feat: add ci-build script for size limit testing

Co-authored-by: Marcus Schiesser <marcus.schiesser@googlemail.com>

.changeset/brown-cherries-brake.md

@@ -0,0 +1,6 @@
+---
+"llamaindex": patch
+"@llamaindex/llamaindex-test": patch
+---
+
+feat: vectorStoreIndex has new option progressCallback

.changeset/light-spiders-pump.md

@@ -0,0 +1,5 @@
+---
+"@llamaindex/anthropic": patch
+---
+
+fix: anthropic temperature parameter not respecting value 0

.changeset/purple-icons-buy.md

@@ -0,0 +1,5 @@
+---
+"@llamaindex/google": patch
+---
+
+Add latest google models to lib

.changeset/shaky-vans-strive.md

@@ -0,0 +1,6 @@
+---
+"@llamaindex/aws": patch
+"@llamaindex/doc": patch
+---
+
+Addition of APAC_ANTHROPIC_CLAUDE_4_SONNET type/record in @llamaindex/aws for APAC support for claude 4 sonnet per issue 2184.

apps/next/CHANGELOG.md

@@ -1,5 +1,16 @@
 # @llamaindex/doc
 
+## 0.2.53
+
+### Patch Changes
+
+- Updated dependencies [1995b38]
+- Updated dependencies [001a515]
+- Updated dependencies [9d7d205]
+  - @llamaindex/workflow@1.1.22
+  - @llamaindex/openai@0.4.18
+  - llamaindex@0.11.28
+
 ## 0.2.52
 
 ### Patch Changes

apps/next/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@llamaindex/doc",
-  "version": "0.2.52",
+  "version": "0.2.53",
   "private": true,
   "scripts": {
     "postinstall": "fumadocs-mdx",

apps/next/src/content/docs/llamaindex/modules/models/llms/bedrock.mdx

@@ -115,6 +115,7 @@ EU_AMAZON_NOVA_MICRO_1 = "eu.amazon.nova-micro-v1:0";
 APAC_ANTHROPIC_CLAUDE_3_5_SONNET = "apac.anthropic.claude-3-5-sonnet-20240620-v1:0";
 APAC_ANTHROPIC_CLAUDE_3_5_SONNET_V2 = "apac.anthropic.claude-3-5-sonnet-20241022-v2:0";
 APAC_ANTHROPIC_CLAUDE_3_7_SONNET = "apac.anthropic.claude-3-7-sonnet-20250219-v1:0";
+APAC_ANTHROPIC_CLAUDE_4_SONNET = "apac.anthropic.claude-sonnet-4-20250514-v1:0";
 APAC_ANTHROPIC_CLAUDE_3_HAIKU = "apac.anthropic.claude-3-haiku-20240307-v1:0";
 APAC_ANTHROPIC_CLAUDE_3_SONNET = "apac.anthropic.claude-3-sonnet-20240229-v1:0";
 APAC_AMAZON_NOVA_PRO_1 = "apac.amazon.nova-pro-v1:0";

apps/next/src/content/docs/llamaindex/tutorials/custom_model_per_request.mdx

@@ -0,0 +1,47 @@
+---
+title: Custom Model Per Request 
+---
+
+There are scenarios, such as the case of a multi-tenant backend API, where it may be required to handle each request with a custom model.
+
+In such a scenario, modifying the `Settings` object directly as follows is not recommended:
+
+```typescript
+import { Settings } from 'llamaindex';
+import { OpenAIEmbedding } from '@llamaindex/embeddings-openai';
+
+Settings.embedModel = new OpenAIEmbedding({ apiKey: 'CLIENT_API_KEY' });
+Settings.llm = openai({ apiKey: key,  model: 'gpt-4o' })
+```
+
+Setting `llm` and `embedModel` directly will lead to unpredictable responses, since `Settings` is global and mutable.
+This can lead to race conditions, as each request modifies `Settings.embedModel` or `Settings.llm`.
+
+The recommended approach is to use `Settings.withEmbedModel` or `Settings.withLLM` as follows:
+
+```typescript
+const embedModel = new OpenAIEmbedding({
+  apiKey: process.env.OPENAI_API_KEY,
+});
+const llm = new OpenAI({ apiKey: process.env.OPENAI_API_KEY });
+
+const llmResponse = await Settings.withEmbedModel(embedModel, async () => {
+  return Settings.withLLM(llm, async () => {
+    const path = "node_modules/llamaindex/examples/abramov.txt";
+    const essay = await fs.readFile(path, "utf-8");
+    // Create Document object with essay
+    const document = new Document({ text: essay, id_: path });
+    // Split text and create embeddings. Store them in a VectorStoreIndex
+    const index = await VectorStoreIndex.fromDocuments([document]);
+    // Query the index
+    const queryEngine = index.asQueryEngine();
+    const { message, sourceNodes } = await queryEngine.query({
+      query: "What did the author do in college?",
+    });
+    // Return response with sources
+    return message.content;
+  });
+});
+```
+
+The full example can be found [here](https://github.com/run-llama/LlamaIndexTS/tree/main/examples/local-settings).

apps/next/src/content/docs/llamaindex/tutorials/meta.json

@@ -7,6 +7,7 @@
     "workflows",
     "local_llm",
     "chatbot",
-    "structured_data_extraction"
+    "structured_data_extraction",
+    "custom_model_per_request"
   ]
 }

e2e/examples/cloudflare-worker-agent/CHANGELOG.md

@@ -1,5 +1,11 @@
 # @llamaindex/cloudflare-worker-agent-test
 
+## 0.0.189
+
+### Patch Changes
+
+- llamaindex@0.11.28
+
 ## 0.0.188
 
 ### Patch Changes

e2e/examples/cloudflare-worker-agent/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@llamaindex/cloudflare-worker-agent-test",
-  "version": "0.0.188",
+  "version": "0.0.189",
   "type": "module",
   "private": true,
   "scripts": {

e2e/examples/llama-parse-browser/package.json

@@ -10,7 +10,7 @@
   },
   "devDependencies": {
     "typescript": "^5.8.3",
-    "vite": "^6.3.3",
+    "vite": "^6.3.6",
     "vite-plugin-wasm": "^3.4.1"
   },
   "dependencies": {

e2e/examples/nextjs-agent/CHANGELOG.md

@@ -1,5 +1,11 @@
 # @llamaindex/next-agent-test
 
+## 0.1.189
+
+### Patch Changes
+
+- llamaindex@0.11.28
+
 ## 0.1.188
 
 ### Patch Changes

e2e/examples/nextjs-agent/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@llamaindex/next-agent-test",
-  "version": "0.1.188",
+  "version": "0.1.189",
   "private": true,
   "scripts": {
     "dev": "next dev",

e2e/examples/nextjs-edge-runtime/CHANGELOG.md

@@ -1,5 +1,11 @@
 # test-edge-runtime
 
+## 0.1.188
+
+### Patch Changes
+
+- llamaindex@0.11.28
+
 ## 0.1.187
 
 ### Patch Changes

e2e/examples/nextjs-edge-runtime/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@llamaindex/nextjs-edge-runtime-test",
-  "version": "0.1.187",
+  "version": "0.1.188",
   "private": true,
   "scripts": {
     "dev": "next dev",

e2e/examples/nextjs-node-runtime/CHANGELOG.md

@@ -1,5 +1,12 @@
 # @llamaindex/next-node-runtime
 
+## 0.1.60
+
+### Patch Changes
+
+- llamaindex@0.11.28
+- @llamaindex/huggingface@0.1.28
+
 ## 0.1.59
 
