API Evangelist conversational phrasing for Taskhawktech Com Governance API

# Generated by API Evangelist (build-phrasing.py). Our phrasing, not observed demand.
overlay: 1.0.0
info:
  title: API Evangelist conversational phrasing for Taskhawktech Com Governance API
  version: 1.0.0
extends: openapi/taskhawktech-com-governance-api-openapi.yml
actions:
- target: $.info
  update:
    x-apievangelist-phrasing:
      method: generated
      generated: '2026-10-01'
      generator: build-phrasing.py
      label: Generated by API Evangelist
      operations: 8
- target: $.paths['/governance/verify'].post
  update:
    x-apievangelist-phrasing:
      intent: Check a proposed agent action against policy
      effect: read
      questions:
      - How do I check whether an agent's proposed action is allowed by policy before it runs?
      - Can I get a signed allow, constrain or deny decision for a transaction an agent wants to make?
      - Which named policy templates can I apply when verifying an action, like robotics-arm?
      instructions:
      - text: Verify a {action_type} action from agent {agent_id} with payload {action_payload} against policy.
        slots:
          action_type: requestBody.action_type
          agent_id: requestBody.agent_id
          action_payload: requestBody.action_payload
      - text: Check agent {agent_id}'s {action_type} action {action_payload} using policy template {template_id}.
        slots:
          agent_id: requestBody.agent_id
          action_type: requestBody.action_type
          action_payload: requestBody.action_payload
          template_id: requestBody.template_id
      method: generated
      generated: '2026-10-01'
- target: $.paths['/governance/attest'].post
  update:
    x-apievangelist-phrasing:
      intent: Record a provenance attestation for an agent action
      effect: write
      questions:
      - How do I log what my agent did into a tamper-evident, hash-chained record?
      - Can a third party independently verify an attestation of an agent's action?
      - Can I link a new attestation to my agent's previous one for chain continuity?
      instructions:
      - text: Attest that agent {agent_id} did {action_description} with details {action_payload}.
        slots:
          agent_id: requestBody.agent_id
          action_description: requestBody.action_description
          action_payload: requestBody.action_payload
      - text: 'Add an attestation for agent {agent_id}: {action_description}, payload {action_payload}, chained to {prior_attestation_hash}.'
        slots:
          agent_id: requestBody.agent_id
          action_description: requestBody.action_description
          action_payload: requestBody.action_payload
          prior_attestation_hash: requestBody.prior_attestation_hash
      method: generated
      generated: '2026-10-01'
- target: $.paths['/governance/bind'].post
  update:
    x-apievangelist-phrasing:
      intent: Bind a declared intent to an agent command
      effect: write
      questions:
      - How can I prove a command was issued in service of a specific declared intent?
      - Can I nest an intent under a parent intent to build a hierarchy?
      - What is the longest duration I can set on an intent binding?
      instructions:
      - text: Bind agent {agent_id}'s {intent_type} intent "{intent_description}" to command {command_payload}.
        slots:
          agent_id: requestBody.agent_id
          intent_type: requestBody.intent_type
          intent_description: requestBody.intent_description
          command_payload: requestBody.command_payload
      - text: Declare intent {intent_description} of type {intent_type} for agent {agent_id}, binding command {command_payload} with goal {goal_state}.
        slots:
          intent_description: requestBody.intent_description
          intent_type: requestBody.intent_type
          agent_id: requestBody.agent_id
          command_payload: requestBody.command_payload
          goal_state: requestBody.goal_state
      method: generated
      generated: '2026-10-01'
- target: $.paths['/governance/verify-outcome'].post
  update:
    x-apievangelist-phrasing:
      intent: Confirm an executed action met its declared intent
      effect: read
      questions:
      - How do I check that an action my agent already executed actually achieved its intent?
