Skip to content

feat(governance): settle the campaign-governance rules that were contradictory or undefined - #9006

Merged
bokelley merged 10 commits into
mainfrom
governance/8733-normative-decisions
Nov 17, 2026
Merged

bokelley merged 10 commits into
mainfrom
governance/8733-normative-decisions

Conversation

@lukasz-pubx

@lukasz-pubx lukasz-pubx commented Nov 14, 2026 •

Copy link
Copy Markdown
Contributor

Summary

PR 2 of 3 for #8733: the normative decisions, as confirmed in this comment. Where the specification contradicted itself or was silent, this PR states the rule the Governance working group chose and brings the reference agent into line for A1 and A4. It was revised after review, and follows the decision record update of 2026-11-15 for A4, C1 and C2. No wire field, enum member or plan_hash rule changes.

Refs #8733. PR 1 was #8931. PR 3 (B2, C4.1, C4.2) was #9007.

What changes

Item Files Change
A1 campaign/specification.mdx, training agent A sync that reduces budget.total (or a period amount) below the amount already committed is rejected with VALIDATION_ERROR and leaves the plan unchanged. The training agent gets the sync-time budget.total check, next to the existing period check.
A4 campaign/tasks/check_governance.mdx, campaign/specification.mdx, campaign/audit-trail.mdx, enums/governance-mode.json, training agent A failed approved_sellers or delegations evaluation for an authenticated caller is a denied verdict with a finding and a check_id, in every governance mode. A caller with no access to the plan gets PLAN_NOT_FOUND, the same response as for an unknown plan_id, and writes no audit entry. PERMISSION_DENIED stays only for an unauthenticated caller or an identity that does not match caller. The audit-trail example of a rogue seller's call becomes an execution check. The three mode examples now use a budget finding.
B1 campaign/specification.mdx, enums/governance-mode.json, safety-model.mdx, index.mdx, tasks/get_plan_audit_logs.mdx Plans with human_review_required: true escalate in every mode. The same sentences now name the A4 denial as the second case that mode does not change.
C1 campaign/tasks/sync_plans.mdx, governance/sync-plans-request.json A plan_id is scoped per owner principal. Another principal's sync_plans with the same ID creates or updates that principal's own plan, and never reads, changes or reveals the first one.
C2 campaign/specification.mdx, enums/delegation-authority.json Defines a pre-approved action. An execute_only delegate acts only on such an action, which includes accept_proposal. The governance agent MUST deny an intent check from such a delegate that would create a new binding or increase committed spend.
C3 campaign/specification.mdx No geography, or country level only, is outside a regions-restricted plan: conditions at intent, denied at execution.
C4.3 campaign/tasks/sync_plans.mdx An unresolvable registry policy ID is REFERENCE_NOT_FOUND.
C4.4 campaign/tasks/check_governance.mdx "The same action" means re-checks that carry the same consultation_context.
B2 follow-up campaign/tasks/sync_plans.mdx The error table states that an explicit human_review_required: false on a plan that requires human review is rejected with VALIDATION_ERROR, as decided on #9007.

All doc paths are under docs/governance/.

Notes for review

What the revision changed. The commit 1d11b5d applies the review and the decision record update. It sits on a merge of main, whose only conflict was two adjacent rows of the sync_plans error table.

  • A4 holds in every mode. The sentence that let mode govern a finding about the target seller is gone. The modes section names two outcomes that do not depend on mode: plans with human_review_required: true escalate, and a failed approved_sellers or delegations evaluation is denied. The mode summaries on index.mdx, safety-model.mdx, tasks/get_plan_audit_logs.mdx and in enums/governance-mode.json say the same.
  • A4 and the uniform-response rule. A caller with no access to the plan gets PLAN_NOT_FOUND, as error-handling.mdx ("Uniform response for inaccessible references") and the PLAN_NOT_FOUND definition require. The specification sentence and the check_governance error row say so, and say that the attempt writes no audit entry. The denied verdict with a delegation_authority finding is for a caller that can access the plan.
  • C1 is per owner principal. No PERMISSION_DENIED on reuse.
  • C2 keeps accept_proposal and words the prohibition as an obligation on the governance agent.
  • B2 follow-up. The sync_plans error table states the VALIDATION_ERROR for an explicit human_review_required: false.

Second revision, 84cbf74, after this review and this comment:

  • Plan access is defined. A plan is accessible to a caller that is its owner principal, that is named in a delegations entry that has not expired, or that presents a governance_context or consultation_context the governance agent issued for that plan. This is the definition given in review, and it is what the reference agent already does. Any other caller gets PLAN_NOT_FOUND.
  • The PERMISSION_DENIED sentence no longer says "only". It now says that a failed delegations or approved_sellers evaluation is never PERMISSION_DENIED, and names the authentication cases as examples. The earlier wording excluded an expired governance_context.
  • The every-mode list is complete. It adds a delegate that acts outside the authority, budget_limit or markets of its delegation.
  • Mode summaries. index.mdx, safety-model.mdx, overview.mdx and enums/governance-mode.json no longer say that audit mode approves everything or never blocks.
  • One test is renamed to match its fixture, a delegate over its budget_limit.

The mode examples in audit-trail.mdx changed. They showed an unapproved target seller that enforce mode denies and advisory and audit mode approve. That is no longer true, so the three examples now show a buy that asks for more than the plan's total budget. One sentence under them says which two outcomes do not move with mode.

Reference agent after this change.

  • A critical seller_compliance or delegation_authority finding is no longer approved in advisory or audit mode. That includes a delegate that exceeds its budget_limit or markets. Four new test cases cover the two modes.
  • For a plan that does not exist or that the caller cannot access, check_governance returns the PLAN_NOT_FOUND error and stores nothing. It returned a denied verdict with a plan_lookup finding and stored a check record. A test asserts that the two cases give byte-identical responses and that neither the owner's session nor the request's session holds a check. No compliance storyboard depended on the old shape.
  • It already scopes plans per owner principal (feat(governance): define cross-role enforcement #6214), so C1 needs no change there.
  • It does not read delegations[].authority, and training-agent.test.ts has an execute_only delegate opening fresh intents that are approved. So the agent does not yet enforce the C2 sentence. That fixture is not changed here.

