fix: langchain parsing token usage for responses api

[navgarcha]

Problem

Using LangChainCallbackHandler (@posthog/ai/langchain) for LLM analysis the token usage is missing when a generation uses OpenAI's responses API.

Changes

LangChain uses the key estimatedTokenUsage for the responses API on llmOutput (vs chat completions API that is currently supported via the tokenUsage key) as seen here. This patch includes this new key in the array of keys to pull this information from.

Release info Sub-libraries affected

Libraries affected

• All of them
• posthog-js (web)
• posthog-js-lite (web lite)
• posthog-node
• posthog-react-native
• @posthog/react
• @posthog/ai
• @posthog/nextjs-config

[vercel]

@navgarcha is attempting to deploy a commit to the PostHog Team on Vercel.

A member of the Team first needs to authorize it.

[greptile-apps]

_{1 file reviewed, no comments}

_{Edit Code Review Agent Settings | Greptile}

[posthog-bot]

This PR hasn't seen activity in a week! Should it be merged, closed, or further worked on? If you want to keep it open, post a comment or remove the stale label – otherwise this will be closed in another week.

[navgarcha]

Anyone from posthog able to review? 🙏