Fix typos across repo

.changeset/tame-deers-shake.md

@@ -0,0 +1,7 @@
+---
+"@openai/agents-core": patch
+"@openai/agents-openai": patch
+"@openai/agents-realtime": patch
+---
+
+Fix typos across repo

docs/src/content/docs/extensions/twilio.mdx

@@ -12,7 +12,7 @@ raw audio from a phone call to a WebSocket server. This set up can be used to co
 [voice agents](/openai-agents-js/guides/voice-agents) to Twilio. You can use the default Realtime Session transport
 in `websocket` mode to connect the events coming from Twilio to your Realtime Session. However,
 this requires you to set the right audio format and adjust your own interruption timing as phone
-calls will naturally introduce more latency than a web-based converstaion.
+calls will naturally introduce more latency than a web-based conversation.
 
 To improve the set up experience, we've created a dedicated transport layer that handles the
 connection to Twilio for you, including handling interruptions and audio forwarding for you.
@@ -72,7 +72,7 @@ for more information on how to use the `RealtimeSession` with voice agents.
 
    In order to receive all the necessary events and audio from Twilio, you should create your
    `TwilioRealtimeTransportLayer` instance as soon as you have a reference to the WebSocket
-   connetion and immediately call `session.connect()` afterwards.
+   connection and immediately call `session.connect()` afterwards.
 
 2. **Access the raw Twilio events.**
 

docs/src/content/docs/guides/mcp.mdx

@@ -59,7 +59,7 @@ To stream incremental MCP results, pass `stream: true` when you run the `Agent`:
 
 For sensitive operations you can require human approval of individual tool calls. Pass either `requireApproval: 'always'` or a fine‑grained object mapping tool names to `'never'`/`'always'`.
 
-If you can programatically determine whether a tool call is safe, you can use the [`onApproval` callback](https://github.com/openai/openai-agents-js/blob/main/examples/mcp/hosted-mcp-on-approval.ts) to approve or reject the tool call. If you require human approval, you can use the same [human-in-the-loop (HITL) approach](/openai-agents-js/guides/human-in-the-loop/) using `interruptions` as for local function tools.
+If you can programmatically determine whether a tool call is safe, you can use the [`onApproval` callback](https://github.com/openai/openai-agents-js/blob/main/examples/mcp/hosted-mcp-on-approval.ts) to approve or reject the tool call. If you require human approval, you can use the same [human-in-the-loop (HITL) approach](/openai-agents-js/guides/human-in-the-loop/) using `interruptions` as for local function tools.
 
 <Code
   lang="typescript"

docs/src/content/docs/guides/results.mdx

@@ -46,7 +46,7 @@ There are two ways you can access the inputs for your next turn:
 
 ## Last agent
 
-The `lastAgent` property contains the last agent that ran. Depending on your application, this is often useful for the next time the user inputs something. For example, if you have a frontline triage agent that hands off to a language-specific agent, you can store the last agent, and re-use it the next time the user messages the agent.
+The `lastAgent` property contains the last agent that ran. Depending on your application, this is often useful for the next time the user inputs something. For example, if you have a frontline triage agent that hands off to a language-specific agent, you can store the last agent, and reuse it the next time the user messages the agent.
 
 In streaming mode it can also be useful to access the `currentAgent` property that's mapping to the current agent that is running.
 

docs/src/content/docs/guides/voice-agents/quickstart.mdx

@@ -72,7 +72,7 @@ import thinClientExample from '../../../../../../examples/docs/voice-agents/thin
 
 4. **Create a session**
 
-   Unlike a regular agent, a Voice Agent is continously running and listening inside a `RealtimeSession` that handles the conversation and connection to the model over time. This session will also handle the audio processing, interruptions, and a lot of the other lifecycle functionality we will cover later on.
+   Unlike a regular agent, a Voice Agent is continuously running and listening inside a `RealtimeSession` that handles the conversation and connection to the model over time. This session will also handle the audio processing, interruptions, and a lot of the other lifecycle functionality we will cover later on.
 
    ```typescript
    import { RealtimeSession } from '@openai/agents-realtime';
@@ -113,7 +113,6 @@ import thinClientExample from '../../../../../../examples/docs/voice-agents/thin
 From here you can start designing and building your own voice agent. Voice agents include a lot of the same features as regular agents, but have some of their own unique features.
 
