feat(llm): add Amazon Bedrock as a first-class provider

Bedrock uses the Converse API (langchain-aws) and the AWS credential chain, so
it has its own client like Anthropic/Google rather than the OpenAI-compatible
registry. langchain-aws is an optional dependency (pip install ".[bedrock]"),
lazy-imported with a clear install hint; importing the package never requires
it. The model name is a Bedrock model ID / inference profile ID.

cli/utils.py

@@ -316,6 +316,7 @@ def _llm_provider_table() -> list[tuple[str, str, str | None]]:
         ("Groq", "groq", "https://api.groq.com/openai/v1"),
         ("NVIDIA NIM", "nvidia", "https://integrate.api.nvidia.com/v1"),
         ("Azure OpenAI", "azure", None),
+        ("Amazon Bedrock", "bedrock", None),
         ("Ollama", "ollama", ollama_url),
         ("OpenAI-compatible (vLLM, LM Studio, llama.cpp, custom relay)", "openai_compatible", None),
     ]