changed_when: true
   when:
     - gitea_runner_systemd_available.stat.exists

ansible/roles/gitea_runner/tasks/integration_test.yml

@@ -18,14 +18,18 @@
       else {} }}
   when: gitea_runner_file_stat.stat.exists | default(false) | bool
 
-- name: Verify runner user service active
+- name: Wait for runner user service to be active
   ansible.builtin.command: systemctl --user is-active gitea-runner
   become: true
   become_user: "{{ gitea_runner_service_user }}"
   environment:
     XDG_RUNTIME_DIR: "/run/user/{{ gitea_runner_uid }}"
+    DBUS_SESSION_BUS_ADDRESS: "unix:path=/run/user/{{ gitea_runner_uid | default(0) }}/bus"
   register: gitea_runner_service_check
   changed_when: false
+  retries: 10
+  delay: 2
+  until: gitea_runner_service_check.stdout | default('') | trim == 'active'
   when:
     - gitea_runner_systemd_available.stat.exists
     - gitea_runner_docker_rootless_setup

ansible/roles/gitea_runner/tasks/main.yml

@@ -17,6 +17,9 @@
 - name: Include healthcheck setup
   ansible.builtin.include_tasks: healthcheck.yml
 
+- name: Include pre-pull images
+  ansible.builtin.include_tasks: pre_pull_images.yml
+
 - name: Include integration test
   ansible.builtin.include_tasks: integration_test.yml
   when: not gitea_runner_skip_registration

ansible/roles/gitea_runner/tasks/pre_pull_images.yml

@@ -0,0 +1,28 @@
+---
+# Pre-pull Docker images that CI runners need to avoid pulling them on
+# every CI run. The runner container image (ci-full) is large (~3.3GB)
+# and pulling it on every run causes timeouts and disk pressure.
+#
+# The healthcheck script's disk-space prune only removes dangling images
+# (not tagged ones), so pre-pulled images persist between CI runs.
+#
+# Set gitea_runner_pre_pull_images to a list of image refs to pull, or
+# empty list to skip pre-pulling.
+
+- name: Pre-pull Docker images for CI runner
+  ansible.builtin.command: "docker pull {{ item }}"
+  become: true
+  become_user: "{{ gitea_runner_service_user }}"
+  environment:
+    DOCKER_HOST: "unix:///run/user/{{ gitea_runner_uid }}/docker.sock"
+    XDG_RUNTIME_DIR: "/run/user/{{ gitea_runner_uid }}"
+    DBUS_SESSION_BUS_ADDRESS: "unix:path=/run/user/{{ gitea_runner_uid | default(0) }}/bus"
+  register: gitea_runner_pre_pull_result
+  changed_when: "'Status: Downloaded' in gitea_runner_pre_pull_result.stdout or 'Status: Downloaded' in gitea_runner_pre_pull_result.stderr"
+  retries: 3
+  delay: 5
+  until: gitea_runner_pre_pull_result is success
+  loop: "{{ gitea_runner_pre_pull_images }}"
+  when:
+    - gitea_runner_docker_rootless_setup
+    - gitea_runner_pre_pull_images | length > 0

ansible/roles/gitea_runner/tasks/prune.yml

@@ -6,6 +6,7 @@
     owner: "{{ gitea_runner_service_user }}"
     group: "{{ gitea_runner_service_user }}"
     mode: "0644"
+  register: gitea_runner_prune_service
 
 - name: Create docker-prune user timer file
   ansible.builtin.template:
@@ -14,6 +15,7 @@
     owner: "{{ gitea_runner_service_user }}"
     group: "{{ gitea_runner_service_user }}"
     mode: "0644"
+  register: gitea_runner_prune_timer
 
 - name: Reload systemd user daemon for prune timer
   ansible.builtin.command: systemctl --user daemon-reload
@@ -21,10 +23,12 @@
   become_user: "{{ gitea_runner_service_user }}"
   environment:
     XDG_RUNTIME_DIR: "/run/user/{{ gitea_runner_uid }}"
+    DBUS_SESSION_BUS_ADDRESS: "unix:path=/run/user/{{ gitea_runner_uid | default(0) }}/bus"
   changed_when: true
   when:
     - gitea_runner_systemd_available.stat.exists
     - gitea_runner_docker_rootless_setup
+    - gitea_runner_prune_service is changed or gitea_runner_prune_timer is changed
 
 - name: Enable and start docker-prune user timer
   ansible.builtin.command: systemctl --user enable --now docker-prune.timer
@@ -32,6 +36,7 @@
   become_user: "{{ gitea_runner_service_user }}"
   environment:
     XDG_RUNTIME_DIR: "/run/user/{{ gitea_runner_uid }}"
+    DBUS_SESSION_BUS_ADDRESS: "unix:path=/run/user/{{ gitea_runner_uid | default(0) }}/bus"
   changed_when: true
   when:
     - gitea_runner_systemd_available.stat.exists

ansible/roles/gitea_runner/tasks/register.yml

@@ -7,11 +7,20 @@
     group: "{{ gitea_runner_service_user }}"
     mode: "0755"
 
-- name: Check if runner is already registered
+- name: Check if runner registration file exists
   ansible.builtin.stat:
     path: "{{ gitea_runner_data_dir }}/.runner"
   register: gitea_runner_registered
 
+- name: Remove stale runner registration file
+  ansible.builtin.file:
+    path: "{{ gitea_runner_data_dir }}/.runner"
+    state: absent
+  when:
+    - gitea_runner_registered.stat.exists
+    - gitea_runner_force_reregister | bool
+  register: gitea_runner_registration_removed
+
 - name: Register runner with Gitea
   ansible.builtin.command: >
     {{ gitea_runner_binary_path }} register
@@ -26,8 +35,25 @@
   become_user: "{{ gitea_runner_service_user }}"
   environment:
     XDG_RUNTIME_DIR: "/run/user/{{ gitea_runner_uid | default(0) }}"
+    DBUS_SESSION_BUS_ADDRESS: "unix:path=/run/user/{{ gitea_runner_uid | default(0) }}/bus"
     DOCKER_HOST: "unix:///run/user/{{ gitea_runner_uid | default(0) }}/docker.sock"
-  when: not gitea_runner_registered.stat.exists
+  when: not gitea_runner_registered.stat.exists or gitea_runner_force_reregister | bool
   register: gitea_runner_register_output
-  changed_when: "'already exists' not in gitea_runner_register_output.stdout | default('')"
+  changed_when: >-
+    gitea_runner_register_output.rc == 0 and
+    ('already exists' not in gitea_runner_register_output.stdout | default(''))
   timeout: 60
+
+- name: Ensure runner service is running after registration
+  ansible.builtin.command: systemctl --user start gitea-runner
+  become: true
+  become_user: "{{ gitea_runner_service_user }}"
+  environment:
+    XDG_RUNTIME_DIR: "/run/user/{{ gitea_runner_uid }}"
+    DBUS_SESSION_BUS_ADDRESS: "unix:path=/run/user/{{ gitea_runner_uid | default(0) }}/bus"
+  changed_when: true
+  when:
+    - gitea_runner_systemd_available.stat.exists
+    - gitea_runner_docker_rootless_setup
+    - gitea_runner_register_output is defined
+    - gitea_runner_register_output.rc | default(1) == 0

ansible/roles/gitea_runner/tasks/rootless_docker.yml

@@ -31,6 +31,11 @@
     - ansible_facts['os_family'] == 'Debian'
     - gitea_runner_docker_apt_repo is changed
 
+# Install Docker packages from the upstream Docker APT repository.
+# We do NOT pin to 28.x because recent Ubuntu releases (e.g. 26.04/plucky)
+# may not have 28.x packages in the Docker repo, and Docker 29 is safe
+# for rootless mode when the daemon.json disables the containerd snapshotter
+# and sets a conservative default nofile ulimit (see daemon.json tasks below).
 - name: Install rootless Docker dependencies (Debian/Ubuntu)
   ansible.builtin.apt:
     name:
@@ -45,6 +50,7 @@
       - docker-compose-plugin
       - rsync
     state: present
+  register: gitea_runner_docker_install
   when: ansible_facts['os_family'] == 'Debian'
 