 ### Patch Changes

e2e/examples/nextjs-node-runtime/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@llamaindex/next-node-runtime-test",
-  "version": "0.1.59",
+  "version": "0.1.60",
   "private": true,
   "scripts": {
     "dev": "next dev",

e2e/examples/vite-import-llamaindex/CHANGELOG.md

@@ -1,5 +1,11 @@
 # vite-import-llamaindex
 
+## 0.0.55
+
+### Patch Changes
+
+- llamaindex@0.11.28
+
 ## 0.0.54
 
 ### Patch Changes

e2e/examples/vite-import-llamaindex/package.json

@@ -1,11 +1,12 @@
 {
   "name": "vite-import-llamaindex",
   "private": true,
-  "version": "0.0.54",
+  "version": "0.0.55",
   "type": "module",
   "scripts": {
     "build": "vite build",
-    "size-limit": "size-limit"
+    "size-limit": "size-limit",
+    "ci-build": "pnpm -C ../../../ build && vite build"
   },
   "size-limit": [
     {
@@ -16,7 +17,7 @@
     "@size-limit/preset-big-lib": "^11.1.6",
     "size-limit": "^11.1.6",
     "typescript": "^5.8.3",
-    "vite": "^6.3.3"
+    "vite": "^6.3.6"
   },
   "dependencies": {
     "llamaindex": "workspace:*"

e2e/examples/waku-query-engine/CHANGELOG.md

@@ -1,5 +1,11 @@
 # @llamaindex/waku-query-engine-test
 
+## 0.0.189
+
+### Patch Changes
+
+- llamaindex@0.11.28
+
 ## 0.0.188
 
 ### Patch Changes

e2e/examples/waku-query-engine/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@llamaindex/waku-query-engine-test",
-  "version": "0.0.188",
+  "version": "0.0.189",
   "type": "module",
   "private": true,
   "scripts": {

examples/CHANGELOG.md

@@ -1,5 +1,28 @@
 # examples
 
+## 0.3.40
+
+### Patch Changes
+
+- Updated dependencies [1995b38]
+- Updated dependencies [001a515]
+- Updated dependencies [9d7d205]
+  - @llamaindex/workflow@1.1.22
+  - @llamaindex/openai@0.4.18
+  - llamaindex@0.11.28
+  - @llamaindex/clip@0.0.74
+  - @llamaindex/deepinfra@0.0.74
+  - @llamaindex/deepseek@0.0.36
+  - @llamaindex/fireworks@0.0.34
+  - @llamaindex/groq@0.0.90
+  - @llamaindex/huggingface@0.1.28
+  - @llamaindex/jinaai@0.0.34
+  - @llamaindex/perplexity@0.0.31
+  - @llamaindex/azure@0.1.35
+  - @llamaindex/together@0.0.34
+  - @llamaindex/vllm@0.0.60
+  - @llamaindex/xai@0.0.21
+
 ## 0.3.39
 
 ### Patch Changes

examples/agents/workflow/joke.ts

@@ -22,7 +22,7 @@ const { withState, getContext } = createStatefulMiddleware(() => ({
 const jokeFlow = withState(createWorkflow());
 
 // Define handlers for each step
-jokeFlow.handle([startEvent], async (event) => {
+jokeFlow.handle([startEvent], async (context, event) => {
   // Prompt the LLM to write a joke
   const prompt = `Write your best joke about ${event.data}. Write the joke between <joke> and </joke> tags.`;
   const response = await llm.complete({ prompt });
@@ -34,7 +34,7 @@ jokeFlow.handle([startEvent], async (event) => {
   return jokeEvent.with({ joke: joke });
 });
 
-jokeFlow.handle([jokeEvent], async (event) => {
+jokeFlow.handle([jokeEvent], async (context, event) => {
   // Prompt the LLM to critique the joke
   const prompt = `Give a thorough critique of the following joke. If the joke needs improvement, put "IMPROVE" somewhere in the critique: ${event.data.joke}`;
   const response = await llm.complete({ prompt });
@@ -50,9 +50,9 @@ jokeFlow.handle([jokeEvent], async (event) => {
   return resultEvent.with({ joke: event.data.joke, critique: response.text });
 });
 
-jokeFlow.handle([critiqueEvent], async (event) => {
+jokeFlow.handle([critiqueEvent], async (context, event) => {
   // Keep track of the number of iterations
-  const state = getContext().state;
+  const state = context.state;
   state.numIterations++;
 
   // Write a new joke based on the previous joke and critique

examples/local-settings/local-settings.ts

@@ -0,0 +1,69 @@
+import { OpenAI, OpenAIEmbedding } from "@llamaindex/openai";
+import express, { Request, Response } from "express";
+import fs from "fs/promises";
+import { Document, Settings, VectorStoreIndex } from "llamaindex";
+
+const app = express();
+const port = 3000;
+
+app.get("/default", async (req: Request, res: Response) => {
+  const embedModel = new OpenAIEmbedding({
+    apiKey: process.env.OPENAI_API_KEY,
+  });
+  const llm = new OpenAI({ apiKey: process.env.OPENAI_API_KEY });
+
+  const llmResponse = await Settings.withEmbedModel(embedModel, async () => {
+    return Settings.withLLM(llm, async () => {
+      const path = "node_modules/llamaindex/examples/abramov.txt";
+      const essay = await fs.readFile(path, "utf-8");
+      // Create Document object with essay
+      const document = new Document({ text: essay, id_: path });
+      // Split text and create embeddings. Store them in a VectorStoreIndex
+      const index = await VectorStoreIndex.fromDocuments([document]);
+      // Query the index
+      const queryEngine = index.asQueryEngine();
+      const { message, sourceNodes } = await queryEngine.query({
+        query: "What did the author do in college?",
+      });
+      // Return response with sources
+      return message.content;
+    });
+  });
+  // res.send(message.content)
+  res.send(llmResponse);
+});
+
+app.get("/custom", async (req: Request, res: Response) => {
+  const embedModel = new OpenAIEmbedding({
+    apiKey: process.env.OPENAI_API_KEY,
+    model: "text-embedding-3-small",
+  });
+  const llm = new OpenAI({
+    apiKey: process.env.OPENAI_API_KEY,
+    model: "gpt-3.5-turbo",
+  });
+
+  const llmResponse = await Settings.withEmbedModel(embedModel, async () => {
+    return Settings.withLLM(llm, async () => {
+      const path = "node_modules/llamaindex/examples/abramov.txt";
+      const essay = await fs.readFile(path, "utf-8");
+      // Create Document object with essay
+      const document = new Document({ text: essay, id_: path });
+      // Split text and create embeddings. Store them in a VectorStoreIndex
+      const index = await VectorStoreIndex.fromDocuments([document]);
+      // Query the index
+      const queryEngine = index.asQueryEngine();
+      const { message, sourceNodes } = await queryEngine.query({
+        query: "What did the author do in college?",
+      });
+      // Return response with sources
+      return message.content;
+    });
+  });
+  // res.send(message.content)
+  res.send(llmResponse);
+});
+
+app.listen(port, () => {
+  console.log(`Example app listening on port ${port}`);
+});

