Machine credentials can create, edit, assign and move factory tasks, and Console task reads follow the factory home.
POST /api/v2/factories/createTask, PATCH /api/v2/factories/updateTask, POST /api/v2/factories/assignTask and POST /api/v2/factories/transitionTask write the tasks of a factory you may read. MCP adds forge_create_factory_task, forge_update_factory_task, forge_assign_factory_task and forge_transition_factory_task.Each write needs the key Console checks for the same operation, held at the task’s factory home. Creating and moving a task need factory:manage, under the new published scope factories:write:tasks; creating also needs it at the deployment root, where Console files the task. Editing and assigning need projects:manage, under the new published scope projects:write. Neither scope is given to the built-in apps. An agent assignee must be an active agent member of the task’s factory, and a person is never assigned. A task write schedules nothing and does not start an agent. See Factories.In Console, a task with no project is no longer shown to every signed-in person. A task that has a factory needs factory:read at the factory’s home, and a task with neither a project nor a factory needs projects:read. Either kind stays visible to the person it is assigned to.POST /api/v2/workflows/create, PATCH /api/v2/workflows/updateDraft, forge_create_workflow and forge_update_workflow_draft accept name, description and canonical typed inputs under workflows:write:draft, with read and write grants at the chosen home. Drafts are shared with Console; keyed retries recheck current draft visibility. Publishing, graph changes and live execution stay separate.Machine credentials can read whether each agent is owned, reviewed and attested, and where a person fixes it.
Summary
GET /api/v2/governance/listAgentAccountability pages, and GET /api/v2/governance/getAgentAccountability reads, each agent’s accountability: whether it is owned by an active person, its owner review is on time, and its identity is attested for its current definition. Both need the existing governance:read bundle (grants:read, policies:read, audit:read), decided at each agent’s home together with agents:read. MCP adds forge_list_agent_accountability and forge_get_agent_accountability. See Agent accountability.New
- Each row carries the
agent_ownershipandidentity_verificationgates’ finding codes and, when there is a finding, a Consolehandoff(/trust-fabric/agent-trust?agent=…,requiredPermission: agents:manage). An inactive owner reads as unowned. listAgentAccountabilitytakescursor,limit(1–50, default 25) andfindings=only, withmeta.partial; a page may be short or empty whilemeta.hasMoreistrue.- No owner identity, attesting person or definition hash is returned, and the reads do not say whether a dial enforces.
- Repairs stay person-only: a person assigns an owner, acknowledges a review or attests an identity in the Console; no API key or External App can.
Summary
New objective list, get and key-result list routes and MCP tools useobjectives:read at the deployment root. Objective paging is filter-bound and truthful; worker owner ids are withheld. Objective and key-result writes remain person-only. See Objectives.Summary
NewGET /api/v2/factories/listBlueprints and GET /api/v2/factories/getBlueprint read the deployment’s factory blueprint catalog: name, factory type, version, status, default team, extra channels and budget defaults. Blueprints have no home org unit, so they need factory:read held at the deployment root; a grant only below the root, or at a partner root, is refused with 403 and requiredPermission: "factory:read". Factory configuration, manager prompt text, the creator, a channel’s external link and repository settings are not returned. See Factories.New
listBlueprintslists ACTIVE blueprints newest first, or all of them withincludeDeprecated=true, optionally of onefactoryTypeId(with both, DEPRECATED blueprints come first), paged by cursor (1–50 per page).- MCP tools
forge_list_factory_blueprintsandforge_get_factory_blueprintin thefactoriesgroup, read-only with structured results;ForgePlatformClient.listFactoryBlueprintsandgetFactoryBlueprint.GET /api/v2/actorlists the new operations, and the OpenAPI document gainsFactoryBlueprint.
Machine credentials can inspect the tool and tool-set catalog without receiving secrets or invocation authority.