Smaller points:

  • A1 is reduction-only in the reference agent. A re-sync that leaves budget.total unchanged on a plan that is already over-committed is accepted, because concurrent approvals can legitimately produce that state (specification.mdx:391). The check compares committedBudget, which only settled outcomes add to, so the two storyboards that cut a plan from 100,000 to 10,000 before any outcome is reported still pass.
  • A4 early denials record mode: "enforce". They are issued before the plan's mode is read.
  • B1 covers more files than the issue listed. safety-model.mdx, index.mdx and the advisory wording repeat the losing sentence, so they change too.
  • C3 and the reference agent. The agent stores plan.regions and never reads it, so the existing rule at specification.mdx:487 is already unimplemented there. Not changed here.
  • C4.3 error.field. It names the policy_ids array parameter, as error-handling.mdx requires for REFERENCE_NOT_FOUND on an array.
  • Not in this PR: a compliance storyboard for A4, a migration-guide entry, and any six-week notice wording for the experimental surface.

Changeset

minor. The surface is experimental governance.campaign, and a previously conformant agent can fail the new sentences. The changeset gives before and after for A1 and A4.

Not settled here: the experimental-surface rule asks for six weeks of notice before a breaking change lands. A1 and A4 change behaviour. Earlier 3.3 changes recorded a waiver in the migration guide; this PR does not edit the release docs.

Verification

Run locally on Node 24.22.1:

  • Pre-commit hook (root unit tests, full server unit suite in four shards, typecheck): pass
  • npm run test:schemas, test:json-schema, test:examples, test:docs-nav, test:owned-links, test:additive-minor, test:mcp-schema-projection, test:compliance-snippets: pass
  • node scripts/check-docs-mdx-syntax.mjs, node scripts/docs-json-field-audit.cjs: pass, no new findings
  • Pre-push storyboard matrix against the training agent: all seven tenants pass. /governance is 59 clean with 183 steps, governance/budget_periods 7 passed, and the five media_buy_seller/governance_* scenarios pass with their required counts

Existing tests changed, because they asserted the old error: training-agent-governance-intent-binding.test.ts (non-audience execution caller) and training-agent-governance-agent-credentials.test.ts (two service-audience assertions). The identity-mismatch assertions beside them are unchanged.

Changed in the revision: four new cases in training-agent-governance-intent-binding.test.ts for an unapproved target seller and an out-of-scope delegate in advisory and audit mode; the unknown-plan assertion in training-agent.test.ts; and the no-access case in training-agent-governance-caller-binding.test.ts, which now expects PLAN_NOT_FOUND.

The second revision, 84cbf74, changes no training-agent or compliance file. The pre-commit hook passed on it. The pre-push hook did not rerun the storyboard matrix for it, so the matrix result above is from 1d11b5d.

🤖 Generated with Claude Code

lukasz-pubx and others added 3 commits November 14, 2026 08:08
…radictory or undefined

PR 2 of 3 for #8733: the normative decisions of the Governance working
group, confirmed by the maintainer on the issue.

- A1: a sync that reduces budget.total below committed spend is rejected
  with VALIDATION_ERROR; the training agent gets the sync-time check
- A4: an authenticated caller that fails approved_sellers or delegations
  gets a denied verdict with a finding and a check_id; PERMISSION_DENIED
  stays for a missing or mismatched identity
- B1: plans with human_review_required: true escalate in every mode
- C1: a plan_id names at most one plan within a governance agent
- C2: execute_only acts only on a pre-approved action binding
- C3: no or country-level geography is outside a regions-restricted plan
- C4.3: an unresolvable registry policy ID is REFERENCE_NOT_FOUND
- C4.4: "the same action" means the same consultation_context

No wire field, enum member or plan_hash rule changes.

Refs #8733

Co-Authored-By: Claude Fable 5.2 <noreply@anthropic.com>
…ed callers in every mode

Follow-up within PR 2 of #8733, where the accepted wording sat against
rules already in the specification.

- C1: plan_id is unique per owner principal, as the reference agent has
  implemented since #6214. A sync never reads, changes or reveals
  another principal's plan, which keeps the plan-ID enumeration rule.
- A4: governance mode does not relax who may call. A buyer-side caller
  that is neither owner nor current delegate, and an execution caller
  that is not the preserved audience, are denied in every mode.

Refs #8733

Co-Authored-By: Claude Fable 5.2 <noreply@anthropic.com>
…e target seller

Follow-up within PR 2 of #8733. The audit-trail mode examples showed an
unapproved seller's execution check approved in advisory and audit
mode, which contradicts the rule that a caller without authority is
denied in every mode. They are the buyer's intent checks naming an
unapproved target seller: a finding about the target follows mode. The
finding text now reads "Target seller", as the reference agent emits.

Refs #8733

Co-Authored-By: Claude Fable 5.2 <noreply@anthropic.com>

@aao-secretariat aao-secretariat Bot left a comment

Copy link
Copy Markdown
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Ladon verdict: Escalate to human review

Escalate — gated schema paths touched without required review approval.

This PR modifies published protocol surface under static/schemas/source/** (delegation-authority.json, governance-mode.json, sync-plans-request.json). These are gated paths under a hard, deterministic approval gate, and review_decision is REVIEW_REQUIRED (not APPROVED). Per decision rule row 2, the gate is not satisfied and the PR cannot be auto-approved — human/CODEOWNERS review is required on the gated files.

The reviewer surfaced no Critical/High/Medium findings: schema↔docs coherence verified (prose-only enumDescription/description edits, no field/type/required/enum-member changes), a correct minor changeset, no wire-shape change, and the authority-denial refactor was confirmed equivalent and leak-free. On the merits this is a clean spec-settling PR. However, the diff touches gated schema source and is a protocol-policy/normative-classification call (Breaking vs Normative), which is the arbiter's/human's judgment and is never auto-approved absent an APPROVED review.

Blocking findings: none.

Escalation reasons:

  • Modifies gated path static/schemas/source/enums/delegation-authority.json with review_decision: REVIEW_REQUIRED — human/CODEOWNERS approval required.
  • Modifies gated path static/schemas/source/enums/governance-mode.json with review_decision: REVIEW_REQUIRED — human/CODEOWNERS approval required.
  • Modifies gated path static/schemas/source/governance/sync-plans-request.json with review_decision: REVIEW_REQUIRED — human/CODEOWNERS approval required.

Why human review

  • Modifies gated path static/schemas/source/enums/delegation-authority.json while review_decision is REVIEW_REQUIRED — human/CODEOWNERS approval required
  • Modifies gated path static/schemas/source/enums/governance-mode.json while review_decision is REVIEW_REQUIRED — human/CODEOWNERS approval required
  • Modifies gated path static/schemas/source/governance/sync-plans-request.json while review_decision is REVIEW_REQUIRED — human/CODEOWNERS approval required
  • This PR touches a path under a hard, non-overridable approval gate (static/schemas/source/enums/delegation-authority.json (modified) matches static/schemas/source/**; static/schemas/source/enums/governance-mode.json (modified) matches static/schemas/source/**; static/schemas/source/governance/sync-plans-request.json (modified) matches static/schemas/source/**) and the current GitHub review decision is 'REVIEW_REQUIRED', not APPROVED. This is a hard gate enforced in code — Ladon cannot auto-approve until a human/CODEOWNERS approval is recorded, regardless of how clean the diff is.

