loop-benchmarking

commit 23bc276e52ad4b72483d00e988f165fe956483fb
parent 507ce236a8d395f65614eb65e9b10ab32c6438d2
Author: Brian Graham <brian@buildingbetterteams.de>
Date:   Tue,  7 Apr 2026 13:56:36 +0200

Increase gameplay bot timeout to 300s (was 180s)

Falling piece detector needs more time to try multiple start triggers.
Playwright timeout 120s -> 240s, harness timeout 180s -> 300s.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

Diffstat:
M
harness/run.py
 | 
4
++--
M
tasks/tetris/eval/playwright.config.ts
 | 
2
+-

2 files changed, 3 insertions(+), 3 deletions(-)
diff --git a/harness/run.py b/harness/run.py
@@ -446,7 +446,7 @@ def evaluate(task_dir: Path, workspace: Path, cell: dict, run_dir: Path):
                     start_new_session=True,
                 )
                 try:
-                    stdout, stderr = bot_proc.communicate(timeout=180)
+                    stdout, stderr = bot_proc.communicate(timeout=300)
                 except subprocess.TimeoutExpired:
                     # Kill entire process group (playwright + child serve processes)
                     try:
@@ -458,7 +458,7 @@ def evaluate(task_dir: Path, workspace: Path, cell: dict, run_dir: Path):
                     results["gameplay_bot"] = {
                         "pass": False,
                         "score": 0,
-                        "error": "Gameplay bot timed out after 180 seconds",
+                        "error": "Gameplay bot timed out after 300 seconds",
                     }
                 else:
                     if report_path.exists():
diff --git a/tasks/tetris/eval/playwright.config.ts b/tasks/tetris/eval/playwright.config.ts
@@ -3,7 +3,7 @@ import { defineConfig } from "@playwright/test";
 export default defineConfig({
   testDir: "./gameplay-bot",
   testMatch: "index.ts",
-  timeout: 120_000, // 2 minutes per test
+  timeout: 240_000, // 4 minutes per test
   retries: 0,
   workers: 1, // sequential -- only one game at a time
   reporter: [["list"]],