diff --git a/agent-quickstart/elixir.mdx b/agent-quickstart/elixir.mdx
new file mode 100644
index 000000000..86c5266eb
--- /dev/null
+++ b/agent-quickstart/elixir.mdx
@@ -0,0 +1,234 @@
+---
+title: "Elixir Agent Quickstart"
+description: "Canonical Firecrawl Elixir quickstart for external agents using search, scrape, and interact."
+---
+
+# Firecrawl Elixir Agent Quickstart
+
+This file is the canonical quickstart for external agents integrating Firecrawl with Elixir. Generated from SDK source (`firecrawl` hex package v1.9) and the Firecrawl OpenAPI spec.
+
+The Elixir SDK is auto-generated from the Firecrawl OpenAPI spec. Function names match OpenAPI operation IDs.
+
+## Install
+
+Add to your `mix.exs`:
+
+```elixir
+defp deps do
+  [
+    {:firecrawl, "~> 1.4"}
+  ]
+end
+```
+
+## Authenticate
+
+Configure the API key globally in your application config:
+
+```elixir
+# config/config.exs
+config :firecrawl, api_key: "fc-YOUR_API_KEY"
+```
+
+Or pass it per-call:
+
+```elixir
+Firecrawl.scrape_and_extract_from_url([url: "https://example.com"], api_key: "fc-YOUR_API_KEY")
+```
+
+Additional per-call options:
+
+| Option | Type | Default | Description |
+|---|---|---|---|
+| `api_key` | `string` | Application config | Override API key for this request. |
+| `base_url` | `string` | `"https://api.firecrawl.dev/v2"` | Override base URL (self-hosted). |
+
+A nil API key is allowed — scrape, search, and interact fall back to a keyless free tier (rate-limited per IP).
+
+## When To Use What
+
+- **`search_and_scrape`**: Start with a query, discover relevant pages. Returns search results with optional scraping of each result.
+- **`scrape_and_extract_from_url`**: Start with a URL, get page content in markdown, HTML, or other formats.
+- **`interact_with_scrape_browser_session`**: Execute code in a browser session from a prior scrape. Use for post-scrape browser automation.
+
+## Search
+
+### Why use it
+
+Use `search_and_scrape` when you have a query and want to discover relevant web pages. Optionally scrape each result to get full page content.
+
+### Preferred SDK function
+
+```
+Firecrawl.search_and_scrape(params, opts)
+```
+
+Bang variant: `Firecrawl.search_and_scrape!(params, opts)` raises on error.
+
+### Example
+
+```elixir
+{:ok, response} = Firecrawl.search_and_scrape(
+  query: "firecrawl web scraping API",
+  limit: 5,
+  scrape_options: [formats: ["markdown"]]
+)
+
+for item <- response.body["data"]["web"] || [] do
+  IO.puts("#{item["url"]} #{String.slice(item["markdown"] || "", 0..200)}")
+end
+```
+
+### Parameters
+
+Parameters are passed as a keyword list. Validated at call time via NimbleOptions.
+
+| Parameter | Type | Description |
+|---|---|---|
+| `query` | `string` | Search query (required). |
+| `limit` | `integer` | Max results. |
+| `sources` | `list(any)` | Sources to search. |
+| `categories` | `list(any)` | Category filters. |
+| `include_domains` | `list(string)` | Restrict results to these domains. |
+| `exclude_domains` | `list(string)` | Exclude results from these domains. |
+| `tbs` | `string` | Time-based search filter (e.g. `"qdr:d"`). |
+| `location` | `string` | Location string for geo-targeted search. |
+| `country` | `string` | Country code (ISO). |
+| `timeout` | `integer` | Timeout in ms. |
+| `highlights` | `boolean` | Generate query-relevant highlights. Server default: `true`. |
+| `ignore_invalid_urls` | `boolean` | Skip invalid URLs. |
+| `enterprise` | `list(string)` | Enterprise options: `["zdr"]` or `["anon"]`. |
+| `scrape_options` | `keyword` | Options for scraping each result page (same params as scrape). |
+
+**Return type:** `{:ok, %Req.Response{}}` or `{:error, exception}`. The response body is a decoded JSON map.
+
+## Scrape
+
+### Why use it
+
+Use `scrape_and_extract_from_url` when you already have a URL and want page content as markdown, HTML, screenshots, structured JSON, or other formats.
+
+### Preferred SDK function
+
+```
+Firecrawl.scrape_and_extract_from_url(params, opts)
+```
+
+Bang variant: `Firecrawl.scrape_and_extract_from_url!(params, opts)` raises on error.
+
+### Example
+
+```elixir
+{:ok, response} = Firecrawl.scrape_and_extract_from_url(
+  url: "https://example.com",
+  formats: ["markdown", "links"],
+  only_main_content: true
+)
+
+data = response.body["data"]
+IO.puts(data["markdown"])
+IO.puts(data["metadata"]["title"])
+```
+
+### Parameters
+
+Parameters are passed as a keyword list.
+
+| Parameter | Type | Description |
+|---|---|---|
+| `url` | `string` | URL to scrape (required). |
+| `formats` | `list(any)` | Output formats: `"markdown"`, `"html"`, `"rawHtml"`, `"links"`, `"images"`, `"screenshot"`, `"json"`, `"changeTracking"`, `"branding"`, `"product"`, `"menu"`, `"audio"`, `"video"`, etc. |
+| `headers` | `any` | Custom HTTP headers. |
+| `include_tags` | `list(string)` | HTML tags to include. |
+| `exclude_tags` | `list(string)` | HTML tags to exclude. |
+| `only_main_content` | `boolean` | Only return main content. Server default: `true`. |
+| `timeout` | `integer` | Timeout in ms. Server default: `60000`. |
+| `wait_for` | `integer` | Wait time in ms before scraping. |
+| `mobile` | `boolean` | Emulate mobile device. |
+| `parsers` | `list(any)` | Parser configuration. |
+| `actions` | `list(any)` | Browser actions before scraping. Each is a keyword list or map with `type` key. |
+| `location` | `keyword` | Geolocation: `[country: "US", languages: ["en"]]`. |
+| `skip_tls_verification` | `boolean` | Skip TLS cert verification. |
+| `remove_base64_images` | `boolean` | Remove base64 images. |
+| `block_ads` | `boolean` | Block ads. Server default: `true`. |
+| `proxy` | `:basic \| :enhanced \| :auto` | Proxy mode. |
+| `max_age` | `integer` | Use cached result if younger than this (ms). |
+| `store_in_cache` | `boolean` | Cache the result. |
+| `lockdown` | `boolean` | Serve from cache only. |
+| `redact_pii` | `boolean` | Redact PII from output. |
+| `profile` | `keyword` | Persistent browser profile. |
+| `audit_metadata` | `keyword` | User attribution: `[username: "user"]`. |
+| `zero_data_retention` | `boolean` | Enable zero data retention. |
+
+**Return type:** `{:ok, %Req.Response{}}`. The response body `data` field is a map with `"markdown"`, `"html"`, `"metadata"`, `"links"`, etc.