Summary
NewGET /api/v2/tools/list, /get, and /listSets routes and MCP tools expose a read-only, platform-global tool catalog under tools:read. Responses include safe identity, effect, version and grant metadata plus optional stored JSON Schemas. Credential configuration, internal paths, sandbox commands, egress configuration and agent assignments remain private, and there is no invocation endpoint. See Tools.Summary
NewGET /api/v2/workflows/listFiscalCalendars and getFiscalCalendar routes, plus forge_list_fiscal_calendars and forge_get_fiscal_calendar, expose the deployment-wide calendar catalog under workflows:read. Responses omit row ids and creator/updater identities. Calendar writes remain person-only in Console.Summary
Forge MCP now publishes generated stdio configurations for Claude Desktop with a static MCP key and VS Code with External App client credentials. A checked fixture pins each host shape, allowed environment variables, credential placeholders, and the setup, rotation, revocation, and recovery lifecycle. See Forge MCP server.New
- Public
buildStdioHostConfigandclassifyCredentialRecoveryhelpers in@tangogroup/forge-mcp. - A checked two-host onboarding fixture that rejects credential values and configuration or lifecycle drift.
- Protocol coverage proving static mode makes no token mint and External App mode mints once and
reuses the cached token while MCP
tools/listverifies local discovery. Operators prove a replacement credential separately with the authorizedforge_list_agentsread.
Availability
Interactive hosted OAuth sign-in remains unavailable. These configurations use service credentials and add no person delegation or new permission.Summary
NewGET /api/v2/health/stops and MCP tool forge_get_stop_state report the global kill switch
and global spend freeze under health:read. The response contains no operator reason or identity,
budget values, agent-specific freeze, or enforcement posture. Stop, freeze, and resume remain
person-only Console actions with a named actor, reason, and audited rollback. See
Stop state.Machine credentials can inspect and control knowledge source syncs without receiving connection configuration.
Summary
New knowledge source routes and MCP tools list sources, get one, list its newest runs, and rename, retime, pause or resume it. Reads useknowledge:read and readable namespaces; changes use knowledge:manage and writable namespaces. Configuration, cursors, container ids, identity mappings, curation, trust weight and creators never leave the server. Connecting and removing sources remain person-only pending the credential-use policy.New
GET /api/v2/knowledge/sources/list,/getand/listRuns;POST /api/v2/knowledge/sources/updatewith 24-hour idempotent response replay while the source remains writable.- MCP tools
forge_list_knowledge_sources,forge_get_knowledge_source,forge_list_knowledge_source_runsandforge_update_knowledge_source. - Console source creation now decides
knowledge:manageat the target namespace, and a removal is audited when requested rather than only after purge.
Platform actors read their organization's gate denial, trust policy and authorization surface reports with explicit coverage.
Summary
NewGET /api/v2/governance/getGateDenyReport, /getPolicyFiredReport and /getAuthzSurfaceReport (scope governance:read) count the Trust Fabric decisions recorded for the credential’s acting organization in a window of at most 30 days: blocked decisions by failed gate, blocked and held decisions by trust policy id, and permission denials by dispatch surface. The population is the one listEvidence reads, and each report states its window, windowCap, resolutionRevision and coverage (complete, partial or unavailable). See Organization reports.New
- The actor must hold
grants:read,policies:readandaudit:readat its acting organization; a credential with no acting organization gets403. OnlystartAt,endAtandwindowCap(1-2,000, default 2,000) are accepted: an organization, person or other parameter returns400. - The window cap counts every organization’s decisions in the window, so a busy deployment reports
partialwith reasonwindow_capuntil the window is narrowed. - MCP tool
forge_get_governance_reportin thegovernancegroup with areportselector;ForgePlatformClient.getGateDenyReport,getPolicyFiredReportandgetAuthzSurfaceReport. The MCP server registers one more tool.GET /api/v2/actorlists the new operations, and the OpenAPI document gainsGovernanceDecisionReport. - Reports that name people and the deployment-wide overview and policy effectiveness reports stay in the Forge Console.
Summary
GET /api/v2/capabilities/get, GET /api/v2/providers/get,
forge_get_capability, and forge_get_provider now include a strict Console handoff on each
credential-health row. It names approve, connect, or rotate, the Console page, and the
permission a person needs. Credential administration remains person-only, and the handoff never
contains a Credential id, name, scope, requester, field, or value.Changed
- Provider detail shows nested Credential rows only where the Console reader holds
credentials:readat that Credential’s scope. - Credential lifecycle writes record value-free audit events, and provider options refuse secret-shaped keys and values.
