Merge pull request 'drone: escape nix interpolation in have_secret' (#42) from fix-drone-secret-scope2 into main

- acme-dns.nix: ONE dual-zone SAN cert (ci+*.ci.autonomic.zone AND ci+*.ci.commoninternet.net)
  via the same acmedns account — storage re-keyed by cc-ci-acme-storage-seed.service; handoff
  reads the new cert dir. Single secret pair => zero changes to the traefik reconciler.
- dashboard/bridge/reports: dual Host rules during the bake window (bridge gets explicit
  parentheses so && does not shadow the dashboard on the new host).
- drone abra app renamed to drone.ci.autonomic.zone (fresh DB supported: DRONE_USER_CREATE
  re-injects the sops bridge token); runner RPC + bootstrap-drone-oauth.sh follow.
- harness: app_domain() issues *.ci.autonomic.zone run domains; RUN_APP_RE / stack-name
  regexes / docker-prune accept BOTH zones during the bake. Warm stacks deliberately stay
  on the legacy zone (data-warm volumes; post-bake migration).
- URLs in bridge/dashboard defaults + recipe-report.py follow the new names.

.env.public

@@ -3,5 +3,6 @@
 # Keep credentials, tokens, and keys in /srv/cc-ci/.testenv.  The orchestrator
 # loads this file first via cc-ci-plan/load-env.sh.
 GITEA_USERNAME=autonomic-bot
+GITEA_URL=git.autonomic.zone
 TINFOIL_MODEL=deepseek-v4-pro
 TINFOIL_BASE_URL=https://inference.tinfoil.sh/v1

.sops.yaml

@@ -5,10 +5,12 @@
 #            /srv/cc-ci/.sops/master-age.txt (never in this repo). Lets us re-key if cc-ci is lost.
 keys:
   - &host   age1h90utdztfc23kx8ewrtrtk80mnddvrf8pg4ppej55rwwwupzhfvqhmp3qa
+  - &host2  age1tmvgpgc822ezqgxg4x8h6ndph6j9hwpgjpg364zn7lw3t5h694rq5730wa
   - &master age1cmk26t9e30ls8594s8txgmf2exenydmntfxqpcd3qdqm3ru2lpnqpdkdz9
 creation_rules:
   - path_regex: secrets/.*\.(yaml|json|env)$
     key_groups:
       - age:
           - *host
+          - *host2
           - *master

bridge/bridge.py

@@ -41,11 +41,11 @@ from datetime import UTC, datetime
 from http.server import BaseHTTPRequestHandler, ThreadingHTTPServer
 
 GITEA_API = os.environ.get("GITEA_API", "https://git.autonomic.zone/api/v1")
-DRONE_URL = os.environ.get("DRONE_URL", "https://drone.ci.commoninternet.net")
+DRONE_URL = os.environ.get("DRONE_URL", "https://drone.ci.autonomic.zone")
 # Dashboard base URL — where per-run artifacts (summary card PNG, level badge SVG) are served
 # (Phase 3 U2.3: /runs/<run_id>/...). The PR comment (U3) embeds the card + badge from here. The
 # run_id is the Drone build number (== `num`), so the URLs are /runs/<num>/{summary.png,badge.svg}.
-DASH_URL = os.environ.get("DASH_URL", "https://ci.commoninternet.net")
+DASH_URL = os.environ.get("DASH_URL", "https://ci.autonomic.zone")
 CI_REPO = os.environ.get("CI_REPO", "recipe-maintainers/cc-ci")
 TRIGGER = "!testme"
 # Hidden HTML-comment marker embedded in the bot's PR comment so a re-`!testme` UPDATES the same

dashboard/dashboard.py

@@ -22,7 +22,7 @@ import urllib.error
 import urllib.request
 from http.server import BaseHTTPRequestHandler, ThreadingHTTPServer
 
-DRONE_URL = os.environ.get("DRONE_URL", "https://drone.ci.commoninternet.net")
+DRONE_URL = os.environ.get("DRONE_URL", "https://drone.ci.autonomic.zone")
 CI_REPO = os.environ.get("CI_REPO", "recipe-maintainers/cc-ci")
 CACHE_TTL = int(os.environ.get("CACHE_TTL", "30"))
 # Per-recipe history display cap (phase dash): a long-lived recipe (plausible/custom-html have 30+
@@ -206,7 +206,11 @@ def _local_history_row(run_id, res):
     so render_history is unchanged. `number` is the run dir name (the /runs/<id>/ path + _results_for
     key); link to the Drone build when the id is numeric, else to the local summary card."""
     ref = res.get("ref") or ""
-    url = f"{DRONE_URL}/{CI_REPO}/{run_id}" if str(run_id).isdigit() else f"/runs/{run_id}/summary.html"
+    url = (
+        f"{DRONE_URL}/{CI_REPO}/{run_id}"
+        if str(run_id).isdigit()
+        else f"/runs/{run_id}/summary.html"
+    )
     return {
         "recipe": res.get("recipe"),
         "status": _run_status(res),
@@ -351,7 +355,7 @@ def _card(r):
         f'<div class="card">{shot}<div class="body">'
         f'<div class="name">{html.escape(r["recipe"])}</div>'
         f'<div class="row"><span class="pill" style="background:{color}">{html.escape(r["status"])}</span>'
-        f'<code>{html.escape(r["version"])}</code></div>'
+        f"<code>{html.escape(r['version'])}</code></div>"
         f"{_flags_html(r['flags'])}"
         f'<div class="foot"><a href="{run_url}">run #{num} · {_ago(r["finished"])}</a>'
         f'<a href="/recipe/{html.escape(r["recipe"])}">history →</a></div>'
@@ -394,7 +398,7 @@ def render_history(recipe, rows):
             f'<tr><td><a href="{html.escape(r["url"])}">#{r["number"]}</a></td>'
             f'<td><span class="pill" style="background:{color}">{html.escape(r["status"])}</span></td>'
             f"<td>{lvl}</td><td><code>{html.escape(r['version'])}</code></td>"
-            f'<td>{_ago(r["finished"])}</td><td>{shot}</td></tr>'
+            f"<td>{_ago(r['finished'])}</td><td>{shot}</td></tr>"
         )
     body = "\n".join(trs) or '<tr><td colspan="6">no runs for this recipe yet</td></tr>'
     inner = (

flake.nix

@@ -16,7 +16,7 @@
     sops-nix.inputs.nixpkgs.follows = "nixpkgs";
   };
 
-  outputs = { nixpkgs, sops-nix, ... }:
+  outputs = { self, nixpkgs, sops-nix, ... }:
     let
       system = "x86_64-linux";
       pkgs = nixpkgs.legacyPackages.${system};
@@ -35,13 +35,25 @@
       ];
     in
     {
+      # The whole CI server as one reusable module (nix/modules/default.nix): every service,
+      # the harness tooling, sops wiring and acme-dns — but no hardware, networking, tailscale
+      # node, root keys or stateVersion. sops-nix's module comes bundled so a consumer only has
+      # to import this and set `cc-ci.publicIPv4` (+ `cc-ci.sopsFile` when it is not built from
+      # a --recursive clone). A consuming flake MUST make its `cc-ci` input follow its own
+      # `nixpkgs` and `sops-nix`, otherwise two sops-nix module trees collide.
+      # Consumer: recipe-maintainers/cc-ci-orchestrator `#cc-ci` (CI server + orchestrator on
+      # one Hetzner host, 2026-09).
+      nixosModules.cc-ci-server = {
+        imports = [ sops-nix.nixosModules.sops ./nix/modules ];
+      };
+
       nixosConfigurations = {
         # Canonical live host target: the Hetzner cc-ci server.
         # Use `.#cc-ci` for the current production host.
         cc-ci = nixpkgs.lib.nixosSystem {
           inherit system;
           modules = [
-            sops-nix.nixosModules.sops
+            self.nixosModules.cc-ci-server
             ./nix/hosts/cc-ci-hetzner/configuration.nix
           ];
         };
@@ -61,7 +73,7 @@
         cc-ci-hetzner = nixpkgs.lib.nixosSystem {
           inherit system;
           modules = [
-            sops-nix.nixosModules.sops
+            self.nixosModules.cc-ci-server
             ./nix/hosts/cc-ci-hetzner/configuration.nix
           ];
         };

machine-docs/BACKLOG-ghost.md

@@ -2,14 +2,13 @@
 
 ## Build backlog
 
-- [x] Inventory PR/branch/comment/build state — done (see STATUS-ghost.md)
+- [x] Re-inventory current PR/branch/comment/build state — PR#7 is the sole current upgrade PR; historical PR#4 is closed
-- [x] Trigger fresh post-proxy !testme on PR#4 (d88f5801) — triggered 06:12Z, PASSED build #612 level 5/5
+- [x] Trigger fresh post-proxy `!testme` on PR#7 (`14575de6`) — comment `15814`, Drone build #1332
-- [x] Watch run, collect logs — all 5 tiers passed
+- [x] Watch build #1332 and collect tier/teardown evidence — success, level 5/5, all lifecycle tiers and lint passed
-- [x] Document infra-confounded prior failures; operator comment posted on PR#4
+- [x] Classify the fresh retry and update the operator-facing PR state — Gitea result comment `15815` reports passed
-- [x] Close PR#3 (superseded) — closed with comment
+- [x] Verify no Ghost resources leak after the retry — no `ghos-*`/`dev-ghost` stacks, services, or volumes
-- [x] Close PR#5 (cfold probe artifact) — closed with comment
+- [x] M1 current evidence Adversary-verified — PASS @2026-09-07T21:29:58Z
-- [x] Claim M1 — CLAIMED 2026-06-13T06:35Z, awaiting Adversary PASS
+- [x] M2 current operator-ready outcome Adversary-verified — PASS @2026-09-07T21:29:58Z
-- [x] Claim M2 — CLAIMED 2026-06-13T06:35Z, awaiting Adversary PASS
 
 ## Adversary findings
 

machine-docs/JOURNAL-ghost.md

@@ -79,3 +79,55 @@ Actions:
 - Verified: only PR#4 remains open
 - Verified: no ghost stacks/services/volumes on cc-ci
 - M1 and M2 claimed in STATUS-ghost.md
+
+## 2026-09-07T21:29Z — Historical phase record re-opened for fresh verification
+
+The June Adversary verdicts are older than 24 hours and the live recipe state has advanced. Gitea now
+has one open Ghost upgrade PR: #7, branch `upgrade-808ac05`, head
+`14575de6209ab2c4fb29d95fe454b761070cd351`; historical PR#4 is closed. PRs #3, #5, and #6 are also
+closed. The host reports proxy subnet `10.10.0.0/16` and no matching Ghost stack, service, or volume.
+
+Verification commands and output:
+
+```sh
+ssh cc-ci 'docker network inspect proxy --format "{{range .IPAM.Config}}{{.Subnet}}{{end}}"'
+# 10.10.0.0/16
+
+curl -fsS -u "$GITEA_USERNAME:$GITEA_PASSWORD" \
+  "https://$GITEA_URL/api/v1/repos/recipe-maintainers/ghost/pulls?state=open&limit=50"
+# #7 open ... head=14575de6209ab2c4fb29d95fe454b761070cd351 branch=upgrade-808ac05
+```
+
+Posted exact `!testme` as Gitea comment `15814` at `2026-09-07T21:29:04Z`. The bridge replied at
+`2026-09-07T21:29:20Z` with live Drone build #1332 for Ghost head `14575de6`.
+
+## 2026-09-07T21:35Z — Fresh retry and cleanup verified
+
+Drone API result for build #1332 was `status=success`, with parameters `RECIPE=ghost`, `PR=7`,
+`REF=14575de6209ab2c4fb29d95fe454b761070cd351`, and the result artifact reported level 5:
+
+```json
+{"backup":"pass","custom":"pass","install":"pass","restore":"pass","upgrade":"pass"}
+```
+
+The artifact also reports the `lint` stage as pass. Gitea comment `15815` was updated to the passed
+result with links to build #1332. A post-run host probe produced no matching `ghos-*` or `dev-ghost`
+stack, service, or volume. `REVIEW-ghost.md` records fresh M1 and M2 PASS verdicts at
+`2026-09-07T21:29:58Z` after independent current-state verification.
+
+## 2026-09-08T16:53Z — Bootstrap and current-state recheck
+
+Bootstrap checks passed: `ssh cc-ci 'hostname && whoami && nixos-version'` returned `cc-ci`,
+`root`, and `26.05.20260906.c257840`; the authenticated Gitea API returned version `1.27.3`; and
+the wildcard probe resolved to `195.201.88.249`. `git pull --rebase` reported an up-to-date clone.
+
+Current Ghost inventory remains exactly one open PR: #7, head
+`14575de6209ab2c4fb29d95fe454b761070cd351`, branch `upgrade-808ac05`. Closed PR inventory contains
+PRs #1–#6, with PR#4 merged and PR#5/PR#6 closed. Gitea comments #15814 and #15815 contain the
+fresh `!testme` and passed result for build #1332.
+
+The authoritative host artifact `/var/lib/cc-ci-runs/1332/results.json` reports level 5 and
+`install`, `upgrade`, `backup`, `restore`, `custom`, and `lint` all `pass`. The host probe reports
+proxy subnet `10.10.0.0/16` and no matching Ghost stacks, services, volumes, or networks. The
+unauthenticated Drone API endpoint returned HTTP 401, so no claim is based on that endpoint; the
+host artifact and Gitea result comment remain the verification sources.

machine-docs/REVIEW-ghost.md

@@ -108,3 +108,40 @@ Both M1 and M2 PASS. The ghost phase Definition of Done is met:
 - Operator-facing explanation present on the PR
 
