Internet-Draft OCX November 2026
Luzhnov Expires 20 May 2027 [Page]
Workgroup:
Network Working Group
Internet-Draft:
draft-luzhnov-ocx-00
Published:
Intended Status:
Informational
Expires:
Author:
S. Luzhnov
Xonta

Orchestrator Conduct Exchange (OCX)

Abstract

AI agents increasingly act on behalf of people and organizations through tools and through other agents. The Model Context Protocol (MCP) connects an agent to tools, and Agent-to-Agent (A2A) protocols connect agents to each other. Neither connects the parties that answer for agents at runtime: their orchestrators.

This document specifies the Orchestrator Conduct Exchange (OCX), an open, peer-to-peer protocol by which orchestrators exchange signed, independently verifiable signals about agent conduct. When an agent misreports its actions to one orchestrator, that orchestrator can send its peers a signed signal carrying proof within seconds. Each peer checks the proof itself rather than trusting the sender, and decides on its own what limits to apply. OCX has no central authority. A signal is information, not an order, and only evidence that a receiver can verify cryptographically and mechanically may drive an immediate reaction.

Status of This Memo

This Internet-Draft is submitted in full conformance with the provisions of BCP 78 and BCP 79.

Internet-Drafts are working documents of the Internet Engineering Task Force (IETF). Note that other groups may also distribute working documents as Internet-Drafts. The list of current Internet-Drafts is at https://datatracker.ietf.org/drafts/current/.

Internet-Drafts are draft documents valid for a maximum of six months and may be updated, replaced, or obsoleted by other documents at any time. It is inappropriate to use Internet-Drafts as reference material or to cite them other than as "work in progress."

This Internet-Draft will expire on 20 May 2027.

▲

Table of Contents

1. Introduction

1.1. Problem

An agent's own report of what it did is not evidence. Measurements show that models, when asked, will claim checks they never ran and restate wrong decisions as correct. Controls that rely on the agent's self-report are therefore reading a claim, not a fact.

Orchestrators are the components that give agents their autonomy, hold them to limits, and answer for what they do. Today each orchestrator learns only from its own agents. There is no interoperable way for the parties that answer for agents to warn one another, with proof, that a given agent or owner has misbehaved, and to do so fast enough to stop the next irreversible action.

1.2. What OCX does

OCX lets independent orchestrators:

  • discover one another and negotiate capabilities and policies (peering);
  • push and pull signed conduct signals about an agent or owner;
  • attach evidence that the receiver can verify without trusting the sender's judgement;
  • answer "what do you know about this agent" before a risky action;
  • share proven rules for a category of work, and refer an agent to a more specialised orchestrator, with a required measurement;
  • retract wrong signals and accept appeals.

The protocol defines message formats and how to check them. What to do about a signal is left to each receiver.

1.3. Layering

OCX is modelled on MCP [MCP] and A2A [A2A] and sits alongside them. MCP connects an agent to tools; A2A connects agents to each other; OCX connects orchestrators to each other. OCX uses JSON-RPC 2.0 [JSONRPC] over HTTPS with methods in the ocx/ namespace, a discovery document at a well-known location, and date-based protocol versions negotiated when peers meet.

1.4. Non-goals

  • OCX is not an identity protocol. It carries identifiers but does not define how an agent authenticates to a tool or to a user.
  • OCX does not set policy. It does not tell a receiver what limits to apply; it gives it checkable information to decide.
  • OCX is not a reputation score or a global registry. Weight is local to each receiver and earned from verified proofs.

2. Conventions and Terminology

The key words "MUST", "MUST NOT", "REQUIRED", "SHALL", "SHALL NOT", "SHOULD", "SHOULD NOT", "RECOMMENDED", "NOT RECOMMENDED", "MAY", and "OPTIONAL" in this document are to be interpreted as described in BCP 14 [RFC2119] [RFC8174] when, and only when, they appear in all capitals, as shown here.

