> ## Documentation Index
> Fetch the complete documentation index at: https://docs.gloo.com/llms.txt
> Use this file to discover all available pages before exploring further.

# 2026-10-22 — Forge updates

> PATCH /api/v2/agents/update and forge_update_agent need switches:use to change an agent's status, and record the same control audit entry as the Console. Chat replies read the agent's stored autonomy rung, and a reply that governance blocks shows its error in the personal agent chat. GET /api/v2/compliance/export/governance records its evidence-access refusal and answers its decisionId, like the recorded-evidence reads. Agent grant changes, accountability repairs and stop controls in the Console now decide against the agent itself: its home org unit, and whether it is someone's Personal Agent. API keys, External Apps and Personal keys holding grants:manage can give and revoke Trust Fabric roles, under the same giving limit as the Console, measured on the calling credential. Inviting a member gives Builder and Auditor through the same giving path as giving a role, and a re-invite no longer restores a revoked grant. Credentials holding grants:manage at the platform scope can invite a user, under the same giving limit as giving a role, and revoke an on-behalf-of grant. The Knowledge API and MCP add a record collection create, a subject collection list, and a collection filter on the case list. Verifications, grades, steward changes, deletes and review decisions made through the API record who decided them. A synced record opened from its collection shows its fields, meaning search marks artifacts waiting for review, and collection counts say what they count. Knowledge cases with synced records list over MCP, the record tools take their inputs, and a new read shows what a namespace holds. Two new Knowledge API routes and MCP tools give a machine credential the Console's source discovery reads. A Personal key reviews, approves or rejects a source's held diff and shrink-guard deletions over HTTP and MCP. Reading or annotating a record you may not read now answers 404, exactly as an unknown record. Knowledge searches and capped lists mark partial answers, history reads authored records, and the learning feed leaves records out. Seven governance routes and MCP tools create, edit, enable, disable and remove trust policies and create, update and remove approval policies, at policies:manage. Credentials holding apikeys:manage at the platform scope can save the MCP server configuration; global instructions are capped at 4,000 characters and every save is audited. forge_get_current_actor answers a summary by default and pages its operations; forge_get_my_authority states the narrowing scopes once; list tools keep their page meta in text. listPolicies can return approver limits, getDoorSwitchBoard reads the door switches, getDenialsByPersonReport counts blocked decisions by person, and a Personal key can read the agent access report. Trust Fabric recorded-decision reads gain opt-in decision fields and correlation, runId and failed-at-a-check filters, gate pass tallies and a gate-path registry route. Machines can read who holds access, a holder's authority, the Access check, a company's access, on-behalf-of grants and their own grants; people's grants are listed without who gave them. Trust Fabric Roles counts say where each role was given, and a role with no grant there shows None instead of 0 holders. A turn's Context section lists each search that was limited to, or measured for, the person the agent answered.

**2026-10-22**

Agent status changes through the API need switches:use.

* **Breaking:** a `PATCH /api/v2/agents/update` (or `forge_update_agent`) that carries `status` now also needs `switches:use` given at the platform, the permission the Console's pause, resume and terminate controls need. Without it the answer is `403 forbidden` naming `switches:use`, and nothing is written. Other fields still need only `agents:write`. See [Who may write which agent](https://docs.gloo.com/forge/reference/http-api/agents#who-may-write-which-agent).
* `paused` is now an update status. Each status change records the same control audit entry the Console records (agent paused, resumed or terminated), naming your App and who gave it `switches:use`.
* An agent never moves back to `draft` through the API (`409 conflict`). Archiving (`DELETE /api/v2/agents/delete`) still needs only `agents:write`.

**2026-10-22**

Chat: agents reply again; a blocked reply shows its error.

* Agents reply in chat again. The chat check now reads each agent's stored autonomy rung. Before, it saw no rung and refused every reply. An agent at the **assistive** rung, or with no rung, is still refused.
* In personal agent chat, a reply that governance blocks now shows its error, what to do next and the error ID. Before, the chat showed **Thinking…** and then nothing. The error code sits under **Technical details**.

**2026-10-22**

Governance export refusals carry a Reference.

