mirror of
https://github.com/mendableai/firecrawl.git
synced 2025-06-27 00:41:33 +00:00
fix: implement per-document cost tracking architecture
- Create DocumentWithCostTracking interface for proper return type - Modify scrapeSearchResult to return individual costTracking instances - Update billing logic to use separate costTracking per document - Fix deep research service to handle new interface structure - Add stealth mode and PDF billing test cases - Prevents shared state accumulation in billing calculations Addresses GitHub comments from mogery and micahstairs: - Reworks cost tracking to return separate instances per document - Restores bypassBilling: false flag as requested - Implements proper per-document billing calculation Co-Authored-By: Micah Stairs <micah@sideguide.dev>
This commit is contained in:
Devin AI
parent
9336e275f4
commit
90469270e0
@ -24,6 +24,11 @@ import type { Logger } from "winston";
|
||||
import { CostTracking } from "../../lib/extract/extraction-service";
|
||||
import { calculateCreditsToBeBilled } from "../../lib/scrape-billing";
|
||||
|
||||
interface DocumentWithCostTracking {
|
||||
document: Document;
|
||||
costTracking: CostTracking;
|
||||
}
|
||||
|
||||
// Used for deep research
|
||||
export async function searchAndScrapeSearchResult(
|
||||
query: string,
|
||||
@ -34,16 +39,15 @@ export async function searchAndScrapeSearchResult(
|
||||
scrapeOptions: ScrapeOptions;
|
||||
},
|
||||
logger: Logger,
|
||||
costTracking: CostTracking,
|
||||
flags: TeamFlags,
|
||||
): Promise<Document[]> {
|
||||
): Promise<DocumentWithCostTracking[]> {
|
||||
try {
|
||||
const searchResults = await search({
|
||||
query,
|
||||
num_results: 5,
|
||||
});
|
||||
|
||||
const documents = await Promise.all(
|
||||
const documentsWithCostTracking = await Promise.all(
|
||||
searchResults.map((result) =>
|
||||
scrapeSearchResult(
|
||||
{
|
||||
@ -53,13 +57,12 @@ export async function searchAndScrapeSearchResult(
|
||||
},
|
||||
options,
|
||||
logger,
|
||||
costTracking,
|
||||
flags,
|
||||
),
|
||||
),
|
||||
);
|
||||
|
||||
return documents;
|
||||
return documentsWithCostTracking;
|
||||
} catch (error) {
|
||||
return [];
|
||||
}
|
||||
@ -74,16 +77,17 @@ async function scrapeSearchResult(
|
||||
scrapeOptions: ScrapeOptions;
|
||||
},
|
||||
logger: Logger,
|
||||
costTracking: CostTracking,
|
||||
flags: TeamFlags,
|
||||
directToBullMQ: boolean = false,
|
||||
isSearchPreview: boolean = false,
|
||||
): Promise<Document> {
|
||||
): Promise<DocumentWithCostTracking> {
|
||||
const jobId = uuidv4();
|
||||
const jobPriority = await getJobPriority({
|
||||
team_id: options.teamId,
|
||||
basePriority: 10,
|
||||
});
|
||||
|
||||
const costTracking = new CostTracking();
|
||||
|
||||
try {
|
||||
if (isUrlBlocked(searchResult.url, flags)) {
|
||||
@ -104,7 +108,7 @@ async function scrapeSearchResult(
|
||||
...options.scrapeOptions,
|
||||
maxAge: 4 * 60 * 60 * 1000,
|
||||
},
|
||||
internalOptions: { teamId: options.teamId, bypassBilling: true },
|
||||
internalOptions: { teamId: options.teamId, bypassBilling: false },
|
||||
origin: options.origin,
|
||||
is_scrape: true,
|
||||
startTime: Date.now(),
|
||||
@ -116,6 +120,19 @@ async function scrapeSearchResult(
|
||||
);
|
||||
|
||||
const doc: Document = await waitForJob(jobId, options.timeout);
|
||||
|
||||
const actualCostTracking = new CostTracking();
|
