@loomcycle/client 1.133.0 → 1.135.0

package/README.md

@@ -221,7 +221,8 @@ Live SSE tails of what changed in the caller's tenant's memory and documents —
 | Method | Returns | Notes |
 |---|---|---|
 | `streamMemoryChanges(opts?)` | `AsyncIterable<ChangeFeedFrame>` | `memory.set` / `memory.delete` / `memory.scope_deleted`. Mirrors `GET /v1/_memory/changes`. |
-| `streamDocumentChanges(opts?)` | `AsyncIterable<ChangeFeedFrame>` | `document.chunk.updated` / `document.chunk.deleted`, naming the `chunk_id`. Mirrors `GET /v1/_document/changes`. |
+| `streamDocumentChanges(opts?)` | `AsyncIterable<ChangeFeedFrame>` | `document.chunk.updated` / `document.chunk.deleted` / `document.edges.changed`, naming the `chunk_id` and `document_id`. Mirrors `GET /v1/_document/changes`. |
+| `documentFeed({scope, scopeId?, tenant?, signal?})` | `AsyncIterable<DocumentFeedFrame>` | RFC FV — the reader's feed, open to a tenant member: one scope (`user` / `tenant`), only documents the caller can list, `{type, chunk_id, document_id, at}` with no cursor (a reconnect is a resync). Mirrors `GET /v1/_document/feed`. |
 
 Each change is a **value-free coordinate** (`seq`, `type`, `scope`, `scope_id`, `key` or `chunk_id`, `at`): it says *what* changed, and you pull the current value through the data API. The first item is always `{ kind: "feed", payload: { enabled, since, embedder? } }`, then one `{ kind: "change", payload: MemoryChange }` per change, oldest first.
 

package/dist/cjs/client.js

@@ -3538,6 +3538,42 @@ class LoomcycleClient {
     async *streamDocumentChanges(opts) {
         yield* this.streamChangeFeed("/v1/_document/changes", opts);
     }
+    /** Watch one scope's DOCUMENTS change, as a reader (RFC FV). Mirrors
+     *  `GET /v1/_document/feed?scope=user|tenant[&scope_id=…][&tenant=…]`.
+     *
+     *  Unlike {@link LoomcycleClient.streamDocumentChanges} (the operator's
+     *  tenant-wide feed) this is open to a tenant MEMBER, gated like
+     *  {@link LoomcycleClient.document}: it names only documents the caller can
+     *  list, in the one scope it asked for.
+     *
+     *  - The first item is `{ kind: "feed" }`; `payload.enabled === false` means
+     *    the server captures no changes — reload on a timer instead of waiting.
+     *  - Then one `{ kind: "change" }` per change. Changes of one type to one
+     *    document inside one server poll arrive as one.
+     *  - There is NO cursor and no resume: the stream starts now. After any
+     *    disconnect, reload your view and open a new stream.
+     *  - A `{ kind: "error" }` with code `store_unavailable` is non-fatal;
+     *    `access_unavailable`, `credential_revoked` and `credential_expired`
+     *    close the stream — reload and reconnect with a valid credential.
+     *  - The server re-authenticates the stream every 30 s: a revoked grant
+     *    stops that document's changes, and a revoked token ends the stream,
+     *    within that window; a token's expiry ends it on time.
+     *  - At most a few streams per principal (`LOOMCYCLE_DOCUMENT_FEED_MAX_STREAMS`,
+     *    default 4); one more is refused with a 429 — a `BackpressureError` with
+     *    code `too_many_streams`, not retryable until you close a stream.
+     *  - Iteration ends when the server closes the stream, or throws an
+     *    `AbortError` when `signal` aborts. */
+    async *documentFeed(opts) {
+        if (opts.scope !== "user" && opts.scope !== "tenant") {
+            throw new Error(`loomcycle: documentFeed scope must be "user" or "tenant", got ${String(opts.scope)}`);
+        }
+        const q = new URLSearchParams({ scope: opts.scope, ...browseQuery(opts) });
+        for await (const ev of this.streamSSEGet(`/v1/_document/feed?${q.toString()}`, opts.signal)) {
+            const frame = toDocumentFeedFrame(ev);
+            if (frame)
+                yield frame;
+        }
+    }
     async *streamChangeFeed(path, opts) {
         const since = opts?.since;
         // The server reads an unparseable or negative `since` as 0 rather than
@@ -3873,6 +3909,26 @@ function toChangeFeedFrame(raw) {
     }
     return null;
 }
+/** toDocumentFeedFrame types one frame of the reader's document feed, or
+ *  returns null for one it does not recognise. `feed` and `error` frames are
+ *  read as on the operator feed; a reader `change` carries no `seq`, so it is
+ *  recognised by its `document_id`. */
+function toDocumentFeedFrame(raw) {
+    const shared = toChangeFeedFrame(raw);
+    if (shared?.kind === "feed") {
+        const { since: _since, ...status } = shared.payload;
+        return { kind: "feed", payload: status };
+    }
+    if (shared?.kind === "error")
+        return shared;
+    if (typeof raw.document_id === "string" &&
+        typeof raw.chunk_id === "string" &&
+        typeof raw.type === "string" &&
+        raw.type.startsWith("document.")) {
+        return { kind: "change", payload: raw };
+    }
+    return null;
+}
 // channelOpPath builds the v0.9.x Channel CRUD URL. Two families:
 //   - scope === "global" → /v1/_channels/{channel}/{op}
 //   - scope === "user"   → /v1/users/{userId}/channels/{channel}/{op}

package/dist/cjs/errors.js

@@ -70,9 +70,11 @@ const TRANSIENT_CODES = new Set([
 /** 429 codes that do NOT clear by waiting: the caller has to act first, so
  *  a retry loop on them never ends. `configured_run_cap`: the user already
  *  holds as many configured (not yet started) runs as the operator allows,
- *  and only starting or discarding one makes room. (A hard token budget,
- *  `token_limit_exceeded`, has a class of its own outside BackpressureError.) */
-const CALLER_ACTION_429_CODES = new Set(["configured_run_cap"]);
+ *  and only starting or discarding one makes room. `too_many_streams`: the
+ *  principal already holds as many document feed streams as allowed, and only
+ *  closing one makes room. (A hard token budget, `token_limit_exceeded`, has a
+ *  class of its own outside BackpressureError.) */
+const CALLER_ACTION_429_CODES = new Set(["configured_run_cap", "too_many_streams"]);
 /** Base class for every HTTP 404 the client surfaces. Lets callers
  *  catch any not-found case with a single `instanceof NotFoundError`
  *  check, regardless of which specific resource was missing

package/dist/cjs/index.js

@@ -78,6 +78,7 @@
  *     // Memory / document change feeds (RFC CD Part C; SSE; substrate:tenant)
  *     streamMemoryChanges(opts?): AsyncIterable<ChangeFeedFrame>     // feed | change | error (non-fatal); resume with opts.since = last seq
  *     streamDocumentChanges(opts?): AsyncIterable<ChangeFeedFrame>
+ *     documentFeed(opts): AsyncIterable<DocumentFeedFrame>           // RFC FV: member-safe, one scope, no cursor (reconnect = resync)
  *
  *     // Interruption (v0.8.16; decline RFC BH)
  *     listUserInterrupts(userId, opts?): Promise<InterruptListResponse>

