## 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.