||||
const credits = await calculateCreditsToBeBilled(options.scrapeOptions, doc, actualCostTracking);
|
||||
actualCostTracking.addCall({
|
||||
type: "other",
|
||||
metadata: {
|
||||
module: "search",
|
||||
operation: "scrape",
|
||||
url: searchResult.url
|
||||
},
|
||||
cost: credits,
|
||||
model: "search-scrape"
|
||||
});
|
||||
|
||||
logger.info("Scrape job completed", {
|
||||
scrapeId: jobId,
|
||||
@ -125,13 +142,17 @@ async function scrapeSearchResult(
|
||||
});
|
||||
await getScrapeQueue().remove(jobId);
|
||||
|
||||
// Move SERP results to top level
|
||||
return {
|
||||
const document = {
|
||||
title: searchResult.title,
|
||||
description: searchResult.description,
|
||||
url: searchResult.url,
|
||||
...doc,
|
||||
};
|
||||
|
||||
return {
|
||||
document,
|
||||
costTracking: actualCostTracking,
|
||||
};
|
||||
} catch (error) {
|
||||
logger.error(`Error in scrapeSearchResult: ${error}`, {
|
||||
scrapeId: jobId,
|
||||
@ -143,8 +164,8 @@ async function scrapeSearchResult(
|
||||
if (error?.message?.includes("Could not scrape url")) {
|
||||
statusCode = 403;
|
||||
}
|
||||
// Return a minimal document with SERP results at top level
|
||||
return {
|
||||
|
||||
const document: Document = {
|
||||
title: searchResult.title,
|
||||
description: searchResult.description,
|
||||
url: searchResult.url,
|
||||
@ -154,6 +175,11 @@ async function scrapeSearchResult(
|
||||
proxyUsed: "basic",
|
||||
},
|
||||
};
|
||||
|
||||
return {
|
||||
document,
|
||||
costTracking: new CostTracking(),
|
||||
};
|
||||
}
|
||||
}
|
||||
|
||||
@ -174,8 +200,10 @@ export async function searchController(
|
||||
data: [],
|
||||
};
|
||||
const startTime = new Date().getTime();
|
||||
const costTracking = new CostTracking();
|
||||
const isSearchPreview = process.env.SEARCH_PREVIEW_TOKEN !== undefined && process.env.SEARCH_PREVIEW_TOKEN === req.body.__searchPreviewToken;
|
||||
|
||||
let credits_billed = 0;
|
||||
let allDocsWithCostTracking: DocumentWithCostTracking[] = [];
|
||||
|
||||
try {
|
||||
req.body = searchRequestSchema.parse(req.body);
|
||||
@ -242,18 +270,18 @@ export async function searchController(
|
||||
scrapeOptions: req.body.scrapeOptions,
|
||||
},
|
||||
logger,
|
||||
costTracking,
|
||||
req.acuc?.flags ?? null,
|
||||
(req.acuc?.price_credits ?? 0) <= 3000,
|
||||
isSearchPreview,
|
||||
),
|
||||
);
|
||||
|
||||
const docs = await Promise.all(scrapePromises);
|
||||
const docsWithCostTracking = await Promise.all(scrapePromises);
|
||||
logger.info("Scraping completed", {
|
||||
num_docs: docs.length,
|
||||
num_docs: docsWithCostTracking.length,
|
||||
});
|
||||
|
||||
const docs = docsWithCostTracking.map(item => item.document);
|
||||
const filteredDocs = docs.filter(
|
||||
(doc) =>
|
||||
doc.serpResults || (doc.markdown && doc.markdown.trim().length > 0),
|
||||
@ -269,18 +297,34 @@ export async function searchController(
|
||||
} else {
|
||||
responseData.data = filteredDocs;
|
||||
}
|
||||
}
|
||||
|
||||
let credits_billed = 0;
|
||||
try {
|
||||
credits_billed = await Promise.all(
|
||||
responseData.data.map(async (document) => {
|
||||
return await calculateCreditsToBeBilled(req.body.scrapeOptions, document, costTracking);
|
||||
})
|
||||
).then(credits => credits.reduce((sum, credit) => sum + credit, 0));
|
||||
} catch (error) {
|
||||
logger.error("Error calculating credits for billing", { error });