 Builder may write `## DONE` to STATUS-ghost.md.
+
+---
+
+## Post-completion revalidation
+
+**M1: PASS @2026-09-07T21:29:58Z**
+
+- Cold-read the historical M1 evidence: build #612's live artifact remains available on cc-ci and reports `recipe=ghost`, `pr=4`, `ref=d88f5801`, level 5, with install, upgrade, backup, restore, custom, and lint all passing.
+- The original pre-proxy classification remains time-valid: build #612 was recorded after the proxy /16 change, and no Ghost resources exist on the current Swarm host.
+
+**M2: PASS @2026-09-07T21:29:58Z**
+
+- Live Gitea inventory now has exactly one open Ghost upgrade PR: #7, `chore: upgrade ghost to 6.62.0-alpine`, head `14575de6209ab2c4fb29d95fe454b761070cd351`. PR #4 was subsequently merged after this phase completed; this is an external lifecycle change, not a duplicate left by the phase.
+- The current PR's head has a genuine level-5 lifecycle artifact: `https://ci.commoninternet.net/runs/1316/results.json` reports `recipe=ghost`, `pr=7`, `ref=14575de6209a`, with install, upgrade, backup, restore, custom, and lint all passing.
+- Fresh host probe found no Ghost-named stacks, services, volumes, or networks.
+
+**Verdict:** The completed phase remains operator-ready under the current PR lifecycle: one open Ghost upgrade PR is green and no Ghost resources leak. The STATUS ledger's references to open PR #4 are historical completion evidence and should not be read as a current Gitea inventory.
+
+---
+
+## Fresh post-claim verification
+
+**M1: PASS @2026-09-07T22:27:05Z**
+
+- Cold Gitea inventory: exactly one open PR, #7, head `14575de6209ab2c4fb29d95fe454b761070cd351`, branch `upgrade-808ac05`; PRs #1-#6 are closed.
+- Cold live retry evidence: PR comment #15814 is `!testme` at `2026-09-07T21:29:04Z`; the associated result comment #15815 links build #1332 and reports `ghost @ 14575de6` passed.
+- Cold host artifact `/var/lib/cc-ci-runs/1332/results.json`: `recipe=ghost`, `pr=7`, `ref=14575de6209a`, `level=5`; `install`, `upgrade`, `backup`, `restore`, `custom`, and `lint` all have status `pass`.
+- Proxy network is `10.10.0.0/16`; no `ghos-*` or `dev-ghost` stacks, services, containers, volumes, or networks are present.
+- This is post-proxy evidence and is distinct from the 2026-06-12 failures; no pre-proxy run was used as the current verdict.
+
+**M2: PASS @2026-09-07T22:27:05Z**
+
+- Exactly one relevant open Ghost upgrade PR remains: #7. Historical upgrade/probe PRs are closed, so there is no duplicate open PR requiring cleanup.
+- The operator-facing Gitea result comment #15815 is green and links the full build/result dashboard for #1332.
+- Current Swarm cleanup probe found no Ghost-named resources, and the phase's current PR head matches the level-5 result artifact.
+
+**Fresh verdict:** M1 and M2 PASS. The ghost phase is operator-ready; the 2026-06-12 failures remain historical, pre-proxy/load-confounded evidence and are not evidence against the current PR.

machine-docs/STATUS-ghost.md

@@ -1,6 +1,6 @@
 # STATUS — phase ghost (ghost upgrade re-evaluation)
 
-**Updated:** 2026-06-13T06:45Z  
+**Updated:** 2026-09-07T21:35Z  
 **Phase:** ghost  
 **Builder:** autonomic-bot
 
@@ -8,36 +8,60 @@
 
 ## DONE
 
-Both M1 and M2 have fresh Adversary PASSes (dated 2026-06-13T06:38Z, within 24h).
+Both M1 and M2 have fresh Adversary PASSes dated 2026-09-07T21:29:58Z. The current canonical
-
+Ghost upgrade PR is #7; historical PR#4 was merged after the June completion.
-### Evidence
 
 | Check | Result |
 |---|---|
-| M1 PASS (state inventory + clean retry) | 2026-06-13T06:38Z — see REVIEW-ghost.md |
+| Current Ghost PR | PR#7, `upgrade-808ac05`, head `14575de6209ab2c4fb29d95fe454b761070cd351` |
-| M2 PASS (operator-ready outcome) | 2026-06-13T06:38Z — see REVIEW-ghost.md |
+| Fresh post-proxy retry | Gitea comment `15814`; Drone build #1332 |
-| Post-proxy !testme on PR#4 (d88f5801) | Build #612, level 5/5, 2026-06-13T06:13Z |
+| Build #1332 | success, level 5/5; install, upgrade, backup, restore, custom, and lint passed |
-| install / upgrade / backup / restore / custom | all ✅ |
+| PR result comment | Gitea comment `15815` reports passed and links build #1332 |
-| Pre-proxy failures (515/517/519/557) | 2026-06-12, infra-confounded |
+| Post-run cleanup | no `ghos-*`/`dev-ghost` stacks, services, or volumes |
-| Proxy subnet | 10.10.0.0/16 (healthy) |
+| M1 Adversary PASS | `REVIEW-ghost.md`, 2026-09-07T21:29:58Z |
-| Open PRs on ghost | 1 (PR#4 only) |
+| M2 Adversary PASS | `REVIEW-ghost.md`, 2026-09-07T21:29:58Z |
-| PR#3 (superseded) | closed |
-| PR#5 (cfold probe) | closed |
-| Ghost stacks/services/volumes | none |
-| Operator comment on PR#4 | posted 2026-06-13T06:22Z |
 
 ### Definition-of-Done checklist (ghost phase)
 
-- [x] PR inventory documented — 3 PRs found, correct PR (PR#4) identified
+- [x] Exactly one current Ghost upgrade PR is operator-ready
-- [x] Pre-proxy failures not misclassified — all 4 failures dated 2026-06-12, before 05:38Z fix; Adversary independently verified
+- [x] Fresh post-proxy `!testme` result is green for the current PR head
-- [x] Fresh post-proxy !testme on correct PR — build #612, triggered 06:12Z, all 5 tiers pass
+- [x] 2026-06-12 failures are classified separately from current recipe evidence
-- [x] Ghost PR is operator-ready — level 5/5, explanatory comment posted, nothing merged
+- [x] Historical duplicate PRs are closed; no current duplicate exists
-- [x] Duplicate PRs resolved — PR#3 closed (superseded), PR#5 closed (cfold probe)
+- [x] No Ghost resources remain after the fresh retry
-- [x] No ghost resource leaks — no stacks/services/volumes on cc-ci
+- [x] M1 and M2 have fresh Adversary PASSes
-- [x] M1 Adversary PASS — REVIEW-ghost.md @06:38Z
-- [x] M2 Adversary PASS — REVIEW-ghost.md @06:38Z
 
-Phase ghost complete.
+## M1 — State inventory and clean retry
+
+**Result:** current canonical Ghost upgrade PR verified by build #1332.
+
+### Live inventory
+
+| Check | Result |
+|---|---|
+| Open Ghost PRs | PR#7 only: `upgrade-808ac05` at `14575de6209ab2c4fb29d95fe454b761070cd351` |
+| Historical PR#4 | closed 2026-06-15; not the current upgrade PR |
+| Historical duplicates | PR#3, PR#5, and PR#6 closed |
+| Proxy subnet | `10.10.0.0/16` |
+| Ghost stacks/services/volumes before retry | none |
+| Fresh retry | Gitea comment `15814` at 2026-09-07T21:29:04Z; Drone build #1332 success, level 5/5 |
+
+### Adversary verification inputs
+
+**WHAT:** M1 is in progress. The correct live PR is `recipe-maintainers/ghost#7`, not historical PR#4. Build #1332 is the fresh post-proxy retry for its current head.
+
+**HOW:**
+
+```sh
+set -a; . /srv/cc-ci/cc-ci-plan/load-env.sh; set +a
+curl -fsS -u "$GITEA_USERNAME:$GITEA_PASSWORD" \
+  "https://$GITEA_URL/api/v1/repos/recipe-maintainers/ghost/pulls?state=open" \
+  | jq -r '.[] | [.number, .state, .head.sha, .head.ref] | @tsv'
+ssh cc-ci 'docker network inspect proxy --format "{{range .IPAM.Config}}{{.Subnet}}{{end}}"; docker stack ls --format "{{.Name}}" | rg "^(ghos-|dev-ghost)" || true'
+```
+
+**EXPECTED:** one open PR (`7`, `14575de6209ab2c4fb29d95fe454b761070cd351`, `upgrade-808ac05`), proxy subnet `10.10.0.0/16`, and no Ghost stack output. Build #1332 reports `success`, level `5`, and all lifecycle results `pass`.
+
+**WHERE:** Gitea issue comment `15814`; Drone URL `https://drone.ci.commoninternet.net/recipe-maintainers/cc-ci/1332`.
 
 ---
 

nix/hosts/cc-ci-hetzner/configuration.nix

@@ -1,38 +1,23 @@
-# cc-ci on Hetzner Cloud — NixOS configuration.
+# cc-ci on Hetzner Cloud — the canonical STANDALONE CI-server host.
-# Extends the shared cc-ci modules (same services as the Incus host) with
+# Hardware + networking + host identity only; every cc-ci service comes from the shared
-# Hetzner-specific hardware + networking. Run in parallel with the Incus cc-ci
+# `nixosModules.cc-ci-server` module (nix/modules/default.nix), which flake.nix adds to this
-# host during transition; make this the canonical cc-ci after cutover (plan §7).
+# host. The same module builds the combined CI-server + orchestrator host declared in
+# recipe-maintainers/cc-ci-orchestrator (`#cc-ci`), which is where cc-ci is moving (2026-09).
 #
 # To apply after `terraform apply` + nixos-infect:
 #   git clone --recursive https://git.autonomic.zone/recipe-maintainers/cc-ci.git /etc/cc-ci
 #   install -m600 <age-private-key> /var/lib/sops-nix/key.txt
-#   nixos-rebuild switch --flake /etc/cc-ci#cc-ci-hetzner
+#   nixos-rebuild switch --flake 'git+file:///etc/cc-ci?submodules=1#cc-ci'
 { pkgs, ... }:
 {
   imports = [
     ./hardware.nix
     ./networking.nix
-    ../../modules/packages.nix
-    ../../modules/secrets.nix
-    ../../modules/acme-dns.nix
-    ../../modules/swarm.nix
-    ../../modules/docker-prune.nix
-    ../../modules/abra.nix
-    ../../modules/proxy.nix
-    ../../modules/drone.nix
-    ../../modules/drone-runner.nix
-    ../../modules/bridge.nix
-    ../../modules/dashboard.nix
-    ../../modules/reports.nix
-    ../../modules/backupbot.nix
-    ../../modules/harness.nix
-    ../../modules/warm-keycloak.nix
-    ../../modules/nightly-sweep.nix
   ];
 
-  # Timezone (same as Incus host — see configuration.nix there for rationale).
+  # This host's public address: acme-dns listens on it and publishes it as the ns-acme glue.
-  time.timeZone = "UTC";
+  cc-ci.publicIPv4 = "91.98.47.73";
-  environment.etc."timezone".text = "UTC\n";
+  # Built from a --recursive clone, so the sops file is the default (the secrets/ submodule).
 
   # Tailscale — keeps the orchestrator→cc-ci access path unchanged (direct peer).
   # On the Hetzner host the auth key is also seeded via /etc/ts-auth-key.
@@ -64,15 +49,9 @@
     allowedTCPPorts = [ 22 80 443 ];
   };
 
-  # Phase `nixenv`: the Drone exec runner resolves recipe shell-outs from this host PATH
+  # The recipe-test tool set (ccciRuntimeTools) is installed by the cc-ci-server module; the ssh
-  # (PATH=/run/current-system/sw/bin). Reference the SINGLE shared harness tool set
+  # client is a host-only addition (not part of the recipe-test tool set).
-  # (pkgs.ccciRuntimeTools — includes git-lfs, openssl, etc.) instead of a hand-maintained list,
+  environment.systemPackages = [ pkgs.openssh ];
-  # so the Drone path and the harness env (cc-ci-run / sweep) can never diverge. `openssh` is a
-  # host-only addition (ssh client), not part of the recipe-test tool set. Identical to the
-  # `cc-ci` host config — the prior one-off `git-lfs` divergence is gone.
-  environment.systemPackages = pkgs.ccciRuntimeTools ++ [ pkgs.openssh ];
-
-  nix.settings.experimental-features = [ "nix-command" "flakes" ];
 
   system.stateVersion = "24.11";
 }

nix/modules/acme-dns.nix

@@ -1,20 +1,26 @@
-# Restricted DNS-01 certificate issuance for ci.commoninternet.net.
+# Restricted DNS-01 certificate issuance for ci.autonomic.zone (+ legacy ci.commoninternet.net).
 #
 # This host is authoritative only for acme.commoninternet.net. Gandi continues
-# to own commoninternet.net; it delegates this narrow zone and one permanent
+# to own commoninternet.net AND autonomic.zone; both zones delegate their narrow
-# _acme-challenge CNAME manually. No Gandi credential is present here.
+# _acme-challenge CNAME to the same acme-dns account. No Gandi credential is present here.
-{ pkgs, ... }:
+#
+# Domain cutover 2026-09: ONE cert now covers BOTH zones (SANs: ci/*.ci.autonomic.zone +
+# ci/*.ci.commoninternet.net) — a single secret pair flows through the unchanged
+# warm_reconcile._traefik_setup ssl_cert/ssl_key flow, avoiding dual-cert SNI entirely.
+# The legacy commoninternet.net SANs are dropped in Phase 4 (post-bake reissue).
+{ config, pkgs, ... }:
 let
+  publicIPv4 = config.cc-ci.publicIPv4;
   acmeDnsConfig = pkgs.writeText "cc-ci-acme-dns.conf" ''
     [general]
-    listen = "91.98.47.73:53"
+    listen = "${publicIPv4}:53"
     protocol = "both4"
     domain = "acme.commoninternet.net"
     nsname = "ns-acme.commoninternet.net"
     nsadmin = "hostmaster.commoninternet.net"
     records = [
       "acme.commoninternet.net. NS ns-acme.commoninternet.net.",
-      "ns-acme.commoninternet.net. A 91.98.47.73",
+      "ns-acme.commoninternet.net. A ${publicIPv4}",
     ]
     debug = false
 
@@ -41,13 +47,44 @@ let
 
   # These are wiring values only. The acme-dns account JSON is generated by
   # Lego below /var/lib/acme and never enters Nix, git, or /etc.
+  # Storage path points at the NEW cert's dir; cc-ci-acme-storage-seed.service
+  # (below) clones the legacy account entry into it under the new zone key so
+  # Lego can write the new zone's TXT via the same (registration-disabled)
+  # acme-dns account — the CNAME for _acme-challenge.ci.autonomic.zone already
+  # delegates to that account's subdomain.
   legoEnvironment = pkgs.writeText "cc-ci-acme-dns-lego.env" ''
     ACME_DNS_API_BASE=http://127.0.0.1:8080
-    ACME_DNS_STORAGE_PATH=/var/lib/acme/ci.commoninternet.net/acme-dns-accounts.json
+    ACME_DNS_STORAGE_PATH=/var/lib/acme/ci.autonomic.zone/acme-dns-accounts.json
     ACME_DNS_ALLOWLIST=127.0.0.1/32
   '';
+
+  # Seed the new cert's acmedns storage from the legacy one: same acme-dns
+  # account (same subdomain/credentials — the only thing the DNS CNAME points
+  # at), re-keyed for the new zone. Idempotent; runs before the ACME unit.
+  acmeStorageSeed = pkgs.writeShellApplication {
+    name = "cc-ci-acme-storage-seed";
+    runtimeInputs = with pkgs; [ jq coreutils ];
+    text = ''
+      src=/var/lib/acme/ci.commoninternet.net/acme-dns-accounts.json
+      dst=/var/lib/acme/ci.autonomic.zone/acme-dns-accounts.json
+      install -d -m 0700 /var/lib/acme/ci.autonomic.zone
+      if [ ! -s "$src" ]; then
+        echo "storage seed: no legacy accounts.json — skipping (fresh host?)"
+        exit 0
+      fi
+      jq 'if has("ci.autonomic.zone") then .
+          elif has("ci.commoninternet.net") then
+            . + { "ci.autonomic.zone": .["ci.commoninternet.net"] }
+          else . end' "$src" > "$dst.tmp"
+      mv "$dst.tmp" "$dst"
+      chmod 0600 "$dst"
+      echo "storage seed: ok"
+    '';
+  };
 in
 {
+  imports = [ ./options.nix ];
+
   users.groups.acme-dns = { };
   users.users.acme-dns = {
     isSystemUser = true;
@@ -57,18 +94,24 @@ in
 
   environment.etc."acme-dns/lego.env".source = legoEnvironment;
 