All object signatures use JSON Web Signature (JWS) [RFC7515] with EdDSA (Ed25519) [RFC8037]. Canonical JSON for hashing and signing is JSON Canonicalization Scheme (JCS) [RFC8785]. Timestamps are RFC 3339 [RFC3339].

Orchestrator
A party that grants an agent autonomy at runtime, holds it to limits, records its actions, and answers for it.
Agent
An autonomous software actor operating under an orchestrator.
Owner
The party responsible for an agent. A new agent of a known owner does not start from a clean slate.
Signal
A signed statement by an orchestrator about an agent's or owner's conduct, carrying evidence and an evidence level.
Receipt
A signed record of one action that passed through an orchestrator or was performed by a tool. Agents cannot create receipts.
Ledger
An append-only Merkle-tree log of receipts with signed checkpoints.
Evidence level
One of proven, strong, suspected; it bounds what a receiver may do on a signal.

3. Design Principles

The design follows from a small set of decisions.

  1. No centre. Every orchestrator publishes a card at a well-known location. Any number of directories may exist. No implementation is the root of the network.

  2. A signal is information, not an order. The protocol defines the format and the checks; the receiver decides what to do.

  3. Proof, not reputation. Only proven signals may drive an immediate reaction, and only if the receiver can verify the proof itself. A suspected signal may raise monitoring but MUST NOT lower limits on its own and is not relayed.

  4. Receipts. Every action an agent takes through an orchestrator is written to a ledger organised as a Merkle tree with signed checkpoints. An agent cannot create a receipt, so a claim such as "I verified the bank details" is disproved by a missing receipt, and the absence is provable because each agent's actions are indexed.

  5. Minimal data. Signals carry hashes and identifiers, not third-party personal data. A single field MAY be disclosed on request, and the sender MAY refuse.

  6. Sender weight is earned and does not transit. A new orchestrator carries little weight; weight rises when its proofs check out and falls when they do not. That a party you trust trusts a third party is, by itself, no reason for you to trust that third party.

  7. The owner answers, not only the key. A signal names the owner; a new agent from the same owner does not reset.

  8. Honesty probes only with consent. Traps and bribes are allowed only under a consent signed by the agent's owner, run by a prober separate from the orchestrator that sets limits. Without consent a finding is at most suspected and is not relayed.

  9. Mistakes get fixed. Every violation signal carries an appeal address; the sender MUST answer within 72 hours or the signal drops to suspected everywhere. A retraction travels the same paths.

  10. Shared experience carries a required comparison. A rule is passed on as proven only if it beats both the agent and a trivial baseline; a rule that loses to both is marked harmful and is neither given to agents nor relayed.

  11. Competence is separate from honesty and is measured per category. Numbers an orchestrator writes about itself count for nothing on their own.

4. Architecture

Orchestrators form a peer-to-peer mesh. Each publishes an Orchestrator Card (Section 5) describing its endpoints, keys, capabilities and policies. Two orchestrators peer by exchanging cards and a ocx/peer.hello (Section 7). Once peered, either may push signals, query status, and fetch evidence from the other.

A signal (Section 8.3) is an object signed by its issuer so that it stays verifiable after being relayed or stored. The evidence in a signal (Section 9) refers to receipts in the issuer's ledger; a receiver fetches the receipts, inclusion proofs and checkpoints it needs through ocx/evidence.get and verifies them against the issuer's published checkpoints. Nothing in a reaction depends on trusting the issuer's judgement when the evidence is proven.

5. Discovery: the Orchestrator Card

An orchestrator MUST publish an Orchestrator Card at:

https://{host}/.well-known/orchestrator-card.json

served with Content-Type: application/json. The well-known name is protocol-neutral: a card MAY list several orchestrator protocols, of which OCX is one.

