chore: import upstream snapshot with attribution

examples/eval-search-rubric/README.md

@@ -0,0 +1,66 @@
+# eval-search-rubric (Search Rubric)
+
+You can run this example with:
+
+```bash
+npx promptfoo@latest init --example eval-search-rubric
+cd eval-search-rubric
+```
+
+This example demonstrates how to use the `search-rubric` assertion type to verify that LLM outputs contain accurate, current information.
+
+## Overview
+
+The `search-rubric` assertion allows you to verify facts by searching the web in real-time. This is particularly useful for:
+
+- Current events and news
+- Stock prices and financial data
+- Weather information
+- Recent company information
+- Any time-sensitive data
+
+## Running the Example
+
+```bash
+npx promptfoo eval
+```
+
+## How It Works
+
+1. The LLM generates a response to your prompt
+2. The search-rubric assertion extracts the claim you want to verify
+3. A provider with web search capabilities searches for current information
+4. The assertion passes or fails based on whether the output matches current web data
+
+## Provider Support
+
+### Anthropic Claude
+
+- Web search capabilities via tool configuration (launched in 2025)
+- Requires explicit `web_search_20250305` tool configuration
+- Pricing: $10 per 1,000 searches plus standard token costs
+
+### OpenAI
+
+- Requires `web_search_preview` tool configuration
+- Works with gpt-5.1, o4-mini, and other Responses API models
+
+### Perplexity
+
+- Built-in web search capabilities
+- No additional configuration needed
+
+## Configuration
+
+```yaml
+assert:
+  - type: search-rubric
+    value: 'search query to verify'
+    threshold: 0.8 # Optional: minimum accuracy score (0-1)
+```
+
+## Notes
+
+- Search rubric assertions add latency (2-5 seconds per assertion)
+- Use caching during development: `npx promptfoo eval --cache`
+- Be specific with your search queries for better results

examples/eval-search-rubric/promptfooconfig.yaml

@@ -0,0 +1,101 @@
+# yaml-language-server: $schema=https://promptfoo.dev/config-schema.json
+description: Search rubric assertions for fact-checking
+
+prompts:
+  - '{{question}}'
+
+providers:
+  # Anthropic Claude 4.6 Opus with web search tool
+  - id: anthropic:messages:claude-opus-4-6
+    config:
+      tools:
+        - type: web_search_20250305
+          name: web_search
+          max_uses: 5
+
+  # OpenAI GPT-5.4 with web search tool
+  - id: openai:responses:gpt-5.4
+    config:
+      tools:
+        - type: web_search_preview
+
+  # Google Gemini 3.1 Pro Preview with googleSearch
+  - id: google:gemini-3.1-pro-preview
+    config:
+      tools:
+        - googleSearch: {}
+
+  # xAI Grok 4.3 with Responses API web search
+  - id: xai:responses:grok-4.3
+    config:
+      tools:
+        - type: web_search
+
+  # Perplexity Sonar Pro with built-in search
+  - perplexity:sonar-pro
+
+tests:
+  # Tech industry leadership
+  - vars:
+      question: 'Who is the current CEO of Microsoft?'
+    assert:
+      - type: search-rubric
+        value: 'Correctly identifies Satya Nadella as the current CEO of Microsoft'
+
+  - vars:
+      question: 'Who is the current CEO of OpenAI?'
+    assert:
+      - type: search-rubric
+        value: 'Correctly identifies the current CEO of OpenAI (Sam Altman as of late 2024)'
+
+  # Real-time financial data
+  - vars:
+      question: 'What is the current stock price of NVIDIA (NVDA)?'
+    assert:
+      - type: search-rubric
+        value: |
+          Provides a recent NVIDIA stock price that:
+          - Is a realistic price (should be in the hundreds of dollars range as of 2025)
+          - Includes the currency (USD or $)
+        threshold: 0.8
+
+  - vars:
+      question: 'What is the current market cap of Apple (AAPL)?'
+    assert:
+      - type: search-rubric
+        value: 'States Apple market cap in the trillions of dollars (should be around $3-4 trillion as of 2025)'
+        threshold: 0.8
+
+  # Current events and sports
+  - vars:
+      question: 'Who won the 2024 US Presidential Election?'
+    assert:
+      - type: search-rubric
+        value: 'Correctly identifies Donald Trump as the winner of the 2024 US Presidential Election'
+
+  - vars:
+      question: 'Who won Super Bowl LVIII in February 2024?'
+    assert:
+      - type: search-rubric
+        value: 'Correctly identifies the Kansas City Chiefs as the winners of Super Bowl LVIII (58) defeating the San Francisco 49ers'
+
+  # Technology facts
+  - vars:
+      question: 'What is the latest version of Node.js LTS?'
+    assert:
+      - type: search-rubric
+        value: |
+          States a currently supported Node.js LTS version:
+          - Names a version that is in Active or Maintenance LTS
+          - Does not recommend an end-of-life version
+        threshold: 0.7
+
+  # Weather (real-time)
+  - vars:
+      question: 'What is the current weather in Tokyo, Japan?'
+    assert:
+      - type: search-rubric
+        value: |
+          Provides current Tokyo weather including:
+          - Temperature with units (Celsius or Fahrenheit)
+          - General conditions (sunny, cloudy, rainy, etc.)

examples/eval-search-rubric/simple-test.yaml

@@ -0,0 +1,21 @@
+# Simple test to verify search-rubric assertion
+prompts:
+  - 'The CEO of Microsoft is {{name}}'
+
+providers:
+  # Test with OpenAI (simpler)
+  - id: openai:gpt-4o-mini
+
+tests:
+  - vars:
+      name: 'Satya Nadella'
+    assert:
+      - type: search-rubric
+        value: 'Confirms that {{name}} is the current CEO of Microsoft'
+
+  - vars:
+      name: 'Bill Gates' # Intentionally wrong
+    assert:
+      - type: search-rubric
+        value: 'States the correct current CEO of Microsoft (should identify this is incorrect)'
+        threshold: 0.8