feat(providers): add supports_thinking to thinking-capable models (#53)

* feat(providers): add supports_thinking field to thinking-capable models

Mark models that support extended thinking / reasoning with
supports_thinking = true so the dashboard can conditionally show
thinking toggles.

Providers updated: anthropic (8), codex-cli (7), gemini (6),
openai (3), qwen (2), deepseek (1). Schema updated accordingly.

* feat(providers): add supports_thinking to remaining thinking-capable models

Cover 19 additional providers: alibaba-coding-plan, allenai, arcee-ai,
fireworks, gemini-cli, groq, liquid, nvidia-nim, ollama, openai (codex),
openrouter, perplexity, qwen-code, replicate, sambanova, tngtech,
venice, vertex-ai, xai.

Total: 62 models across 24 providers now have supports_thinking = true.

* feat(providers): add supports_thinking to chutes, huggingface, together

Missed in prior commits: DeepSeek-R1 on chutes/huggingface/together,
Qwen3-235B on chutes. Total now 66 models across 27 providers.

* feat(providers): add supports_thinking to bedrock, claude-code, aider, moonshot, stepfun

- bedrock: all 5 Claude models
- claude-code: all 3 models (opus/sonnet/haiku wrappers)
- aider: aider/sonnet (Claude-backed)
- moonshot: kimi-k2.5 (reasoning mode)
- stepfun: step-1o-turbo-vision (reasoning model)

Total: 77 models across 32 providers.

* feat(providers): add supports_thinking to alibaba kimi-k2.5, openrouter claude-sonnet-4

providers/vertex-ai.toml

@@ -18,6 +18,7 @@ output_cost_per_m = 10.0
 supports_tools = true
 supports_vision = true
 supports_streaming = true
+supports_thinking = true
 aliases = []
 
 [[models]]
@@ -32,6 +33,7 @@ output_cost_per_m = 0.6
 supports_tools = true
 supports_vision = true
 supports_streaming = true
+supports_thinking = true
 aliases = []
 
 [[models]]