- The unused public
deploymentConfig.updateConfigandsettingsInternal.updateConfigwhole-object overwrites are removed.
Summary
NewGET /api/v2/factories/getSpend returns one factory’s token spend over a window of at most 30 days: totals, and breakdowns by source, model, agent worker and task. It needs factory:read and cost:read — your credential’s scopes must reach both (factories:read and cost:read), and your role grants must hold both at the factory’s home org unit; without cost:read it answers 403 with requiredPermission: "cost:read". Spend is factory token-event attribution, not the deployment cost rollup. Codebase browsing stays Console-only. See Factories.New
- At most 10,000 events are summed, newest first;
meta.partialis always present; when it istrue, every event fromcoveredFromthroughendTimewas summed and none older. Each breakdown holds at most 100 entries and saystruncatedwhen more existed. - Spend is summed in micro-dollars and rounded to cents once. With
taskId, only this factory’s events for that task are summed. Agent workers are itemized; every human worker’s spend is onehumanWorkersrow with no worker ID. The provider, project, workflow run, org-unit columns and micro-dollar cost are not returned. - MCP tool
forge_get_factory_spendin thefactoriesgroup, read-only with a structured result;ForgePlatformClient.getFactorySpend.GET /api/v2/actorlists the new operation, and the OpenAPI document gainsFactorySpend.
Summary
GET /api/v2/factories/listTasks and GET /api/v2/factories/getTask (scope factories:read) read a factory’s tasks: status, priority, kind, tags, and whether an agent or a person holds each one. A task is visible only through its factory, under factory:read at the factory’s home org unit; a task with no factory is never returned. Creating, editing, assigning and moving tasks, and starting factory work, are done by a person in Console. See Factories.New
listTaskstakes a requiredfactoryId, an optionalstatus, and the usuallimit/cursorpaging; rows come in index order (by status, then newest first).getTaskadds the task’sdescription.- No creator, person assignee identity, project, GitHub link or other task link is returned; a person holder is reported as
{ "type": "person" }. - MCP tools
forge_list_factory_tasksandforge_get_factory_taskin thefactoriesgroup.
The governance compliance export pages to the end of any window and the three compliance exports are documented.
Summary
GET /api/v2/compliance/export/governance now reads a bounded number of records per page and pages any window to its end. Before, a window holding more than 20,000 records of one disposition ended early with no signal. The three compliance exports are documented in the OpenAPI document and under Compliance.Changed
- When more governance records share one millisecond than a page can read, the page adds
partial: trueandsaturatedAttodata: the rest of that millisecond is skipped andcursorcontinues below it. A page without skipped records is unchanged, and a cursor issued earlier keeps working. - Exported records keep their stored shape, including
principaland person-resource audit events: the exports are for a deployment-root auditor. No MCP tool exposes them. - The OpenAPI document gains the
Compliancetag,exportAuditEvents,exportGovernanceDecisions,exportComplianceSummary, andComplianceRecordPage,ComplianceGovernancePageandComplianceSummary.GET /api/v2/actorlists the three exports; theirpermissionSatisfiedreflects the acting-unit check only, since the exports also require the deployment root.
Summary
GET /api/v2/compliance/export/audit, /export/governance and /export/summary export the whole deployment’s audit and governance records. Compliance exports cover the whole deployment, so they require audit:read granted at the deployment root; a credential granted only below it receives 403. See Compliance exports over the Platform API.Breaking
- Narrowing. Before, a key or app holding
audit:read(scopecompliance:read) where it acts, including at a tenant org unit or at a partner organization’s own root, exported every organization’s records. It now gets403 forbiddenwithrequiredPermission: "audit:read", recorded as an authorization denial, before any record is read. Platform-scope grants and every migrated key’s root compatibility grant keep the exports, with unchanged responses.
