Commit Graph

4 Commits

Author SHA1 Message Date
ZhouYongyou
041d6d4048 fix(prompts): add explicit stop-loss direction logic for long/short positions
Address DaDaManMan's error where AI set stop-loss incorrectly for short position.

## Problem
AI attempted to set stop-loss at $107,500 for SHORT position at $108,230,
causing validation error: "空单止损必须高于当前价格"

Root cause: Prompts lacked explicit guidance on stop-loss direction logic.

## Solution

### adaptive.txt (Chinese):
- Add "止损方向逻辑" section with clear rules
- Long position: stop_loss < entry_price (protect downside)
- Short position: stop_loss > entry_price (protect upside)
- Include examples and common mistakes to avoid

### nof1.txt (English):
- Add "Stop-Loss Direction Logic" section
- Same directional rules with detailed explanations
- Include real error example from production logs
- Emphasize validation failures when rules are violated

## Impact
-  Prevents AI from setting illogical stop-loss prices
-  Reduces validation errors and failed trades
-  Provides clear examples with entry/stop-loss pairs
-  Addresses DaDaManMan's reported issue directly

## Files Changed
- prompts/adaptive.txt (+19 lines)
- prompts/nof1.txt (+25 lines)

Fixes: #272 (DaDaManMan's comment)

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude <noreply@anthropic.com>
2025-11-03 20:21:47 +08:00
ZhouYongyou
221b03b383 refactor(prompts): enhance partial_close guidance in adaptive & nof1
## Core Changes

### 1. adaptive.txt - Chinese Enhanced Version
- Add comprehensive partial close guidance chapter (line 137-143)
- Update action table with detailed field requirements (line 131)
- Clarify remaining position management strategy (line 273)
- Add compatibility note for close_percentage field (line 276)
- Update base trading constraints to support partial exits (line 69)
- Changes: +13/-4 lines

### 2. nof1.txt - English Enhanced Version
- Add 'PARTIAL CLOSE & DYNAMIC TP/SL GUIDANCE' chapter (line 55-87)
- Enhance partial_close action definition with use cases (line 37-39)
- Update Required field rules (full English translation + enhancements)
- Add example reasoning for multi-stage exit strategy
- Improve all field rules documentation consistency
- Changes: +43/-6 lines

## Benefits
-  Both prompts now have complete partial_close operation guidance
-  Unified standards: clear percentages (25%/50%/75%), remaining position management
-  Language consistency: adaptive (Chinese) / nof1 (English)
-  Practical examples included to guide AI decision-making
-  Detailed instructions for simultaneous TP/SL adjustments

## Backend Compatibility
- All features supported by backend (decision/engine.go)
- No breaking changes
- partial_close, update_stop_loss, update_take_profit all validated

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude <noreply@anthropic.com>
2025-11-03 19:23:04 +08:00
ZhouYongyou
b3b68b2b62 refactor(prompts): unify action schema & optimize trading discipline
## Core Changes

### 1. adaptive.txt - Adopt v5.5.6.1 strict strategy
- Migrate from dual-strategy system to unified adaptive approach
- Maintain strict confidence threshold ≥85 (anti-overtrading)
- Remove complex market state detection, focus on signal quality
- Explicitly disable partial_close (full exit only)
- -160 lines (removed redundant strategy logic)

### 2. nof1.txt - Fix contradictions & align standards
-  Fix: Remove "NO partial exits" contradiction (now explicitly supported)
-  Unify: Change confidence threshold from 60 → 75
-  Unify: Change risk-reward ratio from 2:1 → 3:1
- Add confidence level guidance (75-85: good, 85-100: high)
- +85 lines (enhanced risk management framework)

### 3. default.txt - Add standardized output format
- Add structured thinking summary format
- Add comprehensive JSON schema documentation
- Add required fields rules for all action types
- +36 lines (improved contract clarity)

## Action Schema Migration

All prompts now use unified action naming:
-  open_long / open_short (was: buy_to_enter / sell_to_enter)
-  close_long / close_short (was: close)
-  update_stop_loss / update_take_profit (new)
-  partial_close (new, nof1 only)
-  hold / wait (unchanged)

## Confidence Scale Migration

-  Changed from 0-1 float to 0-100 integer across all prompts
-  Opening threshold: adaptive=85, nof1=75, default=75
-  Prevents overtrading through strict quality control

## Risk-Reward Standardization

-  Minimum RR ratio: 1:3 across all prompts
-  Replaces previous 1:2 requirement in nof1.txt

## Breaking Changes

- Backend must support new action names
- Confidence field now expects integer 0-100 (not float 0-1)
- partial_close action available in nof1.txt only

## Prompt Positioning

- **adaptive.txt**: Strict strategy (conf≥85, RR≥1:3, no partial exits)
- **nof1.txt**: English framework (conf≥75, RR≥1:3, supports partial_close)
- **default.txt**: Balanced CN strategy (conf≥75, RR≥1:3)

Related: feature/partial-close-dynamic-tpsl
2025-11-03 14:52:31 +08:00
SkywalkerJi
4250c11ddf Supports custom system prompts and custom models. 2025-11-01 19:45:54 +08:00