chore: import upstream snapshot with attribution

examples/provider-cerebras/README.md

@@ -0,0 +1,109 @@
+# provider-cerebras (Cerebras Example (High-Performance LLM Inference))
+
+This example demonstrates how to use the Cerebras provider with promptfoo to evaluate Cerebras Inference API models, which offer high-performance inference for Llama and other LLM models.
+
+You can run this example with:
+
+```bash
+npx promptfoo@latest init --example provider-cerebras
+cd provider-cerebras
+```
+
+## Prerequisites
+
+### API Key Setup
+
+1. Sign up for an account at [Cerebras AI](https://console.cerebras.ai/)
+2. Navigate to your account settings to generate an API key
+3. Set your Cerebras API key as an environment variable:
+
+```bash
+export CEREBRAS_API_KEY="your-api-key-here"
+```
+
+Alternatively, you can add it to your `.env` file:
+
+```text
+CEREBRAS_API_KEY=your-api-key-here
+```
+
+## Example Configurations
+
+This repository contains three example configurations demonstrating different Cerebras features:
+
+### 1. Basic Model Evaluation (`promptfooconfig.yaml`)
+
+This configuration evaluates two Cerebras models on their ability to explain complex concepts in simple terms.
+
+```bash
+promptfoo eval
+```
+
+**Expected output:** You'll see a comparison of how each model explains concepts from different domains, with metrics on clarity, accuracy, and response time.
+
+### 2. Structured Outputs (`promptfooconfig-structured.yaml`)
+
+The structured output example demonstrates Cerebras's JSON schema enforcement capabilities, ensuring the model returns consistent, structured recipe data with proper types and required fields.
+
+```bash
+promptfoo eval -c promptfooconfig-structured.yaml
+```
+
+**Expected output:** You'll receive structured JSON outputs for different recipes, with consistent fields like cuisine type, difficulty level, ingredients, and cooking instructions - all following the defined schema.
+
+Example output:
+
+```json
+{
+  "name": "Traditional Pasta Carbonara",
+  "cuisine": "Italian",
+  "difficulty": "medium",
+  "prepTime": 15,
+  "cookTime": 20,
+  "ingredients": [
+    { "name": "spaghetti", "amount": "400g" },
+    { "name": "pancetta", "amount": "150g" },
+    { "name": "eggs", "amount": "3 large" },
+    { "name": "parmesan cheese", "amount": "50g" }
+  ],
+  "instructions": [
+    "Bring a large pot of salted water to boil",
+    "Cook spaghetti according to package instructions",
+    "In a separate pan, cook pancetta until crispy",
+    "In a bowl, whisk eggs and grated parmesan cheese",
+    "Drain pasta, reserving some pasta water",
+    "Toss hot pasta with pancetta, then quickly mix in egg mixture",
+    "Add pasta water as needed to create a silky sauce"
+  ]
+}
+```
+
+### 3. Tool Use (`promptfooconfig-tools.yaml`)
+
+The tool use example demonstrates Cerebras's function calling capabilities with a calculator tool that the model can use to solve math problems.
+
+```bash
+promptfoo eval -c promptfooconfig-tools.yaml
+```
+
+**Expected output:** The model will use the calculator tool to solve math problems and provide step-by-step explanations of the solution process. For example, when given "15 × 7", it will calculate 105 and explain multiplication concepts.
+
+## Model Capabilities
+
+Cerebras supports several powerful models:
+
+- `llama-4-scout-17b-16e-instruct` - Llama 4 Scout 17B model with 16 expert MoE (featured in examples)
+- `llama3.1-8b` - Llama 3.1 8B model
+- `llama-3.3-70b` - Llama 3.3 70B model
+- `deepSeek-r1-distill-llama-70B` (private preview)
+
+## Pricing & Usage
+
+Cerebras Inference API offers competitive pricing compared to other inference services. Check the [official pricing page](https://docs.cerebras.ai) for the most current rates. Usage is billed based on input and output tokens.
+
+## Learn More
+
+- [Cerebras Provider Documentation](https://promptfoo.dev/docs/providers/cerebras)
+- [Cerebras API Reference](https://docs.cerebras.ai/)
+- [Cerebras Structured Outputs Guide](https://docs.cerebras.ai/capabilities/structured-outputs/)
+- [Cerebras Tool Use Guide](https://docs.cerebras.ai/capabilities/tool-use/)

examples/provider-cerebras/promptfooconfig-structured.yaml

@@ -0,0 +1,68 @@
+# yaml-language-server: $schema=https://promptfoo.dev/config-schema.json
+description: Schema-enforced JSON recipe generation with Llama 4
+prompts:
+  - file://structured_prompts.txt
+providers:
+  - id: cerebras:llama-4-scout-17b-16e-instruct
+    config:
+      temperature: 0.7
+      max_completion_tokens: 1024
+      response_format:
+        type: 'json_schema'
+        json_schema:
+          name: 'recipe_schema'
+          strict: true
+          schema:
+            type: 'object'
+            properties:
+              name: { 'type': 'string' }
+              cuisine: { 'type': 'string' }
+              difficulty:
+                type: 'string'
+                enum: ['easy', 'medium', 'hard']
+              prepTime: { 'type': 'integer' }
+              cookTime: { 'type': 'integer' }
+              ingredients:
+                type: 'array'
+                items:
+                  type: 'object'
+                  properties:
+                    name: { 'type': 'string' }
+                    amount: { 'type': 'string' }
+                  required: ['name', 'amount']
+              instructions:
+                type: 'array'
+                items: { 'type': 'string' }
+            required: ['name', 'cuisine', 'difficulty', 'ingredients', 'instructions']
+            additionalProperties: false
+tests:
+  - vars:
+      cuisine: Italian
+      dish: Cacio e Pepe
+    assert:
+      - type: json-schema-valid
+        value: |
+          {
+            "type": "object",
+            "required": ["name", "cuisine", "difficulty", "ingredients", "instructions"]
+          }
+  - vars:
+      cuisine: Japanese
+      dish: Okonomiyaki
+    assert:
+      - type: contains-json-property
+        value: ['ingredients', 'instructions']
+      - type: javascript
+        value: |
+          return output.ingredients.length >= 5 ? 'pass' : 'fail: needs at least 5 ingredients'
+  - vars:
+      cuisine: Mexican
+      dish: Chiles en Nogada
+    assert:
+      - type: contains-json-property
+        value: ['difficulty']
+      - type: javascript
+        value: |
+          return output.instructions.length >= 3 ? 'pass' : 'fail: needs detailed instructions'
+outputs:
+  - type: json

examples/provider-cerebras/promptfooconfig-tools.yaml

@@ -0,0 +1,49 @@
+# yaml-language-server: $schema=https://promptfoo.dev/config-schema.json
+description: Function calling with Llama 4 for mathematical problem solving
+prompts:
+  - file://tool_prompts.txt
+providers:
+  - id: cerebras:llama-4-scout-17b-16e-instruct
+    config:
+      temperature: 0.7
+      max_completion_tokens: 1024
+      tools:
+        - type: 'function'
+          function:
+            name: 'calculate'
+            description: 'A calculator that can perform basic arithmetic operations'
+            parameters:
+              type: 'object'
+              properties:
+                expression:
+                  type: 'string'
+                  description: 'The mathematical expression to evaluate'
+              required: ['expression']
+            strict: true
+tests:
+  - vars:
+      problem: '15 × 7'
+      explanation: 'the product of fifteen and seven'
+    assert:
+      - type: contains
+        value: '105'
+      - type: contains-any
+        value: ['multiply', 'multiplication', 'multiplying', 'product']
+  - vars:
+      problem: '(42 × 3) ÷ 6'
+      explanation: 'forty-two times three, divided by six'
+    assert:
+      - type: contains
+        value: '21'
+      - type: contains-any
+        value: ['order of operations', 'PEMDAS', 'parentheses', 'brackets']
+  - vars:
+      problem: '√(144) + 25²'
+      explanation: 'the square root of one hundred forty-four plus twenty-five squared'
+    assert:
+      - type: contains
+        value: '637'
+      - type: contains-any
+        value: ['square root', 'exponent', 'power', 'squared']
+outputs:
+  - type: text

examples/provider-cerebras/promptfooconfig.yaml

@@ -0,0 +1,42 @@
+# yaml-language-server: $schema=https://promptfoo.dev/config-schema.json
+description: Evaluating Llama models for educational concept explanations
+prompts:
+  - file://prompts.txt
+providers:
+  - id: cerebras:llama-4-scout-17b-16e-instruct
+    config:
+      temperature: 0.7
+      max_completion_tokens: 1024
+  - id: cerebras:llama-3.3-70b
+    config:
+      temperature: 0.5
+      max_completion_tokens: 1024
+tests:
+  - vars:
+      topic: quantum computing
+      concept: quantum entanglement
+    assert:
+      - type: contains-any
+        value: ['particles', 'correlation', 'distance', 'spooky action', 'Einstein']
+  - vars:
+      topic: artificial intelligence
+      concept: transformer architecture
+    assert:
+      - type: contains-any
+        value:
+          ['attention mechanism', 'self-attention', 'parallel processing', 'encoder', 'decoder']
+  - vars:
+      topic: astrophysics
+      concept: black hole information paradox
+    assert:
+      - type: contains-any
+        value:
+          [
+            'Hawking radiation',
+            'event horizon',
+            'quantum mechanics',
+            'information loss',
+            'firewall',
+          ]
+outputs:
+  - type: csv

examples/provider-cerebras/prompts.txt

@@ -0,0 +1,5 @@
+You are an expert in {{topic}} with exceptional teaching skills. Your task is to explain the concept of {{concept}} in simple terms that a high school student could understand.
+
+Keep your explanation under 300 words and include 2-3 real-world examples or analogies that make this concept intuitive and memorable. Avoid overly technical jargon, and when you must use specialized terms, define them clearly.
+
+Begin with a captivating introduction that sparks curiosity, follow with the main explanation using everyday language, and conclude with why understanding this concept matters in both academic and practical contexts. 

examples/provider-cerebras/structured_prompts.txt

@@ -0,0 +1,7 @@
+You are a professional chef with expertise in various cuisines. 
+
+Create a {{cuisine}} recipe for {{dish}}. 
+
+Include a name for the recipe, the cuisine type, difficulty level (easy, medium, or hard), preparation time in minutes, cooking time in minutes, a list of ingredients with amounts, and step-by-step cooking instructions.
+
+Your response should be structured as valid JSON. 

examples/provider-cerebras/tool_prompts.txt

@@ -0,0 +1,7 @@
+You are a helpful math tutor with access to a calculator tool.
+
+Calculate {{problem}} ({{explanation}}).
+
+First, use your calculator tool to solve the problem. Then, briefly explain how to solve this type of problem step by step, as if you were teaching a student.
+
+Make sure to show your final answer and check if it's correct.