fix(extract): make AI imports reliable and fast on local models

client: the import call inherited the global 8s axios timeout and aborted long LLM extractions even though the server finished it; remove the timeout. server: raise the OpenAI-compatible LLM timeout 60s->180s (a cold Ollama model can take ~45s to first token). server: cap extracted text to 8000 chars before the LLM - multi-page T&C tails (30k+ chars) overflowed the context window, truncating the relevant head and making CPU inference crawl; booking details sit at the top.

server/src/nest/llm-parse/clients/openai-compatible.client.ts

@@ -1,6 +1,8 @@
 import type { LlmExtractionClient, LlmExtractionInput } from '../llm-provider.interface';
 
-const TIMEOUT_MS = 60_000;
+// Generous: a local model (Ollama) may cold-load several GB before its first
+// token, and longer documents push inference past a minute.
+const TIMEOUT_MS = 180_000;
 const MAX_TOKENS = 4096;
 
 /**

server/src/nest/llm-parse/llm-parse.service.ts

@@ -54,6 +54,12 @@ export class LlmParseService {
         );
       } else {
         input.text = await extractText(file.buffer, file.originalName);
+        // Booking details sit at the top of a confirmation; multi-page T&C tails
+        // (rental/insurance docs run 30k+ chars) otherwise overflow the model's
+        // context window — truncating the *relevant* head — and balloon CPU
+        // inference time. Cap the text so only the useful head reaches the LLM.
+        const MAX_EXTRACT_CHARS = 8000;
+        if (input.text.length > MAX_EXTRACT_CHARS) input.text = input.text.slice(0, MAX_EXTRACT_CHARS);
         console.debug(`[DEBUG] Extracted text from ${file.originalName} (${input.text.length} chars):\n`, input.text);
         if (!input.text.trim()) {
           return {