Network Working Group I. Schrock
Internet-Draft EMILIA Protocol, Inc.
Intended status: Informational 31 August 2026
Expires: 4 March 2027
The Action Evidence Boundary for Consequential Agent Effects
draft-schrock-action-evidence-boundary-05
Abstract
Consequential agent actions can cross identity, transport,
authorization, policy, and execution systems. Each system can
produce a valid artifact while the executor still lacks a safe rule
for joining the artifacts to the exact effect, consuming one-time
authority, and handling an uncertain outcome. This document defines
the Action Evidence Boundary (AEB), an executor-side processing model
for that lifecycle.
AEB requires native artifact verification, Canonical Action
Identifier (CAID) matching, Authorization Evidence Chain (AEC)
satisfaction, a separate local authorization decision, durable atomic
consumption or reservation, invocation, closed effect outcomes, and
authenticated reconciliation. It defines no receipt or token format,
no policy language, no universal evidence taxonomy, and no new
registry. Native workload credentials, message signatures, attested
per-action tokens, permit records, authorization receipts, and status
mechanisms retain their own semantics and verifiers.
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 4 March 2027.
Schrock Expires 4 March 2027 [Page 1]
Internet-Draft Action Evidence Boundary August 2026
Copyright Notice
Copyright (c) 2026 IETF Trust and the persons identified as the
document authors. All rights reserved.
This document is subject to BCP 78 and the IETF Trust's Legal
Provisions Relating to IETF Documents (https://trustee.ietf.org/
license-info) in effect on the date of publication of this document.
Please review these documents carefully, as they describe your rights
and restrictions with respect to this document. Code Components
extracted from this document must include Revised BSD License text as
described in Section 4.e of the Trust Legal Provisions and are
provided without warranty as described in the Revised BSD License.
Table of Contents
1. Introduction . . . . . . . . . . . . . . . . . . . . . . . . 3
1.1. Scope and Non-Goals . . . . . . . . . . . . . . . . . . . 4
2. Conventions and Terminology . . . . . . . . . . . . . . . . . 5
3. Non-Collapsing Decision and Lifecycle Vocabulary . . . . . . 6
4. Relying-Party Inputs and Pins . . . . . . . . . . . . . . . . 7
5. Required Processing Model . . . . . . . . . . . . . . . . . . 8
5.1. Construct the Observed Material Action . . . . . . . . . 8
5.2. Verify Each Native Artifact . . . . . . . . . . . . . . . 8
5.3. Establish CAID Material-Action MATCH . . . . . . . . . . 9
5.4. Evaluate Required Field-Origin Assertions . . . . . . . . 9
5.5. Evaluate AEC Evidence Satisfaction . . . . . . . . . . . 10
5.6. Pinned Boundary Requirement and Evaluation Record . . . . 10
5.7. Make the Local Authorization Decision . . . . . . . . . . 11
5.8. Atomically Consume or Reserve Before Invocation . . . . . 12
5.9. Invoke the Frozen Action . . . . . . . . . . . . . . . . 12
5.10. Classify the Effect Outcome . . . . . . . . . . . . . . . 13
5.11. Perform Authenticated Reconciliation . . . . . . . . . . 13
6. Declaration and Challenge Semantics . . . . . . . . . . . . . 14
7. Native Evidence and Transport Boundaries . . . . . . . . . . 14
7.1. WIMSE and HTTP Message Signatures . . . . . . . . . . . . 15
7.2. Attested Per-Action Tokens and Permit Records . . . . . . 15
8. Native Compilation Contract . . . . . . . . . . . . . . . . . 16
8.1. Pinned Inputs . . . . . . . . . . . . . . . . . . . . . . 16
8.2. Deterministic Operations . . . . . . . . . . . . . . . . 17
8.3. Closed Compile Result . . . . . . . . . . . . . . . . . . 17
8.4. Semantic-Loss Report . . . . . . . . . . . . . . . . . . 18
8.5. Stable Native Replay Unit . . . . . . . . . . . . . . . . 19
8.6. Path and Provider Ownership . . . . . . . . . . . . . . . 19
8.7. Compilation Conformance . . . . . . . . . . . . . . . . . 20
9. Conformance and Deployment Claims . . . . . . . . . . . . . . 20
10. Security Considerations . . . . . . . . . . . . . . . . . . . 21
11. Privacy Considerations . . . . . . . . . . . . . . . . . . . 22
Schrock Expires 4 March 2027 [Page 2]
Internet-Draft Action Evidence Boundary August 2026
12. Relationship to EMILIA and Adjacent Work . . . . . . . . . . 22
13. IANA Considerations . . . . . . . . . . . . . . . . . . . . . 23
14. Changes since -04 . . . . . . . . . . . . . . . . . . . . . . 23
15. Implementation Status . . . . . . . . . . . . . . . . . . . . 23
16. References . . . . . . . . . . . . . . . . . . . . . . . . . 24
16.1. Normative References . . . . . . . . . . . . . . . . . . 24
16.2. Informative References . . . . . . . . . . . . . . . . . 25
Appendix A. Acknowledgments . . . . . . . . . . . . . . . . . . 26
Author's Address . . . . . . . . . . . . . . . . . . . . . . . . 26
1. Introduction
A remote executor can receive several independently useful inputs: a
workload credential and protected request, a delegation or
capability, a pre-execution permit, a human-authorization artifact,
and a policy decision. None of those inputs alone answers every
question the consequence-owning system has to answer before changing
its system of record.
The missing contract is at the effect boundary. The executor must
determine what exact material action it is about to perform; verify
each artifact under its native rules; correlate independently
verified representations without guessing; evaluate whether the
evidence bundle fills its requirement; make its own authorization
decision; consume or reserve any one-time or bounded authority;
invoke the effect once; and preserve uncertainty when the effect
cannot be observed conclusively.
This document defines that contract. Its required order is:
Schrock Expires 4 March 2027 [Page 3]
Internet-Draft Action Evidence Boundary August 2026
native verification
|
v
CAID material-action MATCH
|
v
AEC evidence SATISFIED
|
v
local policy AUTHORIZED
|
v
atomic CONSUMED / RESERVED
|
v
durable DISPATCH_PENDING
|
v
INVOKED
|
+--> EXECUTED
+--> FAILED
+--> INDETERMINATE --> authenticated reconciliation
Every arrow is conditional. A signature is not authority. Native
verification is not action correlation. Action correlation is not
evidence satisfaction. Evidence satisfaction is not local
authorization. Authorization is not execution. An invocation error
is not proof that no effect occurred.