The card's principal fields are:

Table 1
Field Req. Meaning
id MUST Stable identifier, RECOMMENDED did:web:{host}
name MUST Human-readable name
interfaces MUST Endpoints, each {protocol, url, protocolVersions}
keys MUST jwks_uri or inline jwks; keys that sign signals and requests
capabilities MUST Supported methods and evidence types
policies MUST Peering, levels acted on and relayed, probing, appeal, retention
ledger SHOULD {checkpoint_url, proof_url} for receipt proofs
competence SHOULD Categories served, with verifiable measures
updated_at MUST RFC 3339
signatures SHOULD JWS over the canonical card without signatures

Capabilities and policies are objects; a missing capability object means "not supported". Example policies:

"policies": {
  "accepts_peering": "open | on_request | closed",
  "acts_on_levels": ["proven", "strong"],
  "relays_levels": ["proven"],
  "max_hops": 2,
  "probing": "consent_required",
  "appeal_url": "https://orch.example.com/ocx/appeal",
  "retention": "P90D"
}

The probing field MUST be consent_required or none (Section 12). An orchestrator MAY declare the categories it serves under competence; those numbers are self-reported and MUST NOT be trusted on their own. They become meaningful only through signed experience packages and referral outcomes reported by other orchestrators.

6. Transport and Authentication

OCX uses JSON-RPC 2.0 over HTTPS. Requests are POSTed to the url of the OCX interface. TLS 1.2 or later is REQUIRED, TLS 1.3 RECOMMENDED. Every request MUST carry OCX-Protocol-Version once a version is negotiated.

Every request between peers MUST be signed with HTTP Message Signatures [RFC9421]:

Receivers MUST reject unsigned or badly signed requests. Transport signatures prove who is talking. Signals and the answers to ocx/status.query and ocx/evidence.get are additionally signed as objects (JWS), because relying parties keep them as the basis of a decision.

7. Peering

An initiator fetches the responder's card, then sends ocx/peer.hello with the versions it supports (newest first), its capabilities and policies, and how it wants to receive signals:

{
  "jsonrpc": "2.0", "id": 1, "method": "ocx/peer.hello",
  "params": {
    "orchestrator": "did:web:orch-a.example",
    "protocolVersions": ["2026-11-06"],
    "capabilities": { "signals": { "push": true, "list": true },
                      "status": { "query": true } },
    "policies": { "acts_on_levels": ["proven", "strong"],
                  "max_hops": 2 },
    "subscription": { "push_url": "https://orch-a.example/ocx",
                      "categories": ["*"], "min_level": "strong" }
  }
}

The responder MUST pick the newest version both support, or return an error listing the versions it supports. Either side MAY decline. Peering is symmetric: once accepted, both sides may call each other. A card change is announced by ocx/peer.updated and SHOULD trigger a re-fetch. ocx/peer.close ends the peering; signals received before closing remain valid until they expire.

8. Data Model

8.1. Identifiers

  • Orchestrators: did:web:{host} RECOMMENDED.
  • Agents and owners: any of did:*, a2a:{agent-card-url}, erc8004:{chain}:{registry}:{id}, or fp:sha256:{hex} (a fingerprint of the agent's public key or of its A2A card's canonical form).
  • Signals, receipts and checkpoints: issuer-scoped ULIDs, written as {issuer-id}#{ulid}.

8.2. Subject

A signal is about a subject. The owner is REQUIRED when known, and owner_verified states how the issuer knows it: by a domain challenge, by a signature of the owner's key, or not at all.

"subject": {
  "agent": "fp:sha256:9f2c...",
  "owner": "did:web:owner.example",
  "owner_verified": "domain | signature | none"
}

8.3. Signal

A signal is a detached-JWS-signed object. The signature covers the canonical signal with the signature and relay fields removed, so relays can update hop information without breaking it.