+
+## Interact
+
+### Why use it
+
+Use `interact_with_scrape_browser_session` to execute code in the browser session from a prior scrape. The scrape must have returned a job ID. Use it for post-scrape automation.
+
+### Preferred SDK function
+
+```
+Firecrawl.interact_with_scrape_browser_session(job_id, params, opts)
+```
+
+Bang variant: `Firecrawl.interact_with_scrape_browser_session!(job_id, params, opts)` raises on error.
+
+### Example
+
+```elixir
+# First scrape to get a job_id
+{:ok, scrape_response} = Firecrawl.scrape_and_extract_from_url(
+  url: "https://example.com",
+  formats: ["markdown"]
+)
+job_id = scrape_response.body["data"]["metadata"]["jobId"]
+
+# Interact with the browser session
+{:ok, result} = Firecrawl.interact_with_scrape_browser_session(job_id,
+  code: "document.title",
+  language: :node
+)
+
+IO.puts(result.body["stdout"])
+IO.puts(result.body["result"])
+```
+
+### Parameters
+
+The first argument is `job_id` (string). Remaining parameters are passed as a keyword list.
+
+| Parameter | Type | Description |
+|---|---|---|
+| `job_id` | `string` | Scrape job ID (required, first positional argument). |
+| `code` | `string` | Code to execute (required). |
+| `language` | `:python \| :node \| :bash` | Language for code execution. Default: `"node"` (server-side). |
+| `timeout` | `integer` | Execution timeout in seconds. Server default: `30`. |
+
+**Return type:** `{:ok, %Req.Response{}}`. Body contains `"success"`, `"stdout"`, `"result"`, `"stderr"`, `"exitCode"`, `"killed"`, `"error"`.
+
+### Stop a session
+
+```elixir
+Firecrawl.stop_interactive_scrape_browser_session(job_id)
+```
+
+## Notes
+
+- **Auto-generated from OpenAPI**: Function names match OpenAPI operation IDs and are verbose (e.g. `scrape_and_extract_from_url` instead of `scrape`).
+- **snake_case in, camelCase out**: Pass snake_case keywords (e.g. `only_main_content: true`). They are automatically converted to camelCase JSON keys.
+- **NimbleOptions validation**: Parameters are validated at call time. Passing an unrecognized key or wrong type returns `{:error, %NimbleOptions.ValidationError{}}` immediately.
+- **Bang variants**: Every function `foo/n` has a `foo!/n` that raises `Firecrawl.Error` instead of returning `{:error, _}`.
+- **No client struct**: Unlike other SDKs, there is no connection object to create upfront. A fresh `Req` client is built per call.
+- **Response bodies are raw JSON maps**: No typed response structs — access data via map keys like `response.body["data"]["markdown"]`.
+- **No deprecated aliases**: The generated client has one function per operation.
+- **Keyless free tier**: Works without an API key (rate-limited per IP).
+- **Batch scraping**: `Firecrawl.scrape_and_extract_from_urls/2` is available for batch operations.
+
+## Source Of Truth
+
+- `/firecrawl/apps/elixir-sdk/lib/firecrawl.ex`
+- `/firecrawl/apps/elixir-sdk/mix.exs`
+- `/firecrawl-docs/api-reference/v2-openapi.json`
diff --git a/agent-quickstart/java.mdx b/agent-quickstart/java.mdx
new file mode 100644
index 000000000..e3f46bfe9
--- /dev/null
+++ b/agent-quickstart/java.mdx
@@ -0,0 +1,271 @@
+---
+title: "Java Agent Quickstart"
+description: "Canonical Firecrawl Java quickstart for external agents using search, scrape, and interact."
+---
+
+# Firecrawl Java Agent Quickstart
+
+This file is the canonical quickstart for external agents integrating Firecrawl with Java. Generated from SDK source (`firecrawl-java` v1.12) and the Firecrawl OpenAPI spec.
+
+## Install
+
+**Maven:**
+
+```xml
+<dependency>
+    <groupId>com.firecrawl</groupId>
+    <artifactId>firecrawl-java</artifactId>
+    <version>1.12.1</version>
+</dependency>
+```
+
+**Gradle (Kotlin DSL):**
+
+```kotlin
+implementation("com.firecrawl:firecrawl-java:1.12.1")
+```
+
+Requires Java 11+.
+
+## Authenticate
+
+```java
+import com.firecrawl.client.FirecrawlClient;
+
+// Builder pattern (preferred)
+FirecrawlClient client = FirecrawlClient.builder()
+    .apiKey("fc-YOUR_API_KEY")
+    .build();
+
+// From environment (FIRECRAWL_API_KEY env var or firecrawl.apiKey system property)
+FirecrawlClient client = FirecrawlClient.fromEnv();
+```
+
+Builder options:
+
+| Option | Type | Default | Description |
+|---|---|---|---|
+| `apiKey` | `String` | `FIRECRAWL_API_KEY` env var or `firecrawl.apiKey` system property | API key. Null allowed for keyless free tier. |
+| `apiUrl` | `String` | `"https://api.firecrawl.dev"` | API base URL. Also reads `FIRECRAWL_API_URL` env var. |
+| `timeoutMs` | `long` | `300000` | Per-request timeout in ms. |
+| `maxRetries` | `int` | `3` | Max retries for failed requests. |
+| `backoffFactor` | `double` | `0.5` | Exponential backoff factor. |
+| `asyncExecutor` | `Executor` | `ForkJoinPool.commonPool()` | Executor for async methods. |
+| `httpClient` | `OkHttpClient` | auto-created | Custom OkHttp client (overrides `timeoutMs`). |
+
+## When To Use What
+
+- **`search`**: Start with a query, discover relevant pages. Returns search results with optional scraping of each result.
+- **`scrape`**: Start with a URL, get page content in markdown, HTML, or other formats.
+- **`interact`**: Execute code in a browser session from a prior scrape. Use for post-scrape browser automation.
+
+## Search
+
+### Why use it
+
+Use `search` when you have a query and want to discover relevant web pages. Optionally scrape each result to get full page content.
+
+### Preferred SDK method
+
+```
+client.search(query)
+client.search(query, options)
+```
+
+### Example
+
+```java
+import com.firecrawl.models.SearchOptions;
+import com.firecrawl.models.ScrapeOptions;
+import com.firecrawl.models.SearchData;
+
+SearchData results = client.search("firecrawl web scraping API",
+    SearchOptions.builder()
+        .limit(5)
+        .scrapeOptions(ScrapeOptions.builder()
+            .formats(List.of("markdown"))
+            .build())
+        .build());
+
+for (Map<String, Object> item : results.getWeb()) {
+    System.out.println(item.get("url") + " " + item.get("markdown"));
+}
+```
+
+### Parameters
+
+All fields on `SearchOptions` are nullable and omitted from the request when null.