package/dist/client.d.ts

@@ -26,7 +26,7 @@
 import { InteractiveSession } from "./interactive.js";
 import { LoomcycleOAuth } from "./oauth.js";
 import { ClientToolHost, type ConnectClientToolsOptions } from "./client-tools.js";
-import type { ChangeFeedFrame, StreamChangesOptions, CredentialListResponse, CredentialMeta, CryptoKeyEncoding, CryptoKeyExport, CryptoKeyExternal, CryptoKeyType, CryptoRequest, CryptoResultByOp, DecideRequest, DecideResponse, DecisionModelsResponse, CredentialScope, DirectoryInspection, DirectoryTenant, DirectoryUser, ErasureReport, ErasureResult, MergeSubjectsResult, ReviewQueueFilter, ReviewQueueResult, RuleStatementsResult, RevertRulingResult, ListRulingsResult, ApplyReviewPolicyResult, BindSubjectPrincipalResult, Agent, AgentEvent, AgentList, CancelAgentResult, ClientOptions, ContinueOptions, RunOverrideOptions, EffectiveConfigResponse, RunFileInput, RunInboxDownload, AgentOverridableResponse, RetuneRunResponse, RunConfigResponse, RunPromptResponse, CreateSnapshotOptions, EnsureCodeAgentOptions, EnsureCodeAgentResult, EnsureHookDefOptions, EnsureHookDefResult, HookDefInput, HookDefOverlay, HookDefRowResponse, CreateDefOptions, ForkDefOptions, HookDefForkOverlay, ScheduleDefInput, ScheduleDefOverlay, ScheduleDefRowResponse, WebhookDefInput, WebhookDefOverlay, WebhookDefRowResponse, EnsureMcpServerOptions, EnsureMcpServerResult, HealthResponse, InterruptListResponse, InterruptStatus, ListUserAgentsOptions, WalkRunsPage, AckChannelOptions, AwaitChannelsOptions, BroadcastChannelsOptions, ChannelAckResult, ChannelAwaitResult, ChannelBroadcastResult, ChannelDescriptor, ChannelPeekResult, ListTeamChannelsOptions, PeekTeamChannelOptions, ReleaseTeamChannelOptions, TeamChannelPeekResult, TeamChannelReleaseResult, TeamChannelsResult, ChannelPublishResult, ChannelPurgeResult, ChannelReleaseResult, ChannelSubscribeResult, CreateChannelOptions, ListChannelsResponse, PeekChannelOptions, PublishChannelOptions, ReleaseChannelOptions, SetMemoryEntryOptions, SetMemoryEntryResponse, SubscribeChannelOptions, UpdateChannelOptions, LibraryAgentDefinition, LibraryListResponse, LibraryMcpServerDefinition, LibrarySkillDefinition, ListUsersResponse, UserRecord, CreateUserBody, UpdateUserBody, MintedUserToken, ListUserTokensResponse, UserIdentitiesResponse, AuthGateListResponse, CreateInviteBody, CreatedInvite, AuthInviteListResponse, CreatedPasswordReset, GateIdentitiesResponse, GateTenantStatus, RunnableAgentsResponse, LLMChatOptions, LLMChatResponse, LLMChatStreamItem, LLMEmbeddingsOptions, LLMEmbeddingsResponse, MCPServerDefVerifyResult, MemoryEmbedStatsResponse, MemoryEntriesResponse, MemoryEntryResponse, MemoryBackfillResponse, MemoryPurgeResponse, MemoryReembedResponse, MemoryScopeIDsResponse, MemoryScopesResponse, MemorySearchInput, MemorySearchResponse, PauseResult, RetentionOverride, PersistentVolumesResponse, EphemeralVolumesResponse, ResolveInterruptOptions, ResumeResult, ResolverMatrix, CompactRunResult, RunTreeDeletion, ReplaySessionResult, CancelTurnResult, ReviewRunResult, RunBatchOptions, RunBatchResult, RunOptions, ConfiguredRun, ConfiguredRunPatch, RunStateStreamItem, RuntimeStateResponse, SnapshotCreateResponse, SnapshotDescriptor, SnapshotEnvelope, SnapshotRestoreResponse, StreamUserRunStatesOptions, SubstrateToolInput, SubstrateToolResponse, CreatedTeam, CreateTeamOptions, DefNamesResponse, ForkTeamOptions, ModelAliasesResponse, OperatorTokenDefNamesResponse, ProviderModelsResponse, RoutingResponse, ScheduleListResponse, SchedulePauseResult, ScheduleRunNowResult, ScheduleStateView, ListTeamsResponse, PromotedTeam, RetiredTeam, TeamBreakpoints, TeamDefDetail, TeamRunDetached, TeamRunTarget, TeamVerification, TeamDraft, TeamDraftVerification, TeamVersionList, TeamDiagram, TeamRunResult, PathToolInput, PathToolResponse, DocumentToolInput, DocumentToolResponse, HistoryToolInput, HistoryToolResponse, EvaluationSubmitInput, EvaluationGetInput, EvaluationListForRunInput, EvaluationListForDefInput, EvaluationAggregateInput, EvaluationInput, EvaluationSubmitResult, EvaluationRecord, EvaluationListForRunResult, EvaluationListForDefResult, EvaluationAggregate, TranscriptResponse, WhoamiResponse, UsageDimension, UsageBucket, UsageReportResponse, TokenLimit, TokenLimitsResponse, ConfigResponse, SetTokenLimitRequest, AclBinding, AclBindingListResponse, AclCatalog, AclDefInput, AclDefListResponse, AclDefNamesResponse, AclDefRow, AclRule, AclValidateResult, AuthzDecision, AuthzEvaluationRequest, AuthzEvaluationsRequest, AuthzEvaluationsResponse, AuthzExplainResponse, AuthzSimulateRequest, AuthzSimulateResponse, CreateAclBindingBody, CreateGroupBody, GroupDetail, GroupEffective, GroupListResponse, GroupMemberChange, GroupMemberKind, GroupRow, AppClientConfig, AppClientEntry, ClientDefInput, ClientDefListResponse, ClientDefNamesResponse, ClientDefRecord, ClientDefRetireResult, ClientDefVerifyResult, DeviceLoginOptions, DeviceLoginResult } from "./types.js";
+import type { ChangeFeedFrame, StreamChangesOptions, DocumentFeedFrame, DocumentFeedOptions, CredentialListResponse, CredentialMeta, CryptoKeyEncoding, CryptoKeyExport, CryptoKeyExternal, CryptoKeyType, CryptoRequest, CryptoResultByOp, DecideRequest, DecideResponse, DecisionModelsResponse, CredentialScope, DirectoryInspection, DirectoryTenant, DirectoryUser, ErasureReport, ErasureResult, MergeSubjectsResult, ReviewQueueFilter, ReviewQueueResult, RuleStatementsResult, RevertRulingResult, ListRulingsResult, ApplyReviewPolicyResult, BindSubjectPrincipalResult, Agent, AgentEvent, AgentList, CancelAgentResult, ClientOptions, ContinueOptions, RunOverrideOptions, EffectiveConfigResponse, RunFileInput, RunInboxDownload, AgentOverridableResponse, RetuneRunResponse, RunConfigResponse, RunPromptResponse, CreateSnapshotOptions, EnsureCodeAgentOptions, EnsureCodeAgentResult, EnsureHookDefOptions, EnsureHookDefResult, HookDefInput, HookDefOverlay, HookDefRowResponse, CreateDefOptions, ForkDefOptions, HookDefForkOverlay, ScheduleDefInput, ScheduleDefOverlay, ScheduleDefRowResponse, WebhookDefInput, WebhookDefOverlay, WebhookDefRowResponse, EnsureMcpServerOptions, EnsureMcpServerResult, HealthResponse, InterruptListResponse, InterruptStatus, ListUserAgentsOptions, WalkRunsPage, AckChannelOptions, AwaitChannelsOptions, BroadcastChannelsOptions, ChannelAckResult, ChannelAwaitResult, ChannelBroadcastResult, ChannelDescriptor, ChannelPeekResult, ListTeamChannelsOptions, PeekTeamChannelOptions, ReleaseTeamChannelOptions, TeamChannelPeekResult, TeamChannelReleaseResult, TeamChannelsResult, ChannelPublishResult, ChannelPurgeResult, ChannelReleaseResult, ChannelSubscribeResult, CreateChannelOptions, ListChannelsResponse, PeekChannelOptions, PublishChannelOptions, ReleaseChannelOptions, SetMemoryEntryOptions, SetMemoryEntryResponse, SubscribeChannelOptions, UpdateChannelOptions, LibraryAgentDefinition, LibraryListResponse, LibraryMcpServerDefinition, LibrarySkillDefinition, ListUsersResponse, UserRecord, CreateUserBody, UpdateUserBody, MintedUserToken, ListUserTokensResponse, UserIdentitiesResponse, AuthGateListResponse, CreateInviteBody, CreatedInvite, AuthInviteListResponse, CreatedPasswordReset, GateIdentitiesResponse, GateTenantStatus, RunnableAgentsResponse, LLMChatOptions, LLMChatResponse, LLMChatStreamItem, LLMEmbeddingsOptions, LLMEmbeddingsResponse, MCPServerDefVerifyResult, MemoryEmbedStatsResponse, MemoryEntriesResponse, MemoryEntryResponse, MemoryBackfillResponse, MemoryPurgeResponse, MemoryReembedResponse, MemoryScopeIDsResponse, MemoryScopesResponse, MemorySearchInput, MemorySearchResponse, PauseResult, RetentionOverride, PersistentVolumesResponse, EphemeralVolumesResponse, ResolveInterruptOptions, ResumeResult, ResolverMatrix, CompactRunResult, RunTreeDeletion, ReplaySessionResult, CancelTurnResult, ReviewRunResult, RunBatchOptions, RunBatchResult, RunOptions, ConfiguredRun, ConfiguredRunPatch, RunStateStreamItem, RuntimeStateResponse, SnapshotCreateResponse, SnapshotDescriptor, SnapshotEnvelope, SnapshotRestoreResponse, StreamUserRunStatesOptions, SubstrateToolInput, SubstrateToolResponse, CreatedTeam, CreateTeamOptions, DefNamesResponse, ForkTeamOptions, ModelAliasesResponse, OperatorTokenDefNamesResponse, ProviderModelsResponse, RoutingResponse, ScheduleListResponse, SchedulePauseResult, ScheduleRunNowResult, ScheduleStateView, ListTeamsResponse, PromotedTeam, RetiredTeam, TeamBreakpoints, TeamDefDetail, TeamRunDetached, TeamRunTarget, TeamVerification, TeamDraft, TeamDraftVerification, TeamVersionList, TeamDiagram, TeamRunResult, PathToolInput, PathToolResponse, DocumentToolInput, DocumentToolResponse, HistoryToolInput, HistoryToolResponse, EvaluationSubmitInput, EvaluationGetInput, EvaluationListForRunInput, EvaluationListForDefInput, EvaluationAggregateInput, EvaluationInput, EvaluationSubmitResult, EvaluationRecord, EvaluationListForRunResult, EvaluationListForDefResult, EvaluationAggregate, TranscriptResponse, WhoamiResponse, UsageDimension, UsageBucket, UsageReportResponse, TokenLimit, TokenLimitsResponse, ConfigResponse, SetTokenLimitRequest, AclBinding, AclBindingListResponse, AclCatalog, AclDefInput, AclDefListResponse, AclDefNamesResponse, AclDefRow, AclRule, AclValidateResult, AuthzDecision, AuthzEvaluationRequest, AuthzEvaluationsRequest, AuthzEvaluationsResponse, AuthzExplainResponse, AuthzSimulateRequest, AuthzSimulateResponse, CreateAclBindingBody, CreateGroupBody, GroupDetail, GroupEffective, GroupListResponse, GroupMemberChange, GroupMemberKind, GroupRow, AppClientConfig, AppClientEntry, ClientDefInput, ClientDefListResponse, ClientDefNamesResponse, ClientDefRecord, ClientDefRetireResult, ClientDefVerifyResult, DeviceLoginOptions, DeviceLoginResult } from "./types.js";
 export declare class LoomcycleClient {
     private ctx;
     private readonly tokenProvider?;
@@ -2494,6 +2494,32 @@ export declare class LoomcycleClient {
      *  {@link LoomcycleClient.streamMemoryChanges}; a reader wanting both
      *  families opens both. */
     streamDocumentChanges(opts?: StreamChangesOptions): AsyncIterable<ChangeFeedFrame>;
+    /** Watch one scope's DOCUMENTS change, as a reader (RFC FV). Mirrors
+     *  `GET /v1/_document/feed?scope=user|tenant[&scope_id=…][&tenant=…]`.
+     *
+     *  Unlike {@link LoomcycleClient.streamDocumentChanges} (the operator's
+     *  tenant-wide feed) this is open to a tenant MEMBER, gated like
+     *  {@link LoomcycleClient.document}: it names only documents the caller can
+     *  list, in the one scope it asked for.
+     *
+     *  - The first item is `{ kind: "feed" }`; `payload.enabled === false` means
+     *    the server captures no changes — reload on a timer instead of waiting.
+     *  - Then one `{ kind: "change" }` per change. Changes of one type to one
+     *    document inside one server poll arrive as one.
+     *  - There is NO cursor and no resume: the stream starts now. After any
+     *    disconnect, reload your view and open a new stream.
+     *  - A `{ kind: "error" }` with code `store_unavailable` is non-fatal;
+     *    `access_unavailable`, `credential_revoked` and `credential_expired`
+     *    close the stream — reload and reconnect with a valid credential.
+     *  - The server re-authenticates the stream every 30 s: a revoked grant
+     *    stops that document's changes, and a revoked token ends the stream,
+     *    within that window; a token's expiry ends it on time.
+     *  - At most a few streams per principal (`LOOMCYCLE_DOCUMENT_FEED_MAX_STREAMS`,
+     *    default 4); one more is refused with a 429 — a `BackpressureError` with
+     *    code `too_many_streams`, not retryable until you close a stream.
+     *  - Iteration ends when the server closes the stream, or throws an
+     *    `AbortError` when `signal` aborts. */
+    documentFeed(opts: DocumentFeedOptions): AsyncIterable<DocumentFeedFrame>;
     private streamChangeFeed;
     /** List credential METADATA for a scope (RFC AR) — never a secret value.
      *  `user` = your own subject's tokens (per-user, e.g. a personal Telegram bot

