ci: rebalance portable serial tests across seven shards

.github/workflows/ci.yml

@@ -192,16 +192,14 @@ jobs:
   tests-portable-serial:
     name: Behavior portable serial ${{ matrix.shard }}
     runs-on: ubuntu-latest
-    # Refreshed timings plus conservative hints for grown tests estimate ~84 min
-    # of serial work, balanced over six runners at ~14 min each. Keep the cap
-    # as a hang tripwire with runner-load margin; refresh hints per
-    # docs/fm-test-portable-shards.md when a shard approaches it.
+    # Keep this cap as a hang tripwire; when a shard approaches it, follow the
+    # balance evidence and refresh procedure in docs/fm-test-portable-shards.md.
     timeout-minutes: 20
     strategy:
       # Every shard reports so one failure never hides another shard's result.
       fail-fast: false
       matrix:
-        shard: [1, 2, 3, 4, 5, 6]
+        shard: [1, 2, 3, 4, 5, 6, 7]
     steps:
       - uses: actions/checkout@v6
         with:

bin/fm-test-run.sh

@@ -92,11 +92,9 @@ JOBS_MAX=8
 
 # How many separate-runner shards the portable serial remainder splits into.
 # One owner: CI lane names carry this count and are refused when they disagree.
-PORTABLE_SERIAL_SHARDS=6
+PORTABLE_SERIAL_SHARDS=7
 
-# Balance hint for a portable-serial script with no measured duration, close to
-# the measured per-script mean so a newly added test neither starves nor
-# overloads the shard it lands in.
+# Fallback balance hint for a portable-serial script with no measured duration.
 PORTABLE_SERIAL_DEFAULT_WEIGHT_MS=20000
 
 usage() {
@@ -375,165 +373,179 @@ list_portable_serial() {
   done < <(all_repo_tests)
 }
 
-# Portable-serial duration hints in milliseconds, from CI artifacts, completed
-# log records, and conservative estimates documented in docs/fm-test-portable-shards.md.
+# Portable-serial measured duration hints in milliseconds; source evidence is
+# documented in docs/fm-test-portable-shards.md.
 # These affect balance only: the shard partition stays complete and disjoint, so a
 # stale hint costs balance rather than coverage. That doc owns the refresh
 # procedure.
 portable_serial_weight_hints() {
   cat <<'EOF'
-tests/fm-afk-inject-e2e.test.sh 26008
-tests/fm-afk-pi-herdr-return-e2e.test.sh 47
-tests/fm-afk-return.test.sh 1517
-tests/fm-ask-user-authority.test.sh 138
-tests/fm-backend-cmux-smoke.test.sh 30
-tests/fm-backend-cmux.test.sh 2950
-tests/fm-backend-herdr-focus-flash-e2e.test.sh 21
-tests/fm-backend-herdr-server-detach.test.sh 90000
-tests/fm-backend-orca.test.sh 19416
-tests/fm-backend-tmux-smoke.test.sh 315
-tests/fm-backend-zellij-smoke.test.sh 14
-tests/fm-backend-zellij.test.sh 5188
-tests/fm-backend.test.sh 19862
-tests/fm-backlog-atomicity.test.sh 78496
-tests/fm-backlog-handoff.test.sh 3343
-tests/fm-bearings-snapshot.test.sh 66118
-tests/fm-boat-lifecycle.test.sh 52034
-tests/fm-boat-omp-auth.test.sh 58941
-tests/fm-boat-routing.test.sh 200000
-tests/fm-bootstrap.test.sh 62184
-tests/fm-busy-adapter-wiring.test.sh 17306
-tests/fm-busy-state.test.sh 2821
