> ## Documentation Index > Fetch the complete documentation index at: https://docs.adcontextprotocol.org/llms.txt > Use this file to discover all available pages before exploring further. # check_governance > check_governance is the universal validation gate in AdCP — orchestrators and sellers call it before executing any campaign action. # check\_governance Universal governance check for campaign actions. Both the orchestrator (buyer-side) and the seller call this task -- the `binding` field discriminates the commitment level: | Binding | Who calls | Purpose | Key fields | | ----------- | ------------ | --------------------------------------------------------------------------------------------------------------------------------- | -------------------------------------------------------- | | `proposed` | Orchestrator | Advisory check before sending to a seller. No budget committed. | `tool`, `payload`, `governance_context` | | `committed` | Seller | Binding check before executing. Validates planned delivery against the plan. Budget is committed later via `report_plan_outcome`. | `media_buy_id`, `buyer_ref`, `phase`, `planned_delivery` | The governance agent maintains all state. Callers do not chain check IDs or track conversation history -- they post the action, and the governance agent correlates by `plan_id` + `buyer_campaign_ref`. ## Binding levels ### Proposed (orchestrator) The orchestrator calls with `binding: "proposed"` before sending a tool call to a seller. This is an advisory check -- no budget is committed. The governance agent evaluates the intended `tool` and `payload` against the campaign plan. 1. Orchestrator decides to call a seller tool (e.g., `create_media_buy`) 2. Orchestrator calls `check_governance` with the tool name and full payload 3. If `approved`, orchestrator sends the tool call to the seller 4. If `denied`, orchestrator does not send the tool call 5. If `conditions`, orchestrator adjusts the payload and re-calls `check_governance` 6. If `escalated`, orchestrator halts pending human review ### Committed (seller) The seller calls with `binding: "committed"` when processing a request on an account that has `governance_agents` (set during [`sync_accounts`](/dist/docs/3.0.0-rc.2/accounts/tasks/sync_accounts)). This is a binding check -- budget will be committed if approved. The seller presents the authentication credentials from the agent's configuration. Committed checks cover the full media buy lifecycle through three phases: | Phase | When | What's checked | | -------------- | ------------------------------------ | --------------------------------------------------- | | `purchase` | Before confirming `create_media_buy` | Budget, geo, channels, flight dates, policies | | `modification` | Before confirming `update_media_buy` | Change magnitude, reallocation, new parameters | | `delivery` | Periodically during delivery | Pacing, spend rate, geo drift, channel distribution | Sellers can adopt committed governance checks incrementally: * **Level 1: Purchase only** -- One call per `create_media_buy`. The minimum viable integration. * **Level 2: + Modification** -- One call per `update_media_buy`. * **Level 3: + Delivery reporting** -- Periodic calls during active delivery. ## Status values | Status | Meaning | Caller action | | ------------ | --------------------------------------- | --------------------------------------------------------------------------- | | `approved` | Proceed as planned. | Act before `expires_at` or re-call. | | `denied` | Do not proceed. | Return error to upstream caller. | | `conditions` | Approved if caller accepts adjustments. | Apply conditions, then re-call `check_governance` with adjusted parameters. | | `escalated` | Halted pending human review. | Wait for human resolution. | ### Expiration `expires_at` is present when the status is `approved` or `conditions`. A lapsed approval is no approval -- the caller must re-call `check_governance` before proceeding. ### Conditions When the status is `conditions`, the caller MUST re-call `check_governance` with adjusted parameters before proceeding. Conditions with a `required_value` are machine-actionable -- the caller can programmatically