* `GET /api/v2/compliance/export/governance` used to answer a credential lacking the recorded-evidence bundle (`grants:read`, `policies:read` and `audit:read` at its acting organization) with a bare `403` and no record. It now records the refusal and answers `403 forbidden` with a `decisionId`, the same refusal and message as [listEvidence](https://docs.gloo.com/forge/reference/http-api/governance/listEvidence.md). If Forge cannot record the refusal, the answer is `503`. See [Export governance decision records](https://docs.gloo.com/forge/reference/http-api/compliance/governance.md).

**2026-10-22**

Trust Fabric: Console agent doors check the agent's home and Personal Agents.

* Giving or removing an agent's tools, tool sets, skills, skill sets or procedures from the Console now reaches only an agent you may change: someone else's Personal Agent is answered as not found unless you are its owner or a Platform admin, and an unknown agent is not found.
* [Accountability repairs](https://docs.gloo.com/forge/console/trust-fabric/agent-trust.md) (assign owner, acknowledge review, attest identity) are decided at the agent's home org unit, and the Console still offers them to holders of platform `agents:manage`. A Personal Agent has no unit home, so only a holder of `agents:manage` at the platform can repair it.
* Pause, resume and terminate keep `switches:use` at the platform and still reach every agent, Personal Agents included, so a stop works everywhere during an incident. Their audit rows now name the person who acted.

**2026-10-22**

Give and revoke a role over the Platform API.

* New [giveRole](https://docs.gloo.com/forge/reference/http-api/governance/giveRole.md) and [revokeRole](https://docs.gloo.com/forge/reference/http-api/governance/revokeRole.md) routes, and the `forge_give_role` and `forge_revoke_role` MCP tools, under `grants:manage` where the grant is.
* The calling credential is the giver: it may change only a role whose every permission it holds there, counted from its own grants narrowed by its scopes (a Personal key: its owner's grants narrowed by the key's scopes), never its own grants, and never the last Platform admin. A refusal lists each reason and changes nothing.

**2026-10-22**

Trust Fabric: invites follow the giver limit.

* Inviting a member now gives Builder and Auditor the way [giving a role](https://docs.gloo.com/forge/console/trust-fabric/access) does: you must hold every permission those roles carry at the platform scope, and each grant is recorded as a role given. If you cannot give at the platform scope, the invite is refused and tells you to choose an org unit you can give at.
* Re-inviting someone no longer restores a role an admin revoked. Give it again from Trust Fabric if they should have it back.

**2026-10-22**

Invite a user and revoke an on-behalf-of grant over the Platform API.

* New [inviteUser](https://docs.gloo.com/forge/reference/http-api/governance/inviteUser.md) route and `forge_invite_user` MCP tool, under `grants:manage` at the platform scope as in the Console: gives Builder and Auditor through the same giving limit as [giveRole](https://docs.gloo.com/forge/reference/http-api/governance/giveRole.md), measured on the calling credential. A re-invite never re-enables a revoked grant, and a refusal leaves nothing behind.
* New [revokeOnBehalfOfGrant](https://docs.gloo.com/forge/reference/http-api/governance/revokeOnBehalfOfGrant.md) route and `forge_revoke_on_behalf_of_grant` MCP tool, under `grants:manage` at the platform scope. A note is at most 280 characters, in the Console too.

**2026-10-22**

Knowledge: collections over the API.

* [Create a record collection](https://docs.gloo.com/forge/reference/http-api/knowledge/create-record-collection.md) (`forge_create_knowledge_record_collection`) creates an authored record collection in a namespace you can write. It needs `knowledge:manage` where that namespace lives, and it is created by and audited as the credential.
* [List subject collections](https://docs.gloo.com/forge/reference/http-api/knowledge/list-subject-collections.md) (`forge_list_knowledge_subject_collections`) lists the subject collections you can read. Each one shows how many of its artifacts you can read.
* [List knowledge cases](https://docs.gloo.com/forge/reference/http-api/knowledge/list-cases.md) takes a `collectionId` to list one subject collection's artifacts. An unknown collection, or one you cannot read, answers 404.

**2026-10-22**

Knowledge API: curation records who decided it.