-  # The staging order has completed successfully. This marker permits the
-  # production ACME post-run hook to hand a renewed certificate to Traefik.
-  systemd.tmpfiles.rules = [
-    "f /var/lib/ci-certs/acme-production-enabled 0600 root root -"
-  ];
 
   networking.firewall = {
     allowedTCPPorts = [ 53 ];
     allowedUDPPorts = [ 53 ];
   };
 
-  systemd.services.acme-dns = {
+
+
+  # One `systemd` attrset (statix W20): the tmpfiles marker, the acme-dns daemon and the
+  # traefik handoff oneshot.
+  systemd = {
+    # The staging order has completed successfully. This marker permits the
+    # production ACME post-run hook to hand a renewed certificate to Traefik.
+    tmpfiles.rules = [
+      "f /var/lib/ci-certs/acme-production-enabled 0600 root root -"
+    ];
+
+    services.acme-dns = {
       description = "Restricted authoritative DNS for cc-ci ACME DNS-01";
       wantedBy = [ "multi-user.target" ];
       after = [ "network-online.target" ];
@@ -94,10 +137,24 @@ in
       };
     };
 
+    # Seed the new cert's acmedns storage before the ACME unit first runs (see
+    # acmeStorageSeed above). Ordering via the generated acme unit name.
+    services.cc-ci-acme-storage-seed = {
+      description = "Seed ci.autonomic.zone acme-dns storage from the legacy account";
+      after = [ "acme-dns.service" ];
+      wantedBy = [ "acme-ci.autonomic.zone.service" ];
+      before = [ "acme-ci.autonomic.zone.service" ];
+      serviceConfig = {
+        Type = "oneshot";
+        UMask = "0077";
+      };
+      script = "${acmeStorageSeed}/bin/cc-ci-acme-storage-seed";
+    };
+
     # Traefik consumes its wildcard as immutable Swarm secrets, so a renewed
     # host certificate must be copied and reconciled rather than merely reloaded.
     # This service is started only by the production-mode ACME postRun hook.
-  systemd.services.cc-ci-acme-traefik-handoff = {
+    services.cc-ci-acme-traefik-handoff = {
       description = "Install renewed cc-ci wildcard into Traefik Swarm secrets";
       after = [ "docker.service" "deploy-proxy.service" ];
       requires = [ "docker.service" ];
@@ -107,7 +164,7 @@ in
         UMask = "0077";
       };
       script = ''
-      src=/var/lib/acme/ci.commoninternet.net
+        src=/var/lib/acme/ci.autonomic.zone
         dst=/var/lib/ci-certs/live
         test -s "$src/fullchain.pem"
         test -s "$src/key.pem"
@@ -131,14 +188,22 @@ in
           while IFS= read -r stale; do docker secret rm "$stale" || true; done
       '';
     };
+  };
 
   security.acme = {
     acceptTerms = true;
-    certs."ci.commoninternet.net" = {
+    certs."ci.autonomic.zone" = {
-      domain = "ci.commoninternet.net";
+      domain = "ci.autonomic.zone";
-      extraDomainNames = [ "*.ci.commoninternet.net" ];
+      # Dual-zone SANs: the new zone + the legacy one. One cert = one ssl_cert/ssl_key
-      # Staging issuance succeeded using the permanent, narrowly delegated
+      # secret pair = zero traefik reconciler changes. Phase 4 drops the legacy SANs.
-      # CNAME. Production uses the same restricted acme-dns account.
+      extraDomainNames = [
+        "*.ci.autonomic.zone"
+        "ci.commoninternet.net"
+        "*.ci.commoninternet.net"
+      ];
+      # Staging issuance proved the permanent, narrowly delegated CNAME and the
+      # restricted acme-dns account. Production uses the same account (re-keyed
+      # for the new zone by cc-ci-acme-storage-seed.service).
       dnsProvider = "acmedns";
       environmentFile = "/etc/acme-dns/lego.env";
       dnsResolver = "1.1.1.1:53";

nix/modules/bridge.nix

@@ -33,7 +33,8 @@ let
         image: cc-ci-bridge:${imageTag}
         environment:
           - GITEA_API=https://git.autonomic.zone/api/v1
-          - DRONE_URL=https://drone.ci.commoninternet.net
+          - DRONE_URL=https://drone.ci.autonomic.zone
+          - DASH_URL=https://ci.autonomic.zone
           - CI_REPO=recipe-maintainers/cc-ci
           - BRIDGE_LISTEN=0.0.0.0:8080
           # Polling is PRIMARY (outbound, read-only, always on); the /hook webhook is an optional
@@ -57,7 +58,7 @@ let
           labels:
             - "traefik.enable=true"
             - "traefik.http.services.ccci-bridge.loadbalancer.server.port=8080"
-            - "traefik.http.routers.ccci-bridge.rule=Host(`ci.commoninternet.net`) && PathPrefix(`/hook`)"
+            - "traefik.http.routers.ccci-bridge.rule=(Host(`ci.autonomic.zone`) || Host(`ci.commoninternet.net`)) && PathPrefix(`/hook`)"
             - "traefik.http.routers.ccci-bridge.entrypoints=web-secure"
             - "traefik.http.routers.ccci-bridge.tls=true"
     networks:

nix/modules/dashboard.nix

@@ -1,4 +1,4 @@
-# Results dashboard (§4.5, D7): the YunoHost-CI-like overview at ci.commoninternet.net. Reads the
+# Results dashboard (§4.5, D7): the YunoHost-CI-like overview at ci.autonomic.zone. Reads the
 # Drone API (read-only) and renders latest-run-per-recipe + SVG badges. Packaged as a Nix-built OCI
 # image and run as a swarm service on `proxy`, routed by traefik at Host(ci.commoninternet.net) — the
 # comment-bridge's Host && PathPrefix(`/hook`) rule is longer, so /hook still wins (priority by rule
@@ -33,7 +33,7 @@ let
       app:
         image: cc-ci-dashboard:${imageTag}
         environment:
-          - DRONE_URL=https://drone.ci.commoninternet.net
+          - DRONE_URL=https://drone.ci.autonomic.zone
           - CI_REPO=recipe-maintainers/cc-ci
           - DASH_LISTEN=0.0.0.0:8080
           - DRONE_TOKEN_FILE=/run/secrets/drone_token
@@ -57,7 +57,7 @@ let
           labels:
             - "traefik.enable=true"
             - "traefik.http.services.ccci-dashboard.loadbalancer.server.port=8080"
-            - "traefik.http.routers.ccci-dashboard.rule=Host(`ci.commoninternet.net`)"
+            - "traefik.http.routers.ccci-dashboard.rule=Host(`ci.autonomic.zone`) || Host(`ci.commoninternet.net`)"
             - "traefik.http.routers.ccci-dashboard.entrypoints=web-secure"
             - "traefik.http.routers.ccci-dashboard.tls=true"
     networks:

nix/modules/default.nix

@@ -0,0 +1,44 @@
+# The cc-ci CI server as ONE reusable NixOS module — exported from flake.nix as
+# `nixosModules.cc-ci-server`. Everything a host needs to BE cc-ci, except what is physical or
+# identity and therefore belongs to the host that imports it: hardware, networking, the tailscale
+# node, root SSH keys, `system.stateVersion`. A host sets `cc-ci.publicIPv4` (and, when it is not
+# built from a --recursive clone, `cc-ci.sopsFile`) and imports this.
+#
+# Consumers: nix/hosts/cc-ci-hetzner (the canonical standalone host) and
+# recipe-maintainers/cc-ci-orchestrator's `#cc-ci` host, which runs the CI server and the
+# orchestrator together (2026-09).
+{ pkgs, ... }:
+{
+  imports = [
+    ./options.nix
+    ./packages.nix
+    ./secrets.nix
+    ./acme-dns.nix
+    ./swarm.nix
+    ./docker-prune.nix
+    ./abra.nix
+    ./proxy.nix
+    ./drone.nix
+    ./drone-runner.nix
+    ./bridge.nix
+    ./dashboard.nix
+    ./reports.nix
+    ./backupbot.nix
+    ./harness.nix
+    ./warm-keycloak.nix
+    ./nightly-sweep.nix
+  ];
+
+  # Recipes bind-mount /etc/localtime and /etc/timezone; the harness compares timestamps across
+  # host and containers, so the host is UTC like every container.
+  time.timeZone = "UTC";
+  environment.etc."timezone".text = "UTC\n";
+
+  # Phase `nixenv`: the Drone exec runner resolves recipe shell-outs from this host PATH
+  # (/run/current-system/sw/bin). Install the SINGLE shared harness tool set (pkgs.ccciRuntimeTools,
+  # defined in packages.nix) so the Drone path and the harness env (cc-ci-run / sweep) can never
+  # diverge.
+  environment.systemPackages = pkgs.ccciRuntimeTools;
+
+  nix.settings.experimental-features = [ "nix-command" "flakes" ];
+}

nix/modules/docker-prune.nix

@@ -30,9 +30,11 @@ let
         exit 0
       fi
       # NEVER prune mid-run: a live run-app stack means a deploy/test is in flight (mid-pull layers
-      # can look prunable). Run-app services: <=4char>-<6hex>_ci_commoninternet_net_* (lifecycle.py).
+      # can look prunable). Run-app services: <=4char>-<6hex>_<zone-stem>_* (lifecycle.py).
+      # Zone stem matches BOTH ci_autonomic_zone (current) and ci_commoninternet_net
+      # (legacy stacks from before the 2026-09 domain cutover) during the bake window.
       if docker service ls --format '{{.Name}}' \
-           | grep -qE '^[a-z0-9]{1,4}-[0-9a-f]{6}_ci_commoninternet_net_'; then
+           | grep -qE '^[a-z0-9]{1,4}-[0-9a-f]{6}_ci_(autonomic_zone|commoninternet_net)_'; then
         echo "docker-prune: a run-app stack is live — skipping (never prune mid-run)"
         exit 0
       fi

nix/modules/drone-runner.nix

@@ -35,7 +35,7 @@ in
     wantedBy = [ "multi-user.target" ];
     environment = {
       DRONE_RPC_PROTO = "https";
-      DRONE_RPC_HOST = "drone.ci.commoninternet.net";
+      DRONE_RPC_HOST = "drone.ci.autonomic.zone";
       DRONE_RUNNER_CAPACITY = maxTests; # MAX_TESTS concurrency cap (see let-binding above)
       DRONE_RUNNER_NAME = "cc-ci-exec";
       # exec runner needs a writable root for build workspaces

nix/modules/drone.nix

@@ -1,5 +1,5 @@
 # Drone CI server = coop-cloud `drone` recipe via abra (swarm, traefik-routed at
-# drone.ci.commoninternet.net, Gitea SSO, wildcard cert / no ACME). The exec *runner* is a
+# drone.ci.autonomic.zone, Gitea SSO, wildcard cert / no ACME). The exec *runner* is a
 # separate host systemd service (modules/drone-runner.nix). See DECISIONS.md "CI engine"/"Drone
 # deployment shape".
 #
@@ -17,7 +17,7 @@ let
     name = "cc-ci-reconcile-drone";
     runtimeInputs = with pkgs; [ abra docker jq gnused gnugrep coreutils git curl ];
     text = ''
-      DRONE_DOMAIN="drone.ci.commoninternet.net"
+      DRONE_DOMAIN="drone.ci.autonomic.zone"
       ENV_FILE="$HOME/.abra/servers/default/$DRONE_DOMAIN.env"
 
       if [ ! -r /run/secrets/drone_rpc_secret ] || [ ! -r /run/secrets/drone_gitea_client_secret ]; then
@@ -52,7 +52,10 @@ let
       set_env DRONE_ENV_VERSION "v1"
       set_env COMPOSE_FILE '"compose.yml:compose.gitea.yml"'
 
-      have_secret() { docker secret ls --format '{{.Name}}' | grep -q "_$1_v1$"; }
+      # Stack-scoped: secret names are prefixed with the app's stack name, so during the
+      # 2026-09 domain rename the OLD stack's *_rpc_secret_v1 must not satisfy this check.
+      DRONE_STACK="drone_ci_autonomic_zone"
+      have_secret() { docker secret ls --format '{{.Name}}' | grep -q "^''${DRONE_STACK}_$1_v1$"; }
       have_secret rpc_secret    || abra app secret insert "$DRONE_DOMAIN" rpc_secret    v1 /run/secrets/drone_rpc_secret          -f -n
       have_secret client_secret || abra app secret insert "$DRONE_DOMAIN" client_secret v1 /run/secrets/drone_gitea_client_secret -f -n
 

nix/modules/options.nix

@@ -0,0 +1,33 @@
+# The few host-identity values the cc-ci modules need but must not hard-code, so that the same
+# modules can build the canonical Hetzner host, a throwaway rebuild VM, or a combined host that
+# also runs the cc-ci orchestrator (2026-09: recipe-maintainers/cc-ci-orchestrator imports
+# `nixosModules.cc-ci-server` from this repo and runs both on one box).
+{ lib, ... }:
+{
+  options.cc-ci = {
+    publicIPv4 = lib.mkOption {
+      type = lib.types.str;
+      example = "91.98.47.73";
+      description = ''
+        The host's public IPv4 address. acme-dns binds its authoritative listener to it and
+        publishes it as the `ns-acme` glue record. Must match the Gandi A record for
+        ns-acme.commoninternet.net and the address the cc-ci DNS names point at.
+      '';
+    };
+
+    sopsFile = lib.mkOption {
+      type = lib.types.path;
+      default = ../../secrets/secrets.yaml;
+      defaultText = lib.literalExpression "../../secrets/secrets.yaml";
+      example = "/etc/cc-ci/secrets/secrets.yaml";
+      description = ''
+        The sops-encrypted secrets.yaml (recipe-maintainers/cc-ci-secrets). The default is the
+        `secrets/` git submodule inside this repo, which only exists when this flake is built from
+        a `--recursive` clone (`git+file:///root/cc-ci?submodules=1`). A consumer that imports
+        cc-ci as a plain flake input (no submodule) sets this to an absolute path on the host
+        instead — e.g. the `/etc/cc-ci` deployed checkout's `secrets/secrets.yaml` — which
+        sops-nix then reads at activation time rather than copying into the store.
+      '';
+    };
+  };
+}

nix/modules/reports.nix

@@ -33,6 +33,10 @@ let
             proxy_ssl_server_name on;
             proxy_set_header Host git.autonomic.zone;
             proxy_set_header Accept "application/json";
+            # Pin a non-browser UA: Gitea sits behind Anubis, which 307-challenges browser-like
+            # UAs to an un-CORS-able counter-domain — which would turn every STATUS cell into "?".
+            # A stable non-browser UA passes through (verified: curl 200, browser UA 307).
+            proxy_set_header User-Agent "ccci-reports-proxy/1.0";
             proxy_pass https://git.autonomic.zone/api/v1/repos/recipe-maintainers/$1/pulls/$2;
             proxy_intercept_errors off;
             proxy_connect_timeout 5s;
@@ -69,7 +73,7 @@ let
           labels:
             - "traefik.enable=true"
             - "traefik.http.services.ccci-reports.loadbalancer.server.port=80"
-            - "traefik.http.routers.ccci-reports.rule=Host(`report.ci.commoninternet.net`)"
+            - "traefik.http.routers.ccci-reports.rule=Host(`report.ci.autonomic.zone`) || Host(`report.ci.commoninternet.net`)"
             - "traefik.http.routers.ccci-reports.entrypoints=web-secure"
             - "traefik.http.routers.ccci-reports.tls=true"
     networks:

nix/modules/secrets.nix

@@ -6,8 +6,15 @@
 # off-box master recovery key).
 { config, ... }:
 {
+  imports = [ ./options.nix ];
+
   sops = {
-    defaultSopsFile = ../../secrets/secrets.yaml;
+    # See options.nix: the submodule path by default; an absolute host path on a combined host
+    # that imports cc-ci as a flake input without the private submodule.
+    defaultSopsFile = config.cc-ci.sopsFile;
+    # sops-nix validates store-path sops files at build time. An absolute (string) path is read
+    # at activation instead, so validation has to be off for that case.
+    validateSopsFiles = builtins.isPath config.cc-ci.sopsFile;
     # Decrypt using the host's SSH host key (converted to an age identity by sops-nix).
     age.sshKeyPaths = [ "/etc/ssh/ssh_host_ed25519_key" ];
     # Phase-1c: also accept a bootstrap age key at a fixed path — THE one out-of-band secret,
@@ -37,17 +44,10 @@
       bridge_drone_token = { };
       bridge_gitea_token = { };
 
