[chore]: rm langchain deps

[seanmcguire12]

why

• these were unneeded dependencies:
  • they were not used in library code at all
  • nor were they included in the public export surface

what changed

• removed lanchain/core and langchain/openai from dependencies
• removed langchain examples
• updated lockfile

---

Summary by cubic

Removed unused LangChain dependencies and examples from packages/core to reduce install size and simplify the codebase. No API or runtime behavior changes.

• Dependencies

  • Removed @langchain/core and @langchain/openai from packages/core/package.json.
  • Updated pnpm-lock.yaml to drop related transitive packages.

• Refactors

  • Deleted LangChain examples: packages/core/examples/langchain-client.ts and packages/core/examples/custom-client-langchain.ts.

^{Written for commit e46cfa4. Summary will update on new commits.}

[changeset-bot]

⚠️ No Changeset found

Latest commit: e46cfa4

Merging this PR will not cause a version bump for any packages. If these changes should not result in a new version, you're good to go. If these changes should result in a version bump, you need to add a changeset.

This PR includes no changesets

When changesets are added to this PR, you'll see the packages that this PR includes changesets for and the associated semver types

Click here to learn what changesets are, and how to add one.

Click here if you're a maintainer who wants to add a changeset to this PR

[cubic-dev-ai]

No issues found across 4 files

Confidence score: 5/5

• Automated review surfaced no issues in the provided summaries.
• No files require special attention.

Architecture diagram

sequenceDiagram
    participant Main as Application Code
    participant Stagehand as Stagehand Core
    participant LLMClient as LLMClient (Abstract)
    participant ConcreteClients as OpenAI / Anthropic / Google / Vercel Clients
    participant LLMProviders as LLM Provider APIs

    Note over Main,LLMProviders: Current Architecture: No LangChain integration

    Main->>Stagehand: Create Stagehand instance with desired LLM client

    alt Using Native Client (e.g., ChatOpenAI from package)
        Main->>ConcreteClients: Instantiate ChatOpenAI client
        Main->>Stagehand: Stagehand({ llmClient: chatOpenAI })
    else Using Vercel AI SDK client
        Main->>ConcreteClients: Create Vercel AI provider (openai, anthropic...)
        Main->>Stagehand: Stagehand({ llmClient: vercelAIClient })
    end

    Stagehand->>LLMClient: Calls createChatCompletion(options)
    LLMClient->>ConcreteClients: Dispatches to the correct provider implementation

    alt Successful request
        ConcreteClients->>LLMProviders: HTTP POST to LLM API (OpenAI, Anthropic, etc.)
        LLMProviders-->>ConcreteClients: LLM response (text + usage)
        ConcreteClients-->>LLMClient: Return ChatCompletion
        LLMClient-->>Stagehand: Return structured response
        Stagehand-->>Main: Return extracted result
    else Request fails / rate-limited
        ConcreteClients->>LLMProviders: HTTP POST
        LLMProviders-->>ConcreteClients: Error response (e.g. 429, 500)
        ConcreteClients-->>LLMClient: Throw error
        LLMClient-->>Stagehand: Propagate error
        Stagehand-->>Main: Return error
    end

    Note over Main,LLMProviders: Not in play: @langchain/core, @langchain/openai
    Note over ConcreteClients: Active integrations: OpenAI, Anthropic, Google, Vercel AI SDK

Loading