 - Learn how to give your voice agent:
-
   - [Tools](/openai-agents-js/guides/voice-agents/build#tools)
   - [Handoffs](/openai-agents-js/guides/voice-agents/build#handoffs)
   - [Guardrails](/openai-agents-js/guides/voice-agents/build#guardrails)

examples/docs/results/historyLoop.ts

@@ -7,7 +7,7 @@ const agent = new Agent({
 });
 
 let history: AgentInputItem[] = [
-  // intial message
+  // initial message
   user('Are we there yet?'),
 ];
 

examples/handoffs/index.ts

@@ -71,7 +71,7 @@ async function main() {
     result = await run(secondAgent, [
       ...result.history,
       {
-        content: 'I live in New York City. Whats the population of the city?',
+        content: "I live in New York City. What's the population of the city?",
         role: 'user',
       },
     ]);

examples/tools/web-search.ts

@@ -22,7 +22,7 @@ async function main() {
     const messages = result.history;
     messages.push({
       role: 'user',
-      content: 'search the web for more details of the highlighed player.',
+      content: 'search the web for more details of the highlighted player.',
     });
 
     const result2 = await run(agent, messages);

packages/agents-core/src/agent.ts

@@ -34,30 +34,30 @@ export type ToolUseBehaviorFlags = 'run_llm_again' | 'stop_on_first_tool';
 export type ToolsToFinalOutputResult =
   | {
       /**
-       * Wether this is the final output. If `false`, the LLM will run again and receive the tool call output
+       * Whether this is the final output. If `false`, the LLM will run again and receive the tool call output
        */
       isFinalOutput: false;
       /**
-       * Wether the agent was interrupted by a tool approval. If `true`, the LLM will run again and receive the tool call output
+       * Whether the agent was interrupted by a tool approval. If `true`, the LLM will run again and receive the tool call output
        */
       isInterrupted: undefined;
     }
   | {
       isFinalOutput: false;
       /**
-       * Wether the agent was interrupted by a tool approval. If `true`, the LLM will run again and receive the tool call output
+       * Whether the agent was interrupted by a tool approval. If `true`, the LLM will run again and receive the tool call output
        */
       isInterrupted: true;
       interruptions: RunToolApprovalItem[];
     }
   | {
       /**
-       * Wether this is the final output. If `false`, the LLM will run again and receive the tool call output
+       * Whether this is the final output. If `false`, the LLM will run again and receive the tool call output
        */
       isFinalOutput: true;
 
       /**
-       * Wether the agent was interrupted by a tool approval. If `true`, the LLM will run again and receive the tool call output
+       * Whether the agent was interrupted by a tool approval. If `true`, the LLM will run again and receive the tool call output
        */
       isInterrupted: undefined;
 
@@ -212,7 +212,7 @@ export interface AgentConfiguration<
    * This lets you configure how tool use is handled.
    * - run_llm_again: The default behavior. Tools are run, and then the LLM receives the results
    *   and gets to respond.
-   * - stop_on_first_tool: The output of the frist tool call is used as the final output. This means
+   * - stop_on_first_tool: The output of the first tool call is used as the final output. This means
    *   that the LLM does not process the result of the tool call.
    * - A list of tool names: The agent will stop running if any of the tools in the list are called.
    *   The final output will be the output of the first matching tool call. The LLM does not process
@@ -227,7 +227,7 @@ export interface AgentConfiguration<
   toolUseBehavior: ToolUseBehavior;
 
   /**
-   * Wether to reset the tool choice to the default value after a tool has been called. Defaults
+   * Whether to reset the tool choice to the default value after a tool has been called. Defaults
    * to `true`. This ensures that the agent doesn't enter an infinite loop of tool usage.
    */
   resetToolChoice: boolean;
@@ -383,7 +383,7 @@ export class Agent<
   }
 
   /**
-   * Ouput schema name
+   * Output schema name.
    */
   get outputSchemaName(): string {
     if (this.outputType === 'text') {

packages/agents-core/src/extensions/handoffFilters.ts

@@ -17,7 +17,7 @@ const TOOL_TYPES = new Set([
 ]);
 