      - Can I allow some tolerance when comparing the end state to the goal state?
      instructions:
      - text: Verify agent {agent_id}'s outcome for intent {intent_id} and binding {binding_id} given resulting state {actual_state}.
        slots:
          agent_id: requestBody.agent_id
          intent_id: requestBody.intent_id
          binding_id: requestBody.binding_id
          actual_state: requestBody.actual_state
      - text: Check whether state {actual_state} satisfies intent {intent_id} (binding {binding_id}, agent {agent_id}) within tolerance {tolerance}.
        slots:
          actual_state: requestBody.actual_state
          intent_id: requestBody.intent_id
          binding_id: requestBody.binding_id
          agent_id: requestBody.agent_id
          tolerance: requestBody.tolerance
      method: generated
      generated: '2026-10-01'
- target: $.paths['/governance/bundle'].post
  update:
    x-apievangelist-phrasing:
      intent: Generate a compliance evidence bundle for an agent
      effect: write
      questions:
      - How do I export certifier-grade compliance evidence for one of my agents?
      - Can I limit an evidence bundle to a specific time range?
      - Does the evidence bundle include post-quantum signatures and verification instructions?
      instructions:
      - text: Generate a compliance evidence bundle for agent {agent_id}.
        slots:
          agent_id: requestBody.agent_id
      - text: Build an evidence bundle for agent {agent_id} from {time_range_start} to {time_range_end}.
        slots:
          agent_id: requestBody.agent_id
          time_range_start: requestBody.time_range_start
          time_range_end: requestBody.time_range_end
      method: generated
      generated: '2026-10-01'
- target: $.paths['/governance/mpp/session'].post
  update:
    x-apievangelist-phrasing:
      intent: Open a governed streaming payment session
      effect: write
      questions:
      - How do I let an agent stream payments within a fixed budget and time window?
      - Can I cap how fast an agent spends per minute during a payment session?
      - What does it cost to open a governed MPP payment session?
      instructions:
      - text: Open a payment session for agent {agent_id} with a budget of {session_budget_cents} cents for {duration_seconds} seconds.
        slots:
          agent_id: requestBody.agent_id
          session_budget_cents: requestBody.session_budget_cents
          duration_seconds: requestBody.duration_seconds
      - text: 'Start an MPP session for {agent_id}: {session_budget_cents} cents over {duration_seconds}s on the {payment_rail} rail.'
        slots:
          agent_id: requestBody.agent_id
          session_budget_cents: requestBody.session_budget_cents
          duration_seconds: requestBody.duration_seconds
          payment_rail: requestBody.payment_rail
      method: generated
      generated: '2026-10-01'
- target: $.paths['/governance/mpp/heartbeat'].post
  update:
    x-apievangelist-phrasing:
      intent: Report mid-session spend for a drift check
      effect: write
      questions:
      - How do I check an active payment session for budget overruns or unauthorized services?
      - Is there a charge for sending periodic heartbeats during a streaming payment session?
      instructions:
      - text: 'Heartbeat session {session_id}: {agent_id} spent {spent_cents}c in {transactions_count} txns on {current_service} at {spending_rate_cents_per_minute}c/min.'
        slots:
          session_id: requestBody.session_id
          agent_id: requestBody.agent_id
          spent_cents: requestBody.spent_cents
          transactions_count: requestBody.transactions_count
          current_service: requestBody.current_service
          spending_rate_cents_per_minute: requestBody.spending_rate_cents_per_minute
      - text: Run a drift check on open session {session_id} for agent {agent_id}, now at {spent_cents} cents.
        slots:
          session_id: requestBody.session_id
          agent_id: requestBody.agent_id
          spent_cents: requestBody.spent_cents
      method: generated
      generated: '2026-10-01'
- target: $.paths['/governance/mpp/close'].post
  update:
    x-apievangelist-phrasing:
      intent: Close a streaming payment session
      effect: destructive
      questions:
      - How do I end a streaming payment session and seal its provenance record?
      - Can I record why a payment session ended, like budget exhausted or drift detected?
      instructions:
      - text: Close session {session_id} for agent {agent_id} with final spend {final_spent_cents} cents across {final_transactions_count} transactions.
        slots:
          session_id: requestBody.session_id
          agent_id: requestBody.agent_id
          final_spent_cents: requestBody.final_spent_cents
          final_transactions_count: requestBody.final_transactions_count
      - text: End payment session {session_id} with reason {close_reason}.
        slots:
          session_id: requestBody.session_id
          close_reason: requestBody.close_reason
      method: generated
      generated: '2026-10-01'