@bokelley

Copy link
Copy Markdown
Contributor

@lukasz-pubx thanks for PR 2. A1, B1 and C3 match the decisions. Four places differ from what was settled on #8733 (my comment there: #8733 (comment), plus the working-group record in the issue description). Could you align them?

  1. A4 in every mode. An authenticated caller that fails the approved_sellers evaluation gets verdict: "denied" with a seller_compliance finding and a check_id, whatever the plan's mode. As written, the mode sentence ("Mode governs how findings… are enforced") lets audit or advisory mode return approved plus a finding for an intent target outside approved_sellers, or for a seller removed since the intent. The human-review MUST (B1) applies in every mode, and this should too.
  2. Delegation failures, same treatment for every caller. An authenticated buyer-side agent outside delegations gets denied with a delegation_authority finding. That shouldn't depend on the caller already being tied to the plan. PERMISSION_DENIED stays only for a caller we can't authenticate, or whose identity doesn't match caller.
  3. C1: reject plan_id reuse. plan_id is unique per owner principal, and another principal reusing an existing plan_id gets PERMISSION_DENIED. Please don't let each owner reuse the same id.
  4. C2: keep accept_proposal. An execute_only delegate acts only on actions that already have an approved intent check, and that includes accept_proposal. Please don't narrow it.

Two smaller things:

Since the 3.3 RC is cut Monday, this will land as an RC fix. That's fine for errata-level alignment like this.

@KonstantinMirin

Copy link
Copy Markdown
Collaborator

A question on point 2 of the review above, before @lukasz-pubx aligns to it. Point 2 gives a delegation denial to every authenticated caller, including one with no access to the plan. Doesn't that conflict with PLAN_NOT_FOUND? It says sellers "MUST return this code uniformly for any plan_id not accessible to the calling account — never distinguish 'exists but unauthorized' from 'does not exist'" (error-code.json:199), and error-handling.mdx adds that "a resolve-then-deny path MUST NOT write tenant audit rows". A denied verdict with a check_id and a delegation_authority finding would tell a caller with no access that the plan exists. Would it work to keep PLAN_NOT_FOUND for a caller with no access to the plan, and denied for one that can see the plan but falls outside delegations?

Three smaller questions on the alignment:

  1. A4. governance-mode.json:14 still says audit mode "always returns approved", and the reference agent only adds a finding for a seller outside approved_sellers. Should both change with the rule?
  2. C1. If reuse is rejected with PERMISSION_DENIED, anyone can test a guessed plan_id through sync_plans. Would a SHOULD for unguessable plan IDs be worth adding?
  3. C2. Should the MUST NOT bind the governance agent, since it's the party that refuses the action?

Brings in main at 0709eaf, which includes PR 3 (#9007). The only conflict was two adjacent rows of the sync_plans error table: INVALID_REQUEST takes the row from main, REFERENCE_NOT_FOUND keeps this branch's row.

Co-Authored-By: Claude Fable 5.2 <noreply@anthropic.com>
@lukasz-pubx

Copy link
Copy Markdown
Contributor Author

@KonstantinMirin thanks. The conflict is real.

Point 2 and PLAN_NOT_FOUND. The first version of this PR did what you describe, for the reason you give: a caller with no access to the plan got the same answer as for an unknown plan and wrote nothing to the owner's log, and a caller already tied to the plan got denied with a delegation_authority finding. The passage you cite in error-handling.mdx is more explicit than the ones I had quoted. A denied verdict with a check_id for a caller with no access is a resolve-then-deny path that writes an audit row, and its response differs from the one for an unknown plan. So point 2 as reviewed and the uniform-response rule cannot both hold. Either point 2 gets the limit you describe, or the uniform-response rule gets an exception for check_governance.

@bokelley that is yours to decide. I have the alignment to your four points ready and am holding the push until you answer, because the answer changes what the specification sentence for point 2 says.

C1 has the same shape on a smaller scale: PERMISSION_DENIED for a plan_id in use, against success for a free one, also tells the two cases apart.

On the three smaller questions:

  1. A4. Yes, both change with the rule. In the revision, the audit and advisory descriptions in governance-mode.json name the denial as a case that mode does not change, and the reference agent no longer approves a seller_compliance or delegation_authority finding in advisory or audit mode.
  2. C1 and guessable IDs. That would be a new rule, so it is not in this PR. It would also not close the gap alone, because a caller can still confirm an ID it learned some other way.
  3. C2. Agreed that the governance agent is the party that enforces it. The sentence keeps the working-group wording, which binds the delegate. Naming the governance agent would read: "The governance agent MUST deny an intent check from an execute_only delegate that would create a new binding or increase committed spend." It is the same rule. I have not changed it, since the review asked for the accepted wording.

@bokelley

Copy link
Copy Markdown
Contributor

@lukasz-pubx @KonstantinMirin thanks, you're both right; the uniform-response rule wins.

  • Point 2: a caller with no access to the plan gets PLAN_NOT_FOUND, the same answer as for a plan that doesn't exist, and no audit row. A caller that can see the plan but falls outside delegations gets denied with a delegation_authority finding. That's Lukasz's original version.
  • C1: scope plan_id per owner principal, so another principal's sync_plans with the same id creates their own plan. Drop the PERMISSION_DENIED clause, which leaks existence.
  • A4: yes, change governance-mode.json and the reference agent as Lukasz described.
  • C2: use the governance-agent phrasing ("The governance agent MUST deny an intent check from an execute_only delegate…").

Please push the alignment with these. I'll update the record on #8733 so it matches.

Applies the review on adcp#9006 and the decision record update on
adcp#8733 of 2026-11-15.