+
+| Parameter | Type | Description |
+|---|---|---|
+| `query` | `String` | Search query (required, first argument). |
+| `sources` | `List<Object>` | Sources: strings like `"web"`, `"news"`, `"images"`, or `{type: "web"}` maps. |
+| `categories` | `List<Object>` | Category filters: `"github"`, `"research"`, `"pdf"`. |
+| `includeDomains` | `List<String>` | Restrict results to these domains. |
+| `excludeDomains` | `List<String>` | Exclude results from these domains. |
+| `limit` | `Integer` | Max results. |
+| `tbs` | `String` | Time-based filter (e.g. `"qdr:d"` for past day). |
+| `location` | `String` | Location string for geo-targeted search. |
+| `ignoreInvalidURLs` | `Boolean` | Skip invalid URLs. |
+| `timeout` | `Integer` | Timeout in ms. |
+| `highlights` | `Boolean` | Generate query-relevant highlights. Server default: `true`. |
+| `scrapeOptions` | `ScrapeOptions` | Options for scraping each result page. |
+| `integration` | `String` | Integration identifier. |
+
+**Return type:** `SearchData` with `getWeb()`, `getNews()`, `getImages()` returning `List<Map<String, Object>>`.
+
+### Async variant
+
+```java
+CompletableFuture<SearchData> future = client.searchAsync("query", options);
+```
+
+## Scrape
+
+### Why use it
+
+Use `scrape` when you already have a URL and want page content as markdown, HTML, screenshots, structured JSON, or other formats.
+
+### Preferred SDK method
+
+```
+client.scrape(url)
+client.scrape(url, options)
+```
+
+### Example
+
+```java
+import com.firecrawl.models.ScrapeOptions;
+import com.firecrawl.models.Document;
+
+Document doc = client.scrape("https://example.com",
+    ScrapeOptions.builder()
+        .formats(List.of("markdown", "links"))
+        .onlyMainContent(true)
+        .build());
+
+System.out.println(doc.getMarkdown());
+System.out.println(doc.getMetadata().get("title"));
+```
+
+### Parameters
+
+All fields on `ScrapeOptions` are nullable and omitted when null.
+
+| Parameter | Type | Description |
+|---|---|---|
+| `url` | `String` | URL to scrape (required, first argument). |
+| `formats` | `List<Object>` | Output formats. Strings: `"markdown"`, `"html"`, `"rawHtml"`, `"links"`, `"images"`, `"screenshot"`, `"summary"`, `"json"`, `"audio"`, `"video"`, `"product"`, `"menu"`. Also accepts format config objects (`JsonFormat`, `QuestionFormat`, `HighlightsFormat`). |
+| `headers` | `Map<String, String>` | Custom HTTP headers. |
+| `includeTags` | `List<String>` | HTML tags to include. |
+| `excludeTags` | `List<String>` | HTML tags to exclude. |
+| `onlyMainContent` | `Boolean` | Only return main content. Server default: `true`. |
+| `timeout` | `Integer` | Timeout in ms. Server default: `60000`. |
+| `waitFor` | `Integer` | Wait time in ms before scraping. Server default: `0`. |
+| `mobile` | `Boolean` | Emulate mobile device. |
+| `parsers` | `List<Object>` | Parser configuration (e.g. PDF handling). |
+| `actions` | `List<Map<String, Object>>` | Browser actions before scraping. |
+| `location` | `LocationConfig` | Geolocation: `LocationConfig.builder().country("US").languages(List.of("en")).build()`. |
+| `skipTlsVerification` | `Boolean` | Skip TLS cert verification. |
+| `removeBase64Images` | `Boolean` | Remove base64 images. |
+| `blockAds` | `Boolean` | Block ads. Server default: `true`. |
+| `proxy` | `String` | Proxy mode: `"basic"`, `"stealth"`, `"enhanced"`, `"auto"`. |
+| `maxAge` | `Long` | Use cached result if younger than this (ms). |
+| `storeInCache` | `Boolean` | Cache the result. |
+| `lockdown` | `Boolean` | Serve from cache only. |
+| `redactPII` | `Boolean` | Redact PII from output. |
+| `auditMetadata` | `AuditMetadata` | User attribution for SIEM logging. |
+| `integration` | `String` | Integration identifier. |
+
+**Return type:** `Document` with getters: `getMarkdown()`, `getHtml()`, `getRawHtml()`, `getJson()`, `getSummary()`, `getMetadata()`, `getLinks()`, `getImages()`, `getScreenshot()`, `getAudio()`, `getVideo()`, `getActions()`, `getAnswer()`, `getHighlights()`, `getWarning()`, `getChangeTracking()`, `getBranding()`, `getProduct()`, `getMenu()`.
+
+### Async variant
+
+```java
+CompletableFuture<Document> future = client.scrapeAsync("https://example.com", options);
+```
+
+## Interact
+
+### Why use it
+
+Use `interact` to execute code in the browser session from a prior scrape. The scrape must have returned a job ID (in the response metadata). Use it for post-scrape automation.
+
+### Preferred SDK method
+
+```
+client.interact(jobId, code)
+client.interact(jobId, code, language, timeout)
+```
+
+### Example
+
+```java
+import com.firecrawl.models.BrowserExecuteResponse;
+
+// First scrape to get a jobId
+Document doc = client.scrape("https://example.com",
+    ScrapeOptions.builder().formats(List.of("markdown")).build());
+String jobId = (String) doc.getMetadata().get("scrapeId");
+
+// Interact with the browser session
+BrowserExecuteResponse result = client.interact(jobId, "document.title");
+
+System.out.println(result.getStdout());
+System.out.println(result.getResult());
+```
+
+### Parameters
+
+| Parameter | Type | Description |
+|---|---|---|
+| `jobId` | `String` | Scrape job ID (required). |
+| `code` | `String` | Code to execute (required). |
+| `language` | `String` | Language: `"python"`, `"node"`, `"bash"`. Default: `"node"`. |
+| `timeout` | `Integer` | Execution timeout in seconds. Server default: `30`. |
+| `origin` | `String` | Origin tag. Auto-set to `"java-sdk@1.12.1"`. |
+
+**Return type:** `BrowserExecuteResponse` with fields: `success`, `stdout`, `result`, `stderr`, `exitCode`, `killed`, `error`.
+
+### Overloads
+
+```java
+// Minimal
+client.interact(jobId, code);
+
+// With language and timeout
+client.interact(jobId, code, "node", 60);
+
+// Full
+client.interact(jobId, code, "node", 60, "my-origin");
+```
+
+### Stop a session
+
+```java
+client.stopInteractiveBrowser(jobId);
+```
+
+### Async variants
+
+```java
+CompletableFuture<BrowserExecuteResponse> future = client.interactAsync(jobId, code);
+```
+
+## Notes
+
+- **camelCase** parameter names throughout (e.g. `onlyMainContent`, `includeTags`, `waitFor`).
