@loomcycle/client 1.109.0 → 1.111.0

package/README.md

@@ -143,6 +143,7 @@ The low-level primitives (`runStreaming({interactive:true})` + `sendRunInput` +
 | `cancelAgent(agentId, opts?)` | `Promise<{ cancelledCount: number }>` | Cascades to children via `parent_agent_id`. Idempotent. |
 | `listUserAgents(userId, opts?)` | `Promise<Agent[]>` | Optional filter by status (`running` / `completed` / `failed` / `cancelled`). |
 | `listWalkRuns(walkId, { limit?, cursor? })` | `Promise<WalkRunsPage>` | One page of a team walk's runs — its own run and every member, oldest first: `{ agents, next_cursor }`. Pass `next_cursor` back as `cursor`; `""` on the last page. `limit` defaults to 100, at most 1000. Raises `NotFoundError` for a walk you cannot read. |
+| `listChildRuns(parentRunId, { limit?, cursor? })` | `Promise<WalkRunsPage>` | One page of a run's direct children (the runs it started itself), of every status, oldest first, paged like `listWalkRuns`. Not the run itself, and not its grandchildren. Raises `NotFoundError` for a run you cannot read. |
 | `getTranscript(sessionId)` | `Promise<TranscriptResponse>` | Persisted event log; one row per event with seq/run_id/ts_ns/type/event. |
 | `health()` | `Promise<HealthResponse>` | Liveness probe. Hits `/healthz` (no `/v1` prefix). Unauthenticated. |
 | `getConfig(opts?)` | `Promise<ConfigResponse>` | v1.38.0 — instance configuration: build identity, the feature matrix, and the live provider/model/search cascade with `active`/`selected`. `view` names the disclosure level (`public` / `authenticated` / `admin`). Also readable with **no bearer** against a deployment running `LOOMCYCLE_PUBLIC_CONFIG=1`, which serves the narrower `public` view — the landing-page case. |

package/dist/cjs/client.js

@@ -678,7 +678,8 @@ class LoomcycleClient {
         const resp = await (0, fetch_helpers_js_1.postJSON)(this.ctx, `/v1/agents/${encodeURIComponent(agentId)}/cancel`, { reason: opts?.reason ?? "" }, opts);
         return { cancelledCount: resp.cancelled_count };
     }
-    /** List a user's recent agent runs, optionally filtered by status.
+    /** List a user's recent agent runs, optionally filtered by status. With no
+     *  `status` only running runs are returned; `"all"` returns every status.
      *
      *  v0.9.x — `parentAgentId` narrows the result CLIENT-SIDE to runs
      *  whose `parent_agent_id` matches. The server still returns the
@@ -715,6 +716,23 @@ class LoomcycleClient {
         const resp = await (0, fetch_helpers_js_1.jsonFetch)(this.ctx, `/v1/runs?${params.toString()}`, opts);
         return { agents: resp.agents ?? [], next_cursor: resp.next_cursor ?? "" };
     }
+    /** One page of a run's direct children — the runs it started itself, for
+     *  example through the Agent tool — of every status, oldest first. Not the
+     *  run itself, and not its grandchildren: call it again on a child for
+     *  those. Rows are {@link LoomcycleClient.listWalkRuns}' rows, and none
+     *  carries a `result`. Pass the page's `next_cursor` back as `cursor` for
+     *  the next one; it is "" on the last. `limit` defaults to 100, at most
+     *  1000. Mirrors `GET /v1/runs?parent_run_id=`. Raises NotFoundError for an
+     *  unknown run, or one the caller may not see. */
+    async listChildRuns(parentRunId, opts) {
+        const params = new URLSearchParams({ parent_run_id: parentRunId });
+        if (opts?.limit !== undefined)
+            params.set("limit", String(opts.limit));
+        if (opts?.cursor)
+            params.set("cursor", opts.cursor);
+        const resp = await (0, fetch_helpers_js_1.jsonFetch)(this.ctx, `/v1/runs?${params.toString()}`, opts);
+        return { agents: resp.agents ?? [], next_cursor: resp.next_cursor ?? "" };
+    }
     /** Aggregated token-usage + cost report (RFC AV). Group by any of
      *  tenant/user/provider/model/source over an optional time window; group by
      *  `source` for the operator-vs-tenant split. Tenant-scoped server-side: a
@@ -2323,6 +2341,9 @@ class LoomcycleClient {
         if (opts?.walkId) {
             params.set("walk_id", opts.walkId);
         }
+        if (opts?.parentRunId) {
+            params.set("parent_run_id", opts.parentRunId);
+        }
         const qs = params.toString();
         const path = `/v1/users/${encodeURIComponent(userId)}/agents/stream` +
             (qs ? `?${qs}` : "");