package/dist/client.js

@@ -3535,6 +3535,42 @@ export class LoomcycleClient {
     async *streamDocumentChanges(opts) {
         yield* this.streamChangeFeed("/v1/_document/changes", opts);
     }
+    /** Watch one scope's DOCUMENTS change, as a reader (RFC FV). Mirrors
+     *  `GET /v1/_document/feed?scope=user|tenant[&scope_id=…][&tenant=…]`.
+     *
+     *  Unlike {@link LoomcycleClient.streamDocumentChanges} (the operator's
+     *  tenant-wide feed) this is open to a tenant MEMBER, gated like
+     *  {@link LoomcycleClient.document}: it names only documents the caller can
+     *  list, in the one scope it asked for.
+     *
+     *  - The first item is `{ kind: "feed" }`; `payload.enabled === false` means
+     *    the server captures no changes — reload on a timer instead of waiting.
+     *  - Then one `{ kind: "change" }` per change. Changes of one type to one
+     *    document inside one server poll arrive as one.
+     *  - There is NO cursor and no resume: the stream starts now. After any
+     *    disconnect, reload your view and open a new stream.
+     *  - A `{ kind: "error" }` with code `store_unavailable` is non-fatal;
+     *    `access_unavailable`, `credential_revoked` and `credential_expired`
+     *    close the stream — reload and reconnect with a valid credential.
+     *  - The server re-authenticates the stream every 30 s: a revoked grant
+     *    stops that document's changes, and a revoked token ends the stream,
+     *    within that window; a token's expiry ends it on time.
+     *  - At most a few streams per principal (`LOOMCYCLE_DOCUMENT_FEED_MAX_STREAMS`,
+     *    default 4); one more is refused with a 429 — a `BackpressureError` with
+     *    code `too_many_streams`, not retryable until you close a stream.
+     *  - Iteration ends when the server closes the stream, or throws an
+     *    `AbortError` when `signal` aborts. */
+    async *documentFeed(opts) {
+        if (opts.scope !== "user" && opts.scope !== "tenant") {
+            throw new Error(`loomcycle: documentFeed scope must be "user" or "tenant", got ${String(opts.scope)}`);
+        }
+        const q = new URLSearchParams({ scope: opts.scope, ...browseQuery(opts) });
+        for await (const ev of this.streamSSEGet(`/v1/_document/feed?${q.toString()}`, opts.signal)) {
+            const frame = toDocumentFeedFrame(ev);
+            if (frame)
+                yield frame;
+        }
+    }
     async *streamChangeFeed(path, opts) {
         const since = opts?.since;
         // The server reads an unparseable or negative `since` as 0 rather than
@@ -3869,6 +3905,26 @@ function toChangeFeedFrame(raw) {
     }
     return null;
 }
+/** toDocumentFeedFrame types one frame of the reader's document feed, or
+ *  returns null for one it does not recognise. `feed` and `error` frames are
+ *  read as on the operator feed; a reader `change` carries no `seq`, so it is
+ *  recognised by its `document_id`. */
+function toDocumentFeedFrame(raw) {
+    const shared = toChangeFeedFrame(raw);
+    if (shared?.kind === "feed") {
+        const { since: _since, ...status } = shared.payload;
+        return { kind: "feed", payload: status };
+    }
+    if (shared?.kind === "error")
+        return shared;
+    if (typeof raw.document_id === "string" &&
+        typeof raw.chunk_id === "string" &&
+        typeof raw.type === "string" &&
+        raw.type.startsWith("document.")) {
+        return { kind: "change", payload: raw };
+    }
+    return null;
+}
 // channelOpPath builds the v0.9.x Channel CRUD URL. Two families:
 //   - scope === "global" → /v1/_channels/{channel}/{op}
 //   - scope === "user"   → /v1/users/{userId}/channels/{channel}/{op}

package/dist/errors.js

@@ -66,9 +66,11 @@ const TRANSIENT_CODES = new Set([
 /** 429 codes that do NOT clear by waiting: the caller has to act first, so
  *  a retry loop on them never ends. `configured_run_cap`: the user already
  *  holds as many configured (not yet started) runs as the operator allows,
- *  and only starting or discarding one makes room. (A hard token budget,
- *  `token_limit_exceeded`, has a class of its own outside BackpressureError.) */
-const CALLER_ACTION_429_CODES = new Set(["configured_run_cap"]);
+ *  and only starting or discarding one makes room. `too_many_streams`: the
+ *  principal already holds as many document feed streams as allowed, and only
+ *  closing one makes room. (A hard token budget, `token_limit_exceeded`, has a
+ *  class of its own outside BackpressureError.) */
+const CALLER_ACTION_429_CODES = new Set(["configured_run_cap", "too_many_streams"]);
 /** Base class for every HTTP 404 the client surfaces. Lets callers
  *  catch any not-found case with a single `instanceof NotFoundError`
  *  check, regardless of which specific resource was missing