+- **Builder pattern** on all option classes: `ScrapeOptions.builder()...build()`, `SearchOptions.builder()...build()`.
+- **Method overloads**: Most methods have a minimal version (just required args) and a full version (with options).
+- **Checked exceptions**: All sync methods throw `FirecrawlException`. Subclasses: `AuthenticationException` (401), `RateLimitException` (429), `JobTimeoutException`.
+- **Deprecated aliases**: `scrapeExecute` → `interact`, `deleteScrapeBrowser` → `stopInteractiveBrowser`.
+- **Weakly typed search results**: `SearchData` returns `List<Map<String, Object>>`, not typed model classes.
+- **Keyless free tier**: Scrape, search, and interact work without an API key (rate-limited per IP).
+- **The `jobId` for interact** is obtained from `doc.getMetadata().get("scrapeId")` after a scrape.
+
+## Source Of Truth
+
+- `/firecrawl/apps/java-sdk/src/main/java/com/firecrawl/client/FirecrawlClient.java`
+- `/firecrawl/apps/java-sdk/src/main/java/com/firecrawl/models/` (ScrapeOptions, SearchOptions, Document, etc.)
+- `/firecrawl-docs/api-reference/v2-openapi.json`
diff --git a/agent-quickstart/node.mdx b/agent-quickstart/node.mdx
new file mode 100644
index 000000000..30f5b1b82
--- /dev/null
+++ b/agent-quickstart/node.mdx
@@ -0,0 +1,213 @@
+---
+title: "Node.js Agent Quickstart"
+description: "Canonical Firecrawl Node.js quickstart for external agents using search, scrape, and interact."
+---
+
+# Firecrawl Node.js Agent Quickstart
+
+This file is the canonical quickstart for external agents integrating Firecrawl with Node.js/TypeScript. Generated from SDK source (`@mendable/firecrawl-js` v4) and the Firecrawl OpenAPI spec.
+
+## Install
+
+```bash
+npm install @mendable/firecrawl-js
+```
+
+Requires Node >= 22.
+
+## Authenticate
+
+```javascript
+import Firecrawl from "@mendable/firecrawl-js";
+
+const client = new Firecrawl("fc-YOUR_API_KEY");
+// or use FIRECRAWL_API_KEY env var:
+const client = new Firecrawl();
+```
+
+Constructor options:
+
+| Option | Type | Default | Description |
+|---|---|---|---|
+| `apiKey` | `string \| null` | `process.env.FIRECRAWL_API_KEY` | API key. Omit for keyless free tier. |
+| `apiUrl` | `string \| null` | `"https://api.firecrawl.dev"` | API base URL. |
+| `timeoutMs` | `number` | `300000` | Per-request timeout in ms. |
+| `maxRetries` | `number` | `3` | Max retries on 502 errors. |
+| `backoffFactor` | `number` | `0.5` | Exponential backoff factor in seconds. |
+
+## When To Use What
+
+- **`search`**: Start with a query, discover relevant pages. Returns search results with optional scraping of each result.
+- **`scrape`**: Start with a URL, get page content in markdown, HTML, or other formats.
+- **`interact`**: Execute code or send a prompt in a browser session from a prior scrape. Use for post-scrape browser automation.
+
+## Search
+
+### Why use it
+
+Use `search` when you have a query and want to discover relevant web pages. Optionally scrape each result to get full page content.
+
+### Preferred SDK method
+
+```
+client.search(query, options?)
+```
+
+### Example
+
+```javascript
+const results = await client.search("firecrawl web scraping API", {
+  limit: 5,
+  scrapeOptions: { formats: ["markdown"] },
+});
+
+for (const item of results.web ?? []) {
+  console.log(item.url, item.markdown?.slice(0, 200));
+}
+```
+
+### Parameters
+
+| Parameter | Type | Description |
+|---|---|---|
+| `query` | `string` | Search query (required, first argument). |
+| `sources` | `Array<"web" \| "news" \| "images" \| { type: string }>` | Result sources to include. Determines which arrays appear in the response. |
+| `categories` | `Array<"github" \| "research" \| "pdf" \| "developer">` | Category filters for results. |
+| `includeDomains` | `string[]` | Restrict results to these domains. Cannot combine with `excludeDomains`. |
+| `excludeDomains` | `string[]` | Exclude results from these domains. Cannot combine with `includeDomains`. |
+| `limit` | `number` | Max results. Must be positive. |
+| `tbs` | `string` | Time-based search filter (e.g. `"qdr:d"` for past day, `"qdr:w"` for past week). |
+| `location` | `string` | Location string for geo-targeted search. |
+| `ignoreInvalidURLs` | `boolean` | Skip invalid URLs instead of erroring. |
+| `timeout` | `number` | Timeout in ms. Must be positive. |
+| `highlights` | `boolean` | Generate query-relevant highlights. Server default: `true`. |
+| `scrapeOptions` | `ScrapeOptions` | Options for scraping each result page. Same options as `scrape`. |
+| `enterprise` | `Array<"default" \| "anon" \| "zdr">` | Enterprise search modes. Must be enabled for your team. |
+| `threatProtection` | `object` | Per-request threat protection overrides (enterprise). |
+| `integration` | `string` | Integration identifier. |
+
+**Return type:** `SearchData` with properties `web`, `news`, `images`, `developer` (arrays, depending on `sources`). Do **not** access `.data` — it throws an error.
+
+## Scrape
+
+### Why use it
+
+Use `scrape` when you already have a URL and want page content as markdown, HTML, screenshots, structured JSON, or other formats.
+
+### Preferred SDK method
+
+```
+client.scrape(url, options?)
