Establish INTENT, Stage 1 GOAL, and founding workplan

Claim ownership of the browser-facing approver UI that approval-engine
deliberately does not contain. approval-engine's INTENT names an approvals
inbox under Non-Goals, and docs/keycape-service-registrations.md records that
the human approver client's client_id and callback URI "must come from its
owner once it exists" — leaving key-cape's KEY-WP-0013-T02 blocked on an
unassigned component.

- INTENT.md: Decision Memo concept, the binding/awareness split and the two
  hashes, ownership and non-ownership against the named estate repositories,
  and a provisional PEP-shaped layer placement flagged for a gate-house ruling
  rather than asserted.
- GOAL.md: Stage 1 is the L3 approval approver surface — the narrowest real
  consumer with a live blocking dependency — plus the written answer to who
  owns the approver UI.
- workplans/INFD-WP-0001: founding documents, the gate-house layer/ownership
  ruling, the four specs (PRD, UseCaseCatalog, ArchitectureBlueprint,
  EvidenceModel), schema and canonicalizer promotion out of history/ with the
  isolation vectors under test, the key-cape client registration, and a
  walking skeleton that includes return and discuss.

history/ is preserved unmodified as provenance.

Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01V3W1dQG7GFFM9d94jFx7iR

Assistant: claude-code
Assistant-Model: opus
Assistant-Process: 1565372@bnt-lap001
Assistant-Session: 16bb2f25-b34c-49ef-8e94-5fec3567a568
This commit is contained in:
tegwick 2026-09-09 10:47:36 +02:00
parent 771ddb9ced
commit ee2cca579c
16 changed files with 3218 additions and 1 deletions

