tenant-engine/workplans/TEN-WP-0012-external-conformance-waits.md
tegwick 8fbdff2b97 Classify open workplans with flavor (CUST-WP-0072).
Set flavor on open workplans from origin/prose/status. Copy existing
depends_on aliases only. Do not promote residuals.

Assistant: grok
Assistant-Session: 01a09dc1-b21e-77e1-919e-fcad2f82b267
2026-09-14 15:50:49 +02:00

6.7 KiB

id type title domain repo status flavor owner topic_slug created updated depends_on unblocks origin origin_ref state_hub_workstream_id
TEN-WP-0012 workplan Track the two external dispositions tenant-engine is waiting on infotech tenant-engine blocked residual claude netkingdom 2026-09-07 2026-09-10
TEN-WP-0011
residual TEN-WP-0011 cb7387d0-431d-56a2-bb7b-86a024aeeefb

TEN-WP-0012 — Track the two external dispositions tenant-engine is waiting on

TEN-WP-0011 closed correctly. Its T04 and T06 are done in the sense that matters here: this repository built everything it owns. What neither task could close is the other side — a credential audit-core issues, and a canon edit only net-kingdom may make.

Those two waits have no durable local record. The intakes were filed outbound, on other repositories' intake files, so nothing in this checkout holds them. SCOPE.md mentions both in prose, but prose is not scanned.

The cost is small and repeating: session protocol Step 3 scans workplans/ for open work, finds none, and each session re-derives the same two externally-owned gaps from SCOPE.md and the audit-core source before concluding — correctly — that there is nothing to do. This workplan holds that conclusion so it is read rather than rediscovered.

Why this is a workplan and not an intake

This repository's intake files record work it may act on. Both records here are the opposite: work filed elsewhere, awaiting someone else's disposition. Only workplans/ is read at session start, and wait is the convention's status for work that is blocked on another party.

Non-goals

  • Not editing net-kingdom canon from this repository. TEN-WP-0011-T06 settled that: file an intake, never fork the contract.
  • Not requesting a credential over the message bus. Credential routing is explicit that POST /messages/ asking for a token is an anti-pattern; sender registration is audit-core's to issue.
  • Not re-opening TEN-WP-0011. Our side of both items shipped.
  • No code change was expected from this workplan. That held until 2026-09-10, when audit-core's disposition on T01 arrived carrying a blocking defect in our emitter. The fix was small, wholly inside this repo, and belonged to the wait it unblocks, so it was made here rather than spun into a workplan of its own. A larger one still would.

T01 — audit-core sender registration (AUDIT-IN-0002)

id: TEN-WP-0012-T01
status: wait
flavor: residual
priority: medium
state_hub_task_id: "7898c1aa-b5de-54cf-87b7-67b727b5d0b2"

The emission path shipped in TEN-WP-0011-T04: the local outbox is inside the mutation transaction, the drain POSTs /v1/events and never fails a mutation, and the trade is declared in docs/evidence-emission.md. What is missing is sender registration — a credential audit-core issues and holds custody of. src/tenant_engine/audit_core.py documents that this module holds no audit-core credential beyond that sender token.

Waiting on: AUDIT-IN-0002, filed on audit-core.

2026-09-10 — registered, and a blocking defect found on our side. audit-core registered the sender (attributive, source pinned to tenant-engine, may_write, secret_policy: redact, tenants: ["*"] justified per sender) and recorded our declared completeness trade on the sender identity itself. The token and the operator apply are still theirs to issue, so this task stays wait.

Their review then found that no event we emitted could ever have been accepted. envelope_for sent five of the eight required fields under its own names (event_id, action, resource, observed_at, details) and omitted correlation_id entirely; normalize() rejects that whole, 400. Our drain treated 400 as terminal, so every event would have been marked handled here while audit-core held only an unchained dead letter — lost on both sides, silently, with the integration looking healthy. The root cause was on their side: the wire contract was published nowhere we could read, and docs/audit-backend-contract.md describes the stored record, from which the names we chose were a reasonable inference. It is now published as audit-core docs/event-envelope.md.

Fixed here the same day, ahead of any token:

  • envelope_for emits exactly the eight required fields and sends none of the six audit-core derives.
  • correlation_id is threaded through create / revoke / plan, which had no such field. It is optional on those three request bodies for compatibility; when a caller supplies none this engine mints req-<uuid> for the operation it actually performed and returns it. Never synthesized at the archive, which is what audit-core refuses and is right to refuse.
  • Idempotency-Key is sent and equals the body id.
  • 400 no longer dead-letters. The row stays pending with the rejection reason recorded on it, per their guidance that a 400 is an integration defect to fix, not a delivery outcome to record.
  • wire_envelope upgrades outbox rows written in the old shape at send time, and refuses to send one whose correlation cannot be recovered from its payload.

Verified by running all nine event types, through the API, through audit-core's actual normalize() with a matching SenderIdentity — all accepted. That is the check their message asked for, short of a live non-production 202, which still needs the token.

Done when: audit-core registers the sender and production mutations land externally, or audit-core declines and SCOPE.md row "Independent audit-core emission" is restated to say so.

Do not: request the token by message, or synthesize a local stand-in that would make the outbox look drained when it is not.

T02 — boundary-contract amendment (NET-IN-0002)

id: TEN-WP-0012-T02
status: wait
flavor: residual
priority: low
state_hub_task_id: "f7d27d7c-f599-5d0e-b60b-9c3ad2b27b87"

net-kingdom/canon/standards/tenant-engine-boundary-contract_v0.1.md still calls guardrail/quota policy "reserved, not implemented" and this repository "not a policy enforcement point". Guardrails shipped in TEN-WP-0006/0007, and the write path is PEP-shaped without this repository being a PDP, so both sentences now mislead a reader who trusts the contract over the code.

Waiting on: NET-IN-0002, filed on net-kingdom by TEN-WP-0011-T06.

Done when: the contract is amended at its next cut, or net-kingdom declines and the standing divergence is recorded here rather than left as a live contradiction between contract and code.

Closing this workplan

Close when both tasks reach a disposition, whichever way each falls. If either stays open long enough to stop being worth re-reading, cancel the task and say in SCOPE.md that the gap is permanent — an accepted, documented divergence beats an indefinite wait.