+```
+
+### Example
+
+```javascript
+const doc = await client.scrape("https://example.com", {
+  formats: ["markdown", "links"],
+  onlyMainContent: true,
+});
+
+console.log(doc.markdown);
+console.log(doc.metadata?.title);
+```
+
+### Parameters
+
+| Parameter | Type | Description |
+|---|---|---|
+| `url` | `string` | URL to scrape (required, first argument). |
+| `formats` | `FormatOption[]` | Output formats. Strings: `"markdown"`, `"html"`, `"rawHtml"`, `"links"`, `"images"`, `"screenshot"`, `"summary"`, `"changeTracking"`, `"attributes"`, `"branding"`, `"product"`, `"menu"`, `"audio"`, `"video"`. Objects: `{ type: "json", prompt?, schema? }`, `{ type: "screenshot", fullPage?, quality?, viewport? }`, `{ type: "question", question }`, `{ type: "highlights", query }`, `{ type: "changeTracking", modes, schema?, prompt?, tag? }`, `{ type: "attributes", selectors }`. Note: `"json"` as a bare string throws — use the object form. |
+| `headers` | `Record<string, string>` | Custom HTTP headers. |
+| `includeTags` | `string[]` | HTML tags to include. |
+| `excludeTags` | `string[]` | HTML tags to exclude. |
+| `onlyMainContent` | `boolean` | Only return main content, excluding headers/navs/footers. Server default: `true`. |
+| `timeout` | `number` | Timeout in ms. Range: 1000–300000. Server default: `60000`. |
+| `waitFor` | `number` | Wait time in ms before scraping. Server default: `0`. |
+| `mobile` | `boolean` | Emulate mobile device. Server default: `false`. |
+| `parsers` | `Array<string \| { type: "pdf", mode?, maxPages? }>` | Parser configuration (e.g. PDF handling). |
+| `actions` | `ActionOption[]` | Browser actions before scraping: `wait`, `click`, `write`, `press`, `scroll`, `screenshot`, `scrape`, `executeJavascript`, `pdf`. |
+| `location` | `{ country?: string, languages?: string[] }` | Geolocation settings. |
+| `skipTlsVerification` | `boolean` | Skip TLS cert verification. Server default: `true`. |
+| `removeBase64Images` | `boolean` | Remove base64 images. Server default: `true`. |
+| `fastMode` | `boolean` | Enable fast mode. |
+| `blockAds` | `boolean` | Block ads. Server default: `true`. |
+| `proxy` | `"basic" \| "stealth" \| "enhanced" \| "auto"` | Proxy mode. Server default: `"auto"`. |
+| `maxAge` | `number` | Use cached result if younger than this (ms). Server default: `172800000` (2 days). |
+| `storeInCache` | `boolean` | Cache the result. Server default: `true`. |
+| `lockdown` | `boolean` | Serve from cache only; never make outbound requests. |
+| `redactPII` | `boolean \| RedactPIIOptions` | Redact PII from output. |
+| `profile` | `{ name: string, saveChanges?: boolean }` | Persistent browser profile. |
+| `threatProtection` | `object` | Per-request threat protection overrides (enterprise). |
+| `auditMetadata` | `{ username: string }` | User attribution for SIEM logging. |
+| `integration` | `string` | Integration identifier. |
+
+**Return type:** `Document` with optional fields: `markdown`, `html`, `rawHtml`, `json`, `summary`, `metadata`, `links`, `images`, `screenshot`, `audio`, `video`, `actions`, `answer`, `highlights`, `warning`, `changeTracking`, `branding`, `product`, `menu`.
+
+## Interact
+
+### Why use it
+
+Use `interact` to execute code or send a natural-language prompt in the browser session from a prior scrape. The scrape must have returned a `jobId` (available in the response metadata). Use it for post-scrape browser automation — clicking, filling forms, navigating, or running arbitrary JavaScript.
+
+### Preferred SDK method
+
+```
+client.interact(jobId, args)
+```
+
+### Example
+
+```javascript
+// First scrape to get a jobId
+const doc = await client.scrape("https://example.com", {
+  formats: ["markdown"],
+});
+const jobId = doc.metadata?.jobId;
+
+// Then interact with the browser session
+const result = await client.interact(jobId, {
+  code: "document.title",
+  language: "node",
+});
+
+console.log(result.stdout);
+console.log(result.result);
+```
+
+### Parameters
+
+The second argument is a `ScrapeExecuteRequest` object:
+
+| Parameter | Type | Description |
+|---|---|---|
+| `jobId` | `string` | Scrape job ID (required, first argument). |
+| `code` | `string` | Code to execute. At least one of `code` or `prompt` is required. |
+| `prompt` | `string` | Natural-language instruction for the browser agent. At least one of `code` or `prompt` is required. |
+| `language` | `"python" \| "node" \| "bash"` | Language for code execution. Default: `"node"`. |
+| `timeout` | `number` | Execution timeout in seconds. Range: 1–300. Server default: `30`. |
+
+**Return type:** `ScrapeExecuteResponse` with fields: `success`, `stdout`, `result`, `stderr`, `exitCode`, `killed`, `error`, `cdpUrl`, `liveViewUrl`, `interactiveLiveViewUrl`, `output`.
+
+### Stop a session
+
+```javascript
+await client.stopInteraction(jobId);
+```
+
+## Notes
+
+- **camelCase** parameter names throughout (e.g. `onlyMainContent`, `includeTags`, `waitFor`).
+- **Deprecated aliases**: `scrapeUrl` → `scrape`, `scrapeExecute` → `interact`, `stopInteractiveBrowser` / `deleteScrapeBrowser` → `stopInteraction`. Use the preferred names.
+- **`"json"` format caveat**: Passing `"json"` as a bare string in `formats` throws an error. Use `{ type: "json", prompt: "...", schema: ... }` with at least one of `prompt` or `schema`. Zod schemas are auto-converted to JSON Schema.
+- **`SearchData.data` trap**: Accessing `.data` on search results throws an error. Use `.web`, `.news`, `.images`, or `.developer` instead.
+- **Keyless free tier**: Scrape, search, and interact work without an API key (rate-limited per IP).
+
+## Source Of Truth
+
+- `/firecrawl/apps/js-sdk/firecrawl/src/index.ts`
+- `/firecrawl/apps/js-sdk/firecrawl/src/v2/client.ts`
+- `/firecrawl/apps/js-sdk/firecrawl/src/v2/types.ts`
+- `/firecrawl/apps/js-sdk/firecrawl/src/v2/methods/scrape.ts`
+- `/firecrawl/apps/js-sdk/firecrawl/src/v2/methods/search.ts`
+- `/firecrawl-docs/api-reference/v2-openapi.json`
diff --git a/agent-quickstart/python.mdx b/agent-quickstart/python.mdx
new file mode 100644
index 000000000..07e9ed434
--- /dev/null
+++ b/agent-quickstart/python.mdx
@@ -0,0 +1,214 @@
+---
+title: "Python Agent Quickstart"
+description: "Canonical Firecrawl Python quickstart for external agents using search, scrape, and interact."
+---
+
+# Firecrawl Python Agent Quickstart
+
+This file is the canonical quickstart for external agents integrating Firecrawl with Python. Generated from SDK source (`firecrawl-py` v4) and the Firecrawl OpenAPI spec.
+
+## Install
+
+```bash
+pip install firecrawl-py
+```
+
+## Authenticate
+
+```python
+from firecrawl import Firecrawl
+
+client = Firecrawl(api_key="fc-YOUR_API_KEY")
+# or use FIRECRAWL_API_KEY env var:
+client = Firecrawl()
+```
+
+Constructor parameters:
+
+| Parameter | Type | Default | Description |
+|---|---|---|---|
+| `api_key` | `str` | `FIRECRAWL_API_KEY` env var | API key. Omit for keyless free tier. |
+| `api_url` | `str` | `"https://api.firecrawl.dev"` | API base URL. |
+| `timeout` | `float` | `None` | Default request timeout in seconds. |
+| `max_retries` | `int` | `3` | Max retries for failed requests. |
+| `backoff_factor` | `float` | `0.5` | Exponential backoff factor. |
+
+An async variant is also available: `from firecrawl import AsyncFirecrawl`.