1.1. Scope and Non-Goals
AEB specifies processing requirements for a boundary that controls a
consequential effect. It can be implemented at a protocol gateway,
service mesh component, application middleware, execution adapter, or
system-of-record write path, provided the deployment states which
effect paths the boundary actually mediates.
AEB does not define:
* a new authorization receipt, access token, attestation token,
permit, credential, or execution-evidence format;
* a native signature, credential, revocation, status, or
transparency verification algorithm;
* a policy language, universal authorization decision, or universal
human-approval inference;
Schrock Expires 4 March 2027 [Page 4]
Internet-Draft Action Evidence Boundary August 2026
* general semantic equivalence between actions;
* provider truth, physical truth, legality, safety, wisdom, or
complete mediation merely because an AEB implementation is
present; or
* a registry for evidence types, states, action mappings, or
verifier names.
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.
BCP 14 is indexed by the RFC Editor at [BCP14].
Effect boundary: The last control point that can withhold the
protected mutation before it is submitted to the effecting system.
Relying party: The party that selects trust inputs, action
definitions, mapping profiles, evidence requirements, freshness
rules, and local authorization policy, and that relies on the
resulting decision.
Native artifact: An evidence, credential, permit, token, receipt,
status, or message-protection object defined outside AEB and
verified under its own specification.
Field-origin assertion: A native artifact in which an issuer asserts
how exact fields of an action representation were sourced or
transformed, and optionally the point-in-time snapshot on which
that assertion rests. Verification establishes the issuer's
signed assertion under pinned trust inputs; it does not
independently establish where the bytes truly originated.
Observed action: The immutable material action constructed by the
effect boundary from executor-controlled parsing and system-of-
record facts.
Material field: A field whose change can alter the protected
consequence, as declared by the selected CAID action-type
definition.
Invocation: The first dispatch of the frozen authorized action to a
component that can cause the protected effect.
Schrock Expires 4 March 2027 [Page 5]
Internet-Draft Action Evidence Boundary August 2026
Authoritative reconciliation: An authenticated, audience-bound
observation from the effecting provider or system of record that
is matched to the original action and operation identifier.
3. Non-Collapsing Decision and Lifecycle Vocabulary
AEB uses the following decisions with the meanings established by the
EMILIA architecture and its component drafts:
VERIFIED: One native artifact passed its native verifier under
relying-party-selected trust inputs.
MATCH: Independently verified artifacts denote the same material
action directly or under exact relying-party-pinned CAID mapping
profiles.
SATISFIED: Verified and matched evidence fills every slot in the
relying party's AEC requirement.
AUTHORIZED: The consequence-owning relying party's local policy
permits this exact action at this time.
EXECUTED: The executor records, or an accepted native artifact
attests, that the exact effect occurred. This meaning remains
bounded by the native source and its trust assumptions.
AEB also names operational lifecycle states:
CONSUMED: A one-time authorization, challenge, operation key, or
equivalent native replay unit has been durably made unavailable
for another invocation.
RESERVED: Bounded state, such as a capability budget, has been
durably fenced for the exact operation before invocation.
DISPATCH_PENDING: A durable intent record binds the frozen action,
operation identifier, provider environment, and reservation before
any effecting dispatch can occur. Recovery treats a stranded
intent as uncertain, not as unused authority.
INVOKED: The protected effect was dispatched using the frozen
authorized action and operation identifier.
FAILED: Authoritative executor or reconciliation evidence
establishes that the invoked operation did not cause the protected
effect. A local exception or timeout alone is not sufficient.
INDETERMINATE: Invocation began, but available authoritative
Schrock Expires 4 March 2027 [Page 6]
Internet-Draft Action Evidence Boundary August 2026
evidence does not establish whether the protected effect occurred.
CONSUMED, RESERVED, DISPATCH_PENDING, INVOKED, FAILED, and
INDETERMINATE are lifecycle terms, not new evidence types or IANA
registry values. A deployment MAY use different local labels if
their semantics are at least as strict.
4. Relying-Party Inputs and Pins
The requester, presenter, agent, and mutable intermediary context are
untrusted inputs. They MAY propose an action and present native
artifacts. They MUST NOT select or weaken the controls used to
accept that request.
Before evaluating an action, the relying party MUST configure or pin,
as applicable:
* the supported native artifact revisions, verifier adapters,
algorithms, trust anchors, issuers, audiences, and status sources;
* when field-origin evidence is required, the accepted assertion
profile and digest, trusted issuers and keys, allowed origin
classes and transformations for each exact field, snapshot policy,
maximum snapshot age, and unavailable-state behavior;
* the CAID suite, action-type definition source, exact source
descriptors, and mapping-profile digests;
* the AEC requirement and the admissible native evidence roles for
each slot;
* local policy identifiers, policy epochs, tenant and organization
boundaries, and any separation-of-duty rule;
* the trusted clock, maximum ages, validity windows, allowed skew,
and revocation or status freshness requirements;
* the durable replay, consumption, reservation, and operation-key
namespaces; and
* the protected executor, provider environment, reconciliation
endpoint, and authenticated provider or system-of-record
identities.
A label, key, profile identifier, requirement, status assertion, or
policy identifier carried only in presenter-controlled data MUST NOT
become its own trust anchor. Missing, conflicting, unsupported, or
ambiguous required configuration MUST fail closed.
Schrock Expires 4 March 2027 [Page 7]
Internet-Draft Action Evidence Boundary August 2026
5. Required Processing Model
5.1. Construct the Observed Material Action
The effect boundary MUST construct an immutable observed action from
effect-relevant facts it controls. Depending on the application,
those facts can include the protocol operation, tool or method,
target resource, tenant, account, amount, currency, destination,
environment, input digest, and unique operation identifier.
The boundary MUST resolve a relying-party-pinned CAID action-type
definition and include every field that definition declares material.