package/dist/client.d.ts

@@ -383,7 +383,8 @@ export declare class LoomcycleClient {
         reason?: string;
         signal?: AbortSignal;
     }): Promise<CancelAgentResult>;
-    /** List a user's recent agent runs, optionally filtered by status.
+    /** List a user's recent agent runs, optionally filtered by status. With no
+     *  `status` only running runs are returned; `"all"` returns every status.
      *
      *  v0.9.x — `parentAgentId` narrows the result CLIENT-SIDE to runs
      *  whose `parent_agent_id` matches. The server still returns the
@@ -391,7 +392,7 @@ export declare class LoomcycleClient {
      *  request); the adapter trims before returning. Useful for the
      *  n8n trigger pattern "show me all sub-runs spawned by parent X." */
     listUserAgents(userId: string, opts?: {
-        status?: AgentStatus;
+        status?: AgentStatus | "all";
         parentAgentId?: string;
         /** Super-admin tenant-focus (?tenant=, RFC L v0.17.0). Ignored
          *  server-side for a tenant principal — its own tenant is forced. */
@@ -410,6 +411,19 @@ export declare class LoomcycleClient {
         cursor?: string;
         signal?: AbortSignal;
     }): Promise<WalkRunsPage>;
+    /** One page of a run's direct children — the runs it started itself, for
+     *  example through the Agent tool — of every status, oldest first. Not the
+     *  run itself, and not its grandchildren: call it again on a child for
+     *  those. Rows are {@link LoomcycleClient.listWalkRuns}' rows, and none
+     *  carries a `result`. Pass the page's `next_cursor` back as `cursor` for
+     *  the next one; it is "" on the last. `limit` defaults to 100, at most
+     *  1000. Mirrors `GET /v1/runs?parent_run_id=`. Raises NotFoundError for an
+     *  unknown run, or one the caller may not see. */
+    listChildRuns(parentRunId: string, opts?: {
+        limit?: number;
+        cursor?: string;
+        signal?: AbortSignal;
+    }): Promise<WalkRunsPage>;
     /** Aggregated token-usage + cost report (RFC AV). Group by any of
      *  tenant/user/provider/model/source over an optional time window; group by
      *  `source` for the operator-vs-tenant split. Tenant-scoped server-side: a

package/dist/client.js

@@ -675,7 +675,8 @@ export class LoomcycleClient {
         const resp = await postJSON(this.ctx, `/v1/agents/${encodeURIComponent(agentId)}/cancel`, { reason: opts?.reason ?? "" }, opts);
         return { cancelledCount: resp.cancelled_count };
     }
-    /** List a user's recent agent runs, optionally filtered by status.
+    /** List a user's recent agent runs, optionally filtered by status. With no
+     *  `status` only running runs are returned; `"all"` returns every status.
      *
      *  v0.9.x — `parentAgentId` narrows the result CLIENT-SIDE to runs
      *  whose `parent_agent_id` matches. The server still returns the
@@ -712,6 +713,23 @@ export class LoomcycleClient {
         const resp = await jsonFetch(this.ctx, `/v1/runs?${params.toString()}`, opts);
         return { agents: resp.agents ?? [], next_cursor: resp.next_cursor ?? "" };
     }
+    /** One page of a run's direct children — the runs it started itself, for
+     *  example through the Agent tool — of every status, oldest first. Not the
+     *  run itself, and not its grandchildren: call it again on a child for
+     *  those. Rows are {@link LoomcycleClient.listWalkRuns}' rows, and none
+     *  carries a `result`. Pass the page's `next_cursor` back as `cursor` for
+     *  the next one; it is "" on the last. `limit` defaults to 100, at most
+     *  1000. Mirrors `GET /v1/runs?parent_run_id=`. Raises NotFoundError for an
+     *  unknown run, or one the caller may not see. */
+    async listChildRuns(parentRunId, opts) {
+        const params = new URLSearchParams({ parent_run_id: parentRunId });
+        if (opts?.limit !== undefined)
+            params.set("limit", String(opts.limit));
+        if (opts?.cursor)
+            params.set("cursor", opts.cursor);
+        const resp = await jsonFetch(this.ctx, `/v1/runs?${params.toString()}`, opts);
+        return { agents: resp.agents ?? [], next_cursor: resp.next_cursor ?? "" };
+    }
     /** Aggregated token-usage + cost report (RFC AV). Group by any of
      *  tenant/user/provider/model/source over an optional time window; group by
      *  `source` for the operator-vs-tenant split. Tenant-scoped server-side: a
@@ -2320,6 +2338,9 @@ export class LoomcycleClient {
         if (opts?.walkId) {
             params.set("walk_id", opts.walkId);
         }
+        if (opts?.parentRunId) {
+            params.set("parent_run_id", opts.parentRunId);
+        }
         const qs = params.toString();
         const path = `/v1/users/${encodeURIComponent(userId)}/agents/stream` +
             (qs ? `?${qs}` : "");