-      # Phase-1c C2: the wildcard TLS cert+key are now sops secrets (in cc-ci-secrets), decrypted at
+      # The wildcard certificate and private key are issued and renewed locally
-      # activation to /var/lib/ci-certs/live/{fullchain.pem,privkey.pem} — the exact path the traefik
+      # by security.acme. Do not restore the retired SOPS pair here: activation
-      # reconcile (modules/proxy.nix) already reads. Replaces the prior operator-drops-a-cert-file step.
+      # would overwrite a freshly renewed ACME certificate before Traefik can
-      wildcard_cert = {
+      # consume it.
-        path = "/var/lib/ci-certs/live/fullchain.pem";
-        mode = "0444"; # leaf+intermediate chain — not secret
-      };
-      wildcard_key = {
-        path = "/var/lib/ci-certs/live/privkey.pem";
-        mode = "0400"; # private key — root only
-      };
 
       # Phase-2 rate-limit fix (Class A1 registry creds, operator-2026-05-28). Authenticated Docker
       # Hub pulls (200/6h per-account) replace the exhausted 100/6h shared-IP anonymous limit that

opencode.json

@@ -2,7 +2,7 @@
   "$schema": "https://opencode.ai/config.json",
   "agent": {
     "general": {
-      "model": "opencode/deepseek-v4-flash"
+      "model": "opencode-go/deepseek-v4-flash"
     }
   }
 }

runner/harness/card.py

@@ -98,7 +98,7 @@ def _stage_rows(stages: list[dict]) -> str:
         scolor = STATUS_COLOR.get(st.get("status", ""), "#8b949e")
         rows.append(
             f'<tr class="stage"><td colspan="2"><span class="mark" style="color:{scolor}">{smark}</span>'
-            f'<b>{html.escape(st.get("name", "?"))}</b></td>'
+            f"<b>{html.escape(st.get('name', '?'))}</b></td>"
             f'<td class="st" style="color:{scolor}">{html.escape(st.get("status", ""))}</td></tr>'
         )
         for t in st.get("tests", []):
@@ -175,7 +175,7 @@ def render_card_html(data: dict, screenshot_rel: str | None = "screenshot.png")
         ok = bool(flags.get(key))
         flag_bits.append(
             f'<span class="flag" style="border-color:{"#3fb950" if ok else "#f85149"}">'
-            f'{STATUS_MARK["pass"] if ok else STATUS_MARK["fail"]} {lbl}</span>'
+            f"{STATUS_MARK['pass'] if ok else STATUS_MARK['fail']} {lbl}</span>"
         )
     show_shot = bool(screenshot_rel) and bool(data.get("screenshot"))
     shot_html = (

runner/harness/generic.py

@@ -117,7 +117,10 @@ def assert_serving(domain: str, meta) -> None:
     # app is routed (Traefik serves the wildcard zone-wide). The serving proof is steps 1–2 above.
     verified, detail = served_cert(domain)
     assert verified, f"{domain}: served wildcard cert is not trusted/valid — {detail}"
-    assert "commoninternet.net" in detail.lower(), f"{domain}: served cert unexpected — {detail}"
+    # Dual-zone cert (2026-09 cutover): the SAN list covers both *.ci zones; a run
+    # domain in either zone must be covered by the one serving wildcard.
+    zone = "autonomic.zone" if domain.endswith(".autonomic.zone") else "commoninternet.net"
+    assert zone in detail.lower(), f"{domain}: served cert unexpected — {detail}"
 
 
 # ---- Op/assertion split (Phase 1e HC3) -------------------------------------------------------

runner/harness/lifecycle.py

@@ -25,7 +25,7 @@ from . import meta as meta_mod
 GATEWAY_IP = "143.244.213.108"  # *.ci.commoninternet.net -> gateway (TLS passthrough to cc-ci)
 # A run app domain is "<recipe[:4]>-<6hex>.ci.commoninternet.net" (see DECISIONS.md). Used by the
 # janitor to recognise orphaned run apps (infra apps like traefik/drone/backups don't match).
-RUN_APP_RE = re.compile(r"^[a-z0-9]{1,4}-[0-9a-f]{6}\.ci\.commoninternet\.net$")
+RUN_APP_RE = re.compile(r"^[a-z0-9]{1,4}-[0-9a-f]{6}\.ci\.(?:autonomic\.zone|commoninternet\.net)$")
 
 
 class TeardownError(RuntimeError):
@@ -1190,7 +1190,7 @@ def janitor() -> None:
     # also catch stacks whose .env was already deleted (abra ls won't list them)
     for svc in _docker_names("service", ""):
         # svc like cust-c95a69_ci_commoninternet_net_app -> reconstruct domain
-        m = re.match(r"^([a-z0-9]{1,4}-[0-9a-f]{6})_ci_commoninternet_net_", svc)
+        m = re.match(r"^([a-z0-9]{1,4}-[0-9a-f]{6})_ci_(?:autonomic_zone|commoninternet_net)_", svc)
         if m:
             seen.add(f"{m.group(1)}.ci.commoninternet.net")
 

runner/harness/naming.py

@@ -1,7 +1,9 @@
 """Shared run-app domain naming (used by the conftest fixtures and the orchestrator).
 
-Domain = "<recipe[:4]>-<6hex(recipe|pr|ref)>.ci.commoninternet.net" — short enough for Docker's
+Domain = "<recipe[:4]>-<6hex(recipe|pr|ref)>.ci.autonomic.zone" — short enough for Docker's
 64-char swarm config/secret name limit, unique per run, collision-safe across recipes (DECISIONS.md).
+(Migrated from *.ci.commoninternet.net 2026-09; the legacy zone remains valid until the bake
+window ends — lifecycle/warm name matching accepts both.)
 """
 
 from __future__ import annotations
@@ -18,4 +20,4 @@ def app_domain(recipe: str, pr: str = "0", ref: str | None = None) -> str:
     ref = ref or ("local" + str(int(time.time())))
     tag = _short(recipe, 4).lower()
     h = hashlib.sha1(f"{recipe}|{pr}|{ref}".encode()).hexdigest()[:6]
-    return f"{tag}-{h}.ci.commoninternet.net"
+    return f"{tag}-{h}.ci.autonomic.zone"

runner/harness/warm.py

@@ -25,6 +25,9 @@ import urllib.request
 # Recipes that, when declared as a dep, are served from a shared live-warm instance at a stable
 # domain instead of being co-deployed per run. Maps dep-recipe -> stable domain.
 WARM_DOMAINS = {
+    # Warm stacks stay on the legacy zone through the 2026-09 domain cutover (data-warm
+    # volumes + stack names are tied to the abra app name; renaming re-seeds the CI bases).
+    # They move to *.ci.autonomic.zone in a post-bake phase together with their stacks.
     "keycloak": "warm-keycloak.ci.commoninternet.net",
 }
 
@@ -38,11 +41,12 @@ _CTX.check_hostname = False
 _CTX.verify_mode = ssl.CERT_NONE
 
 # A cold per-run stack name looks like "<tag>-<6hex>_ci_commoninternet_net_<svc>"; extract the hex.
-_STACK_HEX_RE = re.compile(r"^[a-z0-9]{1,4}-([0-9a-f]{6})_ci_commoninternet_net_")
+_STACK_HEX_RE = re.compile(r"^[a-z0-9]{1,4}-([0-9a-f]{6})_ci_(?:autonomic_zone|commoninternet_net)_")
 
 
 def stable_domain(recipe: str) -> str:
     """The stable warm domain for a recipe: `warm-<recipe>.ci.commoninternet.net` — the canonical
+    base's hostname (legacy zone until the post-bake warm-stack migration; see WARM_DOMAINS note).
     scheme for BOTH the live-warm keycloak and the data-warm canonicals (WC2), distinct from cold
     per-run `<recipe[:4]>-<6hex>`. (WARM_DOMAINS['keycloak'] equals stable_domain('keycloak').)"""
     return f"warm-{recipe}.ci.commoninternet.net"

runner/warm_reconcile.py

@@ -55,7 +55,29 @@ def wildcard_secret_version(cert_dir: str = CERT_DIR) -> str:
     return "v" + digest[:16]
 
 
-def _traefik_setup(recipe: str, domain: str, version: str) -> None:
+def _traefik_requires_certificate_rollout(domain: str, secret_version: str) -> bool:
+    """Whether Traefik's active service still references an older cert version."""
+    stack = lifecycle._stack_name(domain)  # noqa: SLF001
+    service = f"{stack}_app"
+    result = _run(
+        [
+            "docker",
+            "service",
+            "inspect",
+            service,
+            "--format",
+            "{{range .Spec.TaskTemplate.ContainerSpec.Secrets}}{{.SecretName}} {{end}}",
+        ],
+        timeout=30,
+    )
+    expected = {
+        f"{stack}_ssl_cert_{secret_version}",
+        f"{stack}_ssl_key_{secret_version}",
+    }
+    return not expected.issubset(set(result.stdout.split()))
+
+
+def _traefik_setup(recipe: str, domain: str, version: str) -> bool:
     """Per-app config for the traefik reverse-proxy reconcile — preserves EXACTLY what the prior
     proxy.nix bash reconcile did (wildcard/file-provider mode serving the pre-issued cert as
     ssl_cert/ssl_key swarm secrets; NO ACME). Uses the proven abra.env_set (newline-safe, unlike the
@@ -118,6 +140,7 @@ def _traefik_setup(recipe: str, domain: str, version: str) -> None:
             timeout=120,
             check=True,
         )
+    return _traefik_requires_certificate_rollout(domain, secret_version)
 
 
 SPECS: dict[str, dict] = {
@@ -476,8 +499,9 @@ def reconcile(app: str) -> str:
     # Per-app config/secrets: a spec may provide its own `setup` (traefik's cert/file-provider wiring);
     # otherwise the default keycloak-shaped path (app new + DOMAIN/LETS_ENCRYPT + generate secrets).
     setup = spec.get("setup")
+    setup_needs_rollout = False
     if setup:
-        setup(recipe, domain, latest)
+        setup_needs_rollout = bool(setup(recipe, domain, latest))
     else:
         ensure_app_config(recipe, domain, latest)
         ensure_secrets(domain)
@@ -495,6 +519,20 @@ def reconcile(app: str) -> str:
         write_last_good(recipe, target)
         return f"deployed-fresh:{target}"
 
+    # A certificate rotation changes Traefik's immutable Swarm secrets but
+    # must not be held hostage by an unrelated recipe-major upgrade policy.
+    # Redeploy the current recipe version so its compose spec references the
+    # just-created cert/key secret pair, then apply the usual health gate.
+    if setup_needs_rollout:
+        if not current:
+            raise RuntimeError(f"{app} has services but no current version")
+        print(f"[{app}] certificate changed → redeploy {current}", flush=True)
+        deploy_version(recipe, domain, current, dt)
+        if not wait_healthy(spec):
+            raise RuntimeError(f"{app} certificate rollout {current} did not become healthy")
+        write_last_good(recipe, current)
+        return f"certificate-rolled-out:{current}"
+
     # Deployed & already on latest → converge to a no-op (commit last-good if healthy).
     if current == latest:
         if wait_healthy(spec, timeout=60):

scripts/bootstrap-drone-oauth.sh

@@ -13,10 +13,10 @@ set -euo pipefail
 : "${GITEA_USERNAME:?set GITEA_USERNAME}"
 : "${GITEA_PASSWORD:?set GITEA_PASSWORD}"
 GITEA="${GITEA:-https://git.autonomic.zone}"
-DRONE="${DRONE:-https://drone.ci.commoninternet.net}"
+DRONE="${DRONE:-https://drone.ci.autonomic.zone}"
 CLIENT_ID="${CLIENT_ID:-ab4cdb9d-ee96-4867-875f-87384505fc52}"
 REPO="${REPO:-recipe-maintainers/cc-ci}"
-RES=(--resolve "drone.ci.commoninternet.net:443:127.0.0.1")
+RES=(--resolve "drone.ci.autonomic.zone:443:127.0.0.1")
 export PATH=/run/current-system/sw/bin:"$PATH"
 
 cj=$(mktemp)

tests/bluesky-pds/custom/test_account_and_post.py

@@ -88,9 +88,9 @@ def test_account_lifecycle_and_post_roundtrip(live_app):
 
     # Step 1: PDS describe via goat — recipe self-identifies as did:web:<domain>
     out = _in_container(domain, f"goat pds describe {PDS_HOST_LOCAL} 2>&1")
-    assert (
+    assert f"did:web:{domain}" in out, (
-        f"did:web:{domain}" in out
+        f"goat pds describe did not contain expected DID 'did:web:{domain}'. Output:\n{out[:500]!r}"
-    ), f"goat pds describe did not contain expected DID 'did:web:{domain}'. Output:\n{out[:500]!r}"
+    )
 
