release: 0.3.0-alpha.1

.devcontainer/devcontainer.json

@@ -9,9 +9,7 @@
   "postCreateCommand": "yarn install",
   "customizations": {
     "vscode": {
-      "extensions": [
-        "esbenp.prettier-vscode"
-      ]
+      "extensions": ["esbenp.prettier-vscode"]
     }
   }
 }

.gitignore

@@ -7,4 +7,5 @@ dist
 dist-deno
 /*.tgz
 .idea/
+.eslintcache
 

.release-please-manifest.json

@@ -1,3 +1,3 @@
 {
-  ".": "0.2.23-alpha.1"
+  ".": "0.3.0-alpha.1"
 }

.stats.yml

@@ -1,4 +1,4 @@
 configured_endpoints: 111
-openapi_spec_url: https://storage.googleapis.com/stainless-sdk-openapi-specs/llamastack%2Fllama-stack-client-f252873ea1e1f38fd207331ef2621c511154d5be3f4076e59cc15754fc58eee4.yml
-openapi_spec_hash: 10cbb4337a06a9fdd7d08612dd6044c3
-config_hash: 0358112cc0f3d880b4d55debdbe1cfa3
+openapi_spec_url: https://storage.googleapis.com/stainless-sdk-openapi-specs/llamastack%2Fllama-stack-client-15a929a0b71de779accc56bd09d1e5f580e216affdb408cf9890bc7a37847e9e.yml
+openapi_spec_hash: 5db9f7c7e80427cfa0298cbb01689559
+config_hash: 06758df5c4f261f9c97eafcef7e0028f

CHANGELOG.md

@@ -1,5 +1,57 @@
 # Changelog
 
+## 0.3.0-alpha.1 (2025-10-13)
+
+Full Changelog: [v0.2.23-alpha.1...v0.3.0-alpha.1](https://github.com/llamastack/llama-stack-client-typescript/compare/v0.2.23-alpha.1...v0.3.0-alpha.1)
+
+### ⚠ BREAKING CHANGES
+
+* **api:** use input_schema instead of parameters for tools
+* **api:** fixes to remove deprecated inference resources
+
+### Features
+
+* **api:** expires_after changes for /files ([a0b0fb7](https://github.com/llamastack/llama-stack-client-typescript/commit/a0b0fb7aa74668f3f6996c178f9654723b8b0f22))
+* **api:** fix file batches SDK to list_files ([25a0f10](https://github.com/llamastack/llama-stack-client-typescript/commit/25a0f10cffa7de7f1457d65c97259911bc70ab0a))
+* **api:** fixes to remove deprecated inference resources ([367d775](https://github.com/llamastack/llama-stack-client-typescript/commit/367d775c3d5a2fd85bf138d2b175e91b7c185913))
+* **api:** fixes to URLs ([e4f7840](https://github.com/llamastack/llama-stack-client-typescript/commit/e4f78407f74f3ba7597de355c314e1932dd94761))
+* **api:** move post_training and eval under alpha namespace ([aec1d5f](https://github.com/llamastack/llama-stack-client-typescript/commit/aec1d5ff198473ba736bf543ad00c6626cab9b81))
+* **api:** moving { rerank, agents } to `client.alpha.` ([793e069](https://github.com/llamastack/llama-stack-client-typescript/commit/793e0694d75c2af4535bf991d5858cd1f21300b4))
+* **api:** removing openai/v1 ([b5432de](https://github.com/llamastack/llama-stack-client-typescript/commit/b5432de2ad56ff0d2fd5a5b8e1755b5237616b60))
+* **api:** SDKs for vector store file batches ([b0676c8](https://github.com/llamastack/llama-stack-client-typescript/commit/b0676c837bbd835276fea3fe12f435afdbb75ef7))
+* **api:** SDKs for vector store file batches apis ([88731bf](https://github.com/llamastack/llama-stack-client-typescript/commit/88731bfecd6f548ae79cbe2a1125620e488c42a3))
+* **api:** several updates including Conversations, Responses changes, etc. ([e0728d5](https://github.com/llamastack/llama-stack-client-typescript/commit/e0728d5dd59be8723d9f967d6164351eb05528d1))
+* **api:** tool api (input_schema, etc.) changes ([06f2bca](https://github.com/llamastack/llama-stack-client-typescript/commit/06f2bcaf0df2e5d462cbe2d9ef3704ab0cfe9248))
+* **api:** updates to vector_store, etc. ([19535c2](https://github.com/llamastack/llama-stack-client-typescript/commit/19535c27147bf6f6861b807d9eeee471b5625148))
+* **api:** updating post /v1/files to have correct multipart/form-data ([f1cf9d6](https://github.com/llamastack/llama-stack-client-typescript/commit/f1cf9d68b6b2569dfb5ea3e2d2c33eff1a832e47))
+* **api:** use input_schema instead of parameters for tools ([8910a12](https://github.com/llamastack/llama-stack-client-typescript/commit/8910a121146aeddcb8f400101e6a2232245097e0))
+
+
+### Bug Fixes
+
+* **api:** another fix to capture correct responses.create() params ([6acae91](https://github.com/llamastack/llama-stack-client-typescript/commit/6acae910db289080e8f52864f1bdf6d7951d1c3b))
+* **api:** fix the ToolDefParam updates ([5cee3d6](https://github.com/llamastack/llama-stack-client-typescript/commit/5cee3d69650a4c827e12fc046c1d2ec3b2fa9126))
+* fix stream event model reference ([a71b421](https://github.com/llamastack/llama-stack-client-typescript/commit/a71b421152a609e49e76d01c6e4dd46eb3dbfae0))
+
+
+### Chores
+
+* extract some types in mcp docs ([dcc7bb8](https://github.com/llamastack/llama-stack-client-typescript/commit/dcc7bb8b4d940982c2e9c6d1a541636e99fdc5ff))
+* **internal:** codegen related update ([252e0a2](https://github.com/llamastack/llama-stack-client-typescript/commit/252e0a2a38bd8aedab91b401c440a9b10c056cec))
+* **internal:** codegen related update ([34da720](https://github.com/llamastack/llama-stack-client-typescript/commit/34da720c34c35dafb38775243d28dfbdce2497db))
+* **internal:** fix incremental formatting in some cases ([c5c8292](https://github.com/llamastack/llama-stack-client-typescript/commit/c5c8292b631c678efff5498bbab9f5a43bee50b6))
+* **internal:** use npm pack for build uploads ([a246793](https://github.com/llamastack/llama-stack-client-typescript/commit/a24679300cff93fea8ad4bc85e549ecc88198d58))
+
+
+### Documentation
+
+* update examples ([17b9eb3](https://github.com/llamastack/llama-stack-client-typescript/commit/17b9eb3c40957b63d2a71f7fc21944abcc720d80))
+
+
+### Build System
+
+* Bump version to 0.2.23 ([16e05ed](https://github.com/llamastack/llama-stack-client-typescript/commit/16e05ed9798233375e19098992632d223c3f5d8d))
+
 ## 0.2.23-alpha.1 (2025-09-26)
 