It MUST NOT copy a requester-supplied action digest, CAID, amount,
destination, or resource reference without deriving or checking the
corresponding fact at the protected boundary. If the boundary cannot
determine all material fields, it MUST refuse before invocation.
The observed action MUST be frozen for the remainder of the
lifecycle. A later adapter MUST NOT reconstruct a different action
from mutable request state after authorization.
Before emitting or comparing a CAID, the boundary MUST validate the
constructed action against the complete pinned action-type
definition. A source representation is construction-compatible only
when a pinned mapping can derive every material target field without
guessing. Construction compatibility is distinct from content
equivalence: compatible inputs can still map to different actions,
while a missing, ambiguous, or unverified material field yields
INDETERMINATE.
5.2. Verify Each Native Artifact
Each required native artifact MUST be verified independently under
its own specification and relying-party-selected trust inputs before
CAID mapping or AEC evaluation. The AEB implementation MUST use the
integrity-protected payload returned by the native verifier, or a
projection for which the adapter establishes integrity coverage of
every projected field.
A successful signature check is only one possible step of native
verification. Schema, algorithm, issuer, audience, key status,
validity, proof-of-possession, freshness, replay, and native policy
checks remain those of the selected native profile. A verifier
exception, unavailable required status source, unsupported critical
field, or ambiguous result MUST become a bounded refusal, never an
allow path.
Schrock Expires 4 March 2027 [Page 8]
Internet-Draft Action Evidence Boundary August 2026
The output of this stage is VERIFIED for each accepted artifact. An
artifact that has not reached VERIFIED MUST NOT participate in action
mapping or fill an AEC requirement slot.
5.3. Establish CAID Material-Action MATCH
The boundary MUST recompute the CAID of the observed action under the
selected suite and definition source. It MUST compare every action-
bound required artifact to that observed action using direct CAID
equality or the Action-Mapping Profile defined by [CAID].
Cross-format mapping MUST occur only after native verification and
MUST use the exact source media type, schema version, target action
type, definition source, and mapping-profile digest pinned by the
relying party. Every target material field MUST be covered.
Missing, lossy, unknown, unpinned, conflicting, or ambiguous mappings
yield INDETERMINATE under CAID and MUST fail a required MATCH. AEB
MUST NOT guess equivalence from names, natural-language descriptions,
trace identifiers, or presenter assertions.
MATCH is content correlation only. It does not validate a native
artifact and does not authorize execution.
5.4. Evaluate Required Field-Origin Assertions
A relying party MAY require a natively verified field-origin
assertion for selected fields before admission. This document
defines the processing contract for that input, not a field-origin
wire format, origin taxonomy, scanner, or transformation language.
The boundary MUST verify the assertion under the relying party's
pinned native verifier, issuer and key, assertion profile and digest,
action binding, field selectors, accepted origin classes, accepted
transformation definitions, snapshot policy, freshness bound, and
status inputs. The verifier output MUST bind each asserted field to
the exact observed action or to a lossless, pinned mapping to that
action. A profile identifier or origin label carried only by the
presenter MUST NOT select its own verifier or trust root.
A verified assertion establishes that the pinned issuer made the
signed claim. It does not independently prove source truth, semantic
correctness, absence of prompt injection, authorization, settlement,
or the truth of a later physical effect. If policy requires an
origin constraint for a material field, a missing assertion, unknown
or disallowed origin, unpinned transformation, stale or unreliable
required snapshot, action mismatch, or unavailable required status
MUST withhold admission. The boundary MUST preserve the distinction
between assertion verification and acceptance under local policy.
Schrock Expires 4 March 2027 [Page 9]
Internet-Draft Action Evidence Boundary August 2026
A field-origin policy SHOULD be discriminating rather than a blanket
prohibition on untrusted content. For example, it can refuse an
untrusted message that selects a payee or destination while accepting
the same origin class for a bounded non-authoritative memo field.
The accepted and refused field classes are relying-party policy, not
universal AEB semantics.
EP-FIELD-ORIGIN-v0.1 and its finance-operations Gap 6 runner are an
informative reference implementation profile [EP-FIELD-ORIGIN]. They
do not become a mandatory AEB format and their same-team results are
not independent implementation evidence.
5.5. Evaluate AEC Evidence Satisfaction
The boundary MUST submit only natively verified, action-matched
evidence to an AEC verifier configured with the relying party's
requirement. The requirement used for the decision MUST come from
relying-party configuration, not from a presenter-controlled AEC
member.
Every required evidence role MUST be filled by an artifact whose
native verifier and adapter are accepted for that role. A workload
identity MUST NOT silently fill a policy-permit or human-
authorization slot. A machine-policy decision MUST NOT silently fill
a named-human slot. A generic operator signature MUST NOT be
interpreted as evidence that a human operated a system or performed a
named approval ceremony.
Only a successful AEC evaluation under these inputs reaches
SATISFIED. UNSATISFIED, malformed, unsupported, or ambiguous results
MUST withhold invocation.
A qualification statement can fill an evaluation-evidence role only
when its native verifier establishes the measured candidate,
evaluation campaign, assignment, policy, freshness, and status. A
qualification result MUST NOT fill an authorization role and MUST NOT
by itself cause SATISFIED, AUTHORIZED, reservation, or invocation.
5.6. Pinned Boundary Requirement and Evaluation Record
The consequence-owning relying party MUST pin the exact adapter
revisions, trust roots, mapping profiles, AEC requirement, and
boundary requirement used for a decision. The presenter MUST NOT
select or weaken those inputs. EP-AEB-REQUIREMENT-v1 is a closed
object whose all_of and any_of members name evidence roles and whose
terms member carries boundary constraints:
Schrock Expires 4 March 2027 [Page 10]
Internet-Draft Action Evidence Boundary August 2026
{
"@version": "EP-AEB-REQUIREMENT-v1",
"all_of": ["human-authorization", "policy-permit"],
"terms": [
{ "type": "distinct-human-quorum",
"role": "human-authorization", "threshold": 2 },
{ "type": "initiator-exclusion",
"roles": ["human-authorization"] },
{ "type": "executor-exclusion",
"roles": ["human-authorization"] },
{ "type": "one-time-consumption" }
]
}
A conforming implementation MUST reject unknown terms. It MUST
require exactly one one-time-consumption term. A distinct-human-
quorum term counts only distinct natural-person subject identifiers
exposed by eligible native verifiers for the named role. initiator-
exclusion and executor-exclusion compare those verified subjects with
the boundary-owned initiator and executor identifiers. Different
encodings of one key or subject MUST NOT count as different humans.
