Commit Graph

5 Commits

Author SHA1 Message Date
mindesbunister
d156abc976 docs: Add mandatory git workflow and critical feedback requirements
CRITICAL UPDATES to AI assistant instructions:

1. MANDATORY GIT WORKFLOW (DO NOT SKIP):
   - Added explicit requirement: implement → test → verify → document → commit → push
   - Made git commits NON-OPTIONAL for all significant changes
   - Added to both general prompt and copilot-instructions.md
   - Rationale: Agent has pattern of skipping documentation/commits

2. CHALLENGE USER IDEAS:
   - Added requirement to think critically about user requests
   - Instruction: "Think freely and don't hold back"
   - Goal: Find BEST solution, not just A solution
   - Push back on ideas that don't make sense
   - Ask "is there a simpler/faster/safer way?"

3. COMPREHENSIVE DOCUMENTATION SECTION:
   - Replaced brief documentation note with full workflow guide
   - Added 80+ lines of detailed documentation requirements
   - Includes examples, red flags, mindset principles
   - Emphasizes: "Git commit + Documentation = Complete work"

Files modified:
- .github/prompts/general prompt.prompt.md (added sections 5a, 6, updated 7-8)
- .github/copilot-instructions.md (comprehensive documentation workflow)

User mandate: "I am sick and tired of reminding you" - this makes it automatic.

Impact: Future implementations will ALWAYS include documentation and git commits as part of standard workflow, not as afterthoughts.
2025-12-02 15:23:20 +01:00
mindesbunister
e748cf709d fix: Correct SSH hop for EPYC worker2 connectivity
- ProxyJump (-J) doesn't work from Docker container
- Changed to nested SSH: hop -> target
- Proper command escaping for nested SSH
- Worker2 (srv-bd-host01) only accessible via worker1 (pve-nu-monitor01)
2025-12-01 19:42:08 +01:00
mindesbunister
1f83a7d7c4 feat: Add coordinator log viewer to cluster UI
- Created /api/cluster/logs endpoint to read coordinator.log
- Added real-time log display in cluster UI (updates every 3s)
- Shows last 100 lines of coordinator.log in terminal-style display
- Includes manual refresh button
- Improves debugging experience - no need to SSH for logs

User feedback: 'why dont we add the output of the log at the bottom of the page so i know whats going on'

This addresses poor visibility into coordinator errors and failures.
Next step: Fix SSH timeout issue blocking worker execution.
2025-12-01 11:49:23 +01:00
mindesbunister
ceb84c3bc1 feat: Revenge system enhancements #4 and #10 - IMPLEMENTED
Enhancement #4: Failed Revenge Tracking
- Added 3 database fields: revengeOutcome, revengePnL, revengeFailedReason
- Added updateRevengeOutcome() method in stop-hunt-tracker.ts
- Position Manager hooks revenge trade closes, records outcome
- Enables data-driven analysis of revenge success rate

Enhancement #10: Metadata Persistence
- Added 4 database fields: firstCrossTime, lowestInZone, highestInZone, zoneResetCount
- Migrated 90-second zone tracking from in-memory to database
- Rewrote shouldExecuteRevenge() with database persistence
- Container restarts now preserve exact zone tracking state

Technical Details:
- Prisma schema updated with 7 new StopHunt fields
- Added signalSource field to ActiveTrade interface
- All zone metadata persisted in real-time to database
- Build verified successful (no TypeScript errors)

Files Changed:
- prisma/schema.prisma (StopHunt model + index)
- lib/trading/stop-hunt-tracker.ts (DB persistence + outcome tracking)
- lib/trading/position-manager.ts (revenge hook + interface)
- docs/REVENGE_ENHANCEMENTS_EXPLAINED.md (comprehensive guide)

Pending User Decision:
- Enhancement #1: ADX confirmation (3 options explained in docs)
- Enhancement #6: SL distance validation (2× ATR recommended)

Status: Ready for deployment after Prisma migration
Date: Nov 27, 2025
2025-11-27 08:08:37 +01:00
mindesbunister
fa3c76c878 docs: Add AI agent prompt for Trading Bot v4
Created comprehensive agent prompt emphasizing:
- Mandatory reading of full copilot-instructions.md (4,400+ lines)
- VERIFICATION MANDATE must be understood before any work
- This is a real money system - every bug costs money
- Never declare 'done/fixed/working' without 100% verification
- Proper workflow: read → code → deploy → verify → document

Key Requirements:
- Check container timestamp > commit timestamp before declaring deployed
- Add logging to confirm changes execute
- Test in production with real data
- Check Common Pitfalls (60+ documented bugs) before coding
- Show verification results as proof, not just code appearance

Financial Stakes:
- User building from $901 → $100,000+ with this system
- Manual restarts = system failure
- Unverified changes = financial risk
- Every change affects real money positions

Prompt ensures agents understand the verification ethos and financial responsibility before starting any work.
2025-11-25 10:25:45 +01:00