 - name: Update pacman cache (Arch Linux)
@@ -133,8 +139,57 @@
     content: |
       [Service]
       Environment="DOCKERD_ROOTLESS_ROOTLESSKIT_NET={{ gitea_runner_docker_rootless_net_driver }}"
-      Environment="DOCKERD_ROOTLESS_ROOTLESSKIT_PORT_DRIVER=implicit"
+      Environment="DOCKERD_ROOTLESS_ROOTLESSKIT_PORT_DRIVER={{ 'implicit' if gitea_runner_docker_rootless_net_driver == 'pasta' else 'builtin' }}"
+      {% if gitea_runner_docker_rootless_net_driver == 'pasta' %}
       Environment="DOCKERD_ROOTLESS_ROOTLESSKIT_FLAGS=--ipv6"
+      {% endif %}
+    mode: "0644"
+    owner: "{{ gitea_runner_service_user }}"
+    group: "{{ gitea_runner_service_user }}"
+  when:
+    - gitea_runner_docker_rootless_setup
+    - not gitea_runner_rootless_docker_check.stat.exists
+
+# Write daemon.json BEFORE the setuptool starts dockerd, so Docker 29
+# starts with containerd snapshotter disabled from the very first boot.
+# Without this, Docker 29 uses containerd snapshots by default, which
+# causes instability in rootless mode.
+- name: Ensure Docker config directory exists (pre-setup)
+  ansible.builtin.file:
+    path: "{{ gitea_runner_home }}/.config/docker"
+    state: directory
+    mode: "0755"
+    owner: "{{ gitea_runner_service_user }}"
+    group: "{{ gitea_runner_service_user }}"
+  when:
+    - gitea_runner_docker_rootless_setup
+    - not gitea_runner_rootless_docker_check.stat.exists
+
+- name: Pre-configure rootless Docker daemon.json (disable containerd snapshotter)
+  ansible.builtin.copy:
+    dest: "{{ gitea_runner_home }}/.config/docker/daemon.json"
+    content: |
+      {
+        "live-restore": {{ gitea_runner_docker_live_restore | to_json }},
+        "shutdown-timeout": {{ gitea_runner_docker_shutdown_timeout }},
+        "max-concurrent-downloads": {{ gitea_runner_docker_max_concurrent_downloads }},
+        "max-concurrent-uploads": {{ gitea_runner_docker_max_concurrent_uploads }},
+        "default-ulimits": {
+          "nofile": {"Name": "nofile", "Hard": {{ gitea_runner_docker_default_nofile }}, "Soft": {{ gitea_runner_docker_default_nofile }}}
+        },
+        "features": {
+          "containerd-snapshotter": false
+        },
+        {% if gitea_runner_docker_rootless_net_driver == 'pasta' %}
+        "ipv6": true,
+        "ip6tables": true,
+        "fixed-cidr-v6": "{{ gitea_runner_docker_ipv6_cidr }}",
+        "dns": ["10.0.2.3", "8.8.8.8"]
+        {% else %}
+        "ipv6": false,
+        "dns": ["8.8.8.8", "1.1.1.1"]
+        {% endif %}
+      }
     mode: "0644"
     owner: "{{ gitea_runner_service_user }}"
     group: "{{ gitea_runner_service_user }}"
@@ -150,6 +205,7 @@
   become_user: "{{ gitea_runner_service_user }}"
   environment:
     XDG_RUNTIME_DIR: "/run/user/{{ gitea_runner_uid }}"
+    DBUS_SESSION_BUS_ADDRESS: "unix:path=/run/user/{{ gitea_runner_uid }}/bus"
     DOCKERD_ROOTLESS_ROOTLESSKIT_NET: "{{ gitea_runner_docker_rootless_net_driver }}"
   when:
     - gitea_runner_docker_rootless_setup
@@ -161,6 +217,7 @@
   become_user: "{{ gitea_runner_service_user }}"
   environment:
     XDG_RUNTIME_DIR: "/run/user/{{ gitea_runner_uid }}"
+    DBUS_SESSION_BUS_ADDRESS: "unix:path=/run/user/{{ gitea_runner_uid }}/bus"
   changed_when: true
   when: gitea_runner_docker_rootless_setup
 
@@ -170,6 +227,7 @@
   become_user: "{{ gitea_runner_service_user }}"
   environment:
     XDG_RUNTIME_DIR: "/run/user/{{ gitea_runner_uid }}"
+    DBUS_SESSION_BUS_ADDRESS: "unix:path=/run/user/{{ gitea_runner_uid }}/bus"
   changed_when: true
   when: gitea_runner_docker_rootless_setup
 
@@ -182,14 +240,16 @@
     group: "{{ gitea_runner_service_user }}"
   when: gitea_runner_docker_rootless_setup
 
-- name: Configure rootless Docker to use pasta with IPv6
+- name: Configure rootless Docker network driver
   ansible.builtin.copy:
     dest: "{{ gitea_runner_home }}/.config/systemd/user/docker.service.d/override.conf"
     content: |
       [Service]
       Environment="DOCKERD_ROOTLESS_ROOTLESSKIT_NET={{ gitea_runner_docker_rootless_net_driver }}"
-      Environment="DOCKERD_ROOTLESS_ROOTLESSKIT_PORT_DRIVER=implicit"
+      Environment="DOCKERD_ROOTLESS_ROOTLESSKIT_PORT_DRIVER={{ 'implicit' if gitea_runner_docker_rootless_net_driver == 'pasta' else 'builtin' }}"
+      {% if gitea_runner_docker_rootless_net_driver == 'pasta' %}
       Environment="DOCKERD_ROOTLESS_ROOTLESSKIT_FLAGS=--ipv6"
+      {% endif %}
     mode: "0644"
     owner: "{{ gitea_runner_service_user }}"
     group: "{{ gitea_runner_service_user }}"
@@ -202,19 +262,36 @@
   become_user: "{{ gitea_runner_service_user }}"
   environment:
     XDG_RUNTIME_DIR: "/run/user/{{ gitea_runner_uid }}"
+    DBUS_SESSION_BUS_ADDRESS: "unix:path=/run/user/{{ gitea_runner_uid }}/bus"
   changed_when: true
   when:
     - gitea_runner_docker_rootless_setup
     - gitea_runner_docker_network_override is changed
 
-- name: Configure rootless Docker daemon with IPv6 enabled
+- name: Configure rootless Docker daemon
   ansible.builtin.copy:
     dest: "{{ gitea_runner_home }}/.config/docker/daemon.json"
     content: |
       {
+        "live-restore": {{ gitea_runner_docker_live_restore | to_json }},
+        "shutdown-timeout": {{ gitea_runner_docker_shutdown_timeout }},
+        "max-concurrent-downloads": {{ gitea_runner_docker_max_concurrent_downloads }},
+        "max-concurrent-uploads": {{ gitea_runner_docker_max_concurrent_uploads }},
+        "default-ulimits": {
+          "nofile": {"Name": "nofile", "Hard": {{ gitea_runner_docker_default_nofile }}, "Soft": {{ gitea_runner_docker_default_nofile }}}
+        },
+        "features": {
+          "containerd-snapshotter": false
+        },
+        {% if gitea_runner_docker_rootless_net_driver == 'pasta' %}
         "ipv6": true,
         "ip6tables": true,
-        "fixed-cidr-v6": "{{ gitea_runner_docker_ipv6_cidr }}"
+        "fixed-cidr-v6": "{{ gitea_runner_docker_ipv6_cidr }}",
+        "dns": ["10.0.2.3", "8.8.8.8"]
+        {% else %}
+        "ipv6": false,
+        "dns": ["8.8.8.8", "1.1.1.1"]
+        {% endif %}
       }
     mode: "0644"
     owner: "{{ gitea_runner_service_user }}"
@@ -228,6 +305,7 @@
   become_user: "{{ gitea_runner_service_user }}"
   environment:
     XDG_RUNTIME_DIR: "/run/user/{{ gitea_runner_uid }}"
+    DBUS_SESSION_BUS_ADDRESS: "unix:path=/run/user/{{ gitea_runner_uid }}/bus"
   changed_when: true
   when:
     - gitea_runner_docker_rootless_setup
@@ -240,6 +318,7 @@
   environment:
     DOCKER_HOST: "unix:///run/user/{{ gitea_runner_uid }}/docker.sock"
     XDG_RUNTIME_DIR: "/run/user/{{ gitea_runner_uid }}"
+    DBUS_SESSION_BUS_ADDRESS: "unix:path=/run/user/{{ gitea_runner_uid }}/bus"
   register: gitea_runner_docker_ready
   until: gitea_runner_docker_ready.rc == 0
   retries: 10

ansible/roles/gitea_runner/tasks/service.yml

@@ -6,6 +6,7 @@
     owner: "{{ gitea_runner_service_user }}"
     group: "{{ gitea_runner_service_user }}"
     mode: "0644"
+  register: gitea_runner_service_file
 
 - name: Reload systemd user daemon
   ansible.builtin.command: systemctl --user daemon-reload
@@ -13,10 +14,25 @@
   become_user: "{{ gitea_runner_service_user }}"
   environment:
     XDG_RUNTIME_DIR: "/run/user/{{ gitea_runner_uid }}"
+    DBUS_SESSION_BUS_ADDRESS: "unix:path=/run/user/{{ gitea_runner_uid | default(0) }}/bus"
   changed_when: true
   when:
     - gitea_runner_systemd_available.stat.exists
     - gitea_runner_docker_rootless_setup
+    - gitea_runner_service_file is changed
+
+- name: Restart gitea-runner if service file changed
+  ansible.builtin.command: systemctl --user restart gitea-runner
+  become: true
+  become_user: "{{ gitea_runner_service_user }}"
+  environment:
+    XDG_RUNTIME_DIR: "/run/user/{{ gitea_runner_uid }}"
+    DBUS_SESSION_BUS_ADDRESS: "unix:path=/run/user/{{ gitea_runner_uid | default(0) }}/bus"
+  changed_when: true
+  when:
+    - gitea_runner_systemd_available.stat.exists
+    - gitea_runner_docker_rootless_setup
+    - gitea_runner_service_file is changed
 
