Stabilize tests. (#20095)

evals/frugalReads.eval.ts

@@ -78,22 +78,23 @@ describe('Frugal reads eval', () => {
       ).toBe(true);
 
       let totalLinesRead = 0;
-      const readRanges: { offset: number; limit: number }[] = [];
+      const readRanges: { start_line: number; end_line: number }[] = [];
 
       for (const call of targetFileReads) {
         const args = JSON.parse(call.toolRequest.args);
 
         expect(
-          args.limit,
+          args.end_line,
-          'Agent read the entire file (missing limit) instead of using ranged read',
+          'Agent read the entire file (missing end_line) instead of using ranged read',
         ).toBeDefined();
 
-        const limit = args.limit;
+        const end_line = args.end_line;
-        const offset = args.offset ?? 0;
+        const start_line = args.start_line ?? 1;
-        totalLinesRead += limit;
+        const linesRead = end_line - start_line + 1;
-        readRanges.push({ offset, limit });
+        totalLinesRead += linesRead;
+        readRanges.push({ start_line, end_line });
 
-        expect(args.limit, 'Agent read too many lines at once').toBeLessThan(
+        expect(linesRead, 'Agent read too many lines at once').toBeLessThan(
           1001,
         );
       }
@@ -108,7 +109,7 @@ describe('Frugal reads eval', () => {
       const errorLines = [500, 510, 520];
       for (const line of errorLines) {
         const covered = readRanges.some(
-          (range) => line >= range.offset && line < range.offset + range.limit,
+          (range) => line >= range.start_line && line <= range.end_line,
         );
         expect(covered, `Agent should have read around line ${line}`).toBe(
           true,
@@ -191,8 +192,8 @@ describe('Frugal reads eval', () => {
       for (const call of targetFileReads) {
         const args = JSON.parse(call.toolRequest.args);
         expect(
-          args.limit,
+          args.end_line,
-          'Agent should have used ranged read (limit) to save tokens',
+          'Agent should have used ranged read (end_line) to save tokens',
         ).toBeDefined();
       }
     },
@@ -253,7 +254,7 @@ describe('Frugal reads eval', () => {
       // and just read the whole file to be efficient with tool calls.
       const readEntireFile = targetFileReads.some((call) => {
         const args = JSON.parse(call.toolRequest.args);
-        return args.limit === undefined;
+        return args.end_line === undefined;
       });
 
       expect(

evals/frugalSearch.eval.ts

@@ -68,7 +68,7 @@ describe('Frugal Search', () => {
         const args = getParams(call);
         return (
           args.file_path === 'src/legacy_processor.ts' &&
-          (args.limit === undefined || args.limit === null)
+          (args.end_line === undefined || args.end_line === null)
         );
       });
 
@@ -87,7 +87,7 @@ describe('Frugal Search', () => {
         if (
           call.toolRequest.name === 'read_file' &&
           args.file_path === 'src/legacy_processor.ts' &&
-          args.limit !== undefined
+          args.end_line !== undefined
         ) {
           return true;
         }

evals/interactive-hang.eval.ts

@@ -56,7 +56,7 @@ describe('interactive_commands', () => {
       const scaffoldCall = logs.find(
         (l) =>
           l.toolRequest.name === 'run_shell_command' &&
-          /npm (init|create)|npx create-|yarn create|pnpm create/.test(
+          /npm (init|create)|npx (.*)?create-|yarn create|pnpm create/.test(
             l.toolRequest.args,
           ),
       );