Add session management, readline history, context compression, --ctx, --micro flags, and context counter in prompt

Fix streaming display in coder CLI - use iter_lines for immediate output, remove threading timer, simplify tool parsing

- Add generate_chat() and generate_chat_stream() methods to VulkanBackend
- These use create_chat_completion() which properly applies model's chat template
- Fallback to manual formatting if create_chat_completion fails
- Update API endpoints to pass messages dict directly instead of formatted prompt
- Fixes garbled output with Qwen3 and other models that use custom chat templates

- Use apply_chat_template() to properly format messages for each model
- This ensures Qwen3 and other models get their correct chat format
- Fallback to <|im_start|>/|im_end|> format if apply_chat_template fails
- Fixes garbled output with <|system|> tags appearing in responses