Repository navigation
Description
Status (updated 2026-11-18): complete
The Governance working group reviewed this issue on a call on 2026-11-10. It accepted every recommendation except C5, which it left open. A4 was decided against the original recommendation. On 2026-11-11 the work was split into three pull requests (split), and the C5 key was settled as (owner_principal, seller_agent) (acceptance, correction). On 2026-11-13 the three questions that were still open were answered (reply): C5 stays in #8931 and ships in 3.3, A4 is the denied verdict as the working group decided, and the default removal goes in PR 3. On 2026-11-15 two of the picks, A4 for delegation failures and C1, were revised to match the uniform-response rule (decision record). All four pull requests are merged, the last one on 2026-11-18. The three questions that this issue leaves undecided are in #9083. This description has been updated in place so that it is the single current statement of what was decided and done; the two comments below record how the decisions were reached (feedback and corrections, call outcome).
| Item | Decision | Change |
|---|---|---|
| A1 | Reject the sync with VALIDATION_ERROR; the previous plan stays in force |
Doc + reference agent |
| A2 | Mode is agent configuration, not a plan field | Doc |
| A3 | Checks do not reserve budget; "reserve" keeps one meaning | Doc |
| A4 | denied verdict, in every governance mode, for an authenticated caller that can access the plan and fails approved_sellers or delegations. A caller that cannot access the plan gets PLAN_NOT_FOUND. PERMISSION_DENIED only for an authentication or credential failure, which includes a governance_context that is expired, fails verification or was issued for another plan |
Doc (three pages) + reference agent |
| A5 | verdict, not status |
Doc |
| A6 | A re-sync does not re-validate active buys | Doc |
| A7 | The delivery outcome example is buyer-called |
Doc |
| A8 | Schema vocabulary (escalations[], escalation_rate) |
Doc |
| A9 | Examples self-consistent; index table carries the note | Doc |
| B1 | The human-review MUST applies in every mode | Doc + enum description |
| B2 | Omission accepted, explicit false rejected; "default": false removed |
Schema (compatible) + doc |
| B3 | Restrict or mark the legacy response branch | Schema description |
| C1 | Unique per owner principal. Another principal's sync_plans with the same ID creates or updates that principal's own plan. A check_governance caller that can access more than one plan with the ID it sends gets VALIDATION_ERROR |
Doc + the plan_id description |
| C2 | execute_only acts only on bindings that already hold an approved intent |
Doc + enum description |
| C3 | No geography, or country level only, is outside a regions-restricted plan | Doc |
| C4 | Four sync_plans validation rules as proposed |
Doc + x-adcp-validation |
| C5 | The key is (owner_principal, seller_agent). Whether buyer-side thresholds also sum across sellers is a separate question, now in #9083 |
Doc + one schema description; changes behaviour for an agent keyed on a derived account |
Pull requests:
- PR 1, merged as docs(governance): align campaign-governance pages with the specification and schemas #8931 on 2026-11-13: A2, A3, A5, A6, A7, A8, A9, B3, C5. Released in 3.3.0-beta.6. The 3.2.x backport is docs(governance): align campaign-governance pages with the specification and schemas (3.2.x backport of #8931, without C5) #8980, without C5.
- PR 2, merged as feat(governance): settle the campaign-governance rules that were contradictory or undefined #9006 on 2026-11-17: A1, A4, B1, C1 to C3, C4.3, C4.4. It differs from the wording accepted on the call in three places (C1, C2, A4). In each, the accepted wording conflicted with a rule that is already in the specification, and the PR follows the existing rule. Each difference is recorded under its item below and in the decision record. On
main, due in the next 3.3 release candidate. - PR 3, merged as fix(governance): accept an omitted human_review_required and state two sync_plans validation rules #9007 on 2026-11-15: B2 with the
defaultremoval, C4.1, C4.2. Released in 3.3.0-rc.0. - PR 4, merged as fix(governance): correct stale campaign-governance pages and schema descriptions #9015 on 2026-11-18: errata outside the list in this issue, found while preparing PRs 2 and 3. Each follows a rule that already exists. On
main, due in the next 3.3 release candidate.
What changed in this description on 2026-11-18: this status section and the pull request list; the A4 and C1 rows of the table; a note under A4, C1 and C2 that records what merged; the two undecided C5 points moved to #9083; one sentence in Compatibility; a result under each acceptance criterion; Related. The evidence quotes and the decisions recorded on 2026-11-10 are left as they were.
What changed in this description on 2026-11-10: A4 rewritten for the reversed decision; B2 extended with the schema default; C5 rewritten as an open question and reclassified from doc-only to normative; a decision line added under every other item; Compatibility, Files affected, Acceptance criteria and Related updated to match. The evidence quotes are unchanged.
What changed in this description on 2026-11-14: the pull request list; the 2026-11-13 answers; a note under A4, C1 and C2 where PR 2 departs from the accepted wording; the C5 placement. The decisions recorded on 2026-11-10 are left as they were recorded.
What changed on 2026-11-11: this status section; C5 rewritten for the accepted key and for a corrected account of where account_id came from; the pull-request list added; the C5 lines in Compatibility, Files affected, Acceptance criteria and Related updated to match. No other item changed.
Summary
The campaign-governance doc set (docs/governance/campaign/**) disagrees with itself in a way an implementer cannot resolve by reading harder. As of ded86cd (3.3.0-beta.4; the same text is live in the 3.2.8 build), the task pages, audit-trail.mdx and safety-model.mdx contradict specification.mdx in 8 places, the specification contradicts its own schemas in 2 places, and 6 behaviours that every governance agent must implement are undefined. This issue asks for a coherence sweep in the style of #8077: one page owns each rule, the others defer to it, and the undefined behaviours get a one-sentence normative answer each. Every claim below was re-verified against the pinned tree; items that were already fixed on main are listed at the end so triage does not re-litigate them.
Line numbers are into the pinned tree at ded86cd94361f0e4eb88ac21e5e7be67f00106d7 and should be re-verified at implementation time. Re-checked on 2026-11-10 at 13092c2: every file cited in this issue is identical to the pinned tree, so the line numbers still hold.
Part A — pages that contradict the specification
For each item: the two passages, which one I recommend wins, the edit, and the working-group decision. Unless stated otherwise the fix is doc-only and the surviving rule is normative (it already is on one of the two pages).
A1. Budget reduced below committed spend: reject the sync, or accept and flag?
docs/governance/campaign/tasks/sync_plans.mdx:291—VALIDATION_ERROR… "Cannot reduce budget below the amount already committed (on plan update), leave a dated commitment outside every budget period, or set a periodamountbelow what is already committed to it." and:166"A rejected sync leaves the plan unchanged."docs/governance/campaign/specification.mdx:620— "If an amendment reduces the budget below the currently committed amount, the governance agent flags this as a finding on the next governance check."
Two conformant agents: one returns VALIDATION_ERROR and keeps the old plan; the other bumps the version, hashes a plan whose budget.total is below committedBudget, and lets the next check_governance compute negative headroom. The reference agent already holds both readings: it rejects a period amount cut at sync time (server/src/training-agent/governance-budget-periods.ts:317), accepts a budget.total cut and surfaces it later as a budget_authority warning finding at outcome time (server/src/training-agent/governance-handlers.ts:3326-3331), while its comment at governance-handlers.ts:1214-1215 asserts the "same VALIDATION_ERROR as a budget.total that drops below committed spend" exists. Recommend the task page wins (reject): #7965 chose reject for periods, and a plan whose total is below its commitments has no usable headroom. Edit: replace the specification.mdx:620 sentence with "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.", and add the missing sync-time check to the reference agent.
Decided (WG call, 2026-11-10): accepted as recommended. The previous plan stays in force, so the campaign keeps running. Reducing spend that is already committed is settled with the seller, not through a plan re-sync.
