feat(go-models): migrate batch 3 model drivers to unified handlers (#17698)

## Summary

Relate to #17284

Migrate 10 OpenAI-compatible drivers (`minimax`, `mistral`,
`modelscope`, `moonshot`, `n1n`, `novita`, `ollama`, `openai`,
`openai_api_compatible`, `openrouter`) to use the unified response
handlers (`HandleNonStreamingResponse` / `HandleStreamingResponse`),
following the same pattern established by `deepseek` in #17634.

- Cut ~150 lines per driver (1692 lines removed, 172 added across 10
files).
- `openai_api_compatible` gains `ChatWithMessages` +
`ChatStreamlyWithSender` required by the unified handler infrastructure.
- `openai` driver preserves `reasoning_content` extraction for o-series
models.
- All drivers: pure deduplication of HTTP plumbing.

---------

Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

internal/entity/models/response_handler.go

@@ -115,8 +115,15 @@ func HandleStreamingResponse(
 
 		accumulateToolCallDeltas(delta, accumulatedToolCalls)
 
-		if reasoningContent, ok := delta["reasoning_content"].(string); ok && reasoningContent != "" {
-			if err := sender(nil, &reasoningContent); err != nil {
+		// Extract reasoning via the protocol hook so each provider can
+		// name its reasoning field differently (reasoning_content,
+		// reasoning, ...) without the shared handler knowing which.
+		extractReasoning := cfg.ExtractStreamReasoning
+		if extractReasoning == nil {
+			extractReasoning = extractDefaultStreamReasoning
+		}
+		if reasoning := extractReasoning(delta); reasoning != "" {
+			if err := sender(nil, &reasoning); err != nil {
 				return err
 			}
 		}