package/dist/index.d.ts

@@ -77,6 +77,7 @@
  *     // Memory / document change feeds (RFC CD Part C; SSE; substrate:tenant)
  *     streamMemoryChanges(opts?): AsyncIterable<ChangeFeedFrame>     // feed | change | error (non-fatal); resume with opts.since = last seq
  *     streamDocumentChanges(opts?): AsyncIterable<ChangeFeedFrame>
+ *     documentFeed(opts): AsyncIterable<DocumentFeedFrame>           // RFC FV: member-safe, one scope, no cursor (reconnect = resync)
  *
  *     // Interruption (v0.8.16; decline RFC BH)
  *     listUserInterrupts(userId, opts?): Promise<InterruptListResponse>
@@ -216,5 +217,5 @@ export { ClientToolHost, clientToolsURL, CLIENT_TOOL_SUBPROTOCOL } from "./clien
 export type { ClientToolSchema, ClientToolInvocation, ConnectClientToolsOptions, WebSocketLike, WebSocketCtor, } from "./client-tools.js";
 export { LoomcycleOAuth, OAuthTokenProvider, parseAuthorizeResponse, pkceChallenge } from "./oauth.js";
 export type { LoomcycleOAuthOptions, OAuthTokenProviderOptions } from "./oauth.js";
-export type { AgentEvent, ClientOptions, ContinueOptions, EventType, HostWidening, ImageMediaType, ParentContext, PromptContent, PromptSegment, RetryInfo, RunOptions, RunOverrideOptions, SamplingOptions, CompactionOptions, ContextOptions, ToolUse, Usage, CallTiming, Agent, AgentStatus, AwaitedState, AgentUsage, RunResult, RunSpec, RunSpecTeam, ConfiguredRun, ConfiguredRunPatch, ToolChoiceOptions, OutputFormatOptions, CancelAgentResult, ListAgentsResponse, ListUserAgentsOptions, AgentList, WalkRunsPage, RunBatchOptions, RunBatchResult, SpawnRunResult, CompactRunResult, RunTreeDeletion, RunTreeNotReached, DirectoryBudget, DirectoryInspection, DirectoryTenant, DirectoryUser, ErasureAccess, ErasureReport, ErasureResidue, ErasureResult, ErasureTier, MergeSubjectsResult, SubjectRef, BindSubjectPrincipalResult, ReviewQueueFilter, ReviewQueueGroup, ReviewQueueResult, RuleStatementsResult, RevertRulingResult, RulingBreakdown, RulingItem, RulingSelector, RulingRecord, ListRulingsResult, PolicyRuleCount, ApplyReviewPolicyResult, ErasureBoundSubject, ErasureTokenRef, CancelTurnResult, ReviewRunResult, ReplaySessionResult, TranscriptEvent, TranscriptResponse, HealthResponse, ListUsersResponse, UserSummary, UserStatus, UserRecord, CreateUserBody, UpdateUserBody, MintedUserToken, TokenRestrictions, UserTokenMeta, ListUserTokensResponse, UserIdentity, UserIdentitiesResponse, AuthGateKind, AuthGate, AuthGateKey, AuthGateRemoval, AuthGateProbe, AuthGateListResponse, CreateInviteBody, CreatedInvite, AuthInviteState, AuthInvite, AuthInviteListResponse, CreatedPasswordReset, GateIdentity, GateIdentitiesResponse, GateTenantStatus, RunnableAgent, RunnableAgentsResponse, WhoamiResponse, WhoamiEffective, WhoamiAuth, PauseResult, RetentionOverride, ResumeResult, RuntimeStateResponse, RuntimeStateStatus, ResolverMatrix, ResolverModelStatus, ResolverProviderAvailability, CreateSnapshotOptions, SnapshotCreateResponse, SnapshotDescriptor, SnapshotEnvelope, SnapshotListResponse, SnapshotRestoreResponse, MemoryEntriesResponse, MemoryEntry, MemoryEntryResponse, MemoryScopeIDsResponse, MemoryScopeIDSummary, MemoryScopeKind, MemoryScopesResponse, MemorySearchDocumentFilter, MemorySearchInput, MemorySource, MemoryWhen, MemoryTimeFilter, MemorySearchEntry, MemorySearchResponse, MemoryEmbedModelStats, MemoryEmbedStatsResponse, MemoryReembedConfigured, MemoryReembedResponse, MemoryBackfillResponse, MemoryPurgeResponse, InterruptListResponse, InterruptRow, InterruptStatus, ResolveInterruptOptions, ChannelHookCall, ChannelHookResult, HookFailMode, HookPhase, HookToolCall, HookToolResult, PostHookCall, PostHookResult, PreHookCall, PreHookResult, SubstrateToolInput, SubstrateToolResponse, TeamNameSummary, ListTeamsResponse, TeamDiagram, CreatedTeam, PromotedTeam, RetiredTeam, TeamDefDetail, TeamVerification, TeamDraft, TeamDraftVerification, TeamIssue, TeamIssueKind, TeamVersion, TeamVersionList, TeamBreakpoints, TeamRunDetached, TeamRunResult, TeamRunTarget, CreateTeamOptions, ForkTeamOptions, DefNameSummary, DefNamesResponse, OperatorTokenDefNameSummary, OperatorTokenDefNamesResponse, ScheduleListEntry, ScheduleListResponse, ScheduleActiveRun, ScheduleStateView, ScheduleRunNowResult, SchedulePauseResult, ModelAlias, ModelAliasesResponse, RoutingResponse, RoutingUserTier, RoutingTier, RoutingCandidate, RoutingThroughput, RoutingProvider, SearchRoutingProvider, RoutingEmbedder, RoutingDecision, RoutingDecisionModel, ProviderModelsResponse, TeamRunStep, TeamDecisionHandler, TeamDecisionQuestion, TeamDecisionAnswer, PathToolInput, PathToolResponse, DocumentToolInput, DocumentEdgeEvidence, DocumentToolResponse, DocumentSearchFilter, DocumentSearchHit, DocumentSearchResult, DocumentRelatedResult, HistoryToolInput, HistoryToolResponse, EvaluationEmitterRole, EvaluationSubmitInput, EvaluationGetInput, EvaluationListForRunInput, EvaluationListForDefInput, EvaluationAggregateInput, EvaluationInput, EvaluationSubmitResult, EvaluationRecord, EvaluationListForRunResult, EvaluationListForDefResult, EvaluationScoreStats, EvaluationAggregate, VolumeMode, PersistentVolumeEntry, PersistentVolumesResponse, EphemeralVolumeEntry, EphemeralVolumesResponse, SystemPromptPayload, UserInputPayload, ChannelDescriptor, ListChannelsResponse, RunStateEvent, RunStateStreamClose, RunStateStreamItem, RunStateStreamOpen, StreamUserRunStatesOptions, ChangeFeedError, ChangeFeedFrame, ChangeFeedStatus, EmbedderHealth, MemoryChange, MemoryChangeScope, MemoryChangeType, StreamChangesOptions, AckChannelOptions, ChannelAckResult, ChannelMessageItem, ChannelPeekResult, ListTeamChannelsOptions, PeekTeamChannelOptions, ReleaseTeamChannelOptions, TeamChannelReleaseResult, TeamChannelDeclaredIn, TeamChannelDescriptor, TeamChannelPeekResult, TeamChannelsResult, ChannelPublishResult, ChannelPurgeResult, ChannelReleaseResult, ChannelScope, ChannelSubscribeResult, PeekChannelOptions, PublishChannelOptions, SubscribeChannelOptions, AwaitChannelsOptions, BroadcastChannelsOptions, ChannelAwaitEntry, ChannelAwaitMode, ChannelAwaitResult, ChannelBroadcastEntry, ChannelBroadcastResult, CreateChannelOptions, ReleaseChannelOptions, UpdateChannelOptions, SetMemoryEntryOptions, SetMemoryEntryResponse, AgentDefRowResponse, AgentDefVerifyResult, SkillDefVerifyResult, EnsureMcpServerOptions, EnsureMcpServerResult, MCPServerDefRowResponse, MCPServerDefVerifyResult, AgentDefOverlay, AgentRouting, AgentChannelACL, AgentInterruptionACL, AgentDecision, MemoryRerank, AgentSampling, AgentCompaction, AgentTranscription, AgentSpeech, AgentContext, TierCandidate, CoreBlock, HookEvent, InlineWebhook, HookEntry, EventHooks, ToolEntry, ToolHooksByTool, EnsureCodeAgentOptions, EnsureCodeAgentResult, CreateDefOptions, ForkDefOptions, EnsureHookDefOptions, EnsureHookDefResult, HookDefBody, HookDefForkOverlay, HookDefInput, HookDefMatch, HookDefOverlay, HookDefRowResponse, HookDefVerifyResult, ScheduleDefInput, ScheduleDefOverlay, ScheduleDefRowResponse, ScheduledRunHook, ScheduledRunPromptContent, ScheduledRunPromptSegment, WebhookDefAuth, WebhookDefFilter, WebhookDefInput, WebhookDefOverlay, WebhookDefRateLimit, WebhookDefRowResponse, WebhookDefDeliveries, WebhookDefSyncResponse, LibraryAgentDefinition, LibraryEntry, LibraryListResponse, LibraryMcpServerDefinition, LibrarySkillDefinition, LLMChatContent, LLMChatMessage, LLMChatOptions, LLMChatResponse, LLMChatStreamDelta, LLMChatStreamItem, LLMChatToolCall, LLMChatUsage, LLMTool, LLMEmbeddingItem, LLMEmbeddingsOptions, LLMEmbeddingsResponse, LLMEmbeddingsUsage, UsageDimension, UsageBucket, UsageAggregate, UsageReportResponse, CapabilityInertInfo, LimitInfo, FileCapturedInfo, TranscriptionInfo, AdmissionInfo, ErrorInfo, CallFormat, CallRef, HookDecisionInfo, TeamDecisionInfo, OverrideInfo, FallbackInfo, InterruptionEventInfo, SpawnChildInfo, TurnCancelledInfo, ChannelEventInfo, ContextCompactionInfo, ContextRecapInfo, ContextStateInfo, ContextExhaustedInfo, ContextTierVerdict, ContextDistillDeclinedInfo, EffectiveConfigResponse, RunFileInput, RunFileImportSource, RunFileImportHeading, RunInboxDownload, EffectiveConfigSource, EffectiveValue, InertContextSetting, AgentOverridableResponse, OverridableField, OverrideLockReason, RetuneRunResponse, RunConfigRecord, SubagentHoldInfo, RunConfigResponse, RunPromptResponse, RunPromptSnapshot, PromptBlock, TokenLimit, TokenLimitsResponse, ConfigResponse, ConfigProvider, ConfigModel, ConfigSearch, ConfigInstance, SetTokenLimitRequest, CredentialScope, CredentialMeta, CredentialListResponse, CryptoKeyVersion, CryptoKeyExport, CryptoKeyType, CryptoKeyEncoding, CryptoKeyBackend, CryptoKeyExternal, CryptoOp, CryptoRequestBase, CryptoKeyRef, CryptoEncryptRequest, CryptoDecryptRequest, CryptoRewrapRequest, CryptoMacRequest, CryptoVerifyMacRequest, CryptoSignRequest, CryptoVerifyRequest, CryptoPublicKeyRequest, CryptoTotpRequest, CryptoHashRequest, CryptoRandomRequest, CryptoHashPasswordRequest, CryptoVerifyPasswordRequest, CryptoRequest, CryptoEncryptResult, CryptoDecryptResult, CryptoRewrapResult, CryptoMacResult, CryptoVerifyResult, CryptoSignResult, CryptoPublicJWK, CryptoPublicKeyResult, CryptoTotpResult, CryptoHashResult, CryptoRandomResult, CryptoHashPasswordResult, CryptoVerifyPasswordResult, CryptoResultByOp, CryptoResult, DecideRequest, DecideResponse, DecisionQuestion, DecisionChoiceQuestion, DecisionNoulQuestion, DecisionScoreQuestion, DecisionAnswer, DecisionChoiceAnswer, DecisionNoulAnswer, DecisionScoreAnswer, DecisionModel, DecisionModelsResponse, AclMode, AclSource, AclEffect, AclSubjectKind, AclCondition, AclRule, AclList, AclDefRow, AclDefListResponse, AclDefNamesResponse, AclValidateResult, AclCatalogType, AclCatalog, AclDefOp, AclDefInput, GroupRow, GroupMemberKind, GroupMember, GroupListResponse, GroupDetail, GroupEffective, CreateGroupBody, GroupMemberChange, AclBinding, AclBindingListResponse, CreateAclBindingBody, AuthzReason, AuthzDecision, AuthzRequestContext, AuthzEvaluationRequest, AuthzEvaluationsSemantic, AuthzEvaluationsRequest, AuthzEvaluationsResponse, AuthzTrace, AuthzAppliedBinding, AuthzExplainResponse, AuthzDraftBinding, AuthzSimulateRequest, AuthzSimulateResult, AuthzSimulateResponse, OAuthServerMetadata, OAuthTokenResponse, OAuthTokenSet, BeginAuthorizeOptions, AuthorizeRequest, AuthorizeResponseParams, CompleteAuthorizeOptions, RefreshTokenOptions, RevokeTokenOptions, TokenProvider, AppClientRefresh, AppClientConfig, ClientDefInput, ClientDefRecord, ConfigAppClient, AppClientEntry, ClientDefListResponse, ClientDefVerifyResult, ClientDefRetireResult, ClientDefNameSummary, ClientDefNamesResponse, DeviceLoginPrompt, DeviceLoginOptions, DeviceLoginResult, } from "./types.js";
+export type { AgentEvent, ClientOptions, ContinueOptions, EventType, HostWidening, ImageMediaType, ParentContext, PromptContent, PromptSegment, RetryInfo, RunOptions, RunOverrideOptions, SamplingOptions, CompactionOptions, ContextOptions, ToolUse, Usage, CallTiming, Agent, AgentStatus, AwaitedState, AgentUsage, RunResult, RunSpec, RunSpecTeam, ConfiguredRun, ConfiguredRunPatch, ToolChoiceOptions, OutputFormatOptions, CancelAgentResult, ListAgentsResponse, ListUserAgentsOptions, AgentList, WalkRunsPage, RunBatchOptions, RunBatchResult, SpawnRunResult, CompactRunResult, RunTreeDeletion, RunTreeNotReached, DirectoryBudget, DirectoryInspection, DirectoryTenant, DirectoryUser, ErasureAccess, ErasureReport, ErasureResidue, ErasureResult, ErasureTier, MergeSubjectsResult, SubjectRef, BindSubjectPrincipalResult, ReviewQueueFilter, ReviewQueueGroup, ReviewQueueResult, RuleStatementsResult, RevertRulingResult, RulingBreakdown, RulingItem, RulingSelector, RulingRecord, ListRulingsResult, PolicyRuleCount, ApplyReviewPolicyResult, ErasureBoundSubject, ErasureTokenRef, CancelTurnResult, ReviewRunResult, ReplaySessionResult, TranscriptEvent, TranscriptResponse, HealthResponse, ListUsersResponse, UserSummary, UserStatus, UserRecord, CreateUserBody, UpdateUserBody, MintedUserToken, TokenRestrictions, UserTokenMeta, ListUserTokensResponse, UserIdentity, UserIdentitiesResponse, AuthGateKind, AuthGate, AuthGateKey, AuthGateRemoval, AuthGateProbe, AuthGateListResponse, CreateInviteBody, CreatedInvite, AuthInviteState, AuthInvite, AuthInviteListResponse, CreatedPasswordReset, GateIdentity, GateIdentitiesResponse, GateTenantStatus, RunnableAgent, RunnableAgentsResponse, WhoamiResponse, WhoamiEffective, WhoamiAuth, PauseResult, RetentionOverride, ResumeResult, RuntimeStateResponse, RuntimeStateStatus, ResolverMatrix, ResolverModelStatus, ResolverProviderAvailability, CreateSnapshotOptions, SnapshotCreateResponse, SnapshotDescriptor, SnapshotEnvelope, SnapshotListResponse, SnapshotRestoreResponse, MemoryEntriesResponse, MemoryEntry, MemoryEntryResponse, MemoryScopeIDsResponse, MemoryScopeIDSummary, MemoryScopeKind, MemoryScopesResponse, MemorySearchDocumentFilter, MemorySearchInput, MemorySource, MemoryWhen, MemoryTimeFilter, MemorySearchEntry, MemorySearchResponse, MemoryEmbedModelStats, MemoryEmbedStatsResponse, MemoryReembedConfigured, MemoryReembedResponse, MemoryBackfillResponse, MemoryPurgeResponse, InterruptListResponse, InterruptRow, InterruptStatus, ResolveInterruptOptions, ChannelHookCall, ChannelHookResult, HookFailMode, HookPhase, HookToolCall, HookToolResult, PostHookCall, PostHookResult, PreHookCall, PreHookResult, SubstrateToolInput, SubstrateToolResponse, TeamNameSummary, ListTeamsResponse, TeamDiagram, CreatedTeam, PromotedTeam, RetiredTeam, TeamDefDetail, TeamVerification, TeamDraft, TeamDraftVerification, TeamIssue, TeamIssueKind, TeamVersion, TeamVersionList, TeamBreakpoints, TeamRunDetached, TeamRunResult, TeamRunTarget, CreateTeamOptions, ForkTeamOptions, DefNameSummary, DefNamesResponse, OperatorTokenDefNameSummary, OperatorTokenDefNamesResponse, ScheduleListEntry, ScheduleListResponse, ScheduleActiveRun, ScheduleStateView, ScheduleRunNowResult, SchedulePauseResult, ModelAlias, ModelAliasesResponse, RoutingResponse, RoutingUserTier, RoutingTier, RoutingCandidate, RoutingThroughput, RoutingProvider, SearchRoutingProvider, RoutingEmbedder, RoutingDecision, RoutingDecisionModel, ProviderModelsResponse, TeamRunStep, TeamDecisionHandler, TeamDecisionQuestion, TeamDecisionAnswer, PathToolInput, PathToolResponse, DocumentToolInput, DocumentEdgeEvidence, DocumentToolResponse, DocumentSearchFilter, DocumentSearchHit, DocumentSearchResult, DocumentRelatedResult, GraphSnapshot, HistoryToolInput, HistoryToolResponse, EvaluationEmitterRole, EvaluationSubmitInput, EvaluationGetInput, EvaluationListForRunInput, EvaluationListForDefInput, EvaluationAggregateInput, EvaluationInput, EvaluationSubmitResult, EvaluationRecord, EvaluationListForRunResult, EvaluationListForDefResult, EvaluationScoreStats, EvaluationAggregate, VolumeMode, PersistentVolumeEntry, PersistentVolumesResponse, EphemeralVolumeEntry, EphemeralVolumesResponse, SystemPromptPayload, UserInputPayload, ChannelDescriptor, ListChannelsResponse, RunStateEvent, RunStateStreamClose, RunStateStreamItem, RunStateStreamOpen, StreamUserRunStatesOptions, ChangeFeedError, ChangeFeedFrame, ChangeFeedStatus, EmbedderHealth, MemoryChange, MemoryChangeScope, MemoryChangeType, StreamChangesOptions, DocumentFeedChange, DocumentFeedChangeType, DocumentFeedFrame, DocumentFeedOptions, DocumentFeedStatus, AckChannelOptions, ChannelAckResult, ChannelMessageItem, ChannelPeekResult, ListTeamChannelsOptions, PeekTeamChannelOptions, ReleaseTeamChannelOptions, TeamChannelReleaseResult, TeamChannelDeclaredIn, TeamChannelDescriptor, TeamChannelPeekResult, TeamChannelsResult, ChannelPublishResult, ChannelPurgeResult, ChannelReleaseResult, ChannelScope, ChannelSubscribeResult, PeekChannelOptions, PublishChannelOptions, SubscribeChannelOptions, AwaitChannelsOptions, BroadcastChannelsOptions, ChannelAwaitEntry, ChannelAwaitMode, ChannelAwaitResult, ChannelBroadcastEntry, ChannelBroadcastResult, CreateChannelOptions, ReleaseChannelOptions, UpdateChannelOptions, SetMemoryEntryOptions, SetMemoryEntryResponse, AgentDefRowResponse, AgentDefVerifyResult, SkillDefVerifyResult, EnsureMcpServerOptions, EnsureMcpServerResult, MCPServerDefRowResponse, MCPServerDefVerifyResult, AgentDefOverlay, AgentRouting, AgentChannelACL, AgentInterruptionACL, AgentDecision, MemoryRerank, AgentSampling, AgentCompaction, AgentTranscription, AgentSpeech, AgentContext, TierCandidate, CoreBlock, HookEvent, InlineWebhook, HookEntry, EventHooks, ToolEntry, ToolHooksByTool, EnsureCodeAgentOptions, EnsureCodeAgentResult, CreateDefOptions, ForkDefOptions, EnsureHookDefOptions, EnsureHookDefResult, HookDefBody, HookDefForkOverlay, HookDefInput, HookDefMatch, HookDefOverlay, HookDefRowResponse, HookDefVerifyResult, ScheduleDefInput, ScheduleDefOverlay, ScheduleDefRowResponse, ScheduledRunHook, ScheduledRunPromptContent, ScheduledRunPromptSegment, WebhookDefAuth, WebhookDefFilter, WebhookDefInput, WebhookDefOverlay, WebhookDefRateLimit, WebhookDefRowResponse, WebhookDefDeliveries, WebhookDefSyncResponse, LibraryAgentDefinition, LibraryEntry, LibraryListResponse, LibraryMcpServerDefinition, LibrarySkillDefinition, LLMChatContent, LLMChatMessage, LLMChatOptions, LLMChatResponse, LLMChatStreamDelta, LLMChatStreamItem, LLMChatToolCall, LLMChatUsage, LLMTool, LLMEmbeddingItem, LLMEmbeddingsOptions, LLMEmbeddingsResponse, LLMEmbeddingsUsage, UsageDimension, UsageBucket, UsageAggregate, UsageReportResponse, CapabilityInertInfo, LimitInfo, FileCapturedInfo, TranscriptionInfo, AdmissionInfo, ErrorInfo, CallFormat, CallRef, HookDecisionInfo, TeamDecisionInfo, OverrideInfo, FallbackInfo, InterruptionEventInfo, SpawnChildInfo, TurnCancelledInfo, ChannelEventInfo, ContextCompactionInfo, ContextRecapInfo, ContextStateInfo, ContextExhaustedInfo, ContextTierVerdict, ContextDistillDeclinedInfo, EffectiveConfigResponse, RunFileInput, RunFileImportSource, RunFileImportHeading, RunInboxDownload, EffectiveConfigSource, EffectiveValue, InertContextSetting, AgentOverridableResponse, OverridableField, OverrideLockReason, RetuneRunResponse, RunConfigRecord, SubagentHoldInfo, RunConfigResponse, RunPromptResponse, RunPromptSnapshot, PromptBlock, TokenLimit, TokenLimitsResponse, ConfigResponse, ConfigProvider, ConfigModel, ConfigSearch, ConfigInstance, SetTokenLimitRequest, CredentialScope, CredentialMeta, CredentialListResponse, CryptoKeyVersion, CryptoKeyExport, CryptoKeyType, CryptoKeyEncoding, CryptoKeyBackend, CryptoKeyExternal, CryptoOp, CryptoRequestBase, CryptoKeyRef, CryptoEncryptRequest, CryptoDecryptRequest, CryptoRewrapRequest, CryptoMacRequest, CryptoVerifyMacRequest, CryptoSignRequest, CryptoVerifyRequest, CryptoPublicKeyRequest, CryptoTotpRequest, CryptoHashRequest, CryptoRandomRequest, CryptoHashPasswordRequest, CryptoVerifyPasswordRequest, CryptoRequest, CryptoEncryptResult, CryptoDecryptResult, CryptoRewrapResult, CryptoMacResult, CryptoVerifyResult, CryptoSignResult, CryptoPublicJWK, CryptoPublicKeyResult, CryptoTotpResult, CryptoHashResult, CryptoRandomResult, CryptoHashPasswordResult, CryptoVerifyPasswordResult, CryptoResultByOp, CryptoResult, DecideRequest, DecideResponse, DecisionQuestion, DecisionChoiceQuestion, DecisionNoulQuestion, DecisionScoreQuestion, DecisionAnswer, DecisionChoiceAnswer, DecisionNoulAnswer, DecisionScoreAnswer, DecisionModel, DecisionModelsResponse, AclMode, AclSource, AclEffect, AclSubjectKind, AclCondition, AclRule, AclList, AclDefRow, AclDefListResponse, AclDefNamesResponse, AclValidateResult, AclCatalogType, AclCatalog, AclDefOp, AclDefInput, GroupRow, GroupMemberKind, GroupMember, GroupListResponse, GroupDetail, GroupEffective, CreateGroupBody, GroupMemberChange, AclBinding, AclBindingListResponse, CreateAclBindingBody, AuthzReason, AuthzDecision, AuthzRequestContext, AuthzEvaluationRequest, AuthzEvaluationsSemantic, AuthzEvaluationsRequest, AuthzEvaluationsResponse, AuthzTrace, AuthzAppliedBinding, AuthzExplainResponse, AuthzDraftBinding, AuthzSimulateRequest, AuthzSimulateResult, AuthzSimulateResponse, OAuthServerMetadata, OAuthTokenResponse, OAuthTokenSet, BeginAuthorizeOptions, AuthorizeRequest, AuthorizeResponseParams, CompleteAuthorizeOptions, RefreshTokenOptions, RevokeTokenOptions, TokenProvider, AppClientRefresh, AppClientConfig, ClientDefInput, ClientDefRecord, ConfigAppClient, AppClientEntry, ClientDefListResponse, ClientDefVerifyResult, ClientDefRetireResult, ClientDefNameSummary, ClientDefNamesResponse, DeviceLoginPrompt, DeviceLoginOptions, DeviceLoginResult, } from "./types.js";
 export { AclDeniedError, AgentIDInUseError, AgentNotFoundError, AlreadyPausingError, AuthError, BackpressureError, DeviceLoginError, NotFoundError, InsufficientScopeError, InvalidArgumentError, ChannelCursorRegressionError, LoomcycleError, NotPausedError, OAuthError, PauseNotConfiguredError, PerUserQuotaExhaustedError, PromptTooLargeError, RateLimitedError, RequestTooLargeError, SessionBusyError, SessionNotFoundError, SnapshotNotFoundError, SnapshotTooLargeError, SnapshotVersionError, SubstrateToolRefusedError, TokenLimitExceededError, UnavailableError, } from "./errors.js";

