fix: REPL display, /compact panic, identity leak, DeepSeek reasoning, thinking blocks

[code-yeongyu]

Five interrelated fixes from parallel Hephaestus sessions:

Changes

1. fix(repl): display assistant text after spinner (#2981, #2982, #2937)

• Added final_assistant_text() call after run_turn spinner completes
• REPL now shows response text like run_prompt_json does

2. fix(compact): handle Thinking content blocks (#2985)

• Added ContentBlock::Thinking variant throughout compact summarizer
• Prevents panic when /compact encounters thinking blocks

3. fix(prompt): provider-aware model identity (#2822)

• New ModelFamilyIdentity enum (Claude vs Generic)
• Non-Anthropic models no longer say 'I am Claude'
• model_family_identity_for() detects provider and sets identity

4. fix(openai): preserve DeepSeek reasoning_content (#2821)

• Stream parser now captures reasoning_content from OpenAI-compat responses
• Emits ThinkingDelta/SignatureDelta events for reasoning models
• Thinking blocks included in conversation history for multi-turn

5. feat(runtime): Thinking block support across codebase

• AssistantEvent::Thinking variant in conversation.rs
• ContentBlock::Thinking in session serialization
• Thinking-aware compact summarization
• Tests for thinking block ordering and content

Testing

• cargo test --workspace passes
• cargo fmt --all clean
• cargo clippy --workspace clean (only pre-existing warnings)

Closes #2981, #2982, #2937, #2985, #2822, #2821