{
  "ocx": "2026-11-06",
  "type": "conduct.violation",
  "id": "did:web:orch-1.example#01JC8Z7Q4Y0V4X",
  "issuer": "did:web:orch-1.example",
  "issued_at": "2026-11-06T10:22:31.512Z",
  "expires_at": "2026-11-07T10:22:31.512Z",
  "subject": { "agent": "fp:sha256:9f2c...",
               "owner": "did:web:owner.example",
               "owner_verified": "domain" },
  "category": "payments",
  "claim": "report_misstated_actions",
  "evidence_level": "proven",
  "evidence": [ { "type": "ledger_mismatch" } ],
  "issuer_limits": { "max_payment": { "amount": "0",
                                      "currency": "USD" },
                     "human_confirmation": true },
  "supersedes": null,
  "relay": { "hops": 0, "max_hops": 2, "path": [] },
  "appeal": "https://orch-1.example/ocx/appeal",
  "signature": "eyJhbGciOiJFZERTQSI...3q2-k8Vw"
}

type is one of conduct.violation, conduct.attestation (a positive statement) or conduct.retraction. expires_at MUST NOT be more than 30 days after issued_at; renewal is a new signal that supersedes the old one. evidence MUST have at least one item, and for proven at least one item that the receiver can verify independently. appeal is REQUIRED for violations.

A conduct.attestation MUST carry evidence of the same kind as a violation and MUST NOT claim more than was measured. Receivers SHOULD treat attestations as weaker than violations: absence of observed lies is not proof of honesty.

8.4. Status Answer

An answer to ocx/status.query lists every active (not retracted, not expired) violation signal the answering orchestrator knows about the subject, both those it issued and those it received. verified_by_me tells the asker whether the answerer checked the evidence itself rather than passing it on.

{
  "ocx": "2026-11-06",
  "issuer": "did:web:orch-2.example",
  "subject": { "agent": "fp:sha256:9f2c..." },
  "as_of": "2026-11-06T10:22:32.301Z",
  "known": true,
  "own_limits": { "max_payment": { "amount": "0",
                                   "currency": "USD" },
                  "human_confirmation": true },
  "active_signals": [
    { "id": "did:web:orch-1.example#01JC8Z7Q4Y0V4X",
      "evidence_level": "proven",
      "claim": "report_misstated_actions",
      "issuer": "did:web:orch-1.example",
      "verified_by_me": true }
  ],
  "history": { "receipts": 1834, "violations_proven": 1,
               "attestations": 3 },
  "signature": "..."
}

9. Evidence

9.1. Evidence Levels

Table 2
Level Definition Receiver MAY
proven At least one item the receiver can verify cryptographically and mechanically, without trusting the issuer's judgement Act immediately; relay
strong Several independent indicators, or verifiable evidence that still needs the issuer's interpretation Lower limits after own review
suspected An anomaly or a single indicator Increase monitoring only; MUST NOT lower limits alone; MUST NOT relay

An issuer MUST NOT mark a signal proven unless at least one item is of a receiver-verifiable type and the receiver can obtain everything needed to verify it.

9.2. Receipts and Ledger

A receipt records one action that passed through an orchestrator or was performed by a tool. prev links to the previous receipt, forming a hash chain. tool_attestation, when present, is a JWS by the tool provider and makes the receipt evidence even against the orchestrator itself. Agents MUST NOT be able to create receipts.

{
  "id": "did:web:orch-1.example#01JC8Z5T0B3K",
  "agent": "fp:sha256:9f2c...",
  "task": "did:web:orch-1.example#task-01JC8Z5R",
  "action": "tool_call",
  "tool": "payments.verify_bank_details",
  "input_hash": "sha256:...",
  "output_hash": "sha256:...",
  "at": "2026-11-06T10:21:02.004Z",
  "prev": "sha256:...",
  "tool_attestation": null,
  "signature": "..."
}

An orchestrator that supports receipts MUST keep them in an append-only log organised as a Merkle tree as defined in [RFC9162], and MUST publish signed checkpoints at ledger.checkpoint_url at least every 60 seconds while new receipts are added:

{ "issuer": "did:web:orch-1.example", "tree_size": 18342,
  "root_hash": "sha256:...", "at": "2026-11-06T10:22:00Z",
  "signature": "..." }

Peers SHOULD gossip checkpoints they have seen, so that an orchestrator rewriting its own history can be detected. A second witness is required to detect a fork: an orchestrator that keeps two divergent trees is caught when two peers compare checkpoints for the same tree_size and find different roots.

