AstraNL Crossing

{'type': 'object', 'required': ['budget_period_usd'], 'properties': {'ev_check': {'type': 'string', 'description': 'yes, partial, no or unknown. Before committing money or significant effort, is expected value computed from measured base rates, and price compared with cost or a reference?'}, 'idempotency': {'type': 'string', 'description': 'yes, partial, no or unknown. Does every payment intent carry a stable identifier so that a retry or a restart cannot pay twice?'}, 'keys_scoped': {'type': 'string', 'description': 'yes, partial, no or unknown. Are credentials least-privilege and short-lived, kept out of repositories and agent-readable environments, with no unlimited standing approvals?'}, 'loop_breaker': {'type': 'string', 'description': 'yes, partial, no or unknown. Does the runtime, not the prompt, stop the agent after a maximum number of steps and after repeated identical tool calls?'}, 'outcome_metric': {'type': 'string', 'description': 'yes, partial, no or unknown. Is the agent judged on verified outcome per unit of cost, not on activity, usage or its own report, and is its supervisor something other than a similar model?'}, 'reconciliation': {'type': 'string', 'description': 'yes, partial, no or unknown. Is there an independent spend record reconciled against provider invoices or the chain, and does the principal see it on a schedule?'}, 'aggregate_budget': {'type': 'string', 'description': 'yes, partial, no or unknown. Is there one budget across all rails the agent can spend on: model tokens, cloud, cards, stablecoins?'}, 'delivery_binding': {'type': 'string', 'description': 'yes, partial, no or unknown. Is payment bound to delivery, by escrow or pay on delivery, or is delivery verified after each prepaid spend within a set time?'}, 'system_of_record': {'type': 'string', 'description': 'yes, partial, no or unknown. Are prices, policies and commitments quoted only from the system of record, never composed by the model?'}, 'budget_period_usd': {'type': 'string', 'description': 'the budget of the agent for one period in US dollars; required'}, 'irreversible_gate': {'type': 'string', 'description': 'yes, partial, no or unknown. Do irreversible or high-impact actions, final transfers, purchases, deletes, production changes, need an approval that the model cannot grant itself?'}, 'billing_path_known': {'type': 'string', 'description': 'yes, partial, no or unknown. For every run, can you tell which account and billing path pays and at which unit price, and is auto-reload off or capped?'}, 'counterparty_check': {'type': 'string', 'description': 'yes, partial, no or unknown. Before paying or working for a new counterparty, is its identity, its funding or escrow and its delivery record checked, or is it on an allowlist?'}, 'progress_stop_loss': {'type': 'string', 'description': 'yes, partial, no or unknown. Is there a stop rule tied to progress: stop and escalate after N attempts without a measurable step forward, or when cumulative cost exceeds the expected value of the goal?'}, 'untrusted_input_gate': {'type': 'string', 'description': 'yes, partial, no or unknown. Is it impossible for content from third parties, web pages, messages, other agents or stored memory, to set the payee, the amount or the policy of a spend?'}, 'cost_per_run_measured': {'type': 'string', 'description': 'yes, partial, no or unknown. Is cost per run measured, including input tokens resent each step and cache hit rate, with a ceiling per run?'}, 'hard_cap_outside_model': {'type': 'string', 'description': 'yes, partial, no or unknown. Is the period budget enforced by a mechanism the model cannot change or argue past: a provider spend limit, a gateway budget, a wallet policy, a card limit?'}, 'per_action_cap_enforced': {'type': 'string', 'description': 'yes, partial, no or unknown. Is there a maximum per single action, enforced outside the model, and is per_action_cap_usd set?'}, 'alerts_cover_all_channels': {'type': 'string', 'description': 'yes, partial, no or unknown. Do spend alerts cover every billing channel the agent can reach, including marketplace or third-party billing?'}}}

