-
Notifications
You must be signed in to change notification settings - Fork 140
Add evals for the bindings server and a hyperdrive binding #117
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.
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
Conversation
input: 'List all my Cloudflare accounts.', | ||
expected: 'The accounts_list tool should be called to retrieve the list of accounts.', | ||
}, | ||
{ |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
I would split these into separate describe eval scripts. Like
describeEval("List accounts", ...)
describeEval("Set account", ...)
Then you don't need to have the if statements below, because to me that feels like a bit of a code smell in tests.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
LGTM
const client = await initializeClient(/* Pass necessary mocks/config */) | ||
const { promptOutput, toolCalls, fullResult } = await runTask(client, model, input) | ||
|
||
if (input.includes('List all my Cloudflare KV Namespaces')) { |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Same here, I'd split this into a separate describe eval.
This PR adds tools for Hyperdrive and introduces evals to the workers-bindings MCP server