A2. Where governance mode lives
docs/governance/campaign/audit-trail.mdx:233— "modeis set on the plan via [sync_plans] and is the operator's primary lever." and:316"A plan can shift modes between revisions".docs/governance/campaign/specification.mdx:876— "Governance mode (audit, advisory, enforce) is an internal implementation detail of the governance agent, not a protocol-level field." and:883"Mode is configured by the buyer's policy team on the governance agent itself, not via the protocol.";tasks/check_governance.mdx:728andtasks/get_plan_audit_logs.mdx:326— "not from a plan field".static/schemas/source/governance/sync-plans-request.jsonhas nomodeproperty;modeexists only response-side (check-governance-response.json:291,get-plan-audit-logs-response.json:311) andenums/governance-mode.jsondescribes it as "Operating mode for a governance agent."
Specification and schema win. Edit audit-trail.mdx:233 and :316 to say mode is agent configuration recorded on each check entry, and that a mode change between two entries reflects a configuration change, not a plan revision.
Decided (WG call, 2026-11-10): accepted as written.
A3. Budget reservation and the word "reserve"
docs/governance/campaign/safety-model.mdx:78— "Concurrent media buys are handled through optimistic concurrency control or budget reservation, preventing concurrent approvals that together exceed the plan budget."docs/governance/campaign/specification.mdx:567— "Budget checks are point-in-time:check_governancevalidates against the current committed total but does not reserve budget. If multiple agents execute concurrently against the same plan, two checks could both pass and the combined outcomes could exceed the authorized budget." (repeated at:391).- The specification also uses "reserve" in a ledger sense:
:563"governance conservatively reserves $150K and records the $120K report as a discrepancy";tasks/report_plan_outcome.mdx:70"the intent reserves the buyer-proposed positive-delta ceiling".
The safety-model page promises a property the specification explicitly disclaims. Specification wins. Edit safety-model.mdx:78 to state the point-in-time limitation and that concurrency control is a deployment concern (matching the "Human controls" and "Monitoring" operational non-goals in docs/reference/known-limitations.mdx:110-111). Separately, pick one verb: use "reserve" only for the intent-ceiling ledger entry, or rename that to "records the ceiling", so "does not reserve budget" cannot be read as contradicting :563.
Decided (WG call, 2026-11-10): accepted as written.
A4. Unapproved seller: error or denied verdict?
docs/governance/campaign/tasks/check_governance.mdx:744—PERMISSION_DENIED… "the target/executing service is not authorized byapproved_sellers."docs/governance/campaign/audit-trail.mdx:179-202— "A different seller callscheck_governanceand gets denied:" with"verdict": "denied","category_id": "seller_compliance", "Caller https://ads.seller-rogue.example is not in the plan's approved sellers list.", and:202"the audit entry captures the denied attempt throughcheck_id."docs/governance/campaign/specification.mdx:215— "approved_sellersis evaluated against the target service that becomes the tokenaud, never against that buyer" — the audit-trail example evaluates it against the caller.
An error has no check_id and no audit check entry; a denied verdict has both. Auditors reading get_plan_audit_logs from two agents will see the rogue-seller attempt in one log and not the other.
Decided (WG call, 2026-11-10): the verdict shape wins. This reverses the original recommendation in this issue, which was PERMISSION_DENIED. The reason given: a rejected attempt by an unapproved seller must appear in the audit log.
- An authenticated caller that fails the
approved_sellersevaluation receivesverdict: "denied"with aseller_compliancefinding and acheck_id. This covers three cases: an intent check whose target is not inapproved_sellers; an execution check whose authenticated caller is not the audience preserved from the approved intent; and an execution check whose caller has since been removed fromapproved_sellers. - Delegation failures are treated the same way. An authenticated buyer-side caller that is neither the plan owner nor covered by a current entry in
delegationsreceivesdeniedwith adelegation_authorityfinding. PERMISSION_DENIEDremains only where there is no trustworthy identity to record: the caller is unauthenticated, or the authenticated identity does not match the declaredcaller. These produce nocheck_idand no plan-scoped audit entry, so a party with no established identity cannot append to another principal's audit log.
PR 2 (#9006) adds one sentence to this decision. The specification says an agent in audit mode always returns approved, and nothing said whether mode applies to an authority failure. PR 2 states that mode governs how findings about the governed action are enforced and does not relax who may call. So an execution caller that is not the preserved audience, and a buyer-side caller outside delegations, are denied in every mode. A finding about the target seller on an intent check still follows mode. One limit applies to point 2: a caller with no access to the plan at all receives PLAN_NOT_FOUND, the same as for an unknown plan_id, because the PLAN_NOT_FOUND definition forbids telling the two apart. This limit was first drafted for PR 4 (#9015) and moved to PR 2.
Revised on 2026-11-15 and merged in #9006 (decision record). Point 2 now applies only to a caller that can access the plan. A plan is accessible to its owner principal, to an agent named in a delegations entry that has not expired, and to a caller that presents a governance_context or consultation_context that the governance agent issued for that plan. Any other caller gets PLAN_NOT_FOUND, exactly as for a plan_id that does not exist, and the attempt writes no audit entry. Point 3 stands, and PERMISSION_DENIED also covers a presented governance_context that is expired, fails verification or was issued for another plan. The governance agent verifies a presented context before it resolves plan access.
Edits:
tasks/check_governance.mdx:744— narrow the row to "Authenticated identity is missing or does not match the declaredcaller."specification.mdx:215— add one sentence: a failedapproved_sellersordelegationsevaluation for an authenticated caller is returned as adeniedverdict with a finding, never as an error.audit-trail.mdx:179-202— the example labels a seller's call"check_type": "intent"(:186, repeated at:242,:265,:290). Underspecification.mdx:215a seller calls execution checks, and on an intent checkapproved_sellersis evaluated against the target, "never against that buyer". The example becomes an execution check.- Reference agent — it already returns the finding for an unapproved seller (
server/src/training-agent/governance-handlers.ts:2072-2083) and already errors on a missing or mismatched identity (:1866-1870,:1515-1522). Two gates returnPERMISSION_DENIEDwhere the decision now calls for a verdict: an authenticated execution caller that is not the preserved audience (:1727-1742), and a buyer-side caller that is neither owner nor delegate (:1895-1903), which returns before thedelegation_authorityfinding at:2048-2070can fire. In both, the error stays only for the unauthenticated case. enums/error-code.json:215is generic across tasks and needs no change.
A5. plans[].entries[].status versus verdict
docs/governance/campaign/tasks/get_plan_audit_logs.mdx:324— "|plans[].entries[].status| enum | Governance check status (present forcheckentries). |"- Every example on the page (
:164,:180) andaudit-trail.mdx:50useverdict;static/schemas/source/governance/get-plan-audit-logs-response.json:299-301definesverdict("Renamed fromstatusin 3.1 alongside check-governance-response for vocabulary consistency") and the entries object has nostatusproperty.
Schema wins; rename the table row. Doc-only.
Decided (WG call, 2026-11-10): accepted as written.
A6. Does a re-sync re-evaluate active campaigns?
docs/governance/campaign/tasks/sync_plans.mdx:112— "Syncing a plan that already exists (sameplan_id) updates it. The governance agent increments the version and re-evaluates any active campaigns against the updated rules."docs/governance/campaign/specification.mdx:620— "Active media buys that were approved under the previous plan version are not automatically re-validated -- the governance agent evaluates them against the updated plan on the nextcheck_governancecall (e.g., the next delivery check)."
Specification wins. Edit sync_plans.mdx:112 to "… increments the version. Active media buys are not re-validated until their next check_governance call."
Decided (WG call, 2026-11-10): accepted as written.
A7. A seller-called delivery outcome in the audit example
docs/governance/campaign/tasks/report_plan_outcome.mdx:16— "Sellers do not call this task. They report delivery data via [check_governance] withphase: "delivery"."docs/governance/campaign/tasks/get_plan_audit_logs.mdx:204-218— entry"id": "out_del_001", "type": "outcome", "caller": "https://ads.seller-example.com/adcp", … "outcome": "delivery".get_plan_audit_logs.mdx:341— "plans[].entries[].delivery… Buyer-attributed observation retained on adeliveryoutcome. It never overwrites the seller statement."