* A verification, grade, steward change, delete or review decision made through the API is now recorded as the person who owns the Personal key, as if they had made it in the Console, and its audit event names the key. An External App is recorded as the app, with the people who granted its access, and a platform key as the key. See [Verify a case](https://docs.gloo.com/forge/reference/http-api/knowledge/verify-case.md).
* The Console names the app or key that made such a change, never its id.

**2026-10-22**

Knowledge: one record view, review badges in meaning search, clearer counts.

* A synced record opened from **Knowledge › Collections** now shows its fields and its source of truth, as it does when opened from search. Its Forge-owned annotations are under **Advanced**. See [Record field ownership](https://docs.gloo.com/forge/knowledge/external-sources.md#record-field-ownership).
* A new source left unnamed is named by its provider and container. When a source you can read already has that name, the new one's name adds the date it was added, so the two never read alike. Existing names and names you type are kept as they are.
* On **Knowledge › Sources**, two sources whose scopes can't be named no longer read alike: each scope adds its source's provider and the date it was added. A named scope always shows its name.
* Search by meaning marks an artifact waiting for a steward's review with a **Pending review** badge.
* An open synced collection says that its count includes every record the source synced, also records you can't read, while its list shows only the records you can read.
* In the chat turn inspector, a measured search whose person reads nothing now says when the search found nothing to leave out.

**2026-10-22**

Knowledge over MCP: synced record cases, callable record tools, a scope's shape.

* `forge_list_knowledge_cases`, `forge_get_knowledge_case` and `forge_get_knowledge_case_revision` accept synced records (`contentType` `record`), so a namespace with records, such as `company`, lists over MCP. The `contentType` filter takes `record` too.
* `forge_list_knowledge_records` and `forge_get_knowledge_record` publish their inputs, so MCP hosts can call them. Six update and history tools also list every input field now.
* [`GET /api/v2/knowledge/scopes/get`](https://docs.gloo.com/forge/reference/http-api/knowledge/get-scope) and `forge_get_knowledge_scope` read one namespace you can read with how many entries of each content type you may read there and the record kinds you can list, each with its source or collection.

**2026-10-22**

Knowledge: source containers and kind completeness over the API.

* [List source containers](https://docs.gloo.com/forge/reference/http-api/knowledge/list-source-containers.md) (`forge_list_synchronized_source_containers`) lists the containers a new source at a writable target could read, such as Freshservice workspaces, so a machine can pick the `externalContainerId` to connect without the Console. It needs `knowledge:manage` and `credentials:use`, the same pair connecting a source needs.
* [Get source kind states](https://docs.gloo.com/forge/reference/http-api/knowledge/get-source-kind-states.md) (`forge_get_synchronized_source_kind_states`) reads a readable source's kinds as the Console drawer shows them: each kind's completeness, every condition it fails, and its record count. It needs `knowledge:read`; a source you cannot read answers 404.

**2026-10-22**

Synchronized source review over HTTP and MCP, for a Personal key.

* Seven routes under `/api/v2/knowledge/synchronized-sources/` and MCP tools of the same names review and decide a source's held changes, as the Forge Console's review does: [`diff`](https://docs.gloo.com/forge/reference/http-api/knowledge/get-source-diff), [`reviewDiff`](https://docs.gloo.com/forge/reference/http-api/knowledge/review-source-diff), [`setDiffPolicy`](https://docs.gloo.com/forge/reference/http-api/knowledge/set-source-diff-policy), [`approveDiff`](https://docs.gloo.com/forge/reference/http-api/knowledge/approve-source-diff), [`rejectDiff`](https://docs.gloo.com/forge/reference/http-api/knowledge/reject-source-diff), [`approveShrink`](https://docs.gloo.com/forge/reference/http-api/knowledge/approve-source-shrink) and [`overrideShrink`](https://docs.gloo.com/forge/reference/http-api/knowledge/override-source-shrink).
* A person decides these: only a Personal key may call them, acting as its owner, who must hold the permission where the source lives. An External App or platform key gets `403 forbidden`.
* [`diff`](https://docs.gloo.com/forge/reference/http-api/knowledge/get-source-diff) lists each recent run's shrink guard (`shrinkGuards`, with or without a diff): the `revision` that `approveShrink` and `overrideShrink` take, so a machine can decide a guard on a run with no diff too.

