From dbb930d546d477d451a2978494f63e1b3b535f41 Mon Sep 17 00:00:00 2001 From: Vuong Hoang Date: Fri, 28 Aug 2026 10:27:03 -0700 Subject: [PATCH] fix(playbooks): 3.0.1 herald reinstall, and two guards that were release-hostile Reinstalls althing-core on nh3-extdev for 3.0.1 (the pane-route fix) and restarts the herald. Both boxes verified BY CONTENT rather than by version string -- forseti's own checks, grep for _PANE_ID and _live_pid, because a dist-info directory records what was installed, not what the files contain. Both went 0 -> 3 and 0 -> 2. Two bugs in the playbook this run exposed, both of which only appear on the second use: The install step was gated on `postbox` not existing. That guard was correct for the cutover, when postbox genuinely was absent, and wrong for every release after it -- postbox exists now, so a version bump would have silently skipped the install and the playbook would have reported success having done nothing. `--force` already makes the reinstall idempotent, so the guard bought nothing and cost correctness. The post_office variable still pointed at nh3-dev, three hours after the post office moved to nh3-docker. It failed in the verify rather than at install time, which reads as a broken deploy rather than as a stale constant. Worth noting the failure message was the outage semantics working exactly as designed: "This is an outage, not an answer: do not treat it as 'no mail'." --- playbooks/nh3-extdev-althing-v3.yaml | 30 +++++++++++++++++++--------- 1 file changed, 21 insertions(+), 9 deletions(-) diff --git a/playbooks/nh3-extdev-althing-v3.yaml b/playbooks/nh3-extdev-althing-v3.yaml index 8b02fd4..22cbe91 100644 --- a/playbooks/nh3-extdev-althing-v3.yaml +++ b/playbooks/nh3-extdev-althing-v3.yaml @@ -1,4 +1,4 @@ -# nh3-extdev: cut the system-wide althing install over from v2.1.0 to v3.0.0 (U9b flag day). +# nh3-extdev: cut the system-wide althing install over from v2.1.0 to v3.0.x (U9b flag day; re-run for each release). # # nh3-extdev is the one box a `git pull` cannot move: althing lives there as a system WHEEL # under /opt/uv-tools/althing-core with entry points in /usr/local/bin, installed from a wheel @@ -19,17 +19,19 @@ # Rerunnable: a second run shows the install and unit steps skipped. vars: - wheel_src: /home/lkraven/development/althing/dist/althing_core-3.0.0-py3-none-any.whl - wheel_dest: /tmp/althing_core-3.0.0-py3-none-any.whl + wheel_src: /home/lkraven/development/althing/dist/althing_core-3.0.1-py3-none-any.whl + wheel_dest: /tmp/althing_core-3.0.1-py3-none-any.whl uv: /home/infra-ops/.local/bin/uv tool_dir: /opt/uv-tools bin_dir: /usr/local/bin - post_office: http://10.100.10.50:8390 + # ⚠ Moved off nh3-dev 2026-08-28. A stale value here does not fail loudly at + # install time — it fails in the VERIFY, which then reads as a broken deploy. + post_office: http://10.100.50.40:8390 steps: - name: Stage the v3.0.0 wheel upload: - src: /home/lkraven/development/althing/dist/althing_core-3.0.0-py3-none-any.whl + src: /home/lkraven/development/althing/dist/althing_core-3.0.1-py3-none-any.whl dest: "{{ wheel_dest }}" mode: "0644" @@ -41,9 +43,11 @@ steps: shell: sudo systemctl disable --now althing-herald.service althing-receiver.service when: "systemctl is-active --quiet althing-herald.service || systemctl is-active --quiet althing-receiver.service" - - name: Install althing-core 3.0.0 over the system wheel install + - name: Install the staged althing-core wheel over the system wheel install + # NOT gated on `postbox` existing — that guard was right for the cutover and + # wrong for every release after it: postbox exists now, so a version bump would + # silently skip. `--force` makes the reinstall idempotent on its own. shell: sudo env UV_TOOL_DIR={{ tool_dir }} UV_TOOL_BIN_DIR={{ bin_dir }} {{ uv }} tool install --force {{ wheel_dest }} - when: "! {{ bin_dir }}/postbox --help >/dev/null 2>&1" - name: Install the post-office herald as a system unit # A system unit rather than a user unit because that is how v2 was supervised here and @@ -74,8 +78,8 @@ steps: sudo systemctl daemon-reload when: "! test -f /etc/systemd/system/althing-po-herald.service" - - name: Enable and start the herald - shell: sudo systemctl enable --now althing-po-herald.service + - name: Enable and (re)start the herald so it picks up the new code + shell: sudo systemctl enable --now althing-po-herald.service && sudo systemctl restart althing-po-herald.service verify: - name: postbox is installed and is v3 @@ -102,3 +106,11 @@ verify: # check fails on identity, not on reachability, and reads as a deployment fault. shell: ALTHING_POST_OFFICE={{ post_office }} {{ bin_dir }}/postbox --handle operator handles | wc -l | awk '{ if ($1 >= 70) exit 0; else exit 1 }' changed_when: "false" + + - name: The 3.0.1 pane-route fix is present BY CONTENT, not by version string + # forseti's own checks. A dist-info directory records what was installed, not + # what the files contain — verify the code, not the label. + shell: | + SP={{ tool_dir }}/althing-core/lib/python3.13/site-packages/althing + grep -q _PANE_ID "$SP/zellij.py" && grep -q _live_pid "$SP/session_source.py" + changed_when: "false"