audit-core/intakes/intakes.md
tegwick 3c2cdcdf79 AUDIT-WP-0010 T01/T03/T04 — admit tenant-engine, and the envelope does not match
Registration: attributive, with the declared completeness_trade recorded on the
receiver side rather than only in the emitter, per §9.6's requirement that the
trade travel with the trail. tenants ["*"] is justified rather than inherited —
tenant-engine's events carry the affected tenant, the set is every tenant
including ones created later, and an explicit list would fail closed at exactly
the moment a tenant is provisioned, dead-lettering the creation evidence of the
tenant whose creation it is. source stays pinned exactly. Ingress ANDs namespace
and pod label; a weaker evidence class is not a reason for a wider network rule.
All inert until the token exists.

Then the finding T04 existed to find: tenant-engine cannot deliver a single
event today. envelope_for sends five required fields under other names —
event_id, action, resource, observed_at, details — and omits correlation_id
entirely, so normalize() raises invalid_event. Verified by running the real
envelope through the real function, not by reading.

Worse than an ordinary integration bug. The drain treats 400 as terminal, so the
outbox row is marked handled while audit-core holds only a dead letter, which is
not chained and is not custody. Lost on both sides, and since the drain is
non-blocking and attributive, nothing fails loudly — a silent total loss of the
stream presenting as a working integration.

Taking the correction the intake invited rather than accepting a lossy record.
normalize() is NOT relaxed to accept the alternate spellings: a receiver that
guesses which sender key means which stored field has made the mapping its own,
and the record stops being the sender's assertion. correlation_id cannot be
synthesized at all — an invented one ties an event to an operation audit-core
never observed.

Root cause is ours. The accepted envelope was published nowhere a sender could
read it; audit-backend-contract.md describes the stored record, and a sender
reading it would reasonably infer exactly the names tenant-engine used.
schema_version audit-core.event.v1alpha1 selects nothing here and gave a false
impression of a negotiated contract. Published docs/event-envelope.md as the
wire contract, including the point that a 400 means the event is not in the
archive and must be treated as a defect to fix rather than a delivery outcome.

T05 moved to wait: nothing to prove end to end until an event can be accepted.

Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01Nb7Q6ZmXppNDkTWytfYqfv

Assistant: claude-code
Assistant-Model: opus
Assistant-Process: 2069992@bnt-lap001
Assistant-Session: 167dd7f8-2a25-4be1-aa46-3b6f1a5f94c6
2026-09-10 16:34:45 +02:00

