Summary of V208 Enhancements (currently running tests, had a few parsing issues - upload soon) Attachments: End_To_End_Advanced_ML_Trading_Framework_PRO_V208_Linux.py.txt (just remove the .txt) I have version 2.09 ready to test after I post the ...

Experimental MT5 EA using Gemini Flash API - GeminiCommanderEA_v1

What the updated will do and (im)prove EXTRACT RUN LOG: 2025-06-16 21:16:26,748 - INFO - PyTorch and PyG loaded successfully. GNN module is available. 2025-06-16 21:16:26,759 - INFO - Successfully loaded and verified dynamic playbook from ...

Experimental MT5 EA using Gemini Flash API - GeminiCommanderEA_v1

Small Update to help find strategies quicker... To help the AI learn I have made changes to the feature engineer and playbook. Reason why? The AI needs to first find some strategies to work then build upon these ideas with more advanced features ...

Experimental MT5 EA using Gemini Flash API - GeminiCommanderEA_v1

Version 2.07 (V207) For those who don't understand the script, it's not just a backtester. The script develops its own strategies using Gemini Flash 2.0, 100% hands off the steering wheel. There's a few things to change if you're not using the same ...

Experimental MT5 EA using Gemini Flash API - GeminiCommanderEA_v1

Can you please provide a bit more detail about the issue?

Experimental MT5 EA using Gemini Flash API - GeminiCommanderEA_v1

For this (and how this has developed so far) running python and hooking into the MT4/MT5 platform will be required. Initially I just wanted to develop a python script that generates strategies, which is does (Version 207) but I unfortunately have ...

Experimental MT5 EA using Gemini Flash API - GeminiCommanderEA_v1

What next? (sorry if there's emojis, they aren't. It's actually code) The next step, integrating these AI-found strategies into a fully autonomous MQL5 EA managed by Gemini, is an advanced but achievable goal. Here is a comprehensive playbook ...

Experimental MT5 EA using Gemini Flash API - GeminiCommanderEA_v1

End_To_End_Advanced_ML_Trading_Framework_PRO_V185_API_Fallback.py I know I said a few versions ago I wasn't going to add any more major updates however ensuring that at least two features that most people use are added and working is where I will ...

Experimental MT5 EA using Gemini Flash API - GeminiCommanderEA_v1

Google Colab Notebook Version 1.84 It seems that a few people had trouble getting the script to work so my only suggestion is to run the script in Colab. Remove the .txt extension In My Drive create a folder called TradingData In the TradingData ...

Experimental MT5 EA using Gemini Flash API - GeminiCommanderEA_v1

V1.83 UPDATE Model Quality Gate (The Hacker Model) Total Net Profit: $ 3,881,122.30 (3881.12%) (I have version 1.84 that fixes this but currently testing) The good thing about using AI is that you can develop your ideas very quickly. The bad thing ...

Experimental MT5 EA using Gemini Flash API - GeminiCommanderEA_v1

Analysis of the Run Log V170 End_To_End_Advanced_ML_Trading_Framework_PRO_V170_Empty_Features_FIX.log The log shows the framework is operating as designed, but it also reveals a clear pattern in the AI's decision-making that is worth discussing. ...

Experimental MT5 EA using Gemini Flash API - GeminiCommanderEA_v1

So after a few more versions... Tested V1.70 and Untested V1.71 (See below changes made since V1.65 - can't believe I have 170 different versions already) I am currently running V1.70 and set the MAX = 3 (under the Main Function and set to 1 as the ...

Experimental MT5 EA using Gemini Flash API - GeminiCommanderEA_v1

UNTESTED UPDATE V 1.65 Rename the script to whatever you want and change the .txt to .py # End_To_End_Advanced_ML_Trading_Framework_PRO_V165_API_Retry_Logic.py # # V165 UPDATE (API Retry Logic): # 1. IMPLEMENTED - Added a robust retry mechanism for ...

Experimental MT5 EA using Gemini Flash API - GeminiCommanderEA_v1

Other improvements in the next update are shown below in the output. The AI intervention is analysed during the trials and not after each compete run (of the script): 2025-06-11 23:34:21,511 - WARNING - ! STRATEGIC INTERVENTION !: Current strategy ...

Experimental MT5 EA using Gemini Flash API - GeminiCommanderEA_v1

What to expect in the next update, including the fixes mentioned previously. I have added in GNN. There is a pytorch check at the start, see example output. Since now I created nicknames for the strategies because the full names once hybrids were ...

Experimental MT5 EA using Gemini Flash API - GeminiCommanderEA_v1

Make as many changes and modifications to the script as you want and I am happy to see it being developed. It may or may not suit everyone as I am only focusing on 4 currency pairs, other assets etc will require different strategies and ways to ...

Experimental MT5 EA using Gemini Flash API - GeminiCommanderEA_v1

One last note (I'll update the script later). Summary of Flaws Based On Some Recent Results: Unrealistic Compounding: The position sizing model doesn't account for real-world market limitations and scales to absurd levels. Perverse AI Learning: The ...

Experimental MT5 EA using Gemini Flash API - GeminiCommanderEA_v1

Another User Request Fix Problem: I don't want to use the timeframes you've hardcoded into the script and I don't want to enter in each of my csv files one at a time. NOTE: The csv file naming convention rules apply. I've updated the script to be ...

Experimental MT5 EA using Gemini Flash API - GeminiCommanderEA_v1

User Requested FIX Problem Identified: The start date for the testing (cycles) was hardcoded to 2024-01-01 and users would have a problem if this date was not part of their own CSV set. The number of cycles is calculated based on three parameters ...

Experimental MT5 EA using Gemini Flash API - GeminiCommanderEA_v1

The moment you change one thing... Script Update: V1.32 + the requirements below This version introduces a critical new layer of defense: AI Parameter Sanitization. It also incorporates the fixes from the previous version which you hadn't run yet. ...

Experimental MT5 EA using Gemini Flash API - GeminiCommanderEA_v1