The example contradicts the page's own table and the task page. Change the example's caller to the buyer agent (the seller statement is the preceding check entry with phase: "delivery"). Doc-only.
Decided (WG call, 2026-11-10): accepted as written.
A8. Three vocabularies for the same drift metrics
docs/governance/campaign/specification.mdx:578,592,607,616—human_review_rate,human_review_rate_min.docs/governance/campaign/tasks/get_plan_audit_logs.mdx:134,143,301,307—escalations[],escalation_rate.docs/governance/campaign/audit-trail.mdx:44,99,101—summary.human_reviews[],human_review_rate,human_review_rate_min.static/schemas/source/governance/get-plan-audit-logs-response.json:155-246definesescalations,drift_metrics.escalation_rate,escalation_rate_trend,auto_approval_rate,human_override_rate,mean_confidence,thresholds.{escalation_rate_max, escalation_rate_min, auto_approval_rate_max, human_override_rate_max}. The onlyhuman_review*token in the schema is thestatuses.human_reviewedcount (:144).human_reviews,human_review_rateandhuman_review_rate_minexist in no schema.
A buyer following the specification's "set human_review_rate_min" guidance has no field to set it in. Schema wins: rewrite the specification and audit-trail passages in the schema's vocabulary (escalations[], escalation_rate, thresholds.escalation_rate_min) and state in one sentence that statuses.human_reviewed counts the resolved escalations. No schema change. Alternative: add human_review_rate to the schema as an alias — rejected here because two names for one number is the defect being fixed.
Decided (WG call, 2026-11-10): accepted as written.
A9. Finding category labels (editorial)
The same geo violation is labelled strategic_alignment in findings (tasks/check_governance.mdx:602,648; specification.mdx:1135) while categories_evaluated on the same page lists geo_compliance (:496), and index.mdx:195 presents a six-row category table without the "agent-internal, not a protocol enum" note that tasks/sync_plans.mdx:232 and check-governance-response.json:151-153 carry. No schema constrains these values, so this is not a conformance conflict, but the examples should be self-consistent and the index table should carry the same note. Doc-only, lowest priority in this issue.
Decided (WG call, 2026-11-10): accepted as written.
Part B — the specification contradicts its own schemas
B1. Audit mode "always returns approved" versus the human-review MUST
docs/governance/campaign/specification.mdx:879— "A governance agent in audit mode internally always returnsapprovedwith findings attached";enums/governance-mode.json:14— "audit": "Log all checks, never block. Findings are recorded but the governance agent always returns approved."specification.mdx:156— "Whenhuman_review_requiredis true, the governance agent MUST escalate any action on the plan for human review before execution — regardless of the plan'sreallocation_threshold.";sync-plans-request.json:294— same MUST.
An agent in audit mode holding a fair_housing plan cannot satisfy both sentences. The MUST exists because of Art 22 / Annex III (#2310); it should not be defeatable by a configuration knob the protocol does not even see. Recommend: the human-review MUST is mode-independent. Edit :879 and the enum description to "… always returns approved with findings attached, except for plans with human_review_required: true, which escalate in every mode." Alternative: audit-mode agents reject sync_plans for such plans with VALIDATION_ERROR — workable but leaks mode into the protocol, which A2 says it must not. Normative; doc + enum-description only.
Decided (WG call, 2026-11-10): accepted as recommended. The human-review MUST applies in every mode; a mode setting must not be able to switch off a legal requirement.
B2. human_review_required "set automatically" versus a schema that rejects its omission
specification.mdx:154— "The governance agent setshuman_review_required: trueautomatically when any resolved policy or policy_category on the plan carriesrequires_human_review: true.";:165— "… overrides a caller-suppliedfalsewhen a triggering policy is present."static/schemas/source/governance/sync-plans-request.json:447-456—"then": { "properties": { "human_review_required": { "const": true } }, "required": ["human_review_required"] }(both the four-category branch at:429-446and theeu_ai_act_annex_iiibranch at:459-481).
With the schema enforced, a plan that omits the flag is INVALID_REQUEST and a plan with false is INVALID_REQUEST, so neither sentence in the prose can ever execute. With the schema not enforced (a client that validates at the model layer only), the prose governs and the explicit-false case is silently rewritten. Two deployments diverge on the same request. Recommend: drop required from both then branches and keep const: true. Explicit false stays schema-rejected (preserving the #2310/#2338 invariant), omission is accepted and the agent sets the flag, and the prose at :154/:165 becomes true as written (change "overrides a caller-supplied false" to "rejects a caller-supplied false"). Schema change, compatible (widens acceptance). Also fix docs/reference/known-limitations.mdx:80, which describes this invariant as rejecting authority_level: agent_full, a field the current schema condition does not use.
Decided (WG call, 2026-11-10): accepted as recommended, with one addition raised after filing.
sync-plans-request.json:293 declares "default": false on human_review_required. Once omission is valid, that annotation works against the decision in two ways. A consumer that applies schema defaults turns a valid omitted field into an explicit false, which the then branches reject, so a valid request becomes an invalid one (reproduced in one SDK, adcontextprotocol/adcp-client-python#1852). It also sits badly with specification.mdx:917: "Governance agents MUST hash the plan as-supplied; they MUST NOT synthesize omitted optionals to default values and MUST NOT drop explicit nulls."
Additional edits: remove "default": false at :293 and say in the description that an omitted flag means the governance agent derives it; add one sentence at specification.mdx:917 that schema default annotations are never applied to the hash preimage. budget.accounting_mode at :60 keeps its "gross_commitment" default, which is semantically real. Both changes are compatible, because default is an annotation and changes no instance's validity. Minor, same area: vector 004b-human-review-explicit-null.json supplies null for a property typed "type": "boolean", so its plan_as_supplied is not schema-valid; a note in the vector that it exercises canonicalisation only would stop a validating harness from rejecting it.
B3. Residual: the legacy check_governance response branch still permits conditions on execution checks
check-governance-response.json:12-31 restricts conditions to check_type: "intent", and specification.mdx:876 says "execution checks return approved or denied", but the else branch for responses without check_type (:69-100) carries no phase restriction, and enums/governance-decision.json / governance-phase.json carry none either. Either add the restriction to the legacy branch or mark that branch as 3.0-compat in its description. Schema-description or x-adcp-validation change; compatible.
Decided (WG call, 2026-11-10): accepted as written.
Part C — behaviours every implementation must decide, undefined today
Each item below had zero hits for the relevant terms in docs/governance/** and static/schemas/source/governance/**. Proposed answers are normative and additive (no field changes unless stated).
C1. plan_id uniqueness namespace
Ownership is defined (check-governance-request.json:233 "A plan is owned by the authenticated buyer principal that synchronized it"; specification.mdx:342-343) but uniqueness is not: tasks/sync_plans.mdx:183 says only "Unique identifier for this plan." Whether two principals may each sync plan-q1-2026 is unstated, and the answer decides whether a sync_plans from a second principal creates a second plan or is an ownership violation. Propose: plan_id is unique per owner principal; a sync naming an existing plan_id from a different principal is rejected with PERMISSION_DENIED (never silently creates a sibling plan). One sentence in sync_plans.mdx and the plan_id description.
Decided (WG call, 2026-11-10): accepted as proposed. Read together, the two halves mean that a plan_id names at most one plan within a governance agent: the principal that first syncs it owns it, and a sync_plans from any other principal naming that id is rejected with PERMISSION_DENIED.
PR 2 (#9006) departs from this, and states a per-owner namespace. Two principals may each hold the same plan_id, and neither can read, change or learn of the other's plan. The reason is the PLAN_NOT_FOUND definition in enums/error-code.json: "never distinguish 'exists but unauthorized' from 'does not exist'". A PERMISSION_DENIED on reuse tells any authenticated principal that the ID exists, and lets one principal block another by syncing an ID first. The reference agent has namespaced plans per owner since #6214. This issue mentioned neither when it proposed C1.