 - name: Enable and start gitea-runner user service
   ansible.builtin.command: systemctl --user enable --now gitea-runner
@@ -24,6 +40,7 @@
   become_user: "{{ gitea_runner_service_user }}"
   environment:
     XDG_RUNTIME_DIR: "/run/user/{{ gitea_runner_uid }}"
+    DBUS_SESSION_BUS_ADDRESS: "unix:path=/run/user/{{ gitea_runner_uid | default(0) }}/bus"
   changed_when: true
   when:
     - gitea_runner_systemd_available.stat.exists

ansible/roles/gitea_runner/tasks/update_runner.yml

@@ -8,6 +8,7 @@
   become_user: "{{ gitea_runner_service_user }}"
   environment:
     XDG_RUNTIME_DIR: "/run/user/{{ gitea_runner_uid }}"
+    DBUS_SESSION_BUS_ADDRESS: "unix:path=/run/user/{{ gitea_runner_uid | default(0) }}/bus"
   when:
     - gitea_runner_systemd_available.stat.exists | default(false) | bool
     - gitea_runner_docker_rootless_setup

ansible/roles/gitea_runner/tasks/validate.yml

@@ -21,6 +21,7 @@
   environment:
     DOCKER_HOST: "unix:///run/user/{{ gitea_runner_uid }}/docker.sock"
     XDG_RUNTIME_DIR: "/run/user/{{ gitea_runner_uid }}"
+    DBUS_SESSION_BUS_ADDRESS: "unix:path=/run/user/{{ gitea_runner_uid | default(0) }}/bus"
   register: gitea_runner_docker_version_output
   changed_when: false
   when: gitea_runner_docker_rootless_setup

ansible/roles/gitea_runner/templates/docker-prune.service.j2

@@ -5,5 +5,19 @@ Description=Docker prune for Gitea runner resources
 Type=oneshot
 Environment=DOCKER_HOST=unix:///run/user/{{ gitea_runner_uid }}/docker.sock
 Environment=XDG_RUNTIME_DIR=/run/user/{{ gitea_runner_uid }}
-ExecStart=/usr/bin/docker system prune -f --filter "label={{ gitea_runner_prune_label }}" --filter "until={{ gitea_runner_prune_until }}"
-ExecStart=/usr/bin/docker volume prune -f --filter "label={{ gitea_runner_prune_label }}"
+# Force-remove stale containers (including running ones) left behind by failed
+# molecule tests. "docker container prune -f" only removes stopped containers,
+# so running containers from crashed/interrupted CI jobs accumulate indefinitely,
+# consuming disk and memory. We stop+rm everything first, then prune the rest.
+# Exclude CI job containers (name starts with GITEA-ACTIONS-TASK) — removing
+# them kills the active CI job and causes "RWLayer is unexpectedly nil" errors.
+# Only remove containers older than 1 hour (grep for "hour/day/week/month/year
+# ago" in RunningFor) to avoid killing molecule test containers that CI jobs
+# are actively using.
+ExecStart=/bin/sh -c 'docker ps -a --format "{% raw %}{{.ID}} {{.Names}} {{.RunningFor}}{% endraw %}" 2>/dev/null | grep -v "GITEA-ACTIONS-TASK" | grep -E "(hour|day|week|month|year)s? ago" | awk "{print $1}" | xargs -r docker rm -f 2>/dev/null || true'
+ExecStart=/usr/bin/docker system prune -af --filter "until={{ gitea_runner_prune_until }}" --volumes
+# Prune networks older than the prune-until threshold to avoid removing
+# networks that molecule tests are actively creating (e.g. 'traefik' network
+# created during molecule create phase before containers are attached).
+ExecStart=/usr/bin/docker network prune -f --filter "until={{ gitea_runner_prune_until }}"
+ExecStart=/usr/bin/docker builder prune -f

ansible/roles/gitea_runner/templates/gitea-runner-user.service.j2

@@ -3,6 +3,8 @@ Description=Gitea Actions Runner (rootless)
 After=docker.service
 Requires=docker.service
 PartOf=docker.service
+StartLimitIntervalSec=300
+StartLimitBurst=10
 
 [Service]
 Type=simple
@@ -14,8 +16,6 @@ ExecStop=/bin/kill -TERM $MAINPID
 TimeoutStopSec=30
 Restart=always
 RestartSec={{ gitea_runner_service_restart_sec }}
-StartLimitIntervalSec=300
-StartLimitBurst=10
 
 [Install]
 WantedBy=default.target

ansible/roles/gitea_runner/templates/runner-healthcheck.sh.j2

@@ -7,18 +7,29 @@ DOCKER_HOST="unix:///run/user/{{ gitea_runner_uid }}/docker.sock"
 XDG_RUNTIME_DIR="/run/user/{{ gitea_runner_uid }}"
 export DOCKER_HOST XDG_RUNTIME_DIR
 
-# 1. Check Docker daemon responsiveness
-if ! docker info >/dev/null 2>&1; then
-    echo "ERROR: Docker daemon not responding at ${DOCKER_HOST}"
+# 1. Check Docker daemon responsiveness (with timeout — a bare `docker info` can
+#    hang indefinitely on a stuck daemon, blocking the healthcheck itself).
+if ! timeout 10 docker info >/dev/null 2>&1; then
+    echo "ERROR: Docker daemon not responding at ${DOCKER_HOST} (timed out after 10s)"
     systemctl --user restart docker.service
     sleep 3
-    if ! docker info >/dev/null 2>&1; then
+    if ! timeout 10 docker info >/dev/null 2>&1; then
         echo "CRITICAL: Docker daemon still down after restart"
         exit 1
     fi
     echo "RECOVERED: Docker daemon restarted successfully"
 fi
 
+# 1b. Clean up stuck containers — containers in "removing" or "stopping" state
+#     for too long cause "cannot kill container: did not receive an exit event"
+#     errors in molecule destroy phases. Force-remove them so subsequent CI jobs
+#     don't inherit the stuck state.
+stuck_containers=$(timeout 10 docker ps -a --filter "status=removing" --filter "status=stopping" --format '{% raw %}{{.ID}}{% endraw %}' 2>/dev/null || true)
+if [[ -n "$stuck_containers" ]]; then
+    echo "WARN: Found stuck containers (removing/stopping), force-cleaning"
+    echo "$stuck_containers" | xargs -r docker rm -f 2>/dev/null || true
+fi
+
 # 2. Check gitea-runner service is active
 runner_state=$(systemctl --user is-active gitea-runner.service 2>/dev/null || true)
 if [[ "$runner_state" != "active" ]]; then
@@ -33,14 +44,222 @@ if [[ "$runner_state" != "active" ]]; then
     echo "RECOVERED: gitea-runner service restarted successfully"
 fi
 