-tests/fm-calm-pi-extension.test.sh 260
-tests/fm-check-unregister.test.sh 356
-tests/fm-classify-decision-key.test.sh 703
-tests/fm-claude-stop-autoarm-live-e2e.test.sh 17
-tests/fm-claude-stop-autoarm.test.sh 60519
-tests/fm-cleanup-skill.test.sh 72
-tests/fm-codex-continuity-live-e2e.test.sh 19
-tests/fm-daemon.test.sh 61329
-tests/fm-devin-adapter.test.sh 280
-tests/fm-devin-herdr-live-e2e.test.sh 13
-tests/fm-dispatch-resolve.test.sh 3995
-tests/fm-documentation-audiences.test.sh 708
-tests/fm-ext-bridge.test.sh 35693
-tests/fm-fleet-snapshot-view.test.sh 13508
-tests/fm-fleet-sync.test.sh 32815
-tests/fm-gate-refuse.test.sh 9270
-tests/fm-gitignore-config.test.sh 25
-tests/fm-gotmp.test.sh 713
-tests/fm-grok-continuity-live-e2e.test.sh 12
-tests/fm-grok-stop-live-e2e.test.sh 21
-tests/fm-guard-stale-banner.test.sh 4698
-tests/fm-herdr-session-cleanup.test.sh 4832
-tests/fm-herdr-submit-confirm-live-e2e.test.sh 21
-tests/fm-hermes-harness.test.sh 146669
-tests/fm-hermes-live-e2e.test.sh 28
-tests/fm-idle-sleep-watch.test.sh 8000
-tests/fm-idle-sleep.test.sh 15000
-tests/fm-inbox-result.test.sh 7377
-tests/fm-inbox.test.sh 7022
-tests/fm-kimi-harness.test.sh 16139
-tests/fm-omp-branch-bash.test.sh 44
-tests/fm-omp-branch-live-e2e.test.sh 12
-tests/fm-omp-branch-supervision.test.sh 4373
-tests/fm-omp-branch-types.test.sh 24
+tests/fm-afk-inject-e2e.test.sh 26538
+tests/fm-afk-pi-herdr-return-e2e.test.sh 76
+tests/fm-afk-return.test.sh 1524
+tests/fm-ask-user-authority.test.sh 154
+tests/fm-backend-cmux-smoke.test.sh 34
+tests/fm-backend-cmux.test.sh 3751
+tests/fm-backend-herdr-focus-flash-e2e.test.sh 22
+tests/fm-backend-herdr-server-detach.test.sh 2649
+tests/fm-backend-orca.test.sh 19716
+tests/fm-backend-tmux-smoke.test.sh 250
+tests/fm-backend-zellij-smoke.test.sh 22
+tests/fm-backend-zellij.test.sh 7129
+tests/fm-backend.test.sh 23256
+tests/fm-backlog-atomicity.test.sh 63215
+tests/fm-backlog-handoff.test.sh 3410
+tests/fm-bearings-snapshot.test.sh 81131
+tests/fm-boat-lane-runner.test.sh 119102
+tests/fm-boat-lifecycle.test.sh 44937
+tests/fm-boat-omp-auth.test.sh 62445
+tests/fm-boat-routing.test.sh 26287
+tests/fm-bootstrap.test.sh 71450
+tests/fm-busy-adapter-wiring.test.sh 19619
+tests/fm-busy-state.test.sh 2879
+tests/fm-calm-pi-extension.test.sh 265
+tests/fm-check-unregister.test.sh 436
+tests/fm-classify-decision-key.test.sh 501
+tests/fm-claude-stop-autoarm-live-e2e.test.sh 20
+tests/fm-claude-stop-autoarm.test.sh 60780
+tests/fm-cleanup-skill.test.sh 74
+tests/fm-codex-continuity-live-e2e.test.sh 20
+tests/fm-daemon.test.sh 60677
+tests/fm-devin-adapter.test.sh 349
+tests/fm-devin-herdr-live-e2e.test.sh 21
+tests/fm-dispatch-resolve.test.sh 8747
+tests/fm-documentation-audiences.test.sh 878
+tests/fm-ext-ask.test.sh 48724
+tests/fm-ext-bridge.test.sh 82962
+tests/fm-ext-decision.test.sh 161682
+tests/fm-ext-plugin-dest.test.sh 7190
+tests/fm-ext-thread-context.test.sh 18046
+tests/fm-ext-topic-threads.test.sh 100660
+tests/fm-ext-waiting-pin.test.sh 103172