Confirmed on 2026-11-15 and merged in #9006 (decision record), with one addition. Because the namespace is per owner, one caller can have access to more than one plan with the same ID, for example a delegate of two owners that chose the same ID. check_governance then returns VALIDATION_ERROR and evaluates the check against neither plan. Buyers SHOULD use globally unique plan IDs. #9077 proposes a way to name the plan owner in that case, for 3.4.
C2. What execute_only may initiate
specification.mdx:337 and enums/delegation-authority.json:14 — "Can execute pre-approved actions but cannot initiate new campaigns or reallocate budget." "Pre-approved" is undefined. Propose: a pre-approved action is one whose opaque action binding already holds an approved intent check in this plan's lifecycle; an execute_only delegate may run execution checks and accept_proposal for such bindings and may not initiate an intent check that would create a new binding or increase committed spend. One sentence in the delegations section and the enum description.
Decided (WG call, 2026-11-10): accepted as proposed.
PR 2 (#9006) is narrower than this. It keeps the definition of a pre-approved action and the prohibition. It does not say that an execute_only delegate may run execution checks, because the specification requires the caller of an execution check to be the seller that the approved intent named, and a delegate is a buyer-side agent.
Merged in #9006 in this narrower form, worded as an obligation on the governance agent: "The governance agent MUST deny an intent check from an execute_only delegate that would create a new binding or increase committed spend." The reference agent did not enforce it, which is #9075.
C3. Regions-restricted plans and requests with no (or country-level) geography
specification.mdx:487 — "A plan with regions: ["US-MA"] rejects actions not explicitly targeting Massachusetts, even if they are otherwise compliant."; sync-plans-request.json:248 — regions "restricts governed actions to these specific regions rather than the full country." Nothing says what a payload with no geographic targeting, or with countries: ["US"] only, is. Propose: such a payload is treated as targeting the whole country and is outside a regions-restricted plan; intent checks return conditions naming the region constraint, execution checks return denied. Doc-only.
Decided (WG call, 2026-11-10): accepted as proposed.
C4. Four small gaps on sync_plans validation
- Flight ordering —
sync-plans-request.json:213-226definesflight.start/endwith no ordering rule. Proposeendstrictly afterstart→INVALID_REQUEST, mirroring the budget-period rule attasks/sync_plans.mdx:289("overlapping or empty windows, a window outsideflight"). - Duplicate ids —
policy-entry.json:10requires bespoke ids "unique within the authoring container" butpolicy_ids(:250-256) has nouniqueItemsand nothing covers acustom_policies[].policy_idcolliding with a registry id inpolicy_ids. Propose both →INVALID_REQUEST. - Unresolvable registry policy id — the
sync_planserror table (:289-291) has onlyINVALID_REQUEST,REFERENCE_NOT_FOUND(brand domain) andVALIDATION_ERROR(budget). ProposeREFERENCE_NOT_FOUNDwitherror.fieldpointing at the id, by precedent with the brand-domain row. - "The same action" in the three re-call rule —
tasks/check_governance.mdx:287"SHOULD returndeniedafter 3 unsuccessful intent re-calls for the same action" never says what "same" means, while:285andcheck-governance-request.json:303already bindconsultation_contextto principal, caller, plan, tool, purchase type and audience. Propose: "the same action" = re-checks carrying the sameconsultation_context.
Items 1 and 2 narrow what the schema accepts. For 3.x, state them in prose and as an x-adcp-validation annotation (the repo's mechanism for rules draft-07 cannot express); tightening the schema itself belongs at 4.0.
Decided (WG call, 2026-11-10): all four accepted as proposed.
C5. The trailing-window aggregation key names an account_id that no schema carries
specification.mdx:400 — "All plans attributable to the same (buyer_agent, seller_agent, account_id) tuple" (and :429) is a MUST-level anti-fragmentation rule, but no governance schema carries account_id (zero hits across static/schemas/source/governance/*.json), and tasks/get_plan_audit_logs.mdx:361 says tenant identity "is resolved from the submitted IDs".
Decided (2026-11-11): the key is (owner_principal, seller_agent). This is the original proposal of this item. The working group accepted it as a starting point on the 2026-11-10 call, the split comment placed it in PR 1, and it was accepted on the thread. The three-part key with brand that this description proposed on 2026-11-10 is withdrawn.
owner_principalis a defined term, not a wire field: the authenticated buyer principal that synchronized the plan.- Delegated sub-agents share the delegating buyer's aggregate, as
:400already says. Theowner_principalelement is the delegating principal, not the sub-agent'sagent_url. - The change is in docs(governance): align campaign-governance pages with the specification and schemas #8931:
specification.mdx:400,:421and:429, and thegovernance.aggregation_window_daysdescription atget-adcp-capabilities-response.json:3006, which named the old tuple too.
Correction to earlier versions of this item. They said that no governance schema carries account_id "since #6214". No governance schema has ever carried it: there are zero hits at v3.0.0, v3.1.0, v3.2.8 and on main. The third element of the key was always derived. The 3.0 and 3.1 request schemas said "the governance agent resolves account from the plan", and get-plan-audit-logs-request.json:21 on main still says "the governance agent resolves account from each plan". What #6214 changed was that wording in check-governance-request.json and report-plan-outcome-request.json, which now describe the plan as owned by the authenticated buyer that synchronized it.
The re-key changes behaviour for some agents. specification.mdx:421:
Governance agents MAY evaluate narrower aggregation scopes additionally (per-brand, per-campaign) but MUST NOT evaluate any scope broader than the declared window without operator sign-off. "Broader" covers both dimensions: a longer trailing window (time) and a wider key tuple (e.g., collapsing across
account_idso two accounts share an aggregate).
Dropping the third element is the widening that sentence names, so :421 gets a different example in the same edit. Two consequences follow:
- An agent that derives an account from the plan and partitions its aggregate by it satisfies the conformance example at
:429-436today. After the re-key it must aggregate across all of that principal's plans per seller, and may keep the per-account figure only as an additional, narrower scope. - A buyer principal that synchronizes plans for several advertisers pools their spend in one aggregate, so thresholds are reached earlier than under a per-account key.
For that reason #8931 asked maintainers to confirm where C5 belongs. Confirmed on 2026-11-13: C5 stays in #8931 and ships in 3.3, and the 3.2.x backport (#8980) leaves it out.
Moved to #9083 on 2026-11-18. These two points were still undecided when the pull requests merged:
- Do the buyer-side thresholds sum across the seller dimension or within it? The working group raised this on the call. The section names three thresholds:
reallocation_threshold,human_review_requiredtrigger points and registry-policy dollar floors. Its own example at:396is a buyer splitting $999,900 into 100 buys of $9,999 to stay under a $10,000 human-review threshold. Summing within one seller leaves the same split across 100 sellers open, which would then need documenting as out of scope. Summing across sellers closes it, with limits defined per seller, such asbudget.per_seller_max_pct(sync-plans-request.json:63-66), still summed within one seller. - Two places docs(governance): align campaign-governance pages with the specification and schemas #8931 leaves alone, because each needs a decision and not an edit.
get-plan-audit-logs-request.json:21still says plans "uniquely scope account and operator".specification.mdx:440says sellers also declare an aggregation window, and a seller cannot always tell a plan owner from its delegate.
C5 citations re-checked at 7ce107a.
Compatibility and migration
- Doc-only on the surviving rule: A1–A3, A5–A9, B1, C1, C2, C3, C4.3, C4.4. Implementations that followed the losing page change behaviour; that is the point of the issue, and in every case the losing page was already contradicted by the specification or the schema.
- Doc on three pages plus a behaviour change, no schema change: A4. An agent that returned
PERMISSION_DENIEDfor an authenticated unapproved seller, or for a buyer-side caller outsidedelegations, now returns adeniedverdict and writes an audit entry. Callers that branch on the error code for those cases must also handle the verdict. Only existing response fields are used. As merged, a caller that cannot access the plan at all getsPLAN_NOT_FOUND; the reference agent returned adeniedverdict with aplan_lookupfinding for that case before. - Schema, compatible: B2. Dropping
requiredin boththenbranches widens acceptance; removing thedefaultannotation changes no instance's validity. - Doc plus one schema description, with a behaviour change for some agents: C5. An agent that partitioned its aggregate by an account derived from the plan now aggregates across that principal's plans per seller, so aggregates get larger and thresholds are reached earlier. No wire field changes.