View file

@ -0,0 +1,289 @@
---
id: INFD-WP-0001
type: workplan
title: "Founding specs and approver-UI ownership"
domain: infotech
repo: informed-decision
status: proposed
owner: claude
topic_slug: netkingdom
created: "2026-09-09"
updated: "2026-09-09"
origin: founding
origin_ref: history/20260909-initial-exploration/InitialExploration.md
---
# INFD-WP-0001 — Founding specs and approver-UI ownership
Establish `informed-decision` as a governed repository in the NetKingdom estate,
settle who owns the browser-facing approver UI that `approval-engine`
deliberately does not contain, and produce the specification set that Stage 1
implementation will be built against.
The trigger is concrete and dated. On 2026-09-08 `key-cape` (`KEY-WP-0013-T02`)
asked `approval-engine` for the human approver client's `client_id` and callback
URI. `approval-engine` correctly declined to invent them and recorded in
`docs/keycape-service-registrations.md` that the human approver flow *"belongs to
whichever browser-facing approver UI presents `approval:approve` tokens to this
engine. That component is not in this repo."* `APPROVAL-WP-0002-T01` remains
`progress` partly because of it. This workplan closes that gap by naming the
owner and shipping the contract.
**Status is `proposed`, pending review** against the current `approval-engine`,
`access-engine`, `key-cape`, `gate-house` and `audit-core` contracts, and
against the deployment estate. T02 is the gate: if `gate-house` places this
component differently, T03T05 are rewritten before they are written.
Scope boundary for this workplan: **specification and contract, plus one
walking skeleton**. Full L3 product build is residual and belongs to
`INFD-WP-0002`.
## Establish the founding documents
```task
id: INFD-WP-0001-T01
status: done
priority: high
```
Write the repository's stable statements of purpose and current stage, derived
from the founding exploration rather than reinvented.
Acceptance: `INTENT.md` states purpose, the Decision Memo concept, ownership and
non-ownership against the named estate repositories, design principles, wrongness
conditions and success criteria; `GOAL.md` states the Stage 1 outcome, exclusions,
invariants and definition of done; `README.md` orients a new reader in under a
minute; `history/20260909-initial-exploration/` is preserved unmodified as the
provenance record.
Completed 2026-09-09: `INTENT.md`, `GOAL.md` and `README.md` written. `SCOPE.md`
is deliberately deferred to T06 — a scope file written before the layer ruling
and the specs would describe an imagined boundary, which is the drift `SCOPE.md`
exists to prevent.
## Settle layer placement and approver-UI ownership with gate-house
```task
id: INFD-WP-0001-T02
status: todo
priority: high
```
Take the ownership question to `gate-house` as doctrine rather than asserting a
catalog row. The proposal to argue: `informed-decision` owns the browser-facing
approver surface, the presentation record and the evidence of informedness; it
is **PEP-shaped** under statute §6.4 and companion §5 because it is
browser-facing and causes a protected side effect on the far side of a decision;
it supplies exactly one PIP-like fact — *what was presented* — as a claim, and
never evaluates it.
Raise explicitly, and do not paper over:
- §17 has no request-claim schema owner assigned. A `view_hash`-bearing
presentation claim must yield to that schema when it exists rather than
inventing a permanent local shape.
- `approval-engine`'s claim already carries *"a digest over the same canonical
binding the decision point already computes"*. Whether `view_hash` is that
digest, a sibling of it, or a distinct presentation attestation is a real
question and the wrong answer creates two competing canonicalizations of the
same act. This is the single highest-risk unknown in the workplan.
- A surface that renders both the question and the answer is adjacent to the
self-dealing objection that kept the object out of `access-engine`. State why
it is not the same failure: this repository holds no state a decision reads
as authority.
Acceptance: an intake is filed with `gate-house`; a ruling or a recorded decision
exists; `layer.yaml` is written from the ruling and matches the catalog row, not
this workplan's prose; `INTENT.md` and `GOAL.md` are amended if the ruling
differs from the proposal; the `view_hash`-versus-binding-digest relationship is
recorded as a decision, not left implicit. Blocking for T05 and T07.
## Product Requirements Document
```task
id: INFD-WP-0001-T03
status: todo
priority: high
```
Write `docs/specs/ProductRequirementsDocument.md` for Stage 1: the L3 approval
approver surface, scoped to one real consumer.
Must cover: the personas (approver holding a mandate, requester, observer/auditor);
the disposition vocabulary and which verbs are legal on which step kinds; the
required-highlight acknowledgment gate; the pre-sign/awareness split as it
appears in the UI; the evidence bundle as an export; accessibility and locale
(DE/EN, given the *Umlaufmappe* framing); and the explicit non-requirements from
`GOAL.md` — no mandate graph, no QES, no notification transport.
State the anti-requirements as first-class: no dark patterns, no dwell timers,
no keystroke analytics, and a UI that makes unmistakable that the whole
instrument is bound rather than only the acknowledged highlights.
Acceptance: every requirement traces to either a `GOAL.md` definition-of-done
item or a named external contract; each requirement is testable; the document
names what it is deliberately not requiring and why.
## Use Case Catalog
```task
id: INFD-WP-0001-T04
status: todo
priority: medium
```
Write `docs/specs/UseCaseCatalog.md` covering the full depth spectrum L0L5, with
Stage 1 scope marked, so that scale invariance is testable as a design property
rather than a claim in a vision statement.
For each level: actor, trigger, requested act, binding level, the verbs that must
be available, the evidence produced, and the estate repository that is the
counterparty. Include the L0 login banner and the L2 ADR accept in full even
though they are out of Stage 1 build scope — their purpose here is to constrain
the schema so the object cannot fork later.
Include the negative cases: `accept` on a Kenntnisnahme step (illegal by design),
a bind attempt with unacknowledged required highlights, an agent attempting a
disposition, and a tenant switch requiring a new bind.
