Interface: ChatMiddlewareContext<TContext>#

Defined in: packages/ai/src/activities/chat/middleware/types.ts:37

Stable context object passed to all middleware hooks. Created once per chat() invocation and shared across all hooks.

Type Parameters#

TContext#

TContext = unknown

Properties#

abort()#

abort: (reason?) => void;

abort: (reason?) => void;

Defined in: packages/ai/src/activities/chat/middleware/types.ts:66

Abort the chat run with a reason

Parameters#

reason?#

string

Returns#

void

accumulatedContent#

accumulatedContent: string;

accumulatedContent: string;

Defined in: packages/ai/src/activities/chat/middleware/types.ts:110

Accumulated text content for the current iteration

chunkIndex#

chunkIndex: number;

chunkIndex: number;

Defined in: packages/ai/src/activities/chat/middleware/types.ts:62

Running count of chunks yielded so far

context#

context: TContext;

context: TContext;

Defined in: packages/ai/src/activities/chat/middleware/types.ts:68

Runtime context provided by chat() options

conversationId?#

optional conversationId: string;

optional conversationId: string;

Defined in: packages/ai/src/activities/chat/middleware/types.ts:56

Deprecated#

Use threadId instead. Retained as an alias of threadId so middleware written before the AG-UI rename keeps working unchanged. Will be removed in a future major release.

createId()#

createId: (prefix) => string;

createId: (prefix) => string;

Defined in: packages/ai/src/activities/chat/middleware/types.ts:117

Generate a unique ID with the given prefix

Parameters#

prefix#

string

Returns#

string

currentMessageId#

currentMessageId: string | null;

currentMessageId: string | null;

Defined in: packages/ai/src/activities/chat/middleware/types.ts:108

Current assistant message ID (changes per iteration)

defer()#

defer: (promise) => void;

defer: (promise) => void;

Defined in: packages/ai/src/activities/chat/middleware/types.ts:74

Defer a non-blocking side-effect promise. Deferred promises do not block streaming and are awaited after the terminal hook (onFinish/onAbort/onError).

Parameters#

promise#

Promise<unknown>

Returns#

void

hasTools#

hasTools: boolean;

hasTools: boolean;

Defined in: packages/ai/src/activities/chat/middleware/types.ts:103

Whether tools are configured

iteration#

iteration: number;

iteration: number;

Defined in: packages/ai/src/activities/chat/middleware/types.ts:60

Current agent loop iteration (0-indexed)

messageCount#

messageCount: number;

messageCount: number;

Defined in: packages/ai/src/activities/chat/middleware/types.ts:101

Number of messages at the start of the request

messages#

messages: readonly ModelMessage<
  | string
  | ContentPart<unknown, unknown, unknown, unknown, unknown>[]
  | null>[];

messages: readonly ModelMessage<
  | string
  | ContentPart<unknown, unknown, unknown, unknown, unknown>[]
  | null>[];

Defined in: packages/ai/src/activities/chat/middleware/types.ts:115

Current messages array (read-only view)

model#

model: string;

model: string;

Defined in: packages/ai/src/activities/chat/middleware/types.ts:81

Model identifier (e.g., 'gpt-4o')

modelOptions?#

optional modelOptions: Record<string, unknown>;

optional modelOptions: Record<string, unknown>;

Defined in: packages/ai/src/activities/chat/middleware/types.ts:96

Provider-specific model options

options?#

optional options: Record<string, unknown>;

optional options: Record<string, unknown>;

Defined in: packages/ai/src/activities/chat/middleware/types.ts:94

Flattened generation options (metadata)

phase#

phase: ChatMiddlewarePhase;

phase: ChatMiddlewarePhase;

Defined in: packages/ai/src/activities/chat/middleware/types.ts:58

Current lifecycle phase

provider#

provider: string;

provider: string;

Defined in: packages/ai/src/activities/chat/middleware/types.ts:79

Provider name (e.g., 'openai', 'anthropic')

requestId#

requestId: string;

requestId: string;

Defined in: packages/ai/src/activities/chat/middleware/types.ts:39

Unique identifier for this chat request

runId#

runId: string;

runId: string;

Defined in: packages/ai/src/activities/chat/middleware/types.ts:43

AG-UI run identifier for correlating client and server events

signal?#

optional signal: AbortSignal;

optional signal: AbortSignal;

Defined in: packages/ai/src/activities/chat/middleware/types.ts:64

Abort signal from the chat request

source#

source: "server" | "client";

source: "server" | "client";

Defined in: packages/ai/src/activities/chat/middleware/types.ts:83

Source of the chat invocation — always 'server' for server-side chat

streamId#

streamId: string;

streamId: string;

Defined in: packages/ai/src/activities/chat/middleware/types.ts:41

Unique identifier for this stream

streaming#

streaming: boolean;

streaming: boolean;

Defined in: packages/ai/src/activities/chat/middleware/types.ts:85

Whether the chat is streaming

systemPrompts#

systemPrompts: SystemPrompt[];

systemPrompts: SystemPrompt[];

Defined in: packages/ai/src/activities/chat/middleware/types.ts:90

System prompts configured for this chat

threadId#

threadId: string;

threadId: string;

Defined in: packages/ai/src/activities/chat/middleware/types.ts:50

AG-UI thread identifier — a stable per-conversation ID used to correlate client and server devtools events. Resolves to the caller-provided threadId (or legacy conversationId), or an auto-generated value when neither is supplied.

toolNames?#

optional toolNames: string[];

optional toolNames: string[];

Defined in: packages/ai/src/activities/chat/middleware/types.ts:92

Names of configured tools, if any