0d3cb498a3
CI / Shell Format Check (push) Has been cancelled
CI / Check Ruby (3.4) (push) Has been cancelled
CI / CI Config (push) Has been cancelled
CI / Test on Node ${{ matrix.node }} and ${{ matrix.os }}${{ matrix.shard && format(' (shard {0}/3)', matrix.shard) || '' }} (push) Has been cancelled
CI / Build on Node ${{ matrix.node }} (push) Has been cancelled
CI / Style Check (push) Has been cancelled
CI / Generate Assets (push) Has been cancelled
CI / Check Python (3.14) (push) Has been cancelled
CI / Check Python (3.9) (push) Has been cancelled
CI / Build Docs (push) Has been cancelled
CI / Code Scan Action (push) Has been cancelled
CI / Site tests (push) Has been cancelled
CI / webui tests (push) Has been cancelled
CI / Run Integration Tests (push) Has been cancelled
CI / Run Smoke Tests (push) Has been cancelled
CI / Go Tests (push) Has been cancelled
CI / Share Test (push) Has been cancelled
CI / Redteam (Production API) (push) Has been cancelled
CI / Redteam (Staging API) (push) Has been cancelled
CI / GitHub Actions Lint (push) Has been cancelled
CI / Check Ruby (3.0) (push) Has been cancelled
release-please / release-please (push) Has been cancelled
release-please / build (push) Has been cancelled
release-please / publish-npm (push) Has been cancelled
release-please / publish-npm-backfill (push) Has been cancelled
release-please / docker (push) Has been cancelled
release-please / publish-code-scan-action (push) Has been cancelled
release-please / attest-code-scan-action (push) Has been cancelled
Deploy local.promptfoo.app / Deploy to Cloudflare Pages (push) Has been cancelled
Test and Publish Multi-arch Docker Image / test (push) Has been cancelled
Test and Publish Multi-arch Docker Image / build-docker-and-push-digests (map[digest-suffix:linux-amd64 platform:linux/amd64 runner:ubuntu-latest]) (push) Has been cancelled
Test and Publish Multi-arch Docker Image / build-docker-and-push-digests (map[digest-suffix:linux-arm64 platform:linux/arm64 runner:ubuntu-24.04-arm]) (push) Has been cancelled
Test and Publish Multi-arch Docker Image / merge-docker-digests (push) Has been cancelled
Test and Publish Multi-arch Docker Image / Attest Multi-arch Image (push) Has been cancelled
Validate Renovate Config / Validate Renovate Configuration (push) Has been cancelled
105 lines
3.3 KiB
YAML
105 lines
3.3 KiB
YAML
# yaml-language-server: $schema=https://promptfoo.dev/config-schema.json
|
|
description: 'Mistral tool routing and output shape QA'
|
|
|
|
prompts:
|
|
- '{{prompt}}'
|
|
|
|
providers:
|
|
- id: mistral:mistral-large-latest
|
|
label: tool-any-inline
|
|
config:
|
|
temperature: 0
|
|
max_tokens: 128
|
|
tool_choice: any
|
|
parallel_tool_calls: false
|
|
tools:
|
|
- type: function
|
|
function:
|
|
name: calculate
|
|
description: Perform basic mathematical calculations
|
|
parameters:
|
|
type: object
|
|
properties:
|
|
operation:
|
|
type: string
|
|
enum: ['add', 'subtract', 'multiply', 'divide']
|
|
a:
|
|
type: number
|
|
b:
|
|
type: number
|
|
required: ['operation', 'a', 'b']
|
|
- id: mistral:mistral-large-latest
|
|
label: tool-any-file
|
|
config:
|
|
temperature: 0
|
|
max_tokens: 128
|
|
tool_choice: any
|
|
parallel_tool_calls: false
|
|
tools: 'file://tools/calculate.yaml'
|
|
- id: mistral:mistral-large-latest
|
|
label: tool-auto-file
|
|
config:
|
|
temperature: 0
|
|
max_tokens: 128
|
|
tool_choice: auto
|
|
parallel_tool_calls: false
|
|
tools: 'file://tools/calculate.yaml'
|
|
- id: mistral:mistral-large-latest
|
|
label: plain-chat
|
|
config:
|
|
temperature: 0
|
|
max_tokens: 64
|
|
|
|
tests:
|
|
- description: Tool-only response with inline tools
|
|
providers:
|
|
- tool-any-inline
|
|
vars:
|
|
prompt: 'You must call the calculate tool for this task. Do not answer in natural language. Compute 15 multiplied by 8.'
|
|
assert:
|
|
- type: is-valid-openai-tools-call
|
|
- type: javascript
|
|
value: output[0].function.name === 'calculate'
|
|
- type: javascript
|
|
value: JSON.parse(output[0].function.arguments).operation === 'multiply'
|
|
|
|
- description: Tool-only response with file-based tools
|
|
providers:
|
|
- tool-any-file
|
|
vars:
|
|
prompt: 'Use the calculate tool to divide 100 by 4. Return only the tool call.'
|
|
assert:
|
|
- type: is-valid-openai-tools-call
|
|
- type: javascript
|
|
value: output[0].function.name === 'calculate'
|
|
- type: javascript
|
|
value: JSON.parse(output[0].function.arguments).operation === 'divide'
|
|
|
|
- description: Mixed content and tool calls
|
|
providers:
|
|
- tool-auto-file
|
|
vars:
|
|
prompt: 'Before calling the calculate tool, include the exact sentence "Let me calculate that." in your assistant message. In the same assistant message, call the calculate tool for 15 multiplied by 8. Do not provide the final numeric answer.'
|
|
assert:
|
|
- type: javascript
|
|
value: |
|
|
return (
|
|
output &&
|
|
typeof output === 'object' &&
|
|
!Array.isArray(output) &&
|
|
typeof output.content === 'string' &&
|
|
output.content.includes('Let me calculate that.') &&
|
|
Array.isArray(output.tool_calls) &&
|
|
output.tool_calls.length > 0 &&
|
|
output.tool_calls[0].function?.name === 'calculate'
|
|
);
|
|
|
|
- description: Plain chat still returns a string
|
|
providers:
|
|
- plain-chat
|
|
vars:
|
|
prompt: 'Respond with the single word: ok'
|
|
assert:
|
|
- type: javascript
|
|
value: "typeof output === 'string' && output.trim().toLowerCase() === 'ok'"
|