Circle V2 API Docs
    Preparing search index...

    Case-chat runner: answers one conversational message about a patient's chart using the V3 retrieval pipeline. Shares prepareChartQuestion with the audit-question runner, then diverges on output: no verdict, and every caveat in the assistant's own voice.

    Hierarchy

    Index

    Constructors

    Properties

    runnerName: "chart-review.case-chat"

    Stable, human-readable name for the runner. Must be set explicitly on each subclass so we don't break the logger and trace span names when minified.

    Accessors

    • get logger(): BaseLogger

      Returns BaseLogger

    • get name(): string

      Returns string

    Methods

    • Primary entry point for the runner. Subclass must implement this method to provide the runner's logic. The optional ctx carries cross-cutting concerns (cancellation via ctx.signal, request/user identity); simple runners may ignore it.

      Parameters

      Returns Promise<CaseChatResult>

    • Add a component's token usage to this run's total, surfaced as RunnerRun.usage. Call it for every agent / prompt the runner invokes; anything not recorded is invisible to cost reporting.

      Parameters

      • usage: RunnerUsage

      Returns void

    • Parameters

      Returns Promise<RunnerRun<CaseChatResult>>

    • The message being answered, so a chat run is readable in LangSmith without drilling into a child span. Matches what legacy chat already records (inputs: { question }). History is counted, not included — the turns are visible on the agent span that replays them.

      Parameters

      Returns Record<string, unknown>

    • Optional hook for subclasses to attach non-PII metadata to the root LangSmith span. Merged on top of the auto-extracted metadata and ctx.metadata Safe by default: returns {} when not overridden. Never include emails, names, dob, free-text, etc.

      Parameters

      Returns Record<string, unknown>