- A4: a failed approved_sellers or delegations evaluation is denied in
  every governance mode. The mode section, the mode summaries and the
  governance-mode enum descriptions name it as a second case that mode
  does not change, next to human_review_required.
- A4, uniform response: a caller with no access to the plan receives
  PLAN_NOT_FOUND, the same response as for an unknown plan_id, and the
  attempt writes no audit entry. The denied verdict for a failed
  delegations evaluation is for a caller that can access the plan.
- C1: plan_id stays scoped per owner principal. No PERMISSION_DENIED on
  reuse, which would reveal that an ID is in use.
- C2: an execute_only delegate acts only on an action that already has
  an approved intent check, which includes accept_proposal. The rule is
  worded as an obligation on the governance agent.
- sync_plans error table: an explicit human_review_required: false on a
  plan that requires human review is rejected with VALIDATION_ERROR.
- audit-trail: the three mode examples use a budget finding, because an
  unapproved seller is now denied in every mode.

Training agent: check_governance no longer approves a failed
approved_sellers or delegations evaluation in advisory or audit mode.
For a plan that does not exist or that the caller cannot access it
returns the PLAN_NOT_FOUND error and stores nothing; it returned a
denied verdict with a plan_lookup finding.

Refs #8733.

Co-Authored-By: Claude Fable 5.2 <noreply@anthropic.com>

@aao-secretariat aao-secretariat Bot left a comment

Copy link
Copy Markdown
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Ladon verdict: Escalate to human review

Escalate — gated schema paths require human/CODEOWNERS approval (review_decision is REVIEW_REQUIRED).

This PR modifies three files under static/schemas/source/**, which are declared under a hard, non-overridable approval gate (gated_paths: true). The current review_decision is REVIEW_REQUIRED, not APPROVED, so the gate is not satisfied. Per decision rule row 2, the outcome must be escalate until a human/CODEOWNERS approval is recorded.

Escalation reasons

  • static/schemas/source/enums/delegation-authority.json (modified) is under a hard approval gate; review_decision is REVIEW_REQUIRED, not APPROVED.
  • static/schemas/source/enums/governance-mode.json (modified) is under a hard approval gate; review_decision is REVIEW_REQUIRED, not APPROVED.
  • static/schemas/source/governance/sync-plans-request.json (modified) is under a hard approval gate; review_decision is REVIEW_REQUIRED, not APPROVED.

No blocking findings exist. The reviewer confirmed a clean pass: schema changes are description-only and coherent with the updated docs (no wire field/enum/required/plan_hash change), a correctly-scoped minor changeset is present, and there are no oneOf/immutability/patch-eligibility issues. The governance-handlers.ts logic matches the budget-period and binding tests. There are no Critical/High/Medium findings.

This is consistent with the prior escalate: the gate persists purely because human approval has not yet been recorded, not because of any defect in the diff. Once review_decision becomes APPROVED, this clean diff can fall through to approve.

Why human review

  • Modifies gated path static/schemas/source/enums/delegation-authority.json while review_decision is REVIEW_REQUIRED — human/CODEOWNERS approval required
  • Modifies gated path static/schemas/source/enums/governance-mode.json while review_decision is REVIEW_REQUIRED — human/CODEOWNERS approval required
  • Modifies gated path static/schemas/source/governance/sync-plans-request.json while review_decision is REVIEW_REQUIRED — human/CODEOWNERS approval required
  • This PR touches a path under a hard, non-overridable approval gate (static/schemas/source/enums/delegation-authority.json (modified) matches static/schemas/source/**; static/schemas/source/enums/governance-mode.json (modified) matches static/schemas/source/**; static/schemas/source/governance/sync-plans-request.json (modified) matches static/schemas/source/**) and the current GitHub review decision is 'REVIEW_REQUIRED', not APPROVED. This is a hard gate enforced in code — Ladon cannot auto-approve until a human/CODEOWNERS approval is recorded, regardless of how clean the diff is.

@lukasz-pubx

Copy link
Copy Markdown
Contributor Author

@bokelley thanks, pushed in 1d11b5d, on top of a merge of main. The description is updated.

  • Point 2. A caller with no access to the plan gets PLAN_NOT_FOUND, the same response as for an unknown plan_id, and writes no audit entry. A caller that can access the plan but falls outside delegations gets denied with a delegation_authority finding. The specification and the check_governance error table say so.
  • C1. plan_id is scoped per owner principal. The PERMISSION_DENIED clause is not there.
  • A4. A failed approved_sellers or delegations evaluation is denied in every mode. governance-mode.json, the mode summaries and the reference agent match.
  • C2. accept_proposal is kept, and the prohibition reads "The governance agent MUST deny an intent check from an execute_only delegate that would create a new binding or increase committed spend."
  • Smaller items. The VALIDATION_ERROR for an explicit human_review_required: false is in the sync_plans error table.

Three things to know before merging:

  • The mode examples in audit-trail.mdx changed. They used an unapproved target seller to show enforce, advisory and audit giving three outcomes. That is now wrong, so they show a buy over the plan's total budget.
  • The reference agent now returns the PLAN_NOT_FOUND error for a plan that does not exist or that the caller cannot access, and stores nothing. It returned a denied verdict with a plan_lookup finding. That change was in fix(governance): correct stale campaign-governance pages and schema descriptions #9015 and moved here, because it is point 2.
  • The reference agent does not read delegations[].authority, so it does not yet enforce the C2 sentence. That is listed in the description and not changed here.

lukasz-pubx added a commit that referenced this pull request Nov 16, 2026
…escriptions

PR 4 for #8733: defects found while preparing PRs 2 and 3. Each edit
follows a rule that is already stated in the specification or schemas.
No schema property, enum member or plan_hash rule changes.

- name all five human-review triggers on the trust, known-limitations
  and FAQ pages; the FAQ says an omitted flag is accepted from 3.3
- the requires_human_review descriptions say the governance agent sets
  plan.human_review_required
- reallocation_threshold is required only without reallocation_unlimited
- overview: advisory mode returns approved; no budget is reserved
- drop a stale reference to a closed issue; mode is agent configuration
- the training agent's plans[].mode is labelled a sandbox test control

Rebuilt on the aligned PR 2 (#9006). The human_override declaration is
removed from this PR, and the PLAN_NOT_FOUND change now lives in #9006.

Refs #8733

Co-Authored-By: Claude Fable 5.2 <noreply@anthropic.com>

@KonstantinMirin KonstantinMirin left a comment

Copy link
Copy Markdown
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Thanks @lukasz-pubx. Point 2, C1, A4 and C2 now match the ruling, but two sentences at specification.mdx:215 need a fix before merge. The reference agent gives an inaccessible plan and a missing one the same bytes and writes nothing, as the uniform-response rule requires.