The coarse Trust Fabric policy simulator is retired; policy simulation replays recorded decisions only.
Summary
The coarse reactive queriesopsInternal.simulateGovernancePolicy and simulatePolicy are removed. They read every organization’s recorded decisions, treated a fact the record does not hold as a non-match, and listed “would block” runs whatever the policy’s action or enforcement. No Console page called them, and no API route or MCP tool exposed them.Removed
simulateGovernancePolicyandsimulatePolicy. UsepolicySimulation.simulatein Forge Console, orPOST /api/v2/governance/simulateTrustPolicyandforge_simulate_trust_policyfrom a machine credential. Both report a missing fact as unknown rather than as a non-match.
Summary
NewGET /api/v2/runs/listEvents pages a run’s structural timeline, oldest first: checkpoints, handoffs, guardrail trips, interventions, cost milestones, errors and completion. It needs runs:read at the run’s home and at every company it carries, the rule GET /api/v2/runs/get uses; any other run is a 404. Milestones only: tool calls, model messages, error payloads, agent identity and cost amounts are never returned (cost stays on GET /api/v2/cost/summary). See List a run’s structural timeline.New
listEventstakesrunId,cursorandlimit(1–100, default 25); a page may be short whilemeta.hasMoreistrue, and an unreadable cursor is a400.- MCP tool
forge_list_run_eventsin therunsgroup, read-only with a strict structured result;ForgePlatformClient.listRunEvents. The MCP server registers one more tool.GET /api/v2/actorlists the new operation, and the OpenAPI document gainsRunEvent.
Machine credentials can author evaluation sets for agents they may write and compare runs they may read.
Summary
POST /api/v2/evals/create, PATCH /api/v2/evals/update and POST /api/v2/evals/archive (scope agents:write) author evaluation sets: a set bound to an agent needs agents:write at that agent’s home org unit, and an unbound catalog set needs it at the deployment root. GET /api/v2/evals/compareRuns (scope agents:read) compares 2-10 runs you may read, computed on read and never stored, with an explicit comparable verdict. Authoring starts no run and spends nothing: sets created through the API are never run by the weekly regression evals. Starting or cancelling a run is not available over the API. See Evals.New
- Strict bodies with published limits (1-200 test cases with unique ids, 20,000-character inputs, weights above 0 up to 100);
dimensionsandgoldenDatasetIdare refused because the eval runner never reads them. - All test cases of a set together are at most 800,000 bytes as JSON.
expectedUpdatedAton update refuses a stale edit with409 conflict; an archived set cannot be edited, and archiving is one-way. The test cases of a set created in the Console or seeded, which the weekly regression evals run, can only be changed in the Console.- A same-key retry replays the recorded answer only while you may still read and write the set (the
eval_setreplay policy). - MCP tools
forge_create_eval_set,forge_update_eval_set,forge_archive_eval_setandforge_compare_eval_runsin theagentsgroup.
Read the knowledge review queue and Learning feed over the API and MCP; a person still decides each item in Console.
Summary
NewGET /api/v2/knowledge/listReviews, /getReview and /listLearning read the knowledge review queue and the Learning feed for the namespaces a credential can read, with knowledge:read held at the deployment root. Items never name the reviewer, the reviewer’s note, the assignee, the run or the decision, and a source-restricted item never appears. Every pending item carries a Console handoff naming requiredPermission: "knowledge:manage": a person decides it in Console, and no API or MCP operation approves, dismisses, merges or verifies a review item. See Review queue and Learning feed.New
listReviewsfilters by repeatablestatusandkindand one readablenamespace, pages by cursor (1–100 per page) and setsmeta.partialwhen its bounded read stopped with items left.getReviewanswers404for an item the credential cannot see.listLearningpages a window of at most 90 days, filtered by repeatablekindandscopeType; its items drop the actor, agent, run and reason.- MCP tools
forge_list_knowledge_reviews,forge_get_knowledge_reviewandforge_list_knowledge_learningin theknowledgegroup, read-only with structured results;ForgePlatformClient.listKnowledgeReviews,getKnowledgeReviewandlistKnowledgeLearning. The MCP server registers three more tools.GET /api/v2/actorlists the new operations, and the OpenAPI document gainsKnowledgeReviewItem,KnowledgeReviewHandoffandKnowledgeLearningItem.
