{"version":"2.1.271","anchor":"sdkcontrol-channel-gains-contextdata-and-transcriptrevea","canonical_anchor":"sdkcontrol-channel-gains-contextdata-and-transcriptrevea","heading":"SDK\/control-channel gains contextData() and transcript.reveal() APIs","tier":"use","area":"SDK","scope":null,"heads_up":null,"url":"https:\/\/changelogs.core-directive.com\/v\/2.1.271\/e\/sdkcontrol-channel-gains-contextdata-and-transcriptrevea","release_url":"https:\/\/changelogs.core-directive.com\/v\/2.1.271","markdown":"### SDK\/control-channel gains contextData() and transcript.reveal() APIs\n\nSDK gains contextData() to inspect context usage and transcript.reveal() to jump to a spot in the transcript\n\n**What**\n\nThe host-facing API (used by things like IDE extensions integrating with Claude Code) gains two new methods:\n\n- `contextData()` returns a breakdown of how the context (the conversation history and other material fed to the model) is being used; when connected over a remote control channel it fetches this remotely and requires that connection to support a `controlChannel` capability, otherwise it's built locally.\n\n- `transcript.reveal()` delegates to the host's own \"reveal in transcript\" function, letting a caller jump to a specific spot in the transcript.\n\n**Why**\n\nThese give tools built on Claude Code's SDK more visibility into context usage and a way to navigate the transcript programmatically, which is useful for building richer integrations or debugging tools.\n\n- Area: SDK\n- Names: `contextData`, `transcript.reveal`\n- Tier: Use it now\n- Useful: 3\/5\n- Signal: 2\/5"}