+# 2b. Detect unregistered runner state. When Gitea no longer recognizes the
+# runner (e.g., server restore, runner record deleted, Gitea restart with
+# token salt change), the runner logs "unregistered runner" every few seconds.
+# A service restart will not fix this; re-registration is required.
+#
+# Detection method: query the Gitea API to verify the runner's UUID still
+# exists.  This is more reliable than parsing journal logs (which requires
+# journal access permissions that runner users may not have — see the
+# 2026-08-08 incident where journalctl --user returned "No journal files
+# were opened due to insufficient permissions" for all runner users,
+# causing the healthcheck to always report "OK: runner healthy" even
+# though all runners were unregistered).
+{% if gitea_runner_auto_recover_api_token %}
+# Auto-recovery is enabled: fetch a new registration token from the Gitea API
+# and re-register the runner automatically. A cooldown prevents infinite loops.
+GITEA_API_TOKEN_FILE="{{ gitea_runner_config_dir }}/auto-recover.token"
+COOLDOWN_FILE="{{ gitea_runner_data_dir }}/auto-recover.cooldown"
+COOLDOWN_SEC={{ gitea_runner_auto_recover_cooldown_sec }}
+GITEA_URL="{{ gitea_url }}"
+RUNNER_NAME="{{ gitea_runner_name }}"
+RUNNER_LABELS="{{ gitea_runner_labels }}"
+BINARY="{{ gitea_runner_binary_path }}"
+RUNNER_FILE="{{ gitea_runner_data_dir }}/.runner"
+{% endif %}
+runner_unregistered=0
+
+# Primary detection: query the Gitea API to check if the runner's ID
+# still exists in Gitea's runner list.  This works regardless of journal
+# permissions.
+{% if gitea_runner_auto_recover_api_token %}
+if [[ -f "$GITEA_API_TOKEN_FILE" && -f "$RUNNER_FILE" ]]; then
+    API_TOKEN=$(cat "$GITEA_API_TOKEN_FILE" 2>/dev/null || true)
+    RUNNER_ID=$(python3 -c "import json; print(json.load(open('$RUNNER_FILE')).get('id',''))" 2>/dev/null || true)
+    if [[ -n "$API_TOKEN" && -n "$RUNNER_ID" ]]; then
+        # List all runners and check if our ID is present
+        runner_found=$(curl -sf --connect-timeout 5 --max-time 10 \
+            -H "Authorization: token $API_TOKEN" \
+            "${GITEA_URL}/api/v1/admin/actions/runners" 2>/dev/null \
+            | python3 -c "
+import sys, json
+try:
+    data = json.load(sys.stdin)
+    runners = data if isinstance(data, list) else data.get('runners', [])
+    ids = [str(r.get('id', '')) for r in runners]
+    print('1' if '$RUNNER_ID' in ids else '0')
+except Exception:
+    print('0')
+" 2>/dev/null || echo "0")
+        if [[ "$runner_found" != "1" ]]; then
+            runner_unregistered=1
+            echo "CRITICAL: runner ID $RUNNER_ID not found in Gitea (unregistered)."
+        fi
+    fi
+fi
+{% endif %}
+
+# Fallback detection: check journal logs (if accessible)
+if [[ "$runner_unregistered" -eq 0 ]]; then
+    recent_errors=$(journalctl --user -u gitea-runner.service --since "5 minutes ago" --no-pager -q 2>/dev/null | grep -c "unregistered runner" || true)
+    if [[ "$recent_errors" -ge 3 ]]; then
+        runner_unregistered=1
+        echo "CRITICAL: runner is unregistered in Gitea (re-login failed $recent_errors times in 5 minutes)."
+    fi
+fi
+
+if [[ "$runner_unregistered" -ge 1 ]]; then
+{% if gitea_runner_auto_recover_api_token %}
+    # Check cooldown — skip if we recently attempted recovery
+    if [[ -f "$COOLDOWN_FILE" ]]; then
+        last_attempt=$(cat "$COOLDOWN_FILE" 2>/dev/null || echo 0)
+        now=$(date +%s)
+        elapsed=$((now - last_attempt))
+        if [[ "$elapsed" -lt "$COOLDOWN_SEC" ]]; then
+            echo "SKIP: auto-recovery cooldown active (${elapsed}s < ${COOLDOWN_SEC}s). Will retry later."
+            exit 3
+        fi
+    fi
+
+    # Mark attempt time BEFORE trying (so failures also get cooldown)
+    date +%s > "$COOLDOWN_FILE" 2>/dev/null || true
+
+    # Read the API token
+    if [[ ! -f "$GITEA_API_TOKEN_FILE" ]]; then
+        echo "ERROR: auto-recover token file not found at $GITEA_API_TOKEN_FILE. Manual re-registration required."
+        exit 3
+    fi
+    API_TOKEN=$(cat "$GITEA_API_TOKEN_FILE" 2>/dev/null || true)
+    if [[ -z "$API_TOKEN" ]]; then
+        echo "ERROR: auto-recover token file is empty. Manual re-registration required."
+        exit 3
+    fi
+
+    echo "ATTEMPT: auto-recovering by fetching new registration token and re-registering..."
+
+    # Fetch a new registration token from the Gitea API
+    # Try org-level first (for org-scoped runners), then instance-level
+    REG_TOKEN=""
+    for endpoint in \
+        "api/v1/orgs/{{ gitea_runner_org | default('oblachno') }}/actions/runners/registration-token" \
+        "api/v1/admin/actions/runners/registration-token"; do
+        REG_TOKEN=$(curl -sf --connect-timeout 5 --max-time 10 -X POST \
+            -H "Authorization: token $API_TOKEN" \
+            "${GITEA_URL}/${endpoint}" 2>/dev/null | python3 -c "import sys,json; print(json.load(sys.stdin).get('token',''))" 2>/dev/null || true)
+        if [[ -n "$REG_TOKEN" ]]; then
+            echo "INFO: fetched registration token from ${endpoint}"
+            break
+        fi
+    done
+
+    if [[ -z "$REG_TOKEN" ]]; then
+        echo "ERROR: failed to fetch registration token from Gitea API. Is Gitea reachable?"
+        exit 3
+    fi
+
+    # Stop the runner service
+    systemctl --user stop gitea-runner.service 2>/dev/null || true
+    sleep 1
+
+    # Remove the stale .runner file
+    rm -f "{{ gitea_runner_data_dir }}/.runner" 2>/dev/null || true
+
+    # Re-register
+    cd "{{ gitea_runner_data_dir }}"
+    if "$BINARY" register \
+        --token "$REG_TOKEN" \
+        --name "$RUNNER_NAME" \
+        --instance "$GITEA_URL" \
+        --labels "$RUNNER_LABELS" \
+        --no-interactive 2>&1; then
+        echo "RECOVERED: runner re-registered successfully"
+    else
+        echo "ERROR: re-registration failed. Manual intervention required."
+        exit 3
+    fi
+
+    # Start the runner service
+    systemctl --user start gitea-runner.service
+    sleep 3
+
+    # Verify recovery — query the Gitea API to confirm the new ID is registered
+    NEW_ID=$(python3 -c "import json; print(json.load(open('$RUNNER_FILE')).get('id',''))" 2>/dev/null || true)
+    if [[ -n "$NEW_ID" ]]; then
+        new_found=$(curl -sf --connect-timeout 5 --max-time 10 \
+            -H "Authorization: token $API_TOKEN" \
+            "${GITEA_URL}/api/v1/admin/actions/runners" 2>/dev/null \
+            | python3 -c "
+import sys, json
+try:
+    data = json.load(sys.stdin)
+    runners = data if isinstance(data, list) else data.get('runners', [])
+    ids = [str(r.get('id', '')) for r in runners]
+    print('1' if '$NEW_ID' in ids else '0')
+except Exception:
+    print('0')
+" 2>/dev/null || echo "0")
+        if [[ "$new_found" == "1" ]]; then
+            echo "OK: runner recovered and registered with new ID $NEW_ID"
+            # Clear cooldown on success
+            rm -f "$COOLDOWN_FILE" 2>/dev/null || true
+        else
+            echo "WARN: runner re-registered but ID not found in Gitea API. Will retry after cooldown."
+            exit 3
+        fi
+    else
+        echo "WARN: could not read new .runner file after re-registration. Will retry after cooldown."
+        exit 3
+    fi
+{% else %}
+    echo "Manual re-registration required: re-run gitea_runner role with gitea_runner_force_reregister=true."
+    # Restart the service once in case it is a transient token refresh issue,
+    # but this cannot recover an unregistered runner without re-registration.
+    systemctl --user restart gitea-runner.service
+    sleep 2
+    exit 3
+{% endif %}
+fi
+
 # 3. Check disk space — prune aggressively if below threshold
 disk_pct=$(df -P / | awk 'NR==2 {gsub(/%/, "", $5); print $5}')
-if [[ "$disk_pct" -ge {{ gitea_runner_healthcheck_disk_threshold }} ]]; then
-    echo "WARN: Disk usage at ${disk_pct}%, pruning all runner resources"
-    docker system prune -af --filter "label={{ gitea_runner_prune_label }}" --filter "until=1h" || true
-    docker volume prune -af --filter "label={{ gitea_runner_prune_label }}" || true
-    # Also prune dangling images (no label)
-    docker image prune -af || true
+if [[ "$disk_pct" -ge {{ gitea_runner_healthcheck_disk_critical }} ]]; then
+    echo "CRITICAL: Disk usage at ${disk_pct}% (>= {{ gitea_runner_healthcheck_disk_critical }}%), full prune"
+    # Critical level: remove ALL stopped containers (no age filter) and ALL
+    # unused images/volumes. The until=1h gentle prune is insufficient here.
+    # Stop+rm stale non-CI containers regardless of age (failed molecule tests
+    # from the last 59 minutes also consume disk).
+    docker ps -a --format '{% raw %}{{.ID}} {{.Names}}{% endraw %}' 2>/dev/null \
+        | grep -v 'GITEA-ACTIONS-TASK' \
+        | awk '{print $1}' \
+        | xargs -r docker rm -f 2>/dev/null || true
+    docker system prune -af --volumes || true
+    docker network prune -f || true
+    docker builder prune -af || true
+    disk_pct=$(df -P / | awk 'NR==2 {gsub(/%/, "", $5); print $5}')
+    echo "INFO: Disk usage after full prune: ${disk_pct}%"
+elif [[ "$disk_pct" -ge {{ gitea_runner_healthcheck_disk_threshold }} ]]; then
+    echo "WARN: Disk usage at ${disk_pct}%, pruning runner resources (until=1h)"
+    # Force-remove stale containers (including running ones from failed molecule tests)
+    # that are older than 1 hour. "docker container prune -f" only removes stopped
+    # containers, so running containers from crashed CI jobs accumulate and consume
+    # disk/memory. Exclude CI job containers (name starts with GITEA-ACTIONS-TASK).
+    # Only remove containers older than 1 hour to avoid killing molecule test
+    # containers that CI jobs are actively using.
+    docker ps -a --format '{% raw %}{{.ID}} {{.Names}} {{.RunningFor}}{% endraw %}' 2>/dev/null \
+        | grep -v 'GITEA-ACTIONS-TASK' \
+        | grep -E '(hour|day|week|month|year)s? ago' \
+        | awk '{print $1}' \
+        | xargs -r docker rm -f 2>/dev/null || true
+    # Prune images and containers older than 1h (until filter is NOT
+    # supported with --volumes, so prune volumes separately without a filter).
+    docker image prune -af --filter "until=1h" 2>/dev/null || true
+    docker container prune -f --filter "until=1h" 2>/dev/null || true
+    docker volume prune -f 2>/dev/null || true
+    # Prune networks older than 1 hour to avoid removing networks that
+    # molecule tests are actively creating (e.g. 'traefik' network created
+    # during molecule create phase before containers are attached).
+    docker network prune -f --filter "until=1h" || true
     disk_pct=$(df -P / | awk 'NR==2 {gsub(/%/, "", $5); print $5}')
     echo "INFO: Disk usage after prune: ${disk_pct}%"
 fi

ansible/start-runner.yml

@@ -33,5 +33,5 @@
       become_user: "{{ gitea_runner_service_user }}"
       environment:
         XDG_RUNTIME_DIR: "/run/user/{{ gitea_runner_uid }}"
-      when: systemd_available.stat.exists
+      when: gitea_runner_systemd_available.stat.exists
       changed_when: true

docs/index.md

@@ -8,12 +8,12 @@ Each runner runs in an isolated **rootless Docker** environment under a dedicate
 
