feat(api): update gpt-4o usage to gpt-4.1

[amplitudesxd]

Summary by cubic

Switch model usage from gpt-4o to gpt-4.1 across extraction and URL processing. Primary calls still use gpt-4o-mini; gpt-4.1 is now the retry/fallback.

• Refactors
  • Updated analyzeSchemaAndPrompt (including fire-0) and generateBasicCompletion to use gpt-4.1.
  • Set gpt-4.1 as the retry model in batchExtract, singleAnswer, extractSmartScrape, and llmExtract.

^{Written for commit 1214cab. Summary will update automatically on new commits.}

[cubic-dev-ai]

1 issue found across 7 files

Prompt for AI agents (all 1 issues)

Check if these issues are valid — if so, understand the root cause of each and fix them.


<file name="apps/api/src/lib/extract/url-processor.ts">

<violation number="1" location="apps/api/src/lib/extract/url-processor.ts:21">
P2: Model changed to `gpt-4.1` but cost tracking still references `openai/gpt-4o`. The `costTracking.addCall` call (lines 44-58) should use `openai/gpt-4.1` for both the `model` field and `calculateCost` to ensure accurate cost tracking and analytics.</violation>
</file>

_{Reply to cubic to teach it or ask questions. Re-run a review with @cubic-dev-ai review this PR}

[cubic-dev-ai]

P2: Model changed to gpt-4.1 but cost tracking still references openai/gpt-4o. The costTracking.addCall call (lines 44-58) should use openai/gpt-4.1 for both the model field and calculateCost to ensure accurate cost tracking and analytics.

Prompt for AI agents

Check if this issue is valid — if so, understand the root cause and fix it. At apps/api/src/lib/extract/url-processor.ts, line 21:

<comment>Model changed to `gpt-4.1` but cost tracking still references `openai/gpt-4o`. The `costTracking.addCall` call (lines 44-58) should use `openai/gpt-4.1` for both the `model` field and `calculateCost` to ensure accurate cost tracking and analytics.</comment>

<file context>
@@ -18,7 +18,7 @@ export async function generateBasicCompletion(
   try {
     const result = await generateText({
-      model: getModel(&quot;gpt-4o&quot;, &quot;openai&quot;),
+      model: getModel(&quot;gpt-4.1&quot;, &quot;openai&quot;),
       prompt: prompt,
       providerOptions: {
</file context>