Execution-time evaluation MUST resolve current status through
relying-party-configured status sources. Presenter-supplied current
status is untrusted. Revoked, expired, stale, unavailable,
ambiguous, or unauthenticated required status MUST withhold
authorization. Historical re-performance MUST be labeled historical
and MUST NOT be used as a current execution decision.
The evaluator SHOULD emit a signed, re-derivable record binding the
observed action and CAID, operation and consumption identifiers,
initiator and executor, adapter and mapping revisions, complete
requirement and configuration digests, native artifact digests,
current-status snapshots, per-leg VERIFIED and MATCH results, AEC
SATISFIED, boundary constraints, and the separate AUTHORIZED or
REFUSED verdict. The record is evidence of the evaluator's decision;
it does not itself perform or authorize an effect.
5.7. Make the Local Authorization Decision
The consequence-owning executor MUST make a separate local
authorization decision after SATISFIED. It MUST evaluate the exact
observed action, audience, tenant, organization, policy epoch,
freshness, current credential and authority status, separation of
duties, local risk controls, and any bounded capability state.
Schrock Expires 4 March 2027 [Page 11]
Internet-Draft Action Evidence Boundary August 2026
Credential revocation and per-action authorization evidence answer
different questions. A current non-revocation or status result can
establish that a credential remains acceptable under local policy; it
does not prove that the credential holder authorized this action. A
per-action authorization artifact does not prove that every
credential in its trust path remains current. When policy requires
both, the boundary MUST verify both without substituting one for the
other.
The boundary reaches AUTHORIZED only if local policy permits the
exact action at the decision time. SATISFIED alone MUST NOT trigger
reservation or invocation.
5.8. Atomically Consume or Reserve Before Invocation
After AUTHORIZED and before invocation, the boundary MUST perform the
durable state transition required by the native evidence and local
policy. This can include consuming a one-time authorization,
challenge nonce, or operation key; reserving a bounded capability or
budget; and fencing the operation to one owner across replicas.
The transition MUST be atomic within the relying party's durable
state domain. Its key MUST be derived from verified evidence or the
executor-owned observed action and operation identifier, never from a
presenter-selected decoy. If the store is unavailable, non-atomic,
stale, or reports an ambiguous result, the boundary MUST refuse
before invocation.
AEB does not claim atomicity between a local store and an unrelated
remote provider. It requires the local consume or reserve transition
to occur first so that any uncertainty after dispatch cannot make the
same authority available for an uncontrolled second effect.
5.9. Invoke the Frozen Action
Before any call, message, or byte can reach an effecting component,
the boundary MUST durably enter DISPATCH_PENDING for the frozen
observed action that reached AUTHORIZED and CONSUMED or RESERVED.
The record MUST bind the action digest, operation identifier,
provider environment, audience, reservation or consumption record,
and adapter. Failure or ambiguity while writing this record MUST
withhold dispatch.
The boundary MUST invoke only from that durable state. It MUST use a
stable, action-bound, unique operation identifier or idempotency key
where the provider supports one. After dispatch begins, it MUST
durably record INVOKED or a terminal outcome before reporting success
to the requester.
Schrock Expires 4 March 2027 [Page 12]
Internet-Draft Action Evidence Boundary August 2026
The adapter MUST receive only the authority and evidence necessary
for the downstream interface. It MUST NOT accept mutable
intermediary or caller context that changes a material field after
the boundary's authorization decision.
5.10. Classify the Effect Outcome
After invocation begins, the boundary MUST classify the result as
EXECUTED, FAILED, or INDETERMINATE. On restart, a DISPATCH_PENDING
operation without an authoritative terminal record MUST be promoted
to INDETERMINATE before any retry or release, because the process
cannot establish that dispatch did not begin.
* EXECUTED requires an authoritative response or accepted native
execution evidence matched to the exact action, operation
identifier, provider environment, and audience.
* FAILED requires authoritative evidence that the invoked operation
did not cause the protected effect. A local parse error,
exception, timeout, connection loss, process crash, or missing
response is not by itself such evidence.
* INDETERMINATE is REQUIRED whenever invocation may have reached the
effecting system but the available authoritative evidence does not
establish EXECUTED or FAILED.
For EXECUTED, the boundary MUST commit any reserved spend and
preserve the terminal evidence. For FAILED, it MUST preserve the
failure evidence and follow the native reservation policy. For
INDETERMINATE, it MUST preserve or consume the reservation, refuse
reuse of the authorization and operation identifier, and prohibit a
blind replay.
5.11. Perform Authenticated Reconciliation
An INDETERMINATE operation, including one recovered from a stranded
DISPATCH_PENDING record, MUST remain closed until reconciliation
authenticates the provider or system of record and matches the result
to the original action, operation identifier, provider environment,
audience, target resource, and every application-specific material
field.
Reconciliation MAY move INDETERMINATE to EXECUTED when authoritative
evidence establishes that the exact effect occurred. It MAY move
INDETERMINATE to FAILED when authoritative evidence establishes that
it did not occur. Missing, stale, conflicting, unauthenticated, or
action-mismatched observations MUST leave the operation
INDETERMINATE.
Schrock Expires 4 March 2027 [Page 13]
Internet-Draft Action Evidence Boundary August 2026
Reconciliation MUST NOT resurrect the original authorization or
silently release its one-time replay unit. If policy permits a later
attempt after an authoritative FAILED result, that attempt MUST use a
new action instance and complete the lifecycle required by local
policy. An implementation MUST NOT invoke again merely because a
timeout elapsed or because the caller retried.
6. Declaration and Challenge Semantics
A deployment MAY publish a static declaration describing protected
actions, material fields, evidence requirements, challenge methods,
and effect-boundary placement. Such a declaration is discovery
metadata. It MUST NOT override the relying party's live, local
enforcement configuration. An unsupported declaration version MUST
be ignored as discovery input; it cannot weaken or replace live
enforcement. An action that the live boundary configuration cannot
classify or process under a supported version MUST fail closed.
