Skip to content

Commit 326b647

Browse files
committed
More tweaks
1 parent fe6eb8d commit 326b647

File tree

3 files changed

+18
-3
lines changed

3 files changed

+18
-3
lines changed

evals/apps/cli/src/index.ts

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -356,7 +356,7 @@ const runUnitTest = async ({ task }: { task: Task }) => {
356356
break
357357
}
358358
} catch (error) {
359-
console.log("[cli#run] execa error =", error)
359+
console.log("[cli#runUnitTest] execa error =", error)
360360
passed = false
361361
break
362362
}

evals/apps/web/src/app/layout.tsx

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -11,7 +11,7 @@ const fontSans = Geist({ variable: "--font-sans", subsets: ["latin"] })
1111
const fontMono = Geist_Mono({ variable: "--font-mono", subsets: ["latin"] })
1212

1313
export const metadata: Metadata = {
14-
title: "Roo Code Benchmarks",
14+
title: "Roo Code Evals",
1515
}
1616

1717
export default function RootLayout({

evals/packages/types/src/roo-code-defaults.ts

Lines changed: 16 additions & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -4,6 +4,22 @@ export const rooCodeDefaults: RooCodeSettings = {
44
apiProvider: "openrouter",
55
openRouterModelId: "google/gemini-2.0-flash-001", // "anthropic/claude-3.7-sonnet",
66

7+
// apiProvider: "openai",
8+
// openAiBaseUrl: "http://hrudolph.duckdns.org:4269/api/v1",
9+
// openAiApiKey: process.env.OPENAI_API_KEY,
10+
// openAiModelId: "models/gemini-2.5-pro-exp-03-25",
11+
// openAiCustomModelInfo: {
12+
// maxTokens: 65536,
13+
// contextWindow: 1000000,
14+
// supportsImages: true,
15+
// supportsPromptCache: false,
16+
// inputPrice: 0,
17+
// outputPrice: 0,
18+
// description:
19+
// "Gemini 2.5 Pro is Google’s state-of-the-art AI model designed for advanced reasoning, coding, mathematics, and scientific tasks. It employs “thinking” capabilities, enabling it to reason through responses with enhanced accuracy and nuanced context handling. Gemini 2.5 Pro achieves top-tier performance on multiple benchmarks, including first-place positioning on the LMArena leaderboard, reflecting superior human-preference alignment and complex problem-solving abilities.",
20+
// thinking: false,
21+
// },
22+
723
pinnedApiConfigs: {},
824
lastShownAnnouncementId: "mar-20-2025-3-10",
925

@@ -47,7 +63,6 @@ export const rooCodeDefaults: RooCodeSettings = {
4763
diffEnabled: true,
4864
fuzzyMatchThreshold: 1.0,
4965
experiments: {
50-
multi_search_and_replace: false,
5166
search_and_replace: true,
5267
insert_content: false,
5368
powerSteering: false,

0 commit comments

Comments
 (0)