package/dist/index.js

@@ -77,6 +77,7 @@
  *     // Memory / document change feeds (RFC CD Part C; SSE; substrate:tenant)
  *     streamMemoryChanges(opts?): AsyncIterable<ChangeFeedFrame>     // feed | change | error (non-fatal); resume with opts.since = last seq
  *     streamDocumentChanges(opts?): AsyncIterable<ChangeFeedFrame>
+ *     documentFeed(opts): AsyncIterable<DocumentFeedFrame>           // RFC FV: member-safe, one scope, no cursor (reconnect = resync)
  *
  *     // Interruption (v0.8.16; decline RFC BH)
  *     listUserInterrupts(userId, opts?): Promise<InterruptListResponse>

package/dist/types.d.ts

@@ -3767,7 +3767,7 @@ export type DocumentEdgeEvidence = {
     char_end?: number;
 };
 export type DocumentToolInput = {
-    op: "create_document" | "get_document" | "documents_summary" | "query_documents" | "delete_document" | "set_path" | "create_chunk" | "upsert_chunk" | "get_chunk" | "update_chunk" | "delete_chunk" | "supersede_chunk" | "graph_recall" | "move_chunk" | "reorder_chunk" | "link_chunks" | "unlink_chunks" | "get_edges" | "get_edge" | "propose_statement" | "accept_statement" | "reject_statement" | "list_statements" | "judge_statements" | "maintain_statement" | "resolve_anchor" | "lease" | "release" | "describe_ontology" | "extract_citations" | "classify" | "accept_classification" | "query_chunks" | "add_tags" | "remove_tags" | "list_tags" | "define_type" | "list_types" | "set_asset" | "get_asset" | "export_md" | "import_md" | "backlinks" | "related" | "unlinked_mentions" | "history" | "get_version" | "diff" | "export_canvas" | "import_canvas" | "list_facts" | "judge_fact" | "verbatim_answer" | "verification_stats" | "remember" | "propose_entity" | "propose_subject" | "search" | "set_remote" | "sync" | "diff_remote";
+    op: "create_document" | "get_document" | "documents_summary" | "query_documents" | "graph_snapshot" | "delete_document" | "set_path" | "copy_documents" | "create_chunk" | "upsert_chunk" | "get_chunk" | "update_chunk" | "delete_chunk" | "supersede_chunk" | "graph_recall" | "move_chunk" | "reorder_chunk" | "link_chunks" | "unlink_chunks" | "get_edges" | "get_edge" | "propose_statement" | "accept_statement" | "reject_statement" | "list_statements" | "judge_statements" | "maintain_statement" | "resolve_anchor" | "lease" | "release" | "describe_ontology" | "extract_citations" | "classify" | "accept_classification" | "query_chunks" | "add_tags" | "remove_tags" | "list_tags" | "define_type" | "list_types" | "set_asset" | "get_asset" | "export_md" | "import_md" | "backlinks" | "related" | "unlinked_mentions" | "history" | "get_version" | "diff" | "export_canvas" | "import_canvas" | "list_facts" | "judge_fact" | "verbatim_answer" | "verification_stats" | "remember" | "propose_entity" | "propose_subject" | "search" | "set_remote" | "sync" | "diff_remote";
     scope?: "agent" | "user" | "tenant";
     /** Document id (get/delete_document) or chunk id (get/update/delete/move_chunk). */
     id?: string;
@@ -3835,8 +3835,9 @@ export type DocumentToolInput = {
      *  names ONE source (chunk_id; session_id + event_seq; or scope + natural_key)
      *  and the verbatim quote, which the server checks against that source. */
     evidence?: DocumentEdgeEvidence[];
-    /** get_edges (default true) / backlinks (default false): include relations
-     *  proposed for review. graph_recall (default false): also follow them. */
+    /** get_edges (default true) / backlinks (default false) / graph_snapshot
+     *  (default false): include relations proposed for review. graph_recall
+     *  (default false): also follow them. */
     include_proposed?: boolean;
     /** get_edges / backlinks / graph_recall / list_facts: also return what has been
      *  retired (superseded relations and facts). list_statements: also list
@@ -3848,8 +3849,9 @@ export type DocumentToolInput = {
     /** get_edges: out | in | both (default both). reorder_chunk: up | down. sync /
      *  diff_remote: pull (default) | push. */
     direction?: "out" | "in" | "both" | "up" | "down" | "pull" | "push";
-    /** get_edges / backlinks / list_statements: the next_cursor of the previous page
-     *  (list_statements: with the same `order`). */
+    /** get_edges / backlinks / list_statements / graph_snapshot: the next_cursor
+     *  of the previous page (list_statements: with the same `order`;
+     *  graph_snapshot: `page.next_cursor`). */
     after?: string;
     /** list_statements: only relations with an evidence row quoting a chunk of
      *  this document. (`document_id` keeps relations with either end in it.) */
@@ -3873,6 +3875,9 @@ export type DocumentToolInput = {
         hops?: 1;
         budget_chars?: number;
     };
+    /** search: also return `query_xyz`, the query placed on the scope's 3D map
+     *  (the axes of graph_snapshot's `projection` block). Absent without a map. */
+    with_projection?: boolean;
     /** related: a chunk whose neighbours BY RELATION to return as `linked`. */
     related_to?: string;
     /** import_md: the markdown is a new edition of document_id / work_key. */
@@ -3911,11 +3916,31 @@ export type DocumentToolInput = {
     /** search / related: never chunks of documents named at or under these paths. */
     exclude_under_paths?: string[];
     /** documents_summary: the documents to summarize. search / related: return
-     *  only chunks of these documents. */
+     *  only chunks of these documents. copy_documents: the documents to copy. */
     document_ids?: string[];
+    /** copy_documents: the scope the copies go to (`scope` is where they are). */
+    to_scope?: "agent" | "user" | "tenant";
+    /** copy_documents: Path prefixes to rewrite, from → to; the longest wins. */
+    path_map?: Record<string, string>;
+    /** copy_documents: true (the default) reports without writing. */
+    dry_run?: boolean;
     /** search / related: never chunks of these documents (e.g. the document under
      *  review, so its own text is not found as evidence for itself). */
     exclude_document_ids?: string[];
+    /** graph_snapshot: only the documents holding these chunks (with
+     *  `document_ids`, the union). A chunk of a document the caller may not read
+     *  selects nothing, as a missing id does. */
+    chunk_ids?: string[];
+    /** graph_snapshot: the sections to return (default all but `projection`).
+     *  `chunks` needs `documents`; `edges`, `facts` and `projection` need
+     *  `chunks`. */
+    include?: Array<"documents" | "chunks" | "edges" | "dirents" | "facts" | "projection">;
+    /** graph_snapshot: documents per page (default 200, at most 1000 — a larger
+     *  value is lowered, never refused). A page always holds whole documents. */
+    page_documents?: number;
+    /** graph_snapshot: the most relations one page returns (default 50000, at
+     *  most 200000); `edges.truncated` says it was reached. */
+    edge_budget?: number;
     /** search / related: chunk types, each including its ontology subtypes (with
      *  `type`, the union of both). */
     types?: string[];
@@ -4088,6 +4113,9 @@ export type DocumentSearchResult = {
     filter?: DocumentSearchFilter;
     reranked?: boolean;
     rerank_reason?: string;
+    /** With `with_projection` and a map for the scope: the query's place on it
+     *  (4 decimals). */
+    query_xyz?: [number, number, number];
 };
 /** Response of `document({op:"related"})` — narrow a {@link DocumentToolResponse}
  *  to it. */
@@ -4103,6 +4131,108 @@ export type DocumentRelatedResult = {
     }>;
     filter?: DocumentSearchFilter;
 };
+/** Response of `document({op:"graph_snapshot"})` — narrow a
+ *  {@link DocumentToolResponse} to it. Columnar: every array of a section is
+ *  parallel (position `i` of each describes one item). An `*_idx` column is a
+ *  position in another section of the same response; a `*_code` column is a
+ *  position in the matching `codes` list, `-1` = none. Timestamps are unix
+ *  nanoseconds. Documents the caller may not read are absent, with their
+ *  chunks, the relations into them and their Path names. */
+export type GraphSnapshot = {
+    page: {
+        /** Documents on this page — always whole documents, in id order. */
+        documents: number;
+        /** Pass as `after` for the next page; absent on the last one. */
+        next_cursor?: string;
+        /** Present when the SQL Memory row cap fitted fewer documents than asked. */
+        clamped_to?: number;
+    };
+    codes: {
+        types: string[];
+        statuses: string[];
+        kinds: string[];
+        fact_classes: string[];
+        methods: string[];
+    };
+    documents?: {
+        ids: string[];
+        titles: string[];
+        root_chunk_ids: string[];
+        type_code: number[];
+        status_code: number[];
+        created_at: number[];
+        updated_at: number[];
+        color_enabled: boolean[];
+        color_scheme: Array<Record<string, unknown> | null>;
+        /** Every Path name of each document, shortest first. */
+        paths: string[][];
+    };
+    chunks?: {
+        ids: string[];
+        document_idx: number[];
+        /** -1 = a root. Always an earlier position: parents come first. */
+        parent_idx: number[];
+        position: number[];
+        type_code: number[];
+        status_code: number[];
+        titles: string[];
+        valid_at: Array<number | null>;
+        invalid_at: Array<number | null>;
+        updated_at: number[];
+        /** Only with `include` naming `facts`. */
+        is_fact?: boolean[];
+        fact_class_code?: number[];
+        fact_confidence?: Array<number | null>;
+        fact_retired?: boolean[];
+    };
+    edges?: {
+        ids: string[];
+        /** A chunk position, or a negative `external[].idx`. */
+        from_idx: number[];
+        to_idx: number[];
+        kind_code: number[];
+        auto: boolean[];
+        created_at: number[];
+        status_code: number[];
+        method_code: number[];
+        confidence: Array<number | null>;
+        valid_at: Array<number | null>;
+        invalid_at: Array<number | null>;
+        /** Ends on another page (or outside the selection). */
+        external: Array<{
+            idx: number;
+            id: string;
+            document_id: string;
+        }>;
+        /** True when `edge_budget` stopped the list. */
+        truncated: boolean;
+    };
+    /** First page only. */
+    dirents?: {
+        paths: string[];
+        kinds: Array<"directory" | "document">;
+        /** A position in `documents` when the document is on this page, else -1. */
+        document_idx: number[];
+        /** The document a name points at ("" for a directory), whatever its page. */
+        document_ids: string[];
+    };
+    /** Only with `include` naming `projection`: each chunk's place on the
+     *  scope's 3D map by meaning. `method` says how the map was fitted: `pca`
+     *  (the embedding on the scope's three principal axes) or `umap` (a layout
+     *  that keeps each chunk's nearest neighbours near it, so a document's
+     *  chunks stay together); absent while the projection is off. `model` is
+     *  the embedder ("<provider>/<model>"); `basis_version` 0 means no map yet,
+     *  with `xyz` empty and every chunk missing. Otherwise `xyz` is one x, y, z
+     *  triple per chunk in `chunks.ids` order (4 decimals), and a chunk with no
+     *  place on the current map is 0, 0, 0 with its position in `missing`. */
+    projection?: {
+        model: string;
+        basis_version: number;
+        method?: "pca" | "umap";
+        xyz: number[];
+        missing: number[];
+    };
+};
 /** Input for {@link LoomcycleClient.history} — the RFC BE History tool
  *  (POST /v1/_history). Browse/search/annotate PAST CHATS (a chat = a session).
  *  Op-discriminated; the owner is resolved server-side from the authenticated
@@ -7084,7 +7214,10 @@ export interface ForkTeamOptions extends CreateTeamOptions {
  *  {@link LoomcycleClient.streamMemoryChanges}, `document.chunk.*` on
  *  {@link LoomcycleClient.streamDocumentChanges}. Mirrors the runtime's
  *  `store.MemoryChangeType`. */
-export type MemoryChangeType = "memory.set" | "memory.delete" | "memory.scope_deleted" | "document.chunk.updated" | "document.chunk.deleted";
+export type MemoryChangeType = "memory.set" | "memory.delete" | "memory.scope_deleted" | "document.chunk.updated" | "document.chunk.deleted"
+/** A statement (a link between chunks) was written, ruled on or removed —
+ *  one per endpoint document (RFC FV). */
+ | "document.edges.changed";
 /** The memory scope a change landed in. `global` is listed because the
  *  runtime's scope enum has it and the feed passes the written scope through
  *  unchanged, not because Memory writes it today. */
@@ -7108,6 +7241,10 @@ export interface MemoryChange {
     scope_id: string;
     key?: string;
     chunk_id?: string;
+    /** The document a `document.*` change belongs to, recorded when the write
+     *  happened (RFC FV). Absent on a row whose writer did not say, and on rows
+     *  from a runtime older than the field. */
+    document_id?: string;
     /** RFC3339 time of the write. */
     at: string;
 }
@@ -7187,6 +7324,60 @@ export interface StreamChangesOptions {
     /** Abort to close the stream; the iterator then throws an `AbortError`. */
     signal?: AbortSignal;
 }
+/** The change types {@link LoomcycleClient.documentFeed} carries. */
+export type DocumentFeedChangeType = "document.chunk.updated" | "document.chunk.deleted" | "document.edges.changed";
+/** One reader-feed change: a document the caller can list changed. NO cursor
+ *  — the reader feed never sends a seq, and a reconnect is a resync. Several
+ *  changes of one type to one document inside one server poll arrive as one,
+ *  naming the latest chunk. Value-free: refetch the document (e.g. through
+ *  `document({op:"graph_snapshot", document_ids:[…]})`). */
+export interface DocumentFeedChange {
+    type: DocumentFeedChangeType;
+    /** The chunk changed; for `document.edges.changed`, the statement's endpoint
+     *  in this document. */
+    chunk_id: string;
+    document_id: string;
+    /** RFC3339 time of the write. */
+    at: string;
+}
+/** The reader feed's opening frame (`event: feed`). Only `enabled`: no
+ *  cursor, and no embedder health (that is the operator feed's). */
+export interface DocumentFeedStatus {
+    /** `false` when the server does not capture changes
+     *  (`LOOMCYCLE_MEMORY_CHANGES_ENABLED` unset): the stream stays open and NO
+     *  change will arrive — fall back to reloading on a timer. */
+    enabled: boolean;
+}
+/** Yielded by {@link LoomcycleClient.documentFeed}: `{ kind: "feed" }` first,
+ *  then one `{ kind: "change" }` per change. An `error` item with code
+ *  `store_unavailable` is non-fatal (the server retries). These end the
+ *  stream: `access_unavailable` (the caller's access could not be re-checked),
+ *  `credential_revoked` (the credential no longer authenticates or is no longer
+ *  admitted) and `credential_expired` (the token's lifetime ended) — reload,
+ *  and reconnect with a valid credential. */
+export type DocumentFeedFrame = {
+    kind: "feed";
+    payload: DocumentFeedStatus;
+} | {
+    kind: "change";
+    payload: DocumentFeedChange;
+} | {
+    kind: "error";
+    payload: ChangeFeedError;
+};
+/** Options for {@link LoomcycleClient.documentFeed}. */
+export interface DocumentFeedOptions {
+    /** The scope to watch. `agent` is not served: agent scopes are private to
+     *  their runs. */
+    scope: "user" | "tenant";
+    /** RFC AS browse override: watch another subject's user scope you may see
+     *  (sent as `?scope_id=`). */
+    scopeId?: string;
+    /** An admin's tenant focus (sent as `?tenant=`); ignored for anyone else. */
+    tenant?: string;
+    /** Abort to close the stream; the iterator then throws an `AbortError`. */
+    signal?: AbortSignal;
+}
 /** The access-control rollout mode a deployment runs in. */
 export type AclMode = "compat" | "shadow" | "enforce";
 /** Marks an entry the config declares rather than the store holds. */

