Remove automatic README loading from context window

README.md is no longer auto-loaded into the LLM context at startup.
This saves ~4,600 tokens per session while AGENTS.md and memory.md
still provide all critical information for code tasks.

Changes:
- Delete read_project_readme() function
- Remove readme_content parameter from combine_project_content()
- Rename extract_readme_heading() -> extract_project_heading()
- Rename Agent constructors: *_with_readme_* -> *_with_project_context_*
- Update context preservation to only check for Agent Configuration
- Remove has_readme field from LoadedContent
- Update all tests to use new markers and function names

The LLM can still read README.md on-demand via read_file when needed.

README.md

@@ -131,7 +131,7 @@ g3 supports local models via llama.cpp with Metal acceleration on macOS. Here's
 #### Local Models
 | Model | Size | Speed | Agentic Score | Notes |
 |-------|------|-------|---------------|-------|
-| **Qwen3-32B** (Dense) | 18 GB | Slow | ⭐⭐⭐ | Good reasoning, spotty execution |
+| ~~Qwen3-32B~~ (Dense) | 18 GB | Slow | ❌ | Good reasoning, but flails on execution and crashes |
 | Qwen3-14B | 8.4 GB | Medium | ⭐⭐ | Understands tasks but makes implementation errors |
 | GLM-4 9B | 5.7 GB | Fast | ⭐⭐ | Quick responses, may struggle with complex tasks |
 | Qwen3-4B | 2.3 GB | Very Fast | ❌ | Generates malformed tool calls - not for agentic use |