addedInput schema / additionalProperties
Added value: +false
changedInput schema / properties / adaptive / description
Previous value: -"With query: stop once the collected pages cover it."New value: +"With query: stop once the collected pages cover it; an object sets coverageThreshold, evidencePerTerm, patience, minGain."
changedInput schema / properties / adaptive / type
Previous value: -"boolean"New value: +[
+ "boolean",
+ "object"
+]
addedInput schema / properties / attachmentLimit / minimum
Added value: +0
changedInput schema / properties / attachmentLimit / type
Previous value: -"number"New value: +"integer"
removedInput schema / properties / deduplicateSimilarURLs
Removed value: -{
- "type": "boolean"
-}
addedInput schema / properties / limit / minimum
Added value: +1
changedInput schema / properties / limit / type
Previous value: -"number"New value: +"integer"
addedInput schema / properties / maxConcurrency / minimum
Added value: +1
changedInput schema / properties / maxConcurrency / type
Previous value: -"number"New value: +"integer"
addedInput schema / properties / maxDepth
Added value: +{
+ "description": "Firecrawl v1 name; only checked against the limit, maxDiscoveryDepth sets the depth.",
+ "minimum": 0,
+ "type": "integer"
+}
addedInput schema / properties / maxDiscoveryDepth / minimum
Added value: +0
changedInput schema / properties / maxDiscoveryDepth / type
Previous value: -"number"New value: +"integer"
removedInput schema / properties / prompt
Removed value: -{
- "type": "string"
-}
addedInput schema / properties / scope
Added value: +{
+ "description": "How far the crawl may leave the seed's directory.",
+ "enum": [
+ "auto",
+ "exact",
+ "parent",
+ "domain"
+ ],
+ "type": "string"
+}
addedInput schema / properties / scrapeOptions / additionalProperties
Added value: +false
addedInput schema / properties / scrapeOptions / properties / actions / items / properties / all
Added value: +{
+ "type": "boolean"
+}
addedInput schema / properties / scrapeOptions / properties / actions / items / properties / format
Added value: +{
+ "type": "string"
+}
addedInput schema / properties / scrapeOptions / properties / actions / items / properties / landscape
Added value: +{
+ "type": "boolean"
+}
addedInput schema / properties / scrapeOptions / properties / actions / items / properties / milliseconds / minimum
Added value: +0
changedInput schema / properties / scrapeOptions / properties / actions / items / properties / milliseconds / type
Previous value: -"number"New value: +"integer"
addedInput schema / properties / scrapeOptions / properties / actions / items / properties / quality
Added value: +{
+ "maximum": 100,
+ "minimum": 1,
+ "type": "integer"
+}
addedInput schema / properties / scrapeOptions / properties / actions / items / properties / scale
Added value: +{
+ "type": "number"
+}
changedInput schema / properties / scrapeOptions / properties / actions / items / properties / type / enum
Previous value: -[
- "wait",
- "screenshot",
- "scroll",
- "scrape",
- "click",
- "write",
- "press",
- "executeJavascript",
- "generatePDF"
-]New value: +[
+ "wait",
+ "click",
+ "write",
+ "press",
+ "scroll",
+ "screenshot",
+ "scrape",
+ "executeJavascript",
+ "pdf"
+]
addedInput schema / properties / scrapeOptions / properties / actions / items / properties / viewport
Added value: +{
+ "properties": {
+ "height": {
+ "type": "integer"
+ },
+ "width": {
+ "type": "integer"
+ }
+ },
+ "required": [
+ "width",
+ "height"
+ ],
+ "type": "object"
+}
addedInput schema / properties / scrapeOptions / properties / blockAds
Added value: +{
+ "description": "Block ads when rendering. Defaults to true.",
+ "type": "boolean"
+}
addedInput schema / properties / scrapeOptions / properties / chunking
Added value: +{
+ "description": "Split markdown into chunks, e.g. {\"type\": \"recursive\", \"size\": 400}.",
+ "properties": {
+ "type": {
+ "type": "string"
+ }
+ },
+ "required": [
+ "type"
+ ],
+ "type": "object"
+}
addedInput schema / properties / scrapeOptions / properties / discoverScripts
Added value: +{
+ "description": "With engine http and the links format: also list same-origin URLs found in external scripts.",
+ "type": "boolean"
+}
addedInput schema / properties / scrapeOptions / properties / egress
Added value: +{
+ "description": "Name of a configured [[egress]] to fetch through.",
+ "type": "string"
+}
changedInput schema / properties / scrapeOptions / properties / engine / description
Previous value: -"pagesift extension: fetch with plain HTTP, a headless browser, or decide automatically (default)."New value: +"Fetch with plain HTTP, a headless browser, or decide automatically (default)."