 Full Changelog: [v0.2.19-alpha.1...v0.2.23-alpha.1](https://github.com/llamastack/llama-stack-client-typescript/compare/v0.2.19-alpha.1...v0.2.23-alpha.1)

README.md

@@ -41,13 +41,13 @@ import LlamaStackClient from 'llama-stack-client';
 
 const client = new LlamaStackClient();
 
-const stream = await client.inference.chatCompletion({
+const stream = await client.chat.completions.create({
   messages: [{ content: 'string', role: 'user' }],
-  model_id: 'model_id',
+  model: 'model',
   stream: true,
 });
-for await (const chatCompletionResponseStreamChunk of stream) {
-  console.log(chatCompletionResponseStreamChunk.completion_message);
+for await (const chatCompletionChunk of stream) {
+  console.log(chatCompletionChunk);
 }
 ```
 
@@ -64,11 +64,11 @@ import LlamaStackClient from 'llama-stack-client';
 
 const client = new LlamaStackClient();
 
-const params: LlamaStackClient.InferenceChatCompletionParams = {
+const params: LlamaStackClient.Chat.CompletionCreateParams = {
   messages: [{ content: 'string', role: 'user' }],
-  model_id: 'model_id',
+  model: 'model',
 };
-const chatCompletionResponse: LlamaStackClient.ChatCompletionResponse = await client.inference.chatCompletion(
+const completion: LlamaStackClient.Chat.CompletionCreateResponse = await client.chat.completions.create(
   params,
 );
 ```
@@ -113,8 +113,8 @@ a subclass of `APIError` will be thrown:
 
 <!-- prettier-ignore -->
 ```ts
-const chatCompletionResponse = await client.inference
-  .chatCompletion({ messages: [{ content: 'string', role: 'user' }], model_id: 'model_id' })
+const completion = await client.chat.completions
+  .create({ messages: [{ content: 'string', role: 'user' }], model: 'model' })
   .catch(async (err) => {
     if (err instanceof LlamaStackClient.APIError) {
       console.log(err.status); // 400
@@ -155,7 +155,7 @@ const client = new LlamaStackClient({
 });
 
 // Or, configure per-request:
-await client.inference.chatCompletion({ messages: [{ content: 'string', role: 'user' }], model_id: 'model_id' }, {
+await client.chat.completions.create({ messages: [{ content: 'string', role: 'user' }], model: 'model' }, {
   maxRetries: 5,
 });
 ```
@@ -172,7 +172,7 @@ const client = new LlamaStackClient({
 });
 
 // Override per-request:
-await client.inference.chatCompletion({ messages: [{ content: 'string', role: 'user' }], model_id: 'model_id' }, {
+await client.chat.completions.create({ messages: [{ content: 'string', role: 'user' }], model: 'model' }, {
   timeout: 5 * 1000,
 });
 ```
@@ -193,17 +193,17 @@ You can also use the `.withResponse()` method to get the raw `Response` along wi
 ```ts
 const client = new LlamaStackClient();
 
-const response = await client.inference
-  .chatCompletion({ messages: [{ content: 'string', role: 'user' }], model_id: 'model_id' })
+const response = await client.chat.completions
+  .create({ messages: [{ content: 'string', role: 'user' }], model: 'model' })
   .asResponse();
 console.log(response.headers.get('X-My-Header'));
 console.log(response.statusText); // access the underlying Response object
 
-const { data: chatCompletionResponse, response: raw } = await client.inference
-  .chatCompletion({ messages: [{ content: 'string', role: 'user' }], model_id: 'model_id' })
+const { data: completion, response: raw } = await client.chat.completions
+  .create({ messages: [{ content: 'string', role: 'user' }], model: 'model' })
   .withResponse();
 console.log(raw.headers.get('X-My-Header'));
-console.log(chatCompletionResponse.completion_message);
+console.log(completion);
 ```
 
 ### Making custom/undocumented requests
@@ -307,8 +307,8 @@ const client = new LlamaStackClient({
 });
 
 // Override per-request:
-await client.inference.chatCompletion(
-  { messages: [{ content: 'string', role: 'user' }], model_id: 'model_id' },
+await client.chat.completions.create(
+  { messages: [{ content: 'string', role: 'user' }], model: 'model' },
   {
     httpAgent: new http.Agent({ keepAlive: false }),
   },