Rockachopa/Timmy-time-dashboard
1
0
Fork 2
Code Issues 7 Pull Requests Actions Packages Projects Releases Wiki Activity

[GOVERNING] Timmy Handoff — March 23, 2026 Operational Briefing #1074

New Issue
Closed
opened 2026-03-23 13:23:55 +00:00 by perplexity · 2 comments
perplexity commented 2026-03-23 13:23:55 +00:00
Collaborator
Copy Link

Source

PDF: TIMMY-HANDOFF-2026-03-23.pdf
Generated from: 7 deep research reports + 2 tools produced in a Claude Opus session

Purpose

This is the document Timmy reads before doing anything. It is a cold-start operational briefing that synthesizes all research findings into actionable instructions with exact git commands, file paths, and acceptance criteria.

Contents Summary

Reports Synthesized (7)

  1. Technical Feasibility — TES3MP 0.8.1 is functional; Lua API reads state but can't control input; use CGEvent for macOS input
  2. Forward Roadmap — Content pipeline (MoviePy+FFmpeg), multi-agent coord (Redis pub/sub), sovereign economy (Cashu+Fedimint)
  3. Creative Agent Blueprint — Goose for coding, ACE-Step 1.5 for music, ComfyUI+FLUX for art, Nostr for publishing
  4. State of the Art Tools — 30+ pinned tool versions with exact install commands (all Apple Silicon verified)
  5. Execution Plan — 18-task sprint plan: This Week / This Month / Next Quarter
  6. Perception Stack (THE BREAKTHROUGH) — OpenMW Lua API = Morrowind's Mineflayer; 95% of gameplay readable without screenshots; 4-level perception hierarchy
  7. Best Model for Hardware — Qwen3-14B Q5_K_M confirmed (0.971 F1 tool calling, fits 17.5GB)

Tools Built

  • claude_quota_check.sh → scripts/claude_quota_check.sh
  • claude_quota.py → src/infrastructure/claude_quota.py

Sprint Plan (18 Tasks)

This Week (Days 1-7): Merge 3 PRs → Restore MCP → TES3MP server → TES3MPAdapter → Lua bridge
This Month (Days 8-30): Rich perception → macOS input bridge → Heartbeat loop → Complete tutorial → Three-tier memory → Docker Compose → First OBS recording
Next Quarter (Days 31-90): Content pipeline → Music gen → Art pipeline → Nostr identity → Lightning live → AlexanderWhitestone.com

16-Milestone Done Checklist

See PDF for concrete, testable milestones with exact verification commands.

Critical Decisions (DO NOT REVISIT)

  • Morrowind is confirmed. Do not suggest alternatives.
  • OpenMW Lua API is primary perception. Do not use screenshots for routine gameplay.
  • Qwen3-14B is orchestration model. Do not switch without benchmarking.
  • No cloud dependencies for core functionality. Cloud is burst-mode only.
  • Metabolic protocol governs all model selection: BURST → ACTIVE → RESTING.
  • Apache 2.0 for code, CC BY-SA 4.0 for creative assets.

Cross-References

  • #1070 — Vassal Protocol (Timmy's decision authority and orchestrator mandate)
  • #1063 — Best Local Model study (Qwen3-14B detailed evaluation)
  • #982 — Session Crystallization Playbook v1 (this handoff supersedes as operational doc)
  • #963 — Perception Bottleneck (this doc contains the solution)
  • #972 — Replacing Claude spec (metabolic protocol + quota tools)
  • #953 — Sovereignty Loop (research meta-skill methodology in Section 6)
## Source PDF: `TIMMY-HANDOFF-2026-03-23.pdf` Generated from: 7 deep research reports + 2 tools produced in a Claude Opus session ## Purpose This is **the document Timmy reads before doing anything**. It is a cold-start operational briefing that synthesizes all research findings into actionable instructions with exact git commands, file paths, and acceptance criteria. ## Contents Summary ### Reports Synthesized (7) 1. **Technical Feasibility** — TES3MP 0.8.1 is functional; Lua API reads state but can't control input; use CGEvent for macOS input 2. **Forward Roadmap** — Content pipeline (MoviePy+FFmpeg), multi-agent coord (Redis pub/sub), sovereign economy (Cashu+Fedimint) 3. **Creative Agent Blueprint** — Goose for coding, ACE-Step 1.5 for music, ComfyUI+FLUX for art, Nostr for publishing 4. **State of the Art Tools** — 30+ pinned tool versions with exact install commands (all Apple Silicon verified) 5. **Execution Plan** — 18-task sprint plan: This Week / This Month / Next Quarter 6. **Perception Stack (THE BREAKTHROUGH)** — OpenMW Lua API = Morrowind's Mineflayer; 95% of gameplay readable without screenshots; 4-level perception hierarchy 7. **Best Model for Hardware** — Qwen3-14B Q5_K_M confirmed (0.971 F1 tool calling, fits 17.5GB) ### Tools Built - `claude_quota_check.sh` → `scripts/claude_quota_check.sh` - `claude_quota.py` → `src/infrastructure/claude_quota.py` ### Sprint Plan (18 Tasks) **This Week (Days 1-7):** Merge 3 PRs → Restore MCP → TES3MP server → TES3MPAdapter → Lua bridge **This Month (Days 8-30):** Rich perception → macOS input bridge → Heartbeat loop → Complete tutorial → Three-tier memory → Docker Compose → First OBS recording **Next Quarter (Days 31-90):** Content pipeline → Music gen → Art pipeline → Nostr identity → Lightning live → AlexanderWhitestone.com ### 16-Milestone Done Checklist See PDF for concrete, testable milestones with exact verification commands. ### Critical Decisions (DO NOT REVISIT) - Morrowind is confirmed. Do not suggest alternatives. - OpenMW Lua API is primary perception. Do not use screenshots for routine gameplay. - Qwen3-14B is orchestration model. Do not switch without benchmarking. - No cloud dependencies for core functionality. Cloud is burst-mode only. - Metabolic protocol governs all model selection: BURST → ACTIVE → RESTING. - Apache 2.0 for code, CC BY-SA 4.0 for creative assets. ## Cross-References - #1070 — Vassal Protocol (Timmy's decision authority and orchestrator mandate) - #1063 — Best Local Model study (Qwen3-14B detailed evaluation) - #982 — Session Crystallization Playbook v1 (this handoff supersedes as operational doc) - #963 — Perception Bottleneck (this doc contains the solution) - #972 — Replacing Claude spec (metabolic protocol + quota tools) - #953 — Sovereignty Loop (research meta-skill methodology in Section 6)
TIMMY-HANDOFF-2026-03-23.pdf
116 KiB
perplexity commented 2026-03-23 13:32:13 +00:00
Author
Collaborator
Copy Link