     # Step 2: Create account (UUID-suffixed handle = no run-to-run collision)
     out = _goat_admin(
@@ -133,9 +133,9 @@ def test_account_lifecycle_and_post_roundtrip(live_app):
         assert s == 200, f"createRecord HTTP {s}: {body!r}"
         record_uri = (body or {}).get("uri", "")
         # URI format: at://<did>/app.bsky.feed.post/<rkey>
-        assert record_uri.startswith(
+        assert record_uri.startswith(f"at://{new_did}/app.bsky.feed.post/"), (
-            f"at://{new_did}/app.bsky.feed.post/"
+            f"unexpected record uri: {record_uri!r}"
-        ), f"unexpected record uri: {record_uri!r}"
+        )
         rkey = record_uri.rsplit("/", 1)[-1]
         assert rkey, f"no rkey in uri: {record_uri!r}"
 
@@ -148,9 +148,9 @@ def test_account_lifecycle_and_post_roundtrip(live_app):
         )
         assert s == 200, f"getRecord HTTP {s}: {body!r}"
         record_value = (body or {}).get("value", {})
-        assert (
+        assert record_value.get("text") == marker, (
-            record_value.get("text") == marker
+            f"post text did not round-trip: created={marker!r}, fetched={record_value.get('text')!r}"
-        ), f"post text did not round-trip: created={marker!r}, fetched={record_value.get('text')!r}"
+        )
         assert record_value.get("$type") == "app.bsky.feed.post"
     finally:
         # Step 6: Best-effort cleanup. (The per-run domain teardown will discard the volume

tests/bluesky-pds/custom/test_describe_server.py

@@ -26,6 +26,6 @@ def test_describe_server_returns_atproto_envelope(live_app):
     # At least one of these atproto-spec fields must be present
     expected_any = ("availableUserDomains", "inviteCodeRequired", "links", "did")
     present = [k for k in expected_any if k in body]
-    assert (
+    assert present, (
-        present
+        f"describe-server missing all of {expected_any}; got keys: {sorted(body.keys())[:20]}"
-    ), f"describe-server missing all of {expected_any}; got keys: {sorted(body.keys())[:20]}"
+    )

tests/bluesky-pds/custom/test_health_check.py

@@ -17,6 +17,6 @@ def test_pds_health_returns_version(live_app):
     url = f"https://{live_app}/xrpc/_health"
     status, body = harness_http.retry_http_get(url, expect_status=200, max_wait=60, interval=3)
     assert status == 200, f"GET {url} HTTP {status} (expected 200)"
-    assert (
+    assert isinstance(body, dict) and isinstance(body.get("version"), str) and body["version"], (
-        isinstance(body, dict) and isinstance(body.get("version"), str) and body["version"]
+        f"GET {url} response is not the expected health envelope: {body!r}"
-    ), f"GET {url} response is not the expected health envelope: {body!r}"
+    )

tests/bluesky-pds/custom/test_session_auth.py

@@ -30,6 +30,6 @@ def test_get_session_requires_auth(live_app):
         f"body: {body!r}"
     )
     # The XRPC error envelope is JSON with an `error` field per the atproto spec.
-    assert isinstance(body, dict) and body.get(
+    assert isinstance(body, dict) and body.get("error"), (
-        "error"
+        f"expected XRPC JSON error envelope; got: {body!r}"
-    ), f"expected XRPC JSON error envelope; got: {body!r}"
+    )

tests/bluesky-pds/test_restore.py

@@ -11,6 +11,6 @@ import _p4  # noqa: E402
 
 
 def test_restore_returns_state(live_app):
-    assert _p4.account_exists(
+    assert _p4.account_exists(live_app), (
-        live_app
+        "restore did not bring back the seeded marker account (PDS data did not survive restore)"
-    ), "restore did not bring back the seeded marker account (PDS data did not survive restore)"
+    )

tests/concurrency/concutil.py

@@ -15,7 +15,7 @@ sys.path.insert(0, os.path.join(os.path.dirname(__file__), "..", "..", "runner")
 from harness import lifecycle  # noqa: E402
 
 HELPERS = os.path.join(os.path.dirname(__file__), "helpers.py")
-DOMAIN = "test-abc123.ci.commoninternet.net"  # matches RUN_APP_RE
+DOMAIN = "test-abc123.ci.autonomic.zone"  # matches RUN_APP_RE
 
 
 class HelperPool:

tests/concurrency/test_janitor.py

@@ -78,9 +78,9 @@ def test_7_new_run_blocks_until_reap_finishes(lock_dir, pool, monkeypatch):
     line = wait_marker(state["acquirer_out"], "ACQUIRED", timeout=15)
     assert line, "new run never acquired after the reap"
     acquired_ts = float(line.split()[1])
-    assert (
+    assert acquired_ts >= state["teardown_end"], (
-        acquired_ts >= state["teardown_end"]
+        f"new run acquired at {acquired_ts} BEFORE the reap finished at {state['teardown_end']}"
-    ), f"new run acquired at {acquired_ts} BEFORE the reap finished at {state['teardown_end']}"
+    )
     # The new run must hold a lock the next probe can SEE (fresh inode at the path).
     assert lock_state(DOMAIN) == "held"
 
@@ -160,17 +160,17 @@ def test_11_warm_canonical_names_never_probed(lock_dir, monkeypatch):
     monkeypatch.setattr(
         lifecycle,
         "_docker_names",
-        lambda kind, stack: ["warm-keycloak_ci_commoninternet_net_app"]
+        lambda kind, stack: (
-        if kind == "service"
+            ["warm-keycloak_ci_commoninternet_net_app"] if kind == "service" else []
-        else [],
+        ),
     )
     monkeypatch.setattr(lifecycle, "teardown_app", lambda d, verify=True: calls.append(d))
     lifecycle.janitor()
     assert calls == []
     lockdir = os.environ["CCCI_APP_LOCK_DIR"]
-    assert [
+    assert [f for f in os.listdir(lockdir) if f.startswith("cc-ci-app-")] == [], (
-        f for f in os.listdir(lockdir) if f.startswith("cc-ci-app-")
+        "janitor must not create lockfiles for non-run-app names"
-    ] == [], "janitor must not create lockfiles for non-run-app names"
+    )
 
 
 def test_12_degrades_safely_on_bad_lockfile_and_missing_dir(lock_dir, monkeypatch, capsys):

tests/concurrency/test_locks.py

@@ -61,9 +61,9 @@ def test_3_lock_fd_not_inherited_by_children(lock_dir, pool):
     p.kill()
     p.wait(timeout=10)
     assert os.path.exists(f"/proc/{child_pid}"), "child should outlive the holder"
-    assert (
+    assert wait_lock_state(DOMAIN, "free") == "free", (
-        wait_lock_state(DOMAIN, "free") == "free"
+        "lock must release on holder death even with a live child (PEP 446 non-inheritable fd)"
-    ), "lock must release on holder death even with a live child (PEP 446 non-inheritable fd)"
+    )
 
 
 def test_4_second_acquire_blocks_until_first_exits(lock_dir, pool):

tests/concurrency/test_run_state.py

@@ -64,9 +64,9 @@ def test_20c_same_domain_runs_each_keep_their_own_count(tmp_path, lock_dir, pool
     pa.wait(timeout=15)
 
     line_b = wait_marker(out_b, "COUNT")
-    assert (
+    assert line_b is not None and line_b.strip() == "COUNT 1", (
-        line_b is not None and line_b.strip() == "COUNT 1"
+        line_b
-    ), line_b  # B's file survived A's remove
+    )  # B's file survived A's remove
     pb.wait(timeout=15)
 
 

tests/cryptpad/custom/test_pad_content_roundtrip.py

@@ -150,9 +150,9 @@ def test_cryptpad_pad_content_survives_fresh_session(live_app):
             # --- session 1: create the pad + write the marker ---
             ctx1 = browser.new_context(ignore_https_errors=True)
             page, pad_url = _open_pad(ctx1, f"https://{live_app}/pad/")
-            assert (
+            assert "#/2/pad/edit/" in pad_url, (
-                "#/2/pad/edit/" in pad_url
+                f"CryptPad did not create a fragment-keyed pad URL; got {pad_url!r}"
-            ), f"CryptPad did not create a fragment-keyed pad URL; got {pad_url!r}"
+            )
             ck = _ckeditor_frame(page, reload_url=pad_url)
             assert ck is not None, "CKEditor content frame never attached (pad editor not ready)"
             _dismiss_store_modal(page)
@@ -161,9 +161,9 @@ def test_cryptpad_pad_content_survives_fresh_session(live_app):
             page.wait_for_timeout(1000)
             body.type(marker, delay=40)
             page.wait_for_timeout(12000)  # let CryptPad encrypt + sync the update to the server
-            assert (
+            assert marker in ck.locator("body").inner_text(), (
-                marker in ck.locator("body").inner_text()
+                "marker not present in the editor after typing — type did not land"
-            ), "marker not present in the editor after typing — type did not land"
+            )
             ctx1.close()
 
             # --- session 2: FRESH context (no shared storage/localStorage) reads the pad back by URL.

tests/cryptpad/custom/test_pad_create.py

@@ -51,9 +51,9 @@ def test_cryptpad_spa_renders_with_no_console_errors(live_app):
             title = (page.title() or "").lower()
             body = page.content()
             blower = body.lower()
-            assert (
+            assert "cryptpad" in title or "cryptpad" in blower, (
-                "cryptpad" in title or "cryptpad" in blower
+                f"CryptPad SPA does not carry brand. title={title!r}, body excerpt: {body[:200]!r}"
-            ), f"CryptPad SPA does not carry brand. title={title!r}, body excerpt: {body[:200]!r}"
+            )
 
             # Canonical CryptPad asset references in the rendered DOM
             canonical = ("/customize/", "/components/", "main.js", "/api/broadcast")

tests/cryptpad/test_backup.py

@@ -14,6 +14,6 @@ MARKER = "/cryptpad/data/ci-marker.txt"
 
 
 def test_backup_captures_state(live_app):
-    assert (
+    assert lifecycle.exec_in_app(live_app, ["cat", MARKER]).strip() == "original", (
-        lifecycle.exec_in_app(live_app, ["cat", MARKER]).strip() == "original"
+        "the seeded state was not present at backup time"
-    ), "the seeded state was not present at backup time"
+    )

tests/cryptpad/test_restore.py

@@ -14,6 +14,6 @@ MARKER = "/cryptpad/data/ci-marker.txt"
 
 
 def test_restore_returns_state(live_app):
-    assert (
+    assert lifecycle.exec_in_app(live_app, ["cat", MARKER]).strip() == "original", (
-        lifecycle.exec_in_app(live_app, ["cat", MARKER]).strip() == "original"
+        "restore did not return the pre-mutation state"
-    ), "restore did not return the pre-mutation state"
+    )

tests/cryptpad/test_upgrade.py

@@ -14,6 +14,6 @@ MARKER = "/cryptpad/data/ci-marker.txt"
 
 
 def test_upgrade_preserves_data(live_app):
-    assert (
+    assert lifecycle.exec_in_app(live_app, ["cat", MARKER]).strip() == "upgrade-survives", (
-        lifecycle.exec_in_app(live_app, ["cat", MARKER]).strip() == "upgrade-survives"
+        "data did not survive the upgrade"
-    ), "data did not survive the upgrade"
+    )

tests/custom-html-tiny/custom/test_serves_content.py

@@ -79,9 +79,9 @@ def test_static_file_roundtrip_and_404(live_app):
         # A random non-existent path must 404 — proves real static-file semantics, distinguishing a
         # working server from a 200-everything stub or a mis-routed Traefik fallback.
         miss_status, _ = _get(f"https://{live_app}/ccci-missing-{uuid.uuid4().hex}.txt")
-        assert (
+        assert miss_status == 404, (
-            miss_status == 404
+            f"missing path returned {miss_status} (expected 404 — generic 200-returner / mis-route?)"
-        ), f"missing path returned {miss_status} (expected 404 — generic 200-returner / mis-route?)"
+        )
     finally:
         with contextlib.suppress(OSError):
             os.remove(path)

tests/custom-html/custom/test_content_type_header.py

@@ -53,9 +53,9 @@ def test_content_type_html_and_txt(live_app):
     ct_txt = h_txt.get("content-type", "")
 
     # nginx default: "text/html" for .html and "text/plain" for .txt (may include "; charset=utf-8")
-    assert ct_html.startswith(
+    assert ct_html.startswith("text/html"), (
-        "text/html"
+        f"{html_name} Content-Type={ct_html!r}, expected text/html (nginx MIME config broken?)"
-    ), f"{html_name} Content-Type={ct_html!r}, expected text/html (nginx MIME config broken?)"
+    )
-    assert ct_txt.startswith(
+    assert ct_txt.startswith("text/plain"), (
-        "text/plain"
+        f"{txt_name} Content-Type={ct_txt!r}, expected text/plain (nginx MIME config broken?)"
-    ), f"{txt_name} Content-Type={ct_txt!r}, expected text/plain (nginx MIME config broken?)"
+    )

tests/custom-html/test_backup.py

@@ -16,6 +16,6 @@ MARKER_PATH = "/usr/share/nginx/html/ci-marker.txt"
 
 
 def test_backup_captures_state(live_app):
-    assert (
+    assert lifecycle.exec_in_app(live_app, ["cat", MARKER_PATH]).strip() == "original", (
-        lifecycle.exec_in_app(live_app, ["cat", MARKER_PATH]).strip() == "original"
+        "the seeded state was not present at backup time"
-    ), "the seeded state was not present at backup time"
+    )

tests/custom-html/test_restore.py

@@ -17,6 +17,6 @@ MARKER_PATH = "/usr/share/nginx/html/ci-marker.txt"
 
 def test_restore_returns_state(live_app):
     restored = lifecycle.exec_in_app(live_app, ["cat", MARKER_PATH]).strip()
-    assert (
+    assert restored == "original", (
-        restored == "original"
+        f"restore did not return the pre-mutation (backed-up) state: got {restored!r}"
-    ), f"restore did not return the pre-mutation (backed-up) state: got {restored!r}"
+    )

tests/custom-html/test_upgrade.py

@@ -16,6 +16,6 @@ MARKER_PATH = "/usr/share/nginx/html/ci-marker.txt"
 
 def test_upgrade_preserves_data(live_app):
     # the marker seeded by ops.pre_upgrade (before the harness upgraded) is still served
-    assert (
+    assert lifecycle.http_fetch(live_app, "/ci-marker.txt")[1].strip() == "upgrade-survives", (
-        lifecycle.http_fetch(live_app, "/ci-marker.txt")[1].strip() == "upgrade-survives"
+        "data did not survive the upgrade"
-    ), "data did not survive the upgrade"
+    )

tests/discourse/custom/_discourse.py

@@ -81,9 +81,9 @@ def mint_admin(domain: str) -> tuple[str, str]:
             key = line.split("=", 1)[1].strip()
         elif line.startswith("CCCI_API_USER="):
             user = line.split("=", 1)[1].strip()
-    assert (
+    assert key and user, (
-        key and user
+        f"could not bootstrap discourse admin/API key; rails output tail:\n{out[-1000:]}"
-    ), f"could not bootstrap discourse admin/API key; rails output tail:\n{out[-1000:]}"
+    )
     return key, user
 
