feat(go-models): migrate batch 1 model drivers to unified handlers (#17696)

## Summary

Relate to #17284

Migrate 10 OpenAI-compatible drivers (`302ai`, `aliyun`, `astraflow`,
`avian`, `azure_openai`, `baichuan`, `baidu`, `cometapi`, `deepinfra`,
`futurmix`) to use the unified response handlers
(`HandleNonStreamingResponse` / `HandleStreamingResponse`), following
the same pattern established by `deepseek` in #17634.

- Cut ~150 lines per driver (1507 lines removed, 144 added across 10
files).
- No functional changes — pure deduplication of HTTP plumbing.
- Each driver now routes through `baseModel.doRequest()` and
`HandleNonStreamingResponse()`.

---------

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

internal/entity/models/response_handler.go

@@ -191,12 +191,17 @@ func extractContentAndChoices(result map[string]any) (*string, *string, []map[st
 	}
 
 	var reasonContent *string
-	if rc, ok := messageMap["reasoning_content"].(string); ok {
+	if rc, ok := messageMap["reasoning_content"].(string); ok && rc != "" {
 		reason := rc
-		if reason != "" && reason[0] == '\n' {
+		if reason[0] == '\n' {
 			reason = reason[1:]
 		}
 		reasonContent = &reason
+	} else if rc, ok := messageMap["reasoning"].(string); ok && rc != "" {
+		// Some providers (e.g. Avian) report reasoning under a top-level
+		// "reasoning" field instead of "reasoning_content".
+		reason := rc
+		reasonContent = &reason
 	} else {
 		// Always return a non-nil pointer so callers can rely on it.
 		empty := ""