Timmy_Foundation/timmy-config
16
0
Fork 0
Code Issues 106 Pull Requests Actions Packages Projects Releases Wiki Activity

[OPS] Import gemini-loop and timmy-orchestrator into timmy-config source of truth #151

New Issue
Closed
opened 2026-04-04 20:20:49 +00:00 by Timmy · 3 comments
Timmy commented 2026-04-04 20:20:49 +00:00
Owner
Copy Link

Problem: ~/.hermes/bin/gemini-loop.sh and ~/.hermes/bin/timmy-orchestrator.sh are still live runtime automations but are not mirrored into timmy-config/bin/. That keeps the system split-brained: runtime truth differs from source-controlled truth, and stale queue logic can come back without review.

Scope:

  • audit both live scripts for stale repo targets, token identity mistakes, queue-resurrection behavior, and runtime-only assumptions
  • import them into clean timmy-config branches from origin/main
  • patch obvious stale paths if found
  • document state files / risks in the automation inventory

Acceptance criteria:

  • both scripts exist in timmy-config/bin/ on a merged PR
  • no human token fallback is introduced
  • repo targets and comments are aligned with current world state
  • queue-resurrection behavior is explicitly documented
  • work is visible in linked PRs/comments for operator visibility
Problem: `~/.hermes/bin/gemini-loop.sh` and `~/.hermes/bin/timmy-orchestrator.sh` are still live runtime automations but are not mirrored into `timmy-config/bin/`. That keeps the system split-brained: runtime truth differs from source-controlled truth, and stale queue logic can come back without review. Scope: - audit both live scripts for stale repo targets, token identity mistakes, queue-resurrection behavior, and runtime-only assumptions - import them into clean `timmy-config` branches from `origin/main` - patch obvious stale paths if found - document state files / risks in the automation inventory Acceptance criteria: - both scripts exist in `timmy-config/bin/` on a merged PR - no human token fallback is introduced - repo targets and comments are aligned with current world state - queue-resurrection behavior is explicitly documented - work is visible in linked PRs/comments for operator visibility
Timmy commented 2026-04-04 20:22:09 +00:00
Author
Owner
Copy Link

Audit findings for live runtime loops:

  1. gemini-loop.sh
  • not mirrored into timmy-config/bin yet
  • stale repo target still includes Timmy_Foundation/autolora
  • usage comment says default 3 while runtime default is 2
  • self-assigns unassigned issues by default, which can silently resurrect queue state
  1. timmy-orchestrator.sh
  • not mirrored into timmy-config/bin yet
  • stale repo target still includes Timmy_Foundation/autolora
  • bulk-assigns every unassigned issue to claude by default, which can repopulate queues after cleanup
  • startup log still references qwen3:30b via Ollama, which is stale world-state messaging

Planned import direction:

  • import both scripts into timmy-config/bin from clean origin/main branches
  • update repo targets to current core repos
  • make self-assignment / bulk auto-assignment opt-in, not default-on
  • update automation inventory to document the new safer defaults
  • land as visible PR linked to this issue
Audit findings for live runtime loops: 1. gemini-loop.sh - not mirrored into timmy-config/bin yet - stale repo target still includes Timmy_Foundation/autolora - usage comment says default 3 while runtime default is 2 - self-assigns unassigned issues by default, which can silently resurrect queue state 2. timmy-orchestrator.sh - not mirrored into timmy-config/bin yet - stale repo target still includes Timmy_Foundation/autolora - bulk-assigns every unassigned issue to claude by default, which can repopulate queues after cleanup - startup log still references qwen3:30b via Ollama, which is stale world-state messaging Planned import direction: - import both scripts into timmy-config/bin from clean origin/main branches - update repo targets to current core repos - make self-assignment / bulk auto-assignment opt-in, not default-on - update automation inventory to document the new safer defaults - land as visible PR linked to this issue
Timmy commented 2026-04-04 20:26:30 +00:00
Author
Owner
Copy Link

Opened implementation PR #152: http://143.198.27.163:3000/Timmy_Foundation/timmy-config/pulls/152

This PR imports the two live runtime loops into timmy-config/bin/ and flips surprise queue mutation to opt-in defaults.

Opened implementation PR #152: http://143.198.27.163:3000/Timmy_Foundation/timmy-config/pulls/152 This PR imports the two live runtime loops into `timmy-config/bin/` and flips surprise queue mutation to opt-in defaults.
Timmy closed this issue 2026-04-04 20:27:40 +00:00
Timmy commented 2026-04-04 20:27:42 +00:00
Author
Owner
Copy Link

PR #152 merged: http://143.198.27.163:3000/Timmy_Foundation/timmy-config/pulls/152

Next step: deploy merged sidecar content and restart the live Gemini loop + Timmy orchestrator so runtime picks up the new safe defaults.

PR #152 merged: http://143.198.27.163:3000/Timmy_Foundation/timmy-config/pulls/152 Next step: deploy merged sidecar content and restart the live Gemini loop + Timmy orchestrator so runtime picks up the new safe defaults.
Sign in to join this conversation.
No Branch/Tag Specified
Branches Tags
Labels
Clear labels
assigned-claw-code
Queued for Code Claw (qwen/openrouter)
 assigned-kimi
Dispatched to Kimi via OpenClaw
 assigned-sonnet
claw-code-done
Code Claw completed this task
 claw-code-in-progress
Code Claw is actively working
 enhancement
epic
kimi-done
Kimi completed this task
 kimi-in-progress
Kimi is actively working on this
 lazzyPit
Lazarus Pit automated recovery system
 research
sonnet-ready
velocity-engine
Auto-generated by velocity engine
No Label
Milestone
No items
No Milestone
Projects
Clear projects
No project
Assignees
Clear assignees
KimiClaw Rockachopa Timmy allegro antigravity bezalel claude claw-code codex-agent ezra gemini google grok groq hermes kimi manus perplexity sonnet
No Assignees
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: Timmy_Foundation/timmy-config#151
Delete Branch "%!s()"

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?