cal/claude-home
1
0
Fork 0
Code Issues 6 Pull Requests 4 Actions Packages Projects Releases Wiki Activity

fix: clean up VM 116 watchstate duplicate and document decommission candidacy (#31) #41

Merged
cal merged 1 commits from issue/31-vm-116-resolve-watchstate-duplicate-and-clean-up-r into main 2026-04-03 20:01:28 +00:00
Conversation 0 Commits 1 Files Changed 2 +18 -4
Claude commented 2026-04-03 16:04:51 +00:00
Collaborator
Copy Link

Closes #31

Summary

  • Confirmed manticore's watchstate (v1.0.2) is healthy and the canonical instance — it's actively syncing Jellyfin state
  • Removed the stopped/broken watchstate container from VM 116 (was in restart loop due to corrupt Caddy PKI cert, stale duplicate)
  • Pruned 5 orphan Docker images on VM 116: watchstate, freetube, pihole, hello-world → 3.36 GB reclaimed
  • VM 116 now runs only Jellyfin (jellyfin container up 8 days, healthy)

Infrastructure changes (live)

VM 116 (10.10.0.124) before:
  containers: watchstate (Exited), jellyfin (Up)
  images: jellyfin, watchstate, freetube, pihole, hello-world

VM 116 (10.10.0.124) after:
  containers: jellyfin (Up 8 days)
  images: lscr.io/linuxserver/jellyfin:latest (750 MB)

Documentation changes

  • server-configs/hosts.yml — added docker-home-servers (VM 116) entry as a decommission candidate, noting Jellyfin-only state and duplicate overlap with manticore
  • vm-management/proxmox-upgrades/proxmox-7-to-9-upgrade-plan.md — updated status from Stopped/Investigate → Decommission Candidate

Next steps (out of scope, for follow-up issues)

  • VM 116 decommission — Jellyfin on manticore already covers this; opening a separate decommission issue following the runbook would reclaim 4 vCPUs + 8 GB RAM
  • VM 110 decommission — also empty (related note in original issue); same opportunity
  • Both together: 8 vCPUs + 16 GB RAM reclaimed
Closes #31 ## Summary - **Confirmed** manticore's watchstate (`v1.0.2`) is healthy and the canonical instance — it's actively syncing Jellyfin state - **Removed** the stopped/broken watchstate container from VM 116 (was in restart loop due to corrupt Caddy PKI cert, stale duplicate) - **Pruned** 5 orphan Docker images on VM 116: watchstate, freetube, pihole, hello-world → **3.36 GB reclaimed** - VM 116 now runs **only Jellyfin** (jellyfin container up 8 days, healthy) ## Infrastructure changes (live) ``` VM 116 (10.10.0.124) before: containers: watchstate (Exited), jellyfin (Up) images: jellyfin, watchstate, freetube, pihole, hello-world VM 116 (10.10.0.124) after: containers: jellyfin (Up 8 days) images: lscr.io/linuxserver/jellyfin:latest (750 MB) ``` ## Documentation changes - `server-configs/hosts.yml` — added `docker-home-servers` (VM 116) entry as a decommission candidate, noting Jellyfin-only state and duplicate overlap with manticore - `vm-management/proxmox-upgrades/proxmox-7-to-9-upgrade-plan.md` — updated status from `Stopped/Investigate` → `Decommission Candidate` ## Next steps (out of scope, for follow-up issues) - **VM 116 decommission** — Jellyfin on manticore already covers this; opening a separate decommission issue following the runbook would reclaim 4 vCPUs + 8 GB RAM - **VM 110 decommission** — also empty (related note in original issue); same opportunity - Both together: 8 vCPUs + 16 GB RAM reclaimed
Claude added 1 commit 2026-04-03 16:04:52 +00:00
fix: clean up VM 116 watchstate duplicate and document decommission candidacy (#31)
All checks were successful
Auto-merge docs-only PRs / auto-merge-docs (pull_request) Successful in 3s
Details
2e504f4998 
- Removed stopped watchstate container from VM 116 (duplicate of manticore's canonical instance)
- Pruned 5 orphan images (watchstate, freetube, pihole, hello-world): 3.36 GB reclaimed
- Confirmed manticore watchstate is healthy and syncing Jellyfin state
- VM 116 now runs only Jellyfin (also runs on manticore)
- Added VM 116 (docker-home-servers) to hosts.yml as decommission candidate
- Updated proxmox-7-to-9-upgrade-plan.md status from Stopped/Investigate to Decommission Candidate

Closes #31

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Claude added the
ai-reviewing
 label 2026-04-03 16:15:26 +00:00
Claude reviewed 2026-04-03 16:16:36 +00:00
Claude left a comment
Author
Collaborator
Copy Link

AI Code Review

Files Reviewed

  • server-configs/hosts.yml (modified)
  • vm-management/proxmox-upgrades/proxmox-7-to-9-upgrade-plan.md (modified)

Findings

Correctness

  • The docker-home-servers entry correctly captures VM 116's current state: only Jellyfin remains, decommission candidacy is noted, and the old commented-out docker-home (same IP, stale "Decommissioned" note) is properly replaced.
  • The upgrade plan update accurately reflects the investigation outcome — status changed from Stopped/Investigate to Decommission Candidate with a concise rationale and issue reference.
  • IP, VMID, user, and config path values in the new YAML entry are all internally consistent with the PR description.