+
+## When To Use What
+
+- **`search`**: Start with a query, discover relevant pages. Returns search results with optional scraping of each result.
+- **`scrape`**: Start with a URL, get page content in markdown, HTML, or other formats.
+- **`interact`**: Execute code or send a prompt in a browser session from a prior scrape. Use for post-scrape browser automation.
+
+## Search
+
+### Why use it
+
+Use `search` when you have a query and want to discover relevant web pages. Optionally scrape each result to get full page content.
+
+### Preferred SDK method
+
+```
+client.search(query, **kwargs)
+```
+
+### Example
+
+```python
+results = client.search(
+    "firecrawl web scraping API",
+    limit=5,
+    scrape_options={"formats": ["markdown"]},
+)
+
+for item in results.web or []:
+    print(item.url, item.markdown[:200] if item.markdown else "")
+```
+
+### Parameters
+
+All parameters except `query` are keyword-only.
+
+| Parameter | Type | Description |
+|---|---|---|
+| `query` | `str` | Search query (required, positional). |
+| `sources` | `list[SourceOption]` | Search sources (e.g. `"web"`, `"news"`, `"images"`). |
+| `categories` | `list[CategoryOption]` | Category filters: `"github"`, `"research"`, `"pdf"`, `"developer"`. |
+| `include_domains` | `list[str]` | Restrict results to these domains. Cannot combine with `exclude_domains`. |
+| `exclude_domains` | `list[str]` | Exclude results from these domains. Cannot combine with `include_domains`. |
+| `limit` | `int` | Max results. Default applied during serialization: `5`. |
+| `tbs` | `str` | Time-based search filter (e.g. `"qdr:d"` for past day). |
+| `location` | `str` | Location string for geo-targeted search. Note: this is a plain string, unlike `scrape`'s `Location` object. |
+| `ignore_invalid_urls` | `bool` | Skip invalid URLs instead of failing. |
+| `timeout` | `int` | Timeout in ms. Default applied during serialization: `300000`. |
+| `highlights` | `bool` | Generate query-relevant highlights. Server default: `True`. |
+| `scrape_options` | `ScrapeOptions \| dict` | Options for scraping each result page. |
+| `enterprise` | `list[str]` | Enterprise options: `["zdr"]` or `["anon"]`. Must be enabled for your team. |
+| `threat_protection` | `ThreatProtectionOptions` | Per-request threat protection overrides (enterprise). |
+| `integration` | `str` | Integration identifier. |
+
+**Return type:** `SearchData` with attributes `web`, `news`, `images`, `developer` (lists). Do **not** access `.data` — it raises `AttributeError` with a helpful message.
+
+## Scrape
+
+### Why use it
+
+Use `scrape` when you already have a URL and want page content as markdown, HTML, screenshots, structured JSON, or other formats.
+
+### Preferred SDK method
+
+```
+client.scrape(url, **kwargs)
+```
+
+### Example
+
+```python
+doc = client.scrape(
+    "https://example.com",
+    formats=["markdown", "links"],
+    only_main_content=True,
+)
+
+print(doc.markdown)
+print(doc.metadata.title if doc.metadata else "")
+```
+
+### Parameters
+
+All parameters except `url` are keyword-only.
+
+| Parameter | Type | Description |
+|---|---|---|
+| `url` | `str` | URL to scrape (required, positional). |
+| `formats` | `list[FormatOption]` | Output formats: `"markdown"`, `"html"`, `"rawHtml"`, `"links"`, `"images"`, `"screenshot"`, `"summary"`, `"json"`, `"changeTracking"`, `"attributes"`, `"branding"`, `"product"`, `"menu"`, `"audio"`, `"video"`. Also accepts format config dicts for `json`, `screenshot`, `question`, `highlights`, `changeTracking`, `attributes`. |
+| `headers` | `dict[str, str]` | Custom HTTP headers. |
+| `include_tags` | `list[str]` | HTML tags to include. |
+| `exclude_tags` | `list[str]` | HTML tags to exclude. |
+| `only_main_content` | `bool` | Only return main content. Server default: `True`. |
+| `timeout` | `int` | Timeout in ms. Server default: `60000`. |
+| `wait_for` | `int` | Wait time in ms before scraping. Server default: `0`. |
+| `mobile` | `bool` | Emulate mobile device. Server default: `False`. |
+| `parsers` | `list` | Parser configuration (e.g. `["pdf"]` or `[PDFParser(mode="ocr")]`). |
+| `actions` | `list[Action]` | Browser actions before scraping: `WaitAction`, `ClickAction`, `WriteAction`, `PressAction`, `ScrollAction`, `ScreenshotAction`, `ScrapeAction`, `ExecuteJavascriptAction`, `PDFAction`. |
+| `location` | `Location` | Geolocation settings. `Location(country="US", languages=["en"])`. |
+| `skip_tls_verification` | `bool` | Skip TLS cert verification. Server default: `True`. |
+| `remove_base64_images` | `bool` | Remove base64 images. Server default: `True`. |
+| `fast_mode` | `bool` | Enable fast mode. |
+| `block_ads` | `bool` | Block ads. Server default: `True`. |
+| `proxy` | `str` | Proxy mode: `"basic"`, `"stealth"`, `"enhanced"`, `"auto"`. Server default: `"auto"`. |
+| `max_age` | `int` | Use cached result if younger than this (ms). Server default: `172800000`. |
+| `store_in_cache` | `bool` | Cache the result. Server default: `True`. |
+| `lockdown` | `bool` | Serve from cache only; never make outbound requests. |
+| `profile` | `dict` | Persistent browser profile: `{"name": "my-profile", "saveChanges": True}`. |
+| `audit_metadata` | `AuditMetadata` | User attribution for SIEM logging. |
+| `threat_protection` | `ThreatProtectionOptions` | Per-request threat protection overrides (enterprise). |
+| `integration` | `str` | Integration identifier. |
+
+**Return type:** `Document` (Pydantic model) with fields: `markdown`, `html`, `raw_html`, `json`, `summary`, `metadata`, `links`, `images`, `screenshot`, `audio`, `video`, `actions`, `answer`, `highlights`, `warning`, `change_tracking`, `branding`, `product`, `menu`.
+
+## Interact
+
+### Why use it
+
+Use `interact` to execute code or send a natural-language prompt in the browser session from a prior scrape. The scrape must have returned a `jobId` (in `metadata`). Use it for post-scrape automation — clicking, filling forms, navigating, or running arbitrary code.