+tests/fm-ext-watch.test.sh 7522
+tests/fm-fleet-snapshot-view.test.sh 12998
+tests/fm-fleet-sync.test.sh 36580
+tests/fm-gate-refuse.test.sh 11343
+tests/fm-gitignore-config.test.sh 29
+tests/fm-gotmp.test.sh 1168
+tests/fm-grok-continuity-live-e2e.test.sh 19
+tests/fm-grok-stop-live-e2e.test.sh 20
+tests/fm-guard-stale-banner.test.sh 5898
+tests/fm-herdr-session-cleanup.test.sh 6849
+tests/fm-herdr-submit-confirm-live-e2e.test.sh 22
+tests/fm-hermes-harness.test.sh 151616
+tests/fm-hermes-live-e2e.test.sh 44
+tests/fm-idle-sleep-watch.test.sh 4560
+tests/fm-idle-sleep.test.sh 13959
+tests/fm-inbox-result.test.sh 9828
+tests/fm-inbox.test.sh 9840
+tests/fm-kimi-harness.test.sh 18045
+tests/fm-landing.test.sh 43476
+tests/fm-main-ci-watch.test.sh 46302
+tests/fm-merge-local.test.sh 2502
+tests/fm-omp-branch-bash.test.sh 41
+tests/fm-omp-branch-live-e2e.test.sh 20
+tests/fm-omp-branch-supervision.test.sh 37015
+tests/fm-omp-branch-types.test.sh 21
 tests/fm-omp-compact-adviser-live-e2e.test.sh 20
-tests/fm-omp-compact-adviser.test.sh 298
-tests/fm-omp-fleet-hooks.test.sh 2407
-tests/fm-omp-harness.test.sh 1764
-tests/fm-omp-herdr-exit-live-e2e.test.sh 16
+tests/fm-omp-compact-adviser.test.sh 1697
+tests/fm-omp-fleet-hooks.test.sh 2743
+tests/fm-omp-harness.test.sh 66500
+tests/fm-omp-herdr-exit-live-e2e.test.sh 19
 tests/fm-omp-herdr-live-e2e.test.sh 19
-tests/fm-omp-primary-live-e2e.test.sh 18
-tests/fm-omp-primary.test.sh 45746
-tests/fm-omp-relaunch-guard.test.sh 4276
-tests/fm-omp-relaunch-tmux-live-e2e.test.sh 21
-tests/fm-omp-secondmate-live-e2e.test.sh 21
-tests/fm-omp-secondmate.test.sh 600000
-tests/fm-omp-task-inbox-doorbell.test.sh 20577
-tests/fm-omp-update.test.sh 448
-tests/fm-omp-worker-tmux-live-e2e.test.sh 17
-tests/fm-on.test.sh 9627
-tests/fm-opencode-primary-live-e2e.test.sh 16
-tests/fm-operational-input.test.sh 176
-tests/fm-pending-reply-sleep-reconcile.test.sh 243
-tests/fm-pending-reply.test.sh 19949
-tests/fm-pi-compatible-family.test.sh 56
+tests/fm-omp-primary-live-e2e.test.sh 19
+tests/fm-omp-primary.test.sh 61283
+tests/fm-omp-relaunch-guard.test.sh 5534
+tests/fm-omp-relaunch-tmux-live-e2e.test.sh 14
+tests/fm-omp-secondmate-live-e2e.test.sh 20
+tests/fm-omp-secondmate.test.sh 113332
+tests/fm-omp-task-inbox-doorbell.test.sh 20456
+tests/fm-omp-update.test.sh 689
+tests/fm-omp-worker-tmux-live-e2e.test.sh 20
+tests/fm-on.test.sh 9816
+tests/fm-opencode-primary-live-e2e.test.sh 20
+tests/fm-operational-input.test.sh 154
+tests/fm-pending-reply-sleep-reconcile.test.sh 229
+tests/fm-pending-reply.test.sh 15024
+tests/fm-pi-compatible-family.test.sh 70
 tests/fm-pi-primary-live-e2e.test.sh 21
-tests/fm-pi-watch-extension.test.sh 22031
-tests/fm-pr-check-handoff.test.sh 42228
-tests/fm-pr-check-security.test.sh 158907
-tests/fm-prepush-guard.test.sh 19208
-tests/fm-procevent-when.test.sh 24358
-tests/fm-procevent.test.sh 61916
-tests/fm-public-followup.test.sh 35559
-tests/fm-quota-array-dispatch-live-e2e.test.sh 12
-tests/fm-receipt-check.test.sh 11636