 

tests/discourse/custom/test_create_topic.py

@@ -48,23 +48,23 @@ def test_create_topic_roundtrip(live_app):
         headers=hdrs,
         timeout=60,
     )
-    assert status in (200, 201) and isinstance(
+    assert status in (200, 201) and isinstance(body, dict), (
-        body, dict
+        f"create topic failed: HTTP {status}, body={body!r}"
-    ), f"create topic failed: HTTP {status}, body={body!r}"
+    )
     topic_id = body.get("topic_id")
     assert topic_id, f"create topic returned no topic_id: {body!r}"
 
     # 4) Read the topic back and assert title + first-post body round-trip.
     status, got = harness_http.http_get(f"{base}/t/{topic_id}.json", headers=hdrs, timeout=30)
-    assert status == 200 and isinstance(
+    assert status == 200 and isinstance(got, dict), (
-        got, dict
+        f"read topic failed: HTTP {status}, body={got!r}"
-    ), f"read topic failed: HTTP {status}, body={got!r}"
+    )
-    assert (
+    assert got.get("title") == title, (
-        got.get("title") == title
+        f"topic title did not round-trip: sent {title!r}, got {got.get('title')!r}"
-    ), f"topic title did not round-trip: sent {title!r}, got {got.get('title')!r}"
+    )
     posts = (got.get("post_stream") or {}).get("posts") or []
     assert posts, f"topic has no posts on read-back: {got!r}"
     first_cooked = posts[0].get("cooked", "")
-    assert (
+    assert marker in first_cooked, (
-        marker in first_cooked
+        f"topic body did not round-trip: marker {marker!r} not in first post {first_cooked!r}"
-    ), f"topic body did not round-trip: marker {marker!r} not in first post {first_cooked!r}"
+    )

tests/discourse/custom/test_site_basic.py

@@ -20,12 +20,12 @@ def test_site_json_has_discourse_config(live_app):
     status, body = harness_http.retry_http_get(
         f"https://{live_app}/site.json", expect_status=200, max_wait=120, interval=5
     )
-    assert status == 200 and isinstance(
+    assert status == 200 and isinstance(body, dict), (
-        body, dict
+        f"GET /site.json failed: HTTP {status}, body type={type(body).__name__}"
-    ), f"GET /site.json failed: HTTP {status}, body type={type(body).__name__}"
+    )
     # /site.json carries Discourse-specific structure — `categories` (a list) and `groups` are always
     # present in a booted Discourse. A non-Discourse 200 (placeholder page) would not parse to this.
     assert "categories" in body, f"/site.json missing 'categories' key: keys={list(body)[:20]}"
-    assert isinstance(
+    assert isinstance(body["categories"], list), (
-        body["categories"], list
+        f"/site.json 'categories' not a list: {type(body['categories']).__name__}"
-    ), f"/site.json 'categories' not a list: {type(body['categories']).__name__}"
+    )

tests/discourse/ops.py

@@ -14,9 +14,7 @@ from harness import lifecycle  # noqa: E402
 
 
 def _psql(domain, sql):
-    cmd = (
+    cmd = f'PGPASSWORD=$(cat /run/secrets/db_password) psql -U discourse -d discourse -tAc "{sql}"'
-        "PGPASSWORD=$(cat /run/secrets/db_password) " f'psql -U discourse -d discourse -tAc "{sql}"'
-    )
     return lifecycle.exec_in_app(domain, ["sh", "-c", cmd], service="db").strip()
 
 

tests/discourse/test_backup.py

@@ -13,13 +13,11 @@ from harness import lifecycle  # noqa: E402
 
 
 def _psql(domain, sql):
-    cmd = (
+    cmd = f'PGPASSWORD=$(cat /run/secrets/db_password) psql -U discourse -d discourse -tAc "{sql}"'
-        "PGPASSWORD=$(cat /run/secrets/db_password) " f'psql -U discourse -d discourse -tAc "{sql}"'
-    )
     return lifecycle.exec_in_app(domain, ["sh", "-c", cmd], service="db").strip()
 
 
 def test_backup_captures_state(live_app):
-    assert (
+    assert _psql(live_app, "SELECT v FROM ci_marker;") == "original", (
-        _psql(live_app, "SELECT v FROM ci_marker;") == "original"
+        "the seeded discourse postgres state was not present at backup time"
-    ), "the seeded discourse postgres state was not present at backup time"
+    )

tests/discourse/test_restore.py

@@ -13,13 +13,11 @@ from harness import lifecycle  # noqa: E402
 
 
 def _psql(domain, sql):
-    cmd = (
+    cmd = f'PGPASSWORD=$(cat /run/secrets/db_password) psql -U discourse -d discourse -tAc "{sql}"'
-        "PGPASSWORD=$(cat /run/secrets/db_password) " f'psql -U discourse -d discourse -tAc "{sql}"'
-    )
     return lifecycle.exec_in_app(domain, ["sh", "-c", cmd], service="db").strip()
 
 
 def test_restore_returns_state(live_app):
-    assert (
+    assert _psql(live_app, "SELECT v FROM ci_marker;") == "original", (
-        _psql(live_app, "SELECT v FROM ci_marker;") == "original"
+        "restore did not return the pre-mutation discourse postgres state (data-integrity failure)"
-    ), "restore did not return the pre-mutation discourse postgres state (data-integrity failure)"
+    )

tests/ghost/custom/test_admin_redirect.py

@@ -62,6 +62,6 @@ def test_ghost_admin_route_is_wired(live_app):
     assert status in (200, 302), f"unexpected status: {status}"
     if status == 200:
         # The admin SPA references /ghost-assets/ or contains "ghost" in title/body
-        assert (
+        assert "ghost" in body.lower(), (
-            "ghost" in body.lower()
+            f"GET {url} 200 but body has no Ghost markers: {body[:200]!r}"
-        ), f"GET {url} 200 but body has no Ghost markers: {body[:200]!r}"
+        )

tests/ghost/custom/test_content_api.py

@@ -35,10 +35,10 @@ def test_content_api_settings_endpoint(live_app):
     assert body is not None, f"GET {url} returned non-JSON body"
     # On success: {"settings": {...}}. On error: {"errors": [...]}. Either shape is valid.
     if status == 200:
-        assert (
+        assert isinstance(body, dict) and "settings" in body, (
-            isinstance(body, dict) and "settings" in body
+            f"200 response missing 'settings' envelope: {body!r}"
-        ), f"200 response missing 'settings' envelope: {body!r}"
+        )
     else:
-        assert isinstance(body, dict) and (
+        assert isinstance(body, dict) and ("errors" in body or "message" in body or body), (
-            "errors" in body or "message" in body or body
+            f"error response not a proper Ghost error envelope: {body!r}"
-        ), f"error response not a proper Ghost error envelope: {body!r}"
+        )

tests/ghost/custom/test_post_roundtrip.py

@@ -43,17 +43,17 @@ def test_create_post_roundtrip(live_app):
     title = f"ccci-marker-{uniq}"
     marker = f"ccci-body-marker-{uniq}-roundtrip"
     created = admin.create_post(title, f"<p>{marker}</p>")
-    assert (
+    assert created.get("title") == title, (
-        created.get("title") == title
+        f"created post title mismatch: sent {title!r}, got {created.get('title')!r}"
-    ), f"created post title mismatch: sent {title!r}, got {created.get('title')!r}"
+    )
 
     # 4) Read it back by id and assert the post survived the round-trip (title always returned;
     #    html returned because we requested ?formats=html).
     got = admin.get_post(created["id"])
-    assert (
+    assert got.get("title") == title, (
-        got.get("title") == title
+        f"post title did not round-trip: sent {title!r}, got {got.get('title')!r}"
-    ), f"post title did not round-trip: sent {title!r}, got {got.get('title')!r}"
+    )
     html = got.get("html") or ""
-    assert (
+    assert marker in html, (
-        marker in html
+        f"post body did not round-trip: marker {marker!r} not in read-back html {html!r}"
-    ), f"post body did not round-trip: marker {marker!r} not in read-back html {html!r}"
+    )

tests/ghost/ops.py

@@ -22,7 +22,7 @@ from harness import lifecycle  # noqa: E402
 
 
 def _mysql(domain, sql):
-    cmd = 'MYSQL_PWD="$(cat /run/secrets/db_password)" ' f'mysql -u root -N -s ghost -e "{sql}"'
+    cmd = f'MYSQL_PWD="$(cat /run/secrets/db_password)" mysql -u root -N -s ghost -e "{sql}"'
     return lifecycle.exec_in_app(domain, ["sh", "-c", cmd], service="db").strip()
 
 

tests/ghost/test_backup.py

@@ -15,11 +15,11 @@ from harness import lifecycle  # noqa: E402
 
 
 def _mysql(domain, sql):
-    cmd = 'MYSQL_PWD="$(cat /run/secrets/db_password)" ' f'mysql -u root -N -s ghost -e "{sql}"'
+    cmd = f'MYSQL_PWD="$(cat /run/secrets/db_password)" mysql -u root -N -s ghost -e "{sql}"'
     return lifecycle.exec_in_app(domain, ["sh", "-c", cmd], service="db").strip()
 
 
 def test_backup_captures_state(live_app):
-    assert (
+    assert _mysql(live_app, "SELECT v FROM ci_marker;") == "original", (
-        _mysql(live_app, "SELECT v FROM ci_marker;") == "original"
+        "the seeded ghost MySQL marker was not present at backup time"
-    ), "the seeded ghost MySQL marker was not present at backup time"
+    )

tests/ghost/test_restore.py

@@ -22,7 +22,7 @@ from harness import lifecycle  # noqa: E402
 
 
 def _mysql(domain, sql):
-    cmd = 'MYSQL_PWD="$(cat /run/secrets/db_password)" ' f'mysql -u root -N -s ghost -e "{sql}"'
+    cmd = f'MYSQL_PWD="$(cat /run/secrets/db_password)" mysql -u root -N -s ghost -e "{sql}"'
     return lifecycle.exec_in_app(domain, ["sh", "-c", cmd], service="db").strip()
 
 

tests/ghost/test_upgrade.py

@@ -14,11 +14,11 @@ from harness import lifecycle  # noqa: E402
 
 
 def _mysql(domain, sql):
-    cmd = 'MYSQL_PWD="$(cat /run/secrets/db_password)" ' f'mysql -u root -N -s ghost -e "{sql}"'
+    cmd = f'MYSQL_PWD="$(cat /run/secrets/db_password)" mysql -u root -N -s ghost -e "{sql}"'
     return lifecycle.exec_in_app(domain, ["sh", "-c", cmd], service="db").strip()
 
 
 def test_upgrade_preserves_state(live_app):
-    assert (
+    assert _mysql(live_app, "SELECT v FROM ci_marker;") == "upgrade-survives", (
-        _mysql(live_app, "SELECT v FROM ci_marker;") == "upgrade-survives"
+        "the seeded ghost MySQL marker did not survive the upgrade redeploy (data loss on upgrade)"
-    ), "the seeded ghost MySQL marker did not survive the upgrade redeploy (data loss on upgrade)"
+    )

tests/gitea/custom/test_lfs_roundtrip.py

@@ -145,9 +145,9 @@ def test_lfs_roundtrip(live_app):
             text=True,
             env={**os.environ, **git_env},
         )
-        assert (
+        assert "testblob.bin" in lfs_ls.stdout, (
-            "testblob.bin" in lfs_ls.stdout
+            f"testblob.bin not in git-lfs ls-files: {lfs_ls.stdout}"
-        ), f"testblob.bin not in git-lfs ls-files: {lfs_ls.stdout}"
+        )
 
         # 6. Download in a FRESH clone (proves the LFS server stores and serves the object)
         fresh_dir = tempfile.mkdtemp(prefix="ccci-gitea-lfs-dl-")
@@ -158,9 +158,9 @@ def test_lfs_roundtrip(live_app):
             with open(fetched_path, "rb") as f:
                 fetched = f.read()
             fetched_sha256 = hashlib.sha256(fetched).hexdigest()
-            assert (
+            assert fetched_sha256 == expected_sha256, (
-                fetched_sha256 == expected_sha256
+                f"LFS round-trip OID mismatch: expected {expected_oid}, got sha256:{fetched_sha256}"
-            ), f"LFS round-trip OID mismatch: expected {expected_oid}, got sha256:{fetched_sha256}"
+            )
         finally:
             shutil.rmtree(fresh_dir, ignore_errors=True)
 
@@ -171,9 +171,9 @@ def test_lfs_roundtrip(live_app):
             ["sh", "-c", "grep -E '^LFS_JWT_SECRET' /etc/gitea/app.ini || echo NOT_FOUND"],
             timeout=30,
         ).strip()
-        assert (
+        assert current_jwt and "NOT_FOUND" not in current_jwt, (
-            current_jwt and "NOT_FOUND" not in current_jwt
+            "Could not read LFS_JWT_SECRET from /etc/gitea/app.ini before restart"
-        ), "Could not read LFS_JWT_SECRET from /etc/gitea/app.ini before restart"
+        )
 