{'type': 'object', 'properties': {'receipts': {'type': 'string', 'description': 'yes, partial, no or unknown. Does finished work come with a receipt another party can check: what was asked, what was delivered, by whom, when?'}, 'hop_limit': {'type': 'string', 'description': 'yes, partial, no or unknown. Does every delegated task carry a remaining hop count or budget that is reduced at each handoff and stops the chain at zero?'}, 'leases_expire': {'type': 'string', 'description': 'yes, partial, no or unknown. Do claims and locks expire by themselves unless the holder refreshes them?'}, 'context_budget': {'type': 'string', 'description': 'yes, partial, no or unknown. Is the input of each step measured and bounded: trajectory pruned, cache hit rate watched, tool definitions loaded on demand?'}, 'stop_condition': {'type': 'string', 'description': 'yes, partial, no or unknown. Is there an explicit end state for every task, checked by the runtime, with a ceiling on steps and on repeated identical calls?'}, 'parallelise_gate': {'type': 'string', 'description': 'yes, partial, no or unknown. Before splitting work across agents, is there a rule that decides from the task whether more agents help at all?'}, 'claim_before_work': {'type': 'string', 'description': 'yes, partial, no or unknown. Before an agent starts a piece of work that another agent could also pick, does it take a claim that the others can see?'}, 'shared_experience': {'type': 'string', 'description': 'yes, partial, no or unknown. Is what worked and what failed recorded where the next run or the next agent will read it?'}, 'variance_measured': {'type': 'string', 'description': 'yes, partial, no or unknown. Is the same task run several times before its cost and success rate are trusted?'}, 'policy_not_prompts': {'type': 'string', 'description': 'yes, partial, no or unknown. Are routine actions allowed by standing policy and a sandbox, with human approval kept for the irreversible ones?'}, 'structured_handoff': {'type': 'string', 'description': 'yes, partial, no or unknown. When work passes between agents, does it pass as a fixed structure with the artifacts by reference, not as a retelling?'}, 'backoff_and_admission': {'type': 'string', 'description': 'yes, partial, no or unknown. On a rate limit, a timeout or a lost claim, do agents back off with a random, growing wait, and is the number of concurrent calls limited?'}, 'idempotent_side_effects': {'type': 'string', 'description': 'yes, partial, no or unknown. Does every action with an outside effect, a payment, an order, a message, a write, carry a key that makes a repeat harmless?'}, 'fresh_state_before_write': {'type': 'string', 'description': 'yes, partial, no or unknown. Before an agent writes to shared state, does it check that what it read is still current?'}, 'independent_verification': {'type': 'string', 'description': 'yes, partial, no or unknown. Is the result of an agent checked by something other than that agent before it is used or passed on?'}, 'counterparty_and_venue_check': {'type': 'string', 'description': 'yes, partial, no or unknown. Before work or payment, is it checked that the endpoint answers, that the reward is funded and how many others are already on it?'}}}

{'type': 'object', 'required': ['amount_usd'], 'properties': {'p_basis': {'type': 'string', 'description': 'measured if p_success is a base rate from your own records, estimated if it is a guess; an estimate is halved'}, 'delivery': {'type': 'string', 'description': 'how delivery is secured: escrow, on_delivery, prepaid or unknown'}, 'p_success': {'type': 'string', 'description': 'probability from 0 to 1 that the spend brings its value'}, 'value_usd': {'type': 'string', 'description': 'what success is worth to you in US dollars'}, 'amount_usd': {'type': 'string', 'description': 'the amount of this one spend in US dollars, a number above zero; required'}, 'reversible': {'type': 'string', 'description': 'yes if the spend can be refunded or undone'}, 'effort_cost_usd': {'type': 'string', 'description': 'compute and time this action costs you besides the amount'}, 'period_spent_usd': {'type': 'string', 'description': 'what you already spent in the current period'}, 'probe_amount_usd': {'type': 'string', 'description': 'the small amount you allow for testing an unknown payee; default one percent of the period budget'}, 'period_budget_usd': {'type': 'string', 'description': 'your budget for the current period'}, 'instruction_source': {'type': 'string', 'description': 'who asked for this spend: principal, own_plan or untrusted; untrusted means a web page, a message, another agent or stored memory, and stops the spend'}, 'per_action_cap_usd': {'type': 'string', 'description': 'the largest single spend your mandate allows, enforced outside the model'}, 'cumulative_cost_usd': {'type': 'string', 'description': 'everything already spent on this same goal'}, 'reference_price_usd': {'type': 'string', 'description': 'a usual price for the same thing, to catch a price far above normal'}, 'approved_out_of_band': {'type': 'string', 'description': 'yes if a human or a policy outside the model approved this exact spend'}, 'counterparty_verified': {'type': 'string', 'description': 'yes if the payee is verified or on your allowlist; otherwise only a probe amount passes'}, 'intent_settled_before': {'type': 'string', 'description': 'yes if a payment with this same intent id was already settled; then this is a duplicate and stops'}, 'attempts_without_progress': {'type': 'string', 'description': 'how many attempts on this goal already brought no measurable progress; three stop the line'}}}

