Skip to content

[3P] Cost governance & abuse controls (gates the public open) #56

Open

Description

@serge-ivo

Part of #58 (the open-to-third-party epic). Must be solid before widening beyond invite/curated.

  • Per-creator + per-agent quotas + rate limits (executions, tokens, subrequests).
  • Cost caps + kill switch per agent/creator (extends admin [Admin][API] Runtime kill switch for platform-paid AI (platform_settings override) #46 platform-AI kill switch).
  • Reassert isolation guarantees for untrusted agents: tenant isolation (exists), secret isolation (Tier-2 #W2), SSRF (exists), no cross-instance data.
  • Incident response: suspend agent/creator; user-facing "this agent was suspended".
  • Content/abuse policy + takedown (DMCA) path.

Activity

  1. added
    deferred: no demandBlocked on the #68 focus bet — not before external users exist
    on Aug 6, 2026
  2. serge-ivo commented on Aug 6, 2026

    @serge-ivo
    ContributorAuthor

    Labelled deferred: no demand — not cancelled, and not started.

    Per #250 ("the board contradicts the focus bet — make deferred-by-strategy legible"), and #58's own wording, which gates this work on demand rather than on readiness.

    The measurement that decides it, taken 2026-08-06 over 30 days (GET /v1/admin/usage/external):

    external users:  0
    operator calls:  2,782
    spend:           $40.92 — entirely the operator's own
    

    This issue serves third-party creators. There are none, and nothing on the board measures progress toward getting one. Leaving it as live work makes the roadmap read as if it were in flight, which is precisely what #250 objects to.

    The un-gate condition is #68's: external users on a first-party runtime agent. When that number is non-zero, this comes back — the endpoint above makes it checkable rather than a matter of opinion.

    Nothing here is judged wrong or wasted. The platform work that already landed (capability registry, connector framework, declarative pipelines, per-tool consent) is what makes first-party agents cheap to build, and it stays. What is deferred is the marketplace layer on top: sandboxing untrusted creator code, curated publish review, payout metering, creator onboarding.

  3. added
    P3: laterDesign, strategy, or deferred pending a decision or demand
    on Aug 18, 2026
  4. serge-ivo commented on Oct 14, 2026

    @serge-ivo
    ContributorAuthor

    Owner decision on 2026-10-14: retire/defer marketplace work for now. Do not start third-party marketplace expansion, creator-code sandbox, public creator submission/review, payout/metering, or related 3P launch work from this ticket set. Current focus is making first-party runtime agents and core PAGS flows work coherently for real users. Reopen/reactivate marketplace work only with a new explicit owner decision.

  5. proagentstore commented on Oct 23, 2026

    @proagentstore

    ❓ The coder stopped on a question: Issue #56 is labelled deferred: no demand with a 2026-10-14 owner decision to defer all third-party marketplace work. The CLI has stopped because that standing directive conflicts with the run objective. How should I proceed?

    Options: Implement #56 now — the run objective overrides the deferral · Keep it deferred — mark this run as done without implementing · Keep it deferred — mark this run as failed/blocked

    Why it asks: The CLI will not start work on a deferred issue without an explicit owner decision to reactivate it.

    Answer it on the run's card or with answer_instance_input. The run is parked until it is answered — answer any time; it continues from where it stopped.

  6. proagentstore commented on Oct 23, 2026

    @proagentstore

    Owner decision (Serge, 24 Oct 2026): skip all marketplace and payout work. The parked run for this issue was closed without changes; nothing was implemented. Issue stays deferred.

  7. proagentstore commented on Oct 30, 2026

    @proagentstore

    Auto-pickup flagged this issue for review (#1407). A run reported it done, but no delivered commit could be found for the run that finished it — labelled needs-human so it is not retried automatically; remove the label once it is confirmed resolved (or reopen the work) and it becomes eligible again.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Metadata

Metadata

Assignees

No one assigned

    Labels

    P3: laterDesign, strategy, or deferred pending a decision or demanddeferred: no demandBlocked on the #68 focus bet — not before external users existenhancementNew feature or requestneeds-human

    Type

    No type

    Projects

    No projects

      Milestone

      No milestone

      Relationships

      None yet

      Development

      No branches or pull requests

      Issue actions