examples/local-settings/package.json

@@ -0,0 +1,22 @@
+{
+  "name": "local-settings",
+  "version": "1.0.0",
+  "main": "index.js",
+  "private": "true",
+  "scripts": {
+    "test": "echo \"No tests for example package\""
+  },
+  "keywords": [],
+  "author": "",
+  "license": "ISC",
+  "description": "",
+  "devDependencies": {
+    "@types/express": "^5.0.3",
+    "typescript": "^5.9.2"
+  },
+  "dependencies": {
+    "@llamaindex/openai": "^0.4.16",
+    "express": "^5.1.0",
+    "llamaindex": "^0.11.26"
+  }
+}

examples/local-settings/tsconfig.json

@@ -0,0 +1,8 @@
+{
+  "extends": "../tsconfig.json",
+  "compilerOptions": {
+    "moduleResolution": "node",
+    "types": ["node", "express"]
+  },
+  "include": ["*.ts"]
+}

examples/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@llamaindex/examples",
-  "version": "0.3.39",
+  "version": "0.3.40",
   "private": true,
   "scripts": {
     "lint": "eslint .",
@@ -14,24 +14,24 @@
     "@llamaindex/anthropic": "^0.3.23",
     "@llamaindex/assemblyai": "^0.1.19",
     "@llamaindex/astra": "^0.0.34",
-    "@llamaindex/azure": "^0.1.34",
+    "@llamaindex/azure": "^0.1.35",
     "@llamaindex/bm25-retriever": "^0.0.9",
     "@llamaindex/chroma": "^0.0.34",
-    "@llamaindex/clip": "^0.0.73",
+    "@llamaindex/clip": "^0.0.74",
     "@llamaindex/cloud": "^4.1.2",
     "@llamaindex/cohere": "^0.0.34",
     "@llamaindex/core": "^0.6.20",
-    "@llamaindex/deepinfra": "^0.0.73",
-    "@llamaindex/deepseek": "^0.0.35",
+    "@llamaindex/deepinfra": "^0.0.74",
+    "@llamaindex/deepseek": "^0.0.36",
     "@llamaindex/discord": "^0.1.19",
     "@llamaindex/elastic-search": "^0.1.20",
     "@llamaindex/env": "^0.1.30",
     "@llamaindex/firestore": "^1.0.27",
-    "@llamaindex/fireworks": "^0.0.33",
+    "@llamaindex/fireworks": "^0.0.34",
     "@llamaindex/google": "^0.3.20",
-    "@llamaindex/groq": "^0.0.89",
-    "@llamaindex/huggingface": "^0.1.27",
-    "@llamaindex/jinaai": "^0.0.33",
+    "@llamaindex/groq": "^0.0.90",
+    "@llamaindex/huggingface": "^0.1.28",
+    "@llamaindex/jinaai": "^0.0.34",
     "@llamaindex/milvus": "^0.1.29",
     "@llamaindex/mistral": "^0.1.20",
     "@llamaindex/mixedbread": "^0.0.34",
@@ -39,8 +39,8 @@
     "@llamaindex/node-parser": "^2.0.20",
     "@llamaindex/notion": "^0.1.19",
     "@llamaindex/ollama": "^0.1.21",
-    "@llamaindex/openai": "^0.4.17",
-    "@llamaindex/perplexity": "^0.0.30",
+    "@llamaindex/openai": "^0.4.18",
+    "@llamaindex/perplexity": "^0.0.31",
     "@llamaindex/pinecone": "^0.1.20",
     "@llamaindex/portkey-ai": "^0.0.62",
     "@llamaindex/postgres": "^0.0.63",
@@ -48,15 +48,15 @@
     "@llamaindex/readers": "^3.1.19",
     "@llamaindex/replicate": "^0.0.62",
     "@llamaindex/supabase": "^0.1.21",
-    "@llamaindex/together": "^0.0.33",
+    "@llamaindex/together": "^0.0.34",
     "@llamaindex/tools": "^0.1.10",
     "@llamaindex/upstash": "^0.0.34",
     "@llamaindex/vercel": "^0.1.20",
-    "@llamaindex/vllm": "^0.0.59",
+    "@llamaindex/vllm": "^0.0.60",
     "@llamaindex/voyage-ai": "^1.0.26",
     "@llamaindex/weaviate": "^0.0.35",
-    "@llamaindex/workflow": "^1.1.21",
-    "@llamaindex/xai": "^0.0.20",
+    "@llamaindex/workflow": "^1.1.22",
+    "@llamaindex/xai": "^0.0.21",
     "@notionhq/client": "^4.0.0",
     "@pinecone-database/pinecone": "^4.0.0",
     "@vercel/postgres": "^0.10.0",
@@ -65,13 +65,14 @@
     "commander": "^12.1.0",
     "dotenv": "^17.2.0",
     "js-tiktoken": "^1.0.14",
-    "llamaindex": "^0.11.27",
+    "llamaindex": "^0.11.28",
     "mongodb": "6.7.0",
     "postgres": "^3.4.4",
     "wikipedia": "^2.1.2",
     "zod": "^3.25.76"
   },
   "devDependencies": {
+    "@types/express": "^5.0.3",
     "@types/node": "^24.0.13",
     "tsx": "^4.20.3",
     "typescript": "^5.8.3"

packages/autotool/CHANGELOG.md

@@ -1,5 +1,11 @@
 # @llamaindex/autotool
 
+## 8.0.28
+
+### Patch Changes
+
+- llamaindex@0.11.28
+
 ## 8.0.27
 
 ### Patch Changes

packages/autotool/examples/01_node/CHANGELOG.md

@@ -1,5 +1,12 @@
 # @llamaindex/autotool-01-node-example
 
+## 0.0.136
+
+### Patch Changes
+
+- llamaindex@0.11.28
+- @llamaindex/autotool@8.0.28
+
 ## 0.0.135
 
 ### Patch Changes

packages/autotool/examples/01_node/package.json

@@ -13,5 +13,5 @@
   "scripts": {
     "start": "node --import tsx --import @llamaindex/autotool/node ./src/index.ts"
   },
-  "version": "0.0.135"
+  "version": "0.0.136"
 }

packages/autotool/package.json

@@ -6,7 +6,7 @@
     "url": "git+https://github.com/run-llama/LlamaIndexTS.git",
     "directory": "packages/autotool"
   },
-  "version": "8.0.27",
+  "version": "8.0.28",
   "description": "auto transpile your JS function to LLM Agent compatible",
   "files": [
     "dist",

packages/experimental/CHANGELOG.md

@@ -1,5 +1,11 @@
 # @llamaindex/experimental
 
+## 0.0.205
+
+### Patch Changes
+
+- llamaindex@0.11.28
+
 ## 0.0.204
 
 ### Patch Changes

packages/experimental/package.json

@@ -1,7 +1,7 @@
 {
   "name": "@llamaindex/experimental",
   "description": "Experimental package for LlamaIndexTS",
-  "version": "0.0.204",
+  "version": "0.0.205",
   "type": "module",
   "types": "dist/type/index.d.ts",
   "main": "dist/cjs/index.js",

packages/llamaindex/CHANGELOG.md

@@ -1,5 +1,12 @@
 # llamaindex
 
+## 0.11.28
+
+### Patch Changes
+
+- Updated dependencies [1995b38]
+  - @llamaindex/workflow@1.1.22
+
 ## 0.11.27
 