|
||||
credits_billed = responseData.data.length;
|
||||
const finalDocsForBilling = responseData.data;
|
||||
|
||||
const creditPromises = finalDocsForBilling.map(async (finalDoc) => {
|
||||
const matchingDocWithCost = docsWithCostTracking.find(item =>
|
||||
item.document.url === finalDoc.url
|
||||
);
|
||||
|
||||
if (matchingDocWithCost) {
|
||||
return await calculateCreditsToBeBilled(
|
||||
req.body.scrapeOptions,
|
||||
matchingDocWithCost.document,
|
||||
matchingDocWithCost.costTracking
|
||||
);
|
||||
} else {
|
||||
return 1;
|
||||
}
|
||||
});
|
||||
|
||||
try {
|
||||
const individualCredits = await Promise.all(creditPromises);
|
||||
credits_billed = individualCredits.reduce((sum, credit) => sum + credit, 0);
|
||||
} catch (error) {
|
||||
logger.error("Error calculating credits for billing", { error });
|
||||
credits_billed = responseData.data.length;
|
||||
}
|
||||
|
||||
allDocsWithCostTracking = docsWithCostTracking;
|
||||
}
|
||||
|
||||
// Bill team once for all successful results
|
||||
@ -317,7 +361,7 @@ export async function searchController(
|
||||
scrapeOptions: req.body.scrapeOptions,
|
||||
origin: req.body.origin,
|
||||
integration: req.body.integration,
|
||||
cost_tracking: costTracking,
|
||||
cost_tracking: allDocsWithCostTracking.length > 0 ? allDocsWithCostTracking[0].costTracking : new CostTracking(),
|
||||
credits_billed,
|
||||
},
|
||||
false,
|
||||
|
||||
@ -134,7 +134,7 @@ export async function performDeepResearch(options: DeepResearchServiceOptions) {
|
||||
maxAge: 4 * 60 * 60 * 1000,
|
||||
storeInCache: true,
|
||||
},
|
||||
}, logger, costTracking, acuc?.flags ?? null);
|
||||
}, logger, acuc?.flags ?? null);
|
||||
return response.length > 0 ? response : [];
|
||||
});
|
||||
|
||||
@ -164,10 +164,10 @@ export async function performDeepResearch(options: DeepResearchServiceOptions) {
|
||||
// Filter out already seen URLs and track new ones
|
||||
const newSearchResults: typeof searchResults = [];
|
||||
for (const result of searchResults) {
|
||||
if (!result.url || state.hasSeenUrl(result.url)) {
|
||||
if (!result.document.url || state.hasSeenUrl(result.document.url)) {
|
||||
continue;
|
||||
}
|
||||
state.addSeenUrl(result.url);
|
||||
state.addSeenUrl(result.document.url);
|
||||
|
||||
urlsAnalyzed++;
|
||||
if (urlsAnalyzed >= maxUrls) {
|
||||
@ -183,10 +183,10 @@ export async function performDeepResearch(options: DeepResearchServiceOptions) {
|
||||
}
|
||||
|
||||
await state.addSources(newSearchResults.map((result) => ({
|
||||
url: result.url ?? "",
|
||||
title: result.title ?? "",
|
||||
description: result.description ?? "",
|
||||
icon: result.metadata?.favicon ?? "",
|
||||
url: result.document.url ?? "",
|
||||
title: result.document.title ?? "",
|
||||
description: result.document.description ?? "",
|
||||
icon: result.document.metadata?.favicon ?? "",
|
||||
})));
|
||||
logger.debug(
|
||||
"[Deep Research] New unique results count:",
|
||||
@ -218,8 +218,8 @@ export async function performDeepResearch(options: DeepResearchServiceOptions) {
|
||||
|
||||
await state.addFindings(
|
||||
newSearchResults.map((result) => ({
|
||||
text: result.markdown ?? "",
|
||||
source: result.url ?? "",
|
||||
text: result.document.markdown ?? "",
|
||||
source: result.document.url ?? "",
|
||||
})),
|
||||
);
|
||||
|
||||
|
||||
Loading…
x
Reference in New Issue
Block a user