cloudflare 7.0.0 → 7.1.0

package/resources/aisearch/namespaces/instances/instances.d.mts

@@ -9,7 +9,7 @@ import { RequestOptions } from "../../../../internal/request-options.mjs";
 export declare class BaseInstances extends APIResource {
     static readonly _key: readonly ['aiSearch', 'namespaces', 'instances'];
     /**
-     * Create a new instance.
+     * Create a new AI Search instance with the given configuration.
      *
      * @example
      * ```ts
@@ -25,7 +25,7 @@ export declare class BaseInstances extends APIResource {
      */
     create(name: string, params: InstanceCreateParams, options?: RequestOptions): APIPromise<InstanceCreateResponse>;
     /**
-     * Update instance.
+     * Update the configuration of an AI Search instance.
      *
      * @example
      * ```ts
@@ -41,7 +41,7 @@ export declare class BaseInstances extends APIResource {
      */
     update(id: string, params: InstanceUpdateParams, options?: RequestOptions): APIPromise<InstanceUpdateResponse>;
     /**
-     * List instances.
+     * List all AI Search instances in the account.
      *
      * @example
      * ```ts
@@ -56,7 +56,7 @@ export declare class BaseInstances extends APIResource {
      */
     list(name: string, params: InstanceListParams, options?: RequestOptions): PagePromise<InstanceListResponsesV4PagePaginationArray, InstanceListResponse>;
     /**
-     * Delete instance.
+     * Permanently delete an AI Search instance and all its indexed data.
      *
      * @example
      * ```ts
@@ -90,7 +90,7 @@ export declare class BaseInstances extends APIResource {
      */
     chatCompletions(id: string, params: InstanceChatCompletionsParams, options?: RequestOptions): APIPromise<InstanceChatCompletionsResponse>;
     /**
-     * Read instance.
+     * Retrieve the configuration and status of an AI Search instance.
      *
      * @example
      * ```ts
@@ -123,7 +123,7 @@ export declare class BaseInstances extends APIResource {
      */
     search(id: string, params: InstanceSearchParams, options?: RequestOptions): APIPromise<InstanceSearchResponse>;
     /**
-     * Retrieves usage statistics for AI Search instances.
+     * Retrieve usage and indexing statistics for an AI Search instance.
      *
      * @example
      * ```ts
@@ -165,7 +165,7 @@ export interface InstanceCreateResponse {
     chunk_size?: number;
     created_by?: string | null;
     custom_metadata?: Array<InstanceCreateResponse.CustomMetadata>;
-    embedding_model?: '@cf/qwen/qwen3-embedding-0.6b' | '@cf/qwen/qwen3-vl-embedding-2b' | '@cf/baai/bge-m3' | '@cf/baai/bge-large-en-v1.5' | '@cf/google/embeddinggemma-300m' | 'google-ai-studio/gemini-embedding-001' | 'google-ai-studio/gemini-embedding-2-preview' | 'openai/text-embedding-3-small' | 'openai/text-embedding-3-large' | '' | null;
+    embedding_model?: '@cf/qwen/qwen3-embedding-0.6b' | '@cf/qwen/qwen3-vl-embedding-2b' | '@cf/baai/bge-m3' | '@cf/baai/bge-large-en-v1.5' | '@cf/google/embeddinggemma-300m' | 'google-ai-studio/gemini-embedding-001' | 'google-ai-studio/gemini-embedding-2-preview' | 'google-ai-studio/gemini-embedding-2' | 'openai/text-embedding-3-small' | 'openai/text-embedding-3-large' | '' | null;
     enable?: boolean;
     engine_version?: number;
     fusion_method?: 'max' | 'rrf';
@@ -239,6 +239,21 @@ export declare namespace InstanceCreateResponse {
     interface PublicEndpointParams {
         authorized_hosts?: Array<string>;
         chat_completions_endpoint?: PublicEndpointParams.ChatCompletionsEndpoint;
+        /**
+         * Custom domain hostnames that alias this public endpoint. GET and create
+         * responses return the current set; on update (PUT) this field is only echoed back
+         * when supplied in the request body, otherwise it is null (omit it to leave
+         * domains unchanged).
+         */
+        custom_domains?: Array<string> | null;
+        /**
+         * When false, the instance is reachable only via a registered custom domain and
+         * the default <public_endpoint_id>.search.ai.cloudflare.com host returns 404.
+         * Requires at least one custom domain. Defaults to true. public_endpoint_params is
+         * replaced wholesale on update, so resend default_domain_enabled on every update
+         * to keep the default host off — omitting it resets to true.
+         */
+        default_domain_enabled?: boolean;
         enabled?: boolean;
         mcp?: PublicEndpointParams.Mcp;
         rate_limit?: PublicEndpointParams.RateLimit;
@@ -281,7 +296,9 @@ export declare namespace InstanceCreateResponse {
         /**
          * Controls which documents are candidates for BM25 scoring. 'and' restricts
          * candidates to documents containing all query terms; 'or' includes any document
-         * containing at least one term, ranked by BM25 relevance. Defaults to 'and'.
+         * containing at least one term, ranked by BM25 relevance. When omitted on an
+         * update, the existing stored value is preserved; when never set, search falls
+         * back to 'and'.
          */
         keyword_match_mode?: 'and' | 'or';
     }
@@ -307,13 +324,15 @@ export declare namespace InstanceCreateResponse {
         /**
          * List of path patterns to exclude. Uses micromatch glob syntax: \* matches within
          * a path segment, ** matches across path segments (e.g., /admin/** matches
-         * /admin/users and /admin/settings/advanced)
+         * /admin/users and /admin/settings/advanced). Most accounts are limited to 10
+         * rules; contact support to raise it.
          */
         exclude_items?: Array<string>;
         /**
          * List of path patterns to include. Uses micromatch glob syntax: \* matches within
          * a path segment, ** matches across path segments (e.g., /blog/** matches
-         * /blog/post and /blog/2024/post)
+         * /blog/post and /blog/2024/post). Most accounts are limited to 10 rules; contact
+         * support to raise it.
          */
         include_items?: Array<string>;
         prefix?: string;
@@ -322,10 +341,51 @@ export declare namespace InstanceCreateResponse {
     }
     namespace SourceParams {
         interface WebCrawler {
+            /**
+             * Options for parse_type 'discover', where Browser Run discovers URLs by link
+             * following and sitemaps. Ignored for 'sitemap'.
+             */
+            discover_options?: WebCrawler.DiscoverOptions;
             parse_options?: WebCrawler.ParseOptions;
-            parse_type?: 'sitemap' | 'crawl';
+            /**
+             * How URLs are discovered. 'sitemap' reads XML sitemaps; 'discover' follows links
+             * recursively and requires the source to be a Verified zone on this account.
+             */
+            parse_type?: 'sitemap' | 'discover';
         }
         namespace WebCrawler {
+            /**
+             * Options for parse_type 'discover', where Browser Run discovers URLs by link
+             * following and sitemaps. Ignored for 'sitemap'.
+             */
+            interface DiscoverOptions {
+                /**
+                 * Maximum link-follow depth from the seed URL.
+                 */
+                depth?: number;
+                /**
+                 * Follow links that point outside the source domain. Must stay `false` — discover
+                 * crawls are restricted to the zone you own.
+                 */
+                include_external_links?: boolean;
+                /**
+                 * Follow links to subdomains of the source host.
+                 */
+                include_subdomains?: boolean;
+                /**
+                 * Maximum number of pages to crawl (1-100000).
+                 */
+                limit?: number;
+                /**
+                 * Maximum content age in seconds to accept (0–604800).
+                 */
+                max_age?: number;
+                /**
+                 * Where the crawler looks for URLs: 'sitemaps' reads sitemap XML only, 'links'
+                 * follows page links only, 'all' does both.
+                 */
+                source?: 'all' | 'sitemaps' | 'links';
+            }
             interface ParseOptions {
                 /**
                  * List of path-to-selector mappings for extracting specific content from crawled
@@ -389,7 +449,7 @@ export interface InstanceUpdateResponse {
     chunk_size?: number;
     created_by?: string | null;
     custom_metadata?: Array<InstanceUpdateResponse.CustomMetadata>;
-    embedding_model?: '@cf/qwen/qwen3-embedding-0.6b' | '@cf/qwen/qwen3-vl-embedding-2b' | '@cf/baai/bge-m3' | '@cf/baai/bge-large-en-v1.5' | '@cf/google/embeddinggemma-300m' | 'google-ai-studio/gemini-embedding-001' | 'google-ai-studio/gemini-embedding-2-preview' | 'openai/text-embedding-3-small' | 'openai/text-embedding-3-large' | '' | null;
+    embedding_model?: '@cf/qwen/qwen3-embedding-0.6b' | '@cf/qwen/qwen3-vl-embedding-2b' | '@cf/baai/bge-m3' | '@cf/baai/bge-large-en-v1.5' | '@cf/google/embeddinggemma-300m' | 'google-ai-studio/gemini-embedding-001' | 'google-ai-studio/gemini-embedding-2-preview' | 'google-ai-studio/gemini-embedding-2' | 'openai/text-embedding-3-small' | 'openai/text-embedding-3-large' | '' | null;
     enable?: boolean;
     engine_version?: number;
     fusion_method?: 'max' | 'rrf';
@@ -463,6 +523,21 @@ export declare namespace InstanceUpdateResponse {
     interface PublicEndpointParams {
         authorized_hosts?: Array<string>;
         chat_completions_endpoint?: PublicEndpointParams.ChatCompletionsEndpoint;
+        /**
+         * Custom domain hostnames that alias this public endpoint. GET and create
+         * responses return the current set; on update (PUT) this field is only echoed back
+         * when supplied in the request body, otherwise it is null (omit it to leave
+         * domains unchanged).
+         */
+        custom_domains?: Array<string> | null;
+        /**
+         * When false, the instance is reachable only via a registered custom domain and
+         * the default <public_endpoint_id>.search.ai.cloudflare.com host returns 404.
+         * Requires at least one custom domain. Defaults to true. public_endpoint_params is
+         * replaced wholesale on update, so resend default_domain_enabled on every update
+         * to keep the default host off — omitting it resets to true.
+         */
+        default_domain_enabled?: boolean;
         enabled?: boolean;
         mcp?: PublicEndpointParams.Mcp;
         rate_limit?: PublicEndpointParams.RateLimit;
@@ -505,7 +580,9 @@ export declare namespace InstanceUpdateResponse {
         /**
          * Controls which documents are candidates for BM25 scoring. 'and' restricts
          * candidates to documents containing all query terms; 'or' includes any document
-         * containing at least one term, ranked by BM25 relevance. Defaults to 'and'.
+         * containing at least one term, ranked by BM25 relevance. When omitted on an
+         * update, the existing stored value is preserved; when never set, search falls
+         * back to 'and'.
          */
         keyword_match_mode?: 'and' | 'or';
     }
@@ -531,13 +608,15 @@ export declare namespace InstanceUpdateResponse {
         /**
          * List of path patterns to exclude. Uses micromatch glob syntax: \* matches within
          * a path segment, ** matches across path segments (e.g., /admin/** matches
-         * /admin/users and /admin/settings/advanced)
+         * /admin/users and /admin/settings/advanced). Most accounts are limited to 10
+         * rules; contact support to raise it.
          */
         exclude_items?: Array<string>;
         /**
          * List of path patterns to include. Uses micromatch glob syntax: \* matches within
          * a path segment, ** matches across path segments (e.g., /blog/** matches
-         * /blog/post and /blog/2024/post)
+         * /blog/post and /blog/2024/post). Most accounts are limited to 10 rules; contact
+         * support to raise it.
          */
         include_items?: Array<string>;
         prefix?: string;
@@ -546,10 +625,51 @@ export declare namespace InstanceUpdateResponse {
     }
     namespace SourceParams {
         interface WebCrawler {
+            /**
+             * Options for parse_type 'discover', where Browser Run discovers URLs by link
+             * following and sitemaps. Ignored for 'sitemap'.
+             */
+            discover_options?: WebCrawler.DiscoverOptions;
             parse_options?: WebCrawler.ParseOptions;
-            parse_type?: 'sitemap' | 'crawl';
+            /**
+             * How URLs are discovered. 'sitemap' reads XML sitemaps; 'discover' follows links
+             * recursively and requires the source to be a Verified zone on this account.
+             */
+            parse_type?: 'sitemap' | 'discover';
         }
         namespace WebCrawler {
+            /**
+             * Options for parse_type 'discover', where Browser Run discovers URLs by link
+             * following and sitemaps. Ignored for 'sitemap'.
+             */
+            interface DiscoverOptions {
+                /**
+                 * Maximum link-follow depth from the seed URL.
+                 */
+                depth?: number;
+                /**
+                 * Follow links that point outside the source domain. Must stay `false` — discover
+                 * crawls are restricted to the zone you own.
+                 */
+                include_external_links?: boolean;
+                /**
+                 * Follow links to subdomains of the source host.
+                 */
+                include_subdomains?: boolean;
+                /**
+                 * Maximum number of pages to crawl (1-100000).
+                 */
+                limit?: number;
+                /**
+                 * Maximum content age in seconds to accept (0–604800).
+                 */
+                max_age?: number;
+                /**
+                 * Where the crawler looks for URLs: 'sitemaps' reads sitemap XML only, 'links'
+                 * follows page links only, 'all' does both.
+                 */
+                source?: 'all' | 'sitemaps' | 'links';
+            }
             interface ParseOptions {
                 /**
                  * List of path-to-selector mappings for extracting specific content from crawled
@@ -593,224 +713,161 @@ export declare namespace InstanceUpdateResponse {
     }
 }
 export interface InstanceListResponse {
-    /**
-     * AI Search instance ID. Lowercase alphanumeric, hyphens, and underscores.
-     */
     id: string;
+    ai_gateway_id: string | null;
+    ai_search_model: string | null;
+    cache: boolean;
+    cache_threshold: 'super_strict_match' | 'close_enough' | 'flexible_friend' | 'anything_goes' | null;
+    cache_ttl: 600 | 1800 | 3600 | 7200 | 21600 | 43200 | 86400 | 172800 | 259200 | 518400;
+    chunk: boolean;
+    chunk_overlap: number | null;
+    chunk_size: number | null;
     created_at: string;
+    created_by: string | null;
+    custom_metadata: Array<InstanceListResponse.CustomMetadata> | null;
+    embedding_model: string | null;
+    enable: boolean;
+    engine_version: number;
+    fusion_method: 'max' | 'rrf';
+    hybrid_search_enabled: boolean;
+    index_method: InstanceListResponse.IndexMethod;
+    indexing_options: InstanceListResponse.IndexingOptions | null;
+    last_activity: string | null;
+    max_num_results: number | null;
+    metadata: InstanceListResponse.Metadata | null;
     modified_at: string;
-    ai_gateway_id?: string | null;
-    ai_search_model?: '@cf/meta/llama-3.3-70b-instruct-fp8-fast' | '@cf/zai-org/glm-4.7-flash' | '@cf/meta/llama-3.1-8b-instruct-fast' | '@cf/meta/llama-3.1-8b-instruct-fp8' | '@cf/meta/llama-4-scout-17b-16e-instruct' | '@cf/qwen/qwen3-30b-a3b-fp8' | '@cf/deepseek-ai/deepseek-r1-distill-qwen-32b' | '@cf/moonshotai/kimi-k2-instruct' | '@cf/google/gemma-3-12b-it' | '@cf/google/gemma-4-26b-a4b-it' | '@cf/moonshotai/kimi-k2.5' | 'anthropic/claude-3-7-sonnet' | 'anthropic/claude-sonnet-4' | 'anthropic/claude-opus-4' | 'anthropic/claude-3-5-haiku' | 'cerebras/qwen-3-235b-a22b-instruct' | 'cerebras/qwen-3-235b-a22b-thinking' | 'cerebras/llama-3.3-70b' | 'cerebras/llama-4-maverick-17b-128e-instruct' | 'cerebras/llama-4-scout-17b-16e-instruct' | 'cerebras/gpt-oss-120b' | 'google-ai-studio/gemini-2.5-flash' | 'google-ai-studio/gemini-2.5-pro' | 'grok/grok-4' | 'groq/llama-3.3-70b-versatile' | 'groq/llama-3.1-8b-instant' | 'openai/gpt-5' | 'openai/gpt-5-mini' | 'openai/gpt-5-nano' | '' | null;
-    cache?: boolean;
-    cache_threshold?: 'super_strict_match' | 'close_enough' | 'flexible_friend' | 'anything_goes';
-    /**
-     * Cache entry TTL in seconds. Allowed values: 600 (10min), 1800 (30min), 3600
-     * (1h), 7200 (2h), 21600 (6h), 43200 (12h), 86400 (24h), 172800 (48h), 259200
-     * (72h), 518400 (6d).
-     */
-    cache_ttl?: 600 | 1800 | 3600 | 7200 | 21600 | 43200 | 86400 | 172800 | 259200 | 518400;
-    chunk_overlap?: number;
-    chunk_size?: number;
-    created_by?: string | null;
-    custom_metadata?: Array<InstanceListResponse.CustomMetadata>;
-    embedding_model?: '@cf/qwen/qwen3-embedding-0.6b' | '@cf/qwen/qwen3-vl-embedding-2b' | '@cf/baai/bge-m3' | '@cf/baai/bge-large-en-v1.5' | '@cf/google/embeddinggemma-300m' | 'google-ai-studio/gemini-embedding-001' | 'google-ai-studio/gemini-embedding-2-preview' | 'openai/text-embedding-3-small' | 'openai/text-embedding-3-large' | '' | null;
-    enable?: boolean;
-    engine_version?: number;
-    fusion_method?: 'max' | 'rrf';
-    /**
-     * @deprecated Deprecated — use index_method instead.
-     */
-    hybrid_search_enabled?: boolean;
-    /**
-     * Controls which storage backends are used during indexing. Defaults to
-     * vector-only.
-     */
-    index_method?: InstanceListResponse.IndexMethod;
-    indexing_options?: InstanceListResponse.IndexingOptions | null;
-    last_activity?: string | null;
-    max_num_results?: number;
-    metadata?: InstanceListResponse.Metadata;
-    modified_by?: string | null;
-    namespace?: string | null;
-    paused?: boolean;
-    public_endpoint_id?: string | null;
-    public_endpoint_params?: InstanceListResponse.PublicEndpointParams;
-    reranking?: boolean;
-    reranking_model?: '@cf/baai/bge-reranker-base' | '' | null;
-    retrieval_options?: InstanceListResponse.RetrievalOptions | null;
-    rewrite_model?: '@cf/meta/llama-3.3-70b-instruct-fp8-fast' | '@cf/zai-org/glm-4.7-flash' | '@cf/meta/llama-3.1-8b-instruct-fast' | '@cf/meta/llama-3.1-8b-instruct-fp8' | '@cf/meta/llama-4-scout-17b-16e-instruct' | '@cf/qwen/qwen3-30b-a3b-fp8' | '@cf/deepseek-ai/deepseek-r1-distill-qwen-32b' | '@cf/moonshotai/kimi-k2-instruct' | '@cf/google/gemma-3-12b-it' | '@cf/google/gemma-4-26b-a4b-it' | '@cf/moonshotai/kimi-k2.5' | 'anthropic/claude-3-7-sonnet' | 'anthropic/claude-sonnet-4' | 'anthropic/claude-opus-4' | 'anthropic/claude-3-5-haiku' | 'cerebras/qwen-3-235b-a22b-instruct' | 'cerebras/qwen-3-235b-a22b-thinking' | 'cerebras/llama-3.3-70b' | 'cerebras/llama-4-maverick-17b-128e-instruct' | 'cerebras/llama-4-scout-17b-16e-instruct' | 'cerebras/gpt-oss-120b' | 'google-ai-studio/gemini-2.5-flash' | 'google-ai-studio/gemini-2.5-pro' | 'grok/grok-4' | 'groq/llama-3.3-70b-versatile' | 'groq/llama-3.1-8b-instant' | 'openai/gpt-5' | 'openai/gpt-5-mini' | 'openai/gpt-5-nano' | '' | null;
-    rewrite_query?: boolean;
-    score_threshold?: number;
-    source?: string | null;
-    source_params?: InstanceListResponse.SourceParams | null;
-    status?: string;
-    /**
-     * Interval between automatic syncs, in seconds. Allowed values: 900 (15min), 1800
-     * (30min), 3600 (1h), 7200 (2h), 14400 (4h), 21600 (6h), 43200 (12h), 86400 (24h).
-     */
-    sync_interval?: 900 | 1800 | 3600 | 7200 | 14400 | 21600 | 43200 | 86400;
-    token_id?: string;
-    type?: 'r2' | 'web-crawler' | null;
+    modified_by: string | null;
+    namespace: string;
+    paused: boolean;
+    public_endpoint_id: string | null;
+    public_endpoint_params: InstanceListResponse.PublicEndpointParams | null;
+    reranking: boolean;
+    reranking_model: string | null;
+    retrieval_options: InstanceListResponse.RetrievalOptions | null;
+    rewrite_model: string | null;
+    rewrite_query: boolean;
+    score_threshold: number | null;
+    source: string | null;
+    source_params: InstanceListResponse.SourceParams | null;
+    status: string;
+    summarization: boolean;
+    summarization_model: string | null;
+    sync_interval: 900 | 1800 | 3600 | 7200 | 14400 | 21600 | 43200 | 86400;
+    system_prompt_ai_search: string | null;
+    system_prompt_index_summarization: string | null;
+    system_prompt_rewrite_query: string | null;
+    token_id: string | null;
+    type: 'r2' | 'web-crawler' | null;
 }
 export declare namespace InstanceListResponse {
     interface CustomMetadata {
         data_type: 'text' | 'number' | 'boolean' | 'datetime';
         field_name: string;
     }
-    /**
-     * Controls which storage backends are used during indexing. Defaults to
-     * vector-only.
-     */
     interface IndexMethod {
-        /**
-         * Enable keyword (BM25) storage backend.
-         */
         keyword: boolean;
-        /**
-         * Enable vector (embedding) storage backend.
-         */
         vector: boolean;
+        [k: string]: unknown;
     }
     interface IndexingOptions {
-        /**
-         * Tokenizer used for keyword search indexing. porter provides word-level
-         * tokenization with Porter stemming (good for natural language queries). trigram
-         * enables character-level substring matching (good for partial matches, code,
-         * identifiers). Changing this triggers a full re-index. Defaults to porter.
-         */
         keyword_tokenizer?: 'porter' | 'trigram';
+        [k: string]: unknown;
     }
     interface Metadata {
         created_from_aisearch_wizard?: boolean;
         worker_domain?: string;
+        [k: string]: unknown;
     }
     interface PublicEndpointParams {
         authorized_hosts?: Array<string>;
         chat_completions_endpoint?: PublicEndpointParams.ChatCompletionsEndpoint;
+        custom_domains?: Array<string> | null;
+        default_domain_enabled?: boolean;
         enabled?: boolean;
         mcp?: PublicEndpointParams.Mcp;
         rate_limit?: PublicEndpointParams.RateLimit;
         search_endpoint?: PublicEndpointParams.SearchEndpoint;
+        [k: string]: unknown;
     }
     namespace PublicEndpointParams {
         interface ChatCompletionsEndpoint {
-            /**
-             * Disable chat completions endpoint for this public endpoint
-             */
             disabled?: boolean;
+            [k: string]: unknown;
         }
         interface Mcp {
             description?: string;
-            /**
-             * Disable MCP endpoint for this public endpoint
-             */
             disabled?: boolean;
+            [k: string]: unknown;
         }
         interface RateLimit {
             period_ms?: number;
             requests?: number;
             technique?: 'fixed' | 'sliding';
+            [k: string]: unknown;
         }
         interface SearchEndpoint {
-            /**
-             * Disable search endpoint for this public endpoint
-             */
             disabled?: boolean;
+            [k: string]: unknown;
         }
     }
     interface RetrievalOptions {
-        /**
-         * Metadata fields to boost search results by. Each entry specifies a metadata
-         * field and an optional direction. Direction defaults to 'asc' for
-         * numeric/datetime fields and 'exists' for text/boolean fields. Fields must match
-         * 'timestamp' or a defined custom_metadata field.
-         */
         boost_by?: Array<RetrievalOptions.BoostBy>;
-        /**
-         * Controls which documents are candidates for BM25 scoring. 'and' restricts
-         * candidates to documents containing all query terms; 'or' includes any document
-         * containing at least one term, ranked by BM25 relevance. Defaults to 'and'.
-         */
         keyword_match_mode?: 'and' | 'or';
+        [k: string]: unknown;
     }
     namespace RetrievalOptions {
         interface BoostBy {
-            /**
-             * Metadata field name to boost by. Use 'timestamp' for document freshness, or any
-             * custom_metadata field. Numeric and datetime fields support all four directions
-             * (asc, desc, exists, not_exists); text/boolean fields only support
-             * exists/not_exists.
-             */
             field: string;
-            /**
-             * Boost direction. 'desc' = higher values rank higher (e.g. newer timestamps).
-             * 'asc' = lower values rank higher. 'exists' = boost chunks that have the field.
-             * 'not_exists' = boost chunks that lack the field. Optional — defaults to 'asc'
-             * for numeric/datetime fields, 'exists' for text/boolean fields.
-             */
+            dataType?: 'number' | 'datetime' | 'text' | 'boolean';
             direction?: 'asc' | 'desc' | 'exists' | 'not_exists';
+            [k: string]: unknown;
         }
     }
     interface SourceParams {
-        /**
-         * List of path patterns to exclude. Uses micromatch glob syntax: \* matches within
-         * a path segment, ** matches across path segments (e.g., /admin/** matches
-         * /admin/users and /admin/settings/advanced)
-         */
         exclude_items?: Array<string>;
-        /**
-         * List of path patterns to include. Uses micromatch glob syntax: \* matches within
-         * a path segment, ** matches across path segments (e.g., /blog/** matches
-         * /blog/post and /blog/2024/post)
-         */
         include_items?: Array<string>;
         prefix?: string;
         r2_jurisdiction?: string;
         web_crawler?: SourceParams.WebCrawler;
+        [k: string]: unknown;
     }
     namespace SourceParams {
         interface WebCrawler {
+            discover_options?: WebCrawler.DiscoverOptions;
             parse_options?: WebCrawler.ParseOptions;
-            parse_type?: 'sitemap' | 'crawl';
+            parse_type?: 'sitemap' | 'discover';
+            [k: string]: unknown;
         }
         namespace WebCrawler {
-            interface ParseOptions {
+            interface DiscoverOptions {
+                depth?: number;
+                include_external_links?: boolean;
+                include_subdomains?: boolean;
                 /**
-                 * List of path-to-selector mappings for extracting specific content from crawled
-                 * pages. Each entry pairs a URL glob pattern with a CSS selector. The first
-                 * matching path wins. Only the matched HTML fragment is stored and indexed. Omit
-                 * the field to disable content selection — empty arrays are rejected.
+                 * Maximum number of pages to crawl. New values are capped at 100000; instances
+                 * configured before that cap may report a higher stored value, which the crawler
+                 * clamps at run time.
                  */
+                limit?: number;
+                max_age?: number;
+                source?: 'all' | 'sitemaps' | 'links';
+                [k: string]: unknown;
+            }
+            interface ParseOptions {
                 content_selector?: Array<ParseOptions.ContentSelector>;
-                /**
-                 * Up to 5 custom HTTP headers sent with each crawl request. Names must be RFC-7230
-                 * token characters (no spaces, colons, or control characters); values must be
-                 * HTAB + printable ASCII (no CR/LF).
-                 */
                 include_headers?: {
                     [key: string]: string;
                 };
                 include_images?: boolean;
-                /**
-                 * List of specific sitemap URLs to use for crawling. Only valid when parse_type is
-                 * 'sitemap'.
-                 */
                 specific_sitemaps?: Array<string>;
                 use_browser_rendering?: boolean;
+                [k: string]: unknown;
             }
             namespace ParseOptions {
                 interface ContentSelector {
-                    /**
-                     * Glob pattern to match against the page URL path. Uses standard glob syntax: \*
-                     * matches within a segment, \*\* crosses directories.
-                     */
                     path: string;
-                    /**
-                     * CSS selector to extract content from pages matching the path pattern. Must not
-                     * contain disallowed characters (;, `, $, {, }, \). Must target a single element;
-                     * if multiple elements match, the selector is ignored and the full page is used.
-                     */
                     selector: string;
+                    [k: string]: unknown;
                 }
             }
         }
@@ -837,7 +894,7 @@ export interface InstanceDeleteResponse {
     chunk_size?: number;
     created_by?: string | null;
     custom_metadata?: Array<InstanceDeleteResponse.CustomMetadata>;
-    embedding_model?: '@cf/qwen/qwen3-embedding-0.6b' | '@cf/qwen/qwen3-vl-embedding-2b' | '@cf/baai/bge-m3' | '@cf/baai/bge-large-en-v1.5' | '@cf/google/embeddinggemma-300m' | 'google-ai-studio/gemini-embedding-001' | 'google-ai-studio/gemini-embedding-2-preview' | 'openai/text-embedding-3-small' | 'openai/text-embedding-3-large' | '' | null;
+    embedding_model?: '@cf/qwen/qwen3-embedding-0.6b' | '@cf/qwen/qwen3-vl-embedding-2b' | '@cf/baai/bge-m3' | '@cf/baai/bge-large-en-v1.5' | '@cf/google/embeddinggemma-300m' | 'google-ai-studio/gemini-embedding-001' | 'google-ai-studio/gemini-embedding-2-preview' | 'google-ai-studio/gemini-embedding-2' | 'openai/text-embedding-3-small' | 'openai/text-embedding-3-large' | '' | null;
     enable?: boolean;
     engine_version?: number;
     fusion_method?: 'max' | 'rrf';
@@ -911,6 +968,21 @@ export declare namespace InstanceDeleteResponse {
     interface PublicEndpointParams {
         authorized_hosts?: Array<string>;
         chat_completions_endpoint?: PublicEndpointParams.ChatCompletionsEndpoint;
+        /**
+         * Custom domain hostnames that alias this public endpoint. GET and create
+         * responses return the current set; on update (PUT) this field is only echoed back
+         * when supplied in the request body, otherwise it is null (omit it to leave
+         * domains unchanged).
+         */
+        custom_domains?: Array<string> | null;
+        /**
+         * When false, the instance is reachable only via a registered custom domain and
+         * the default <public_endpoint_id>.search.ai.cloudflare.com host returns 404.
+         * Requires at least one custom domain. Defaults to true. public_endpoint_params is
+         * replaced wholesale on update, so resend default_domain_enabled on every update
+         * to keep the default host off — omitting it resets to true.
+         */
+        default_domain_enabled?: boolean;
         enabled?: boolean;
         mcp?: PublicEndpointParams.Mcp;
         rate_limit?: PublicEndpointParams.RateLimit;
@@ -953,7 +1025,9 @@ export declare namespace InstanceDeleteResponse {
         /**
          * Controls which documents are candidates for BM25 scoring. 'and' restricts
          * candidates to documents containing all query terms; 'or' includes any document
-         * containing at least one term, ranked by BM25 relevance. Defaults to 'and'.
+         * containing at least one term, ranked by BM25 relevance. When omitted on an
+         * update, the existing stored value is preserved; when never set, search falls
+         * back to 'and'.
          */
         keyword_match_mode?: 'and' | 'or';
     }
@@ -979,13 +1053,15 @@ export declare namespace InstanceDeleteResponse {
         /**
          * List of path patterns to exclude. Uses micromatch glob syntax: \* matches within
          * a path segment, ** matches across path segments (e.g., /admin/** matches
-         * /admin/users and /admin/settings/advanced)
+         * /admin/users and /admin/settings/advanced). Most accounts are limited to 10
+         * rules; contact support to raise it.
          */
         exclude_items?: Array<string>;
         /**
          * List of path patterns to include. Uses micromatch glob syntax: \* matches within
          * a path segment, ** matches across path segments (e.g., /blog/** matches
-         * /blog/post and /blog/2024/post)
+         * /blog/post and /blog/2024/post). Most accounts are limited to 10 rules; contact
+         * support to raise it.
          */
         include_items?: Array<string>;
         prefix?: string;
@@ -994,10 +1070,51 @@ export declare namespace InstanceDeleteResponse {
     }
     namespace SourceParams {
         interface WebCrawler {
+            /**
+             * Options for parse_type 'discover', where Browser Run discovers URLs by link
+             * following and sitemaps. Ignored for 'sitemap'.
+             */
+            discover_options?: WebCrawler.DiscoverOptions;
             parse_options?: WebCrawler.ParseOptions;
-            parse_type?: 'sitemap' | 'crawl';
+            /**
+             * How URLs are discovered. 'sitemap' reads XML sitemaps; 'discover' follows links
+             * recursively and requires the source to be a Verified zone on this account.
+             */
+            parse_type?: 'sitemap' | 'discover';
         }
         namespace WebCrawler {
+            /**
+             * Options for parse_type 'discover', where Browser Run discovers URLs by link
+             * following and sitemaps. Ignored for 'sitemap'.
+             */
+            interface DiscoverOptions {
+                /**
+                 * Maximum link-follow depth from the seed URL.
+                 */
+                depth?: number;
+                /**
+                 * Follow links that point outside the source domain. Must stay `false` — discover
+                 * crawls are restricted to the zone you own.
+                 */
+                include_external_links?: boolean;
+                /**
+                 * Follow links to subdomains of the source host.
+                 */
+                include_subdomains?: boolean;
+                /**
+                 * Maximum number of pages to crawl (1-100000).
+                 */
+                limit?: number;
+                /**
+                 * Maximum content age in seconds to accept (0–604800).
+                 */
+                max_age?: number;
+                /**
+                 * Where the crawler looks for URLs: 'sitemaps' reads sitemap XML only, 'links'
+                 * follows page links only, 'all' does both.
+                 */
+                source?: 'all' | 'sitemaps' | 'links';
+            }
             interface ParseOptions {
                 /**
                  * List of path-to-selector mappings for extracting specific content from crawled
@@ -1055,7 +1172,7 @@ export declare namespace InstanceChatCompletionsResponse {
     }
     namespace Choice {
         interface Message {
-            content: string | Array<Message.UnionMember0 | Message.UnionMember1> | null;
+            content: string | Array<Message.UnionMember0 | Message.UnionMember1 | Message.UnionMember2> | null;
             role: 'system' | 'developer' | 'user' | 'assistant' | 'tool';
             [k: string]: unknown;
         }
@@ -1073,6 +1190,17 @@ export declare namespace InstanceChatCompletionsResponse {
                     url: string;
                 }
             }
+            interface UnionMember2 {
+                file: UnionMember2.File;
+                type: 'file';
+            }
+            namespace UnionMember2 {
+                interface File {
+                    filename: string;
+                    file_data?: string;
+                    file_id?: string;
+                }
+            }
         }
     }
     interface Chunk {
@@ -1122,7 +1250,7 @@ export interface InstanceReadResponse {
     chunk_size?: number;
     created_by?: string | null;
     custom_metadata?: Array<InstanceReadResponse.CustomMetadata>;
-    embedding_model?: '@cf/qwen/qwen3-embedding-0.6b' | '@cf/qwen/qwen3-vl-embedding-2b' | '@cf/baai/bge-m3' | '@cf/baai/bge-large-en-v1.5' | '@cf/google/embeddinggemma-300m' | 'google-ai-studio/gemini-embedding-001' | 'google-ai-studio/gemini-embedding-2-preview' | 'openai/text-embedding-3-small' | 'openai/text-embedding-3-large' | '' | null;
+    embedding_model?: '@cf/qwen/qwen3-embedding-0.6b' | '@cf/qwen/qwen3-vl-embedding-2b' | '@cf/baai/bge-m3' | '@cf/baai/bge-large-en-v1.5' | '@cf/google/embeddinggemma-300m' | 'google-ai-studio/gemini-embedding-001' | 'google-ai-studio/gemini-embedding-2-preview' | 'google-ai-studio/gemini-embedding-2' | 'openai/text-embedding-3-small' | 'openai/text-embedding-3-large' | '' | null;
     enable?: boolean;
     engine_version?: number;
     fusion_method?: 'max' | 'rrf';
@@ -1196,6 +1324,21 @@ export declare namespace InstanceReadResponse {
     interface PublicEndpointParams {
         authorized_hosts?: Array<string>;
         chat_completions_endpoint?: PublicEndpointParams.ChatCompletionsEndpoint;
+        /**
+         * Custom domain hostnames that alias this public endpoint. GET and create
+         * responses return the current set; on update (PUT) this field is only echoed back
+         * when supplied in the request body, otherwise it is null (omit it to leave
+         * domains unchanged).
+         */
+        custom_domains?: Array<string> | null;
+        /**
+         * When false, the instance is reachable only via a registered custom domain and
+         * the default <public_endpoint_id>.search.ai.cloudflare.com host returns 404.
+         * Requires at least one custom domain. Defaults to true. public_endpoint_params is
+         * replaced wholesale on update, so resend default_domain_enabled on every update
+         * to keep the default host off — omitting it resets to true.
+         */
+        default_domain_enabled?: boolean;
         enabled?: boolean;
         mcp?: PublicEndpointParams.Mcp;
         rate_limit?: PublicEndpointParams.RateLimit;
@@ -1238,7 +1381,9 @@ export declare namespace InstanceReadResponse {
         /**
          * Controls which documents are candidates for BM25 scoring. 'and' restricts
          * candidates to documents containing all query terms; 'or' includes any document
-         * containing at least one term, ranked by BM25 relevance. Defaults to 'and'.
+         * containing at least one term, ranked by BM25 relevance. When omitted on an
+         * update, the existing stored value is preserved; when never set, search falls
+         * back to 'and'.
          */
         keyword_match_mode?: 'and' | 'or';
     }
@@ -1264,13 +1409,15 @@ export declare namespace InstanceReadResponse {
         /**
          * List of path patterns to exclude. Uses micromatch glob syntax: \* matches within
          * a path segment, ** matches across path segments (e.g., /admin/** matches
-         * /admin/users and /admin/settings/advanced)
+         * /admin/users and /admin/settings/advanced). Most accounts are limited to 10
+         * rules; contact support to raise it.
          */
         exclude_items?: Array<string>;
         /**
          * List of path patterns to include. Uses micromatch glob syntax: \* matches within
          * a path segment, ** matches across path segments (e.g., /blog/** matches
-         * /blog/post and /blog/2024/post)
+         * /blog/post and /blog/2024/post). Most accounts are limited to 10 rules; contact
+         * support to raise it.
          */
         include_items?: Array<string>;
         prefix?: string;
@@ -1279,10 +1426,51 @@ export declare namespace InstanceReadResponse {
     }
     namespace SourceParams {
         interface WebCrawler {
+            /**
+             * Options for parse_type 'discover', where Browser Run discovers URLs by link
+             * following and sitemaps. Ignored for 'sitemap'.
+             */
+            discover_options?: WebCrawler.DiscoverOptions;
             parse_options?: WebCrawler.ParseOptions;
-            parse_type?: 'sitemap' | 'crawl';
+            /**
+             * How URLs are discovered. 'sitemap' reads XML sitemaps; 'discover' follows links
+             * recursively and requires the source to be a Verified zone on this account.
+             */
+            parse_type?: 'sitemap' | 'discover';
         }
         namespace WebCrawler {
+            /**
+             * Options for parse_type 'discover', where Browser Run discovers URLs by link
+             * following and sitemaps. Ignored for 'sitemap'.
+             */
+            interface DiscoverOptions {
+                /**
+                 * Maximum link-follow depth from the seed URL.
+                 */
+                depth?: number;
+                /**
+                 * Follow links that point outside the source domain. Must stay `false` — discover
+                 * crawls are restricted to the zone you own.
+                 */
+                include_external_links?: boolean;
+                /**
+                 * Follow links to subdomains of the source host.
+                 */
+                include_subdomains?: boolean;
+                /**
+                 * Maximum number of pages to crawl (1-100000).
+                 */
+                limit?: number;
+                /**
+                 * Maximum content age in seconds to accept (0–604800).
+                 */
+                max_age?: number;
+                /**
+                 * Where the crawler looks for URLs: 'sitemaps' reads sitemap XML only, 'links'
+                 * follows page links only, 'all' does both.
+                 */
+                source?: 'all' | 'sitemaps' | 'links';
+            }
             interface ParseOptions {
                 /**
                  * List of path-to-selector mappings for extracting specific content from crawled
@@ -1464,7 +1652,7 @@ export interface InstanceCreateParams {
     /**
      * Body param
      */
-    embedding_model?: '@cf/qwen/qwen3-embedding-0.6b' | '@cf/qwen/qwen3-vl-embedding-2b' | '@cf/baai/bge-m3' | '@cf/baai/bge-large-en-v1.5' | '@cf/google/embeddinggemma-300m' | 'google-ai-studio/gemini-embedding-001' | 'google-ai-studio/gemini-embedding-2-preview' | 'openai/text-embedding-3-small' | 'openai/text-embedding-3-large' | '' | null;
+    embedding_model?: '@cf/qwen/qwen3-embedding-0.6b' | '@cf/qwen/qwen3-vl-embedding-2b' | '@cf/baai/bge-m3' | '@cf/baai/bge-large-en-v1.5' | '@cf/google/embeddinggemma-300m' | 'google-ai-studio/gemini-embedding-001' | 'google-ai-studio/gemini-embedding-2-preview' | 'google-ai-studio/gemini-embedding-2' | 'openai/text-embedding-3-small' | 'openai/text-embedding-3-large' | '' | null;
     /**
      * Body param
      */
@@ -1576,6 +1764,21 @@ export declare namespace InstanceCreateParams {
     interface PublicEndpointParams {
         authorized_hosts?: Array<string>;
         chat_completions_endpoint?: PublicEndpointParams.ChatCompletionsEndpoint;
+        /**
+         * Custom domain hostnames that alias this public endpoint. GET and create
+         * responses return the current set; on update (PUT) this field is only echoed back
+         * when supplied in the request body, otherwise it is null (omit it to leave
+         * domains unchanged).
+         */
+        custom_domains?: Array<string> | null;
+        /**
+         * When false, the instance is reachable only via a registered custom domain and
+         * the default <public_endpoint_id>.search.ai.cloudflare.com host returns 404.
+         * Requires at least one custom domain. Defaults to true. public_endpoint_params is
+         * replaced wholesale on update, so resend default_domain_enabled on every update
+         * to keep the default host off — omitting it resets to true.
+         */
+        default_domain_enabled?: boolean;
         enabled?: boolean;
         mcp?: PublicEndpointParams.Mcp;
         rate_limit?: PublicEndpointParams.RateLimit;
@@ -1618,7 +1821,9 @@ export declare namespace InstanceCreateParams {
         /**
          * Controls which documents are candidates for BM25 scoring. 'and' restricts
          * candidates to documents containing all query terms; 'or' includes any document
-         * containing at least one term, ranked by BM25 relevance. Defaults to 'and'.
+         * containing at least one term, ranked by BM25 relevance. When omitted on an
+         * update, the existing stored value is preserved; when never set, search falls
+         * back to 'and'.
          */
         keyword_match_mode?: 'and' | 'or';
     }
@@ -1644,13 +1849,15 @@ export declare namespace InstanceCreateParams {
         /**
          * List of path patterns to exclude. Uses micromatch glob syntax: \* matches within
          * a path segment, ** matches across path segments (e.g., /admin/** matches
-         * /admin/users and /admin/settings/advanced)
+         * /admin/users and /admin/settings/advanced). Most accounts are limited to 10
+         * rules; contact support to raise it.
          */
         exclude_items?: Array<string>;
         /**
          * List of path patterns to include. Uses micromatch glob syntax: \* matches within
          * a path segment, ** matches across path segments (e.g., /blog/** matches
-         * /blog/post and /blog/2024/post)
+         * /blog/post and /blog/2024/post). Most accounts are limited to 10 rules; contact
+         * support to raise it.
          */
         include_items?: Array<string>;
         prefix?: string;
@@ -1659,10 +1866,51 @@ export declare namespace InstanceCreateParams {
     }
     namespace SourceParams {
         interface WebCrawler {
+            /**
+             * Options for parse_type 'discover', where Browser Run discovers URLs by link
+             * following and sitemaps. Ignored for 'sitemap'.
+             */
+            discover_options?: WebCrawler.DiscoverOptions;
             parse_options?: WebCrawler.ParseOptions;
-            parse_type?: 'sitemap' | 'crawl';
+            /**
+             * How URLs are discovered. 'sitemap' reads XML sitemaps; 'discover' follows links
+             * recursively and requires the source to be a Verified zone on this account.
+             */
+            parse_type?: 'sitemap' | 'discover';
         }
         namespace WebCrawler {
+            /**
+             * Options for parse_type 'discover', where Browser Run discovers URLs by link
+             * following and sitemaps. Ignored for 'sitemap'.
+             */
+            interface DiscoverOptions {
+                /**
+                 * Maximum link-follow depth from the seed URL.
+                 */
+                depth?: number;
+                /**
+                 * Follow links that point outside the source domain. Must stay `false` — discover
+                 * crawls are restricted to the zone you own.
+                 */
+                include_external_links?: boolean;
+                /**
+                 * Follow links to subdomains of the source host.
+                 */
+                include_subdomains?: boolean;
+                /**
+                 * Maximum number of pages to crawl (1-100000).
+                 */
+                limit?: number;
+                /**
+                 * Maximum content age in seconds to accept (0–604800).
+                 */
+                max_age?: number;
+                /**
+                 * Where the crawler looks for URLs: 'sitemaps' reads sitemap XML only, 'links'
+                 * follows page links only, 'all' does both.
+                 */
+                source?: 'all' | 'sitemaps' | 'links';
+            }
             interface ParseOptions {
                 /**
                  * List of path-to-selector mappings for extracting specific content from crawled
@@ -1755,7 +2003,7 @@ export interface InstanceUpdateParams {
     /**
      * Body param
      */
-    embedding_model?: '@cf/qwen/qwen3-embedding-0.6b' | '@cf/qwen/qwen3-vl-embedding-2b' | '@cf/baai/bge-m3' | '@cf/baai/bge-large-en-v1.5' | '@cf/google/embeddinggemma-300m' | 'google-ai-studio/gemini-embedding-001' | 'google-ai-studio/gemini-embedding-2-preview' | 'openai/text-embedding-3-small' | 'openai/text-embedding-3-large' | '' | null;
+    embedding_model?: '@cf/qwen/qwen3-embedding-0.6b' | '@cf/qwen/qwen3-vl-embedding-2b' | '@cf/baai/bge-m3' | '@cf/baai/bge-large-en-v1.5' | '@cf/google/embeddinggemma-300m' | 'google-ai-studio/gemini-embedding-001' | 'google-ai-studio/gemini-embedding-2-preview' | 'google-ai-studio/gemini-embedding-2' | 'openai/text-embedding-3-small' | 'openai/text-embedding-3-large' | '' | null;
     /**
      * Body param
      */
@@ -1883,6 +2131,21 @@ export declare namespace InstanceUpdateParams {
     interface PublicEndpointParams {
         authorized_hosts?: Array<string>;
         chat_completions_endpoint?: PublicEndpointParams.ChatCompletionsEndpoint;
+        /**
+         * Custom domain hostnames that alias this public endpoint. GET and create
+         * responses return the current set; on update (PUT) this field is only echoed back
+         * when supplied in the request body, otherwise it is null (omit it to leave
+         * domains unchanged).
+         */
+        custom_domains?: Array<string> | null;
+        /**
+         * When false, the instance is reachable only via a registered custom domain and
+         * the default <public_endpoint_id>.search.ai.cloudflare.com host returns 404.
+         * Requires at least one custom domain. Defaults to true. public_endpoint_params is
+         * replaced wholesale on update, so resend default_domain_enabled on every update
+         * to keep the default host off — omitting it resets to true.
+         */
+        default_domain_enabled?: boolean;
         enabled?: boolean;
         mcp?: PublicEndpointParams.Mcp;
         rate_limit?: PublicEndpointParams.RateLimit;
@@ -1925,7 +2188,9 @@ export declare namespace InstanceUpdateParams {
         /**
          * Controls which documents are candidates for BM25 scoring. 'and' restricts
          * candidates to documents containing all query terms; 'or' includes any document
-         * containing at least one term, ranked by BM25 relevance. Defaults to 'and'.
+         * containing at least one term, ranked by BM25 relevance. When omitted on an
+         * update, the existing stored value is preserved; when never set, search falls
+         * back to 'and'.
          */
         keyword_match_mode?: 'and' | 'or';
     }
@@ -1951,13 +2216,15 @@ export declare namespace InstanceUpdateParams {
         /**
          * List of path patterns to exclude. Uses micromatch glob syntax: \* matches within
          * a path segment, ** matches across path segments (e.g., /admin/** matches
-         * /admin/users and /admin/settings/advanced)
+         * /admin/users and /admin/settings/advanced). Most accounts are limited to 10
+         * rules; contact support to raise it.
          */
         exclude_items?: Array<string>;
         /**
          * List of path patterns to include. Uses micromatch glob syntax: \* matches within
          * a path segment, ** matches across path segments (e.g., /blog/** matches
-         * /blog/post and /blog/2024/post)
+         * /blog/post and /blog/2024/post). Most accounts are limited to 10 rules; contact
+         * support to raise it.
          */
         include_items?: Array<string>;
         prefix?: string;
@@ -1966,10 +2233,51 @@ export declare namespace InstanceUpdateParams {
     }
     namespace SourceParams {
         interface WebCrawler {
+            /**
+             * Options for parse_type 'discover', where Browser Run discovers URLs by link
+             * following and sitemaps. Ignored for 'sitemap'.
+             */
+            discover_options?: WebCrawler.DiscoverOptions;
             parse_options?: WebCrawler.ParseOptions;
-            parse_type?: 'sitemap' | 'crawl';
+            /**
+             * How URLs are discovered. 'sitemap' reads XML sitemaps; 'discover' follows links
+             * recursively and requires the source to be a Verified zone on this account.
+             */
+            parse_type?: 'sitemap' | 'discover';
         }
         namespace WebCrawler {
+            /**
+             * Options for parse_type 'discover', where Browser Run discovers URLs by link
+             * following and sitemaps. Ignored for 'sitemap'.
+             */
+            interface DiscoverOptions {
+                /**
+                 * Maximum link-follow depth from the seed URL.
+                 */
+                depth?: number;
+                /**
+                 * Follow links that point outside the source domain. Must stay `false` — discover
+                 * crawls are restricted to the zone you own.
+                 */
+                include_external_links?: boolean;
+                /**
+                 * Follow links to subdomains of the source host.
+                 */
+                include_subdomains?: boolean;
+                /**
+                 * Maximum number of pages to crawl (1-100000).
+                 */
+                limit?: number;
+                /**
+                 * Maximum content age in seconds to accept (0–604800).
+                 */
+                max_age?: number;
+                /**
+                 * Where the crawler looks for URLs: 'sitemaps' reads sitemap XML only, 'links'
+                 * follows page links only, 'all' does both.
+                 */
+                source?: 'all' | 'sitemaps' | 'links';
+            }
             interface ParseOptions {
                 /**
                  * List of path-to-selector mappings for extracting specific content from crawled
@@ -2070,7 +2378,7 @@ export interface InstanceChatCompletionsParams {
 }
 export declare namespace InstanceChatCompletionsParams {
     interface Message {
-        content: string | Array<Message.UnionMember0 | Message.UnionMember1> | null;
+        content: string | Array<Message.UnionMember0 | Message.UnionMember1 | Message.UnionMember2> | null;
         role: 'system' | 'developer' | 'user' | 'assistant' | 'tool';
         [k: string]: unknown;
     }
@@ -2088,6 +2396,17 @@ export declare namespace InstanceChatCompletionsParams {
                 url: string;
             }
         }
+        interface UnionMember2 {
+            file: UnionMember2.File;
+            type: 'file';
+        }
+        namespace UnionMember2 {
+            interface File {
+                filename: string;
+                file_data?: string;
+                file_id?: string;
+            }
+        }
     }
     interface AISearchOptions {
         cache?: AISearchOptions.Cache;
@@ -2256,7 +2575,7 @@ export declare namespace InstanceSearchParams {
         }
     }
     interface Message {
-        content: string | Array<Message.UnionMember0 | Message.UnionMember1> | null;
+        content: string | Array<Message.UnionMember0 | Message.UnionMember1 | Message.UnionMember2> | null;
         role: 'system' | 'developer' | 'user' | 'assistant' | 'tool';
         [k: string]: unknown;
     }
@@ -2274,6 +2593,17 @@ export declare namespace InstanceSearchParams {
                 url: string;
             }
         }
+        interface UnionMember2 {
+            file: UnionMember2.File;
+            type: 'file';
+        }
+        namespace UnionMember2 {
+            interface File {
+                filename: string;
+                file_data?: string;
+                file_id?: string;
+            }
+        }
     }
 }
 export interface InstanceStatsParams {