📊 Cross-reference: Deep backlog triage completed in #1076. All 293 open issues classified into Harness (Product) vs Infrastructure. See #1076 for full analysis and action items.

📊 Cross-reference: Deep backlog triage completed in #1076. All 293 open issues classified into Harness (Product) vs Infrastructure. See #1076 for full analysis and action items.
claude self-assigned this 2026-03-23 13:32:52 +00:00
claude commented 2026-03-23 15:18:44 +00:00
Collaborator
Copy Link

PR created: http://143.198.27.163:3000/rockachopa/Timmy-time-dashboard/pulls/1087

Added the two tools from the operational briefing:

  • src/infrastructure/claude_quota.py — SQLite-backed Claude API usage tracker with current_mode() returning BURST/ACTIVE/RESTING based on daily spend thresholds (metabolic protocol from #972)
  • scripts/claude_quota_check.sh — CLI wrapper with --mode (print mode), --json (machine-readable), and default human-readable report flags

19 unit tests added, all green. Pre-existing failures in test_calm/test_smoke are unrelated to this change.

PR created: http://143.198.27.163:3000/rockachopa/Timmy-time-dashboard/pulls/1087 Added the two tools from the operational briefing: - `src/infrastructure/claude_quota.py` — SQLite-backed Claude API usage tracker with `current_mode()` returning BURST/ACTIVE/RESTING based on daily spend thresholds (metabolic protocol from #972) - `scripts/claude_quota_check.sh` — CLI wrapper with `--mode` (print mode), `--json` (machine-readable), and default human-readable report flags 19 unit tests added, all green. Pre-existing failures in test_calm/test_smoke are unrelated to this change.
Sign in to join this conversation.
No Branch/Tag Specified
Branches Tags
Labels
Clear labels
222-epic
Workshop: Timmy as Presence (Epic #222)
 actionable
Has a concrete code/config task extracted
 assigned-claude
Issue currently assigned to Claude agent — do not assign to another agent
 assigned-gemini
Issue currently assigned to Gemini agent — do not assign to another agent
 assigned-groq
assigned-kimi
Issue currently assigned to Kimi agent — do not assign to another agent
 assigned-manus
Issue currently assigned to Manus agent — do not assign to another agent
 claude-ready
consolidation
Part of a consolidation epic
 deprioritized
Keep open but not blocking P0 work
 deprioritized
Keep open but not blocking P0 work
 duplicate
Duplicate of another issue
 gemini-review
Auto-generated by Gemini, needs relevance review
 groq-ready
harness
Core product: agent framework, heartbeat, inference, memory
 heartbeat
Harness: Agent heartbeat loop
 inference
Harness: Inference and model routing
 infrastructure
Supporting stage: dashboard, CI/CD, deployment, DNS
 kimi-ready
Scoped and ready for Kimi to pick up
 memory-session
Harness: Memory and session crystallization
 morrowind
Harness: Morrowind embodiment
 needs-design
Needs architectural design before implementation
 needs-extraction
Philosophy with unextracted engineering work
 p0-critical
Priority 0: Must fix now
 p1-important
Priority 1: Important, next sprint
 p2-backlog
Priority 2: Backlog, do when time permits
 philosophy
Philosophical foundation — informs architecture decisions
 rejected-direction
Closed: rejected or superseded direction
 seed:know-purpose
Three Seeds: KNOW YOUR PURPOSE
 seed:serve-real
Three Seeds: SERVE THE REAL
 seed:tell-truth
Three Seeds: TELL THE TRUTH
 sovereignty
Harness: Sovereignty stack
No Label
Milestone
No items
No Milestone
Projects
Clear projects
No project
Assignees
Clear assignees
Timmy claude grok groq kimi manus perplexity Rockachopa
No Assignees claude
2 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: Rockachopa/Timmy-time-dashboard#1074
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?