 [![CI](https://git.oblachno.oblachno.fyi/oblachno-oss/grm/actions/workflows/ci.yml/badge.svg)](https://git.oblachno.oblachno.fyi/oblachno-oss/grm/actions)
 [![License: GPL-3.0](https://img.shields.io/badge/license-GPL--3.0-blue)](https://git.oblachno.oblachno.fyi/oblachno-oss/grm/src/branch/master/LICENSE)
-[![Coverage](https://git.oblachno.oblachno.fyi/oblachno-oss/grm/raw/commit/bf77093ceedcbb44e60ebfdbd10ebf17643377d5/coverage.svg)](https://git.oblachno.oblachno.fyi/oblachno-oss/grm/actions)
-[![Tests](https://git.oblachno.oblachno.fyi/oblachno-oss/grm/raw/commit/bf77093ceedcbb44e60ebfdbd10ebf17643377d5/tests.svg)](https://git.oblachno.oblachno.fyi/oblachno-oss/grm/actions)
-[![Docs](https://git.oblachno.oblachno.fyi/oblachno-oss/grm/raw/commit/bf77093ceedcbb44e60ebfdbd10ebf17643377d5/docs.svg)](https://git.oblachno.oblachno.fyi/oblachno-oss/grm/wiki)
-[![Code Quality](https://git.oblachno.oblachno.fyi/oblachno-oss/grm/raw/commit/bf77093ceedcbb44e60ebfdbd10ebf17643377d5/quality.svg)](https://git.oblachno.oblachno.fyi/oblachno-oss/grm/actions)
-[![Version](https://git.oblachno.oblachno.fyi/oblachno-oss/grm/raw/commit/bf77093ceedcbb44e60ebfdbd10ebf17643377d5/version.svg)](https://git.oblachno.oblachno.fyi/oblachno-oss/grm/releases)
-[![Python](https://git.oblachno.oblachno.fyi/oblachno-oss/grm/raw/commit/bf77093ceedcbb44e60ebfdbd10ebf17643377d5/python.svg)](https://www.python.org/downloads/)
+[![Coverage](https://git.oblachno.oblachno.fyi/oblachno-oss/grm/raw/commit/918ffe7df0c91464112f012126e3fd60a0dfa2d5/coverage.svg)](https://git.oblachno.oblachno.fyi/oblachno-oss/grm/actions)
+[![Tests](https://git.oblachno.oblachno.fyi/oblachno-oss/grm/raw/commit/918ffe7df0c91464112f012126e3fd60a0dfa2d5/tests.svg)](https://git.oblachno.oblachno.fyi/oblachno-oss/grm/actions)
+[![Docs](https://git.oblachno.oblachno.fyi/oblachno-oss/grm/raw/commit/918ffe7df0c91464112f012126e3fd60a0dfa2d5/docs.svg)](https://git.oblachno.oblachno.fyi/oblachno-oss/grm/wiki)
+[![Code Quality](https://git.oblachno.oblachno.fyi/oblachno-oss/grm/raw/commit/918ffe7df0c91464112f012126e3fd60a0dfa2d5/quality.svg)](https://git.oblachno.oblachno.fyi/oblachno-oss/grm/actions)
+[![Version](https://git.oblachno.oblachno.fyi/oblachno-oss/grm/raw/commit/918ffe7df0c91464112f012126e3fd60a0dfa2d5/version.svg)](https://git.oblachno.oblachno.fyi/oblachno-oss/grm/releases)
+[![Python](https://git.oblachno.oblachno.fyi/oblachno-oss/grm/raw/commit/918ffe7df0c91464112f012126e3fd60a0dfa2d5/python.svg)](https://www.python.org/downloads/)
 
 ## Overview
 

docs/tech/ci-cd-workflow.md

@@ -259,9 +259,9 @@ OS platform matrix (defined in `devx.molecule.platforms`), then splits
 the resulting test pairs evenly across the requested number of runners.
 Each pair is encoded as `scenario|platform_name|platform_image|platform_command`.
 
-`devx.molecule.molecule_ci_guard` runs the actual molecule test for a
-given test pair, with CI context (Gitea URL, token, run ID) for
-reporting results back to the commit status API.
+The CI workflow runs each test pair sequentially via a shell loop that
+sets the appropriate `MOLECULE_PLATFORM_*` environment variables and
+invokes `molecule test` directly.
 
 ### Commit Message Validation
 

docs/tech/testing-strategy.md

@@ -91,7 +91,7 @@ The `molecule-tests` job uses `fromJSON()` to consume the dynamic matrix, and pa
 
 `devx.molecule.distribute_molecule` discovers all molecule scenarios under `ansible/roles/*/molecule/` and crosses them with the supported OS platform matrix, then splits the resulting test pairs evenly across the requested number of runners. Each pair is encoded as `scenario|platform_name|platform_image|platform_command`.
 
-`devx.molecule.molecule_ci_guard` runs the actual molecule test for a given test pair, with CI context (Gitea URL, token, run ID) for reporting results back to the commit status API.
+The CI workflow runs each test pair sequentially via a shell loop that sets the appropriate `MOLECULE_PLATFORM_*` environment variables and invokes `molecule test` directly.
 
 ### Path-based CI filtering
 

pyproject.toml

@@ -32,10 +32,11 @@ version = {attr = "grm.__version__"}
 ci = [
     "pytest==9.1.1",
     "pytest-cov==7.1.0",
+    "pytest-xdist==3.8.0",
     "build==1.5.1",
     "twine==6.2.0",
     # Reusable CI/CD and dev tools (auto-merge, pr-review, pre-push checks, etc.)
-    "devx @ git+https://git.oblachno.oblachno.fyi/oblachno-oss/devx.git@v0.47.1",
+    "devx @ git+https://git.oblachno.oblachno.fyi/oblachno-oss/devx.git@v0.48.1",
 ]
 # Lint and type-checking tools (validate job)
 lint = [
@@ -55,7 +56,7 @@ molecule = [
 dev = [
     "grm[ci,lint,molecule]",
     # Reusable CI/CD and dev tools (pre-push hooks, create-task, create-pr)
-    "devx @ git+https://git.oblachno.oblachno.fyi/oblachno-oss/devx.git@v0.47.1",
+    "devx @ git+https://git.oblachno.oblachno.fyi/oblachno-oss/devx.git@v0.48.1",
     # Non-Python dev dependency: checkmake (Makefile linter)
     # Install via: go install github.com/checkmake/checkmake/cmd/checkmake@latest
 ]

scripts/cleanup_stale_runners.py

@@ -0,0 +1,136 @@
+#!/usr/bin/env python3
+"""Clean up stale runner registrations from Gitea.
+
+A runner is considered stale if it hasn't been online for more than a
+configurable threshold (default: 1 hour).  Stale runners accumulate when:
+- A runner host is rebuilt or re-provisioned (old registration remains)
+- A runner is re-registered (old entry remains alongside the new one)
+- A runner process dies and the healthcheck can't auto-recover
+
+This script queries the Gitea API for all runners, identifies stale ones,
+and deletes them via ``DELETE /api/v1/admin/actions/runners/{id}``.
+
+Usage::
+
+    python3 scripts/cleanup_stale_runners.py --gitea-url https://git.example.com --token <admin-token>
+    python3 scripts/cleanup_stale_runners.py --gitea-url https://git.example.com --token <admin-token> --dry-run
+    python3 scripts/cleanup_stale_runners.py --gitea-url https://git.example.com --token <admin-token> \\
+        --stale-threshold 3600
+"""
+
+from __future__ import annotations
+
+import argparse
+import json
+import sys
+import time
+import urllib.error
+import urllib.request  # noqa: PTH123  # nosec B404
+from typing import Any
+
+
+def _api_request(base_url: str, token: str, method: str, path: str) -> Any:
+    url = f"{base_url.rstrip('/')}/api/v1{path}"
+    req = urllib.request.Request(url, method=method)  # nosec B310
+    req.add_header("Authorization", f"token {token}")
+    req.add_header("Accept", "application/json")
+    try:
+        with urllib.request.urlopen(req) as resp:  # noqa: PTH123  # nosec B310
+            if resp.status == 204:
+                return None
+            raw = resp.read()
+            return json.loads(raw) if raw else None
+    except urllib.error.HTTPError as e:
+        detail = e.read().decode("utf-8", errors="replace")
+        raise RuntimeError(f"Gitea API error {e.code}: {detail}") from e
+
+
+def list_runners(base_url: str, token: str) -> list[dict[str, Any]]:
+    data = _api_request(base_url, token, "GET", "/admin/actions/runners")
+    if data is None:
+        return []
+    if isinstance(data, list):
+        return data
+    if isinstance(data, dict):
+        return data.get("runners", [])
+    return []
+
+
+def delete_runner(base_url: str, token: str, runner_id: int) -> bool:
+    try:
+        _api_request(base_url, token, "DELETE", f"/admin/actions/runners/{runner_id}")
+        return True
+    except RuntimeError as e:
+        print(f"  ERROR deleting runner {runner_id}: {e}", file=sys.stderr)
+        return False
+
+
+def main(argv: list[str] | None = None) -> int:
+    parser = argparse.ArgumentParser(description="Clean up stale Gitea runner registrations")
+    parser.add_argument("--gitea-url", required=True, help="Gitea base URL")
+    parser.add_argument("--token", required=True, help="Gitea admin API token")
+    parser.add_argument(
+        "--stale-threshold",
+        type=int,
+        default=3600,
+        help="Seconds since last_online before a runner is considered stale (default: 3600 = 1h)",
+    )
+    parser.add_argument("--dry-run", action="store_true", help="List stale runners without deleting")
+    args = parser.parse_args(argv)
+
+    runners = list_runners(args.gitea_url, args.token)
+    if not runners:
+        print("No runners found.")
+        return 0
+
+    now = int(time.time())
+    stale: list[dict[str, Any]] = []
+    online: list[dict[str, Any]] = []
+
+    for runner in runners:
+        last_online = runner.get("last_online", 0) or 0
+        seconds_since = now - last_online
+        runner["seconds_since_online"] = seconds_since
+        if seconds_since > args.stale_threshold:
+            stale.append(runner)
+        else:
+            online.append(runner)
+
+    print(f"Total runners: {len(runners)}")
+    print(f"Online (within {args.stale_threshold}s): {len(online)}")
+    print(f"Stale (>{args.stale_threshold}s): {len(stale)}")
+    print()
+
+    if not stale:
+        print("No stale runners to clean up.")
+        return 0
+
+    print("Stale runners:")
+    for r in stale:
+        rid = r.get("id", "?")
+        name = r.get("name", "?")
+        uuid = r.get("uuid", "?")[:8]
+        secs = r.get("seconds_since_online", 0)
+        hours = secs / 3600
+        print(f"  id={rid} name={name} uuid={uuid}... offline={hours:.1f}h ago")
+
+    if args.dry_run:
+        print("\n--dry-run: not deleting. Remove --dry-run to clean up.")
+        return 0
+
+    print(f"\nDeleting {len(stale)} stale runners...")
+    deleted = 0
+    for r in stale:
+        rid = r.get("id")
+        if rid is None:
+            continue
+        if delete_runner(args.gitea_url, args.token, rid):
+            deleted += 1
+            print(f"  Deleted runner id={rid} ({r.get('name', '?')})")
+
+    print(f"\nDone: {deleted}/{len(stale)} stale runners deleted.")
+    return 0 if deleted == len(stale) else 1
+
+
+if __name__ == "__main__":  # pragma: no cover
+    sys.exit(main())

