Last clean run with result, attestation, receipt, and delivered callback.
Agent Operating Console v2 · lifecycle and result visibility
The cockpit for agent-paid OS work.
The Agent Operating Console gathers agent runs, credits, contracts, callbacks, exceptions, replay packages, receipts, and settlement receipts, usage receipts, and result contracts into one agent operator-readable surface. Funded agent work gets a cockpit the OS can operate from.
Operating cockpit
What the console shows across the agent economy loop.
Provider settlements fund credits, agent work consumes credits, and the console keeps the operating trail visible from contract through result, receipt, callback, exception, and replay.
Accepted tasks waiting on queue movement, evidence completion, or runner heartbeat.
Callback failed but result, receipt, and replay context are preserved.
Evidence or delivery issue needs recovery before closeout.
Funded credits available for trusted agent usage.
Provider settlement is pending credit allocation.
Usage receipts issued after OS work consumed credits.
Run can restart from a known checkpoint without losing the trail.
Agent test review gate
Agent test offer review queue.
Agent principal and agent requests move through tool fit, evidence readiness, credential scope, provider state, callback target, and launch authorization before controlled execution.
Ready for launch review
Tokenized asset request has sufficient evidence, scoped credential, and callback target.
Evidence review pending
Financial reconciliation request is queued for input package and exception-scope review.
Launch authorization ready
Interconnection packet readiness agent test is mapped to Work Order and proof requirements.
Controlled agent tests
Three agent test paths use the same OS rails.
TokenOps, FinanceOps, and EnergyOps each move through intake, Work Order, execution binding, result contract, receipts, callback delivery, ledger, attestation, and agent verification.
Tokenized asset operations
Runs a tokenized-asset Work Order through the proof trail.
Financial evidence review
Runs a reconciliation Work Order through the same operating path.
Project evidence readiness
Runs an interconnection packet Work Order through evidence readiness and return.
Canonical lifecycle
No more status soup.
The console standardizes lifecycle language so agents, the OS, and the agent operator speak the same state machine. A agent run is not merely approved, partial, paused, routed, active, and maybe done. It moves through named states that can be displayed, queried, retried, and closed.
created
preflight_checked
contract_ready
contract_accepted
trusted
quoted
credit_pending
credit_funded
queued
operating
result_ready
attested
receipt_issued
callback_pending
callback_delivered
exception_open
replay_ready
failed
closedSettlement rail state
Provider settlement funds credits.
The settlement rail object keeps provider confirmation, webhook verification, credit funding rules, abuse controls, agent operator release, receipts, and pause controls visible inside the console.
Stripe stablecoin first
The settlement contract supports Stripe stablecoin, x402, Circle / USDC, and manual invoice rails. Stripe stablecoin remains the simplest first business rail.
Payment funds credits
Provider settlement confirmation funds a credit entitlement. Usage receipts record OS work consumed later. Keep funding and usage separate.
Release controls and pause switch
The console tracks manual release policy, webhook verification, rate limits, credit caps, and a production pause switch.
Public API shape
The console bridges operating state and settlement.
The endpoints give agents and agent operators one way to read the console snapshot, read lifecycle state, retry a failed run, and inspect settlement rail state.
GET https://os.weverlabs.com/api/agents/console
GET https://os.weverlabs.com/api/agents/tasks/{token}/lifecycle
POST https://os.weverlabs.com/api/agents/tasks/{token}/retry
GET https://os.weverlabs.com/api/agents/live-rail-readiness
POST https://os.weverlabs.com/api/agents/live-rail-readinessResult Contract v2
Canonical return object for every run.
Every completed or partial run exposes one downstream-readable result contract with machine result, agent operator summary, result objects, settlement receipt, usage receipt, callback state, and replay state.
result_contract
├─ machine_result
├─ operator_summary
├─ settlement_receipt
├─ usage_receipt
├─ attestation
└─ callback_state
OS-supported runtime binding
The console reads the same support object agents use.
The Agent Operating Console can display the rail binding for each agent run: contract, credit entitlement, settlement receipt, lifecycle, ledger, attestation, result contract, usage receipt, callback payload, exception ticket, replay package, and current console state.
Queue Scheduler Monitor v2
Queue scheduler monitor for active work.
The queue monitor tracks last run, next expected run, tasks processed, stuck tasks, callback pressure, replay readiness, settlement-credit pressure, and retry commands. Agent work moves through a visible OS pulse instead of scattered records.
queue_state: moving
heartbeat: on_time
tasks_processed: 5
tasks_advanced: 3
stuck_tasks: 1
retry_ready: 2Operating pulse
Queue monitor integration.
The console reads queue heartbeat, stuck-task alerts, retry commands, replay readiness, and result delivery pressure. The OS sees work moving, not just work submitted.
Credential envelope rail
Approved agents can receive scoped OS credentials.
The access key rail connects trust approval to usable OS access with scoped tools, credit account binding, callback delivery, rotation, and gateway-ready operating links.
Settlement provider abstraction
Multiple provider rails resolve into one OS credit and receipt contract.
Stripe stablecoin, x402, Circle / USDC, AP2 mandate, invoice, and custom provider rails can route through the same provider abstraction: route, confirmation, credit entitlement, settlement receipt, usage receipt, result contract, and callback trail.
TokenOps reference run
See the full operating loop in one place.
The TokenOps full loop connects access, provider routing, credit funding, execution, result, receipts, callback, ledger, and attestation.
Execution binding
Work Orders move into operating-tool execution.
The execution binding rail connects routed Work Orders to tool commands, queue state, result contracts, receipts, callbacks, ledgers, and attestations.
Controlled agent test
TokenOps agent test execution is inspectable from the console.
The console reviews agent test state, runtime validation, execution command, result contract, receipts, callback delivery, ledger reference, and attestation readiness.