+
+### Preferred SDK method
+
+```
+client.interact(job_id, code=None, *, prompt=None, language="node", timeout=None)
+```
+
+### Example
+
+```python
+# First scrape to get a job_id
+doc = client.scrape("https://example.com", formats=["markdown"])
+job_id = doc.metadata.scrape_id if doc.metadata else None
+
+# Then interact with the browser session
+result = client.interact(
+    job_id,
+    code="document.title",
+    language="node",
+)
+
+print(result.stdout)
+print(result.result)
+```
+
+### Parameters
+
+| Parameter | Type | Description |
+|---|---|---|
+| `job_id` | `str` | Scrape job ID (required, positional). |
+| `code` | `str \| None` | Code to execute (positional). At least one of `code` or `prompt` required. |
+| `prompt` | `str \| None` | Natural-language instruction for the browser agent. At least one of `code` or `prompt` required. |
+| `language` | `"python" \| "node" \| "bash"` | Language for code execution. Default: `"node"`. |
+| `timeout` | `int \| None` | Execution timeout in seconds. Range: 1–300. Server default: `30`. |
+
+**Return type:** `BrowserExecuteResponse` with fields: `success`, `stdout`, `result`, `stderr`, `exit_code`, `killed`, `error`, `output`, `cdp_url`, `live_view_url`, `interactive_live_view_url`.
+
+### Stop a session
+
+```python
+client.stop_interaction(job_id)
+```
+
+## Notes
+
+- **snake_case** parameter names throughout (e.g. `only_main_content`, `include_tags`, `wait_for`, `skip_tls_verification`).
+- **Deprecated aliases**: `scrape_url` → `scrape`, `scrape_execute` → `interact`, `stop_interactive_browser` / `delete_scrape_browser` → `stop_interaction`. Use the preferred names.
+- **`code` is positional** in `interact()`: you can call `client.interact(job_id, "some_code")` without naming the parameter.
+- **`SearchData.data` trap**: Accessing `.data` on search results raises `AttributeError`. Use `.web`, `.news`, `.images`, or `.developer` instead.
+- **`location` differs by endpoint**: In `scrape()`, `location` is a `Location` object (with `country` and `languages`). In `search()`, it is a plain `str`.
+- **Keyless free tier**: Scrape, search, and interact work without an API key (rate-limited per IP).
+- Legacy alias `FirecrawlApp` is available but `Firecrawl` is preferred.
+
+## Source Of Truth
+
+- `/firecrawl/apps/python-sdk/firecrawl/client.py`
+- `/firecrawl/apps/python-sdk/firecrawl/v2/client.py`
+- `/firecrawl/apps/python-sdk/firecrawl/v2/types.py`
+- `/firecrawl-docs/api-reference/v2-openapi.json`
diff --git a/agent-quickstart/rust.mdx b/agent-quickstart/rust.mdx
new file mode 100644
index 000000000..62b930721
--- /dev/null
+++ b/agent-quickstart/rust.mdx
@@ -0,0 +1,253 @@
+---
+title: "Rust Agent Quickstart"
+description: "Canonical Firecrawl Rust quickstart for external agents using search, scrape, and interact."
+---
+
+# Firecrawl Rust Agent Quickstart
+
+This file is the canonical quickstart for external agents integrating Firecrawl with Rust. Generated from SDK source (`firecrawl` crate v2) and the Firecrawl OpenAPI spec.
+
+## Install
+
+Add to your `Cargo.toml`:
+
+```toml
+[dependencies]
+firecrawl = "2"
+tokio = { version = "1", features = ["full"] }
+```
+
+## Authenticate
+
+```rust
+use firecrawl::Client;
+
+// With API key
+let client = Client::new("fc-YOUR_API_KEY")?;
+
+// With custom API URL (self-hosted)
+let client = Client::new_selfhosted(
+    "https://your-firecrawl.example.com",
+    Some("fc-YOUR_API_KEY"),
+)?;
+
+// Keyless free tier (rate-limited per IP)
+let client = Client::new_selfhosted("https://api.firecrawl.dev", None::<&str>)?;
+```
+
+## When To Use What
+
+- **`search`**: Start with a query, discover relevant pages. Returns search results with optional scraping of each result.
+- **`scrape`**: Start with a URL, get page content in markdown, HTML, or other formats.
+- **`interact`**: Execute code or send a prompt in a browser session from a prior scrape. Use for post-scrape browser automation.
+
+## Search
+
+### Why use it
+
+Use `search` when you have a query and want to discover relevant web pages. Optionally scrape each result to get full page content.
+
+### Preferred SDK method
+
+```
+client.search(query, options).await
+```
+
+### Example
+
+```rust
+use firecrawl::{Client, SearchOptions, ScrapeOptions, Format};
+
+let client = Client::new("fc-YOUR_API_KEY")?;
+
+let response = client.search("firecrawl web scraping API", SearchOptions {
+    limit: Some(5),
+    scrape_options: Some(ScrapeOptions {
+        formats: Some(vec![Format::Markdown]),
+        ..Default::default()
+    }),
+    ..Default::default()
+}).await?;
+
+if let Some(web) = &response.data.web {
+    for item in web {
+        println!("{:?}", item);
+    }
+}
+```
+
+### Parameters
+
+All fields on `SearchOptions` are `Option<T>` and default to `None` (omitted from request).
+
+| Parameter | Type | Description |
+|---|---|---|
+| `query` | `&str` | Search query (required, first argument). |
+| `limit` | `Option<u32>` | Max results. Server default: `10`. |
+| `sources` | `Option<Vec<SearchSource>>` | Sources: `SearchSource::Web`, `News`, `Images`. |
+| `categories` | `Option<Vec<SearchCategory>>` | Categories: `SearchCategory::Github`, `Research`, `Pdf`. |
+| `include_domains` | `Option<Vec<String>>` | Restrict results to these domains. |
+| `exclude_domains` | `Option<Vec<String>>` | Exclude results from these domains. |
+| `tbs` | `Option<String>` | Time-based filter (e.g. `"qdr:d"`). |
+| `location` | `Option<String>` | Location string for geo-targeted search. |
+| `ignore_invalid_urls` | `Option<bool>` | Skip invalid URLs. |
+| `timeout` | `Option<u32>` | Timeout in ms. |
+| `highlights` | `Option<bool>` | Generate query-relevant highlights. Server default: `true`. |
+| `scrape_options` | `Option<ScrapeOptions>` | Options for scraping each result page. |
+| `integration` | `Option<String>` | Integration identifier. |
+
+**Return type:** `SearchResponse` with `success: bool`, `data: SearchData`, `warning: Option<String>`. `SearchData` has `web: Option<Vec<SearchResultOrDocument>>`, `news`, `images`.
+
+### Convenience method
+
+```rust
+let docs = client.search_and_scrape("query", 5).await?;
+```
+
+Calls `search` with default `ScrapeOptions` and returns only `Document` results.
+
+## Scrape
+
+### Why use it
+
+Use `scrape` when you already have a URL and want page content as markdown, HTML, screenshots, structured JSON, or other formats.
+
+### Preferred SDK method
+
+```
+client.scrape(url, options).await
+```
+
+### Example
+
+```rust
+use firecrawl::{Client, ScrapeOptions, Format};
+
+let client = Client::new("fc-YOUR_API_KEY")?;
+
+let doc = client.scrape("https://example.com", ScrapeOptions {
+    formats: Some(vec![Format::Markdown, Format::Links]),
+    only_main_content: Some(true),
+    ..Default::default()
+}).await?;
+
+println!("{}", doc.markdown.unwrap_or_default());
+```
+
+### Parameters
+
+All fields on `ScrapeOptions` are `Option<T>` and default to `None`.
