Member Junction
    Preparing search index...

    Class BaseCloudHarnessAdapterAbstract

    Abstract base class for remote HTTP/cloud agent harness adapters (Antigravity Cloud, Claude Code Cloud, OpenAI Codex Cloud).

    Implements full session initialization, credential & header assembly, bounded-poll and adaptive-wake turn waiting modes, mid-turn cancellation, deduplicated incremental event emission, and idempotent session teardown that preserves remote execution when detached for AgentWake.

    Hierarchy (View Summary)

    Index

    Constructors

    Properties

    authHeaders: Record<string, string> = {}
    config: HarnessSessionConfig = null
    didResume: boolean = false
    emittedEventKeys: Set<string> = ...
    httpTransport: ICloudHttpTransport
    isDetachedForWake: boolean = false
    lastExecutionState: CloudExecutionState
    permissionPolicy: HarnessPermissionPolicy
    reportedModel: string
    resumedSnapshot: CloudNormalizedSnapshot = null
    resumedWasDetached: boolean = false
    runtimeSettings: ResolvedCloudRuntimeSettings = null
    sessionId: string
    systemPrompt: string

    Accessors

    • get DidResumeSession(): boolean

      Whether this session actually continued HarnessSessionConfig.ResumeSessionId.

      Default false: a harness that cannot resume, or one offered no prior session, starts cold and must be sent the full conversation. Adapters that DO resume MUST override this and report truthfully — the caller sends only the newest message when it returns true, so a false positive leaves the harness answering a question it never saw the context for.

      Deliberately separate from CapabilitySettings.SessionResume. That flag says the adapter CAN resume in principle; this says it DID, this time. A stale or pruned session id makes the two disagree, and only the second one is safe to branch the turn input on.

      Returns boolean

    • get ReportedModel(): string

      The model the harness actually used, if it reports one.

      Adapters that can observe this SHOULD override it. Accounting resolves AIPromptRun.ModelID from this first and only falls back to the harness row's declared model, because a harness left to choose its own model will — and billing a run against a model it never used is worse than having no attribution at all, since it looks authoritative.

      Returns string

    Methods

    • Builds standard JSON request headers combining auth headers, JSON content-type, and extraHeaders.

      Parameters

      • includeJsonContentType: boolean = true

      Returns Record<string, string>

    • Tears the session down.

      MUST be idempotent and MUST be safe to call on every exit path — success, failure, cancellation and crash — because it is what revokes the per-run MCP credential and releases the workspace. A teardown that only runs on the happy path leaks a live credential.

      Returns Promise<void>

    • Optional hook invoked during StartSession when starting a brand-new session (no ResumeSessionId). Stateful session-container platforms (e.g. Claude Cloud /v1/sessions) override this to allocate the remote session upfront; interaction-per-turn platforms leave the default no-op.

      Parameters

      • Optional_signal: AbortSignal

      Returns Promise<void>

    • Answers a permission-request the adapter raised.

      Only meaningful when Capabilities.PermissionHooks is true; adapters without hooks should treat this as a no-op rather than throwing, because the posture layer above may still call it defensively.

      Parameters

      • _requestId: string
      • _approved: boolean
      • Optional_note: string

      Returns Promise<void>

    • Runs one turn and streams what happens.

      The first call receives the task prompt; subsequent calls receive formatted results of steps MJ executed on the harness's behalf. Implementations MUST emit exactly one terminal event — turn-complete or session-error — so the caller's accumulation loop always terminates.

      Where the harness cannot resume a session natively (SessionResume false), the adapter is responsible for replaying prior context into a fresh invocation here, and for reporting the resulting token cost through usage so the run's guardrails see the true spend.

      Parameters

      • input: string

      Returns AsyncIterable<HarnessTurnEvent>

    • Injects a custom sleep implementation for deterministic timer control in tests.

      Parameters

      • sleepFn: (ms: number, signal?: AbortSignal) => Promise<void>

      Returns void

    • Supplies MJ's system prompt for the session, where the harness can accept one.

      Harnesses ship their own system prompt defining their identity, and it dominates anything sent as user text. MJ's turn-end contract delivered as a user message therefore competes with the harness's own instructions and loses — observed directly: a harness given the contract in the user turn still answered "what can you do?" in prose, costing a retry every run.

      Adapters whose harness accepts a system prompt SHOULD override this. Those that cannot are no worse off than before: the contract still rides in the turn input.

      Parameters

      • systemPrompt: string

      Returns void