-tests/fm-receipt.test.sh 1331
-tests/fm-reflect-skill.test.sh 372
-tests/fm-remote-backlog-handoff.test.sh 15173
-tests/fm-remote-doctor.test.sh 6203
-tests/fm-remote-entrypoint.test.sh 208
-tests/fm-remote-job.test.sh 48694
-tests/fm-remote-reply.test.sh 99366
-tests/fm-remote-secondmate-lifecycle-e2e.test.sh 700000
-tests/fm-remote-secondmate-parent-binding.test.sh 15892
-tests/fm-remote-secondmate-sleep-reconcile.test.sh 3000
-tests/fm-remote-secondmate-trace-context.test.sh 49391
-tests/fm-runpod-lifecycle.test.sh 56695
-tests/fm-runpod-omp-auth.test.sh 1012
-tests/fm-runpod-pod-boot.test.sh 45589
-tests/fm-runpod-routing.test.sh 28030
-tests/fm-secondmate-harness.test.sh 151987
-tests/fm-secondmate-lifecycle-e2e.test.sh 5372
-tests/fm-secondmate-liveness.test.sh 20126
-tests/fm-secondmate-restart.test.sh 31003
-tests/fm-secondmate-safety.test.sh 55903
-tests/fm-secondmate-sync.test.sh 17159
-tests/fm-send-inbox-doorbell-live-e2e.test.sh 18
-tests/fm-send-inbox.test.sh 37394
-tests/fm-send-resolve-key.test.sh 12632
-tests/fm-send-secondmate-marker-herdr-e2e.test.sh 48
-tests/fm-send-secondmate-marker.test.sh 4320
-tests/fm-send-turn-start.test.sh 11143
-tests/fm-session-lock-ancestry.test.sh 1284
-tests/fm-session-start.test.sh 77942
-tests/fm-sessionstart-nudge.test.sh 284
-tests/fm-shared-captain-inheritance.test.sh 4259
-tests/fm-spawn-dispatch-profile.test.sh 193113
-tests/fm-spawn-pool-base-freshen.test.sh 35139
-tests/fm-spawn-relaunch-dead-endpoint.test.sh 31467
-tests/fm-spawn-worktree-settle.test.sh 5788
+tests/fm-pi-watch-extension.test.sh 22125
+tests/fm-pr-check-handoff.test.sh 15330
+tests/fm-pr-check-security.test.sh 163835
+tests/fm-prepush-guard.test.sh 19861
+tests/fm-procevent-when.test.sh 21536
+tests/fm-procevent.test.sh 69535
+tests/fm-public-followup.test.sh 47380
+tests/fm-quota-array-dispatch-live-e2e.test.sh 19
+tests/fm-receipt-check.test.sh 6254
+tests/fm-receipt.test.sh 1854
+tests/fm-reflect-skill.test.sh 473
+tests/fm-remote-backlog-handoff.test.sh 20170
+tests/fm-remote-doctor.test.sh 5787
+tests/fm-remote-entrypoint.test.sh 263
+tests/fm-remote-job.test.sh 48956
+tests/fm-remote-omp-update-restart-live-e2e.test.sh 20
+tests/fm-remote-reply.test.sh 82089
+tests/fm-remote-secondmate-lifecycle-e2e.test.sh 657637
+tests/fm-remote-secondmate-parent-binding.test.sh 15757
+tests/fm-remote-secondmate-sleep-reconcile.test.sh 1287
+tests/fm-remote-secondmate-trace-context.test.sh 59252
+tests/fm-remote-secondmate-update-restart.test.sh 30187
+tests/fm-runpod-lifecycle.test.sh 58778
+tests/fm-runpod-omp-auth.test.sh 1192
+tests/fm-runpod-pod-boot.test.sh 43135
+tests/fm-runpod-routing.test.sh 37449
+tests/fm-secondmate-harness.test.sh 170105
+tests/fm-secondmate-lifecycle-e2e.test.sh 6278
+tests/fm-secondmate-liveness.test.sh 20034
+tests/fm-secondmate-restart.test.sh 36334
+tests/fm-secondmate-safety.test.sh 58742
+tests/fm-secondmate-sync.test.sh 40216
+tests/fm-send-inbox-doorbell-live-e2e.test.sh 22
+tests/fm-send-inbox.test.sh 40199