 ### Patch Changes

packages/llamaindex/package.json

@@ -1,6 +1,6 @@
 {
   "name": "llamaindex",
-  "version": "0.11.27",
+  "version": "0.11.28",
   "license": "MIT",
   "type": "module",
   "keywords": [

packages/llamaindex/src/indices/vectorStore/index.ts

@@ -54,6 +54,7 @@ export interface VectorIndexOptions extends IndexStructOptions {
   storageContext?: StorageContext | undefined;
   vectorStores?: VectorStoreByType | undefined;
   logProgress?: boolean | undefined;
+  progressCallback?: ((progress: number, total: number) => void) | undefined;
 }
 
 export interface VectorIndexConstructorProps extends BaseIndexInit<IndexDict> {
@@ -121,6 +122,7 @@ export class VectorStoreIndex extends BaseIndex<IndexDict> {
       // If nodes are passed in, then we need to update the index
       await index.buildIndexFromNodes(options.nodes, {
         logProgress: options.logProgress,
+        progressCallback: options.progressCallback,
       });
     }
     return index;
@@ -170,7 +172,12 @@ export class VectorStoreIndex extends BaseIndex<IndexDict> {
    */
   async getNodeEmbeddingResults(
     nodes: BaseNode[],
-    options?: { logProgress?: boolean | undefined },
+    options?: {
+      logProgress?: boolean | undefined;
+      progressCallback?:
+        | ((progress: number, total: number) => void)
+        | undefined;
+    },
   ): Promise<BaseNode[]> {
     const nodeMap = splitNodesByType(nodes);
     for (const type in nodeMap) {
@@ -180,6 +187,7 @@ export class VectorStoreIndex extends BaseIndex<IndexDict> {
       if (embedModel && nodes) {
         await embedModel(nodes, {
           logProgress: options?.logProgress,
+          progressCallback: options?.progressCallback,
         });
       }
     }
@@ -193,7 +201,12 @@ export class VectorStoreIndex extends BaseIndex<IndexDict> {
    */
   async buildIndexFromNodes(
     nodes: BaseNode[],
-    options?: { logProgress?: boolean | undefined },
+    options?: {
+      logProgress?: boolean | undefined;
+      progressCallback?:
+        | ((progress: number, total: number) => void)
+        | undefined;
+    },
   ) {
     await this.insertNodes(nodes, options);
   }
@@ -361,7 +374,12 @@ export class VectorStoreIndex extends BaseIndex<IndexDict> {
 
   async insertNodes(
     nodes: BaseNode[],
-    options?: { logProgress?: boolean | undefined },
+    options?: {
+      logProgress?: boolean | undefined;
+      progressCallback?:
+        | ((progress: number, total: number) => void)
+        | undefined;
+    },
   ): Promise<void> {
     if (!nodes || nodes.length === 0) {
       return;

packages/llamaindex/tests/CHANGELOG.md

@@ -1,5 +1,13 @@
 # @llamaindex/core-test
 
+## 0.1.19
+
+### Patch Changes
+
+- Updated dependencies [001a515]
+- Updated dependencies [9d7d205]
+  - @llamaindex/openai@0.4.18
+
 ## 0.1.18
 
 ### Patch Changes

packages/llamaindex/tests/indices/VectorStoreIndex.test.ts

@@ -89,4 +89,42 @@ describe("[VectorStoreIndex] use embedding model", () => {
     expect(customSpy).toHaveBeenCalled();
     expect(settingsSpy).not.toHaveBeenCalled();
   });
+
+  describe("[VectorStoreIndex] call progressCallback", () => {
+    it("should call progressCallback with correct values", async () => {
+      const documents = Array.from(
+        { length: 20 },
+        (_, i) => new Document({ text: `This is document ${i + 1}` }),
+      );
+
+      const progressCalls: Array<{ current: number; total: number }> = [];
+      const progressCallback = (current: number, total: number) => {
+        progressCalls.push({ current, total });
+      };
+
+      const embedModel = new OpenAIEmbedding();
+      mockEmbeddingModel(embedModel);
+      const embedSpy = vi.spyOn(embedModel, "getTextEmbeddingsBatch");
+
+      Settings.embedModel = embedModel;
+      const storageContext = await mockStorageContext(testDir, embedModel);
+
+      await VectorStoreIndex.fromDocuments(documents, {
+        storageContext,
+        logProgress: true,
+        progressCallback,
+      });
+
+      // Expect the embedding model to be called
+      expect(embedSpy).toHaveBeenCalled();
+
+      // Verify that progressCallback was called with correct values
+      expect(progressCalls.length).toBeGreaterThan(0);
+      expect(progressCalls[0]).toEqual({ current: 10, total: 20 });
+      expect(progressCalls[progressCalls.length - 1]).toEqual({
+        current: 20,
+        total: 20,
+      });
+    });
+  });
 });

packages/llamaindex/tests/package.json

@@ -1,7 +1,7 @@
 {
   "name": "@llamaindex/llamaindex-test",
   "private": true,
-  "version": "0.1.18",
+  "version": "0.1.19",
   "type": "module",
   "scripts": {
     "test": "vitest run"

packages/providers/anthropic/src/llm.ts

@@ -179,7 +179,7 @@ export class Anthropic extends ToolCallLLM<
   constructor(init?: Partial<Anthropic>) {
     super();
     this.model = init?.model ?? "claude-3-opus";
-    this.temperature = init?.temperature ?? 1; // default in anthropic is 1
+    this.temperature = init?.temperature != null ? init.temperature : 1; // default in anthropic is 1
     this.topP = init?.topP;
     this.maxTokens = init?.maxTokens ?? undefined;
 

