From b5b612c35b70c42b5f05e23fed12e71f46412ca0 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Gerg=C5=91=20M=C3=B3ricz?= <mo.geryy@gmail.com>
Date: Thu, 15 May 2025 16:32:59 +0200
Subject: [PATCH] feat(api/extract/fire-0): error logging (#1556)

---
 .../extract/fire-0/extraction-service-f0.ts   | 81 +++++++++++++++++++
 1 file changed, 81 insertions(+)

diff --git a/apps/api/src/lib/extract/fire-0/extraction-service-f0.ts b/apps/api/src/lib/extract/fire-0/extraction-service-f0.ts
index fcf133e5..72cc8e2e 100644
--- a/apps/api/src/lib/extract/fire-0/extraction-service-f0.ts
+++ b/apps/api/src/lib/extract/fire-0/extraction-service-f0.ts
@@ -106,6 +106,22 @@ import { getACUCTeam } from "../../../controllers/auth";
       logger.error("No search results found", {
         query: request.prompt,
       });
+      logJob({
+        job_id: extractId,
+        success: false,
+        message: "No search results found",
+        num_docs: 1,
+        docs: [],
+        time_taken: (new Date().getTime() - Date.now()) / 1000,
+        team_id: teamId,
+        mode: "extract",
+        url: request.urls?.join(", ") || "",
+        scrapeOptions: request,
+        origin: request.origin ?? "api",
+        num_tokens: 0,
+        tokens_billed: 0,
+        sources,
+      });
       return {
         success: false,
         error: "No search results found",
@@ -191,6 +207,22 @@ import { getACUCTeam } from "../../../controllers/auth";
       logger.error("0 links! Bailing.", {
         linkCount: links.length,
       });
+      logJob({
+        job_id: extractId,
+        success: false,
+        message: "No valid URLs found to scrape",
+        num_docs: 1,
+        docs: [],
+        time_taken: (new Date().getTime() - Date.now()) / 1000,
+        team_id: teamId,
+        mode: "extract",
+        url: request.urls?.join(", ") || "",
+        scrapeOptions: request,
+        origin: request.origin ?? "api",
+        num_tokens: 0,
+        tokens_billed: 0,
+        sources,
+      });
       return {
         success: false,
         error:
@@ -524,6 +556,22 @@ import { getACUCTeam } from "../../../controllers/auth";
   
       } catch (error) {
         logger.error(`Failed to transform array to object`, { error });
+        logJob({
+          job_id: extractId,
+          success: false,
+          message: "Failed to transform array to object",
+          num_docs: 1,
+          docs: [],
+          time_taken: (new Date().getTime() - Date.now()) / 1000,
+          team_id: teamId,
+          mode: "extract",
+          url: request.urls?.join(", ") || "",
+          scrapeOptions: request,
+          origin: request.origin ?? "api",
+          num_tokens: 0,
+          tokens_billed: 0,
+          sources,
+        });
         return {
           success: false,
           error:
@@ -602,6 +650,23 @@ import { getACUCTeam } from "../../../controllers/auth";
   
         logger.debug("Scrapes finished.", { docCount: validResults.length });
       } catch (error) {
+        logger.error("Failed to scrape documents", { error });
+        logJob({
+          job_id: extractId,
+          success: false,
+          message: "Failed to scrape documents",
+          num_docs: 1,
+          docs: [],
+          time_taken: (new Date().getTime() - Date.now()) / 1000,
+          team_id: teamId,
+          mode: "extract",
+          url: request.urls?.join(", ") || "",
+          scrapeOptions: request,
+          origin: request.origin ?? "api",
+          num_tokens: 0,
+          tokens_billed: 0,
+          sources,
+        });
         return {
           success: false,
           error: error.message,
@@ -614,6 +679,22 @@ import { getACUCTeam } from "../../../controllers/auth";
       if (docsMap.size == 0) {
         // All urls are invalid
         logger.error("All provided URLs are invalid!");
+        logJob({
+          job_id: extractId,
+          success: false,
+          message: "All provided URLs are invalid",
+          num_docs: 1,
+          docs: [],
+          time_taken: (new Date().getTime() - Date.now()) / 1000,
+          team_id: teamId,
+          mode: "extract",
+          url: request.urls?.join(", ") || "",
+          scrapeOptions: request,
+          origin: request.origin ?? "api",
+          num_tokens: 0,
+          tokens_billed: 0,
+          sources,
+        });
         return {
           success: false,
           error: