@oh-my-pi/pi-ai 18.1.1 → 18.1.2

package/CHANGELOG.md

@@ -2,6 +2,22 @@
 
 ## [Unreleased]
 
+## [18.1.2] - 2026-09-01
+
+### Added
+
+- Added thinking controls for Amazon Bedrock models.
+- Added dynamic mid-conversation updates for Anthropic system prompts, tools, and reasoning effort.
+- Added deferred tool loading and prompt caching for Anthropic models.
+- Added configurable handling for invalid Anthropic thinking blocks through `anthropicPrefixMismatchBehavior`.
+
+### Fixed
+
+- Fixed compatibility issues with Anthropic thinking and prompt-cache breakpoints across deployments, preserving valid reasoning context while preventing invalid-signature errors.
+- Fixed incorrect operating-system information reported in request headers on non-Linux systems.
+- Fixed Google Antigravity quota handling so requests rotate to another account with available usage instead of unnecessarily switching models.
+- Fixed Anthropic authentication for newer models by updating the Claude Code request fingerprint.
+
 ## [18.1.0] - 2026-09-01
 
 ### Added

package/dist/types/auth-gateway/types.d.ts

@@ -60,6 +60,8 @@ export interface AuthGatewayParsedRequestOptions {
     hideThinkingSummary?: boolean;
     /** Anthropic `output_config.task_budget` advisory loop budget. */
     taskBudget?: TokenTaskBudget;
+    /** Anthropic preserved-thinking behavior for a changed conversation prefix. */
+    anthropicPrefixMismatchBehavior?: "drop_block" | "error";
     /** OpenAI service tier (auto|default|flex|scale|priority). */
     serviceTier?: ServiceTier;
     /** Cache retention hint derived from inbound `cache_control` markers. */

package/dist/types/providers/anthropic-messages-server-schema.d.ts

@@ -196,24 +196,56 @@ export declare const userMessageSchema: import("@oh-my-pi/omptype").FluentType<{
     role: "user";
 }>;
 export declare const systemMessageSchema: import("@oh-my-pi/omptype").FluentType<{
-    content: string | {
+    clear_at?: "never" | "next_user_message" | undefined;
+    content: string | ({
         cache_control?: {
             ttl?: "1h" | "5m" | undefined;
             type: "ephemeral";
         } | undefined;
         text: string;
         type: "text";
-    }[];
+    } | {
+        tool: {
+            name: string;
+            type: "tool_reference";
+        };
+        type: "tool_addition";
+    } | {
+        tool: {
+            name: string;
+            type: "tool_reference";
+        };
+        type: "tool_removal";
+    })[];
+    output_config?: {
+        effort?: "high" | "low" | "max" | "medium" | "xhigh" | undefined;
+    } | undefined;
     role: "system";
 }, {
-    content: string | {
+    clear_at?: "never" | "next_user_message" | undefined;
+    content: string | ({
         cache_control?: {
             ttl?: "1h" | "5m" | undefined;
             type: "ephemeral";
         } | undefined;
         text: string;
         type: "text";
-    }[];
+    } | {
+        tool: {
+            name: string;
+            type: "tool_reference";
+        };
+        type: "tool_addition";
+    } | {
+        tool: {
+            name: string;
+            type: "tool_reference";
+        };
+        type: "tool_removal";
+    })[];
+    output_config?: {
+        effort?: "high" | "low" | "max" | "medium" | "xhigh" | undefined;
+    } | undefined;
     role: "system";
 }>;
 export declare const assistantMessageSchema: import("@oh-my-pi/omptype").FluentType<{
@@ -352,14 +384,30 @@ export declare const messageSchema: import("@oh-my-pi/omptype").FluentType<{
     })[];
     role: "user";
 } | {
-    content: string | {
+    clear_at?: "never" | "next_user_message" | undefined;
+    content: string | ({
         cache_control?: {
             ttl?: "1h" | "5m" | undefined;
             type: "ephemeral";
         } | undefined;
         text: string;
         type: "text";
-    }[];
+    } | {
+        tool: {
+            name: string;
+            type: "tool_reference";
+        };
+        type: "tool_addition";
+    } | {
+        tool: {
+            name: string;
+            type: "tool_reference";
+        };
+        type: "tool_removal";
+    })[];
+    output_config?: {
+        effort?: "high" | "low" | "max" | "medium" | "xhigh" | undefined;
+    } | undefined;
     role: "system";
 } | {
     content: string | ({
@@ -460,14 +508,30 @@ export declare const messageSchema: import("@oh-my-pi/omptype").FluentType<{
     })[];
     role: "user";
 } | {
-    content: string | {
+    clear_at?: "never" | "next_user_message" | undefined;
+    content: string | ({
         cache_control?: {
             ttl?: "1h" | "5m" | undefined;
             type: "ephemeral";
         } | undefined;
         text: string;
         type: "text";
-    }[];
+    } | {
+        tool: {
+            name: string;
+            type: "tool_reference";
+        };
+        type: "tool_addition";
+    } | {
+        tool: {
+            name: string;
+            type: "tool_reference";
+        };
+        type: "tool_removal";
+    })[];
+    output_config?: {
+        effort?: "high" | "low" | "max" | "medium" | "xhigh" | undefined;
+    } | undefined;
     role: "system";
 } | {
     content: string | ({
@@ -511,6 +575,7 @@ export declare const toolSchema: import("@oh-my-pi/omptype").FluentType<{
         ttl?: "1h" | "5m" | undefined;
         type: "ephemeral";
     } | undefined;
+    defer_loading?: boolean | undefined;
     description?: string | undefined;
     input_schema: Record<string, unknown>;
     name: string;
@@ -519,6 +584,7 @@ export declare const toolSchema: import("@oh-my-pi/omptype").FluentType<{
         ttl?: "1h" | "5m" | undefined;
         type: "ephemeral";
     } | undefined;
+    defer_loading?: boolean | undefined;
     description?: string | undefined;
     input_schema: Record<string, unknown>;
     name: string;
@@ -554,14 +620,23 @@ export declare const thinkingConfigSchema: import("@oh-my-pi/omptype").FluentTyp
     display?: unknown;
     type: "disabled";
 } | {
+    block_binding?: {
+        prefix_mismatch_behavior: "drop_block" | "error";
+    } | undefined;
     budget_tokens?: number | undefined;
     display?: unknown;
     type: "adaptive";
 } | {
+    block_binding?: {
+        prefix_mismatch_behavior: "drop_block" | "error";
+    } | undefined;
     budget_tokens: number;
     display?: unknown;
     type: "enabled";
 }, {
+    block_binding?: {
+        prefix_mismatch_behavior: "drop_block" | "error";
+    } | undefined;
     budget_tokens: number;
     display?: unknown;
     type: "enabled";
@@ -569,6 +644,9 @@ export declare const thinkingConfigSchema: import("@oh-my-pi/omptype").FluentTyp
     display?: unknown;
     type: "disabled";
 } | {
+    block_binding?: {
+        prefix_mismatch_behavior: "drop_block" | "error";
+    } | undefined;
     budget_tokens?: number | undefined;
     display?: unknown;
     type: "adaptive";
@@ -641,14 +719,30 @@ export declare const anthropicMessagesRequestSchema: import("@oh-my-pi/omptype")
         })[];
         role: "user";
     } | {
-        content: string | {
+        clear_at?: "never" | "next_user_message" | undefined;
+        content: string | ({
             cache_control?: {
                 ttl?: "1h" | "5m" | undefined;
                 type: "ephemeral";
             } | undefined;
             text: string;
             type: "text";
-        }[];
+        } | {
+            tool: {
+                name: string;
+                type: "tool_reference";
+            };
+            type: "tool_addition";
+        } | {
+            tool: {
+                name: string;
+                type: "tool_reference";
+            };
+            type: "tool_removal";
+        })[];
+        output_config?: {
+            effort?: "high" | "low" | "max" | "medium" | "xhigh" | undefined;
+        } | undefined;
         role: "system";
     } | {
         content: string | ({
@@ -714,10 +808,16 @@ export declare const anthropicMessagesRequestSchema: import("@oh-my-pi/omptype")
         display?: unknown;
         type: "disabled";
     } | {
+        block_binding?: {
+            prefix_mismatch_behavior: "drop_block" | "error";
+        } | undefined;
         budget_tokens?: number | undefined;
         display?: unknown;
         type: "adaptive";
     } | {
+        block_binding?: {
+            prefix_mismatch_behavior: "drop_block" | "error";
+        } | undefined;
         budget_tokens: number;
         display?: unknown;
         type: "enabled";
@@ -741,6 +841,7 @@ export declare const anthropicMessagesRequestSchema: import("@oh-my-pi/omptype")
             ttl?: "1h" | "5m" | undefined;
             type: "ephemeral";
         } | undefined;
+        defer_loading?: boolean | undefined;
         description?: string | undefined;
         input_schema: Record<string, unknown>;
         name: string;
@@ -815,14 +916,30 @@ export declare const anthropicMessagesRequestSchema: import("@oh-my-pi/omptype")
         })[];
         role: "user";
     } | {
-        content: string | {
+        clear_at?: "never" | "next_user_message" | undefined;
+        content: string | ({
             cache_control?: {
                 ttl?: "1h" | "5m" | undefined;
                 type: "ephemeral";
             } | undefined;
             text: string;
             type: "text";
-        }[];
+        } | {
+            tool: {
+                name: string;
+                type: "tool_reference";
+            };
+            type: "tool_addition";
+        } | {
+            tool: {
+                name: string;
+                type: "tool_reference";
+            };
+            type: "tool_removal";
+        })[];
+        output_config?: {
+            effort?: "high" | "low" | "max" | "medium" | "xhigh" | undefined;
+        } | undefined;
         role: "system";
     } | {
         content: string | ({
@@ -885,6 +1002,9 @@ export declare const anthropicMessagesRequestSchema: import("@oh-my-pi/omptype")
     }[] | undefined;
     temperature?: number | undefined;
     thinking?: {
+        block_binding?: {
+            prefix_mismatch_behavior: "drop_block" | "error";
+        } | undefined;
         budget_tokens: number;
         display?: unknown;
         type: "enabled";
@@ -892,6 +1012,9 @@ export declare const anthropicMessagesRequestSchema: import("@oh-my-pi/omptype")
         display?: unknown;
         type: "disabled";
     } | {
+        block_binding?: {
+            prefix_mismatch_behavior: "drop_block" | "error";
+        } | undefined;
         budget_tokens?: number | undefined;
         display?: unknown;
         type: "adaptive";
@@ -915,6 +1038,7 @@ export declare const anthropicMessagesRequestSchema: import("@oh-my-pi/omptype")
             ttl?: "1h" | "5m" | undefined;
             type: "ephemeral";
         } | undefined;
+        defer_loading?: boolean | undefined;
         description?: string | undefined;
         input_schema: Record<string, unknown>;
         name: string;

package/dist/types/providers/anthropic-messages-server.d.ts

@@ -8,7 +8,7 @@ import type { AuthGatewayStreamControl, AuthGatewayParsedRequest as ParsedReques
 export type { ParsedRequest };
 export declare function parseRequest(body: unknown, headers?: Headers): ParsedRequest;
 export declare function encodeResponse(message: AssistantMessage, requestedModelId: string): Record<string, unknown>;
-export declare function encodeStream(events: AssistantMessageEventStream, requestedModelId: string, _options?: ParsedRequest["options"], control?: AuthGatewayStreamControl): ReadableStream<Uint8Array>;
+export declare function encodeStream(events: AssistantMessageEventStream, requestedModelId: string, options?: ParsedRequest["options"], control?: AuthGatewayStreamControl): ReadableStream<Uint8Array>;
 /**
  * Anthropic error envelope: `{ type: "error", error: { type, message } }`.
  * See https://docs.anthropic.com/en/api/errors. Returned as a `Response` so

package/dist/types/providers/anthropic-wire.d.ts

@@ -11,7 +11,9 @@
  * `scope`, tool `strict`/`eager_input_streaming`, mid-conversation `system`
  * role) are first-class here instead of being patched in via casts.
  */
-import type { TokenTaskBudget } from "../types.js";
+import type { ProviderInputTransformation, TokenTaskBudget } from "../types.js";
+/** Beta enabling preserved-thinking block controls and transformation reports. */
+export declare const THINKING_BINDING_CONTROLS_BETA = "thinking-binding-controls-2026-08-01";
 /** Ephemeral prefix-cache breakpoint marker. */
 export type CacheControlEphemeral = {
     type: "ephemeral";
@@ -87,6 +89,18 @@ export type ToolSearchToolResultBlockParam = {
     content: unknown;
     [key: string]: unknown;
 };
+export type ToolChangeReferenceParam = {
+    type: "tool_reference";
+    name: string;
+};
+export type ToolAdditionBlockParam = {
+    type: "tool_addition";
+    tool: ToolChangeReferenceParam;
+};
+export type ToolRemovalBlockParam = {
+    type: "tool_removal";
+    tool: ToolChangeReferenceParam;
+};
 /** Anthropic server-tool history variants omp can replay atomically. */
 export type AnthropicServerToolHistoryBlockParam = WebSearchServerToolUseBlockParam | WebSearchToolResultBlockParam | ToolSearchServerToolUseBlockParam | ToolSearchToolResultBlockParam;
 /** True when a block is complete Anthropic server-tool history omp can replay. */
@@ -121,7 +135,7 @@ export type FallbackBlockParam = {
         model: string;
     };
 };
-export type ContentBlockParam = TextBlockParam | ImageBlockParam | ToolUseBlockParam | ToolResultBlockParam | ServerToolUseBlockParam | WebSearchToolResultBlockParam | ToolSearchToolResultBlockParam | ThinkingBlockParam | RedactedThinkingBlockParam | FallbackBlockParam;
+export type ContentBlockParam = TextBlockParam | ImageBlockParam | ToolUseBlockParam | ToolResultBlockParam | ServerToolUseBlockParam | WebSearchToolResultBlockParam | ToolSearchToolResultBlockParam | ToolAdditionBlockParam | ToolRemovalBlockParam | ThinkingBlockParam | RedactedThinkingBlockParam | FallbackBlockParam;
 /**
  * A single conversation turn.
  *
@@ -132,6 +146,10 @@ export type ContentBlockParam = TextBlockParam | ImageBlockParam | ToolUseBlockP
 export type MessageParam = {
     role: "user" | "assistant" | "system";
     content: string | ContentBlockParam[];
+    /** Turn-scoped system-message lifetime. */
+    clear_at?: "never" | "next_user_message";
+    /** Per-message effort override. */
+    output_config?: OutputConfig;
 };
 export type ToolInputSchema = {
     type: "object";
@@ -148,6 +166,8 @@ export type Tool = {
     strict?: boolean;
     /** Fine-grained tool streaming beta: stream tool input as it is generated. */
     eager_input_streaming?: boolean;
+    /** Withhold this tool until a later `tool_addition` block references it. */
+    defer_loading?: boolean;
 };
 export type ToolChoiceAuto = {
     type: "auto";
@@ -169,11 +189,16 @@ export type ToolChoice = ToolChoiceAuto | ToolChoiceAny | ToolChoiceTool | ToolC
 export type Metadata = {
     user_id?: string | null;
 };
+export type ThinkingBlockBinding = {
+    prefix_mismatch_behavior: "drop_block" | "error";
+};
 export type ThinkingConfigEnabled = {
     type: "enabled";
     budget_tokens: number;
     /** Opus 4.7+ reasoning display mode. */
     display?: "summarized" | "omitted";
+    /** Preserved-thinking prefix mismatch policy. */
+    block_binding?: ThinkingBlockBinding;
 };
 export type ThinkingConfigDisabled = {
     type: "disabled";
@@ -182,6 +207,8 @@ export type ThinkingConfigAdaptive = {
     type: "adaptive";
     /** Opus 4.7+ reasoning display mode. */
     display?: "summarized" | "omitted";
+    /** Preserved-thinking prefix mismatch policy. */
+    block_binding?: ThinkingBlockBinding;
 };
 export type ThinkingConfigParam = ThinkingConfigEnabled | ThinkingConfigDisabled | ThinkingConfigAdaptive;
 export type OutputConfig = {
@@ -228,6 +255,8 @@ export type MessageCreateParams = {
     speed?: "fast";
     /** Claude Code context-management beta. */
     context_management?: ContextManagement;
+    /** Google Cloud rawPredict carries Anthropic beta names in the body. */
+    anthropic_beta?: string[];
     /**
      * Server-side fallback beta chain — up to three fallback models the API
      * retries when a classifier blocks the primary. Required companion beta
@@ -271,6 +300,14 @@ export type Usage = {
     iterations?: UsageIteration[] | null;
 };
 /** The `message` envelope carried by `message_start`. */
+export type InputTransformation = {
+    type: string;
+    path?: string;
+    reason?: string;
+    [key: string]: unknown;
+};
+/** Parse Anthropic's forward-compatible input transformation list. */
+export declare function parseAnthropicInputTransformations(value: unknown): ProviderInputTransformation[];
 export type ResponseMessage = {
     id: string;
     type?: "message";
@@ -279,6 +316,7 @@ export type ResponseMessage = {
     content?: unknown[];
     stop_reason?: StopReason | null;
     stop_sequence?: string | null;
+    input_transformations?: InputTransformation[];
     usage: Usage;
 };
 /** `content_block` payload carried by `content_block_start`. */
@@ -351,6 +389,7 @@ export type RawMessageDeltaEvent = {
     type: "message_delta";
     delta: MessageDelta;
     usage: Usage;
+    input_transformations?: InputTransformation[];
 };
 export type RawMessageStopEvent = {
     type: "message_stop";

package/dist/types/providers/anthropic.d.ts

@@ -1,6 +1,6 @@
 import type { Api, FetchImpl, Message, Model, ProviderSessionState, ServiceTier, SimpleStreamOptions, StreamFunction, StreamOptions, Usage } from "../types.js";
 import { type AnthropicFetchOptions, type AnthropicMessagesClientLike } from "./anthropic-client.js";
-import { type FallbackParam, type MessageParam } from "./anthropic-wire.js";
+import { type FallbackParam, type MessageParam, type TextBlockParam } from "./anthropic-wire.js";
 export type AnthropicHeaderOptions = {
     apiKey: string;
     baseUrl?: string;
@@ -10,13 +10,14 @@ export type AnthropicHeaderOptions = {
     modelHeaders?: Record<string, string>;
     isCloudflareAiGateway?: boolean;
     claudeCodeSessionId?: string;
-    coworkBetas?: readonly string[];
+    claudeCodeBetas?: readonly string[];
     /** Allow explicit fingerprint headers to replace OAuth defaults on non-official endpoints. */
     allowAnthropicHeaderOverrides?: boolean;
 };
 export declare function normalizeAnthropicBaseUrl(baseUrl?: string): string | undefined;
 export declare function buildBetaHeader(baseBetas: readonly string[], extraBetas: readonly string[]): string;
 export declare function buildAnthropicHeaders(options: AnthropicHeaderOptions): Record<string, string>;
+type AnthropicCacheControl = NonNullable<TextBlockParam["cache_control"]>;
 /**
  * Clears the in-session "server rejected fast mode" sticky flag. Call when the
  * caller is explicitly re-arming `serviceTier: "priority"` (e.g. user toggled
@@ -32,12 +33,15 @@ export declare function clearAnthropicFastModeFallback(providerSessionState: Map
  */
 export declare function isAnthropicFastModeFallbackDisabled(providerSessionState: Map<string, ProviderSessionState> | undefined, model: Model<Api>): boolean;
 export * from "./claude-code-fingerprint.js";
+/** Maps Node's platform identifier to the Stainless wire value. */
+export declare function mapStainlessOs(platform: string): "MacOS" | "Windows" | "Linux" | "FreeBSD" | `Other::${string}`;
+/** Maps Node's architecture identifier to the Stainless wire value. */
 export declare function mapStainlessArch(arch: string): "x64" | "arm64" | "x86" | `other::${string}`;
-/** Static headers emitted by Cowork's Linux Claude runtime. */
-export declare const coworkHeaders: {
+/** Static headers emitted by Claude Code's CLI runtime. */
+export declare const claudeCodeHeaders: {
     "X-Stainless-Arch": "arm64" | "x64" | "x86" | `other::${string}`;
     "X-Stainless-Lang": string;
-    "X-Stainless-OS": string;
+    "X-Stainless-OS": "FreeBSD" | "Linux" | "MacOS" | "Windows" | `Other::${string}`;
     "X-Stainless-Package-Version": string;
     "X-Stainless-Retry-Count": string;
     "X-Stainless-Runtime": string;
@@ -207,6 +211,8 @@ export type AnthropicUsageLike = {
  * zero-valued objects clear prior extras from earlier stream usage snapshots.
  */
 export declare function applyAnthropicUsageExtras(usage: Usage, source: AnthropicUsageLike): void;
+/** Detects the preserved-thinking error caused by rewriting a signed block's conversation prefix. */
+export declare function isThinkingPrefixBindingError(message: string): boolean;
 export declare function isInvalidThinkingSignatureError(message: string): boolean;
 /**
  * Prepend a pointed remediation to Anthropic's `Invalid signature in thinking
@@ -225,12 +231,15 @@ export declare const streamAnthropic: StreamFunction<"anthropic-messages">;
 export type AnthropicSystemBlock = {
     type: "text";
     text: string;
+    cache_control?: AnthropicCacheControl;
 };
 type SystemBlockOptions = {
     includeClaudeCodeInstruction?: boolean;
     extraInstructions?: string[];
     /** Text of the first user message — used as fingerprint seed for the billing header. */
     firstUserMessageText?: string;
+    /** Cache lifetime shared by the OAuth system breakpoint and later message breakpoints. */
+    cacheControl?: AnthropicCacheControl;
 };
 export declare function buildAnthropicSystemBlocks(systemPrompt: readonly string[] | undefined, options?: SystemBlockOptions): AnthropicSystemBlock[] | undefined;
 export declare function normalizeExtraBetas(betas?: string[] | string): string[];
@@ -251,5 +260,7 @@ export type AnthropicMessageParam = MessageParam;
  */
 export declare function convertAnthropicMessages(messages: Message[], model: Model<"anthropic-messages">, isOAuthToken: boolean, opts?: {
     serverSideFallbackEnabled?: boolean;
+    dropAllThinking?: boolean;
+    droppedThinkingBlocks?: ReadonlySet<string>;
 }): AnthropicMessageParam[];
 export declare function normalizeAnthropicToolSchema(schema: unknown): unknown;

package/dist/types/providers/claude-code-fingerprint.d.ts

@@ -1,5 +1,5 @@
 /**
- * Cowork inference-fingerprint constants, kept in a leaf module so consumers
+ * Claude Code inference-fingerprint constants, kept in a leaf module so consumers
  * outside the provider (`registry/oauth/anthropic`, `usage/claude`) don't
  * import the heavy `providers/anthropic` module.
  *
@@ -7,15 +7,15 @@
  * `registry` → `registry/oauth/anthropic` → back into the still-initializing
  * provider module.
  */
-/** Claude runtime version bundled by the current Cowork desktop release. */
-export declare const claudeCodeVersion = "2.1.246";
-/** `@anthropic-ai/sdk` version bundled by the current Cowork desktop release. */
+/** Current Claude Code CLI version represented on the Anthropic wire. */
+export declare const claudeCodeVersion = "2.1.257";
+/** `@anthropic-ai/sdk` version bundled by the current Claude Code release. */
 export declare const claudeCodeSdkVersion = "0.112.1";
-/** User-Agent emitted by Cowork's `claude-desktop` inference entrypoint. */
-export declare const coworkUserAgent = "claude-cli/2.1.246 (external, claude-desktop)";
+/** User-Agent emitted by Claude Code's CLI inference entrypoint. */
+export declare const claudeCodeUserAgent = "claude-cli/2.1.257 (external, cli)";
 /** Prefix used to isolate custom Anthropic OAuth tools from built-in tools. */
 export declare const claudeToolPrefix: string;
-/** Identity block prepended by Cowork's Claude runtime. */
-export declare const claudeCodeSystemInstruction = "You are a Claude agent, built on Anthropic's Claude Agent SDK.";
-/** Cowork's per-request output-token ceiling. */
+/** Identity block prepended by Claude Code's CLI runtime. */
+export declare const claudeCodeSystemInstruction = "You are Claude Code, Anthropic's official CLI for Claude.";
+/** Claude Code's per-request output-token ceiling. */
 export declare const CLAUDE_CODE_MAX_OUTPUT_TOKENS = 64000;