Summary
NewGET /api/v2/governance/listTrustPolicies and /listTrustPolicyRevisions read the Trust Fabric gate policies (trust policies) and each policy’s revision chain at the deployment root, without the author. New POST /api/v2/governance/simulateTrustPolicy replays a candidate, or a stored revision, against the decisions recorded for the credential’s acting organization in a window of at most 30 days. A historical simulation replays facts recorded on past decisions. It is not an authorization, does not predict today’s gates, and reports any fact the record does not hold as unknown. See Trust policies.New
listTrustPolicieslists each policy once at its newest revision;listTrustPolicyRevisionsreturns one chain oldest first, withmeta.partialpast 200 revisions. Both needgrants:read,policies:readandaudit:readat the platform scope or the deployment root.simulateTrustPolicyevaluates only decisions recorded for exactly the acting organization with no private fence, never client-reported ones. Each item ismatch,noneorunknown, with the missing recorded fields named; a page states coverage and carrieshistorical: true. A condition onprincipal.personIdorprincipal.servicePrincipalIdreturns400. It is a read carried in a body: noIdempotency-Key.- MCP tools
forge_list_trust_policies,forge_list_trust_policy_revisionsandforge_simulate_trust_policyin thegovernancegroup, read-only with structured results;ForgePlatformClient.listTrustPolicies,listTrustPolicyRevisionsandsimulateTrustPolicy. The MCP server registers three more tools.GET /api/v2/actorlists the new operations, and they are in the OpenAPI document.
Changed
listPoliciesandforge_list_policiesare described as approval policies, apart from trust policies. Their behavior is unchanged.- No machine route creates or changes a policy: that stays person-only, in the Console.
Summary
Two knowledge health remedies the Console offers are now in the API and MCP, underknowledge:manage and only for knowledge in the caller’s writable namespaces: retrying a stuck pending entry and asking a source to sync now. See Remedies.New
POST /api/v2/knowledge/retryPendingEntry({entryId}→{entryId, scheduled}) andPOST /api/v2/knowledge/sources/requestSync({sourceId}→{sourceId, outcome},scheduled|running|inactive). The OpenAPI document gains strictRetryKnowledgeEntryResultandRequestKnowledgeSourceSyncResultschemas.- A same-key repeat returns the recorded result only while the entry or source is still writable by the caller (see Knowledge remedy replay).
- MCP tools
forge_retry_knowledge_entryandforge_request_knowledge_source_syncin theknowledgegroup, with structured results and an optionalidempotencyKey.
Summary
NewGET /api/v2/workflows/listTriggers and GET /api/v2/workflows/getTrigger read a workflow’s triggers: kind (cron, one_shot, ingress, email), timing, whether each follows the active version or pins one, the org unit its fires run at, and when it fires next. A trigger is visible only when the caller holds workflows:read at both the workflow’s home and the trigger’s orgUnitId. The owner, creator, stored inputs and ingress material are never returned. See listTriggers.New
GET /api/v2/workflows/listTriggers?workflowId=(workflows:read, scopeworkflows:read) pages newest first withlimit(at most 50) andcursor, andmeta.hasMore.GET /api/v2/workflows/getTrigger?id=returns one trigger. A trigger the caller cannot read is left out or answers404.- MCP tools
forge_list_workflow_triggersandforge_get_workflow_triggerin theworkflowsgroup, read-only with structured results;ForgePlatformClient.listWorkflowTriggersandgetWorkflowTrigger. The MCP server registers two more tools.GET /api/v2/actorlists both operations, and the OpenAPI document gains the strictWorkflowTriggerschema. - Changing a trigger stays person-only (Console):
workflows:managecan never be held by an API key, External App or agent.