packages/providers/aws/src/llm/bedrock/index.ts

@@ -134,13 +134,14 @@ export const INFERENCE_BEDROCK_MODELS = {
   EU_AMAZON_NOVA_PRO_1: "eu.amazon.nova-pro-v1:0",
   EU_AMAZON_NOVA_LITE_1: "eu.amazon.nova-lite-v1:0",
   EU_AMAZON_NOVA_MICRO_1: "eu.amazon.nova-micro-v1:0",
-
   APAC_ANTHROPIC_CLAUDE_3_5_SONNET:
     "apac.anthropic.claude-3-5-sonnet-20240620-v1:0",
   APAC_ANTHROPIC_CLAUDE_3_5_SONNET_V2:
     "apac.anthropic.claude-3-5-sonnet-20241022-v2:0",
   APAC_ANTHROPIC_CLAUDE_3_7_SONNET:
     "apac.anthropic.claude-3-7-sonnet-20250219-v1:0",
+  APAC_ANTHROPIC_CLAUDE_4_SONNET:
+    "apac.anthropic.claude-sonnet-4-20250514-v1:0q",
   APAC_ANTHROPIC_CLAUDE_3_HAIKU: "apac.anthropic.claude-3-haiku-20240307-v1:0",
   APAC_ANTHROPIC_CLAUDE_3_SONNET:
     "apac.anthropic.claude-3-sonnet-20240229-v1:0",
@@ -226,6 +227,8 @@ export const INFERENCE_TO_BEDROCK_MAP: Record<
     BEDROCK_MODELS.ANTHROPIC_CLAUDE_3_5_SONNET_V2,
   [INFERENCE_BEDROCK_MODELS.APAC_ANTHROPIC_CLAUDE_3_7_SONNET]:
     BEDROCK_MODELS.ANTHROPIC_CLAUDE_3_7_SONNET,
+  [INFERENCE_BEDROCK_MODELS.APAC_ANTHROPIC_CLAUDE_4_SONNET]:
+    BEDROCK_MODELS.ANTHROPIC_CLAUDE_4_SONNET,
   [INFERENCE_BEDROCK_MODELS.APAC_ANTHROPIC_CLAUDE_3_HAIKU]:
     BEDROCK_MODELS.ANTHROPIC_CLAUDE_3_HAIKU,
   [INFERENCE_BEDROCK_MODELS.APAC_ANTHROPIC_CLAUDE_3_SONNET]:

packages/providers/clip/CHANGELOG.md

@@ -1,5 +1,13 @@
 # @llamaindex/clip
 
+## 0.0.74
+
+### Patch Changes
+
+- Updated dependencies [001a515]
+- Updated dependencies [9d7d205]
+  - @llamaindex/openai@0.4.18
+
 ## 0.0.73
 
 ### Patch Changes

packages/providers/clip/package.json

@@ -1,7 +1,7 @@
 {
   "name": "@llamaindex/clip",
   "description": "Clip Embedding Adapter for LlamaIndex",
-  "version": "0.0.73",
+  "version": "0.0.74",
   "type": "module",
   "types": "dist/index.d.ts",
   "main": "dist/index.cjs",

packages/providers/deepinfra/CHANGELOG.md

@@ -1,5 +1,13 @@
 # @llamaindex/deepinfra
 
+## 0.0.74
+
+### Patch Changes
+
+- Updated dependencies [001a515]
+- Updated dependencies [9d7d205]
+  - @llamaindex/openai@0.4.18
+
 ## 0.0.73
 
 ### Patch Changes

packages/providers/deepinfra/package.json

@@ -1,7 +1,7 @@
 {
   "name": "@llamaindex/deepinfra",
   "description": "Deepinfra Adapter for LlamaIndex",
-  "version": "0.0.73",
+  "version": "0.0.74",
   "type": "module",
   "main": "./dist/index.cjs",
   "module": "./dist/index.js",

packages/providers/deepseek/CHANGELOG.md

@@ -1,5 +1,13 @@
 # @llamaindex/deepseek
 
+## 0.0.36
+
+### Patch Changes
+
+- Updated dependencies [001a515]
+- Updated dependencies [9d7d205]
+  - @llamaindex/openai@0.4.18
+
 ## 0.0.35
 
 ### Patch Changes

packages/providers/deepseek/package.json

@@ -1,7 +1,7 @@
 {
   "name": "@llamaindex/deepseek",
   "description": "DeepSeek Adapter for LlamaIndex",
-  "version": "0.0.35",
+  "version": "0.0.36",
   "type": "module",
   "main": "./dist/index.cjs",
   "module": "./dist/index.js",

packages/providers/fireworks/CHANGELOG.md

@@ -1,5 +1,13 @@
 # @llamaindex/fireworks
 
+## 0.0.34
+
+### Patch Changes
+
+- Updated dependencies [001a515]
+- Updated dependencies [9d7d205]
+  - @llamaindex/openai@0.4.18
+
 ## 0.0.33
 
 ### Patch Changes

packages/providers/fireworks/package.json

@@ -1,7 +1,7 @@
 {
   "name": "@llamaindex/fireworks",
   "description": "Fireworks Adapter for LlamaIndex",
-  "version": "0.0.33",
+  "version": "0.0.34",
   "type": "module",
   "main": "./dist/index.cjs",
   "module": "./dist/index.js",

packages/providers/google/src/constants.ts

@@ -27,6 +27,9 @@ export enum GEMINI_MODEL {
   GEMINI_2_5_PRO_PREVIEW = "gemini-2.5-pro-preview-03-25",
   GEMINI_2_5_PRO_PREVIEW_LATEST = "gemini-2.5-pro-preview-06-05",
   GEMINI_2_5_FLASH_PREVIEW = "gemini-2.5-flash-preview-05-20",
+  GEMINI_2_5_PRO_LATEST = "gemini-2.5-pro",
+  GEMINI_2_5_FLASH_LATEST = "gemini-2.5-flash",
+  GEMINI_2_5_FLASH_LITE = "gemini-2.5-flash-lite",
 }
 
 export const GEMINI_MODEL_INFO_MAP: Record<
@@ -54,6 +57,9 @@ export const GEMINI_MODEL_INFO_MAP: Record<
   [GEMINI_MODEL.GEMINI_2_5_PRO_PREVIEW]: { contextWindow: 10 ** 6 },
   [GEMINI_MODEL.GEMINI_2_5_PRO_PREVIEW_LATEST]: { contextWindow: 10 ** 6 },
   [GEMINI_MODEL.GEMINI_2_5_FLASH_PREVIEW]: { contextWindow: 10 ** 6 },
+  [GEMINI_MODEL.GEMINI_2_5_PRO_LATEST]: { contextWindow: 10 ** 6 },
+  [GEMINI_MODEL.GEMINI_2_5_FLASH_LATEST]: { contextWindow: 10 ** 6 },
+  [GEMINI_MODEL.GEMINI_2_5_FLASH_LITE]: { contextWindow: 10 ** 6 },
 };
 
 export const SUPPORT_TOOL_CALL_MODELS: GEMINI_MODEL[] = [
@@ -73,6 +79,9 @@ export const SUPPORT_TOOL_CALL_MODELS: GEMINI_MODEL[] = [
   GEMINI_MODEL.GEMINI_2_5_PRO_PREVIEW,
   GEMINI_MODEL.GEMINI_2_5_PRO_PREVIEW_LATEST,
   GEMINI_MODEL.GEMINI_2_5_FLASH_PREVIEW,
+  GEMINI_MODEL.GEMINI_2_5_PRO_LATEST,
+  GEMINI_MODEL.GEMINI_2_5_FLASH_LATEST,
+  GEMINI_MODEL.GEMINI_2_5_FLASH_LITE,
 ];
 
 export const DEFAULT_GEMINI_PARAMS = {

packages/providers/groq/CHANGELOG.md

@@ -1,5 +1,13 @@
 # @llamaindex/groq
 
+## 0.0.90
+
+### Patch Changes
+
+- Updated dependencies [001a515]
+- Updated dependencies [9d7d205]
+  - @llamaindex/openai@0.4.18
+
 ## 0.0.89
 
 ### Patch Changes

packages/providers/groq/package.json

@@ -1,7 +1,7 @@
 {
   "name": "@llamaindex/groq",
   "description": "Groq Adapter for LlamaIndex",
-  "version": "0.0.89",
+  "version": "0.0.90",
   "type": "module",
   "main": "./dist/index.cjs",
   "module": "./dist/index.js",

packages/providers/huggingface/CHANGELOG.md

@@ -1,5 +1,13 @@
 # @llamaindex/huggingface
 
+## 0.1.28
+
+### Patch Changes
+
+- Updated dependencies [001a515]
+- Updated dependencies [9d7d205]
+  - @llamaindex/openai@0.4.18
+
 ## 0.1.27
 
 ### Patch Changes

packages/providers/huggingface/package.json

@@ -1,7 +1,7 @@
 {
   "name": "@llamaindex/huggingface",
   "description": "Huggingface Adapter for LlamaIndex",
-  "version": "0.1.27",
+  "version": "0.1.28",
   "type": "module",
   "types": "dist/index.d.ts",
   "main": "dist/index.cjs",

packages/providers/jinaai/CHANGELOG.md

@@ -1,5 +1,13 @@
 # @llamaindex/jinaai
 
+## 0.0.34
+
+### Patch Changes
+
+- Updated dependencies [001a515]
+- Updated dependencies [9d7d205]
+  - @llamaindex/openai@0.4.18
+
 ## 0.0.33
 
 ### Patch Changes

packages/providers/jinaai/package.json

@@ -1,7 +1,7 @@
 {
   "name": "@llamaindex/jinaai",
   "description": "JinaAI Adapter for LlamaIndex",
-  "version": "0.0.33",
+  "version": "0.0.34",
   "type": "module",
   "main": "./dist/index.cjs",
   "module": "./dist/index.js",

packages/providers/openai/CHANGELOG.md

@@ -1,5 +1,12 @@
 # @llamaindex/openai
 
+## 0.4.18
+
+### Patch Changes
+
+- 001a515: chore: add minimal reasoning effort for gpt5
+- 9d7d205: fix: fix the problem that the usage field in the streaming response was not handled correctly
+
 ## 0.4.17
 
 ### Patch Changes

packages/providers/openai/package.json

@@ -1,7 +1,7 @@
 {
   "name": "@llamaindex/openai",
   "description": "OpenAI Adapter for LlamaIndex",
-  "version": "0.4.17",
+  "version": "0.4.18",
   "type": "module",
   "main": "./dist/index.cjs",
   "module": "./dist/index.js",

packages/providers/openai/src/llm.ts

@@ -40,6 +40,7 @@ import { OpenAILive } from "./live.js";
 import {
   ALL_AVAILABLE_OPENAI_MODELS,
   isFunctionCallingModel,
+  isReasoningEffortSupported,
   isReasoningModel,
   isTemperatureSupported,
   type LLMInstance,
@@ -54,7 +55,7 @@ export class OpenAI extends ToolCallLLM<OpenAIAdditionalChatOptions> {
     // string & {} is a hack to allow any string, but still give autocomplete
     | (string & {});
   temperature: number;
-  reasoningEffort?: "low" | "medium" | "high" | undefined;
+  reasoningEffort?: "low" | "medium" | "high" | "minimal" | undefined;
   topP: number;
   maxTokens?: number | undefined;
   additionalChatOptions?: OpenAIAdditionalChatOptions | undefined;
@@ -90,9 +91,11 @@ export class OpenAI extends ToolCallLLM<OpenAIAdditionalChatOptions> {
 
     this.model = init?.model ?? "gpt-4o";
     this.temperature = init?.temperature ?? 0.1;
-    this.reasoningEffort = isReasoningModel(this.model)
-      ? init?.reasoningEffort
-      : undefined;
+    this.reasoningEffort =
+      isReasoningModel(this.model) &&
+      isReasoningEffortSupported(this.model, init?.reasoningEffort)
+        ? init?.reasoningEffort
+        : undefined;
     this.topP = init?.topP ?? 1;
     this.maxTokens = init?.maxTokens ?? undefined;
 
@@ -370,25 +373,18 @@ export class OpenAI extends ToolCallLLM<OpenAIAdditionalChatOptions> {
     let currentToolCall: PartialToolCall | null = null;
     const toolCallMap = new Map<string, PartialToolCall>();
     for await (const part of stream) {
-      if (part.choices.length === 0) {
+      const choice = part.choices && part.choices[0];
+      const hasValidContent =
+        choice?.delta?.content ||
+        choice?.delta?.tool_calls ||
+        choice?.finish_reason;
+
+      if (!hasValidContent) {
         if (part.usage) {
-          yield {
-            raw: part,
-            delta: "",
-          };
+          yield { raw: part, delta: "" };
         }
         continue;
       }
-      const choice = part.choices[0]!;
-      // skip parts that don't have any content
-      if (
-        !(
-          choice.delta?.content ||
-          choice.delta?.tool_calls ||
-          choice.finish_reason
-        )
-      )
-        continue;
 
       let shouldEmitToolCall: PartialToolCall | null = null;
       if (

packages/providers/openai/src/utils.ts

@@ -187,6 +187,16 @@ export function isReasoningModel(model: ChatModel | string): boolean {
   return isO1 || isO3 || isO4 || isGPT5;
 }
 
+export function isReasoningEffortSupported(
+  model: ChatModel | string,
+  effort: string | undefined,
+): boolean {
+  const supportedReasoningEffort = ["low", "medium", "high", undefined];
+  return model.startsWith("gpt-5")
+    ? [...supportedReasoningEffort, "minimal"].includes(effort)
+    : supportedReasoningEffort.includes(effort);
+}
+
 export function isTemperatureSupported(model: ChatModel | string): boolean {
   return !model.startsWith("o3") && !model.startsWith("o4");
 }

packages/providers/openai/tests/chat.test.ts

@@ -283,4 +283,100 @@ describe("OpenAI streamChat", () => {
     expect(chunks[0].options).toEqual({});
     expect(chunks[0].delta).toBe("");
   });
+
+  it("should handle part with undefined choices", async () => {
+    // Create a mock stream that yields a part without choices
+    const mockStream = async function* () {
+      yield {
+        // No choices property defined
+        usage: {
+          prompt_tokens: 10,
+          completion_tokens: 5,
+          total_tokens: 15,
+        },
+      };
+    };
+
+    // Mock the OpenAI session and chat completions
+    const mockSession = {
+      chat: {
+        completions: {
+          create: vi.fn().mockResolvedValue(mockStream()),
+        },
+      },
+    };
+
+    const openai = new OpenAI({
+      model: "gpt-4o-mini",
+      apiKey: "test-key",
+      // @ts-expect-error: mockSession is a mock object for testing purposes
+      session: mockSession,
+    });
+
+    // @ts-expect-error accessing protected method
+    const stream = openai.streamChat({
+      messages: [{ role: "user" as const, content: "Hello" }],
+      stream: true,
+    });
+
+    const chunks: ChatResponseChunk[] = [];
+    for await (const chunk of stream) {
+      chunks.push(chunk);
+    }
+
+    expect(chunks).toHaveLength(1);
+    expect(chunks[0].delta).toBe("");
+    expect(chunks[0].raw).toHaveProperty("usage");
+  });
+
+  it("should handle part with invalid content", async () => {
+    const mockStream = async function* () {
+      yield {
+        choices: [
+          {
+            delta: {
+              role: "assistant",
+              content: "",
+            },
+          },
+        ],
+        usage: {
+          prompt_tokens: 10,
+          completion_tokens: 5,
+          total_tokens: 15,
+        },
+      };
+    };
+
+    // Mock the OpenAI session and chat completions
+    const mockSession = {
+      chat: {
+        completions: {
+          create: vi.fn().mockResolvedValue(mockStream()),
+        },
+      },
+    };
+
+    const openai = new OpenAI({
+      model: "gpt-4o-mini",
+      apiKey: "test-key",
+      // @ts-expect-error: mockSession is a mock object for testing purposes
+      session: mockSession,
+    });
+
+    // @ts-expect-error accessing protected method
+    const stream = openai.streamChat({
+      messages: [{ role: "user" as const, content: "Hello" }],
+      stream: true,
+    });
+
+    const chunks: ChatResponseChunk[] = [];
+    for await (const chunk of stream) {
+      chunks.push(chunk);
+    }
+
+    expect(chunks).toHaveLength(1);
+    expect(chunks[0].delta).toBe("");
+    expect(chunks[0].raw).toHaveProperty("usage");
+  });
 });