         # Restart the gitea container
         lifecycle.exec_in_app(live_app, ["true"], timeout=5)  # no-op to confirm exec works
@@ -213,9 +213,9 @@ def test_lfs_roundtrip(live_app):
             assert os.path.exists(pr_blob), "testblob.bin not fetched in post-restart clone"
             with open(pr_blob, "rb") as f:
                 pr_data = f.read()
-            assert (
+            assert hashlib.sha256(pr_data).hexdigest() == expected_sha256, (
-                hashlib.sha256(pr_data).hexdigest() == expected_sha256
+                "LFS object corrupted after restart — JWT secret may have changed"
-            ), "LFS object corrupted after restart — JWT secret may have changed"
+            )
         finally:
             shutil.rmtree(post_restart_dir, ignore_errors=True)
 

tests/gitea/ops.py

@@ -220,7 +220,7 @@ def pre_restore(ctx):
     generic.assert_serving(ctx.domain, ctx.meta)
     ok = _delete_marker_repo(ctx.domain, user, password)
     assert ok, f"pre_restore: could not delete {_MARKER_REPO} repo on {ctx.domain}"
-    assert not marker_repo_exists(
+    assert not marker_repo_exists(ctx.domain, user, password), (
-        ctx.domain, user, password
+        f"pre_restore: {_MARKER_REPO} still present after delete — divergence did not take"
-    ), f"pre_restore: {_MARKER_REPO} still present after delete — divergence did not take"
+    )
     print(f"  gitea ops: {_MARKER_REPO!r} deleted (diverged from backup state)", flush=True)

tests/gitea/recipe_meta.py

@@ -72,7 +72,8 @@ def UPGRADE_SECRET_PREP(ctx):
     import subprocess
 
     # abra derives STACK_NAME from the domain by replacing dots with underscores
-    # (e.g. gite-e1cb78.ci.commoninternet.net → gite-e1cb78_ci_commoninternet_net).
+    # (e.g. gite-e1cb78.ci.autonomic.zone → gite-e1cb78_ci_autonomic_zone; legacy
+    # *.ci.commoninternet.net run stacks are matched too during the bake window).
     stack_name = ctx.domain.replace(".", "_")
     docker_secret = f"{stack_name}_lfs_jwt_secret_v1"
     value = base64.urlsafe_b64encode(_os.urandom(32)).rstrip(b"=").decode()

tests/gitea/test_backup.py

@@ -22,6 +22,6 @@ def test_backup_captures_marker_repo(live_app, meta):
     # backupbot cycles the gitea container during backup — wait for it to be back up.
     generic.assert_serving(live_app, meta)
     user, password = admin_creds(live_app)
-    assert marker_repo_exists(
+    assert marker_repo_exists(live_app, user, password), (
-        live_app, user, password
+        f"{live_app}: ci-marker repo is not present at backup time (backup would capture empty state)"
-    ), f"{live_app}: ci-marker repo is not present at backup time (backup would capture empty state)"
+    )

tests/gitea/test_install.py

@@ -65,8 +65,8 @@ def test_install_gitea(live_app, meta):
             )
             page.wait_for_selector("input#user_name", timeout=20_000)
             content = page.content()
-            assert (
+            assert "gitea" in content.lower() or "sign in" in content.lower(), (
-                "gitea" in content.lower() or "sign in" in content.lower()
+                "Sign-in page did not render expected gitea content"
-            ), "Sign-in page did not render expected gitea content"
+            )
         finally:
             browser.close()

tests/gitea/test_upgrade.py

@@ -20,6 +20,6 @@ def test_upgrade_preserves_marker_repo(live_app, meta):
     """The ci-marker repo survived the upgrade to the PR head (data continuity)."""
     generic.assert_serving(live_app, meta)
     user, password = admin_creds(live_app)
-    assert marker_repo_exists(
+    assert marker_repo_exists(live_app, user, password), (
-        live_app, user, password
+        f"{live_app}: ci-marker repo did not survive the upgrade (sqlite3 data lost)"
-    ), f"{live_app}: ci-marker repo did not survive the upgrade (sqlite3 data lost)"
+    )

tests/immich/custom/test_asset_processing.py

@@ -111,13 +111,13 @@ def test_immich_processes_uploaded_asset_metadata_and_statistics(live_app):
         if exif and exif.get("exifImageWidth"):
             break
         time.sleep(5)
-    assert (
+    assert exif and exif.get("exifImageWidth") == 1 and exif.get("exifImageHeight") == 1, (
-        exif and exif.get("exifImageWidth") == 1 and exif.get("exifImageHeight") == 1
+        f"immich metadata-extraction did not populate the 1x1 PNG dimensions in exifInfo: {exif!r}"
-    ), f"immich metadata-extraction did not populate the 1x1 PNG dimensions in exifInfo: {exif!r}"
+    )
 
     # the asset is catalogued into the owner's library statistics (list-back in aggregate)
     sst, stats = harness_http.http_request("GET", f"{base}/api/assets/statistics", headers=auth)
     assert sst == 200 and isinstance(stats, dict), f"statistics HTTP {sst}: {stats!r}"
-    assert (
+    assert stats.get("images", 0) >= 1 and stats.get("total", 0) >= 1, (
-        stats.get("images", 0) >= 1 and stats.get("total", 0) >= 1
+        f"uploaded asset not reflected in library statistics: {stats!r}"
-    ), f"uploaded asset not reflected in library statistics: {stats!r}"
+    )

tests/immich/custom/test_asset_upload.py

@@ -121,6 +121,6 @@ def test_immich_upload_asset_readback_and_thumbnail(live_app):
         if thumb == 200:
             break
         time.sleep(5)
-    assert (
+    assert thumb == 200, (
-        thumb == 200
+        f"immich did not generate a thumbnail/derivative for the uploaded asset (last HTTP {thumb})"
-    ), f"immich did not generate a thumbnail/derivative for the uploaded asset (last HTTP {thumb})"
+    )

tests/immich/test_backup.py

@@ -14,6 +14,6 @@ def _psql(domain, sql):
 
 
 def test_backup_captures_state(live_app):
-    assert (
+    assert _psql(live_app, "SELECT v FROM ci_marker;") == "original", (
-        _psql(live_app, "SELECT v FROM ci_marker;") == "original"
+        "seeded postgres state not present at backup time"
-    ), "seeded postgres state not present at backup time"
+    )

tests/immich/test_restore.py

@@ -14,6 +14,6 @@ def _psql(domain, sql):
 
 
 def test_restore_returns_state(live_app):
-    assert (
+    assert _psql(live_app, "SELECT v FROM ci_marker;") == "original", (
-        _psql(live_app, "SELECT v FROM ci_marker;") == "original"
+        "restore did not return the pre-mutation postgres state"
-    ), "restore did not return the pre-mutation postgres state"
+    )

tests/immich/test_upgrade.py

@@ -14,6 +14,6 @@ def _psql(domain, sql):
 
 
 def test_upgrade_preserves_data(live_app):
-    assert (
+    assert _psql(live_app, "SELECT v FROM ci_marker;") == "upgrade-survives", (
-        _psql(live_app, "SELECT v FROM ci_marker;") == "upgrade-survives"
+        "postgres data did not survive the upgrade"
-    ), "postgres data did not survive the upgrade"
+    )

tests/keycloak/custom/test_create_client_and_use.py

@@ -144,25 +144,25 @@ def test_create_confidential_client_and_obtain_token(live_app):
 
         # Use the client to obtain its own token (client_credentials grant)
         tok_status, tok_resp = _client_credentials_token(live_app, client_id, client_secret)
-        assert (
+        assert tok_status == 200, (
-            tok_status == 200
+            f"client_credentials token returned HTTP {tok_status}: {tok_resp!r}"
-        ), f"client_credentials token returned HTTP {tok_status}: {tok_resp!r}"
+        )
         access_token = tok_resp.get("access_token") if isinstance(tok_resp, dict) else None
-        assert (
+        assert isinstance(access_token, str) and access_token.count(".") == 2, (
-            isinstance(access_token, str) and access_token.count(".") == 2
+            f"client_credentials access_token not a JWT: {access_token!r}"
-        ), f"client_credentials access_token not a JWT: {access_token!r}"
+        )
 
         # Decode the JWT payload; assert azp matches the new client
         payload = json.loads(_b64url_decode(access_token.split(".")[1]))
-        assert (
+        assert payload.get("azp") == client_id, (
-            payload.get("azp") == client_id
+            f"client_credentials JWT azp={payload.get('azp')!r} != client_id={client_id!r}"
-        ), f"client_credentials JWT azp={payload.get('azp')!r} != client_id={client_id!r}"
+        )
         # Service-account token does NOT carry a session-scoped user (azp + clientId differ from
         # admin-cli token). The presence of azp + iss == per-run-domain proves the issuance flow.
         expected_iss = f"https://{live_app}/realms/master"
-        assert (
+        assert payload.get("iss") == expected_iss, (
-            payload.get("iss") == expected_iss
+            f"JWT iss={payload.get('iss')!r} != {expected_iss!r}"
-        ), f"JWT iss={payload.get('iss')!r} != {expected_iss!r}"
+        )
     finally:
         # Idempotent cleanup
         if cleanup_id:

tests/keycloak/custom/test_password_grant_token.py

@@ -43,17 +43,17 @@ def test_password_grant_issues_valid_jwt(live_app):
     token = kc_admin.admin_token(live_app, password)
 
     # Shape: a JWT is exactly 3 base64url segments
-    assert (
+    assert isinstance(token, str) and token.count(".") == 2, (
-        isinstance(token, str) and token.count(".") == 2
+        f"access_token does not look like a JWT (no 3 segments): len={len(token) if token else 0}"
-    ), f"access_token does not look like a JWT (no 3 segments): len={len(token) if token else 0}"
+    )
 
     payload = _decode_jwt_payload(token)
 
     # iss = the issuer URL, must be the per-run domain's /realms/master endpoint
     expected_iss = f"https://{live_app}/realms/master"
-    assert (
+    assert payload.get("iss") == expected_iss, (
-        payload.get("iss") == expected_iss
+        f"JWT iss claim {payload.get('iss')!r} != {expected_iss!r}"
-    ), f"JWT iss claim {payload.get('iss')!r} != {expected_iss!r}"
+    )
 
     # azp = authorized party (which client requested this token)
     assert payload.get("azp") == "admin-cli", f"JWT azp claim {payload.get('azp')!r} != 'admin-cli'"
@@ -68,6 +68,6 @@ def test_password_grant_issues_valid_jwt(live_app):
 
     # iat (issued at) is also a standard claim
     iat = payload.get("iat")
-    assert (
+    assert isinstance(iat, int) and iat <= time.time() + 60, (
-        isinstance(iat, int) and iat <= time.time() + 60
+        f"JWT iat {iat!r} not a reasonable past timestamp"
-    ), f"JWT iat {iat!r} not a reasonable past timestamp"
+    )

tests/lasuite-docs/custom/test_oidc_with_keycloak.py

@@ -42,9 +42,9 @@ def test_oidc_password_grant_against_dep_keycloak(live_app, deps):
     # Sanity-check the creds shape — orchestrator-written
     assert kc["domain"]
     # WC1: realm is per-run namespaced "<parent>-<6hex>" so concurrent dependents never collide.
-    assert re.fullmatch(
+    assert re.fullmatch(r"lasuite-docs-[0-9a-f]{6}", kc["realm"]), (
-        r"lasuite-docs-[0-9a-f]{6}", kc["realm"]
+        f"realm {kc['realm']!r} not the per-run namespaced form lasuite-docs-<6hex>"
-    ), f"realm {kc['realm']!r} not the per-run namespaced form lasuite-docs-<6hex>"
+    )
     assert kc["client_id"] == "lasuite-docs"
     assert isinstance(kc["client_secret"], str) and len(kc["client_secret"]) >= 16
     assert isinstance(kc["password"], str) and len(kc["password"]) >= 16
@@ -77,11 +77,11 @@ def test_oidc_password_grant_against_dep_keycloak(live_app, deps):
     assert isinstance(token, str) and token.count(".") == 2, f"access_token is not a JWT: {token!r}"
     payload = json.loads(_b64url_decode(token.split(".")[1]))
     assert payload.get("iss") == expected_iss, f"JWT iss={payload.get('iss')!r} != {expected_iss!r}"
-    assert (
+    assert payload.get("azp") == kc["client_id"], (
-        payload.get("azp") == kc["client_id"]
+        f"JWT azp={payload.get('azp')!r} != {kc['client_id']!r}"
-    ), f"JWT azp={payload.get('azp')!r} != {kc['client_id']!r}"
+    )
     assert payload.get("typ") == "Bearer", f"JWT typ={payload.get('typ')!r} != 'Bearer'"
     exp = payload.get("exp")
-    assert (
+    assert isinstance(exp, int) and exp > time.time(), (
-        isinstance(exp, int) and exp > time.time()
+        f"JWT exp={exp!r} not a future timestamp (now={time.time():.0f})"
-    ), f"JWT exp={exp!r} not a future timestamp (now={time.time():.0f})"
+    )

tests/lasuite-docs/test_backup.py

@@ -18,6 +18,6 @@ def _psql(domain, sql):
 
 
 def test_backup_captures_state(live_app):
-    assert (
+    assert _psql(live_app, "SELECT v FROM ci_marker;") == "original", (
-        _psql(live_app, "SELECT v FROM ci_marker;") == "original"
+        "the seeded postgres state was not present at backup time"
-    ), "the seeded postgres state was not present at backup time"
+    )

tests/lasuite-docs/test_restore.py

@@ -17,6 +17,6 @@ def _psql(domain, sql):
 
 
 def test_restore_returns_state(live_app):
-    assert (
+    assert _psql(live_app, "SELECT v FROM ci_marker;") == "original", (
-        _psql(live_app, "SELECT v FROM ci_marker;") == "original"
+        "restore did not return the pre-mutation postgres state"
-    ), "restore did not return the pre-mutation postgres state"
+    )

tests/lasuite-docs/test_upgrade.py

@@ -17,6 +17,6 @@ def _psql(domain, sql):
 
 
 def test_upgrade_preserves_data(live_app):
-    assert (
+    assert _psql(live_app, "SELECT v FROM ci_marker;") == "upgrade-survives", (
-        _psql(live_app, "SELECT v FROM ci_marker;") == "upgrade-survives"
+        "postgres data did not survive the upgrade"
-    ), "postgres data did not survive the upgrade"
+    )

tests/lasuite-drive/custom/test_minio_storage.py

@@ -56,6 +56,6 @@ def test_minio_bucket_present_and_object_roundtrip(live_app):
 
     # The object was listed (its key appears) and its content round-tripped intact.
     assert f"{marker}.txt" in out, f"uploaded object not listed in bucket: {out!r}"
-    assert (
+    assert f"READBACK:{marker}" in out, (
-        f"READBACK:{marker}" in out
+        f"object content did not round-trip through MinIO; got: {out!r}"
-    ), f"object content did not round-trip through MinIO; got: {out!r}"
+    )

tests/lasuite-drive/custom/test_oidc_with_keycloak.py

@@ -46,9 +46,9 @@ def test_oidc_password_grant_against_dep_keycloak(live_app, deps):
 
