feat(v2): add ReasoningLevel option; thinking/reasoning across providers

Introduces an opt-in level-based reasoning toggle (low/medium/high) that
each provider translates to its native parameter:

- Anthropic: thinking.budget_tokens (1024/8000/24000), with temperature
  forced to default and MaxTokens auto-grown above the budget.
- OpenAI/xAI/Groq via openaicompat: reasoning_effort string, gated by a
  new Rules.SupportsReasoning predicate so non-reasoning models don't
  receive the parameter. xAI uses Rules.MapReasoningEffort to remap
  "medium" to "high" since its API only accepts low|high.
- Google: thinking_config.thinking_budget + include_thoughts:true.
- DeepSeek: SupportsReasoning=false (reasoner is always-on; the
  reasoning_content trace was already extracted via openaicompat).

Reasoning content is surfaced as Response.Thinking on Complete and as
StreamEventThinking deltas during streaming. Provider-side: extracted
from Anthropic thinking content blocks, Google's part.Thought=true
parts, and the non-standard reasoning_content field that DeepSeek and
Groq emit (parsed out of raw JSON since openai-go doesn't type it).

Public API:
  - llm.ReasoningLevel + ReasoningLow/Medium/High constants
  - llm.WithReasoning(level) request option
  - Model.WithReasoning(level) for baked-in defaults
  - provider.Request.Reasoning, provider.Response.Thinking
  - provider.StreamEventThinking

Tests cover Rules-based gating, MapReasoningEffort, reasoning_content
extraction (Complete + Stream), Anthropic budget mapping, and
temperature suppression when thinking is enabled. Existing behavior is
unchanged when Reasoning is the empty string.

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>

v2/openai/openai.go

@@ -24,12 +24,15 @@ func New(apiKey string, baseURL string) *Provider {
 		baseURL = DefaultBaseURL
 	}
 	return openaicompat.New(apiKey, baseURL, openaicompat.Rules{
-		RestrictTemperature: restrictTemperature,
+		RestrictTemperature: isReasoningModel,
+		SupportsReasoning:   isReasoningModel,
 	})
 }
 
-// restrictTemperature reports whether OpenAI rejects a user-supplied
-// temperature for this model. o-series reasoning models and gpt-5* both do.
-func restrictTemperature(model string) bool {
+// isReasoningModel reports whether the named OpenAI model is a reasoning
+// model (o-series or gpt-5*). Reasoning models reject a user-supplied
+// temperature and accept a reasoning_effort parameter; everything else
+// rejects reasoning_effort.
+func isReasoningModel(model string) bool {
 	return strings.HasPrefix(model, "o") || strings.HasPrefix(model, "gpt-5")
 }