 /**
- * Filters out all tool items: file search, web serach and function calls+output
+ * Filters out all tool items: file search, web search and function calls+output
  * @param handoffInputData
  * @returns
  */

packages/agents-core/src/handoff.ts

@@ -119,7 +119,7 @@ export class Handoff<
   /**
    * The function that invokes the handoff. The parameters passed are:
    * 1. The handoff run context
-   * 2. The arugments from the LLM, as a JSON string. Empty string if inputJsonSchema is empty.
+   * 2. The arguments from the LLM, as a JSON string. Empty string if inputJsonSchema is empty.
    *
    * Must return an agent
    */

packages/agents-core/src/run.ts

@@ -767,7 +767,7 @@ export class Runner extends RunHooks<any, AgentOutputType<unknown>> {
 
           if (!finalResponse) {
             throw new ModelBehaviorError(
-              'Model did not procude a final response!',
+              'Model did not produce a final response!',
               result.state,
             );
           }

packages/agents-core/src/runImplementation.ts

@@ -144,7 +144,7 @@ export function processModelResponse<TContext>(
         });
         if (!mcpServerTool.providerData.on_approval) {
           // When onApproval function exists, it confirms the approval right after this.
-          // Thus, this approval item must be appended only for the next turn interrpution patterns.
+          // Thus, this approval item must be appended only for the next turn interruption patterns.
           items.push(approvalItem);
         }
       }
@@ -956,7 +956,7 @@ export async function executeHandoffCalls<
 
   if (runHandoffs.length > 1) {
     // multiple handoffs. Ignoring all but the first one by adding reject responses for those
-    const outputMessage = 'Multiple handoffs detected, ignorning this one.';
+    const outputMessage = 'Multiple handoffs detected, ignoring this one.';
     for (let i = 1; i < runHandoffs.length; i++) {
       newStepItems.push(
         new RunToolCallOutputItem(

packages/agents-core/src/tool.ts

@@ -238,7 +238,7 @@ export type FunctionToolResult<
     }
   | {
       /**
-       * Indiciates that the tool requires approval before it can be called.
+       * Indicates that the tool requires approval before it can be called.
        */
       type: 'function_approval';
       /**
@@ -252,7 +252,7 @@ export type FunctionToolResult<
     }
   | {
       /**
-       * Indiciates that the tool requires approval before it can be called.
+       * Indicates that the tool requires approval before it can be called.
        */
       type: 'hosted_mcp_tool_approval';
       /**

packages/agents-core/src/tracing/processor.ts

@@ -15,7 +15,7 @@ type Span = TSpan<any>;
  */
 export interface TracingProcessor {
   /**
-   * Called when the trace processor should start procesing traces.
+   * Called when the trace processor should start processing traces.
    * Only available if the processor is performing tasks like exporting traces in a loop to start
    * the loop
    */

packages/agents-core/src/types/protocol.ts

@@ -5,7 +5,7 @@ import { z } from '@openai/zod/v3';
 // ----------------------------
 
 /**
- * Every item in the protocol provides a `providerData` field to accomodate custom functionality
+ * Every item in the protocol provides a `providerData` field to accommodate custom functionality
  * or new fields
  */
 export const SharedBase = z.object({

packages/agents-openai/CHANGELOG.md

@@ -69,7 +69,7 @@
 
 ### Patch Changes
 
-- adeb218: Ignore empty tool list when callling LLM
+- adeb218: Ignore empty tool list when calling LLM
 - cbd4deb: feat: handle unknown hosted tools in responses model
 - Updated dependencies [544ed4b]
   - @openai/[email protected]

packages/agents-realtime/src/clientMessages.ts

@@ -57,7 +57,7 @@ export type RealtimeTurnDetectionConfigAsIs = {
   threshold?: number;
 };
 
-// The Realtime API accepts snake_cased keys, so when using this, this SDK coverts the keys to snake_case ones before passing it to the API
+// The Realtime API accepts snake_cased keys, so when using this, this SDK converts the keys to snake_case ones before passing it to the API.
 export type RealtimeTurnDetectionConfigCamelCase = {
   type?: 'semantic_vad' | 'server_vad';
   createResponse?: boolean;

packages/agents-realtime/src/openaiRealtimeBase.ts

@@ -50,7 +50,7 @@ export const DEFAULT_OPENAI_REALTIME_MODEL: OpenAIRealtimeModels =
   'gpt-4o-realtime-preview';
 
 /**
- * The default session config that gets send over during session connection unless overriden
+ * The default session config that gets send over during session connection unless overridden
  * by the user.
  */
 export const DEFAULT_OPENAI_REALTIME_SESSION_CONFIG: Partial<RealtimeSessionConfig> =