infra(ci): route publish/deploy ship jobs to dedicated publish lane (internal#462)

Urgent prod-deploy publish builds currently FIFO-compete with ordinary
PR required-CI on the shared 20-runner pool. PR#1350's (CTO-reported
canvas-message-loss fix) production image build sat ~25min behind the
PR-CI backlog after merge, directly delaying a user-facing fix.

internal#462 comment 32299 + the already-merged operator-config
publish-lane scaffolding (config.publish.yaml + publish-lane-ensure.sh,
internal#394/#399) define a reserved `publish`/`release` sub-pool
(molecule-runner-publish-*, OUTSIDE the managed 1..20 range so it is
never auto-drained / recycled / drift-flagged). This retargets the 7
post-merge ship jobs across 5 workflows from `runs-on: ubuntu-latest`
to `runs-on: publish` so a merged fix's image build/push/deploy gets
reserved capacity and starts immediately, while PR-CI keeps the
general pool:

  - publish-workspace-server-image.yml: build-and-push, deploy-production
  - publish-canvas-image.yml: build-and-push
  - publish-runtime.yml: publish, cascade
  - redeploy-tenants-on-main.yml: redeploy
  - redeploy-tenants-on-staging.yml: redeploy

publish-runtime-autobump.yml is intentionally NOT moved: it is
pull_request-triggered (PR-CI by nature, a required status), not a
post-merge ship job — the lane reserves capacity for the ship path,
not for PR checks.

HARD MERGE PRECONDITION: this MUST NOT merge until the publish-lane
runners are registered and advertising the `publish` label. Targeting
an unregistered label queues jobs indefinitely with zero eligible
runners — the exact #599/#576 `docker`-label failure mode. Lane
registration is a GO-gated live-fleet mutation (publish-lane-ensure.sh
ALLOW_FLEET_MUTATION=1, requires explicit Hongming in-chat GO).

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

.gitea/workflows/publish-canvas-image.yml

@@ -49,13 +49,17 @@ jobs:
   # bp-exempt: post-merge image publication side effect; CI / all-required gates source changes.
   build-and-push:
     name: Build & push canvas image
-    # REVERTED (infra/revert-docker-runner-label): `runs-on: ubuntu-latest` restored.
-    # The `docker` label is not registered on any act_runner. `runs-on: [ubuntu-latest, docker]`
-    # causes jobs to queue indefinitely with zero eligible runners — strictly worse than the
-    # pre-#599 coin-flip (50% success rate). Once the `docker` label is registered on
-    # ≥2 runners, re-apply the fix from #599 (infra/docker-runner-label).
-    # See issue #576 + infra-lead pulse ~00:30Z.
-    runs-on: ubuntu-latest
+    # Dedicated publish/release lane (internal#462 / #394 / #399). Ship
+    # path (on: push:main, canvas/**) — reserved capacity so a merged
+    # canvas fix's image build never FIFO-queues behind PR required-CI.
+    # The `publish` label resolves ONLY to the molecule-runner-publish-*
+    # sub-pool (config.publish.yaml). HARD DEPENDENCY: this MUST land
+    # AFTER the publish-lane runners are registered/advertising `publish`
+    # — the earlier #599 `docker` label attempt queued indefinitely with
+    # zero eligible runners precisely because the label was targeted
+    # before any runner advertised it (see #576). The lane is registered
+    # in this rollout (internal#462) so the precondition holds.
+    runs-on: publish
     # Phase 3 (RFC #219 §1): surface broken workflows without blocking.
     # mc#774: pre-existing continue-on-error mask; root-fix and remove, do not renew silently.
     continue-on-error: true

.gitea/workflows/publish-runtime.yml

@@ -66,7 +66,10 @@ concurrency:
 
 jobs:
   publish:
-    runs-on: ubuntu-latest
+    # Dedicated publish/release lane (internal#462 / #394 / #399). Ship
+    # path (on: push tag runtime-v*) — reserved capacity, never FIFO
+    # behind PR-CI. `publish` resolves only to molecule-runner-publish-*.
+    runs-on: publish
     outputs:
       version: ${{ steps.version.outputs.version }}
       wheel_sha256: ${{ steps.wheel_hash.outputs.wheel_sha256 }}
@@ -166,7 +169,9 @@ jobs:
 
   cascade:
     needs: publish
-    runs-on: ubuntu-latest
+    # Publish/release lane (internal#462) — downstream of the runtime
+    # publish ship job; keep it on the reserved lane too.
+    runs-on: publish
     steps:
       - name: Wait for PyPI to propagate the new version
         env:

.gitea/workflows/publish-workspace-server-image.yml

@@ -54,7 +54,14 @@ env:
 
 jobs:
   build-and-push:
-    runs-on: ubuntu-latest
+    # Dedicated publish/release lane (internal#462 / #394 / #399). This
+    # is a post-merge ship job (on: push:main) — it must NOT FIFO-compete
+    # with PR required-CI on the shared pool (PR#1350's prod image build
+    # was delayed ~25min this way). The `publish` label resolves ONLY to
+    # the reserved molecule-runner-publish-* sub-pool (config.publish.yaml,
+    # OUTSIDE the managed 1..20 range) so a merged fix's image build
+    # starts immediately while PR-CI keeps the general pool.
+    runs-on: publish
     steps:
       - name: Checkout
         uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2
@@ -181,7 +188,9 @@ jobs:
     name: Production auto-deploy
     needs: build-and-push
     if: ${{ github.event_name == 'push' && github.ref == 'refs/heads/main' }}
-    runs-on: ubuntu-latest
+    # Publish/release lane (internal#462) — production deploy of a merged
+    # fix; reserved capacity, never queued behind PR-CI.
+    runs-on: publish
     timeout-minutes: 75
     env:
       CP_URL: ${{ vars.PROD_CP_URL || 'https://api.moleculesai.app' }}

.gitea/workflows/redeploy-tenants-on-main.yml

@@ -68,7 +68,10 @@ jobs:
   # bp-exempt: production redeploy is a side-effect workflow, not a merge gate.
   redeploy:
     if: ${{ github.event_name == 'workflow_dispatch' }}
-    runs-on: ubuntu-latest
+    # Dedicated publish/release lane (internal#462 / #394 / #399).
+    # Production tenant redeploy — a deploy action, reserved capacity so
+    # it never queues behind PR-CI. `publish` -> molecule-runner-publish-*.
+    runs-on: publish
     # Phase 3 (RFC #219 §1): surface broken workflows without blocking.
     # mc#774: pre-existing continue-on-error mask; root-fix and remove, do not renew silently.
     continue-on-error: true

.gitea/workflows/redeploy-tenants-on-staging.yml

@@ -75,7 +75,10 @@ env:
 jobs:
   # bp-exempt: post-merge staging redeploy side effect; CI / all-required gates source changes.
   redeploy:
-    runs-on: ubuntu-latest
+    # Dedicated publish/release lane (internal#462 / #394 / #399).
+    # Post-merge staging redeploy — a deploy action, reserved capacity.
+    # `publish` -> molecule-runner-publish-* sub-pool.
+    runs-on: publish
     # Phase 3 (RFC #219 §1): surface broken workflows without blocking.
     # mc#774: pre-existing continue-on-error mask; root-fix and remove, do not renew silently.
     continue-on-error: true