addedInput schema / properties / scrapeOptions / properties / explain
Added value: +{
+ "description": "Record how the result was produced in metadata.pagesift.plan.",
+ "type": "boolean"
+}
addedInput schema / properties / scrapeOptions / properties / exportImages
Added value: +{
+ "description": "Export the page's images (PDF embedded images, Office media, web images); returned as resource links.",
+ "type": "boolean"
+}
changedInput schema / properties / scrapeOptions / properties / formats / description
Previous value: -"Output formats. Defaults to [\"markdown\"]."New value: +"Output formats. Defaults to [\"markdown\"]. Object form passes options: {\"type\": \"extract\", \"schema\": {\"baseSelector\": ..., \"fields\": [...]}} extracts structured data with CSS selectors (no LLM; selectors are relocated after a redesign when a store is open), {\"type\": \"json\", \"schema\": {...}, \"prompt\": \"...\"} asks the LLM."
addedInput schema / properties / scrapeOptions / properties / formats / items / anyOf
Added value: +[
+ {
+ "enum": [
+ "markdown",
+ "html",
+ "rawHtml",
+ "links",
+ "images",
+ "extract"
+ ],
+ "type": "string"
+ },
+ {
+ "additionalProperties": false,
+ "properties": {
+ "intent": {
+ "description": "extract without a schema: what to extract; the LLM writes the schema.",
+ "type": "string"
+ },
+ "modes": {
+ "description": "changeTracking: diff modes.",
+ "items": {
+ "type": "string"
+ },
+ "type": "array"
+ },
+ "prompt": {
+ "description": "json: what to extract.",
+ "type": "string"
+ },
+ "schema": {
+ "description": "extract: CSS schema {baseSelector, fields}; json: JSON Schema for the LLM.",
+ "type": "object"
+ },
+ "type": {
+ "enum": [
+ "markdown",
+ "html",
+ "rawHtml",
+ "links",
+ "images",
+ "extract"
+ ],
+ "type": "string"
+ }
+ },
+ "required": [
+ "type"
+ ],
+ "type": "object"
+ }
+]
removedInput schema / properties / scrapeOptions / properties / formats / items / enum
Removed value: -[
- "markdown",
- "html",
- "rawHtml",
- "screenshot",
- "links",
- "images",
- "summary",
- "changeTracking",
- "branding",
- "json",
- "query",
- "audio"
-]
removedInput schema / properties / scrapeOptions / properties / formats / items / type
Removed value: -"string"
addedInput schema / properties / scrapeOptions / properties / headers
Added value: +{
+ "additionalProperties": {
+ "type": "string"
+ },
+ "description": "Extra request headers.",
+ "type": "object"
+}
changedInput schema / properties / scrapeOptions / properties / ifModifiedSince / description
Previous value: -"pagesift extension: HTTP date for a conditional request."New value: +"HTTP date for a conditional request."
changedInput schema / properties / scrapeOptions / properties / ifNoneMatch / description
Previous value: -"pagesift extension: ETag for a conditional request."New value: +"ETag for a conditional request."
removedInput schema / properties / scrapeOptions / properties / jsonOptions
Removed value: -{
- "description": "Options for the json format.",
- "properties": {
- "prompt": {
- "type": "string"
- },
- "schema": {
- "type": "object"
- }
- },
- "type": "object"
-}
addedInput schema / properties / scrapeOptions / properties / keepSession
Added value: +{
+ "description": "Keep the browser page open and return its id in metadata.scrapeId, to continue with pagesift_interact. Only on pagesift_scrape. Close it with pagesift_interact_stop.",
+ "type": "boolean"
+}
addedInput schema / properties / scrapeOptions / properties / location / additionalProperties
Added value: +false
removedInput schema / properties / scrapeOptions / properties / lockdown
Removed value: -{
- "type": "boolean"
-}
addedInput schema / properties / scrapeOptions / properties / maxAge / minimum
Added value: +0
changedInput schema / properties / scrapeOptions / properties / maxAge / type
Previous value: -"number"New value: +"integer"
addedInput schema / properties / scrapeOptions / properties / minAge
Added value: +{
+ "description": "Only return a cached copy at least this many milliseconds old.",
+ "minimum": 0,
+ "type": "integer"
+}
addedInput schema / properties / scrapeOptions / properties / mobile / description
Added value: +"Emulate a phone when rendering."