apply the value. Conditions without a `required_value` are advisory -- the caller should interpret the `reason` and adjust accordingly. Governance agents SHOULD return `denied` (not `conditions`) after 3 unsuccessful re-calls for the same action. This prevents infinite negotiation loops, particularly for seller-side checks where the seller has no visibility into the campaign plan. ### Escalation When the status is `escalated`, the action is halted. The `escalation` object provides the reason, severity, and whether human approval is required. The caller must not proceed until the escalation is resolved. For `committed` checks (seller-side), `escalated` is operationally equivalent to `denied` -- the seller cannot hold a request indefinitely while waiting for human review on the buyer side. Sellers SHOULD treat `escalated` as `denied`, return an error to the orchestrator, and let the orchestrator handle the human-in-the-loop flow. After the escalation is resolved, the orchestrator re-initiates the media buy and the seller gets a new request. ### Linking to outcomes The response includes a `check_id`. Use this in [`report_plan_outcome`](./report_plan_outcome) to link outcomes to the governance check that authorized them. ## When the governance agent is unavailable If the governance agent is configured and the caller cannot reach it (timeout, network error), the caller MUST NOT proceed. Governance is a gate -- when the gate is unreachable, the default is halt. The caller SHOULD retry with backoff and report the failure upstream. ## Delivery cadence The presence of `next_check` in a response is the signal that the governance agent expects ongoing delivery reporting. The seller SHOULD call no later than the `next_check` time. The governance agent MAY treat a missed deadline as a finding on the next delivery check. ## Request ### Proposed (orchestrator checking before sending to seller) ```json theme={null} { "tool": "check_governance", "arguments": { "plan_id": "plan_q1_2026_launch", "buyer_campaign_ref": "q1-2026-spring-launch", "binding": "proposed", "caller": "https://orchestrator.example.com", "tool": "create_media_buy", "payload": { "buyer_ref": "q1-launch-pinnacle-001", "product_id": "premium_video_300k", "budget": 150000, "currency": "USD", "geo": { "countries": ["US"] }, "channels": ["olv"], "flight": { "start": "2026-03-15T00:00:00Z", "end": "2026-06-15T00:00:00Z" } }, "governance_context": { "total_budget": { "amount": 150000, "currency": "USD" }, "countries": ["US"], "channels": ["olv"], "flight": { "start": "2026-03-15T00:00:00Z", "end": "2026-06-15T00:00:00Z" } } } } ``` When `governance_context` is present, the governance agent uses it for plan validation instead of parsing tool-specific payload structures. The caller extracts governance-relevant fields into this canonical shape so the governance agent doesn't need to understand every tool's payload format. ### Committed -- purchase ```json theme={null} { "tool": "check_governance", "arguments": { "plan_id": "plan_q1_2026_launch", "buyer_campaign_ref": "q1-2026-spring-launch", "binding": "committed", "caller": "https://seller.example.com", "media_buy_id": "mb_seller_456", "buyer_ref": "q1-launch-pinnacle-001", "phase": "purchase", "planned_delivery": { "geo": { "countries": ["US"] }, "channels": ["olv"], "start_time": "2026-03-15T00:00:00Z", "end_time": "2026-06-15T00:00:00Z", "total_budget": 150000, "currency": "USD", "frequency_cap": { "max_impressions": 3, "per": "user", "window": { "interval": 1, "unit": "days" } }, "audience_summary": "Adults 25-54, US, premium video inventory", "enforced_policies": ["us_coppa"] } } } ``` ### Committed -- modification ```json theme={null} { "tool": "check_governance", "arguments": { "plan_id": "plan_q1_2026_launch", "buyer_campaign_ref": "q1-2026-spring-launch", "binding": "committed", "caller": "https://seller.example.com", "media_buy_id": "mb_seller_456", "buyer_ref": "q1-launch-pinnacle-001", "phase": "modification", "modification_summary": "Budget increase from $150,000 to $200,000 and flight extension to 2026-07-15.", "planned_delivery": { "geo": { "countries": ["US"] }, "channels": ["olv"], "start_time": "2026-03-15T00:00:00Z", "end_time": "2026-07-15T00:00:00Z", "total_budget": 