packages/providers/perplexity/CHANGELOG.md

@@ -1,5 +1,13 @@
 # @llamaindex/perplexity
 
+## 0.0.31
+
+### Patch Changes
+
+- Updated dependencies [001a515]
+- Updated dependencies [9d7d205]
+  - @llamaindex/openai@0.4.18
+
 ## 0.0.30
 
 ### Patch Changes

packages/providers/perplexity/package.json

@@ -1,7 +1,7 @@
 {
   "name": "@llamaindex/perplexity",
   "description": "Perplexity Adapter for LlamaIndex",
-  "version": "0.0.30",
+  "version": "0.0.31",
   "type": "module",
   "main": "./dist/index.cjs",
   "module": "./dist/index.js",

packages/providers/storage/azure/CHANGELOG.md

@@ -1,5 +1,13 @@
 # @llamaindex/azure
 
+## 0.1.35
+
+### Patch Changes
+
+- Updated dependencies [001a515]
+- Updated dependencies [9d7d205]
+  - @llamaindex/openai@0.4.18
+
 ## 0.1.34
 
 ### Patch Changes

packages/providers/storage/azure/package.json

@@ -1,7 +1,7 @@
 {
   "name": "@llamaindex/azure",
   "description": "Azure Storage for LlamaIndex",
-  "version": "0.1.34",
+  "version": "0.1.35",
   "type": "module",
   "main": "./dist/index.cjs",
   "module": "./dist/index.js",

packages/providers/together/CHANGELOG.md

@@ -1,5 +1,13 @@
 # @llamaindex/together
 
+## 0.0.34
+
+### Patch Changes
+
+- Updated dependencies [001a515]
+- Updated dependencies [9d7d205]
+  - @llamaindex/openai@0.4.18
+
 ## 0.0.33
 
 ### Patch Changes

packages/providers/together/package.json

@@ -1,7 +1,7 @@
 {
   "name": "@llamaindex/together",
   "description": "Together Adapter for LlamaIndex",
-  "version": "0.0.33",
+  "version": "0.0.34",
   "type": "module",
   "main": "./dist/index.cjs",
   "module": "./dist/index.js",

packages/providers/vllm/CHANGELOG.md

@@ -1,5 +1,13 @@
 # @llamaindex/vllm
 
+## 0.0.60
+
+### Patch Changes
+
+- Updated dependencies [001a515]
+- Updated dependencies [9d7d205]
+  - @llamaindex/openai@0.4.18
+
 ## 0.0.59
 
 ### Patch Changes

packages/providers/vllm/package.json

@@ -1,7 +1,7 @@
 {
   "name": "@llamaindex/vllm",
   "description": "vLLM Adapter for LlamaIndex",
-  "version": "0.0.59",
+  "version": "0.0.60",
   "type": "module",
   "main": "./dist/index.cjs",
   "module": "./dist/index.js",

packages/providers/xai/CHANGELOG.md

@@ -1,5 +1,13 @@
 # @llamaindex/xai
 
+## 0.0.21
+
+### Patch Changes
+
+- Updated dependencies [001a515]
+- Updated dependencies [9d7d205]
+  - @llamaindex/openai@0.4.18
+
 ## 0.0.20
 
 ### Patch Changes

packages/providers/xai/package.json

@@ -1,7 +1,7 @@
 {
   "name": "@llamaindex/xai",
   "description": "XAI Adapter for LlamaIndex",
-  "version": "0.0.20",
+  "version": "0.0.21",
   "type": "module",
   "main": "./dist/index.cjs",
   "module": "./dist/index.js",

packages/workflow/CHANGELOG.md

@@ -1,5 +1,11 @@
 # @llamaindex/workflow
 
+## 1.1.22
+
+### Patch Changes
+
+- 1995b38: bump @llamaindex/workflow-core in workflow package
+
 ## 1.1.21
 
 ### Patch Changes

packages/workflow/package.json

@@ -1,7 +1,7 @@
 {
   "name": "@llamaindex/workflow",
   "description": "Workflow API",
-  "version": "1.1.21",
+  "version": "1.1.22",
   "type": "module",
   "types": "dist/index.d.ts",
   "module": "dist/index.js",
@@ -49,6 +49,6 @@
     "zod-to-json-schema": "^3.24.6"
   },
   "dependencies": {
-    "@llamaindex/workflow-core": "^1.0.0"
+    "@llamaindex/workflow-core": "^1.3.0"
   }
 }

packages/workflow/src/agent/agent-handler.ts

@@ -1,4 +1,7 @@
-import { getContext, type WorkflowEventData } from "@llamaindex/workflow-core";
+import {
+  type WorkflowContext,
+  type WorkflowEventData,
+} from "@llamaindex/workflow-core";
 import {
   AgentWorkflow,
   startAgentEvent,
@@ -71,9 +74,10 @@ function createWorkflowForStepHandler(
 export const agentHandler = (
   params: Omit<StepHandlerParams, "workflowContext">,
 ) => {
-  return async (event: WorkflowEventData<unknown>) => {
-    const context = getContext();
-
+  return async (
+    context: WorkflowContext,
+    event: WorkflowEventData<unknown>,
+  ) => {
     const workflow = createWorkflowForStepHandler({
       ...params,
       workflowContext: context,

packages/workflow/src/agent/agent-workflow.ts

@@ -8,7 +8,6 @@ import { stringifyJSONToMessageContent } from "@llamaindex/core/utils";
 import { consoleLogger, emptyLogger, type Logger } from "@llamaindex/env";
 import {
   createWorkflow,
-  getContext,
   workflowEvent,
   type Handler,
   type Workflow,
@@ -16,7 +15,10 @@ import {
   type WorkflowEvent,
   type WorkflowEventData,
 } from "@llamaindex/workflow-core";
-import { createStatefulMiddleware } from "@llamaindex/workflow-core/middleware/state";
+import {
+  createStatefulMiddleware,
+  type StatefulContext,
+} from "@llamaindex/workflow-core/middleware/state";
 import { z } from "zod";
 import type { AgentWorkflowState, BaseWorkflowAgent } from "./base";
 import {
@@ -339,9 +341,10 @@ export class AgentWorkflow implements Workflow {
   }
 
   private handleInputStep = async (
+    context: StatefulContext<AgentWorkflowState>,
     event: WorkflowEventData<AgentInputData>,
   ) => {
-    const { state } = this.stateful.getContext();
+    const { state } = context;
     const { userInput, chatHistory } = event.data;
     const memory = state.memory;
     if (chatHistory) {
@@ -375,7 +378,10 @@ export class AgentWorkflow implements Workflow {
     });
   };
 
