cyb50-quant/research/dragon/v2/openspec/changes/followthrough-mid-exit-shadow-probe/acceptance-summary.md

Acceptance Summary

Delivered

• Added entry-specific exit helper:
• dragon_glued_followthrough_exit.py
• Added default-off config gates in:
• dragon_strategy_config.py
• Added new shadow branch config:
• alpha_first_glued_followthrough_mid_exit_probe_config()
• Wired branch-gated hold into:
• dragon_strategy.py
• Exposed branch in:
• dragon_daily_signal_pipeline.py
• Added review/report artifacts:
• dragon_followthrough_mid_exit_review.py
• dragon_followthrough_mid_exit_branch_summary.csv
• dragon_followthrough_mid_exit_trade_details.csv
• dragon_followthrough_mid_exit_trade_diff.csv
• dragon_followthrough_mid_exit_review.md
• Added regression test:
• tests/test_followthrough_mid_exit_probe.py

Validation

• py -3 -m py_compile dragon_glued_followthrough_exit.py dragon_followthrough_mid_exit_review.py tests/test_followthrough_mid_exit_probe.py dragon_daily_signal_pipeline.py
• py -3 -m unittest tests.test_followthrough_mid_exit_probe -v
• py -3 dragon_followthrough_mid_exit_review.py
• py -3 -m unittest discover -s tests -v
• py -3 dragon_daily_signal_pipeline.py
• py -3 dragon_forward_observation_pipeline.py

Final validation status:

• full suite 26 tests passed
• daily pipeline smoke passed
• forward observation pipeline smoke passed

Key Historical Fixture

• branch: alpha_first_glued_followthrough_mid_exit_probe
• trade count in release window: 91
• followthrough reentry trade:
• buy date 2020-12-01
• buy reason glued_followthrough_reentry_buy:confirmed_mid_zone_very_weak_b1
• sell date 2021-02-19
• sell reason high_regime_confirmed_exit:kdj_sell
• holding days 80
• return 26.648684%

Comparative Findings

• original mid probe:
• reentry path 2020-12-01 -> 2020-12-09
• same_close -0.24%
• next_open -0.50%

• sell knife_take_profit_2_glued

• mid exit probe:

• reentry path 2020-12-01 -> 2021-02-19

• same_close +26.65%

• next_open +26.51%

• sell high_regime_confirmed_exit:kdj_sell

• branch-level metrics:

• same_close compounded return:

• base 1424.12%

• mid_probe 1420.41%

• mid_exit_probe 1460.02%

• next_open compounded return:

• base 1295.54%

• mid_probe 1288.52%

• mid_exit_probe 1332.91%

Operational Reading

• RC1 default path remains unchanged.
• The new exit treatment is promising enough to keep as a shadow observation branch.
• Evidence is still only one repaired-trend path, so promotion is not justified yet.