package/dist/types/types.d.ts

@@ -236,6 +236,11 @@ export interface StreamOptions {
      * Side-channel and advisor requests must leave it unset.
      */
     anthropicCacheRefresh?: boolean;
+    /**
+     * Anthropic preserved-thinking behavior when a signed block no longer matches
+     * its conversation prefix. Binding-capable models default to `"drop_block"`.
+     */
+    anthropicPrefixMismatchBehavior?: "drop_block" | "error";
     /** @internal Marks a replay-only Anthropic request that must use non-streaming `max_tokens: 0`. */
     anthropicCacheRefreshRequest?: boolean;
     /**
@@ -679,7 +684,24 @@ export interface OpenAIResponsesHistoryPayload {
     dt?: boolean;
     items: Array<Record<string, unknown>>;
 }
-export type ProviderPayload = OpenAIResponsesHistoryPayload;
+/** Anthropic-only controls attached to a mid-conversation system message. */
+export interface AnthropicMessagePayload {
+    type: "anthropicMessage";
+    clearAt?: "never" | "next_user_message";
+    effort?: "low" | "medium" | "high" | "xhigh" | "max";
+    toolChanges?: Array<{
+        type: "tool_addition" | "tool_removal";
+        name: string;
+    }>;
+}
+export type ProviderPayload = OpenAIResponsesHistoryPayload | AnthropicMessagePayload;
+/** Provider-reported rewrite applied to request content before inference. */
+export interface ProviderInputTransformation {
+    type: string;
+    path?: string;
+    reason?: string;
+    [key: string]: unknown;
+}
 export interface UserMessage {
     role: "user";
     content: string | (TextContent | ImageContent)[];
@@ -687,6 +709,8 @@ export interface UserMessage {
     synthetic?: boolean;
     /** True when injected mid-turn as a steer; consumed by the agent's pre-LLM transform to wrap it for emphasis. Never rendered. */
     steering?: boolean;
+    /** Timestamp of a client-side history rewrite represented by this message. */
+    historyRewriteAt?: number;
     /** Who initiated this message for billing/attribution semantics. */
     attribution?: MessageAttribution;
     /** Provider-specific opaque payload used to reconstruct transport-native history. */
@@ -782,6 +806,8 @@ export interface AssistantMessage {
      * server's actual state.
      */
     disabledFeatures?: string[];
+    /** Provider-reported input rewrites such as dropped bound-thinking blocks. */
+    inputTransformations?: ProviderInputTransformation[];
     /** Provider-specific opaque payload used to reconstruct transport-native history. */
     providerPayload?: ProviderPayload;
     timestamp: number;
@@ -1033,6 +1059,8 @@ export interface Tool<TParameters extends TSchema = TSchema> {
     parameters: TParameters;
     /** If true, tool is strictly typed and validated against the parameters schema before execution */
     strict?: boolean;
+    /** Withhold this Anthropic tool until a `tool_addition` message references it. */
+    deferLoading?: boolean;
     /**
      * Optional grammar constraint for OpenAI custom-tool emission.
      * When set, providers that support grammar-constrained tools (currently only

package/package.json

@@ -1,7 +1,7 @@
 {
 	"type": "module",
 	"name": "@oh-my-pi/pi-ai",
-	"version": "18.1.1",
+	"version": "18.1.2",
 	"description": "Unified LLM API with automatic model discovery and provider configuration",
 	"homepage": "https://omp.sh",
 	"author": "Stencil Labs, Inc.",
@@ -37,10 +37,10 @@
 		"fmt": "oxfmt --no-error-on-unmatched-pattern 'src/**/*.{ts,tsx}' '{test,bench,examples,scripts}/**/*.ts' '*.ts'"
 	},
 	"dependencies": {
-		"@oh-my-pi/omptype": "18.1.1",
-		"@oh-my-pi/pi-catalog": "18.1.1",
-		"@oh-my-pi/pi-utils": "18.1.1",
-		"@oh-my-pi/pi-wire": "18.1.1"
+		"@oh-my-pi/omptype": "18.1.2",
+		"@oh-my-pi/pi-catalog": "18.1.2",
+		"@oh-my-pi/pi-utils": "18.1.2",
+		"@oh-my-pi/pi-wire": "18.1.2"
 	},
 	"devDependencies": {
 		"@types/bun": "^1.3.14"

package/src/auth-gateway/server.ts

@@ -159,6 +159,9 @@ function buildStreamOptions(parsed: ParsedFormatRequest, api: Api, signal: Abort
 	if (options.disableReasoning !== undefined) opts.disableReasoning = options.disableReasoning;
 	if (options.hideThinkingSummary !== undefined) opts.hideThinkingSummary = options.hideThinkingSummary;
 	if (options.taskBudget !== undefined) opts.taskBudget = options.taskBudget;
+	if (options.anthropicPrefixMismatchBehavior !== undefined) {
+		opts.anthropicPrefixMismatchBehavior = options.anthropicPrefixMismatchBehavior;
+	}
 	if (options.serviceTier !== undefined) opts.serviceTier = options.serviceTier;
 	if (options.cacheRetention !== undefined) opts.cacheRetention = options.cacheRetention;
 	if (options.include !== undefined) opts.include = options.include;