chore: import upstream snapshot with attribution

tests/agent_tasks/README.md

@@ -0,0 +1,33 @@
+# Contributing Agent Tasks
+
+Contribute your own agent tasks and we test if the agent solves them for CI testing!
+
+## How to Add a Task
+
+1. Create a new `.yaml` file in this directory (`tests/agent_tasks/`).
+2. Use the following format:
+
+```yaml
+name: My Task Name
+task: Describe the task for the agent to perform
+judge_context:
+  - List criteria for success, one per line
+max_steps: 10
+```
+
+## Guidelines
+- Be specific in your task and criteria.
+- The `judge_context` should list what counts as a successful result.
+- The agent's output will be judged by an LLM using these criteria.
+
+## Running the Tests
+
+To run all agent tasks:
+
+```bash
+pytest tests/ci/test_agent_real_tasks.py
+```
+
+---
+
+Happy contributing! 

tests/agent_tasks/amazon_laptop.yaml

@@ -0,0 +1,7 @@
+name: Amazon Laptop Search
+task: Go to amazon.com, search for 'laptop', and return the first result
+judge_context:
+  - The agent must navigate to amazon.com
+  - The agent must search for 'laptop'
+  - The agent must return name of the first laptop 
+max_steps: 10

tests/agent_tasks/browser_use_pip.yaml

@@ -0,0 +1,5 @@
+name: Find pip install command for browser-use
+task: Find the pip installation command for the browser-use repo
+judge_context:
+  - The output must include the command ('pip install browser-use') 
+max_steps: 10