Clarify dynamic volatility context in Telegram signals

[Pigbibi]

Summary

• emit SOXL volatility delever reasons with an explicit effective threshold detail
• include dynamic percentile/lookback/floor-cap/sample context when rolling thresholds are active
• keep the legacy trigger code and fallback text for backward compatibility

Verification

• python -m py_compile src/us_equity_strategies/strategies/soxl_soxx_trend_income.py
• python -m pytest tests/test_strategy_plans.py -q -k dynamic_volatility_delever (skipped locally because numpy/pandas are not installed on the VPS)

[chatgpt-codex-connector]

💡 Codex Review

Here are some automated review suggestions for this pull request.

Reviewed commit: 15fa8519e2

ℹ️ About Codex in GitHub

Your team has set up Codex to review pull requests in this repo. Reviews are triggered when you

• Open a pull request for review
• Mark a draft as ready
• Comment "@codex review".

If Codex has suggestions, it will comment; otherwise it will react with 👍.

Codex can also answer questions or update the PR. Try commenting "@codex address that feedback".

[chatgpt-codex-connector]

Use the fixed volatility-delever reason key for fixed mode

When callers leave blend_gate_volatility_delever_threshold_mode at its default fixed, this still emits the new blend_gate_reason_volatility_delever_dynamic reason key. With the repo's default translator or any existing catalog that only knows the previous fixed reason key, the Telegram/diagnostic reason is mislabeled as dynamic even though the threshold detail says it is fixed; choose the dynamic key only for rolling-percentile mode, or keep a generic/fixed key for the fixed path.

Useful? React with 👍 / 👎.