Blocking

  1. Define plan access. Lines 215 and 885 choose between PLAN_NOT_FOUND and the delegation_authority denial by whether the caller "can access the plan", and no page defines access. The reference agent reads it as the owner, a current delegate, or a caller that presents a governance_context or consultation_context issued for the plan (governance-handlers.ts:336, :1462). Today two agents can answer the same call differently. Please state that definition in the specification.
  2. Scope the PERMISSION_DENIED sentence. "returns PERMISSION_DENIED only when the caller is unauthenticated or its authenticated identity does not match caller" excludes an expired or invalid governance_context. error-code.json:217 lists that case under PERMISSION_DENIED, the reference agent returns it (governance-handlers.ts:1737), and the new test at training-agent-governance-intent-binding.test.ts:985 asserts it. Suggested: "A failed delegations or approved_sellers evaluation is never PERMISSION_DENIED."

Non-blocking

  • The list after "denied in every mode:" at line 885 reads as complete, but it leaves out a delegate acting outside its budget_limit, markets or execute_only scope. The reference agent denies those in every mode.
  • Some mode summaries still say audit mode approves everything: campaign/index.mdx:31 and governance/overview.mdx:240. safety-model.mdx:62 and governance-mode.json:14 keep "never block" next to the denied exception, and the audit risk column still says "Zero."
  • The test at training-agent-governance-intent-binding.test.ts:949 is named "outside delegations", but its fixture is a delegate over its budget_limit.

Local runs at 1d11b5d: test:schemas and lint:additive-minor pass, the 14 governance and training-agent test files pass (1,072 tests), and CI is green.

@bokelley

Copy link
Copy Markdown
Contributor

@lukasz-pubx thanks for 1d11b5d. One sentence still needs settling. The spec now gives denied to "a buyer-side caller that can access the plan but is neither its owner nor a current delegate", but it never says who can access a plan. If access means owner or current delegate, that case can't happen: every such caller would get PLAN_NOT_FOUND.

I'd define it as: the plan's owner, a current delegate, or a holder of a governance context issued for that plan. The last group covers a delegate whose delegation lapsed mid-flow, who then gets denied with a delegation_authority finding. Everyone else gets PLAN_NOT_FOUND. #9015 builds on this sentence, so it would be good to fix it here.

Second revision of adcp#9006 after review.

- specification.mdx: define which callers can access a plan. A plan is
  accessible to its owner principal, to a caller named in a delegations
  entry that has not expired, and to a caller that presents a
  governance_context or consultation_context issued for that plan. Any
  other caller gets PLAN_NOT_FOUND. This is what the reference agent does.
- specification.mdx: the PERMISSION_DENIED sentence no longer says
  "only". It says a failed delegations or approved_sellers evaluation is
  never PERMISSION_DENIED and names the authentication cases as examples,
  so an expired governance_context is not excluded.
- specification.mdx: the list of outcomes that are denied in every mode
  adds a delegate that acts outside the authority, budget_limit or
  markets of its delegation.
- check_governance.mdx: the PLAN_NOT_FOUND row states the access rule.
- index.mdx, overview.mdx, safety-model.mdx, governance-mode.json: the
  audit mode summaries no longer say that the mode approves everything or
  never blocks.
- Rename one test to match its fixture, a delegate over its budget_limit.
- Changeset: state the access rule.

No behaviour change in the training agent.

Co-Authored-By: Claude Fable 5.2 <noreply@anthropic.com>

@aao-secretariat aao-secretariat Bot left a comment

Copy link
Copy Markdown
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Ladon verdict: Escalate to human review

Escalate — gated schema paths require human/CODEOWNERS approval.

This PR modifies three files under the hard approval gate static/schemas/source/**, and review_decision is REVIEW_REQUIRED (not APPROVED). Per decision-table row 2, the outcome must be escalate until a human/CODEOWNERS approval is recorded. The clean diff cannot lift this gate on its own.

The reviewer found no Critical/High/Medium findings: this is a coherent documentation-and-wording refinement pass (PLAN_NOT_FOUND vs PERMISSION_DENIED model stated consistently, the "two outcomes hold in every mode" exception aligned across index/safety-model/overview and the governance-mode enum, a test rename matching the added delegation-scope exception). Schema↔docs coherence holds; no enum member, wire field, or plan_hash change. The prior escalate also carried no blocking findings — so escalation here persists solely because the gated-path approval is still outstanding, not because of code concerns.

Escalation reasons

  • Modifies gated path static/schemas/source/enums/delegation-authority.json while review_decision is REVIEW_REQUIRED — human/CODEOWNERS approval required.
  • Modifies gated path static/schemas/source/enums/governance-mode.json while review_decision is REVIEW_REQUIRED — human/CODEOWNERS approval required.
  • Modifies gated path static/schemas/source/governance/sync-plans-request.json while review_decision is REVIEW_REQUIRED — human/CODEOWNERS approval required.

Once a human/CODEOWNERS approval is recorded, this PR is clean and can fall through to approval.

Why human review

  • Modifies gated path static/schemas/source/enums/delegation-authority.json while review_decision is REVIEW_REQUIRED — human/CODEOWNERS approval required
  • Modifies gated path static/schemas/source/enums/governance-mode.json while review_decision is REVIEW_REQUIRED — human/CODEOWNERS approval required
  • Modifies gated path static/schemas/source/governance/sync-plans-request.json while review_decision is REVIEW_REQUIRED — human/CODEOWNERS approval required
  • This PR touches a path under a hard, non-overridable approval gate (static/schemas/source/enums/delegation-authority.json (modified) matches static/schemas/source/**; static/schemas/source/enums/governance-mode.json (modified) matches static/schemas/source/**; static/schemas/source/governance/sync-plans-request.json (modified) matches static/schemas/source/**) and the current GitHub review decision is 'REVIEW_REQUIRED', not APPROVED. This is a hard gate enforced in code — Ladon cannot auto-approve until a human/CODEOWNERS approval is recorded, regardless of how clean the diff is.

@lukasz-pubx

Copy link
Copy Markdown
Contributor Author

@bokelley @KonstantinMirin thanks, you both asked for the same sentence. It is in 84cbf74, and the description is updated.

1. Plan access. The specification now defines it, in the identity paragraph:

A plan is accessible to a caller that is its owner principal, that is named in a delegations entry that has not expired, or that presents a governance_context or consultation_context the governance agent issued for that plan. For any other caller check_governance returns PLAN_NOT_FOUND, exactly as for a plan_id that does not exist, and the attempt writes no audit entry.

This is the definition bokelley gave, and it is what the reference agent already does. One detail: the sentence names both context kinds. An intent check cannot carry a governance_context, so a delegate whose delegation lapsed mid-flow reaches the delegation_authority denial on a re-check through its consultation_context. On an execution check the seller presents the governance_context, and the delegation is evaluated for the buyer that made the original intent. The PLAN_NOT_FOUND row on the check_governance page says the same in short form.