When required evidence is absent or unacceptable, a boundary MAY use
its application protocol to return a dynamic challenge. A challenge
MUST identify the boundary-computed action, the missing evidence
roles, the policy context, an intended audience, a short expiry, and
a single-use unpredictable nonce or equivalent replay unit. The
nonce MUST NOT be consumed merely because untrusted bytes parse. It
MUST be consumed atomically only after the selected native verifier
establishes the integrity and challenge binding of an in-window
presentation, and before that presentation can reach SATISFIED or
authorize an effect. A presentation that is malformed,
unauthenticated, expired, or not bound to the challenge MUST be
refused without burning the nonce. A natively verified, challenge-
bound presentation consumes the nonce whether or not the remaining
evidence satisfies the requirement. Follow-up challenges MUST remain
bound to the original boundary-computed action and MUST NOT derive
that action from presenter input.
A declaration or challenge authorizes nothing, reserves nothing, and
promises no execution. A satisfied challenge still proceeds through
native verification, MATCH, SATISFIED, local AUTHORIZED, and atomic
consumption or reservation. This document intentionally defines no
new manifest object, challenge object, well-known URI, HTTP status
code, or media type.
7. Native Evidence and Transport Boundaries
Schrock Expires 4 March 2027 [Page 14]
Internet-Draft Action Evidence Boundary August 2026
7.1. WIMSE and HTTP Message Signatures
WIMSE workload credentials and the WIMSE HTTP Message Signatures
profile [WIMSE-HTTP] can provide end-to-end workload authentication
and message integrity for the request components covered by the
validated signature, including a body protected by a validated
content digest. HTTP Message Signatures [RFC9421] provide the
underlying component-signing mechanism.
AEB consumes those results; it does not redefine them. A validated
WIMSE request can establish which workload possessed the protected
key and that covered message components were not modified
undetectably. It does not by itself establish CAID MATCH, AEC
SATISFIED, named-human authorization, local AUTHORIZED, one-time
consumption, or execution.
The AI Agent Authentication and Authorization framework [KLRC-AUTH]
and the WIMSE authorization-evidence profile [MUNOZ-WIMSE-EVIDENCE]
describe adjacent runtime authorization and signed-evidence
compositions. AEB treats their selected credentials, tokens, and
evidence records as native inputs. It does not replace their
issuance, verification, or authorization semantics.
PEDIGREE [PEDIGREE] describes native identity and delegation-chain
evidence. The AEB result records whether the relying party's stated
delegation requirement was satisfied by the mapped evidence. It does
not reinterpret, re-derive, or override the delegation protocol's
native decision. In particular, a PEDIGREE completion block is post-
effect evidence and MUST NOT fill a pre-action authorization role.
Headers, routing metadata, forwarded identity, trace context, or
other values that an intermediary can add, remove, or mutate outside
the validated end-to-end integrity coverage MUST NOT be load-bearing
authorization evidence. They MAY be used for routing or diagnostics.
If such a value affects the protected consequence, the boundary MUST
derive it independently or require it to be covered by accepted
native integrity and the observed action's material binding.
7.2. Attested Per-Action Tokens and Permit Records
Attested per-action tokens, including artifacts described by a
deployment as OASNT-like, remain native evidence formats. AEB does
not assign that descriptive label a token type, claim set, registry
entry, or trust meaning. The selected native verifier determines
what the token proves and exposes its integrity-protected action
commitment, issuer, audience, validity, freshness, status, and
bounded result to the AEB adapter.
Schrock Expires 4 March 2027 [Page 15]
Internet-Draft Action Evidence Boundary August 2026
SCITT Permit records defined by [MUNOZ-PERMIT] likewise remain native
pre-execution decision evidence. AEB does not reserialize a Permit
or convert it into an AEB receipt. It verifies the selected Permit
revision through its native adapter, maps its protected material
action only through a pinned CAID profile, and assigns it only to
evidence roles permitted by the relying party's AEC requirement.
A native format's valid signature proves only the statement and
signer semantics that format defines. It does not, without an
additional accepted profile and evidence, prove that a natural person
operated the workload, understood the action, held authority, or
performed a particular approval ceremony.
8. Native Compilation Contract
An AEB adapter compiles the result of a native verifier into the
inputs needed by the AEB processing model. The native artifact,
verifier, trust model, and result remain authoritative for their own
semantics. Compilation MUST NOT convert a native result into an AEB
credential or permit, and an AEB result MUST NOT overwrite a native
result.
The compilation target is the ordered AEB decision and lifecycle
vocabulary: native verification, exact-action matching, evidence
satisfaction, local authorization, atomic reservation or consumption,
provider entry, outcome classification, and authenticated
reconciliation. A successful compile establishes only that the
native result can be evaluated at those interfaces. It does not
establish that the action is authorized, executed, safe, lawful, or
true.
8.1. Pinned Inputs
Before compilation, the relying party MUST pin:
* the native protocol, document revision, media type, schema
version, and verifier revision;
* the adapter identifier, adapter revision, verifier implementation
identifier, and implementation digest;
* the native trust anchors, issuer and audience policy, clock,
freshness rules, and required status sources;
* the exact source descriptor, target CAID action type, mapping
profile identifier, mapping revision, and mapping digest;
* the accepted evidence role or roles;
Schrock Expires 4 March 2027 [Page 16]
Internet-Draft Action Evidence Boundary August 2026
* the native replay-unit derivation profile and replay scope; and
* every native field whose omission or change can affect the
protected consequence, evidence role, freshness, replay unit, or
local policy.
Presented data MAY select among already pinned native variants only
where the native protocol defines that selection and the relying
party enables it. Presented data MUST NOT add or change a trust
root, verifier, mapping, evidence role, material-field rule, or
replay scope.
A verifier implementation identifier and digest are relying-party-
selected configuration metadata. They do not prove that a measured
runtime loaded or executed those bytes. A compile result MUST keep
runtime measurement unestablished unless a separate accepted native
attestation proves it.