200000, "currency": "USD", "frequency_cap": { "max_impressions": 3, "per": "user", "window": { "interval": 1, "unit": "days" } }, "audience_summary": "Adults 25-54, US, premium video inventory", "enforced_policies": ["us_coppa"] } } } ``` ### Committed -- delivery ```json theme={null} { "tool": "check_governance", "arguments": { "plan_id": "plan_q1_2026_launch", "buyer_campaign_ref": "q1-2026-spring-launch", "binding": "committed", "caller": "https://seller.example.com", "media_buy_id": "mb_seller_456", "buyer_ref": "q1-launch-pinnacle-001", "phase": "delivery", "planned_delivery": { "geo": { "countries": ["US"] }, "channels": ["olv"], "start_time": "2026-03-15T00:00:00Z", "end_time": "2026-06-15T00:00:00Z", "total_budget": 150000, "currency": "USD", "frequency_cap": { "max_impressions": 3, "per": "user", "window": { "interval": 1, "unit": "days" } }, "audience_summary": "Adults 25-54, US, premium video inventory", "enforced_policies": ["us_coppa"] }, "delivery_metrics": { "reporting_period": { "start": "2026-03-15T00:00:00Z", "end": "2026-03-22T00:00:00Z" }, "spend": 12500, "cumulative_spend": 12500, "impressions": 850000, "cumulative_impressions": 850000, "geo_distribution": { "US": 100 }, "channel_distribution": { "olv": 100 }, "pacing": "on_track" } } } ``` ## Response ### approved (proposed) ```json theme={null} { "check_id": "chk_001", "status": "approved", "binding": "proposed", "mode": "enforce", "plan_id": "plan_q1_2026_launch", "buyer_campaign_ref": "q1-2026-spring-launch", "explanation": "Proposed create_media_buy is within plan parameters. Budget: $150,000 of $500,000 plan total. Geo: US (within plan). Channel: OLV (within 40-70% target range).", "categories_evaluated": ["budget_authority", "geo_compliance", "channel_compliance", "flight_compliance", "delegation_authority"], "policies_evaluated": ["us_coppa", "alcohol_advertising"], "expires_at": "2026-03-15T01:00:00Z" } ``` The orchestrator proceeds to send the `create_media_buy` to the seller before `expires_at`. ### approved (committed purchase with delivery opt-in) ```json theme={null} { "check_id": "chk_002", "status": "approved", "binding": "committed", "mode": "enforce", "plan_id": "plan_q1_2026_launch", "buyer_campaign_ref": "q1-2026-spring-launch", "explanation": "Planned delivery is within plan parameters. Budget: $150,000 of $500,000 plan total. Geo: US (within plan). Channel: OLV (within 40-70% target range).", "expires_at": "2026-03-15T01:00:00Z", "next_check": "2026-03-22T00:00:00Z" } ``` The seller proceeds with the media buy. The presence of `next_check` signals that the governance agent expects delivery reporting starting at that time. ### approved (committed delivery) ```json theme={null} { "check_id": "chk_003", "status": "approved", "binding": "committed", "mode": "enforce", "plan_id": "plan_q1_2026_launch", "buyer_campaign_ref": "q1-2026-spring-launch", "explanation": "Delivery on track. Week 1 spend: $12,500 of $150,000 (8.3%). Pacing is on target for 13-week flight. Geo and channel distribution match plan parameters.", "next_check": "2026-03-29T00:00:00Z" } ``` The seller continues delivery and schedules the next governance check for `next_check`. ### denied (proposed) ```json theme={null} { "check_id": "chk_004", "status": "denied", "binding": "proposed", "plan_id": "plan_q1_2026_launch", "buyer_campaign_ref": "q1-2026-spring-launch", "explanation": "Proposed media buy targets CA (Canada) which is not within the plan's geography.", "findings": [ { "category_id": "strategic_alignment", "severity": "critical", "explanation": "Geo targeting includes CA but plan only covers US.", "details": { "plan_countries": ["US"], "payload_countries": ["US", "CA"] } } ] } ``` The orchestrator MUST NOT send the tool call to the seller. ### denied (committed delivery -- geo drift) ```json theme={null} { "check_id": "chk_005", "status": "denied", "binding": "committed", "plan_id": "plan_q1_2026_launch", "buyer_campaign_ref": "q1-2026-spring-launch", "explanation": "Delivery has drifted outside plan parameters. 