Security

  • No issues found. No credentials, tokens, or PII introduced. Internal homelab IPs (10.10.0.x) are consistent with the rest of the file.

Style & Conventions

  • YAML structure and field ordering of the new docker-home-servers entry matches the project's existing docker-type host pattern.
  • Markdown prose and table formatting in the upgrade plan matches the surrounding document style.
  • The decommission_candidate: true field and dated notes string are good ops practice for a hosts inventory.

Suggestions

  • docker-home-servers is the only docker-type host in hosts.yml without an ssh_alias field. Other docker hosts (ubuntu-manticore, discord-bots, sba-bots, strat-database, etc.) all carry one. Since sync-configs.sh uses this file for SSH-based config management, omitting ssh_alias means any automation that iterates over hosts would silently skip VM 116 or error. If the intent is to prevent automation from touching it (reasonable for a decommission candidate), a brief inline comment noting that would clarify the intent. No change required before merge.

Verdict: APPROVED

Clean, well-scoped documentation update. Changes accurately reflect the live infrastructure state after cleanup. The decommission candidacy is properly recorded in both the host inventory and the upgrade plan. No correctness, security, or convention issues found.

Automated review by Claude PR Reviewer

## AI Code Review ### Files Reviewed - `server-configs/hosts.yml` (modified) - `vm-management/proxmox-upgrades/proxmox-7-to-9-upgrade-plan.md` (modified) ### Findings #### Correctness - The `docker-home-servers` entry correctly captures VM 116's current state: only Jellyfin remains, decommission candidacy is noted, and the old commented-out `docker-home` (same IP, stale "Decommissioned" note) is properly replaced. - The upgrade plan update accurately reflects the investigation outcome — status changed from `Stopped/Investigate` to `Decommission Candidate` with a concise rationale and issue reference. - IP, VMID, user, and config path values in the new YAML entry are all internally consistent with the PR description. #### Security - No issues found. No credentials, tokens, or PII introduced. Internal homelab IPs (10.10.0.x) are consistent with the rest of the file. #### Style & Conventions - YAML structure and field ordering of the new `docker-home-servers` entry matches the project's existing docker-type host pattern. - Markdown prose and table formatting in the upgrade plan matches the surrounding document style. - The `decommission_candidate: true` field and dated `notes` string are good ops practice for a hosts inventory. #### Suggestions - `docker-home-servers` is the only docker-type host in `hosts.yml` without an `ssh_alias` field. Other docker hosts (ubuntu-manticore, discord-bots, sba-bots, strat-database, etc.) all carry one. Since `sync-configs.sh` uses this file for SSH-based config management, omitting `ssh_alias` means any automation that iterates over hosts would silently skip VM 116 or error. If the intent is to prevent automation from touching it (reasonable for a decommission candidate), a brief inline comment noting that would clarify the intent. No change required before merge. ### Verdict: APPROVED Clean, well-scoped documentation update. Changes accurately reflect the live infrastructure state after cleanup. The decommission candidacy is properly recorded in both the host inventory and the upgrade plan. No correctness, security, or convention issues found. --- *Automated review by Claude PR Reviewer*
Claude added
ai-reviewed
 and removed
ai-reviewing
 labels 2026-04-03 16:16:42 +00:00
cal force-pushed issue/31-vm-116-resolve-watchstate-duplicate-and-clean-up-r from 2e504f4998 to 66143f6090 2026-04-03 20:01:16 +00:00 Compare
cal merged commit 938240e1f9 into main 2026-04-03 20:01:28 +00:00
cal deleted branch issue/31-vm-116-resolve-watchstate-duplicate-and-clean-up-r 2026-04-03 20:01:28 +00:00
Sign in to join this conversation.
Reviewers
No reviewers
Labels
Clear labels   
ai-changes-requested

   
ai-failed

   
ai-pr-opened

   
ai-reviewed

   
ai-reviewing

   
ai-working

   
infra-audit

Infrastructure audit remediation tasks

  
monitoring

Monitoring, alerting, and observability

  
operations

Ongoing operational improvements

  
proxmox

Proxmox VM/CT management

  
script

Script improvements and tooling

No Label
ai-changes-requested
ai-failed
ai-pr-opened
ai-reviewed
ai-reviewing
ai-working
infra-audit
monitoring
operations
proxmox
script
Milestone
Clear milestone
No items
No Milestone
Projects
Clear projects
No project
Assignees
Clear assignees
No Assignees
2 Participants
Notifications
Due Date
The due date is invalid or out of range. Please use the format 'yyyy-mm-dd'.

No due date set.

Dependencies

No dependencies set.

Reference: cal/claude-home#41
No description provided.
Delete Branch "issue/31-vm-116-resolve-watchstate-duplicate-and-clean-up-r"

Deleting a branch is permanent. Although the deleted branch may continue to exist for a short time before it actually gets removed, it CANNOT be undone in most cases. Continue?