Skip to content

chore(evals): unblock ToolPredictionScorer #962

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Draft
JoshFerge wants to merge 1 commit into
base: main
Choose a base branch
from
+7 −7
Draft

chore(evals): unblock ToolPredictionScorer #962

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
14 changes: 7 additions & 7 deletions packages/mcp-server-evals/src/evals/utils/toolPredictionScorer.ts
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -19,12 +19,7 @@ async function getAvailableTools(): Promise<string[]> {
// Use pnpm exec to run the binary from the workspace
const transport = new Experimental_StdioMCPTransport({
command: "pnpm",
args: [
"exec",
"sentry-mcp",
"--access-token=mocked-access-token",
"--all-scopes",
Copy link
Copy Markdown
Member

@dcramer dcramer May 13, 2026

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

im actually surprised this wouldnt break something

],
args: ["exec", "sentry-mcp", "--access-token=mocked-access-token"],
env: {
...process.env,
SENTRY_ACCESS_TOKEN: "mocked-access-token",
Expand Down Expand Up @@ -73,7 +68,12 @@ const predictionSchema = z.object({
.array(
z.object({
name: z.string(),
arguments: z.record(z.any()).optional().default({}),
// Serialize arguments as a JSON string so the schema stays compatible
// with OpenAI's strict response_format (z.record(z.any()) emits
// `additionalProperties` without a `type`, which the API rejects).
argumentsJson: z
.string()
.describe("JSON-encoded tool arguments, e.g. '{}' for none."),
}),
)
.describe("What tools the AI would likely call"),
Expand Down
Loading