scripts/tests/test_cleanup_stale_runners.py

@@ -0,0 +1,217 @@
+"""Tests for cleanup_stale_runners.py."""
+
+from __future__ import annotations
+
+import time
+from unittest.mock import MagicMock, patch
+
+from scripts.cleanup_stale_runners import (
+    _api_request,
+    delete_runner,
+    list_runners,
+    main,
+)
+
+
+class TestListRunners:
+    """Tests for list_runners()."""
+
+    @patch("scripts.cleanup_stale_runners._api_request")
+    def test_returns_list_of_runners(self, mock_req: MagicMock) -> None:
+        mock_req.return_value = [{"id": 1, "name": "runner-1"}, {"id": 2, "name": "runner-2"}]
+        result = list_runners("https://git.example.com", "token")
+        assert len(result) == 2
+        assert result[0]["id"] == 1
+
+    @patch("scripts.cleanup_stale_runners._api_request")
+    def test_returns_empty_on_none(self, mock_req: MagicMock) -> None:
+        mock_req.return_value = None
+        result = list_runners("https://git.example.com", "token")
+        assert result == []
+
+    @patch("scripts.cleanup_stale_runners._api_request")
+    def test_extracts_runners_from_dict(self, mock_req: MagicMock) -> None:
+        mock_req.return_value = {"runners": [{"id": 1}]}
+        result = list_runners("https://git.example.com", "token")
+        assert len(result) == 1
+        assert result[0]["id"] == 1
+
+    @patch("scripts.cleanup_stale_runners._api_request")
+    def test_returns_empty_on_non_list_non_dict(self, mock_req: MagicMock) -> None:
+        mock_req.return_value = "not a list"
+        result = list_runners("https://git.example.com", "token")
+        assert result == []
+
+
+class TestDeleteRunner:
+    """Tests for delete_runner()."""
+
+    @patch("scripts.cleanup_stale_runners._api_request")
+    def test_returns_true_on_success(self, mock_req: MagicMock) -> None:
+        mock_req.return_value = None
+        assert delete_runner("https://git.example.com", "token", 42) is True
+
+    @patch("scripts.cleanup_stale_runners._api_request")
+    def test_returns_false_on_error(self, mock_req: MagicMock) -> None:
+        mock_req.side_effect = RuntimeError("API error 404: not found")
+        assert delete_runner("https://git.example.com", "token", 42) is False
+
+
+class TestApiRequest:
+    """Tests for _api_request()."""
+
+    @patch("scripts.cleanup_stale_runners.urllib.request.urlopen")
+    def test_returns_json_on_success(self, mock_urlopen: MagicMock) -> None:
+        mock_resp = MagicMock()
+        mock_resp.status = 200
+        mock_resp.read.return_value = b'{"key": "value"}'
+        mock_urlopen.return_value.__enter__.return_value = mock_resp
+        result = _api_request("https://git.example.com", "token", "GET", "/test")
+        assert result == {"key": "value"}
+
+    @patch("scripts.cleanup_stale_runners.urllib.request.urlopen")
+    def test_returns_none_on_204(self, mock_urlopen: MagicMock) -> None:
+        mock_resp = MagicMock()
+        mock_resp.status = 204
+        mock_urlopen.return_value.__enter__.return_value = mock_resp
+        result = _api_request("https://git.example.com", "token", "DELETE", "/test/1")
+        assert result is None
+
+    @patch("scripts.cleanup_stale_runners.urllib.request.urlopen")
+    def test_returns_none_on_empty_body(self, mock_urlopen: MagicMock) -> None:
+        mock_resp = MagicMock()
+        mock_resp.status = 200
+        mock_resp.read.return_value = b""
+        mock_urlopen.return_value.__enter__.return_value = mock_resp
+        result = _api_request("https://git.example.com", "token", "GET", "/test")
+        assert result is None
+
+    @patch("scripts.cleanup_stale_runners.urllib.request.urlopen")
+    def test_raises_on_http_error(self, mock_urlopen: MagicMock) -> None:
+        import urllib.error
+
+        mock_error = urllib.error.HTTPError(
+            "url",
+            404,
+            "Not Found",
+            {},
+            None,
+        )
+        mock_error.read = MagicMock(return_value=b'{"message": "not found"}')
+        mock_urlopen.side_effect = mock_error
+        import pytest
+
+        with pytest.raises(RuntimeError, match="404"):
+            _api_request("https://git.example.com", "token", "GET", "/test")
+
+
+class TestMain:
+    """Tests for main()."""
+
+    @patch("scripts.cleanup_stale_runners.list_runners")
+    def test_no_runners(self, mock_list: MagicMock) -> None:
+        mock_list.return_value = []
+        rc = main(["--gitea-url", "https://git.example.com", "--token", "t"])
+        assert rc == 0
+
+    @patch("scripts.cleanup_stale_runners.list_runners")
+    def test_no_stale_runners(self, mock_list: MagicMock) -> None:
+        now = int(time.time())
+        mock_list.return_value = [
+            {"id": 1, "name": "runner-1", "last_online": now - 60},
+        ]
+        rc = main(["--gitea-url", "https://git.example.com", "--token", "t"])
+        assert rc == 0
+
+    @patch("scripts.cleanup_stale_runners.list_runners")
+    def test_dry_run_does_not_delete(self, mock_list: MagicMock) -> None:
+        now = int(time.time())
+        mock_list.return_value = [
+            {"id": 1, "name": "runner-1", "last_online": now - 7200},
+        ]
+        with patch("scripts.cleanup_stale_runners.delete_runner") as mock_del:
+            rc = main(
+                [
+                    "--gitea-url",
+                    "https://git.example.com",
+                    "--token",
+                    "t",
+                    "--dry-run",
+                ]
+            )
+            assert rc == 0
+            mock_del.assert_not_called()
+
+    @patch("scripts.cleanup_stale_runners.list_runners")
+    @patch("scripts.cleanup_stale_runners.delete_runner")
+    def test_deletes_stale_runners(self, mock_del: MagicMock, mock_list: MagicMock) -> None:
+        now = int(time.time())
+        mock_list.return_value = [
+            {"id": 1, "name": "runner-1", "last_online": now - 60},
+            {"id": 2, "name": "runner-2", "last_online": now - 7200},
+            {"id": 3, "name": "runner-3", "last_online": now - 9999},
+        ]
+        mock_del.return_value = True
+        rc = main(
+            [
+                "--gitea-url",
+                "https://git.example.com",
+                "--token",
+                "t",
+                "--stale-threshold",
+                "3600",
+            ]
+        )
+        assert rc == 0
+        assert mock_del.call_count == 2
+
+    @patch("scripts.cleanup_stale_runners.list_runners")
+    @patch("scripts.cleanup_stale_runners.delete_runner")
+    def test_returns_1_on_partial_failure(self, mock_del: MagicMock, mock_list: MagicMock) -> None:
+        now = int(time.time())
+        mock_list.return_value = [
+            {"id": 1, "name": "runner-1", "last_online": now - 7200},
+            {"id": 2, "name": "runner-2", "last_online": now - 7200},
+        ]
+        mock_del.side_effect = [True, False]
+        rc = main(["--gitea-url", "https://git.example.com", "--token", "t"])
+        assert rc == 1
+
+    @patch("scripts.cleanup_stale_runners.list_runners")
+    def test_runner_with_zero_last_online(self, mock_list: MagicMock) -> None:
+        """Runners with last_online=0 should be considered stale."""
+        mock_list.return_value = [
+            {"id": 1, "name": "runner-1", "last_online": 0},
+        ]
+        with patch("scripts.cleanup_stale_runners.delete_runner") as mock_del:
+            mock_del.return_value = True
+            rc = main(["--gitea-url", "https://git.example.com", "--token", "t"])
+            assert rc == 0
+            mock_del.assert_called_once()
+
+    @patch("scripts.cleanup_stale_runners.list_runners")
+    def test_runner_with_missing_last_online(self, mock_list: MagicMock) -> None:
+        """Runners with missing last_online should be considered stale."""
+        mock_list.return_value = [
+            {"id": 1, "name": "runner-1"},
+        ]
+        with patch("scripts.cleanup_stale_runners.delete_runner") as mock_del:
+            mock_del.return_value = True
+            rc = main(["--gitea-url", "https://git.example.com", "--token", "t"])
+            assert rc == 0
+            mock_del.assert_called_once()
+
+    @patch("scripts.cleanup_stale_runners.list_runners")
+    @patch("scripts.cleanup_stale_runners.delete_runner")
+    def test_skips_runner_with_none_id(self, mock_del: MagicMock, mock_list: MagicMock) -> None:
+        """Runners with id=None should be skipped during deletion."""
+        now = int(time.time())
+        mock_list.return_value = [
+            {"id": None, "name": "bad-runner", "last_online": now - 7200},
+            {"id": 2, "name": "runner-2", "last_online": now - 7200},
+        ]
+        mock_del.return_value = True
+        rc = main(["--gitea-url", "https://git.example.com", "--token", "t"])
+        # 1/2 deleted (None id skipped), so rc=1 (partial)
+        assert rc == 1
+        mock_del.assert_called_once_with("https://git.example.com", "t", 2)