- Schema-description / annotation, compatible: B3, C4.1, C4.2 (as
x-adcp-validation; schema tightening deferred to 4.0). - Nothing here changes a wire field name, an enum member, or
plan_hashcanonicalization.
Files affected (as of ded86cd, identical at 13092c2; re-verify at implementation)
docs/governance/campaign/specification.mdx— A1, A3, A4 (:215), A6 (owner), A8, A9, B1, B2 (:154,:165,:917), C1–C4; C5 (:400,:421,:429)docs/governance/campaign/audit-trail.mdx— A2, A4 (the example becomes an execution check), A8docs/governance/campaign/safety-model.mdx— A3docs/governance/campaign/tasks/sync_plans.mdx— A6, C1, C4docs/governance/campaign/tasks/check_governance.mdx— A4 (the:744row), A9, C4.4docs/governance/campaign/tasks/get_plan_audit_logs.mdx— A5, A7docs/governance/campaign/index.mdx— A9docs/reference/known-limitations.mdx— B2 (field name)static/schemas/source/governance/sync-plans-request.json— B2 (thenbranches;defaultat:293), C4 (descriptions /x-adcp-validation)static/schemas/source/governance/check-governance-response.json— B3static/schemas/source/protocol/get-adcp-capabilities-response.json— C5 (:3006, theaggregation_window_daysdescription)static/schemas/source/enums/governance-mode.json,delegation-authority.json— B1, C2 descriptionsserver/src/training-agent/governance-handlers.ts— A1 (sync-timebudget.totalcheck), A4 (the gates at:1727-1742and:1895-1903), B2 (set the flag on omission; the cascade at:374-384already does this)static/compliance/source/test-vectors/plan-hash/004b-human-review-explicit-null.json— B2 (a note only; the expected hash is unchanged)- Deliberately untouched:
check-governance-request.json,report-plan-outcome-request.json,get-plan-audit-logs-response.json(the schemas win in A5 and A8),plan_hashcanonicalization and every vector's expected hash, and the compliance storyboards — a grep ofstatic/compliance/sourcefor the losing phrases (re-evaluat,budget reservation,human_review_rate,human_reviews) hits only delivery-phase re-evaluation text, which the specification supports. No storyboard exercises an unapproved seller or an undelegated caller oncheck_governancetoday (approved_sellersappears understatic/compliance/sourceonly in a plan-hash vector), so A4 breaks no existing scenario; a scenario for it is worth adding.
Acceptance criteria
- For each of A1–A8 a single page states the rule and every other page either repeats it verbatim or links to it;
grepfor the losing phrase returns nothing. - On
check_governance, an authenticated caller that failsapproved_sellersordelegationsreceivesverdict: "denied"with acheck_id, and the attempt appears inget_plan_audit_logs; an unauthenticated or mismatched caller receivesPERMISSION_DENIEDand leaves no entry. The training agent behaves this way. sync-plans-request.jsonaccepts a regulated-category plan that omitshuman_review_required, rejects one that sets itfalse, and carries nodefaulton the field; the training agent sets the flag on the omitted case.- Each of C1–C4 is answered by one normative sentence in the page named above. For C5,
specification.mdx:400,:421and:429state the key as(owner_principal, seller_agent); the cross-seller threshold question is answered in the same section or split into its own issue. docs/reference/known-limitations.mdx:80names the field the schema actually constrains.
Result at 61a1638 (2026-11-18):
- Met. A search of
docs/governance/,docs/reference/known-limitations.mdxandstatic/schemas/source/governance/for the losing phrase of A1 to A6 and A8 returns nothing, and the A7 example names the buyer as the caller. - Met, as revised on 2026-11-15. An unauthenticated or mismatched caller gets
PERMISSION_DENIED. A caller that cannot access the plan getsPLAN_NOT_FOUNDand leaves no entry. The training agent was changed to match in feat(governance): settle the campaign-governance rules that were contradictory or undefined #9006. - Met. Both
thenbranches carryconst: trueand norequired, and the field has nodefault(fix(governance): accept an omitted human_review_required and state two sync_plans validation rules #9007). - Met for C1 to C4 and for the C5 key. The cross-seller threshold question is split into Governance: decide whether aggregated-spend thresholds sum across sellers, and fix two statements left open by #8733 #9083.
- Met. The line names
human_review_required.
Already resolved on main — listed so triage does not reopen them
These were real conflicts at 3.1.24 and are fixed in the pinned tree (and in 3.2.8): advisory-mode semantics (specification.mdx:880, safety-model.mdx:63, via #6214); the check_governance intent example now being a valid create_media_buy payload (tasks/check_governance.mdx:316-327, #6214); report_plan_outcome requiring check_id for every outcome with either the intent or the execution check accepted (report-plan-outcome-request.json:12-31, specification.mdx:235, #6214/#6305); execution checks being binary in the modern response shape (check-governance-response.json:12-31); credential binding by resolved agent URL plus owner principal instead of an undefined "account" (specification.mdx:872, #6214); and the modification delta model (specification.mdx:199).
Related
- docs(schema): 3.3 coherence sweep (x-added-in, offline metrics registry, provenance table) #8077 — the 3.3 coherence sweep this issue mirrors in shape; that one covered schema annotations and registries, not the campaign-governance prose.
- feat(governance): define cross-role enforcement #6214 (PR) — cross-role authorization; fixed six of the original findings and introduced the owner-principal model that C5's key was never updated for.
- docs(governance): align campaign-governance pages with the specification and schemas #8931 (PR) — PR 1 of the three: A2, A3, A5 to A9, B3 and C5. Merged. Its description lists the few edits it makes beyond the files named above, and why.
- docs(governance): align campaign-governance pages with the specification and schemas (3.2.x backport of #8931, without C5) #8980 (PR) — the 3.2.x backport of docs(governance): align campaign-governance pages with the specification and schemas #8931, without C5.
- feat(governance): settle the campaign-governance rules that were contradictory or undefined #9006 (PR) — PR 2: A1, A4, B1, C1 to C3, C4.3, C4.4. Merged.
- fix(governance): accept an omitted human_review_required and state two sync_plans validation rules #9007 (PR) — PR 3: B2, C4.1, C4.2. Merged.
- fix(governance): correct stale campaign-governance pages and schema descriptions #9015 (PR) — PR 4: errata outside this issue's list. Merged.
- Governance: decide whether aggregated-spend thresholds sum across sellers, and fix two statements left open by #8733 #9083 — the three questions this issue leaves undecided: whether aggregated-spend thresholds sum across sellers, who declares the aggregation window, and the
plan_idsdescription onget_plan_audit_logs. - Governance: declare
human_overrideon thesync_plansplan item and state the human-review downgrade rule #9068 / feat(governance): declare human_override and state the human-review downgrade rule #9074 (PR) —human_overrideon the plan item, split out of PR 4 and decided for 3.4. - Training agent: enforce
execute_onlydelegations,governance_contexterror codes and planregionsincheck_governance#9075 / fix(training-agent): enforce execute_only, governance_context codes and plan regions #9080 (PR) — three rules from feat(governance): settle the campaign-governance rules that were contradictory or undefined #9006 that the reference agent did not enforce. - Governance: let check_governance name the plan owner when a plan_id is ambiguous (3.4) #9077 — naming the plan owner when a
plan_idis ambiguous, for 3.4. - feat(governance): reconcile delivery and plan adjustments #6305 (PR) — delivery and adjustment reconciliation; added the buyer-attributed
deliverytable row that A7's example now contradicts. - feat(governance): add budget periods to campaign governance plans #7965 (PR) / Proposal (3.3): budget periods on campaign governance plans #7956 — budget periods; reinforced the reject side of A1 on the task page without touching the specification sentence.