Summary
The memory routes (GET /api/v2/memory/list and /get, POST /api/v2/memory/create and /delete, PATCH /api/v2/memory/update) and the Forge MCP memory tools now decide an API key’s access at the home of the agent a memory names: the key’s role grants must hold memory:read at the agent’s home org unit to read its memory and memory:write there to write it. External Apps keep their owner-scope chain. See Which agents’ memory the API reaches.Breaking
- Narrowing. Before, an API key with no External App reached every non-personal agent’s memory, whatever org unit its grants were at. A key granted only below the deployment root no longer reaches other organizations’ agents, and no key reaches the memory of an agent with no home. Keys granted at the deployment root or the platform scope keep reaching every homed agent.
- An unreachable agent’s memory lists empty, is left out of a listing by
channelIdalone, and answers404toget,updateanddelete;createanswers403“agentId’s home does not grant this credential memory:write”. A key holdingmemory:readbut notmemory:writeat the agent’s home reads its memory and gets403onupdateanddelete. - A same-key repeat of a memory write returns the recorded response only while the key may still write that agent’s memory at its home; otherwise the non-disclosing
409.
External Apps write only the agents they own, at each agent's home; operator pauses and terminations hold, and delete archives.
Summary
POST /api/v2/agents/create, PATCH /api/v2/agents/update and DELETE /api/v2/agents/delete, and the Forge MCP forge_create_agent, forge_update_agent and forge_delete_agent tools, decide every write at the agent’s home. Create homes the agent at the calling App’s owning org unit, so the App can read what it creates. See Who may write which agent and Agent write replay.Fixed
- An External App could set a paused or terminated agent back to
activethroughPATCH /api/v2/agents/update. A status change on an agent whose status ispaused,deprecated(terminated) orarchivedis now409 conflictand nothing is written; resume a paused agent in the Console. DELETE /api/v2/agents/deletehard-deleted the agent, skipping the Console’s archive step. It now archives the agent and its versions and keeps its memory and knowledge.
Breaking
- Creating an agent needs an External App owned by an org unit, holding
agents:writeandagents:readat that unit; otherwise403 forbidden. The agent’s worker role is granted at that unit’s company root, no longer at the deployment root’s. - Update and delete need
agents:writeat the agent’s home. An agent the App may not read at its home is404 not_found. - Bodies are strict: unknown fields, a status outside
draft/active(create) ordraft/active/deprecated(update), and a malformedmodelorpromptare400 bad_requestinstead of being ignored. A missing update or deleteidis400, not404. DELETE /api/v2/agents/deleteanswers{ok, agentId, status: "archived"}; deleting an archived agent is409 conflict. Permanent deletion is Console-only.
Migration
- Agents an App created before 2026-10-01 stay homed at the deployment root; they are not re-homed.
- Send
agentId,nameanddescriptionon create, and only the documented fields on update. - MCP write tools now return structured
{ data, meta }and acceptidempotencyKey.
Summary
GET /api/v2/knowledge/health (scope knowledge:read) returns the health the Console’s Knowledge › Health page shows, for the knowledge the credential can read: stuck pending entries, failing and overdue sources, failing and quarantined source items, embedding staleness and open review items, plus the deployment’s latest re-embed run, integrity audit, knowledge cron runs and learning settings. Each section names its scope, readable or deployment. See Knowledge health.New
GET /api/v2/knowledge/health, with an optionalnamespacethat must be readable (else403). The OpenAPI document gains a strictKnowledgeHealthschema.- MCP tool
forge_get_knowledge_healthin theknowledgegroup, read-only with a structured result. - No source configuration, cursor or case key is returned; source and item errors are redacted, an item whose case you may not read is
restrictedwith no error, and the re-embed run’s error text is withheld (hasError).
Machine credentials can read the Trust Fabric role catalog and the role grants of API keys, External Apps and agents.