-  private setupAgent = async (event: WorkflowEventData<AgentInput>) => {
+  private setupAgent = async (
+    context: StatefulContext<AgentWorkflowState>,
+    event: WorkflowEventData<AgentInput>,
+  ) => {
     const currentAgentName = event.data.currentAgentName;
     const agent = this.agents.get(currentAgentName);
     if (!agent) {
@@ -396,16 +402,19 @@ export class AgentWorkflow implements Workflow {
     });
   };
 
-  private runAgentStep = async (event: WorkflowEventData<AgentSetup>) => {
-    const { sendEvent } = this.stateful.getContext();
+  private runAgentStep = async (
+    context: StatefulContext<AgentWorkflowState>,
+    event: WorkflowEventData<AgentSetup>,
+  ) => {
+    const { sendEvent } = context;
     const agent = this.agents.get(event.data.currentAgentName);
     if (!agent) {
       throw new Error("No valid agent found");
     }
 
     const output = await agent.takeStep(
-      this.stateful.getContext(),
-      this.stateful.getContext().state,
+      context,
+      context.state,
       event.data.input,
       agent.tools,
     );
@@ -421,7 +430,10 @@ export class AgentWorkflow implements Workflow {
     sendEvent(agentOutputEvent.with(output));
   };
 
-  private parseAgentOutput = async (event: WorkflowEventData<AgentStep>) => {
+  private parseAgentOutput = async (
+    context: StatefulContext<AgentWorkflowState>,
+    event: WorkflowEventData<AgentStep>,
+  ) => {
     const { agentName, response, toolCalls } = event.data;
     const agent = this.agents.get(agentName);
     if (!agent) {
@@ -442,15 +454,12 @@ export class AgentWorkflow implements Workflow {
         raw: response,
         currentAgentName: agentName,
       };
-      const content = await agent.finalize(
-        this.stateful.getContext().state,
-        agentOutput,
-      );
+      const content = await agent.finalize(context.state, agentOutput);
 
       return stopAgentEvent.with({
         message: content.response,
         result: content.response.content,
-        state: this.stateful.getContext().state,
+        state: context.state,
       });
     }
 
@@ -460,8 +469,11 @@ export class AgentWorkflow implements Workflow {
     });
   };
 
-  private executeToolCalls = async (event: WorkflowEventData<ToolCalls>) => {
-    const { sendEvent } = getContext();
+  private executeToolCalls = async (
+    context: StatefulContext<AgentWorkflowState>,
+    event: WorkflowEventData<ToolCalls>,
+  ) => {
+    const { sendEvent } = context;
     const { agentName, toolCalls } = event.data;
     const agent = this.agents.get(agentName);
     if (!agent) {
@@ -507,6 +519,7 @@ export class AgentWorkflow implements Workflow {
   };
 
   private processToolResults = async (
+    context: StatefulContext<AgentWorkflowState>,
     event: WorkflowEventData<ToolResults>,
   ) => {
     const { agentName, results } = event.data;
@@ -517,10 +530,7 @@ export class AgentWorkflow implements Workflow {
       throw new Error(`Agent ${agentName} not found`);
     }
 
-    await agent.handleToolCallResults(
-      this.stateful.getContext().state,
-      results,
-    );
+    await agent.handleToolCallResults(context.state, results);
 
     const directResult = results.find(
       (r: AgentToolCallResult) => r.returnDirect,
@@ -542,22 +552,22 @@ export class AgentWorkflow implements Workflow {
         currentAgentName: agent.name,
       };
 
-      await agent.finalize(this.stateful.getContext().state, agentOutput);
+      await agent.finalize(context.state, agentOutput);
 
       if (isHandoff) {
-        const nextAgentName = this.stateful.getContext().state.nextAgentName;
+        const nextAgentName = context.state.nextAgentName;
 
         this.logger.log(
           `[Agent ${agentName}]: Handoff to ${nextAgentName}: ${directResult.toolOutput.result}`,
         );
 
         if (nextAgentName) {
-          this.stateful.getContext().state.currentAgentName = nextAgentName;
-          this.stateful.getContext().state.nextAgentName = null;
+          context.state.currentAgentName = nextAgentName;
+          context.state.nextAgentName = null;
 
-          const messages = await this.stateful
-            .getContext()
-            .state.memory.getLLM(this.agents.get(nextAgentName)?.llm);
+          const messages = await context.state.memory.getLLM(
+            this.agents.get(nextAgentName)?.llm,
+          );
 
           this.logger.log(`[Agent ${nextAgentName}]: Starting agent`);
 
@@ -571,14 +581,14 @@ export class AgentWorkflow implements Workflow {
       return stopAgentEvent.with({
         message: responseMessage,
         result: output,
-        state: this.stateful.getContext().state,
+        state: context.state,
       });
     }
 
     // Continue with another agent step
-    const messages = await this.stateful
-      .getContext()
-      .state.memory.getLLM(this.agents.get(agent.name)?.llm);
+    const messages = await context.state.memory.getLLM(
+      this.agents.get(agent.name)?.llm,
+    );
     return agentInputEvent.with({
       input: messages,
       currentAgentName: agent.name,

packages/workflow/src/index.ts

@@ -1,5 +1,4 @@
 export * from "@llamaindex/workflow-core";
-export * from "@llamaindex/workflow-core/middleware/snapshot";
 export * from "@llamaindex/workflow-core/middleware/state";
 export * from "@llamaindex/workflow-core/stream/run";
 export { zodEvent } from "@llamaindex/workflow-core/util/zod";

tsconfig.json

@@ -223,6 +223,9 @@
     },
     {
       "path": "./packages/community/tsconfig.json"
+    },
+    {
+      "path": "./examples/local-settings/tsconfig.json"
     }
   ]
 }

unit/CHANGELOG.md

@@ -1,5 +1,16 @@
 # @llamaindex/unit-test
 
+## 0.1.60
+
+### Patch Changes
+
+- Updated dependencies [1995b38]
+- Updated dependencies [001a515]
+- Updated dependencies [9d7d205]
+  - @llamaindex/workflow@1.1.22
+  - @llamaindex/openai@0.4.18
+  - llamaindex@0.11.28
+
 ## 0.1.59
 
 ### Patch Changes

unit/package.json

@@ -1,7 +1,7 @@
 {
   "name": "@llamaindex/unit-test",
   "private": true,
-  "version": "0.1.59",
+  "version": "0.1.60",
   "type": "module",
   "scripts": {
     "test": "vitest run"