- Schema docs: governance report/audit schemas reject
account— author intuition collides withplan_idscoping #2776 / feat(schema): asset_type discriminator + governance plan_id scoping (#2776, #2777) #2795 —plan_idscoping (plan implies account); defined ownership, not the uniqueness namespace C1 asks for. - GDPR Art 22 / EU AI Act Annex III: block agent_full for regulated verticals #2310 / feat(governance)!: enforce Art 22 / Annex III as schema invariants (#2310) #2338 — the schema-level human-review invariant B2 proposes to relax from "required" to "const true".
- Document campaign governance audit trail: internal vs shareable views #3139 / docs(governance): audit-trail internal-vs-shareable views + Addie anonymous knowledge tools #3175 — the audit-trail page's origin; A2, A4 and A8 are drift between that page and later specification revisions.
- report_plan_outcome commits budget from buyer self-report with no token binding #5827 / fix(schema): require check_id on budget-committing report_plan_outcome outcomes (3.2 hardening) #5985 —
check_idbinding onreport_plan_outcome; resolved, listed above. - Security: governance revocation-list example is General JWS serialization, prose says flattened #8734 — governance revocation-list example was General JWS while the prose said flattened; found in the same read-through and filed separately. Fixed by docs(security): revocation-list example uses JWS flattened serialization #8781 and closed.
- governance: no
plan_hashhelper andmodel_dumpis not a JCS-safe preimage;sync_plansbudgetoneOf/ human-reviewallOfunenforced only on the low-levelcreate_tool_callerpath (7.0.2; partly open onmain) adcp-client-python#1852 — Python SDKplan_hashpreimage and schema defaults; the reproduced case behind thedefaultaddition in B2.
Activity
lukasz-pubx commentedon Nov 10, 2026
Update: working-group feedback so far, one reversal, one correction
Re-verified at
8114430. None of the governance docs, schemas, vectors or reference-agent files cited in this issue has changed sinceded86cd, so the line numbers above still hold. #8734 was fixed by #8781 in the meantime.The feedback below reached me outside this thread. I am recording it here so the resolutions sit in one place; anyone who gave it should correct me if I have it wrong.
VALIDATION_ERROR. The previous plan stays in force, so the campaign keeps running. Reducing spend that is already committed is settled with the seller, not through a plan re-sync.deniedverdict to the error, so that a rejected attempt by an unapproved seller appears in the audit log.PERMISSION_DENIEDwhen another principal reuses the id.(owner principal, seller agent)as a starting point, with an open question: does the seller belong in the key, given what the trailing-window limits are meant to protect?A4 as a
deniedverdict: three things the edit has to settleThe audit-trail example (
audit-trail.mdx:179-202) becomes the rule, and thePERMISSION_DENIEDrow attasks/check_governance.mdx:744narrows. That row currently covers three conditions in one sentence:PERMISSION_DENIED, with nocheck_idand no plan-scoped audit entry. An authenticated caller that fails theapproved_sellersevaluation receivesverdict: "denied"with aseller_compliancefinding and acheck_id. Without that floor, a party with no established identity can append entries to another principal's audit log.delegations, anddelegation_authorityis already listed as an evaluated category in the examples (audit-trail.mdx:153,:190;tasks/check_governance.mdx:496). Recommend the same treatment: authenticated caller outsidedelegationsgetsdeniedwith adelegation_authorityfinding. Either answer works, but the row should not leave the two cases split by accident.specification.mdx:215: "On an execution check, the authenticatedcallerMUST equal the audience preserved from the approved intent, and that seller identity is evaluated againstapproved_sellers." On an intent check the same paragraph saysapproved_sellersis evaluated against the target service, "never against that buyer". The example labels a seller's call"check_type": "intent"(audit-trail.mdx:186, repeated at:242,:265,:290); it should be an execution check. The rule should also say that all three seller failures are verdicts: an intent whose target is not inapproved_sellers, an execution check whose caller is not the preserved audience, and an execution check whose caller has since been removed fromapproved_sellers.Edits under this resolution:
tasks/check_governance.mdx:744(narrow the row to missing or unauthenticated identity),audit-trail.mdx:179-202and its repeats (execution check), and one sentence atspecification.mdx:215stating that these evaluations produce adeniedverdict.enums/error-code.json:215needs a read to confirm its description still fits the narrowed use.C5: a correction to this issue, then the seller question
Correction. C5 above describes the re-key as doc-only, "a definition of a term the MUST already depends on". That understates it.
specification.mdx:421:Dropping
account_idfrom the tuple is exactly the widening that sentence names. The re-key is still needed, because no governance schema has carriedaccount_idsince #6214 and an agent cannot key on a field it never receives. But:421has to change in the same edit, and the change is normative: aggregates get larger and more commits cross a threshold. Please read the Compatibility section with C5 moved from "doc-only on the surviving rule" to "normative behaviour change".Does the seller belong in the key? The section states what it protects at
specification.mdx:396:The thresholds it names are
reallocation_threshold,human_review_requiredtrigger points and registry-policy dollar floors. All three bound the buyer's own behaviour; none is a per-seller limit. With the seller in the key, the same $999,900 placed with 100 sellers at $9,999 each never aggregates. That is the argument:400already makes for sub-agents: "otherwise the delegation surface itself reopens the fragmentation hole".One fact that may explain the seller element:
:440says "Sellers and governance agents declare their aggregation window". A seller-side evaluator sees only its own commits, so a per-seller aggregate is the most a seller can enforce. Only the governance agent sees across sellers.Options:
(owner principal, seller agent).:421keeps its rule against silent widening, with a different example.(owner principal, seller agent)only. Smallest change from today's text. Cross-seller fragmentation stays open and should then be documented as out of scope.(owner principal, seller agent)as the MUST floor, owner-principal-only as a declared capability. Closest to:421as written, which already allows a broader scope with operator sign-off. The cost is that buyers must check one more capability before relying on the defence.Any of the three resolves the issue. What cannot survive is a MUST keyed on a field no schema carries.
Addendum to B2: the schema
defaultstatic/schemas/source/governance/sync-plans-request.json:293declares"default": falseonhuman_review_required. If B2 is accepted as recommended (omission accepted, explicitfalserejected on regulated plans), that annotation works against it in two ways:false, which thethenbranches reject. A valid request becomes an invalid one. Code generators do apply it; governance: noplan_hashhelper andmodel_dumpis not a JCS-safe preimage;sync_plansbudgetoneOf/ human-reviewallOfunenforced only on the low-levelcreate_tool_callerpath (7.0.2; partly open onmain) adcp-client-python#1852 has one reproduced case.specification.mdx:917: "Governance agents MUST hash the plan as-supplied; they MUST NOT synthesize omitted optionals to default values and MUST NOT drop explicit nulls." Vectors004aand004bpin omitted andnullto different hashes.Proposed: remove
"default": falseat:293and state in the description that an omitted flag means the governance agent derives it.budget.accounting_modeat:60also carries a default ("gross_commitment"). That one is semantically real and can stay, with one sentence added at:917that schemadefaultannotations are never applied to the hash preimage. Both are compatible:defaultis an annotation and changes no instance's validity.Minor, same area: vector
004b-human-review-explicit-null.jsonsuppliesnullfor a property typed"type": "boolean", so itsplan_as_suppliedis not schema-valid. A note in the vector that it exercises canonicalisation only would prevent a validating harness from rejecting it.Citations re-verified against
8114430with Claude Code assistance; re-verify at implementation time.lukasz-pubx commentedon Nov 10, 2026
Update: working-group call, 2026-11-10
Re-verified at
8114430; the cited files are unchanged.The working group reviewed the remaining questions on a call today. Every recommendation in this issue and in my previous comment was accepted, with one exception: C5 stays open. Recording the outcome here; anyone on the call should correct me if I have it wrong.
