refactor(thinking): pass source and target formats to ApplyThinking for cross-format validation

Update ApplyThinking signature to accept fromFormat and toFormat parameters
instead of a single provider string. This enables:

- Proper level-to-budget conversion when source is level-based (openai/codex)
  and target is budget-based (gemini/claude)
- Strict budget range validation when source and target formats match
- Level clamping to nearest supported level for cross-format requests
- Format alias resolution in SDK translator registry for codex/openai-response

Also adds ErrBudgetOutOfRange error code and improves iflow config extraction
to fall back to openai format when iflow-specific config is not present.

internal/thinking/errors.go

@@ -24,6 +24,10 @@ const (
 	// Example: using level with a budget-only model
 	ErrLevelNotSupported ErrorCode = "LEVEL_NOT_SUPPORTED"
 
+	// ErrBudgetOutOfRange indicates the budget value is outside model range.
+	// Example: budget 64000 exceeds max 20000
+	ErrBudgetOutOfRange ErrorCode = "BUDGET_OUT_OF_RANGE"
+
 	// ErrProviderMismatch indicates the provider does not match the model.
 	// Example: applying Claude format to a Gemini model
 	ErrProviderMismatch ErrorCode = "PROVIDER_MISMATCH"