**2026-10-22**

Knowledge records: one 404 for an unknown or unreadable record.

* [`POST /api/v2/knowledge/records/get`](https://docs.gloo.com/forge/reference/http-api/knowledge/get-record), `GET /api/v2/knowledge/records/annotations` and `POST /api/v2/knowledge/records/annotate` answer a record you may not read with the same `404 not_found` as a record that does not exist, and record nothing. They used to answer a recorded `403`, which confirmed that the record existed. The MCP tools `forge_get_knowledge_record`, `forge_get_knowledge_record_annotations` and `forge_annotate_knowledge_record` answer `not_found` the same way.
* A record you can read but may not annotate still answers `403 forbidden`.
* `POST /api/v2/knowledge/records/create`, `/update` and `/remove` answer a collection you may not read with the same `404` as a collection that does not exist, and record nothing; a collection you can read but may not manage still answers `403`. See [Authored knowledge records](https://docs.gloo.com/forge/knowledge/external-sources.md#authored-records).
* [`POST /api/v2/knowledge/records/list`](https://docs.gloo.com/forge/reference/http-api/knowledge/list-records) with a `collectionId` you may not read refuses `incomplete` with reason `unknown_collection`, exactly as a collection that does not exist.

**2026-10-22**

Knowledge: partial answers marked, authored-record history, record-free learning feed.

* [`getChunks`](https://docs.gloo.com/forge/reference/http-api/knowledge/get-chunks) and [`ask`](https://docs.gloo.com/forge/reference/http-api/knowledge/ask) answer `meta.partial: true` when the search reached its candidate cap before the ranking settled.
* Case versions, case uses, golden-set runs and source runs answer `meta.partial: true` when the list stopped at its cap.
* `POST /api/v2/knowledge/history` reads an authored record by `collectionId`, `kind` and `externalId`.
* `GET /api/v2/knowledge/collections/get` answers an id that names no collection with `404`, as other Knowledge reads do, instead of `400`.
* The learning feed no longer reports synchronized or authored records as case events, and, as the Console feed does, it leaves out cases a knowledge source synced.
* MCP tool hints and descriptions match what the tools do and name the keys they require.

**2026-10-22**

Trust Fabric: change trust and approval policies over the API.

* New [policy writes](https://docs.gloo.com/forge/reference/http-api/governance#policy-writes): `createTrustPolicy`, `editTrustPolicy`, `toggleTrustPolicy` and `removeTrustPolicy`, and `createApprovalPolicy`, `updateApprovalPolicy` and `removeApprovalPolicy`, with matching Forge MCP tools. Each needs `policies:manage` at the platform scope, runs the Console's validation and records the credential that decided in the audit event. Each takes an optional `Idempotency-Key`.
* `simulateTrustPolicy` now says why a condition was refused (for example an unknown field), instead of only that it is not a recorded condition.

**2026-10-22**

Save the MCP server configuration over the Platform API.

* New [updateMcpConfig](https://docs.gloo.com/forge/reference/http-api/governance/updateMcpConfig.md) route and the `forge_update_mcp_config` MCP tool, under `apikeys:manage` at the platform scope.
* `globalInstructions` (sent to every MCP client) is capped at 4,000 characters, in the Console too. Every save, from the Console or the API, records one `mcp_config_updated` audit event with the configuration before and after, naming who saved it.

**2026-10-22**

MCP: smaller self-describe answers and complete list text.

* [`forge_get_current_actor`](https://docs.gloo.com/forge/reference/mcp-server#current-actor-1-every-group) answers a summary with operation counts by default. Pass `detail: "operations"` to page the operations, or `detail: "full"` for every operation at once, as before.
* `forge_get_my_authority` states the credential's narrowing scopes once, as `narrowedBy`, and marks each narrowed permission `narrowed: true`.
* List tools keep `hasMore`, `nextCursor` and `partial` in their text, and tool descriptions name scopes as catalog permission keys only.