budget.totalor a periodamountbelow the committed amount is rejected withVALIDATION_ERRORand the previous plan stays in force. The sentence atspecification.mdx:620is replaced and the reference agent gains the missing sync-time check.approved_sellersevaluation receivesverdict: "denied"with aseller_compliancefinding and acheck_id, so the attempt is audit-logged. A caller whose identity is missing or cannot be authenticated still receivesPERMISSION_DENIEDwith no audit entry.delegationsreceivesdeniedwith adelegation_authorityfinding. The row attasks/check_governance.mdx:744narrows to missing or unauthenticated identity, and the audit-trail example becomes an execution check.requiredfrom boththenbranches and keepconst: true: omission is accepted and the agent sets the flag, an explicitfalsestays rejected. Remove"default": falseatsync-plans-request.json:293, and state atspecification.mdx:917that schemadefaultannotations are never applied to the hash preimage.plan_idis unique per owner principal; reuse by another principal isPERMISSION_DENIED.execute_onlydelegate acts only on bindings that already hold an approved intent check and may not open a new intent.conditions, execution checks returndenied.C5 remains open
The question is the trailing-window aggregation key at
specification.mdx:400, now that no governance schema carriesaccount_id. One refinement since my previous comment, which supersedes its option 1.Keep a three-part tuple. Option 1 proposed the owner principal alone for buyer-side thresholds. That loses what
account_iddid, which was to keep one buyer's clients apart. A buyer principal that syncs plans for several advertisers would pool their spend, and one advertiser's buys could trip another's human-review threshold. That is the wideningspecification.mdx:421names ("collapsing acrossaccount_idso two accounts share an aggregate"). Every plan already carries a requiredbrand(sync-plans-request.json:33-36, required at:422), so the tuple can keep its shape with a field that exists:Each commit is recorded under the full tuple, and each threshold states which dimensions it sums over. The section's "correct tuple" and "wider key tuple" language keeps working, and an auditor can re-derive both the per-seller and the cross-seller figure from the same records.
Two questions are left for the group:
brandthe right replacement foraccount_id? For portfolio plans the schema saysbrand"is the holding company or parent organization", so aggregation would happen at that level. That may be intended, and should be stated either way.reallocation_threshold,human_review_requiredtrigger points and registry-policy dollar floors. Summing within one seller leaves cross-seller fragmentation open, which would then need documenting as out of scope. Summing across sellers closes it, with limits defined per seller, such asbudget.per_seller_max_pct(sync-plans-request.json:63-66), still summed within one seller.Either answer is a normative change, and
:421needs a new example. C5 does not need to block the accepted items; it can be split into its own issue if that is easier to track.Citations re-verified against
8114430with Claude Code assistance; re-verify at implementation time.bokelley commentedon Nov 11, 2026
Thanks — this is exactly the sweep the governance pages needed. Pinning the tree and listing what's already fixed saves a lot of triage. I spot-checked against main today; A1 through A8, B1, B2 and C5 are all still present as you describe.
Proposed resolution, in three PRs so the uncontroversial part isn't held up by the decisions:
PR 1: errata, doc-only (the losing page simply changes). A2, A3, A5, A6, A7, A8, A9, B3 (mark the legacy
check_governanceresponse branch as 3.0-compat in its description) and C5 (re-key the aggregation tuple on the owner principal,(owner_principal, seller_agent), since #6214 removedaccount_id). In each of these, the specification or the schema already wins, so this is a correction and patch-eligible, and we'd backport it to 3.2.x. It can go up now.PR 2: normative decisions (doc + enum descriptions). Where the spec contradicts itself, these are the picks, and they match your recommendations:
budget.totalor a periodamountbelow committed spend is rejected withVALIDATION_ERRORand leaves the plan unchanged. The reference agent gets the missing sync-timebudget.totalcheck.PERMISSION_DENIED, evaluated against the target service that becomes the tokenaud(specification.mdx). The audit-trail example is rewritten to show the error.human_review_requiredis mode-independent. Audit mode "always returns approved" except for plans withhuman_review_required: true, which escalate in every mode.PR 3: schema. B2: drop
requiredfrom boththenbranches insync-plans-request.jsonand keepconst: true. Explicitfalseis still rejected, an omitted flag is accepted, and the agent sets it. The prose changes from "overrides" to "rejects" a caller-suppliedfalse, andknown-limitations.mdxnames the field the schema actually constrains. This widens what the schema accepts, so it goes to 3.3/main, not a 3.2.x patch. C4.1 and C4.2 ship asx-adcp-validationannotations now, and the schema tightening goes on the 4.0 list in #8756.B2 also settles part of adcp-client-python#1852 (whether an omitted flag is a valid request), so we'll link the two.
If you'd like to take PR 1, go ahead. PRs 2 and 3 can follow once there's no objection here to the picks above.
lukasz-pubx commentedon Nov 11, 2026
Thanks @bokelley, the three-PR split works for me, and I'll take PR 1 with the scope you listed: A2, A3, A5, A6, A7, A8, A9, B3 (legacy branch marked 3.0-compat in its description) and C5.
C5: accepting
(owner_principal, seller_agent). I want to record this explicitly, because the working group left C5 open on the 2026-11-10 call and I had since suggested a three-part key withbrandin the third slot. I'm withdrawing that suggestion. No governance schema carriesaccount_idatmainor atv3.2.8, so no agent can key on it today, and re-keying on the owner principal describes what a conformant agent can already do. That also means my earlier note calling the change normative overstated it; errata is a fair classification. In PR 1 the edit coversspecification.mdx:400and:429, and:421, which currently gives "collapsing acrossaccount_id" as its example of a widened key and needs a different example. Delegated sub-agents keep folding into the delegating principal as:400already says. The question the group raised on the call, whether buyer-side thresholds should also aggregate across sellers, is separate from this correction and is not blocked by it. If anyone from the call sees C5 differently, this thread is the place to say so before PR 1 merges.One objection to the PR 2 picks: A4. The pick above is my original recommendation, but the working group decided the other way on the call, and the issue description was updated on 2026-11-10 to match:
approved_sellersevaluation getsverdict: "denied"with aseller_compliancefinding and acheck_id, so the attempt is in the audit log. The group's reason was that a rejected attempt by an unapproved seller has to be visible to auditors.delegation_authorityfinding.PERMISSION_DENIEDstays for a caller that is unauthenticated or whose authenticated identity does not match the declaredcaller.The reference agent already returns the finding for an unapproved seller (
server/src/training-agent/governance-handlers.ts:2072-2083), so the verdict shape is the smaller change there. The A4 section of the description lists the edits and the two gates in the reference agent that would change.One addition for PR 3: the
defaultonhuman_review_required. The group also accepted removing"default": falseatsync-plans-request.json:293as part of B2. Once omission is valid, a consumer that applies the schema default turns a valid omitted field into an explicitfalse, which thethenbranches reject. That is the part of adcontextprotocol/adcp-client-python#1852 this issue settles. Details are in the B2 section of the description.The other picks match what the group agreed.
Checked against
ea017e1; the governance docs, schemas and reference-agent handlers are unchanged since the description was last verified.lukasz-pubx commentedon Nov 11, 2026
A correction to my previous comment on C5, found while preparing PR 1.
I wrote that no governance schema carries
account_idatmainorv3.2.8, "so no agent can key on it today", and that errata was therefore a fair classification. The first half is true but the inference is not. No governance schema has ever carried anaccount_idfield, from 3.0.0 onward. The third element of the key was always derived: the 3.0 and 3.1 request schemas said "the governance agent resolves account from the plan", andget-plan-audit-logs-request.json:21onmainstill says "Plans uniquely scope account and operator … the governance agent resolves account from each plan". What #6214 changed was that wording incheck-governance-request.jsonandreport-plan-outcome-request.json, which now describe the plan as owned by the authenticated buyer principal.So an agent can key on a derived account today, and one that does satisfies the conformance row at
specification.mdx:429-436now and would not after the re-key to(owner_principal, seller_agent). That makes C5 a behaviour change for such agents, not only a correction.I still think
(owner_principal, seller_agent)is the right key under the owner-principal model. The open point is only whether it belongs in the patch-eligible PR 1 or in PR 2. PR 1 will carry it as scoped, with this spelled out in the description, so that it can be moved without affecting the rest.lukasz-pubx commentedon Nov 12, 2026
PR 1 is up as #8931, with the scope from the split above: A2, A3, A5 to A9, B3 and C5. All checks pass and the IPR signature is recorded. The description of this issue is updated to match, including the corrected history for C5.