2. PERMISSION_DENIED. The "only" is gone. The sentence now reads:

A failed delegations or approved_sellers evaluation is never PERMISSION_DENIED; that error is for authentication and credential failures, such as an unauthenticated caller or an authenticated identity that does not match caller.

The cases are examples, so an expired governance_context is no longer excluded.

Non-blocking points from the review

  • Every-mode list. It now includes an intent check by a delegate that acts outside the authority, budget_limit or markets of its delegation. One correction: the reference agent denies budget_limit and markets failures in every mode, but it does not read delegations[].authority, so it does not enforce execute_only in any mode. That gap is older than this PR and is not closed here.
  • Mode summaries. campaign/index.mdx:31 and governance/overview.mdx:240 no longer say that audit mode approves everything. safety-model.mdx:62 and governance-mode.json:14 drop "never block", and the audit risk column no longer says "Zero."
  • Test name. It now says "a delegate over its budget_limit".

@KonstantinMirin KonstantinMirin left a comment

Copy link
Copy Markdown
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Thanks @lukasz-pubx. 84cbf74 fixes both points from my last review: plan access is defined at specification.mdx:215, and the PERMISSION_DENIED sentence no longer excludes credential failures. I have one question about C1 before merge.

Which plan does a shared plan_id name? With plan_id unique per owner (sync_plans.mdx:114), brands A and B can both sync q1-2027 and delegate the same agency. The agency's intent check carries only plan_id (check-governance-request.json:233), so I can't find what decides whose budget it runs against. get-plan-audit-logs-request.json:21 ("Plans uniquely scope account") also stops being true.

Could we make plan_id unique instead of scoping it? Two ways:

  • A UUID, the pattern idempotency_key already follows ("Use a fresh UUID v4").
  • An ID the governance agent mints, the way a seller mints media_buy_id.

Either way the buyer gets a separate field for its own label. IDs can't collide, so neither per-owner scoping nor a tie-break rule is needed. @bokelley, does that fit your C1 ruling?

Smaller points

  • A governance_context issued for another plan reads as PLAN_NOT_FOUND at :215, but error-code.json:217 makes it PERMISSION_DENIED. Could the spec say the context is verified before access is resolved, and add the case to the row at check_governance.mdx:744?
  • sync-plans-request.json:383 says an expired delegate's actions are denied, while :215 gives that delegate PLAN_NOT_FOUND.
  • The list at :885 misses an execution check whose original buyer has since lost its delegation.
  • index.mdx:146 still says "approve everything", and overview.mdx:240 still has advisory mode returning denied.
  • The rc.1 notes need the notice basis for A1 and A4, as 3-2-to-3-3.mdx:936 records one.
  • No storyboard grades A4 or PLAN_NOT_FOUND byte identity yet. A follow-up is fine.

Local runs at 84cbf74: test:schemas and test:additive-minor pass, and the 14 governance and training-agent files pass (1,072 tests). CI is green.

Comment thread docs/governance/campaign/index.mdx Resolved
Comment thread docs/governance/overview.mdx Resolved
…ch the specification

The row listed two cases as if exhaustive; the specification now gives them as
examples of authentication and credential failures.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
@bokelley

bokelley commented Nov 17, 2026 •

Copy link
Copy Markdown
Contributor

@lukasz-pubx thanks, the access definition and the rescoped sentence are right. I pushed one line in 3eecc18 to save a round trip: the PERMISSION_DENIED row in the check_governance error table still read as a closed list, so it now matches the specification ("Authentication or credential failure, such as an unauthenticated caller or an authenticated identity that does not match the declared caller"). rc.0 is already out, so I'll merge once CI is green and this goes out in rc.1 with #9015. Could you file the reference agent's execute_only enforcement gap as its own issue?

…d mode wording

- Verify a presented governance_context before resolving plan access; a context
  that fails verification or names another plan is PERMISSION_DENIED, matching
  error-code.json.
- The every-mode denied list is non-exhaustive and includes an execution check
  whose original buyer lost its delegation.
- A conditions re-check returns the same consultation_context.
- Mode wording in the campaign index and overview no longer contradicts the
  specification.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>

@aao-secretariat aao-secretariat Bot left a comment

Copy link
Copy Markdown
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Ladon verdict: Escalate to human review

Escalate — gated schema paths require human/CODEOWNERS approval.

This PR modifies protocol source-of-truth files under static/schemas/source/**, which fall under a hard, deterministic approval gate. The current review_decision is not APPROVED (unknown/none), so the gate is not satisfied and auto-approval is prohibited regardless of how clean the diff is.

Findings: None. The reviewer found no blocking or medium issues. This subsequent pass addressed only a 13-line docs clarification (the PERMISSION_DENIED row in check_governance.mdx broadened to cover authentication/credential failures), coherent with the adjacent PLAN_NOT_FOUND row and the A4 decision — no spec drift.

Why escalate (not approve): Row 2 of the decision table — gated_paths: true AND review_decision ≠ APPROVED. The gate lifts only when a real human/CODEOWNERS approval is recorded. The prior decision was also escalate for the same reason.

Escalation reasons:

  • Modifies gated path static/schemas/source/enums/delegation-authority.json — human/CODEOWNERS approval required
  • Modifies gated path static/schemas/source/enums/governance-mode.json — human/CODEOWNERS approval required
  • Modifies gated path static/schemas/source/governance/sync-plans-request.json — human/CODEOWNERS approval required

A human reviewer with CODEOWNERS authority must approve the schema-source changes before this can merge.

Why human review

  • Modifies gated path static/schemas/source/enums/delegation-authority.json while review_decision is not APPROVED — human/CODEOWNERS approval required
  • Modifies gated path static/schemas/source/enums/governance-mode.json while review_decision is not APPROVED — human/CODEOWNERS approval required
  • Modifies gated path static/schemas/source/governance/sync-plans-request.json while review_decision is not APPROVED — human/CODEOWNERS approval required
  • This PR touches a path under a hard, non-overridable approval gate (static/schemas/source/enums/delegation-authority.json (modified) matches static/schemas/source/**; static/schemas/source/enums/governance-mode.json (modified) matches static/schemas/source/**; static/schemas/source/governance/sync-plans-request.json (modified) matches static/schemas/source/**) and the current GitHub review decision is 'unknown', not APPROVED. This is a hard gate enforced in code — Ladon cannot auto-approve until a human/CODEOWNERS approval is recorded, regardless of how clean the diff is.

