diff --git a/agent.md b/agent.md
index 34741d3..6500822 100644
--- a/agent.md
+++ b/agent.md
@@ -69,6 +69,7 @@ This project replaces the Excel/VBA workflow named `Catalog maker - 20` with a N
 - Use Playwright for all supplier/manufacturer website scraping and browser page inspection.
 - Do not implement new scraping with raw `fetch`, regex-only HTML parsing, Selenium or direct HTTP shortcuts.
 - Scrapers must use controlled browser navigation, selectors, explicit waits and bounded request counts.
+- The configured browser engine for a source is authoritative. If a source says `firefox`, launch Firefox or fail loudly; do not silently fall back to Chromium, Edge or another browser.
 - Keep scraping slow and observable, preserve source URL/status information, and handle blocked pages or missing selectors as explicit errors.
 - Supplier data remains a local draft until the user explicitly confirms an Apply / Save action.
 
diff --git a/src/services/browser-adapter.ts b/src/services/browser-adapter.ts
index f79e21b..983580f 100644
--- a/src/services/browser-adapter.ts
+++ b/src/services/browser-adapter.ts
@@ -58,13 +58,7 @@ function launchBrowser(engine, headless) {
     ...(executablePath ? { executablePath } : {}),
   };
 
-  return browserType.launch(options).catch((error) => {
-    if (normalizedEngine !== "firefox") throw error;
-
-    const chromiumPath = resolveSystemBrowser("chromium");
-    if (!chromiumPath) throw error;
-    return chromium.launch({ headless, timeout: 10_000, executablePath: chromiumPath });
-  });
+  return browserType.launch(options);
 }
 
 function resolveSystemBrowser(engine) {