fix(openai): use max_completion_tokens and skip temperature for GPT-5/o-series models (#213)

GPT-5 and o-series models reject the legacy max_tokens parameter and
require max_completion_tokens instead. Additionally, gpt-5-mini,
gpt-5-nano, and o-series models only support the default temperature (1).

This patch adds model-aware branching in buildRequestBody() to:
- Send max_completion_tokens instead of max_tokens for gpt-5*/o1/o3/o4
- Skip temperature parameter for gpt-5-mini/gpt-5-nano/o-series

Co-authored-by: Marcelo Emmerich <marcelo@agenticsystems.de>

internal/providers/openai.go

@@ -313,10 +313,18 @@ func (p *OpenAIProvider) buildRequestBody(model string, req ChatRequest, stream
 
 	// Merge options
 	if v, ok := req.Options[OptMaxTokens]; ok {
-		body["max_tokens"] = v
+		if strings.HasPrefix(model, "gpt-5") || strings.HasPrefix(model, "o1") || strings.HasPrefix(model, "o3") || strings.HasPrefix(model, "o4") {
+			body["max_completion_tokens"] = v
+		} else {
+			body["max_tokens"] = v
+		}
 	}
 	if v, ok := req.Options[OptTemperature]; ok {
-		body["temperature"] = v
+		// GPT-5 mini/nano and o-series models only support default temperature
+		skipTemp := strings.HasPrefix(model, "gpt-5-mini") || strings.HasPrefix(model, "gpt-5-nano") || strings.HasPrefix(model, "o1") || strings.HasPrefix(model, "o3") || strings.HasPrefix(model, "o4")
+		if !skipTemp {
+			body["temperature"] = v
+		}
 	}
 
 	// Inject reasoning_effort for o-series models (ignored by models that don't support it)