+tests/fm-send-resolve-key.test.sh 22866
+tests/fm-send-secondmate-marker-herdr-e2e.test.sh 49
+tests/fm-send-secondmate-marker.test.sh 4337
+tests/fm-send-turn-start.test.sh 11083
+tests/fm-session-lock-ancestry.test.sh 1513
+tests/fm-session-start.test.sh 65773
+tests/fm-sessionstart-nudge.test.sh 303
+tests/fm-shared-captain-inheritance.test.sh 13503
+tests/fm-spawn-dispatch-profile.test.sh 249954
+tests/fm-spawn-pool-base-freshen.test.sh 35286
+tests/fm-spawn-relaunch-dead-endpoint.test.sh 35039
+tests/fm-spawn-worktree-settle.test.sh 11488
 tests/fm-stall-recovery.test.sh 48
-tests/fm-startup-memory-budget.test.sh 7593
-tests/fm-subagent-pretool-check.test.sh 709
-tests/fm-supervision-events.test.sh 462
-tests/fm-tangle-guard.test.sh 8797
-tests/fm-task-delivery.test.sh 9829
-tests/fm-task-inbox.test.sh 37450
-tests/fm-teardown-endpoint-safety.test.sh 1797
-tests/fm-teardown.test.sh 107078
-tests/fm-test-fixture-cleanup.test.sh 542
-tests/fm-test-isolation-proof.test.sh 426
-tests/fm-todo-project.test.sh 6065
-tests/fm-trace-context-lib.test.sh 1424
-tests/fm-trace-context-spawn.test.sh 46250
-tests/fm-treehouse-orphan-recovery.test.sh 125
-tests/fm-treehouse-status-read-only.test.sh 225
-tests/fm-treehouse-sweep.test.sh 4886
-tests/fm-turnend-guard.test.sh 20258
-tests/fm-update.test.sh 10591
-tests/fm-vendor-auth-probe.test.sh 42632
-tests/fm-wake-daemon-lifecycle-e2e.test.sh 19948
-tests/fm-wake-drain-open-decisions-cursor.test.sh 22217
-tests/fm-wake-drain-open-decisions.test.sh 3443
-tests/fm-wake-drain-unread-status.test.sh 14508
-tests/fm-wake-queue.test.sh 72347
-tests/fm-watch-arm.test.sh 66052
-tests/fm-watch-checkpoint.test.sh 4768
-tests/fm-watch-recovery-loop.test.sh 67796
-tests/fm-watch-triage.test.sh 407955
-tests/fm-watcher-lock.test.sh 38168
+tests/fm-startup-memory-budget.test.sh 6514
+tests/fm-subagent-pretool-check.test.sh 968
+tests/fm-supervision-events.test.sh 628
+tests/fm-tangle-guard.test.sh 10406
+tests/fm-task-delivery.test.sh 19399
+tests/fm-task-inbox.test.sh 37373
+tests/fm-tasks-axi.test.sh 18227
+tests/fm-teardown-endpoint-safety.test.sh 30883
+tests/fm-teardown.test.sh 137584
+tests/fm-test-fixture-cleanup.test.sh 681
+tests/fm-test-isolation-proof.test.sh 588
+tests/fm-todo-project.test.sh 9125
+tests/fm-trace-context-lib.test.sh 1997
+tests/fm-trace-context-spawn.test.sh 45140
+tests/fm-treehouse-orphan-recovery.test.sh 111
+tests/fm-treehouse-status-read-only.test.sh 223
+tests/fm-treehouse-sweep.test.sh 4347
+tests/fm-turnend-guard.test.sh 21290
+tests/fm-update.test.sh 9518
+tests/fm-vendor-auth-probe.test.sh 42927
+tests/fm-wake-daemon-lifecycle-e2e.test.sh 69696
+tests/fm-wake-drain-open-decisions-cursor.test.sh 26536
+tests/fm-wake-drain-open-decisions.test.sh 12358
+tests/fm-wake-drain-unread-status.test.sh 30489
+tests/fm-wake-queue.test.sh 85314
+tests/fm-watch-arm.test.sh 85430
+tests/fm-watch-checkpoint.test.sh 5858
+tests/fm-watch-recovery-loop.test.sh 66814
+tests/fm-watch-triage.test.sh 428164
+tests/fm-watcher-lock.test.sh 46975
 EOF
 }