Files
windmill/ai_evals/cases/cli.yaml
2026-04-13 14:05:46 +02:00

67 lines
3.1 KiB
YAML

- id: bun-hello-script
prompt: |-
Create a Windmill Bun script at `f/evals/hello.ts`.
It should take a `name` input and return a greeting object like `{ greeting: "Hello, Alice!" }`.
expected: ai_evals/fixtures/cli/expected/bun-hello-script
judgeChecklist:
- creates the requested Bun script at f/evals/hello.ts
- takes a name input
- returns an object containing the greeting
- id: bun-hello-flow
prompt: |-
Create a Windmill flow at `f/evals/hello__flow`.
It should take a `name` input and return a greeting object like `{ greeting: "Hello, Alice!" }`.
Put the step code in `hello.ts`.
expected: ai_evals/fixtures/cli/expected/bun-hello-flow
judgeChecklist:
- creates the requested flow folder with flow.yaml and hello.ts
- wires the name input into the flow step
- returns the greeting object
- id: python-add-numbers-script
prompt: |-
Add a Windmill Python script at `f/evals/add_numbers.py`.
It should take `a` and `b` as inputs and return `{ "total": a + b }`.
expected: ai_evals/fixtures/cli/expected/python-add-numbers-script
judgeChecklist:
- creates the requested Python script at f/evals/add_numbers.py
- takes `a` and `b` as inputs
- returns an object with total equal to a plus b
- id: bun-hello-script-uppercase
prompt: |-
Update `f/evals/hello.ts` so it accepts an optional `uppercase` boolean.
Keep returning `{ greeting: ... }`, but when `uppercase` is true the greeting should be uppercased before returning it.
initial: ai_evals/fixtures/cli/initial/bun-hello-script-uppercase
expected: ai_evals/fixtures/cli/expected/bun-hello-script-uppercase
judgeChecklist:
- updates the existing hello.ts file rather than creating a new script
- accepts an optional uppercase boolean input
- keeps returning an object with greeting
- uppercases the greeting when uppercase is true
- id: bun-hello-flow-punctuation
prompt: |-
Update the existing flow in `f/evals/hello__flow` so it also accepts an optional `punctuation` input.
The greeting should use that punctuation and default to `!` when it is missing.
initial: ai_evals/fixtures/cli/initial/bun-hello-flow-punctuation
expected: ai_evals/fixtures/cli/expected/bun-hello-flow-punctuation
judgeChecklist:
- updates the existing hello flow instead of creating a new one
- adds an optional punctuation input to the flow
- updates the step code so the returned greeting uses punctuation
- defaults punctuation to an exclamation mark when omitted
- id: flow-reuse-existing-script
prompt: |-
There is already a reusable greeting script at `f/lib/format_greeting.ts`.
Create a flow at `f/evals/reuse_greeting__flow` that takes a `name` input and reuses that existing script instead of duplicating the logic inline.
initial: ai_evals/fixtures/cli/initial/flow-reuse-existing-script
expected: ai_evals/fixtures/cli/expected/flow-reuse-existing-script
judgeChecklist:
- creates the requested flow at f/evals/reuse_greeting__flow
- reuses the existing script from f/lib by path
- does not duplicate the greeting logic in a new inline script
- wires the name input into the reused script