@aao-secretariat aao-secretariat Bot left a comment

Copy link
Copy Markdown
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Ladon verdict: Escalate to human review

Escalate — gated path requires human/CODEOWNERS approval.

This PR modifies files under static/schemas/source/**, which are under a hard, non-overridable approval gate (gated_paths: true). The current review_decision is unknown/none, not APPROVED, so the gate is not satisfied (decision table row 2).

The reviewer pass was clean: no critical/high/medium findings. The delta is four governance docs (72 lines) plus schema enum/description reconciliation, and the reviewer confirmed schema↔docs coherence (governance-mode.json and delegation-authority.json enum descriptions match the delta text) with no spec drift. The prior run also escalated solely on the gated-path trigger with no actionable findings. Row 6 (sticky escalation) does not independently apply since this run surfaces no fresh critical/high/medium findings — but the gated-path gate (row 2) fires regardless and holds until a human/CODEOWNERS approval is recorded.

Escalation reasons

  • Modifies gated path static/schemas/source/enums/delegation-authority.json while review_decision is not APPROVED — human/CODEOWNERS approval required.
  • Modifies gated path static/schemas/source/enums/governance-mode.json while review_decision is not APPROVED — human/CODEOWNERS approval required.
  • Modifies gated path static/schemas/source/governance/sync-plans-request.json while review_decision is not APPROVED — human/CODEOWNERS approval required.

The diff is mechanically clean; once a human/CODEOWNERS approval is recorded the gate lifts.

Why human review

  • Modifies gated path static/schemas/source/enums/delegation-authority.json while review_decision is not APPROVED — human/CODEOWNERS approval required
  • Modifies gated path static/schemas/source/enums/governance-mode.json while review_decision is not APPROVED — human/CODEOWNERS approval required
  • Modifies gated path static/schemas/source/governance/sync-plans-request.json while review_decision is not APPROVED — human/CODEOWNERS approval required
  • This PR touches a path under a hard, non-overridable approval gate (static/schemas/source/enums/delegation-authority.json (modified) matches static/schemas/source/**; static/schemas/source/enums/governance-mode.json (modified) matches static/schemas/source/**; static/schemas/source/governance/sync-plans-request.json (modified) matches static/schemas/source/**) and the current GitHub review decision is 'unknown', not APPROVED. This is a hard gate enforced in code — Ladon cannot auto-approve until a human/CODEOWNERS approval is recorded, regardless of how clean the diff is.

@lukasz-pubx

Copy link
Copy Markdown
Contributor Author

@bokelley thanks for 3eecc18 and b8b5097, both read right to me. The reference agent gaps are filed as #9075.

  • execute_only. The agent stores authority and never reads it. One existing test expects a fresh intent from an execute_only delegate to be approved, so that fixture changes with the fix.
  • governance_context. The issue names the two sites that return VALIDATION_ERROR. The checks already run before plan access is resolved, as the sentence added in b8b5097 requires, so only the error code differs.
  • Plan regions. I added this one because it is the same kind of gap. The agent stores regions and never evaluates them, which this PR's description records as not changed here.

…ble plan

Per-owner plan_id scoping lets a delegate of two owners see two plans with the
same ID, and an intent check carries only plan_id. The governance agent now
rejects that check with VALIDATION_ERROR and evaluates it against neither plan,
and buyers SHOULD use globally unique plan IDs.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>

@aao-secretariat aao-secretariat Bot left a comment

Copy link
Copy Markdown
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Ladon verdict: Escalate to human review

Escalate — gated schema paths require human/CODEOWNERS approval.

This PR modifies files under static/schemas/source/**, which are under a hard, non-overridable approval gate (gated_paths: true), and the current review_decision is REVIEW_REQUIRED, not APPROVED. Per decision rule row 2, the outcome must be escalate until a human/CODEOWNERS approval is recorded.

Escalation reasons

  • Modifies gated path static/schemas/source/enums/delegation-authority.json while review_decision is not APPROVED — human/CODEOWNERS approval required.
  • Modifies gated path static/schemas/source/enums/governance-mode.json while review_decision is not APPROVED — human/CODEOWNERS approval required.
  • Modifies gated path static/schemas/source/governance/sync-plans-request.json while review_decision is not APPROVED — human/CODEOWNERS approval required.

No blocking findings. The reviewer's subsequent pass is clean: the delta is 3 docs-only files adding one normative decision (a check_governance caller that can access more than one plan under the same plan_id returns VALIDATION_ERROR), which composes cleanly with existing PLAN_NOT_FOUND and PERMISSION_DENIED cases with no contradiction or cross-principal leak. The prior pass was also clean. This escalation is driven purely by the unsatisfied gated-path approval requirement, not by any code defect — the gate lifts once review_decision becomes APPROVED.

Why human review

  • Modifies gated path static/schemas/source/enums/delegation-authority.json while review_decision is not APPROVED — human/CODEOWNERS approval required
  • Modifies gated path static/schemas/source/enums/governance-mode.json while review_decision is not APPROVED — human/CODEOWNERS approval required
  • Modifies gated path static/schemas/source/governance/sync-plans-request.json while review_decision is not APPROVED — human/CODEOWNERS approval required
  • This PR touches a path under a hard, non-overridable approval gate (static/schemas/source/enums/delegation-authority.json (modified) matches static/schemas/source/**; static/schemas/source/enums/governance-mode.json (modified) matches static/schemas/source/**; static/schemas/source/governance/sync-plans-request.json (modified) matches static/schemas/source/**) and the current GitHub review decision is 'REVIEW_REQUIRED', not APPROVED. This is a hard gate enforced in code — Ladon cannot auto-approve until a human/CODEOWNERS approval is recorded, regardless of how clean the diff is.

…sync_plans

Generated by build:compliance; the PR bundle check requires it committed.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>

@aao-secretariat aao-secretariat Bot left a comment

Copy link
Copy Markdown
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Ladon verdict: Escalate to human review

Escalate — gated schema paths require human/CODEOWNERS approval.

This PR modifies files under static/schemas/source/**, which is a hard, deterministic approval gate (gated_paths: true). The current review_decision is REVIEW_REQUIRED, not APPROVED, so the gate is not satisfied (decision table row 2). Ladon cannot auto-approve until a human/CODEOWNERS approval is recorded.

Review quality: The diff is clean. The reviewer found no critical/high/medium findings. The only delta since the prior run is a single editorial change in docs/governance/campaign/tasks/sync_plans.mdx — converting a bare VALIDATION_ERROR reference into a cross-reference link to /docs/building/verification/compliance-catalog#error-code-validation-error, with the anchor verified to exist and the link format matching established convention. Schema↔docs coherence, changeset scope, and oneOf discriminator checks surfaced nothing actionable.