src/grm/__init__.py

@@ -1,3 +1,3 @@
 """Gitea Runner Manager — lean CLI for managing Gitea Actions runners."""
 
-__version__ = "0.18.2"
+__version__ = "0.20.0"

src/grm/cli.py

@@ -145,11 +145,25 @@ def cli(ctx: click.Context, become_password_file: str | None, verbose: bool) ->
         "Example: docker:docker://alpine:latest"
     ),
 )
+@click.option(
+    "--force-reregister/--no-force-reregister",
+    default=False,
+    help=_("Force re-registration even if .runner file exists (env: GITEA_FORCE_REREGISTER)"),
+)
 @click.option(
     "--ask-become-pass/--no-ask-become-pass",
     default=True,
     help=_("Prompt for sudo password (default)"),
 )
+@click.option(
+    "--auto-recover-token",
+    default=None,
+    help=_(
+        "Gitea API token for healthcheck auto-recovery (env: GITEA_AUTO_RECOVER_TOKEN). "
+        "When set, the healthcheck can automatically re-register the runner "
+        "if it becomes unregistered. Requires admin or org-level access."
+    ),
+)
 @_handle_errors("Installation failed: {error}")
 def install(
     host: str,
@@ -161,10 +175,14 @@ def install(
     admin_token: str | None,
     integration_retries: int,
     labels: str | None,
+    force_reregister: bool,
     ask_become_pass: bool,
+    auto_recover_token: str | None,
 ) -> None:
     if labels is None:
         labels = os.getenv("GITEA_RUNNER_LABELS")
+    if auto_recover_token is None:
+        auto_recover_token = os.getenv("GITEA_AUTO_RECOVER_TOKEN")
     manager = RunnerManager()
     manager.install(
         host=host,
@@ -176,9 +194,11 @@ def install(
         admin_token=admin_token,
         integration_retries=integration_retries,
         labels=labels,
+        force_reregister=force_reregister,
         ask_become_pass=ask_become_pass,
         become_password_file=_get_become_password_file(),
         verbose=_get_verbose(),
+        auto_recover_token=auto_recover_token,
     )
 
 
@@ -506,7 +526,7 @@ def list_runners(ask_become_pass: bool, no_status: bool) -> None:
     click.echo(f"{_('NAME'):<18} {_('HOST'):<16} {_('USER'):<10} {_('LABELS'):<30} {_('STATUS')}")
     click.echo("-" * 90)
     for r in runners:
-        click.echo(f"{r['name']:<18} {r['host']:<16} {r['user']:<10} {r['labels']:<30} {r['status']}")
+        click.echo(f"{r['name']:<18} {r['host']:<16} {r['user']:<10} {(r['labels'] or ''):<30} {r['status']}")
 
 
 @cli.command(name="trigger-workflow", help=_("Trigger a Gitea Actions workflow via the API."))

src/grm/runner_manager.py

@@ -87,8 +87,10 @@ class RunnerManager:
         integration_retries: int = 3,
         ask_become_pass: bool = False,
         labels: str | None = None,
+        force_reregister: bool = False,
         become_password_file: str | None = None,
         verbose: bool = False,
+        auto_recover_token: str | None = None,
     ) -> None:
         """Install a runner on a remote host using Ansible."""
         if not name:
@@ -98,16 +100,19 @@ class RunnerManager:
         if not token:
             raise AnsibleError(_("GITEA_REGISTRATION_TOKEN must be set (or pass --token)"))
 
-        extra_vars: dict[str, str | int] = {
+        extra_vars: dict[str, str | int | bool] = {
             "registration_token": token,
             "gitea_runner_name": name,
             "gitea_url": gitea_url,
             "gitea_runner_integration_retries": integration_retries,
+            "gitea_runner_force_reregister": force_reregister,
         }
         if admin_token:
             extra_vars["gitea_admin_token"] = admin_token
         if labels is not None:
             extra_vars["gitea_runner_labels"] = labels
+        if auto_recover_token:
+            extra_vars["gitea_runner_auto_recover_api_token"] = auto_recover_token
 
         with track_steps() as tracker:
             tracker.begin(_("Installing Gitea Runner on {host}", host=host))

src/grm/translations.json

@@ -367,6 +367,14 @@
     "ru": "Токен регистрации (env: GITEA_REGISTRATION_TOKEN)",
     "zh": "注册令牌（环境变量: GITEA_REGISTRATION_TOKEN）"
   },
+  "Force re-registration even if .runner file exists (env: GITEA_FORCE_REREGISTER)": {
+    "bg": "Принудителна повторна регистрация, дори ако .runner файлът съществува (env: GITEA_FORCE_REREGISTER)",
+    "de": "Erneute Registrierung erzwingen, auch wenn .runner-Datei existiert (env: GITEA_FORCE_REREGISTER)",
+    "en": "Force re-registration even if .runner file exists (env: GITEA_FORCE_REREGISTER)",
+    "pl": "Wymuś ponowną rejestrację, nawet jeśli plik .runner istnieje (env: GITEA_FORCE_REREGISTER)",
+    "ru": "Принудительно повторно зарегистрировать, даже если файл .runner существует (env: GITEA_FORCE_REREGISTER)",
+    "zh": "即使存在 .runner 文件也强制重新注册（环境变量: GITEA_FORCE_REREGISTER）"
+  },
   "Remove a registered Gitea Runner completely.": {
     "bg": "Пълно премахване на регистриран Gitea Runner.",
     "de": "Einen registrierten Gitea Runner vollständig entfernen.",
@@ -774,5 +782,13 @@
     "pl": "Workflow uruchomiony pomyślnie. ID uruchomienia: {run_id}",
     "ru": "Workflow успешно запущен. ID запуска: {run_id}",
     "zh": "工作流触发成功。运行 ID：{run_id}"
+  },
+  "Gitea API token for healthcheck auto-recovery (env: GITEA_AUTO_RECOVER_TOKEN). When set, the healthcheck can automatically re-register the runner if it becomes unregistered. Requires admin or org-level access.": {
+    "bg": "Gitea API token for healthcheck auto-recovery (env: GITEA_AUTO_RECOVER_TOKEN). When set, the healthcheck can automatically re-register the runner if it becomes unregistered. Requires admin or org-level access.",
+    "de": "Gitea API token for healthcheck auto-recovery (env: GITEA_AUTO_RECOVER_TOKEN). When set, the healthcheck can automatically re-register the runner if it becomes unregistered. Requires admin or org-level access.",
+    "en": "Gitea API token for healthcheck auto-recovery (env: GITEA_AUTO_RECOVER_TOKEN). When set, the healthcheck can automatically re-register the runner if it becomes unregistered. Requires admin or org-level access.",
+    "pl": "Gitea API token for healthcheck auto-recovery (env: GITEA_AUTO_RECOVER_TOKEN). When set, the healthcheck can automatically re-register the runner if it becomes unregistered. Requires admin or org-level access.",
+    "ru": "Gitea API token for healthcheck auto-recovery (env: GITEA_AUTO_RECOVER_TOKEN). When set, the healthcheck can automatically re-register the runner if it becomes unregistered. Requires admin or org-level access.",
+    "zh": "Gitea API token for healthcheck auto-recovery (env: GITEA_AUTO_RECOVER_TOKEN). When set, the healthcheck can automatically re-register the runner if it becomes unregistered. Requires admin or org-level access."
   }
 }

tests/unit/test_cli.py

@@ -50,9 +50,11 @@ class TestCLI:
             admin_token="",
             integration_retries=3,
             labels=None,
+            force_reregister=False,
             ask_become_pass=True,
             become_password_file=None,
             verbose=False,
+            auto_recover_token=None,
         )
 
     @patch("grm.cli.RunnerManager")
@@ -73,9 +75,11 @@ class TestCLI:
             admin_token="",
             integration_retries=3,
             labels=None,
+            force_reregister=False,
             ask_become_pass=False,
             become_password_file=None,
             verbose=False,
+            auto_recover_token=None,
         )
 