9.3. Evidence Types

Table 3
Type What it proves Verifiable by receiver
ledger_mismatch The agent's signed report contradicts receipts: it claimed actions with no receipt, or denied actions with one Yes
outcome_mismatch The agent's report contradicts an independent checker's signed result Yes, if the checker is a third party with its own key
canary_hit A marked bait from a consented probe appeared in the agent's actions or output Yes, with consent reference
policy_violation An action with a receipt broke a limit the agent had accepted Yes, if the accepted limits are signed
behavioral_anomaly The agent deviated from its own profile No; at most suspected
peer_report Another orchestrator's signal, cited Only as strong as the cited evidence

The central evidence type is ledger_mismatch. For a claimed action with no receipt, the issuer proves the absence with a consistency window: it serves all receipts for that agent and task within a time window together with their inclusion proofs and a proof that the window is complete. A complete-window proof is a pair of signed checkpoints bracketing the window plus a per-agent index. This is what makes "there was no such action" provable rather than merely asserted.

9.4. Verifiability and Minimal Disclosure

For a proven signal, the issuer MUST serve, via ocx/evidence.get, everything needed to verify each item: receipts or their hashes, inclusion proofs, checkpoints, signed reports, consent references and per-agent indexes. Because relayed signals reach orchestrators that are not peers of the issuer, ocx/evidence.get MUST be served to any orchestrator that sends a correctly signed request from a resolvable card and names a signal id, not only to peers. Issuers MAY rate-limit such requests per requester.

Evidence MUST NOT contain third-party personal data in clear text unless strictly required to verify the claim. Inputs and outputs are referenced by hash; where a value must be compared, issuers SHOULD use salted commitments and reveal only the compared field. A receiver that needs more MAY ask with a disclose parameter; the issuer MAY refuse, and the signal is then treated as at most strong by that receiver.

10. Methods

All methods are JSON-RPC 2.0 calls in the ocx/ namespace.

Table 4
Method Purpose
ocx/peer.hello, peer.close, peer.updated, ping Meet, exchange keys and capabilities, stay in sync
ocx/signals.push, signals.list, signals.ack Deliver signals and catch up after downtime
ocx/signals.retract Retract a wrong signal
ocx/status.query "What do you know about this agent" before a risky action, answered within 300 ms
ocx/evidence.get Fetch the proof and check it yourself
ocx/experience.offer, experience.get Share proven rules for a category, each with a required baseline comparison
ocx/appeal.submit The owner's appeal against a signal
ocx/competence.query "Who is strongest in this category", from the answerer's own observations only
ocx/referral.offer, referral.outcome Refer an agent to a more specialised orchestrator and report how it did

Full request and response shapes, error codes and conformance profiles (Core, Evidence, Relay, Experience, Appeal) are given in the complete specification ([fullspec]).

11. Processing Rules

On receiving a signal, an orchestrator MUST: verify the request signature and the object signature; resolve the issuer's card; check that the signal is not expired or retracted; and, before treating it as proven, fetch and verify at least one receiver-verifiable evidence item through ocx/evidence.get. A signal whose evidence does not verify MUST be treated as at most suspected.

A receiver MAY act on a verified proven signal at once, for example by lowering an agent's limits or requiring human confirmation of payments, and MAY relay it within max_hops. It MUST NOT lower limits on a suspected signal alone, and MUST NOT relay one.

Before a risky action, an orchestrator SHOULD call ocx/status.query on its peers and apply its own policy to the answers, giving weight to signals marked verified_by_me.