12% of impressions delivered in CA (Canada) which is not within the plan's geography.", "findings": [ { "category_id": "strategic_alignment", "severity": "critical", "confidence": 0.98, "explanation": "Geo distribution shows 12% delivery in CA, but plan only covers US.", "details": { "plan_countries": ["US"], "actual_distribution": { "US": 88, "CA": 12 } } } ] } ``` The seller MUST pause delivery immediately and correct the geo targeting before resuming. ### conditions (committed purchase) ```json theme={null} { "check_id": "chk_006", "status": "conditions", "binding": "committed", "plan_id": "plan_q1_2026_launch", "buyer_campaign_ref": "q1-2026-spring-launch", "explanation": "Budget approved but frequency cap must be applied per brand policy.", "conditions": [ { "field": "planned_delivery.frequency_cap", "required_value": { "max_impressions": 5, "per": "user", "window": { "interval": 1, "unit": "days" } }, "reason": "Brand policy requires daily frequency cap of 5 or fewer impressions per user." } ], "expires_at": "2026-03-15T01:00:00Z" } ``` The seller MUST adjust its planned delivery, then re-call `check_governance` with the updated parameters before proceeding. ### conditions (committed delivery -- overpacing) ```json theme={null} { "check_id": "chk_007", "status": "conditions", "binding": "committed", "plan_id": "plan_q1_2026_launch", "buyer_campaign_ref": "q1-2026-spring-launch", "explanation": "Delivery is pacing 40% ahead of schedule. Cumulative spend of $42,000 after 2 weeks exceeds expected $23,000 for this point in the flight.", "conditions": [ { "field": "pacing", "reason": "Reduce daily spend rate to align with the planned flight duration. At current pace, budget will be exhausted by week 7 of 13." } ], "next_check": "2026-03-31T00:00:00Z" } ``` The seller MUST adjust pacing and re-call `check_governance` immediately. The `next_check` is set closer than normal so the governance agent can verify the correction. ### escalated ```json theme={null} { "check_id": "chk_008", "status": "escalated", "binding": "committed", "plan_id": "plan_q1_2026_launch", "buyer_campaign_ref": "q1-2026-spring-launch", "explanation": "Budget reallocation of $75,000 exceeds the plan's reallocation threshold of $25,000. Human approval required.", "findings": [ { "category_id": "budget_authority", "severity": "critical", "explanation": "Reallocation amount exceeds plan threshold.", "details": { "reallocation_amount": 75000, "threshold": 25000 } } ], "escalation": { "reason": "Budget reallocation exceeds plan threshold. A human stakeholder must approve before the seller can proceed.", "severity": "critical", "requires_human": true, "approval_tier": "director" } } ``` The caller MUST NOT proceed. The action is halted until a human resolves the escalation. ## Fields ### Request | Field | Type | Required | Description | | ---------------------- | ------------ | --------- | --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | | `plan_id` | string | Yes | Campaign governance plan identifier. | | `buyer_campaign_ref` | string | Yes | Buyer's campaign identifier. The governance agent tracks state per campaign within a plan. | | `binding` | enum | Yes | `proposed` (advisory, no budget committed) or `committed` (binding, budget committed if approved). | | `caller` | string (URI) | Yes | URL of the agent making the request (orchestrator for proposed, seller for committed). | | `tool` | string | Proposed | The AdCP tool being checked. Required for `proposed` checks. | | `payload` | object | Proposed | Full tool arguments as they would be sent to the seller. Required for `proposed` checks. | | `governance_context` | object | No | Normalized governance-relevant fields extracted from the payload. When present, the governance agent SHOULD use these fields for plan validation instead of parsing the payload directly. See the [governance context schema](https://adcontextprotocol.org/schemas/latest/governance/governance-context.json). | | `media_buy_id` | string | Committed | Seller's media buy identifier. Required for `committed` checks. | | `buyer_ref` | string | No | Buyer's reference identifier from the `create_media_buy` request. | | `phase` | enum | Committed | `purchase`, `modification`, or `delivery`. Defaults to `purchase`. Required for `committed` checks. | | `planned_delivery` | object | Committed | What will actually be delivered. Required for `committed` checks. See [planned delivery](/dist/docs/3.0.0-rc.2/governance/campaign/specification#integration-with-create_media_buy). | | `delivery_metrics` | object | Delivery | Actual delivery performance data. Required when `phase` is `delivery`. | | `modification_summary` | string | No | Human-readable summary of what changed. SHOULD be present for `modification` phase. | ### Delivery metrics | Field | Type | Description | | ------------------------ | ------- | -------------------------------------------------------------------------------------------- | | `reporting_period` | object | Reporting window with `start` and `end` timestamps (ISO 8601). Required. | | `spend` | number | Spend during the reporting period. | | `cumulative_spend` | number | Total spend since the media buy started. | | `impressions` | integer | Impressions during the reporting period. | | `cumulative_impressions` | integer | Total impressions since the media buy started. | | `geo_distribution` | object | Actual geographic distribution. Keys are ISO 3166-1 alpha-2 codes, values are percentages. | | `channel_distribution` | object | Actual channel distribution. Keys are values from the channels enum, values are percentages. | | `pacing` | enum | `ahead`, `on_track`, or `behind`. | ### Response | Field | Type | Description | | ---------------------- | --------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | | `check_id` | string | Unique identifier for this governance check. Use in `report_plan_outcome` to link outcomes. | | `status` | enum | `approved`, `denied`, `conditions`, or `escalated`. | | `binding` | enum | Echoed from request. Confirms the governance agent understood the commitment level. | | `plan_id` | string | Echoed from request. | | `buyer_campaign_ref` | string | Echoed from request. | | `explanation` | string | Human-readable explanation of the decision. | | `findings` | array | Per-category issues found. Present when status is `denied`, `conditions`, or `escalated`. MAY also be present on `approved` for advisory findings. Each finding has `category_id`, `severity`, `explanation`, and optionally `policy_id`, `details`, `confidence` (0-1), and `uncertainty_reason`. | | `conditions` | array | Present when status is `conditions`. Adjustments the caller must make before re-calling. | | `mode` | enum | The governance mode under which this check was evaluated (`audit`, `advisory`, or `enforce`). Present so audit trails can distinguish advisory denials from enforced denials. | | `categories_evaluated` | string\[] | Governance categories evaluated during this check (e.g., `budget_authority`, `geo_compliance`, `channel_compliance`). Useful for verifying which validations ran. | | `policies_evaluated` | string\[] | Registry policy IDs evaluated during this check. | | `escalation` | object | Present when status is `escalated`. Contains `reason`, `severity`, `requires_human`, and optionally `approval_tier` (the organizational role required to resolve, e.g., `"manager"`, `"director"`, `"legal"`). | | `expires_at` | string | Present when status is `approved` or `conditions`. The caller must act before this time or re-call. A lapsed approval is no approval. | | `next_check` | string | When the seller should next call `check_governance` with delivery metrics. Present when the governance agent expects ongoing delivery reporting. | ## Error codes | Code | Recovery | Description | | ----------------------- | ----------- | ----------------------------------------------------------------- | | `PLAN_NOT_FOUND` | correctable | No plan with this ID. The buyer may not have synced the plan yet. | | `CAMPAIGN_SUSPENDED` | correctable | Campaign governance is suspended pending human review. | | `SELLER_NOT_RECOGNIZED` | correctable | The caller URL is not in the plan's `approved_sellers` list. | ## Related tasks * [`sync_plans`](./sync_plans) -- The plan this governance check validates against * [`report_plan_outcome`](./report_plan_outcome) -- Report what happened after the action was confirmed * [`get_plan_audit_logs`](./get_plan_audit_logs) -- View plan state and audit trail