Escalation reasons:

  • Modifies gated path static/schemas/source/enums/delegation-authority.json while review_decision is REVIEW_REQUIRED — human/CODEOWNERS approval required.
  • Modifies gated path static/schemas/source/enums/governance-mode.json while review_decision is REVIEW_REQUIRED — human/CODEOWNERS approval required.
  • Modifies gated path static/schemas/source/governance/sync-plans-request.json while review_decision is REVIEW_REQUIRED — human/CODEOWNERS approval required.

Once a human/CODEOWNERS approval lands and review_decision becomes APPROVED, this clean diff can fall through to approve.

Why human review

  • Modifies gated path static/schemas/source/enums/delegation-authority.json while review_decision is REVIEW_REQUIRED — human/CODEOWNERS approval required
  • Modifies gated path static/schemas/source/enums/governance-mode.json while review_decision is REVIEW_REQUIRED — human/CODEOWNERS approval required
  • Modifies gated path static/schemas/source/governance/sync-plans-request.json while review_decision is REVIEW_REQUIRED — human/CODEOWNERS approval required
  • This PR touches a path under a hard, non-overridable approval gate (static/schemas/source/enums/delegation-authority.json (modified) matches static/schemas/source/**; static/schemas/source/enums/governance-mode.json (modified) matches static/schemas/source/**; static/schemas/source/governance/sync-plans-request.json (modified) matches static/schemas/source/**) and the current GitHub review decision is 'REVIEW_REQUIRED', not APPROVED. This is a hard gate enforced in code — Ladon cannot auto-approve until a human/CODEOWNERS approval is recorded, regardless of how clean the diff is.

@bokelley
bokelley merged commit 954eb9d into main Nov 17, 2026
65 checks passed
@bokelley
bokelley deleted the governance/8733-normative-decisions branch November 17, 2026 16:19
lukasz-pubx added a commit that referenced this pull request Nov 17, 2026
…escriptions

PR 4 for #8733: defects found while preparing PRs 2 and 3. Each edit
follows a rule that is already stated in the specification or schemas.
No schema property, enum member or plan_hash rule changes.

- name all five human-review triggers on the trust, known-limitations
  and FAQ pages; the FAQ says an omitted flag is accepted from 3.3
- the requires_human_review descriptions say the governance agent sets
  plan.human_review_required
- reallocation_threshold is required only without reallocation_unlimited
- overview: advisory mode returns approved; no budget is reserved
- drop a stale reference to a closed issue; mode is agent configuration
- the training agent's plans[].mode is labelled a sandbox test control

Rebuilt on the aligned PR 2 (#9006). The human_override declaration is
removed from this PR, and the PLAN_NOT_FOUND change now lives in #9006.

Refs #8733

Co-Authored-By: Claude Fable 5.2 <noreply@anthropic.com>
bokelley pushed a commit that referenced this pull request Nov 18, 2026
…escriptions (#9015)

* fix(governance): correct stale campaign-governance pages and schema descriptions

PR 4 for #8733: defects found while preparing PRs 2 and 3. Each edit
follows a rule that is already stated in the specification or schemas.
No schema property, enum member or plan_hash rule changes.

- name all five human-review triggers on the trust, known-limitations
  and FAQ pages; the FAQ says an omitted flag is accepted from 3.3
- the requires_human_review descriptions say the governance agent sets
  plan.human_review_required
- reallocation_threshold is required only without reallocation_unlimited
- overview: advisory mode returns approved; no budget is reserved
- drop a stale reference to a closed issue; mode is agent configuration
- the training agent's plans[].mode is labelled a sandbox test control

Rebuilt on the aligned PR 2 (#9006). The human_override declaration is
removed from this PR, and the PLAN_NOT_FOUND change now lives in #9006.

Refs #8733

Co-Authored-By: Claude Fable 5.2 <noreply@anthropic.com>

* fix(governance): apply review corrections to the follow-up errata

Second revision of adcp#9015 after review.

- policy-category-definition.json: the requires_human_review description
  no longer says that a policy can override the category's setting. A
  policy adds the requirement, and no policy removes a category's.
- get-plan-audit-logs-response.json: the entries[].mode description no
  longer mentions a governed_actions[].mode field, which does not exist.
- specification.mdx, audit-trail.mdx: state one strength for mode on
  audit entries, the one the schema has. A governance agent SHOULD record
  the mode on check entries, and outcome entries carry none. The
  specification said MAY and the audit-trail page said every entry.
- overview.mdx: the image alt text no longer says budget is reserved.
- specification.mdx, sync-plans-request.json: the reallocation table and
  the reallocation_threshold description point to
  reallocation_unlimited: true for unlimited reallocation, because a
  threshold equal to total tightens when total changes.
- Changeset: cover the edits above.

No schema property, enum member or plan_hash rule changes.

Co-Authored-By: Claude Fable 5.2 <noreply@anthropic.com>

* fix(governance): say that mode is reported on the check_governance response

The specification said that governance mode is "an internal
implementation detail of the governance agent, not a protocol-level
field". The check_governance response has carried an optional mode
property since 3.1, the task page documents it, and the reference agent
returns it.

- specification.mdx: mode is configuration of the governance agent. No
  request carries it, and it is not a plan field. The agent MAY report
  the mode in force on the check_governance response. Callers still MUST
  NOT branch on it.
- Changeset: cover the edit.

No schema, wire field or agent behaviour changes.

Co-Authored-By: Claude Fable 5.2 <noreply@anthropic.com>

* fix(governance): align the delegation expiry description with the plan-access rule

The delegations[].expires_at description in sync-plans-request.json said
that the governance agent denies an expired delegate's actions. Since
adcp#9006 a caller with an expired delegation and no issued context
gets PLAN_NOT_FOUND.

- sync-plans-request.json: after expiration the agent is no longer a
  current delegate. Its intent re-check that presents a
  consultation_context issued for the plan, and an execution check on an
  action it proposed, are denied with a delegation_authority finding.
  Any other check from that agent returns PLAN_NOT_FOUND.
- Changeset: cover the edit.

Description only. No schema property or validation outcome changes.

Co-Authored-By: Claude Fable 5.2 <noreply@anthropic.com>

---------

Co-authored-by: Claude Fable 5.2 <noreply@anthropic.com>
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

ladon/needs-human-review Ladon has escalated this PR for human review.

Projects

None yet

Development

Successfully merging this pull request may close these issues.

3 participants