Summary
GET /api/v2/governance/listRoles returns the system roles of the Trust Fabric catalog, and GET /api/v2/governance/listGrants pages the role grants held by API keys, External Apps and agents that the caller may see. Both need the existing governance:read bundle (grants:read, policies:read, audit:read). The catalog is decided at the deployment root; each grant is decided at its own scope, and an agent’s grant also needs agents:read at the agent’s home. MCP adds forge_list_roles and forge_list_grants. See Roles and grants.New
listRoles(403naminggrants:readwhen your grants do not reach the platform scope or the deployment root) andlistGrants(cursor,limit1–50,actorKindofapi_key,external_apporagent), each withmeta.partial.- Person grants are never returned, and no grant carries who gave it, a name or an email;
actorKind=personis400. Compatibility roles are never listed. - Giving or revoking roles stays person-only (Console):
grants:manageandroles:managecan never be held by an API key, External App or agent.
Six new published scopes prepare project, workforce, tool, objective, workflow-draft and agent-management APIs.
Summary
The published scope catalog now includesprojects:read, workforce:read, tools:read, objectives:read, workflows:write:draft and agents:manage. Each scope only narrows an existing role grant; it grants no authority by itself. The built-in Magellan and Code Red Intake apps receive the four read scopes and explicitly exclude the two mutating scopes.Summary
NewPOST /api/v2/external/customers/unlink and MCP forge_unlink_customer remove only the calling External App’s link to a customer, with body exactly {id}, and return {id, unlinked: true}. They never archive or change the shared customer, other apps’ links or the customer’s organization home. A customer that is missing or not linked to the app is 404. See Removing your app’s link.New
POST /api/v2/external/customers/unlink(customers:manage, scopecustomers:write, External App credential only). Afterwards the app can no longer read, update, cost-query or dispatch for that customer untilfindOrCreatelinks it again.- With a management JWT, a same-key repeat of a completed unlink returns the recorded
{id, unlinked: true}to the same app while it holdscustomers:manage(see External App customer writes). forge_unlink_customer(destructive, optionalidempotencyKey) in thecustomersMCP group;ForgePlatformClient.unlinkCustomer. The MCP server registers one more tool.GET /api/v2/actorlists the new operation, and it is in the OpenAPI document.
Read the procedure catalog at each procedure's home: families, versions, usage and retirement blockers, over the API and MCP.
Summary
GET /api/v2/procedures/list, /get and the new /listVersions return only the procedure versions the caller may read, with procedures:read held at each version’s home org unit. The list pages procedure families with an opaque family cursor; get returns an allowlisted ProcedureDetail with dispatch usage, hard-delete blockers and a family-level current-workflow reference flag. See Procedure catalog.New
GET /api/v2/procedures/listVersions?procedureId=lists every visible version, highest first, with status and dispatch usage.ProcedureDetailgainsretirement.blockers(builtin,active,approved,non_provisional_tier,recorded_usage),familyReferencedByCurrentWorkflow(nullwhen undecided) andimmutable: true. The OpenAPI document gains strictProcedure,ProcedureDetailandProcedureVersionschemas.- MCP tools
forge_list_procedures,forge_get_procedureandforge_list_procedure_versionsin theworkflowsgroup, read-only with structured results.
Breaking
- The list cursor is an opaque family cursor; a numeric offset cursor is
400. The list returns one item per family and drops the snapshot build fields andoperationContract.binding. getno longer returns row ids, creator, synthesis request, lifecycle actors, sandbox, image digest, repository or draft state, connection bindings orusage.totalReferences.- Procedures are homed at the deployment root, so a credential whose grants are scoped only to org units below the root no longer sees them.
Migration
- Restart a list walk without
cursor, then followmeta.nextCursorwhilemeta.hasMoreistrue. - Read
familyReferencedByCurrentWorkflowinstead ofusage.totalReferences.
