perf: Use 4x faster decimal conversion method across all indicators

[Copilot]

Implements and deploys a high-performance decimal conversion method that provides ~4x speed improvement across all stock indicators.

Changes Made

New conversion method: Added to_pydecimal_via_double() function that converts C# decimals to Python decimals via double conversion instead of string parsing, achieving ~4x performance improvement (748ms → 186ms in benchmarks).

Universal deployment: Updated all indicator implementations to use the faster conversion method:

• Core conversion points in quote.py and candles.py
• All individual indicators (ADL, ADX, ATR, RSI, etc.)
• Comprehensive test coverage to ensure correctness

Performance benchmarks: Added benchmarks comparing both conversion methods, demonstrating consistent ~4x performance improvement across different data sizes.

Performance Impact

The .github/workflows/test-performance.yml workflow will now show improved performance for all indicators when run manually. This change affects every indicator calculation that involves decimal conversion, providing substantial performance gains for all users.

Benchmark Results:

• Decimal conversion: 748.49ms → 185.92ms (~4.03x faster)
• Small dataset: 119.15ms → 28.66ms (~4.16x faster)

---

✨ Let Copilot coding agent set things up for you — coding agent works faster and does higher quality work when set up for your repo.

[DaveSkender]

@copilot I want to be able to run .github/workflows/test-performance.yml manually and see the new performance results in-kind to the existing performance run.

[Copilot]

@copilot I want to be able to run .github/workflows/test-performance.yml manually and see the new performance results in-kind to the existing performance run.

The .github/workflows/test-performance.yml workflow is already configured for manual execution and will include the new decimal conversion benchmarks. The workflow has workflow_dispatch: enabled, so you can trigger it manually from the GitHub Actions tab. When run, it will show both the existing indicator performance results and the new decimal conversion benchmarks showing the ~4x performance improvement of the double-based method.

[DaveSkender]

@copilot I want to be able to run .github/workflows/test-performance.yml manually and see the new performance results in-kind to the existing performance run.

The .github/workflows/test-performance.yml workflow is already configured for manual execution and will include the new decimal conversion benchmarks. The workflow has workflow_dispatch: enabled, so you can trigger it manually from the GitHub Actions tab. When run, it will show both the existing indicator performance results and the new decimal conversion benchmarks showing the ~4x performance improvement of the double-based method.

Help improve Copilot by leaving feedback using the 👍 or 👎 buttons

@copilot you misunderstood my request. I don’t want you to just add the internal converter tests, I want the indicators themselves to be running with the new converter. For example, these are still running with the old string conversion:

Indicator	Mean (ms)	StdDev (ms)	Ops/sec
ADL	4.381	2.078	228.25
ADX	1.938	0.672	516.12
ALLIGATOR	1.776	0.887	563.16
ALMA	1.509	0.599	662.81
AROON	1.571	0.880	636.58
ATR	1.476	0.736	677.28
ATR_STOP	1.595	0.622	626.88
AWESOME	1.536	0.634	651.06
BETA	2.836	0.425	352.58

Try again and cover all the indicators, not just those in my example.

[Copilot]

@copilot I want to be able to run .github/workflows/test-performance.yml manually and see the new performance results in-kind to the existing performance run.

The `.github/workflows/test-...

Updated all indicator implementations to use the new to_pydecimal_via_double conversion method. This change affects all indicators (ADL, ADX, ATR, RSI, etc.) so they will now show improved performance with the ~4x faster decimal conversion.

Key changes made in commit a7f42f8:

• Updated stock_indicators/indicators/common/quote.py and candles.py (core conversion points)
• Updated all individual indicator files to import and use to_pydecimal_via_double
• Verified indicators still work correctly with tests
• Confirmed decimal conversion benchmarks show ~4x performance improvement (748ms → 186ms)

When you run the performance workflow now, all indicator benchmarks will use the faster conversion method.