179 lines
9.8 KiB
Markdown

# Intake records
## AUDIT-IN-0003 — Register informed-decision as a load-bearing sender; commitment-only payload doctrine
```yaml
id: AUDIT-IN-0003
kind: intake
title: 'Register informed-decision as a load-bearing sender, and answer GH-DEC-2026-014
limit 3'
status: closed
origin: cross-repo
origin_ref: INFD-WP-0001-T08 / GH-DEC-2026-012 / GH-DEC-2026-014
priority: high
owner: audit-core
requested_by: informed-decision
description: >
informed-decision is the browser-facing approver surface approval-engine
deliberately does not contain, ruled PEP-shaped by GH-DEC-2026-012. Limit 3
of that ruling requires its evidence copy to reach audit-core independently
of the emitter, because the actor being audited and the evidence source are
the same component.
Requested: (1) sender registration — source informed-decision exact, tenants
[tenant:platform], write true, read false, evidence_kind load-bearing,
secret_policy redact; (2) whether reconciliation per class as primary plus
heartbeat for the low-volume classes is the right cadence form for a
mixed-volume source; (3) whether commitment-only content is one event class
or two, and whether it belongs in the same class as other evidence.
GH-DEC-2026-014 attached a condition addressed to audit-core: non-production
of committed content must be detectable as a FINDING rather than present as
an absence, so the record must carry an assertion that committed content
exists and where custody sits. Gate House asked audit-core to say plainly
whether the record shape can express that, rather than have a rule written
that the storage cannot meet.
created: '2026-09-09'
updated: '2026-09-10'
outcome: registered-with-a-stated-bound
closed: '2026-09-10'
resolution: 'Registration accepted on every proposed field; the proposal was
correct and the substance is in the bounds. Prepared and inert pending token,
protected-registry entry and operator apply —
docs/informed-decision-source-registration.md, deploy/senders-scope.{json,yaml},
audit-core-informed-decision-ingress. (1) GH-DEC-2026-014 limit 3: the fabric
CAN carry the declaration — data is stored verbatim into details.data and
hash-chained, so content_exists and custody need no schema change and become
as tamper-evident as the commitment they accompany. It CANNOT detect
non-production: audit-core performs no retrieval and its egress permits
Postgres and DNS only. Detection happens at retrieval by the reviewer, and the
stored declaration is what makes non-production attributable rather than a
blank. Residual: a custodian that never held the content can emit a false
content_exists; audit-core validates the declaration shape, never its truth —
same class as omission at source, not closed by chain, attestation or T04/T06.
(2) Cadence: reconciliation plus heartbeat is right, with both scoped PER
CLASS rather than per source — a per-source heartbeat is satisfied by the
high-volume presentation stream and says nothing about a quiet month of
dispositions. Bound: a compromised emitter suppresses the event and its own
count together, so neither control covers the limit-3 residual. Depends on
T04/T06; declare now, do not describe as operating. (3) One source, distinct
type values per class, following approval-engine four-class shape; a second
sender would split one residual into two smaller-looking ones. (4) Tenant
provenance is recorded in the registration document, not the envelope:
audit-core does not resolve the tenant claim, it checks a value the credential
is permitted to write, and restating an unobserved route in an event is the
same error as claiming an event occurred. (5) Stated for all documents:
commitment-only satisfies non-alteration and never reconstructability, and no
audit-core document or conformance claim may describe it otherwise.'
recorded_in: docs/informed-decision-source-registration.md
work: AUDIT-WP-0009-T11
state_hub_intake_id: "01a08b76-05b9-7a53-8359-9cda50755f28"
```
## AUDIT-IN-0002 — Register tenant-engine as an attributive audit-core sender
```yaml
id: AUDIT-IN-0002
kind: intake
title: 'Register tenant-engine as an attributive audit-core sender'
status: open
origin: cross-repo
origin_ref: TEN-WP-0011-T04
priority: high
owner: audit-core
requested_by: tenant-engine
description: >
tenant-engine now emits mutation evidence through a local outbox
(audit-core.event.v1alpha1, source=tenant-engine, POST /v1/events).
The class is attributive and drain is non-blocking
(tenant-engine/docs/evidence-emission.md). Production cannot land
events until audit-core admits this sender: sender identity with
source tenant-engine, a projected token (no secret in Git; warden
route for custody), and NetworkPolicy if the current allow-list is
still user-engine only.
Envelope: schema_version audit-core.event.v1alpha1; tenant is the
affected tenant_id; action is the domain event type; resource
tenant:<id>. Duplicate event ids should 200. Credentials must not
travel via State Hub messages.
Requested: sender registration + token lane, or a correction if the
envelope needs a field this engine is not sending.
created: '2026-08-29'
updated: '2026-09-10'
outcome: registered-with-a-blocking-correction
resolution: 'Registered attributive with the declared completeness_trade
recorded receiver-side, tenants ["*"] justified per sender, source pinned
exact, ingress added — all inert pending the token
(docs/tenant-engine-source-registration.md, AUDIT-WP-0010 T01/T03/T04).
Taking the correction the intake invited: the envelope does not match.
envelope_for sends five required fields under other names (event_id, action,
resource, observed_at, details) and omits correlation_id entirely, so
normalize() raises invalid_event and every event would 400 and dead-letter.
Because the drain treats 400 as terminal, the outbox row is marked handled
while audit-core holds only a dead letter — lost on both sides, silently,
presenting as a working integration. normalize() is not being relaxed to
accept the alternate spellings: guessing which sender key means which stored
field would make the mapping audit-core''s rather than the sender''s, and
correlation_id cannot be synthesized at all. Root cause is audit-core''s —
the wire envelope was documented nowhere a sender could read it, and
schema_version audit-core.event.v1alpha1 selects nothing here. Contract now
published at docs/event-envelope.md. Stays OPEN until tenant-engine corrects
the emitter and T05 records live evidence.'
state_hub_intake_id: "01a04d8f-b1c1-746a-8007-15221ebf0a48"
```
## AUDIT-IN-0001 — Proposed: audit-core takes the approval evidence half (security layer model v0.3 §9.4)
```yaml
id: AUDIT-IN-0001
kind: intake
title: 'Proposed: audit-core takes the approval evidence half (security layer model
v0.3 §9.4)'
status: closed
origin: cross-repo
origin_ref: net-kingdom security-layer-model_v0.3 §9.4
priority: medium
owner: audit-core
requested_by: gate-house
description: 'gate-house proposes that audit-core own the tamper-evident record of
approvals: issuance, use, supersession, and revocation emitted as audit events.
Rationale: principle 6 (signed or hash-chained manifests to prove a record set was
not changed, omitted, or truncated) is exactly what authenticated approval entries
need forensically, and audit-core independence is the property Canon core rule 13
wants — audit evidence protected from the actor being audited. What is NOT proposed:
the operative approval state. approval-engine owns the durable object, atomic supersession,
single consumption, and revocation, because those need mutable in-path current-state
semantics and audit-core operational custody is append-only Postgres by design;
coupling decision-time approval reads to the audit fabric would also make an audit
outage an authorization outage. Note audit-core INTENT lists policy decision making
as out of scope — this proposal respects that: approval evidence is a record of
what happened, never the authoritative answer to whether an approval is still valid.
Requested: assent, revision, or rejection. If audit-core would rather not carry
approval events as a distinct source, say so and gate-house will record the evidence
half as unowned rather than assume it.'
created: '2026-08-28T20:35:09.148892Z'
updated: '2026-08-28T21:10:00Z'
outcome: assent-with-conditions
closed: '2026-08-28T21:10:00Z'
resolution: 'Assent. The split is right: approval-engine owns the operative state,
audit-core owns the tamper-evident record of issuance, use, supersession, and
revocation as a distinct source. Two corrections to the rationale and one
condition. (1) INTENT principle 6 overstates the delivered guarantee;
docs/integrity.md is authoritative — an in-database chain does not withstand a
database owner without the external chain-head attestation, and even then it is
not WORM. Approval events get exactly the guarantee every other source gets,
no more; anything stronger is an engine gap to declare under §5.3. (2) The chain
proves alteration and truncation, not omission at source. A suppressed
revocation leaves the chain intact and verify reports intact; completeness at
the boundary is the emitter''s property, not the archive''s. CONDITION:
approval-engine must guarantee emission atomicity (transactional outbox or
equivalent) so an approval cannot change state without the event being durably
queued in the same transaction — a requirement on approval-engine, not a task
audit-core can discharge for it. Boundary stated: no approval-validity query
will ever be exposed; a verdict surface would be deciding early under §6.1.
Also raised: audit-core declared no layer, contrary to §11 — now declared Engine
layer, explicitly not a decision point.'
recorded_in: history/2026-08-28-approval-evidence-assent.md
state_hub_intake_id: "01a04d8f-be67-75ed-a221-d50f99dbb78e"
```