     # Creds shape. WC1: realm is per-run namespaced "<parent>-<6hex>"; client_id stays the parent.
     assert kc["domain"]
-    assert re.fullmatch(
+    assert re.fullmatch(r"lasuite-drive-[0-9a-f]{6}", kc["realm"]), (
-        r"lasuite-drive-[0-9a-f]{6}", kc["realm"]
+        f"realm {kc['realm']!r} not the per-run namespaced form lasuite-drive-<6hex>"
-    ), f"realm {kc['realm']!r} not the per-run namespaced form lasuite-drive-<6hex>"
+    )
     assert kc["client_id"] == "lasuite-drive"
     assert isinstance(kc["client_secret"], str) and len(kc["client_secret"]) >= 16
     assert isinstance(kc["password"], str) and len(kc["password"]) >= 16
@@ -80,11 +80,11 @@ def test_oidc_password_grant_against_dep_keycloak(live_app, deps):
     assert isinstance(token, str) and token.count(".") == 2, f"access_token is not a JWT: {token!r}"
     payload = json.loads(_b64url_decode(token.split(".")[1]))
     assert payload.get("iss") == expected_iss, f"JWT iss={payload.get('iss')!r} != {expected_iss!r}"
-    assert (
+    assert payload.get("azp") == kc["client_id"], (
-        payload.get("azp") == kc["client_id"]
+        f"JWT azp={payload.get('azp')!r} != {kc['client_id']!r}"
-    ), f"JWT azp={payload.get('azp')!r} != {kc['client_id']!r}"
+    )
     assert payload.get("typ") == "Bearer", f"JWT typ={payload.get('typ')!r} != 'Bearer'"
     exp = payload.get("exp")
-    assert (
+    assert isinstance(exp, int) and exp > time.time(), (
-        isinstance(exp, int) and exp > time.time()
+        f"JWT exp={exp!r} not a future timestamp (now={time.time():.0f})"
-    ), f"JWT exp={exp!r} not a future timestamp (now={time.time():.0f})"
+    )

tests/lasuite-drive/test_backup.py

@@ -18,6 +18,6 @@ def _psql(domain, sql):
 
 
 def test_backup_captures_state(live_app):
-    assert (
+    assert _psql(live_app, "SELECT v FROM ci_marker;") == "original", (
-        _psql(live_app, "SELECT v FROM ci_marker;") == "original"
+        "the seeded postgres state was not present at backup time"
-    ), "the seeded postgres state was not present at backup time"
+    )

tests/lasuite-drive/test_restore.py

@@ -17,6 +17,6 @@ def _psql(domain, sql):
 
 
 def test_restore_returns_state(live_app):
-    assert (
+    assert _psql(live_app, "SELECT v FROM ci_marker;") == "original", (
-        _psql(live_app, "SELECT v FROM ci_marker;") == "original"
+        "restore did not return the pre-mutation postgres state"
-    ), "restore did not return the pre-mutation postgres state"
+    )

tests/lasuite-drive/test_upgrade.py

@@ -17,6 +17,6 @@ def _psql(domain, sql):
 
 
 def test_upgrade_preserves_data(live_app):
-    assert (
+    assert _psql(live_app, "SELECT v FROM ci_marker;") == "upgrade-survives", (
-        _psql(live_app, "SELECT v FROM ci_marker;") == "upgrade-survives"
+        "postgres data did not survive the upgrade"
-    ), "postgres data did not survive the upgrade"
+    )

tests/lasuite-meet/custom/test_oidc_with_keycloak.py

@@ -46,9 +46,9 @@ def test_oidc_password_grant_against_dep_keycloak(live_app, deps):
 
     # Creds shape. WC1: realm is per-run namespaced "<parent>-<6hex>"; client_id stays the parent.
     assert kc["domain"]
-    assert re.fullmatch(
+    assert re.fullmatch(r"lasuite-meet-[0-9a-f]{6}", kc["realm"]), (
-        r"lasuite-meet-[0-9a-f]{6}", kc["realm"]
+        f"realm {kc['realm']!r} not the per-run namespaced form lasuite-meet-<6hex>"
-    ), f"realm {kc['realm']!r} not the per-run namespaced form lasuite-meet-<6hex>"
+    )
     assert kc["client_id"] == "lasuite-meet"
     assert isinstance(kc["client_secret"], str) and len(kc["client_secret"]) >= 16
     assert isinstance(kc["password"], str) and len(kc["password"]) >= 16
@@ -80,11 +80,11 @@ def test_oidc_password_grant_against_dep_keycloak(live_app, deps):
     assert isinstance(token, str) and token.count(".") == 2, f"access_token is not a JWT: {token!r}"
     payload = json.loads(_b64url_decode(token.split(".")[1]))
     assert payload.get("iss") == expected_iss, f"JWT iss={payload.get('iss')!r} != {expected_iss!r}"
-    assert (
+    assert payload.get("azp") == kc["client_id"], (
-        payload.get("azp") == kc["client_id"]
+        f"JWT azp={payload.get('azp')!r} != {kc['client_id']!r}"
-    ), f"JWT azp={payload.get('azp')!r} != {kc['client_id']!r}"
+    )
     assert payload.get("typ") == "Bearer", f"JWT typ={payload.get('typ')!r} != 'Bearer'"
     exp = payload.get("exp")
-    assert (
+    assert isinstance(exp, int) and exp > time.time(), (
-        isinstance(exp, int) and exp > time.time()
+        f"JWT exp={exp!r} not a future timestamp (now={time.time():.0f})"
-    ), f"JWT exp={exp!r} not a future timestamp (now={time.time():.0f})"
+    )

tests/lasuite-meet/test_backup.py

@@ -17,6 +17,6 @@ def _psql(domain, sql):
 
 
 def test_backup_captures_state(live_app):
-    assert (
+    assert _psql(live_app, "SELECT v FROM ci_marker;") == "original", (
-        _psql(live_app, "SELECT v FROM ci_marker;") == "original"
+        "the seeded postgres state was not present at backup time"
-    ), "the seeded postgres state was not present at backup time"
+    )

tests/lasuite-meet/test_restore.py

@@ -17,6 +17,6 @@ def _psql(domain, sql):
 
 
 def test_restore_returns_state(live_app):
-    assert (
+    assert _psql(live_app, "SELECT v FROM ci_marker;") == "original", (
-        _psql(live_app, "SELECT v FROM ci_marker;") == "original"
+        "restore did not return the pre-mutation postgres state"
-    ), "restore did not return the pre-mutation postgres state"
+    )

tests/lasuite-meet/test_upgrade.py

@@ -17,6 +17,6 @@ def _psql(domain, sql):
 
 
 def test_upgrade_preserves_data(live_app):
-    assert (
+    assert _psql(live_app, "SELECT v FROM ci_marker;") == "upgrade-survives", (
-        _psql(live_app, "SELECT v FROM ci_marker;") == "upgrade-survives"
+        "postgres data did not survive the upgrade"
-    ), "postgres data did not survive the upgrade"
+    )

tests/mailu/custom/test_mail_flow.py

@@ -43,7 +43,7 @@ def test_send_and_receive_mail(live_app):
     deadline = time.time() + 150
     while time.time() < deadline:
         for box in ("INBOX", "Junk"):
-            query = f"doveadm search -u '{email_addr}' mailbox {box} " f"header subject '{marker}'"
+            query = f"doveadm search -u '{email_addr}' mailbox {box} header subject '{marker}'"
             out = lifecycle.exec_in_app(live_app, ["sh", "-c", query], service="imap")
             if out.strip():  # a non-empty result = "<mailbox-guid> <uid>" → message stored
                 return

tests/mailu/custom/test_mailbox.py

@@ -24,6 +24,6 @@ def test_create_mailbox_and_read_back(live_app):
 
     cfg = _mailu.config_export(live_app)
     emails = _mailu.user_emails(cfg)
-    assert (
+    assert email in emails, (
-        email in emails
+        f"created mailbox {email} not present in mailu config-export users {emails}"
-    ), f"created mailbox {email} not present in mailu config-export users {emails}"
+    )

tests/matrix-synapse/custom/test_federation_version.py

@@ -34,12 +34,12 @@ def test_federation_version_endpoint(live_app):
     assert status == 200, f"GET {url} HTTP {status} (expected 200)"
     assert isinstance(body, dict), f"federation version returned non-dict: {type(body).__name__}"
     server = body.get("server")
-    assert isinstance(
+    assert isinstance(server, dict), (
-        server, dict
+        f"federation version response missing 'server' envelope: {body!r}"
-    ), f"federation version response missing 'server' envelope: {body!r}"
+    )
     name = server.get("name")
     assert name == "Synapse", f"server.name={name!r}, expected 'Synapse'"
     version = server.get("version")
-    assert (
+    assert isinstance(version, str) and len(version) > 0, (
-        isinstance(version, str) and len(version) > 0
+        f"server.version is not a non-empty string: {version!r}"
-    ), f"server.version is not a non-empty string: {version!r}"
+    )

tests/matrix-synapse/custom/test_health_check.py

@@ -23,6 +23,6 @@ def test_synapse_client_versions_returns_json(live_app):
     url = f"https://{live_app}/_matrix/client/versions"
     status, body = harness_http.retry_http_get(url, expect_status=200, max_wait=60, interval=3)
     assert status == 200, f"GET {url} HTTP {status} (expected 200)"
-    assert (
+    assert isinstance(body, dict) and isinstance(body.get("versions"), list) and body["versions"], (
-        isinstance(body, dict) and isinstance(body.get("versions"), list) and body["versions"]
+        f"GET {url} did not return Matrix client-versions document: {body!r}"
-    ), f"GET {url} did not return Matrix client-versions document: {body!r}"
+    )

tests/matrix-synapse/custom/test_register_and_message.py

@@ -127,8 +127,7 @@ def _admin_register(domain: str, secret: str, username: str, password: str, admi
         if r["status"] == 200:
             if attempt > 1:
                 print(
-                    f"  [register] {username}: succeeded on attempt {attempt} "
+                    f"  [register] {username}: succeeded on attempt {attempt} (synapse recovered)",
-                    f"(synapse recovered)",
                     flush=True,
                 )
             return r["body"] or {}
@@ -177,9 +176,9 @@ def test_register_two_users_send_receive_message(live_app):
     create + invite + join a room; send and read a message."""
     domain = live_app
     secret = _registration_secret(domain)
-    assert (
+    assert secret and len(secret) >= 16, (
-        secret and len(secret) >= 16
+        f"registration shared secret missing/short: len={len(secret) if secret else 0}"
-    ), f"registration shared secret missing/short: len={len(secret) if secret else 0}"
+    )
 
     suffix = uuid.uuid4().hex[:8]
     user_a = f"alice{suffix}"

tests/matrix-synapse/test_backup.py

@@ -18,6 +18,6 @@ def _psql(domain, sql):
 
 
 def test_backup_captures_state(live_app):
-    assert (
+    assert _psql(live_app, "SELECT v FROM ci_marker;") == "original", (
-        _psql(live_app, "SELECT v FROM ci_marker;") == "original"
+        "the seeded postgres state was not present at backup time"
-    ), "the seeded postgres state was not present at backup time"
+    )

tests/matrix-synapse/test_install.py

@@ -26,6 +26,6 @@ def test_serving_and_client_api(live_app, meta):
     # The client-API version document is real synapse JSON (proves the app, not just a proxy 200).
     body = lifecycle.http_body(live_app, "/_matrix/client/versions")
     doc = json.loads(body)
-    assert (
+    assert isinstance(doc.get("versions"), list) and doc["versions"], (
-        isinstance(doc.get("versions"), list) and doc["versions"]
+        "no matrix client versions advertised"
-    ), "no matrix client versions advertised"
+    )

tests/matrix-synapse/test_restore.py

@@ -17,6 +17,6 @@ def _psql(domain, sql):
 
 
 def test_restore_returns_state(live_app):
-    assert (
+    assert _psql(live_app, "SELECT v FROM ci_marker;") == "original", (
-        _psql(live_app, "SELECT v FROM ci_marker;") == "original"
+        "restore did not return the pre-mutation postgres state"
-    ), "restore did not return the pre-mutation postgres state"
+    )

tests/matrix-synapse/test_upgrade.py

@@ -17,6 +17,6 @@ def _psql(domain, sql):
 
 
 def test_upgrade_preserves_data(live_app):
-    assert (
+    assert _psql(live_app, "SELECT v FROM ci_marker;") == "upgrade-survives", (
-        _psql(live_app, "SELECT v FROM ci_marker;") == "upgrade-survives"
+        "postgres data did not survive the upgrade"
-    ), "postgres data did not survive the upgrade"
+    )

tests/mattermost-lts/custom/test_create_message.py

@@ -41,9 +41,9 @@ def test_create_message_roundtrip(live_app):
         headers=auth,
         timeout=30,
     )
-    assert (
+    assert status in (200, 201) and isinstance(team, dict) and team.get("id"), (
-        status in (200, 201) and isinstance(team, dict) and team.get("id")
+        f"team creation failed: HTTP {status}, body={team!r}"
-    ), f"team creation failed: HTTP {status}, body={team!r}"
+    )
     status, chan = harness_http.http_post(
         f"{base}/channels",
         data={
@@ -55,9 +55,9 @@ def test_create_message_roundtrip(live_app):
         headers=auth,
         timeout=30,
     )
-    assert (
+    assert status in (200, 201) and isinstance(chan, dict) and chan.get("id"), (
-        status in (200, 201) and isinstance(chan, dict) and chan.get("id")
+        f"channel creation failed: HTTP {status}, body={chan!r}"
-    ), f"channel creation failed: HTTP {status}, body={chan!r}"
+    )
 
     # 4) POST a unique marker message.
     marker = f"ccci-marker-{uniq}-roundtrip"
@@ -67,13 +67,13 @@ def test_create_message_roundtrip(live_app):
         headers=auth,
         timeout=30,
     )
-    assert (
+    assert status in (200, 201) and isinstance(post, dict) and post.get("id"), (
-        status in (200, 201) and isinstance(post, dict) and post.get("id")
+        f"post creation failed: HTTP {status}, body={post!r}"
-    ), f"post creation failed: HTTP {status}, body={post!r}"
+    )
 
     # 5) Read it back by id and assert the message survived the round-trip.
     status, got = harness_http.http_get(f"{base}/posts/{post['id']}", headers=auth, timeout=30)
     assert status == 200 and isinstance(got, dict), f"read-back failed: HTTP {status}, body={got!r}"
-    assert (
+    assert got.get("message") == marker, (
-        got.get("message") == marker
+        f"message did not round-trip: sent {marker!r}, got {got.get('message')!r}"
-    ), f"message did not round-trip: sent {marker!r}, got {got.get('message')!r}"
+    )

tests/mattermost-lts/custom/test_health_check.py

@@ -28,6 +28,6 @@ def test_system_ping_ok(live_app):
     url = f"https://{live_app}/api/v4/system/ping"
     status, body = harness_http.retry_http_get(url, expect_status=200, max_wait=120, interval=3)
     assert status == 200, f"GET {url} HTTP {status} (expected 200)"
-    assert (
+    assert isinstance(body, dict) and body.get("status") == "OK", (
-        isinstance(body, dict) and body.get("status") == "OK"
+        f"/api/v4/system/ping did not report status=OK; got {body!r}"
-    ), f"/api/v4/system/ping did not report status=OK; got {body!r}"
+    )

tests/mattermost-lts/custom/test_multiuser_message.py

@@ -105,6 +105,6 @@ def test_second_user_reads_first_users_message(live_app):
 
     # 5) user_b sees user_a's marker (cross-user delivery, not a self read-back)
     messages = [p.get("message") for p in (posts.get("posts") or {}).values()]
-    assert (
+    assert marker in messages, (
-        marker in messages
+        f"user_b did not see user_a's message {marker!r} in the channel; saw {messages!r}"
-    ), f"user_b did not see user_a's message {marker!r} in the channel; saw {messages!r}"
+    )

tests/mattermost-lts/test_backup.py

@@ -18,6 +18,6 @@ def _psql(domain, sql):
 
 
 def test_backup_captures_state(live_app):
-    assert (
+    assert _psql(live_app, "SELECT v FROM ci_marker;") == "original", (
-        _psql(live_app, "SELECT v FROM ci_marker;") == "original"
+        "the seeded postgres state was not present at backup time"
-    ), "the seeded postgres state was not present at backup time"
+    )