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@loomcycle/client",
-  "version": "1.133.0",
+  "version": "1.135.0",
   "description": "TypeScript client for the loomcycle sidecar (HTTP+SSE). 71 methods covering run streaming, agent metadata, pause/resume/state, resolver re-probe (resolveProbe — issue #88 operator escape hatch), operator-token admin (operatorTokenDef — RFC L OSS multi-tenant auth) + whoami (RFC L authoritative principal, v0.17.0) + tenant-scoped listUsers / listUserAgents, dynamic MCP registration (mcpServerDef + v0.18.0 typed mcpServerDefVerify + ensureMcpServer idempotent register-if-changed), snapshot lifecycle, memory admin (incl. v0.9.0 Vector Memory embed_stats + reembed AND v0.11.5 setMemoryEntry + deleteMemoryEntry), interruption resolve, hook management, v0.8.22 substrate admin (agentDef + skillDef), v0.9.x n8n Phase 0 (listChannels + streamUserRunStates), v0.9.x Channel CRUD (publishChannel + subscribeChannel + peekChannel + ackChannel), v0.11.5 Channel admin CRUD (createChannel + updateChannel + deleteChannel — runtime substrate; yaml channels refuse mutation with HTTP 409), v0.9.x content_sha256 verify, v0.9.1 transcript first-cycle, v0.9.x dynamic MCP server registration (mcpServerDef + MCPServerDefVerifyResult), v0.10.3 Library v2 enumeration (listLibraryAgents + listLibrarySkills + listLibraryMcpServers), and v0.11.0 LLM Gateway (llmChat + llmStream — direct provider routing without agent overhead; primary target is n8n's LoomCycleChatModel AI Agent sub-node and any LangChain-compatible consumer). v0.10.1 — dual ESM + CommonJS distribution (additive — ESM consumers unchanged; CJS consumers like n8n's community-node loader now work). v0.19.0 — typed inline code-js agent ingestion (AgentDefOverlay.code_body + ensureCodeAgent — register a deterministic code agent through the substrate with no host filesystem bind; RFC J). v0.20.0 — ensureMcpServer surfaces discoveredToolCount straight from create (loomcycle now auto-discovers MCP tools at ingestion); rediscover is now an explicit force-refresh. v0.21.0 — run/continue accept optional non-secret `metadata` (repo name, review policy, …) passed to the agent, symmetric with the WebHook/Schedule trigger paths. v0.22.0 — version-aligned lockstep release; no client-surface change (RFC N tenant isolation of the agent/skill/MCP/Schedule/Webhook definition plane + real op-schemas on the builtin MCP meta-tools are both server-side). v0.23.0 — version-aligned lockstep release; no client-surface change (RFCs O/P/R MCP-server hardening + thin client and the RFC Q DeepSeek tool-content fix are all server-side / MCP-transport-side). v0.24.0 — purgeChannel clears a channel's buffered messages without deleting its definition (allowed on yaml-declared channels too, unlike deleteChannel — F20); AgentDefOverlay gains channels / evaluation_scopes / interruption so a COMPLETE interactive/multi-agent agent round-trips over the substrate (F14). (Consolidates the interim 0.24/0.25 package bumps, which were never tag-published, back into lockstep with the loomcycle v0.24.0 tag.) v0.25.0 — adds the RFC S channel fan-in/fan-out client twins: awaitChannels() (wait for any/all/at_least N messages across channels, or a timeout — non-committing) + broadcastChannels() (publish one payload to N channels in one atomic-pre-flight call), the client-facing counterparts of the in-band Channel.await / Channel.broadcast tool ops (the rest of v0.25.0 — the manual-management Web UI console + Context op=time + max_fires self-retiring schedules — is server-side / in-band, no client-surface change). v0.29.1 — Usage gains optional `max_context_tokens` (the serving model's context-window ceiling, stamped by the loop from Provider.Capabilities() on each usage event) so a consumer can render a 'context used / max' gauge without a hard-coded per-model table; additive + optional, no behavior change. (Lockstep catch-up: the field landed in loomcycle v0.29.0 but the adapter publish skipped on a version mismatch; v0.29.1 realigns the package version with the release tag so it publishes.) v0.33.0 — gRPC + TS client parity for the RFC Y external fan-out and the compaction surface: spawnRunBatch() (POST /v1/runs:batch — spawn up to 32 fresh runs concurrently in one call, combined index-aligned envelope, per-child failures in-envelope) + compactRun(runId) (POST /v1/runs/{run_id}/compact — summarize a parked run's context); plus per-run sampling + compaction overrides now accepted on runStreaming / continueSession (an explicit temperature 0 is preserved as deterministic, not dropped as falsy). (The gRPC half adds the matching SpawnRunBatch / CompactRun RPCs + the sampling/compaction fields on RunRequest/ContinueRequest — server-side.) v0.34.0 — version-aligned lockstep release; no client-surface change (context-transform plugins / RFC Z Phase 1a are server-side config; the exp7 hardening pass is server-side; the R2 cross-provider thinking-model downgrade surfaces a new `model_downgraded` SSE event the generic stream passes through unchanged). v0.35.0 — RFC AH dynamic filesystem volumes: volumeDef() (POST /v1/_volumedef — op-discriminated create/get/list/delete/purge; a Volume is flat, so delete unmaps + purge RemoveAll's, no retire/promote/fork) + listVolumes() / listEphemeralVolumes() (GET /v1/_volumes[/ephemeral] — tenant-scoped; host paths redacted for non-operator callers). Tenant-confined; the runtime derives the path inside an operator-blessed dynamic_root, so callers pass name + mode, never a host path. v1.1.1 — RFC AI interactive agentic sessions: an `interactive: true` flag on runStreaming/continueSession (a run that parks at end_turn for steering) + sendRunInput(runId, text) (POST /v1/runs/{id}/input — steer a live run) + streamRunByID(runId, {fromSeq}) (GET /v1/runs/{id}/stream — re-attach by run_id; the operator's prior turns replay as `steer` events so a cold client reconstructs the whole conversation) + a high-level InteractiveSession driver (client.interactiveSession / attachInteractiveSession — events()/send()/cancel(), the adapter port of the Web UI run terminal). The AgentEvent union gains awaiting_input/steer/context_compaction frames. Version-aligned with the loomcycle v1.1.x line so the v1.1.1 tag publishes it (also carrying the previously-unpublished v0.35.0 volume surface). v1.4.0 — RFC AL Path VFS + RFC AK Document on the wire: path(input) (POST /v1/_path — a Unix-like filesystem over Memory/Volumes/Documents; resolve/ls/stat/mkdir/mv/rm) + document(input) (POST /v1/_document — chunked-graph documents; 13 ops, needs SQL Memory on the sidecar). Scope (agent/user/tenant) + tenant are resolved server-side from the authenticated principal, never the wire; an off-run scope:'user' op keys on the principal subject so it interoperates with that user's agent runs. New PathToolInput / DocumentToolInput types; responses are op-varying (unknown — narrow as needed). v1.7.0 — RFC AT image/vision input: the PromptContent union gains an `image` variant ({ type:'image'; media_type: ImageMediaType; data: base64-no-prefix }) accepted in a user segment by runStreaming / continueSession (segments pass through unchanged — no method change). The model must be vision-capable or the run errors before the call. New ImageMediaType type (image/png|jpeg|gif|webp). v1.12.1 — Path/Document browse-by-subject + the full Document op set (RFC AS/AK): path(input, opts) / document(input, opts) accept optional scopeId / tenant browse overrides sent as ?scope_id= / ?tenant= query params (server reads them from the URL, re-checks authorization; omit both to browse your own subject — byte-identical to the pre-RFC-AS request), and DocumentToolInput.op now covers all 16 backend ops (adds set_path, export_md, import_md) with the matching include_metadata / markdown fields. Additive — existing path() / document() callers are unchanged. v1.16.0 — RFC BC client-executed tools (local tool host): connectClientTools({tools,onInvoke}) opens a persistent WebSocket to /v1/client-tools, registers tools this client runs on the user's machine (browser DOM / files / shell), and answers the invoke frames loomcycle routes when an agent of your principal calls a client:<tool> — returning your reply as an ordinary tool result. Returns a ClientToolHost driver (.close() to stop; auto-reconnect); dependency-free (global WebSocket in browsers / Node 22+, or an injected WebSocketImpl like the ws package on older Node); the bearer rides the Sec-WebSocket-Protocol subprotocol (browsers can't set an Authorization header on a WebSocket). The runtime's first WebSocket surface. v1.45.0 — RFC BL P5 subject erasure: erasureReport(subject, {tenant}) (GET /v1/_erasure — what this deployment holds about one subject, in three tiers: deletable with existing primitives, subject-keyed but not deletable, and facts ABOUT the subject in scopes they do not own) + erasureExecute(subject, {dryRun, confirm, tenant}) (POST /v1/_erasure — removes tiers 1 and 2). DEFAULTS TO A DRY RUN: dryRun defaults true and a live run also requires confirm === subject. The tier-3 residue is traceable only through the subject's chats, which a live run deletes, so a report afterwards shows rows: 0 while those facts remain — the returned object is the only durable record of what was not reached; persist it. New ErasureReport / ErasureResult / ErasureTier / ErasureResidue types. v1.47.0 — RFC BV memory-view SDK: memorySearch() (POST /v1/_memory/search — off-run unified semantic search spanning k/v entries AND document-chunk bodies in one ranked list, each hit tagged kind memory|document with chunk_id on document hits) + memoryEmbedStats(scope) + reembedMemory(scope, scopeId, {dryRun,limit}) (the Vector Memory embed-admin reads the memory-view console needs; dry_run defaults true). Fact reads (list_facts + get_chunk's entity block) ride the existing document() passthrough. Additive — existing callers unchanged. v1.61.0 — RFC CJ per-run context-window override: runStreaming / continueSession accept an optional maxContextTokens (integer tokens) that wins over the agent's own max_context_tokens; omitted inherits it (which defers to the provider/driver default). Distinct from a model's output cap; primarily for local inference (Ollama num_ctx). Serialized as the snake_case max_context_tokens field on POST /v1/runs + the continuation body; additive, existing callers unchanged. v1.72.1 — the TeamDef version lifecycle: listTeamVersions(name) (op=list — every version of one team, newest first), promoteTeam(defId) (op=promote — point the active pointer, which is what a run BY NAME executes; forkTeam defaults to promote:false, so authoring and putting in force stay two steps), retireTeam(defId, retired) (op=retire — reversible and version-scoped, unlike deleteTeam) and verifyTeam(name, contentSha256) (op=verify — the drift check for a workflow kept in source control and pushed to several deployments; an absent team answers deployed:false rather than raising). The ops existed on the substrate and over HTTP; a client that could author a team could not put one in force.",
   "license": "Apache-2.0",
   "type": "module",