SyslogSolution/prose-contracts
7
0
Fork 0
Code Issues 2 Pull Requests Actions Packages Projects Releases Wiki Activity

fix: ship pm2-self-heal crash-loop guard + align gpu-dense docs to Qwen3.8-27B #49

Merged
mumuni-bot merged 1 commits from fix/pm2-guard-gpu-doc into master 2026-08-17 02:34:49 +00:00
Conversation 0 Commits 1 Files Changed 4
+23 -15
mumuni-bot commented 2026-08-17 02:33:08 +00:00
Owner
Copy Link
Copy Source

Ships the two outstanding high-risk fixes flagged in the Aug 16 management brief.

  1. pm2-self-heal.sh crash-loop guard (Abiba drafted, was uncommitted): restart abiba-telegram when TEL_RESTARTS > 1000 even if it reports online — catches quiet crash-loops (the 10k-restarts spoton incident). Doc pm2-self-heal.prose.md Rule 2 updated.

  2. gpu-dense doc drift: gpu-fleet.prose.md + gpu-self-heal.prose.md still described SmartCode-Fable-5-27B. Live model (verified .8:8080, Aug 16) is Qwen3.8-27B-Uncensored-Q4_K_M (~16.8GB), served under alias qwen3.6-27B-code for LiteLLM routing. Aligned.

Ships the two outstanding high-risk fixes flagged in the Aug 16 management brief. 1. **pm2-self-heal.sh crash-loop guard** (Abiba drafted, was uncommitted): restart abiba-telegram when TEL_RESTARTS > 1000 even if it reports online — catches quiet crash-loops (the 10k-restarts spoton incident). Doc pm2-self-heal.prose.md Rule 2 updated. 2. **gpu-dense doc drift**: gpu-fleet.prose.md + gpu-self-heal.prose.md still described SmartCode-Fable-5-27B. Live model (verified .8:8080, Aug 16) is Qwen3.8-27B-Uncensored-Q4_K_M (~16.8GB), served under alias qwen3.6-27B-code for LiteLLM routing. Aligned.
mumuni-bot added 1 commit 2026-08-17 02:33:09 +00:00
fix: ship pm2-self-heal crash-loop guard + align gpu-dense docs to Qwen3.8-27B
PR Pipeline — Authorize → Validate → Review → Merge / auth (pull_request) Successful in 3s
Details
PR Pipeline — Authorize → Validate → Review → Merge / validate (pull_request) Successful in 4s
Details
PR Pipeline — Authorize → Validate → Review → Merge / lint (pull_request) Successful in 3s
Details
PR Pipeline — Authorize → Validate → Review → Merge / ai-review (pull_request) Successful in 2s
Details
PR Pipeline — Authorize → Validate → Review → Merge / gate (pull_request) Successful in 0s
Details
20fe5adcbc 
- pm2-self-heal.sh: restart abiba-telegram when TEL_RESTARTS > 1000 even if 'online'
  (catches quiet crash-loops like the 10k-restarts spoton incident); alert includes count.
- pm2-self-heal.prose.md: document the crash-loop guard under Rule 2.
- gpu-fleet.prose.md / gpu-self-heal.prose.md: gpu-dense is Qwen3.8-27B-Uncensored-Q4_K_M
  (~16.8GB, alias qwen3.6-27B-code for LiteLLM routing), not SmartCode-Fable-5 (verified live
  on .8:8080 Aug 16).
mumuni-bot merged commit c3306e87e4 into master 2026-08-17 02:34:49 +00:00
Sign in to join this conversation.
Reviewers
No Reviewers
Labels
No items
No labels
Milestone
No items
No Milestone
Projects
Clear projects
No projects
Assignees
Clear assignees
abiba-bot jerome (Jerome Kwame Tabiri) kagentz-bot kwame (Kwame Tabiri) mumuni-bot (Mumuni 🦅 (Syslog Falcon)) tanko-bot theo
No Assignees
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: SyslogSolution/prose-contracts#49