V0.11.0 alpha2 fix codex #61

2026-04-20T23:28:39+02:00

umpire274 commented

2026-04-20 23:28:39 +02:00

(Migrated from github.com)

No description provided.

chatgpt-codex-connector[bot] (Migrated from github.com) reviewed

2026-04-20 23:35:12 +02:00

chatgpt-codex-connector[bot] (Migrated from github.com) left a comment

💡 Codex Review

Here are some automated review suggestions for this pull request.

Reviewed commit: b87fca919b

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".

### 💡 Codex Review Here are some automated review suggestions for this pull request. **Reviewed commit:** `b87fca919b` <details> <summary>ℹ️ About Codex in GitHub</summary> [Your team has set up Codex to review pull requests in this repo](https://chatgpt.com/codex/cloud/settings/general). 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". </details>

src/engine/play_ball.rs

					
				@ -73,7 +87,13 @@ pub fn run_play_ball_engine(

				                    if !pas.is_empty() {

				                        has_events = true;

Exclude hit and walk rows from composite replay pass

run_play_ball_engine now classifies every non-"steal" runner_movements row as composite_movements, and replay_plate_appearances_and_log applies all of them through apply_composite_state. That unintentionally re-applies normal PA movements ("walk", "hit_auto", "hit_override") that were already applied by apply_plate_appearance_row, so resumed games can double-count scoring movements (especially rows ending at HOME) and corrupt replayed state.

Useful? React with 👍 / 👎.

**![P1 Badge](https://img.shields.io/badge/P1-orange?style=flat) Exclude hit and walk rows from composite replay pass** `run_play_ball_engine` now classifies every non-`"steal"` `runner_movements` row as `composite_movements`, and `replay_plate_appearances_and_log` applies all of them through `apply_composite_state`. That unintentionally re-applies normal PA movements (`"walk"`, `"hit_auto"`, `"hit_override"`) that were already applied by `apply_plate_appearance_row`, so resumed games can double-count scoring movements (especially rows ending at `HOME`) and corrupt replayed state. Useful? React with 👍 / 👎.

src/engine/play_ball.rs

Increment inning buckets for HOME composite movements

When replaying composite rows that end at HOME, this branch increments only state.score.away/home and skips away_innings/home_innings. That makes resumed state inconsistent with live scoring (add_runs_to_score) and can show mismatched totals vs inning-by-inning lines in the TUI after FC/composite scoring plays.

Useful? React with 👍 / 👎.

**![P2 Badge](https://img.shields.io/badge/P2-yellow?style=flat) Increment inning buckets for HOME composite movements** When replaying composite rows that end at `HOME`, this branch increments only `state.score.away/home` and skips `away_innings/home_innings`. That makes resumed state inconsistent with live scoring (`add_runs_to_score`) and can show mismatched totals vs inning-by-inning lines in the TUI after FC/composite scoring plays. Useful? React with 👍 / 👎.

Sign in to join this conversation.

No reviewers