# What changed in @langchain/typesafe

> 31 changes in @langchain/typesafe 0.0 to 0.1 from its official release notes, upgrade guides and advisories: 14 breaking, 2 deprecations, 1 security, 14 new APIs and options. Each one cited. Sources checked 2026-11-12. HTML: https://unstale.sh/npm/@langchain/typesafe/

To see which of these apply to a repository, run `npx @unstale/cli init` in it.

## @langchain/typesafe 0.1

### Breaking changes

- ClassificationResponse is removed; question and answer types are re-exported from core. (0.1.0) — [release notes](https://github.com/langchain-ai/langchainjs/releases/tag/%40langchain/typesafe%400.1.0)
- TypeSafeClassifier responses now use core's ClassifierResponse, with token usage provided through usage_metadata. (0.1.0) — [release notes](https://github.com/langchain-ai/langchainjs/releases/tag/%40langchain/typesafe%400.1.0)
- Every question now requires instructions. (0.1.0) — [release notes](https://github.com/langchain-ai/langchainjs/releases/tag/%40langchain/typesafe%400.1.0)
- An invalid question now throws a plain Error from invoke instead of a TypeSafeError from the constructor. (0.1.0) — [release notes](https://github.com/langchain-ai/langchainjs/releases/tag/%40langchain/typesafe%400.1.0)
- JsonValue is removed. (0.1.0) — [release notes](https://github.com/langchain-ai/langchainjs/releases/tag/%40langchain/typesafe%400.1.0)
- TypeSafeClassifier now requires @langchain/core >= 1.4.0. (0.1.0) — [release notes](https://github.com/langchain-ai/langchainjs/releases/tag/%40langchain/typesafe%400.1.0)
- QuestionContent is removed; the replacement name is Content. (0.1.0) — [release notes](https://github.com/langchain-ai/langchainjs/releases/tag/%40langchain/typesafe%400.1.0)
- State now uses core's type, which no longer lists Date; dates are still sent as ISO strings. (0.1.0) — [release notes](https://github.com/langchain-ai/langchainjs/releases/tag/%40langchain/typesafe%400.1.0)
- TypeSafeClassifier now extends BaseDecisionModel; questions are supplied in each invoke request instead of the constructor, and invoke receives { state, questions }. (0.1.0) — [release notes](https://github.com/langchain-ai/langchainjs/releases/tag/%40langchain/typesafe%400.1.0)
- TypeSafeClassifierCallOptions is removed. (0.1.0) — [release notes](https://github.com/langchain-ai/langchainjs/releases/tag/%40langchain/typesafe%400.1.0)
- Usage is removed. (0.1.0) — [release notes](https://github.com/langchain-ai/langchainjs/releases/tag/%40langchain/typesafe%400.1.0)
- Token usage uses input_tokens, output_tokens, and total_tokens instead of usage with inputTokens and outputTokens. (0.1.0) — [release notes](https://github.com/langchain-ai/langchainjs/releases/tag/%40langchain/typesafe%400.1.0)
- ValidatedQuestions is removed. (0.1.0) — [release notes](https://github.com/langchain-ai/langchainjs/releases/tag/%40langchain/typesafe%400.1.0)
- Installed dependencies now require Zod 4.6.6 or newer to exclude versions affected by GHSA-mrhx-c7xc-m3w5; Zod v3 schemas remain supported through zod/v3. (0.1.0) — [release notes](https://github.com/langchain-ai/langchainjs/releases/tag/%40langchain/typesafe%400.1.0)

### Deprecations

- autoModeMiddleware from @langchain/typesafe/middleware is deprecated, warns once when called, and will be removed in 0.2.0; use the version from langchain with classifier: new TypeSafeClassifier(). (0.1.0) — [release notes](https://github.com/langchain-ai/langchainjs/releases/tag/%40langchain/typesafe%400.1.0)
- modelRouterMiddleware from @langchain/typesafe/middleware is deprecated, warns once when called, and will be removed in 0.2.0; use the version from langchain with classifier: new TypeSafeClassifier(). (0.1.0) — [release notes](https://github.com/langchain-ai/langchainjs/releases/tag/%40langchain/typesafe%400.1.0)

### New APIs and options

- Resumes pagination using the cursor returned by the previous page. (0.1.0) — [docs](https://docs.langchain.com/langsmith/smith-api/teams/list-organization-teams)
- Filters results to teams the specified organization identity is a direct member of. (0.1.0) — [docs](https://docs.langchain.com/langsmith/smith-api/teams/list-organization-teams)
- Controls the number of teams per page; accepts values from 1 to 100 and defaults to 20. (0.1.0) — [docs](https://docs.langchain.com/langsmith/smith-api/teams/list-organization-teams)
- Filters results to workspace teams under the specified organization-wide team. (0.1.0) — [docs](https://docs.langchain.com/langsmith/smith-api/teams/list-organization-teams)
- Adds an endpoint to retrieve a team by ID. Organization-scoped teams require organization:teams:read; workspace-scoped teams require workspaces:teams:read in their workspace. (0.1.0) — [docs](https://docs.langchain.com/langsmith/smith-api/teams/get-a-team)
- Adds an endpoint to list a team's access policies, with cursor-based pagination and organization- or workspace-scoped read permissions. (0.1.0) — [docs](https://docs.langchain.com/langsmith/smith-api/teams/list-a-teams-access-policies)
- Adds a paginated endpoint to list workspace identities for a workspace-scoped team's members. It accepts page_size and cursor and requires workspaces:teams:read in the team's workspace. (0.1.0) — [docs](https://docs.langchain.com/langsmith/smith-api/teams/list-workspace-scoped-team-members)
- Adds an endpoint to grant an organization-wide team a role in a workspace. It requires organization:teams:manage-grants and allows at most one grant per team per workspace. (0.1.0) — [docs](https://docs.langchain.com/langsmith/smith-api/teams/grant-a-team-a-role-in-a-workspace)
- Adds a GET endpoint to retrieve an organization-wide team's grant in a workspace. It requires organization:teams:read or workspace-scoped workspaces:teams:read permission. (0.1.0) — [docs](https://docs.langchain.com/langsmith/smith-api/teams/get-a-teams-role-in-a-workspace)
- Filters teams to those belonging to or granted into the specified workspace; results can include role_id and role_name. (0.1.0) — [docs](https://docs.langchain.com/langsmith/smith-api/teams/list-organization-teams)
- Box questions are now supported. (0.1.0) — [release notes](https://github.com/langchain-ai/langchainjs/releases/tag/%40langchain/typesafe%400.1.0)
- Adds an endpoint to attach an existing organization access policy to a team, optionally limiting an organization-wide team's policy to one workspace. (0.1.0) — [docs](https://docs.langchain.com/langsmith/smith-api/teams/attach-an-access-policy-to-a-team)
- Image content blocks in state or question content can now be sent as TypeSafe image assets. (0.1.0) — [release notes](https://github.com/langchain-ai/langchainjs/releases/tag/%40langchain/typesafe%400.1.0)

## @langchain/typesafe 0.0

### Security

- Adds middleware for blocking risky tool calls using a calibrated TypeSafe Noul probability. (0.0.2) — [release notes](https://github.com/langchain-ai/langchainjs/releases/tag/%40langchain/typesafe%400.0.2)

### New APIs and options

- Adds TypeSafe Choice-based model routing middleware. (0.0.2) — [release notes](https://github.com/langchain-ai/langchainjs/releases/tag/%40langchain/typesafe%400.0.2)