8.2. Deterministic Operations
An adapter exposes two logically separate operations. The first,
verifyNative, verifies the artifact under the pinned native rules and
returns the integrity-protected native result. The second,
mapAction, maps only a VERIFIED native result to the relying party's
expected action under the pinned mapping profile.
Both operations MUST be deterministic for the supplied bytes and
pins. They MUST NOT perform a network request, consult ambient
credentials or trust stores, read mutable global state, or accept a
caller-supplied verification verdict. Required current status and
time MUST be explicit relying-party inputs.
The boundary MUST supply detached, recursively immutable copies of
the native artifact, expected action, trust inputs, status inputs,
adapter configuration, and mapping profile. An adapter MUST NOT
change a pinned input between native verification and action mapping.
8.3. Closed Compile Result
For each native artifact, the compiler MUST return a closed result
that contains:
* the native protocol, exact revision, artifact digest, and native
verification result;
* the adapter identifier, revision, and configuration digest, plus
the pinned verifier implementation identifier, revision, and
digest;
Schrock Expires 4 March 2027 [Page 17]
Internet-Draft Action Evidence Boundary August 2026
* the mapping profile identifier, revision, and digest, plus mapper
and resolver identifiers and the resolver implementation digest;
* the source schema or media type and target action type;
* the exact relying-party-supplied expected material action value,
digest, and input provenance;
* the CAID and normalized-action digest, or a named reason they were
not produced;
* the accepted evidence role and subject, plus the status input and
derived freshness result under pinned adapter rules;
* the stable native replay unit and replay scope;
* whether verifier runtime measurement is established;
* the semantic-loss report defined below; and
* every compiler state that remains unsupported or indeterminate.
The compile result is typed verifier output. It is not a bearer
token, permit, receipt, or proof of execution. A deployment MAY
serialize it for diagnostics or evidence transport, but that
serialization MUST NOT become reusable authority.
A native profile MAY expose actor, acting-for principal, target,
declared purpose, audience, constraints, validity, or native
nonclaims only when its native verifier and pinned mapping establish
those values. The generic compiler MUST NOT infer them from a
subject identifier, policy decision, action label, natural-language
field, or trace metadata merely to fill a common shape.
A caller-supplied local-policy decision MAY be reported as an
explicit input, but it MUST NOT establish local authorization.
Authorization, reservation or consumption, provider entry, outcome,
and reconciliation remain unestablished until the component that owns
each transition evaluates and records it.
8.4. Semantic-Loss Report
The adapter MUST enumerate every field exposed by the native verifier
that the selected mapping does not carry into the target action or
accepted evidence role. Each omission MUST be classified as
material, non-material, or unknown under relying-party-pinned rules,
with a stable field path and declared basis.
Schrock Expires 4 March 2027 [Page 18]
Internet-Draft Action Evidence Boundary August 2026
An omitted material or unknown field makes exact-action matching
INDETERMINATE. That leg MUST NOT report equivalence, MATCH,
SATISFIED, or AUTHORIZED. Renaming, moving, defaulting, unit-
converting, rounding, truncating, or combining a material field is a
transformation and requires a pinned deterministic rule. Natural-
language similarity, an agent assertion, or a shared trace identifier
is not such a rule.
The compiler MAY retain a native mapper's raw relation, CAID, and
normalized-action digest for diagnostics, but MUST label them as raw
native output. They MUST NOT appear as the compiler-effective
relation after material or unknown loss. The effective CAID and
normalized- action digest are absent in that case.
If two compiled legs produce one CAID but different normalized-
action digests, the boundary MUST refuse the join. CAID remains a
typed content identifier. It is not an authorization claim or a
general declaration that two source formats have identical semantics.
8.5. Stable Native Replay Unit
Every accepted authorization-bearing native result MUST expose a
stable native replay unit derived from the verified native authority.
The replay unit MUST NOT include an AEB wrapper digest, AEB operation
identifier, consumption nonce, caller retry identifier, or other
value whose change would make the same native authority spendable
again.
The evaluator MUST probe the adapter with a second deterministic
wrapper reference. If the replay unit changes while the verified
native authority does not, the result is INDETERMINATE. If two
distinct verified native artifacts from one adapter collapse onto one
replay unit without the native profile defining that equivalence, the
result is INDETERMINATE. A replay-unit value does not prove that
reservation or consumption occurred.
8.6. Path and Provider Ownership
A deployment MUST state whether the AEB boundary controls the
credential or other capability that reaches the effecting provider,
which provider-entry paths it mediates, and every direct,
administrator, break-glass, alternate-protocol, queued, or system-of-
record path that bypasses it. An observe-only adapter or an adapter
placed beside a write path MUST NOT be described as consequence
admission or complete mediation.
Schrock Expires 4 March 2027 [Page 19]
Internet-Draft Action Evidence Boundary August 2026
The compile result MAY record provider-attempt and reconciliation
bindings only after the corresponding AEB transitions occur. A
policy allow, access token, message signature, transparency receipt,
action record, audit record, or native permit MUST NOT be relabeled
as proof that provider entry, commitment, or an external effect
occurred.
8.7. Compilation Conformance
A native compilation profile MUST publish exact source locks, at
least one positive vector containing the original native bytes, and a
condition-removed control for every negative vector. Reports MUST
keep native verification, mapping, AEC, local policy, reservation,
provider outcome, and reconciliation results separate.
The profile MUST include hostile vectors for material-field omission
and substitution, mapping-pin change, stale or unavailable status,
wrapper replay, alternate-path bypass, refusal-time consumption,
concurrent admission, timeout after provider entry, blind retry, and
reconciliation binding mismatch. It MUST state every native semantic
that could not be compiled without invention.
A generic AEB compiler conformance claim requires at least two
materially unrelated native profiles to reach the same AEB lifecycle
without changing their native wire formats or result semantics. A
same-team runner is reference evidence, not an independent
implementation. Matching a finite vector set does not establish
complete mediation, production deployment, or provider truth.