Summary
POST /api/v2/knowledge/delete now answers alreadyDeleted, false only for the call that deleted the entry and wrote its audit event. A refused company add names the permission that would allow it. A same-key repeat of a completed add or delete returns the recorded response instead of 409 idempotency_result_unavailable, while the caller still holds knowledge:read and may still read (add) or delete (delete) the entry. forge_add_knowledge and forge_delete_knowledge return structured results and accept an idempotencyKey. See Add a knowledge entry, Delete a knowledge entry and Knowledge write replay.Changed
- Delete outcome. The delete’s
200body gainsalreadyDeleted({ id, status: "deleted", alreadyDeleted }). The decision is made inside the delete’s transaction: of two racing deletes of one entry, exactly one answersfalse. - Company refusal. A
403for an add tocompanyby a caller withoutknowledge:managecarrieserror.requiredPermission: "knowledge:manage". A refusal for any other namespace, or forcompanyto a caller that already holdsknowledge:manage, names no permission, because none would allow it. - Replay. A same-key repeat of a completed add returns its stored
201, or200withdeduplicated: true; of a completed delete, its stored200. Both need the route’s permission andknowledge:read; a missingknowledge:readanswers403, and an added entry deleted since, an entry that left the caller’s writable namespaces, a delete response stored before this change (it has noalreadyDeleted), or a repeat of a refused request answers409idempotency_result_unavailable. Nothing is written twice. - De-duplication scope, documented. An add de-duplicates on an active entry with the same
externalRef, namespace and principal. Every platform and MCP key shares one principal per namespace; an External App has its own. - MCP.
forge_add_knowledgeandforge_delete_knowledgereturn{ data, meta }with strict output schemas, carry write annotations (delete is destructive and idempotent), acceptidempotencyKey, and explain an unknown outcome and its same-key recovery.
Summary
CredentialHealth.resolved, in GET /api/v2/capabilities/get, GET /api/v2/providers/get and the matching Forge MCP tools, is now the credential resolver’s own answer at the deployment scope, the scope a provider resolves at when no run names an organization. See Credential health.Fixed
- A connection whose only approved credential is homed at one organization reported
resolved: truealthough a deployment-scope dispatch finds no credential for it. It now reportsresolved: false; the credential still counts inapprovedCount. The response shape is unchanged.
Summary
Console Trust Fabric policy authoring keeps one live revision per policy. Only a policy’s newest revision can be enabled, edited or deleted; an earlier revision can still be disabled. An edit keeps the policy’s enabled state, the policy table shows each policy once at its newest revision, and deleting a revision never strands the rest of its history. See Policies.Fixed
- An earlier revision of an edited policy could be re-enabled and was then enforced beside the newest one, while
GET /api/v2/governance/listTrustPoliciesreported only the newest. Enabling an earlier revision is now refused. - Editing an earlier revision created a second live revision with a duplicate revision number, and editing a disabled policy enabled it. Editing an earlier revision is now refused, and an edit keeps the enabled state.
- Deleting a policy’s first revision hid the policy’s live revision from
listTrustPolicies. A delete now acts on the newest revision only.
Removed
- The unused reactive policy mutation
update, which rewrote a revision’s content in place. UseopsInternal.editGovernancePolicy(a new revision) ortoggleGovernancePolicy.
Changed
listTrustPolicies,listTrustPolicyRevisionsand the matching Forge MCP tools state that trust policy writes are person-only. Responses are unchanged.
While Forge is stopped by an operator, machine writes, knowledge answers and inference calls are refused before any effect.
Summary
When a person engages the global kill switch (“stop everything”) in the Console, every/api/v2 write, POST /api/v2/knowledge/ask and POST /api/v2/knowledge/getChunks answer 403 forbidden, and /api/inference/v1/chat/completions and the inference file writes answer 403 platform_killed, each with the fixed message “Forge is stopped by an operator. A person resumes it in the Console.” Before, these requests ran while Forge was stopped. A refused request records no Idempotency-Key, so the same key sent after Forge resumes executes once. Reads keep working. The operator’s reason is never returned. See Errors and Idempotency.Changed
- Writes over the API and the Forge MCP write tools are refused while Forge is stopped, including credential rotation and External App deactivation: during a stop, a person revokes a credential in the Console.
- The inference proxy’s chat refusal while stopped no longer includes the operator’s reason.
Four workforce GET routes and four MCP tools now read org units and positions under
workforce:read. Org-unit grants include descendants, outputs use safe allowlists and legacy IDs, and list continuation remains truthful through empty filtered pages. Raw worker/person directory reads remain separate. Component faults remain server failures rather than becoming missing rows or empty enrichment.