Acceptance: every use case maps onto the single Decision Memo schema with no
level-specific object; each negative case names the invariant it protects; the
catalog states for each level which estate repository would consume it.
## Architecture Blueprint
```task
id: INFD-WP-0001-T05
status: todo
priority: high
```
Write `docs/specs/ArchitectureBlueprint.md`. Depends on T02 — the layer ruling
determines what this component is permitted to be.
Must cover: the component boundary and its position in the security layer model;
the call graph to `key-cape` (OIDC authorization-code + PKCE for humans),
`approval-engine` (bearer `approval:approve`, never `approval:consume`),
`access-engine` (decision, never rendered here) and `audit-core` (evidence
emission); the storage posture for memos, presentations and dispositions;
the deployment shape including the Ingress and external origin that
`approval-engine` explicitly does not have; and the failure modes — what the
surface does when `approval-engine`, `key-cape` or `audit-core` is unavailable.
Fail-closed is the default and must be stated per dependency. A surface that
degrades into showing a memo it cannot bind is acceptable; a surface that
degrades into binding without evidence is not.
Acceptance: no component in the diagram renders an authorization decision; the
token audiences, scopes and principal types match `approval-engine`'s
`docs/keycape-service-registrations.md` exactly; every external dependency has a
stated unavailable-stance; the blueprint names which parts are Stage 1 and which
are placeholders.
## Evidence model, schema promotion and canonicalization under test
```task
id: INFD-WP-0001-T06
status: todo
priority: high
```
Promote the exploration artifacts from `history/` into governed, tested
repository assets, and write `docs/specs/EvidenceModel.md`.
Move `decision-memo.schema.json` to `schemas/`, `canonicalize.py` into the
package, and the fixtures in `vectors/` into the test suite. `history/` stays
untouched as provenance; the governed copies are the ones that change.
The four isolation properties from the exploration become tests that must stay
green:
1. shuffling object keys does not change either hash;
2. editing an awareness field does not change `view_hash`;
3. changing `binding.target` does change `view_hash`;
4. selecting a role after login emits `session.hat_selected` and does not
rewrite `view_hash`.
`EvidenceModel.md` covers what an evidence bundle contains, how it verifies
offline, its relationship to `audit-core`'s archive, and — carried over from
`approval-engine`'s reasoning rather than rediscovered — the honest statement
that a hash chain proves records were not altered after arrival and cannot prove
a record was never sent.
Write `SCOPE.md` as the last step of this task, once the layer ruling and the
specs have fixed the real boundary.
Acceptance: schema, canonicalizer and vectors live outside `history/` and are
exercised in CI; the three published expected hashes reproduce byte-for-byte;
`EvidenceModel.md` states the residual it does not close; `SCOPE.md` exists and
describes the implemented-and-first-cut boundary, not the aspiration.
## Publish the OIDC browser-client contract to key-cape
```task
id: INFD-WP-0001-T07
status: todo
priority: high
```
Own and publish the two strings `approval-engine` could not supply: the human
approver client's `client_id` and its full callback URI. Depends on T02 for the
ownership ruling and on T05 for the deployment origin.
The registration is an authorization-code + PKCE public or confidential browser
client — not `client_credentials` — and the resulting access token must carry
`aud=approval-engine`, `principal_type: human`, `tenant: tenant:platform` and
scope `approval:approve`. Redirect URIs match exactly at `/authorize`, so the
origin must be a real deployed origin, decided in T05, not a placeholder.
Do not request `approval:consume`: `approval-engine` refuses it for human
principals, and consumption belongs to the PEP that causes the side effect.
Acceptance: `docs/keycape-client-registration.md` publishes both strings and the
expected token shape; the contract is sent to `key-cape` referencing
`KEY-WP-0013-T02`, and to `approval-engine` referencing its
`docs/keycape-service-registrations.md` follow-up; a token issued against the
registration is accepted by `approval-engine`'s verifier; `KEY-WP-0013-T02` is
unblocked. **This is the task that discharges the gap that created this
repository.**
## Walking skeleton — one approval, end to end
```task
id: INFD-WP-0001-T08
status: todo
priority: medium
```
Prove the specs against reality with the thinnest possible L3 path: sign in via
`key-cape`, list approvals awaiting this principal from `approval-engine`,
render one as a Decision Memo with brief, packet and highlights, acknowledge the
required highlights, and submit an approval entry with a stored presentation
record carrying `view_hash`.
`return` and `discuss` are in this skeleton, not deferred. They are the
differentiator; a skeleton with only approve/reject proves the wrong product.
Acceptance: one approval is approved by a real human through this surface
against a deployed `approval-engine`; the approval entry is reconstructable from
a stored presentation; a bind attempt with unacknowledged required highlights
fails closed; `return` produces a structured reason and is distinguishable from
`decline` in the record; no code path in this repository evaluates whether the
act is permitted.
Gated externally on `approval-engine` `APPROVAL-WP-0002-T01` reaching `done` and
on the service being deployed with an origin this surface can reach.
## Known risks
- **T02 is a hard gate.** Writing the blueprint before the layer ruling risks
building a component the statute does not permit in that shape.
- **Two canonicalizations.** If `view_hash` and `approval-engine`'s binding
digest are not reconciled in T02, the estate ends up with two hashes over the
same act and no rule for which one is authoritative.
- **Deployment origin is on someone else's critical path.** T07 cannot complete
without a real external origin, and this repository does not yet own an
Ingress. This is the most likely cause of slip.
- **Scope pressure toward an approvals inbox.** The fastest way to close
`KEY-WP-0013-T02` is to build a queue with two buttons. That would satisfy the
dependency and abandon the thesis. T04 exists to make the cost of that visible.