     @patch("grm.cli.RunnerManager")
@@ -114,9 +118,11 @@ class TestCLI:
                 admin_token=None,
                 integration_retries=3,
                 labels=None,
+                force_reregister=False,
                 ask_become_pass=True,
                 become_password_file=None,
                 verbose=False,
+                auto_recover_token=None,
             )
 
     @patch("grm.cli.RunnerManager")
@@ -165,9 +171,11 @@ class TestCLI:
             admin_token="",
             integration_retries=3,
             labels=None,
+            force_reregister=False,
             ask_become_pass=True,
             become_password_file=None,
             verbose=False,
+            auto_recover_token=None,
         )
 
     @patch("grm.cli.RunnerManager")
@@ -188,9 +196,11 @@ class TestCLI:
             admin_token="",
             integration_retries=3,
             labels=None,
+            force_reregister=False,
             ask_become_pass=True,
             become_password_file=None,
             verbose=False,
+            auto_recover_token=None,
         )
 
     @patch("grm.cli.RunnerManager")
@@ -226,9 +236,92 @@ class TestCLI:
             admin_token="",
             integration_retries=3,
             labels="docker:docker://alpine:latest",
+            force_reregister=False,
             ask_become_pass=True,
             become_password_file=None,
             verbose=False,
+            auto_recover_token=None,
+        )
+
+    @patch("grm.cli.RunnerManager")
+    def test_install_force_reregister(self, mock_manager_class: MagicMock) -> None:
+        mock_manager = MagicMock()
+        mock_manager_class.return_value = mock_manager
+
+        runner = CliRunner(env=_TEST_ENV)
+        result = runner.invoke(cli, ["install", "host1", "--user", "ubuntu", "--token", "tok", "--force-reregister"])
+        assert result.exit_code == 0
+        mock_manager.install.assert_called_once_with(
+            host="host1",
+            user="ubuntu",
+            key=None,
+            name=None,
+            token="tok",
+            gitea_url="https://git.example.com",
+            admin_token="",
+            integration_retries=3,
+            labels=None,
+            force_reregister=True,
+            ask_become_pass=True,
+            become_password_file=None,
+            verbose=False,
+            auto_recover_token=None,
+        )
+
+    @patch("grm.cli.RunnerManager")
+    def test_install_with_auto_recover_token(self, mock_manager_class: MagicMock) -> None:
+        """--auto-recover-token passes the token to the manager for healthcheck auto-recovery."""
+        mock_manager = MagicMock()
+        mock_manager_class.return_value = mock_manager
+
+        runner = CliRunner(env=_TEST_ENV)
+        result = runner.invoke(
+            cli,
+            ["install", "host1", "--user", "ubuntu", "--token", "tok", "--auto-recover-token", "api-tok"],
+        )
+        assert result.exit_code == 0
+        mock_manager.install.assert_called_once_with(
+            host="host1",
+            user="ubuntu",
+            key=None,
+            name=None,
+            token="tok",
+            gitea_url="https://git.example.com",
+            admin_token="",
+            integration_retries=3,
+            labels=None,
+            force_reregister=False,
+            ask_become_pass=True,
+            become_password_file=None,
+            verbose=False,
+            auto_recover_token="api-tok",
+        )
+
+    @patch("grm.cli.RunnerManager")
+    def test_install_auto_recover_token_from_env(self, mock_manager_class: MagicMock) -> None:
+        """GITEA_AUTO_RECOVER_TOKEN env var is used when --auto-recover-token is not passed."""
+        mock_manager = MagicMock()
+        mock_manager_class.return_value = mock_manager
+
+        env = {**_TEST_ENV, "GITEA_AUTO_RECOVER_TOKEN": "env-tok"}
+        runner = CliRunner(env=env)
+        result = runner.invoke(cli, ["install", "host1", "--user", "ubuntu", "--token", "tok"])
+        assert result.exit_code == 0
+        mock_manager.install.assert_called_once_with(
+            host="host1",
+            user="ubuntu",
+            key=None,
+            name=None,
+            token="tok",
+            gitea_url="https://git.example.com",
+            admin_token="",
+            integration_retries=3,
+            labels=None,
+            force_reregister=False,
+            ask_become_pass=True,
+            become_password_file=None,
+            verbose=False,
+            auto_recover_token="env-tok",
         )
 
     @patch("grm.cli.RunnerManager")
@@ -250,9 +343,11 @@ class TestCLI:
             admin_token="",
             integration_retries=3,
             labels="",
+            force_reregister=False,
             ask_become_pass=True,
             become_password_file=None,
             verbose=False,
+            auto_recover_token=None,
         )
 
     @patch("grm.cli.RunnerManager")
@@ -274,9 +369,11 @@ class TestCLI:
             admin_token="",
             integration_retries=3,
             labels="docker:docker://alpine:latest",
+            force_reregister=False,
             ask_become_pass=True,
             become_password_file=None,
             verbose=False,
+            auto_recover_token=None,
         )
 
     @patch("grm.cli.RunnerManager")
@@ -307,9 +404,11 @@ class TestCLI:
                 admin_token="",
                 integration_retries=3,
                 labels=None,
+                force_reregister=False,
                 ask_become_pass=True,
                 become_password_file=pw_file,
                 verbose=False,
+                auto_recover_token=None,
             )
         finally:
             import os
@@ -334,9 +433,11 @@ class TestCLI:
             admin_token="",
             integration_retries=3,
             labels=None,
+            force_reregister=False,
             ask_become_pass=True,
             become_password_file=None,
             verbose=True,
+            auto_recover_token=None,
         )
 
     @patch("grm.cli.RunnerManager")
@@ -741,6 +842,27 @@ class TestCLI:
         assert "active" in result.output
         mock_manager.list_runners.assert_called_once_with(become_pass=None, no_status=False)
 
+    @patch("grm.cli.RunnerManager")
+    def test_list_with_none_labels(self, mock_manager_class: MagicMock) -> None:
+        """Runners with labels=None should not crash the list command."""
+        mock_manager = MagicMock()
+        mock_manager.list_runners.return_value = [
+            {
+                "name": "r1",
+                "host": "10.0.0.1",
+                "user": "ubuntu",
+                "labels": None,
+                "status": "active",
+            },
+        ]
+        mock_manager_class.return_value = mock_manager
+
+        runner = CliRunner()
+        result = runner.invoke(cli, ["list"])
+        assert result.exit_code == 0
+        assert "r1" in result.output
+        assert "active" in result.output
+
     @patch("grm.cli.RunnerManager")
     def test_list_no_status(self, mock_manager_class: MagicMock) -> None:
         """--no-status skips SSH checks and shows registry only."""

tests/unit/test_runner_manager.py

@@ -51,6 +51,7 @@ class TestRunnerManager:
         assert manager._captured_extra_vars["registration_token"] == "tok"
         assert manager._captured_extra_vars["gitea_runner_name"] == "192.168.1.10"
         assert manager._captured_extra_vars["gitea_url"] == "https://git.example.com"
+        assert manager._captured_extra_vars["gitea_runner_force_reregister"] is False
         assert "Installing Gitea Runner on 192.168.1.10" in mock_executor.run.call_args.kwargs["description"]
         mock_registry.add.assert_called_once_with(
             name="192.168.1.10",
@@ -76,6 +77,7 @@ class TestRunnerManager:
         assert "/key" in cmd_str
         assert manager._captured_extra_vars["registration_token"] == "preset"
         assert manager._captured_extra_vars["gitea_runner_name"] == "my-runner"
+        assert manager._captured_extra_vars["gitea_runner_force_reregister"] is False
         assert "--ask-become-pass" not in cmd_str
         mock_registry.add.assert_called_once_with(
             name="my-runner",
@@ -97,6 +99,52 @@ class TestRunnerManager:
         cmd_str = " ".join(cmd)
         assert "--ask-become-pass" in cmd_str
 
+    def test_install_force_reregister(self) -> None:
+        mock_registry = MagicMock()
+        manager = RunnerManager(registry=mock_registry)
+        mock_executor = MagicMock()
+        manager._executor = mock_executor
+
+        manager.install(
+            "host1",
+            "root",
+            token="tok",
+            gitea_url="https://git.example.com",
+            force_reregister=True,
+        )
+        assert manager._captured_extra_vars["gitea_runner_force_reregister"] is True
+
+    def test_install_with_auto_recover_token(self) -> None:
+        """auto_recover_token is passed as extra_var to Ansible."""
+        mock_registry = MagicMock()
+        manager = RunnerManager(registry=mock_registry)
+        mock_executor = MagicMock()
+        manager._executor = mock_executor
+
+        manager.install(
+            "host1",
+            "root",
+            token="tok",
+            gitea_url="https://git.example.com",
+            auto_recover_token="api-tok",
+        )
+        assert manager._captured_extra_vars["gitea_runner_auto_recover_api_token"] == "api-tok"
+
+    def test_install_without_auto_recover_token(self) -> None:
+        """When auto_recover_token is None, the extra_var is not set."""
+        mock_registry = MagicMock()
+        manager = RunnerManager(registry=mock_registry)
+        mock_executor = MagicMock()
+        manager._executor = mock_executor
+
+        manager.install(
+            "host1",
+            "root",
+            token="tok",
+            gitea_url="https://git.example.com",
+        )
+        assert "gitea_runner_auto_recover_api_token" not in manager._captured_extra_vars
+
     def test_install_missing_gitea_url(self) -> None:
         manager = RunnerManager()
         with pytest.raises(AnsibleError, match="GITEA_URL must be set"):