+
+| Parameter | Type | Description |
+|---|---|---|
+| `url` | `&str` | URL to scrape (required, first argument). |
+| `formats` | `Option<Vec<Format>>` | Output formats. Enum variants: `Markdown`, `Html`, `RawHtml`, `Links`, `Images`, `Screenshot`, `Summary`, `ChangeTracking`, `Json`, `Attributes`, `Branding`, `Product`, `Menu`, `Audio`, `Video`. Also: `Question(QuestionFormat)`, `Highlights(HighlightsFormat)`. |
+| `headers` | `Option<HashMap<String, String>>` | Custom HTTP headers. |
+| `include_tags` | `Option<Vec<String>>` | HTML tags to include. |
+| `exclude_tags` | `Option<Vec<String>>` | HTML tags to exclude. |
+| `only_main_content` | `Option<bool>` | Only return main content. Server default: `true`. |
+| `timeout` | `Option<u32>` | Timeout in ms. Server default: `60000`. |
+| `wait_for` | `Option<u32>` | Wait time in ms before scraping. Server default: `0`. |
+| `mobile` | `Option<bool>` | Emulate mobile device. Server default: `false`. |
+| `parsers` | `Option<Vec<ParserConfig>>` | Parser configuration (e.g. PDF handling). |
+| `actions` | `Option<Vec<Action>>` | Browser actions before scraping. Enum variants: `Wait`, `Click`, `Write`, `Press`, `Scroll`, `Screenshot`, `Scrape`, `ExecuteJavascript`. |
+| `location` | `Option<LocationConfig>` | Geolocation: `{ country, languages }`. |
+| `skip_tls_verification` | `Option<bool>` | Skip TLS cert verification. |
+| `remove_base64_images` | `Option<bool>` | Remove base64 images. |
+| `fast_mode` | `Option<bool>` | Enable fast mode. |
+| `block_ads` | `Option<bool>` | Block ads. Server default: `true`. |
+| `proxy` | `Option<ProxyType>` | Proxy mode: `Basic`, `Stealth`, `Enhanced`, `Auto`. Server default: `Auto`. |
+| `max_age` | `Option<u32>` | Use cached result if younger than this (ms). |
+| `store_in_cache` | `Option<bool>` | Cache the result. |
+| `lockdown` | `Option<bool>` | Serve from cache only. |
+| `redact_pii` | `Option<bool>` | Redact PII from output. |
+| `profile` | `Option<ProfileConfig>` | Persistent browser profile: `{ name, save_changes }`. |
+| `audit_metadata` | `Option<AuditMetadata>` | User attribution for SIEM logging. |
+| `json_options` | `Option<JsonOptions>` | JSON extraction: `{ schema, system_prompt, prompt }`. |
+| `screenshot_options` | `Option<ScreenshotOptions>` | Screenshot config: `{ full_page, quality, viewport }`. |
+| `change_tracking_options` | `Option<ChangeTrackingOptions>` | Change tracking config. |
+| `attribute_selectors` | `Option<Vec<AttributeSelector>>` | Attribute selectors: `{ selector, attribute }`. |
+| `integration` | `Option<String>` | Integration identifier. |
+
+**Return type:** `Document` with optional fields: `markdown`, `html`, `raw_html`, `json`, `summary`, `metadata`, `links`, `images`, `screenshot`, `audio`, `video`, `actions`, `answer`, `highlights`, `warning`, `change_tracking`, `branding`, `product`, `menu`.
+
+### Convenience method
+
+```rust
+let json_value = client.scrape_with_schema("https://example.com", schema, Some("Extract product info")).await?;
+```
+
+## Interact
+
+### Why use it
+
+Use `interact` to execute code or send a natural-language prompt in the browser session from a prior scrape. The scrape must have returned a job ID. Use it for post-scrape automation.
+
+### Preferred SDK method
+
+```
+client.interact(job_id, options).await
+```
+
+### Example
+
+```rust
+use firecrawl::{Client, ScrapeOptions, ScrapeExecuteOptions, Format};
+
+let client = Client::new("fc-YOUR_API_KEY")?;
+
+// First scrape to get a job_id
+let doc = client.scrape("https://example.com", ScrapeOptions {
+    formats: Some(vec![Format::Markdown]),
+    ..Default::default()
+}).await?;
+
+let job_id = doc.metadata
+    .as_ref()
+    .and_then(|m| m.get("jobId"))
+    .and_then(|v| v.as_str())
+    .expect("no jobId");
+
+// Interact with the browser session
+let result = client.interact(job_id, ScrapeExecuteOptions {
+    code: Some("document.title".to_string()),
+    ..Default::default()
+}).await?;
+
+println!("{:?}", result.stdout);
+```
+
+### Parameters
+
+| Parameter | Type | Description |
+|---|---|---|
+| `job_id` | `&str` | Scrape job ID (required, first argument). |
+| `code` | `Option<String>` | Code to execute. At least one of `code` or `prompt` required (client-side validation). |
+| `prompt` | `Option<String>` | Natural-language instruction for the browser agent. |
+| `language` | `Option<ScrapeExecuteLanguage>` | Language: `Python`, `Node`, `Bash`. Default: `Node`. |
+| `timeout` | `Option<u32>` | Execution timeout in seconds. Range: 1–300. Server default: `30`. |
+
+**Return type:** `ScrapeExecuteResponse` with fields: `success`, `stdout`, `result`, `stderr`, `exit_code`, `killed`, `error`, `live_view_url`, `interactive_live_view_url`, `output`.
+
+### Stop a session
+
+```rust
+client.stop_interaction(job_id).await?;
+```
+
+## Notes
+
+- **snake_case** field names throughout, serialized to camelCase via `#[serde(rename_all = "camelCase")]`.
+- **No builder pattern**: Use struct-update syntax `..Default::default()` to fill optional fields.
+- **`impl Into<Option<T>>`**: Both `scrape` and `search` accept `None`, `Some(opts)`, or `opts` directly for the options argument.
+- **All methods are `async`** and return `Result<T, FirecrawlError>`.
+- **Deprecated aliases**: `scrape_execute` → `interact`, `stop_interactive_browser` / `delete_scrape_browser` → `stop_interaction`.
+- **Client-side validation**: `interact` returns `FirecrawlError::Misuse` if neither `code` nor `prompt` is provided.
+- **Keyless free tier**: Works without an API key (rate-limited per IP).
+
+## Source Of Truth
+
+- `/firecrawl/apps/rust-sdk/src/client.rs`
+- `/firecrawl/apps/rust-sdk/src/scrape.rs`
+- `/firecrawl/apps/rust-sdk/src/search.rs`
+- `/firecrawl-docs/api-reference/v2-openapi.json`