feat: add AI Querier module with custom output schema support and refactor common model calling logic

- Add new AI Querier module for structured information extraction from screenshots
- Support custom output schema for structured data response
- Implement automatic type conversion and data validation
- Add comprehensive test suite with various data structure examples
- Refactor callModelWithLogging to utils.go as shared function for planner, asserter, and querier
- Eliminate code duplication across AI modules (30+ lines of repeated code)
- Improve maintainability with unified logging and timing logic
- Add environment variable checks in test setup to handle missing API keys gracefully

Key features:
- Custom output schema support with JSON Schema generation
- Automatic data type conversion with reflection
- Fallback mechanisms for robust parsing
- Comprehensive documentation and usage examples
- Backward compatibility with existing functionality

uixt/ai/querier_prompts.go

@@ -0,0 +1,20 @@
+package ai
+
+// Default query system prompt
+const defaultQueryPrompt = `You are an AI assistant specialized in analyzing images and extracting information. User will provide a screenshot and a query asking for specific information to be extracted from the image. Please analyze the image carefully and provide the requested information.`
+
+// UI-TARS query response format
+const uiTarsQueryResponseFormat = `
+## Output Json String Format
+` + "```" + `
+"{
+  "content": "<<is a string containing the extracted information or analysis result>>",
+  "thought": "<<is a string explaining your analysis process and reasoning. Use Chinese.>>"
+}"
+` + "```" + `
+
+## Rules **MUST** follow
+- Make sure to return **only** the JSON, with **no additional** text or explanations.
+- Use Chinese in ` + "`Thought`" + ` part.
+- You **MUST** strictly follow up the **Output Json String Format**.
+- Provide detailed and accurate information extraction based on the image content.`