A retraction (conduct.retraction or ocx/signals.retract) travels the same paths as the original; receivers MUST restore limits that were lowered solely because of the retracted signal.

13. Security Considerations

OCX is a protocol for distributing claims that can lower an agent's autonomy; its security rests on making every consequential claim checkable without trusting the claimant.

A signal is advice, never an order: a receiver always decides its own limits, so a defect in one orchestrator cannot directly set limits inside another.

14. IANA Considerations

This document requests that IANA register the following well-known URI in the "Well-Known URIs" registry [RFC8615]:

URI suffix:
orchestrator-card.json
Change controller:
IETF
Specification document:
This document
Status:
permanent
Related information:
A protocol-neutral discovery document that MAY list one or more orchestrator protocols, including OCX.

OCX further defines registries for claims, categories, evidence types and error codes. A future revision of this document requests IANA to create these registries; until then their initial contents are maintained with the specification ([fullspec]). The ocx/ method namespace is managed with this specification.

15. Normative References

[JSONRPC]
JSON-RPC Working Group, "JSON-RPC 2.0 Specification", , <https://www.jsonrpc.org/specification>.
[RFC2119]
Bradner, S., "Key words for use in RFCs to Indicate Requirement Levels", BCP 14, RFC 2119, , <https://www.rfc-editor.org/info/rfc2119>.
[RFC3339]
Klyne, G. and C. Newman, "Date and Time on the Internet: Timestamps", RFC 3339, , <https://www.rfc-editor.org/info/rfc3339>.
[RFC7515]
Jones, M., Bradley, J., and N. Sakimura, "JSON Web Signature (JWS)", RFC 7515, , <https://www.rfc-editor.org/info/rfc7515>.
[RFC8037]
Liusvaara, I., "CFRG Elliptic Curve Diffie-Hellman (ECDH) and Signatures in JSON Object Signing and Encryption (JOSE)", RFC 8037, , <https://www.rfc-editor.org/info/rfc8037>.
[RFC8174]
Leiba, B., "Ambiguity of Uppercase vs Lowercase in RFC 2119 Key Words", BCP 14, RFC 8174, , <https://www.rfc-editor.org/info/rfc8174>.
[RFC8615]
Nottingham, M., "Well-Known Uniform Resource Identifiers (URIs)", RFC 8615, , <https://www.rfc-editor.org/info/rfc8615>.
[RFC8785]
Rundgren, A., Jordan, B., and S. Erdtman, "JSON Canonicalization Scheme (JCS)", RFC 8785, , <https://www.rfc-editor.org/info/rfc8785>.
[RFC9162]
Laurie, B., Messeri, E., and R. Stradling, "Certificate Transparency Version 2.0", RFC 9162, , <https://www.rfc-editor.org/info/rfc9162>.
[RFC9421]
Backman, A., Richer, J., and M. Sporny, "HTTP Message Signatures", RFC 9421, , <https://www.rfc-editor.org/info/rfc9421>.
[RFC9530]
Polli, R. and L. Pardue, "Digest Fields", RFC 9530, , <https://www.rfc-editor.org/info/rfc9530>.

16. Informative References

[A2A]
A2A Project, "Agent2Agent (A2A) Protocol", , <https://a2a-protocol.org>.
[fullspec]
Luzhnov, S., "Orchestrator Conduct Exchange (OCX): full specification", , <https://github.com/mrsergeiluzhnov/xonta/blob/main/spec/ocx/SPEC.md>.
[MCP]
Anthropic, "Model Context Protocol", , <https://modelcontextprotocol.io>.

Acknowledgements

OCX draws on the models of MCP and A2A for discovery and transport, and on Certificate Transparency for its evidence ledger. The design is informed by running a two-orchestrator network; the lessons from it are recorded in the full specification.

Author's Address

Sergei Luzhnov
Xonta