9. Conformance and Deployment Claims
An implementation conforms to AEB only if every protected invocation
follows the ordered processing model in Section 5 and fails closed on
every missing or ambiguous required transition. A deployment MUST
document:
* the protected action types and the effect paths actually mediated;
* the trusted configuration and durable-state boundaries;
* the native verifier revisions and relying-party pins;
* the method used to derive material action fields at the boundary;
* the consumption, reservation, and cross-replica fencing mechanism;
* the authoritative sources and matching rules used for
reconciliation; and
Schrock Expires 4 March 2027 [Page 20]
Internet-Draft Action Evidence Boundary August 2026
* all direct, break-glass, administrator, alternate-protocol, and
system-of-record paths that bypass the AEB implementation.
An implementation placed beside a write path is not complete
mediation. A deployment MUST NOT claim complete mediation unless the
protected system rejects all material alternate paths or subjects
them to an equivalent boundary. Observe-only operation MAY be useful
during deployment, but it MUST NOT be described as enforcement.
10. Security Considerations
*Cross-binding.* An attacker can splice a valid permit, approval,
credential, or receipt for action A into a request for action B.
Native verification before mapping, executor-owned action
construction, exact CAID matching, and a relying-party-pinned AEC
requirement are all required defenses. Omitting any one of them
reopens the attack.
*Mutable context.* Intermediary-added headers and agent annotations
are convenient but are not trustworthy merely because they arrived on
an authenticated hop. Every load-bearing field needs accepted end-
to-end integrity coverage or independent derivation at the effect
boundary.
*Time of check and time of use.* The action passed to the executor
must be the frozen action that was verified, matched, satisfied,
authorized, and consumed or reserved. Mutable aliases, provider
defaults, exchange rates, destinations, branch heads, and policy
epochs can change a consequence after approval; profiles must bind or
revalidate them as material fields.
*Replay and distributed state.* Process-local caches are insufficient
where replicas can invoke the same effect. Replay, consumption,
reservation, and operation ownership state must be durable, atomic,
and shared across every boundary instance that can reach the
protected executor.
*Freshness and revocation.* Expiration, nonce checks, credential
status, authority status, and policy epoch are separate checks. A
fresh message does not make a revoked credential valid, and a current
credential does not make old per-action evidence fresh.
*Indeterminate effects.* Retrying after a timeout can duplicate a
payment, mutation, disclosure, or physical action. An invocation
that might have reached the provider consumes the operation's retry
right until authenticated reconciliation resolves the exact outcome.
Caller assurances and unauthenticated webhooks do not resolve it.
Schrock Expires 4 March 2027 [Page 21]
Internet-Draft Action Evidence Boundary August 2026
*Signature overclaiming.* A cryptographic signature can establish
control of a key and integrity of covered content under a selected
verification profile. It does not inherently identify a human, prove
human operation, prove comprehension, establish legal authority, or
prove execution.
*Boundary bypass.* A correct AEB implementation does not protect
direct database credentials, alternate APIs, shell access,
administrator consoles, side channels, or actuator paths that bypass
it. Deployment topology and credential placement are security
properties, not implementation details.
11. Privacy Considerations
Action objects and evidence can expose identities, destinations,
resources, policy choices, commercial relationships, and sensitive
operational timing. Deployments SHOULD minimize the evidence passed
to the executor and retained in portable records, use opaque high-
entropy references where appropriate, and avoid treating a plain
digest of low-entropy personal data as anonymization.
Reconciliation queries can disclose that an operation is disputed or
uncertain. They SHOULD be authenticated, authorized, rate-limited,
and limited to the exact operation. AEB does not require public
disclosure of native evidence or local policy.
12. Relationship to EMILIA and Adjacent Work
CAID [CAID] owns typed material-action identity and exact, relying-
party-pinned cross-format mapping. AEB invokes CAID after native
verification and does not extend CAID with trust semantics.
AEC [AEC] owns heterogeneous evidence composition and the SATISFIED
or UNSATISFIED result under a relying-party requirement. AEB invokes
AEC and then makes the separate local authorization and effect-
lifecycle decisions. The earlier Action Evidence Graph series [AEG]
is replaced by AEC; an implementation following an older citation
MUST NOT treat the superseded series as a second composition
contract.
Authorization Receipts [RECEIPTS] define one native action-bound
organizational approval artifact and its receipt-specific consumption
semantics. AEB does not make that format mandatory and does not
generalize every native artifact into an EMILIA receipt.
Static declarations and dynamic evidence challenges remain distinct
protocol surfaces. A manifest can advertise discovery metadata,
while an Authorization Evidence Challenge can carry the live, action-
Schrock Expires 4 March 2027 [Page 22]
Internet-Draft Action Evidence Boundary August 2026
bound refusal and acquisition instructions. AEB owns the executor
lifecycle in which those inputs are evaluated; it does not absorb or
replace their wire formats.
Qualification, revocation, remedy, and action-to-outcome continuity
artifacts are optional native inputs or downstream records. They
retain their own semantics. AEB composes them only through pinned
verification, exact-action binding, local policy, durable custody,
and authenticated reconciliation.
A refusal MAY be represented by an action-bound signed refusal
statement. The refusal artifact records what the boundary refused
and why; it MUST NOT be interpreted as proof that every bypass path
was mediated, that delivery to a requester occurred, or that a later
action was refused.
13. IANA Considerations
This document has no IANA actions. In particular, it creates no
registry for native evidence types, lifecycle labels, verifier
adapters, action mappings, or policy identifiers.
14. Changes since -04
This revision adds a deterministic, loss-aware Native Compilation
Contract for AEB adapters. It requires exact native, implementation,
and mapping pins; a closed compile result; a complete semantic-loss
report; stable native replay units; provider-path disclosure; and
hostile conformance across at least two unrelated native profiles.
Native formats and results retain their own ownership. The revision
creates no new credential, permit, receipt, registry, or assertion
that compilation proves authorization or execution. The ordered AEB
lifecycle and provider-outcome boundaries are unchanged.