addedInput schema / properties / scrapeOptions / properties / parsers / description
Added value: +"PDF parser selection, e.g. [\"pdf\"] or [{\"type\": \"pdf\", \"maxPages\": 10}]."
removedInput schema / properties / scrapeOptions / properties / parsers / items
Removed value: -{
- "enum": [
- "pdf"
- ],
- "type": "string"
-}
removedInput schema / properties / scrapeOptions / properties / pdfOptions
Removed value: -{
- "properties": {
- "maxPages": {
- "maximum": 10000,
- "minimum": 1,
- "type": "integer"
- }
- },
- "type": "object"
-}
removedInput schema / properties / scrapeOptions / properties / profile
Removed value: -{
- "properties": {
- "name": {
- "type": "string"
- },
- "saveChanges": {
- "type": "boolean"
- }
- },
- "required": [
- "name"
- ],
- "type": "object"
-}
changedInput schema / properties / scrapeOptions / properties / proxy / description
Previous value: -"Only basic and auto are supported; pagesift does not bypass bot protection."New value: +"\"basic\", \"auto\", or an http/https/socks5 proxy URL. pagesift does not solve CAPTCHAs; a block or challenge page is reported as an error."
removedInput schema / properties / scrapeOptions / properties / proxy / enum
Removed value: -[
- "basic",
- "stealth",
- "enhanced",
- "auto"
-]
addedInput schema / properties / scrapeOptions / properties / queryFilter
Added value: +{
+ "description": "Keep only the blocks relevant to a query: a string, or {query, threshold, relative, topK, maxTokens, minTokens, headings}.",
+ "type": [
+ "string",
+ "object"
+ ]
+}
removedInput schema / properties / scrapeOptions / properties / queryOptions
Removed value: -{
- "description": "Options for the query format.",
- "properties": {
- "mode": {
- "default": "freeform",
- "enum": [
- "directQuote",
- "freeform"
- ],
- "type": "string"
- },
- "prompt": {
- "maxLength": 10000,
- "type": "string"
- }
- },
- "required": [
- "prompt"
- ],
- "type": "object"
-}
removedInput schema / properties / scrapeOptions / properties / redactPII
Removed value: -{
- "type": "boolean"
-}
addedInput schema / properties / scrapeOptions / properties / respondTiming
Added value: +{
+ "description": "When a rendered page counts as ready: html does not run scripts; the others wait for visible content, DOM mutations to settle, scripts/XHR to go quiet, or media to load.",
+ "enum": [
+ "html",
+ "visible-content",
+ "mutation-idle",
+ "resource-idle",
+ "media-idle",
+ "network-idle"
+ ],
+ "type": "string"
+}
removedInput schema / properties / scrapeOptions / properties / screenshotOptions
Removed value: -{
- "properties": {
- "fullPage": {
- "type": "boolean"
- },
- "quality": {
- "type": "number"
- },
- "viewport": {
- "properties": {
- "height": {
- "type": "number"
- },
- "width": {
- "type": "number"
- }
- },
- "required": [
- "width",
- "height"
- ],
- "type": "object"
- }
- },
- "type": "object"
-}
removedInput schema / properties / scrapeOptions / properties / skipTlsVerification
Removed value: -{
- "type": "boolean"
-}
addedInput schema / properties / scrapeOptions / properties / storeSnapshot
Added value: +{
+ "description": "Keep a snapshot of this page for later change tracking.",
+ "type": "boolean"
+}
changedInput schema / properties / scrapeOptions / properties / timeout / minimum
Previous value: -1New value: +1000
changedInput schema / properties / scrapeOptions / properties / waitFor / description
Previous value: -"Milliseconds to wait before capturing the page."New value: +"Milliseconds to wait before capturing a rendered page."
addedInput schema / properties / scrapeOptions / properties / waitFor / minimum
Added value: +0
changedInput schema / properties / scrapeOptions / properties / waitFor / type
Previous value: -"number"New value: +"integer"
removedInput schema / properties / scrapeOptions / properties / zeroDataRetention
Removed value: -{
- "type": "boolean"
-}
addedInput schema / properties / webhook / description
Added value: +"URL, or {url, headers, metadata, events}."
changedInput schema / properties / webhook / type
Previous value: -"string"New value: +[
+ "string",
+ "object"
+]
removedInput schema / properties / webhookHeaders
Removed value: -{
- "additionalProperties": {
- "type": "string"
- },
- "type": "object"
-}