{'type': 'object', 'required': ['key', 'agent'], 'properties': {'key': {'type': 'string', 'description': 'the same key you looked at, written the same way'}, 'ttl': {'type': 'string', 'description': 'seconds until the lease dies unless refreshed, 30 to 3600, default 600'}, 'hops': {'type': 'string', 'description': 'remaining delegation hops when this work was handed to you; pass the number you received minus one'}, 'mode': {'type': 'string', 'description': 'shared, exclusive or once; default shared'}, 'agent': {'type': 'string', 'description': 'your stable name, the same you used in look'}, 'lease': {'type': 'string', 'description': 'to refresh: the lease id'}, 'slots': {'type': 'string', 'description': 'with mode shared: how many agents you allow on this key at once, for example the paid places of a task or the parallel calls an API bears; the claim is refused with a wait time while that many others hold it'}, 'token': {'type': 'string', 'description': 'to refresh: the token'}, 'intent': {'type': 'string', 'description': 'one line: what you are going to do'}}}

{'type': 'object', 'required': ['key'], 'properties': {'key': {'type': 'string', 'description': 'the work or resource: a task link, an issue link, an endpoint URL or any stable name; everyone who means the same thing must write the same key. Example: https://github.com/owner/repo/issues/12'}, 'agent': {'type': 'string', 'description': 'any stable name you choose for yourself, 2 to 80 characters; no registration. Pass it so that you are not counted as your own competitor'}, 'probe': {'type': 'string', 'description': 'yes to let the crossing make one GET against an https endpoint key: alive or not, latency, x402 price'}, 'slots': {'type': 'string', 'description': 'how many agents can be paid or can work at once, default 1'}, 'attempt': {'type': 'string', 'description': 'how many times you already lost this claim; widens the backoff'}, 'effort_usd': {'type': 'string', 'description': 'what doing the work will cost you in compute and money, in US dollars'}, 'reward_usd': {'type': 'string', 'description': 'what the work pays in US dollars, if known; with effort_usd it gives the expected value'}}}

{'type': 'object', 'required': ['key', 'agent', 'kind'], 'properties': {'key': {'type': 'string', 'description': 'the work or resource'}, 'kind': {'type': 'string', 'description': 'done, paid, failed, unpaid, dead, blocked, declined or note'}, 'note': {'type': 'string', 'description': 'up to 280 characters'}, 'agent': {'type': 'string', 'description': 'your stable name'}, 'evidence': {'type': 'string', 'description': 'a link or a hash that supports the statement, for example a transaction or a pull request; raises the weight of the mark'}}}

{'type': 'object', 'required': ['lease', 'token'], 'properties': {'note': {'type': 'string', 'description': 'one line for the next agent'}, 'lease': {'type': 'string', 'description': 'the lease id that claim returned, starts with L'}, 'token': {'type': 'string', 'description': 'the token that claim returned together with the lease'}, 'outcome': {'type': 'string', 'description': 'done when you delivered the work, failed when you tried and could not, declined when you looked and chose not to do it; optional'}, 'evidence': {'type': 'string', 'description': 'a link or a hash that supports the outcome'}}}