15. Implementation Status
The Apache-2.0 reference implementation provides relying-party-pinned
adapter and mapping registries, multi-leg CAID joins, the boundary
terms defined above, current-status verification, signed
configuration-bound evaluation records, durable ownership-fenced one-
time consumption, execution reservation and reconciliation, and
signed refusal statements. It also exposes a closed native-compiler
report over the adapter contract, an AuthZEN-derived local PEP-
observation profile, a source-pinned OAuth Transaction Authorization
Challenge profile [OAUTH-TXN-CHALLENGE], a strict request-only
profile over WPT-02 [WIMSE-WPT] and Transaction Tokens -11
[OAUTH-TXN-TOKENS], and a WIMSE R10 compatibility matrix. All three
paths pass locally. The AuthZEN-derived path verifies an EMILIA-
Schrock Expires 4 March 2027 [Page 23]
Internet-Draft Action Evidence Boundary August 2026
signed local PEP observation, not an artifact defined or signed by
AuthZEN. It therefore does not count toward the two-external-native-
profile gate. OAuth transaction challenge and WPT plus Transaction
Tokens are the two direct external-native candidates. Their mappings
have not been reviewed by the native protocol owners, the published
profiles still need an audited match against every required hostile
vector and paired control, and their OAuth adjacency requires an
explicit protocol-diversity judgment before the generic gate can
close. The result is not an independent implementation or an
adoption claim. The informative EP-FIELD-ORIGIN-v0.1 profile is
evaluated before admission in the reference Gate. Its Gap 6
implementation profile has 14 deterministic cases, including
disallowed field origins, unknown origin, profile substitution, an
unpinned transformation, and the positive case in which untrusted
content supplies only a bounded memo field. Conformance vectors and
adversarial tests cover selected reference paths; the full
conformance set above remains future conformance work and is not
established by this revision. These same-team artifacts are not an
independent implementation and do not prove that a deployment
mediates every effect path.
16. References
16.1. Normative References
[AEC] Schrock, I., "Authorization Evidence Chains: Composing
Heterogeneous Agent-Action Evidence (EP-AEC)", Work in
Progress, Internet-Draft, draft-schrock-ep-authorization-
evidence-chain-05, July 2026,
.
[BCP14] Internet Engineering Task Force, "Key Words for Use in
RFCs to Indicate Requirement Levels", BCP 14, 2017,
.
[CAID] Schrock, I., "The Canonical Action Identifier (CAID)",
Work in Progress, Internet-Draft, draft-schrock-canonical-
action-identifier-02, 9 August 2026,
.
[RFC2119] Bradner, S., "Key words for use in RFCs to Indicate
Requirement Levels", BCP 14, RFC 2119,
DOI 10.17487/RFC2119, March 1997,
.
Schrock Expires 4 March 2027 [Page 24]
Internet-Draft Action Evidence Boundary August 2026
[RFC8174] Leiba, B., "Ambiguity of Uppercase vs Lowercase in RFC
2119 Key Words", BCP 14, RFC 8174, DOI 10.17487/RFC8174,
May 2017, .
16.2. Informative References
[AEG] Schrock, I., "Action Evidence Graph for Consequential
Agent Actions", Work in Progress, Internet-Draft, draft-
schrock-ep-action-evidence-graph-00, July 2026,
.
[EP-FIELD-ORIGIN]
EMILIA Protocol, "EP-FIELD-ORIGIN-v0.1 Informative
Implementation Profile and Gap 6 Runner", 15 August 2026,
.
[KLRC-AUTH]
Kasselman, P., Lombardo, J., Rosomakho, Y., Campbell, B.,
Steele, N., and A. Parecki, "AI Agent Authentication and
Authorization", Work in Progress, Internet-Draft, draft-
klrc-aiagent-auth-03, July 2026,
.
[MUNOZ-PERMIT]
Munoz, C., "A SCITT Profile for Pre-Execution AI Action
Authorization Records", Work in Progress, Internet-Draft,
draft-munoz-scitt-permit-profile-01, July 2026,
.
[MUNOZ-WIMSE-EVIDENCE]
Munoz, C., "Signed Authorization-Evidence Records for
WIMSE-Authorized AI Agent Actions", Work in Progress,
Internet-Draft, draft-munoz-wimse-authorization-evidence-
01, July 2026, .
[OAUTH-TXN-CHALLENGE]
Rosomakho, Y., Campbell, B., McGuinness, K., and P.
Kasselman, "OAuth Transaction Authorization Challenge",
Work in Progress, Internet-Draft, draft-rosomakho-oauth-
txn-challenge-00, 25 June 2026,
.
Schrock Expires 4 March 2027 [Page 25]
Internet-Draft Action Evidence Boundary August 2026
[OAUTH-TXN-TOKENS]
Tulshibagwale, A., Fletcher, G., and P. Kasselman,
"Transaction Tokens", Work in Progress, Internet-Draft,
draft-ietf-oauth-transaction-tokens-11, 30 July 2026,
.
[PEDIGREE] Rampalli, K., "PEDIGREE: Verifiable Delegation Identity
for Agentic AI Systems", Work in Progress, Internet-Draft,
draft-rampalli-pedigree-00, April 2026,
.
[RECEIPTS] Schrock, I., "Authorization Receipts for High-Risk Agent
Actions", Work in Progress, Internet-Draft, draft-schrock-
ep-authorization-receipts-12, 16 August 2026,
.
[RFC9421] Backman, A., Ed., Richer, J., Ed., and M. Sporny, "HTTP
Message Signatures", RFC 9421, DOI 10.17487/RFC9421,
February 2024, .
[WIMSE-HTTP]
Salowey, J. and Y. Sheffer, "WIMSE Workload-to-Workload
Authentication with HTTP Signatures", Work in Progress,
Internet-Draft, draft-ietf-wimse-http-signature-06, 4
August 2026, .
[WIMSE-WPT]
Campbell, B. and A. Schwenkschuster, "WIMSE Workload Proof
Token", Work in Progress, Internet-Draft, draft-ietf-
wimse-wpt-02, 27 August 2026,
.
Appendix A. Acknowledgments
External review sharpened the boundaries between workload and message
integrity, per-action authorization evidence, credential status,
human operation, and executor-owned effect control. Those
distinctions are load-bearing in this document. Acknowledgment does
not imply endorsement.
Author's Address
Schrock Expires 4 March 2027 [Page 26]
Internet-Draft Action Evidence Boundary August 2026
Iman Schrock
EMILIA Protocol, Inc.
United States of America
Email: team@emiliaprotocol.ai
Schrock Expires 4 March 2027 [Page 27]