refactor(ai-client): unify OpenAI-compatible path to AI SDK generateText

Eliminate the dual code path (raw fetch vs AI SDK) for text and vision.
All providers now go through createLanguageModel() + generateText(),
removing chatOpenAiCompatible/analyzeOpenAiCompatible, the manual Usage
type, summarizeUsage, and responseFormat plumbing from 8 call sites.

Key fix: @ai-sdk/openai v3 defaults to the Responses API (/responses);
DeepSeek only supports Chat Completions, so we use .chat() explicitly.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

app/api/parse-style-image/route.ts

@@ -55,7 +55,6 @@ export async function POST(req: Request) {
       config.vision,
       body.imageDataUrl,
       STYLE_EXTRACTION_PROMPT,
-      { responseFormat: "json_object" },
     );
 
     let parsed: { stylePrompt?: string };