@bokelley, three points from this thread are still open and need a decision:
(owner_principal, seller_agent)belongs in the patch-eligible PR 1 or in PR 2, given that it changes behaviour for an agent that keys on an account derived from the plan. The PR is written so that C5 can move without affecting the rest.PERMISSION_DENIEDfor an unapproved seller. The working group decided on adeniedverdict with aseller_compliancefinding, so that the attempt is in the audit log. PR 2 depends on which of the two stands."default": falseatsync-plans-request.json:293goes into PR 3 with the rest of B2.bokelley commentedon Nov 13, 2026
@lukasz-pubx thanks, and sorry for the lag. On your three points:
approved_sellersgetsverdict: "denied"with aseller_compliancefinding and acheck_id. Delegation failures get the same, with adelegation_authorityfinding.PERMISSION_DENIEDstays for a caller that is unauthenticated or whose identity doesn't matchcaller. PR 2 should be written that way."default": falseatsync-plans-request.json:293goes into PR 3.PRs 2 and 3 target 3.3. If they're up by Monday they can make rc.0; otherwise they go in as RC fixes. #8931 is approved and merging now.
docs(governance): align campaign-governance pages with the specificat…
lukasz-pubx commentedon Nov 14, 2026
@bokelley thanks, those three answers are applied. PRs 2 and 3 are up against
main, ahead of the Monday cut for rc.0. They are independent of each other.defaultremoval, C4.1, C4.2.PRs 2 and 3 touch two adjacent rows of the
sync_planserror table, so whichever merges second needs a small rebase.PR 2 departs from the wording accepted on the 2026-11-10 call in three places. In each, the accepted wording conflicted with a rule that is already in the specification, and the PR follows the existing rule. These are the points to confirm or overrule; the PR description quotes the rule for each.
plan_id. Rejecting a second principal withPERMISSION_DENIEDwould reveal that a plan ID exists, which thePLAN_NOT_FOUNDdefinition forbids, and the reference agent has namespaced plans per owner since feat(governance): define cross-role enforcement #6214. The issue did not mention either when it proposed C1.execute_onlydelegate run execution checks, because only the seller that is the token audience can make that call. It keeps the definition of a pre-approved action and the prohibition.Found while preparing these, and not fixed, because each needs a rule that does not exist yet. A recommendation is given where the existing text points one way.
sync_plans. Nothing says whether one invalid plan rejects the whole request. The response schema allows a per-planstatus: "error", and the reference agent rejects the whole request and never emits it. Recommend all-or-nothing, since the response has no per-plan error carrier.consultation_contextacross repeatedconditions. Nothing says the handle stays the same. C4.4 now defines "the same action" by it, so an agent that mints a new handle each time never reaches the three re-call limit. Recommend that the agent returns the same handle for the whole negotiation, as the reference agent does.budget.totaland period amounts. A re-sync can still cutbudget.allocations.<type>.amountbelow what is committed to that type, or changebudget.currencywhile spend is committed. Recommend the sameVALIDATION_ERRORfor both.approved. The same section also speaks of a "human_review_requiredtrigger at $10,000", though that field is a boolean and no plan field carries a dollar trigger for human review.governance/policy-registry.mdxlists 14 policies that have no file understatic/registry/policies, includingus_coppaandalcohol_advertising, and does not list 33 that do. C4.3 makes an unresolvable ID an error, so it now matters which set is the registry.regionsanddelegations[].authorityand reads neither, and it does not check flight order or policy ID uniqueness. These follow from existing text and from PRs 2 and 3, and are not in any of the three PRs.images/concepts/budget-commitment-phases.pngshows budget as "reserved" between check and outcome. PR 4 adds a sentence under it; the image needs redrawing.Checked against
01abd19.lukasz-pubx commentedon Nov 14, 2026
@bokelley everything in this issue is now either merged or in an open pull request, and the description above is updated to match.
human_overridein thesync_plansschema, names all five human-review triggers where pages named three, and corrects stale statements on the overview, FAQ, trust, known-limitations and audit-trail pages. In the reference agent,check_governancenow returnsPLAN_NOT_FOUNDfor a plan that is unknown or not accessible to the caller. PR 4 sits on top of PRs 2 and 3, so only commit1b6616cis its own change. It is rebased and marked ready once both have merged.What waits on a decision.
One point that affects merge order. PRs 3 and 4 each add a test file to the single-line
test:schemasscript inpackage.json. They conflict whenever another pull request that adds a schema test merges first, which has happened twice today. Each time the branch takes the list frommainand re-adds its own tests, so the merge commits on those branches contain nothing else.Checked against
bbf10ef.fix(governance): accept an omitted human_review_required and state tw…
bokelley commentedon Nov 16, 2026
Decision record update (2026-11-15): two of the picks are revised to match the uniform-response rule. The review on #9006 found that both conflicted with it.
PLAN_NOT_FOUNDmust be returned uniformly for anyplan_idthe calling account can't access, never telling "exists but unauthorized" apart from "does not exist" (error-code.json). A resolve-then-deny path must not write tenant audit rows (error-handling.mdx, uniform-response rule). As recorded, both picks would have let a caller with no access learn that a plan exists.delegationsgetsdeniedwith adelegation_authorityfinding.PLAN_NOT_FOUND, the same response as for an unknown plan, with no audit row. A caller that can see the plan but falls outsidedelegationsgetsdeniedwith adelegation_authorityfinding, audit-logged.plan_iduniqueness (revised).plan_idis unique per owner principal, and another principal reusing an id getsPERMISSION_DENIED.plan_idis scoped per owner principal. Another principal'ssync_planswith the same id creates or updates that principal's own plan.PERMISSION_DENIEDclause is dropped: answering "in use" for one id and success for another leaks existence.Unchanged:
deniedwith aseller_compliancefinding in every mode.governance-mode.jsonand the reference agent change to match.execute_onlydelegate that would create a new binding or increase committed spend."falseis rejected withVALIDATION_ERROR.Credit to @KonstantinMirin for catching the conflict and @lukasz-pubx for the original reading. #9006 carries the alignment.
fix(governance): align A4, C1 and C2 with the reviewed decisions
fix(governance): correct stale campaign-governance pages and schema d…
feat(governance): settle the campaign-governance rules that were cont…
fix(governance): correct stale campaign-governance pages and schema d…
fix(governance): correct stale campaign-governance pages and schema d…
lukasz-pubx commentedon Nov 18, 2026
All four pull requests for this issue are merged, so I am closing it. The description above is updated to the final state, with a result under each acceptance criterion, checked at
61a1638.What merged
main, due in the next 3.3 release candidate. It differs from the wording accepted on the 2026-11-10 call for A4, C1 and C2, as the decision record and the notes under those items explain.main, due in the next 3.3 release candidate.What this issue hands on
plan_idsdescription onget_plan_audit_logs. The fourth acceptance criterion asked for that split.human_overrideon thesync_plansplan item and state the human-review downgrade rule #9068 and feat(governance): declare human_override and state the human-review downgrade rule #9074:human_overrideon the plan item, decided for 3.4.execute_onlydelegations,governance_contexterror codes and planregionsincheck_governance#9075 and fix(training-agent): enforce execute_only, governance_context codes and plan regions #9080: three rules from feat(governance): settle the campaign-governance rules that were contradictory or undefined #9006 that the reference agent did not enforce.plan_idis ambiguous, for 3.4.One gap that no issue covers yet
No compliance storyboard grades the rules that #9006 settled for
check_governance. At61a1638, nothing understatic/compliance/sourcementionsPLAN_NOT_FOUND,seller_complianceordelegation_authority, andapproved_sellersanddelegationsappear only in a plan-hash vector. This issue said that a scenario for A4 was worth adding, and that still holds for thedeniedverdict in every mode and for thePLAN_NOT_FOUNDrule.Thanks @bokelley and @KonstantinMirin for the reviews and the decisions.