**2026-10-22**

Trust Fabric: approver limits, the door switch board and denials by person over the API.

* [`listPolicies`](https://docs.gloo.com/forge/reference/http-api/governance/listPolicies) with `includeApproverLimits=true` returns each approval policy's approver limits. Without the parameter the response is unchanged.
* New [`getDoorSwitchBoard`](https://docs.gloo.com/forge/reference/http-api/governance/getDoorSwitchBoard): whether each door is stopped, the global stop and the publish check's mode, with fixed copy. It needs `switches:use` at the platform scope and never returns an operator's reason or who changed a switch.
* New [`getDenialsByPersonReport`](https://docs.gloo.com/forge/reference/http-api/governance/getDenialsByPersonReport): blocked decisions by person id, with no name, grant or reason.
* New [`getAgentAccessOnBehalfOfReport`](https://docs.gloo.com/forge/reference/http-api/governance/getAgentAccessOnBehalfOfReport): which agents used which tools on behalf of a person, for a Personal key acting as its owner. Other credentials get a recorded `403`.
* Forge MCP: `forge_get_door_switch_board`, `forge_get_agent_access_report`, a `denials_by_person` report, and approver limits on `forge_list_policies`.

**2026-10-22**

Recorded decisions: decision fields, filters, gate tallies and the gate-path registry.

* [List recorded decisions](https://docs.gloo.com/forge/reference/http-api/governance/listEvidence.md) filters by `runId` (the run each item's correlation names) and by `gateOutcome=failed` with `gate` (decisions where that gate ran and failed). With `includeDecisionFields=true`, list and [get](https://docs.gloo.com/forge/reference/http-api/governance/getEvidence.md) items add `policyId`, `dispatchSurface`, `missingPermissionKeys`, `blockedByGate`, `heldBy`, `retryable` and `evidence.sourceKind`. Without it, responses are unchanged.
* [Explain a recorded decision](https://docs.gloo.com/forge/reference/http-api/governance/explainDecision.md) adds the recorded run, step and dispatch correlation with `includeCorrelation=true`.
* [Report gate denials](https://docs.gloo.com/forge/reference/http-api/governance/getGateDenyReport.md) adds each gate's pass and block tallies with `includePassTallies=true`.
* New: [Read the gate-path registry](https://docs.gloo.com/forge/reference/http-api/governance/getGatePathRegistry.md) returns each dispatch path's gates in run order and each gate's label, description and memberships.

**2026-10-22**

Trust Fabric Access reads over the Platform API.

* New [governance](https://docs.gloo.com/forge/reference/http-api/governance#roles-and-grants) reads under `grants:read`: who holds grants at a place, a holder's effective authority with a give or revoke preview, the Access check for a person or agent, a company's access inventory and the on-behalf-of grants. `listEnforcementSites` (under `roles:read`) lists where a permission is enforced, and `listMyGrants` lists your own credential's grants.
* `listGrants` returns people's grants too, by id, when you pass `includePersonGrants=true` (or `actorKind=person`); the default page is unchanged. No read returns who gave a grant, why, or a person's name.
* An agent's grant is shown, in `listGrants` and in these reads, only when your credential's scopes reach `agents:read` as well as your role grants holding it at the agent's home; a company's credentials likewise need `credentials:read` in your scopes.

**2026-10-22**

Trust Fabric: Roles say where each role was given.

* [Roles](https://docs.gloo.com/forge/console/trust-fabric/access#roles) counts now say where each role was given, at your company, a unit above it, or the platform ("12 given at the platform"), instead of "holders at" your company. A role with no such grant shows "None" rather than "0 holders", and Base reads "None directly · included in Builder and Operator".

**2026-10-22**

Chat: the turn inspector shows Knowledge access.

* When an agent's knowledge search was limited to what the person it answered can read, the chat turn inspector now says so under **Knowledge access**, naming the person. **Limited** means the limit applied. **Measuring** means the limit only counted how many results it would have left out. See [knowledge\_search](https://docs.gloo.com/forge/reference/tool-sets.md#knowledge_search).
* A search that read no shared knowledge says why: the person has no knowledge access here, or couldn't be identified.


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.