package/dist/index.d.ts

@@ -132,5 +132,5 @@ export { InteractiveSession } from "./interactive.js";
 export type { InteractiveSessionOps } from "./interactive.js";
 export { ClientToolHost, clientToolsURL, CLIENT_TOOL_SUBPROTOCOL } from "./client-tools.js";
 export type { ClientToolSchema, ClientToolInvocation, ConnectClientToolsOptions, WebSocketLike, WebSocketCtor, } from "./client-tools.js";
-export type { AgentEvent, ClientOptions, ContinueOptions, EventType, HostWidening, ImageMediaType, ParentContext, PromptContent, PromptSegment, RetryInfo, RunOptions, SamplingOptions, CompactionOptions, ContextOptions, ToolUse, Usage, CallTiming, Agent, AgentStatus, AwaitedState, AgentUsage, RunResult, RunSpec, RunSpecTeam, ConfiguredRun, ConfiguredRunPatch, ToolChoiceOptions, OutputFormatOptions, CancelAgentResult, ListAgentsResponse, WalkRunsPage, RunBatchOptions, RunBatchResult, SpawnRunResult, CompactRunResult, DirectoryBudget, DirectoryInspection, DirectoryTenant, DirectoryUser, ErasureReport, ErasureResidue, ErasureResult, ErasureTier, CancelTurnResult, ReviewRunResult, TranscriptEvent, TranscriptResponse, HealthResponse, ListUsersResponse, UserSummary, UserRecord, CreateUserBody, UpdateUserBody, MintedUserToken, UserTokenMeta, ListUserTokensResponse, RunnableAgent, RunnableAgentsResponse, WhoamiResponse, PauseResult, ResumeResult, RuntimeStateResponse, RuntimeStateStatus, ResolverMatrix, ResolverModelStatus, ResolverProviderAvailability, CreateSnapshotOptions, SnapshotCreateResponse, SnapshotDescriptor, SnapshotEnvelope, SnapshotListResponse, SnapshotRestoreResponse, MemoryEntriesResponse, MemoryEntry, MemoryEntryResponse, MemoryScopeIDsResponse, MemoryScopeIDSummary, MemoryScopeKind, MemoryScopesResponse, 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, PathToolInput, PathToolResponse, DocumentToolInput, DocumentToolResponse, HistoryToolInput, HistoryToolResponse, VolumeMode, PersistentVolumeEntry, PersistentVolumesResponse, EphemeralVolumeEntry, EphemeralVolumesResponse, SystemPromptPayload, UserInputPayload, ChannelDescriptor, ListChannelsResponse, RunStateEvent, RunStateStreamClose, RunStateStreamItem, RunStateStreamOpen, StreamUserRunStatesOptions, 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, HookEvent, InlineWebhook, HookEntry, EventHooks, ToolEntry, ToolHooksByTool, EnsureCodeAgentOptions, EnsureCodeAgentResult, LibraryAgentDefinition, LibraryEntry, LibraryListResponse, LibraryMcpServerDefinition, LibrarySkillDefinition, LLMChatContent, LLMChatMessage, LLMChatOptions, LLMChatResponse, LLMChatStreamDelta, LLMChatStreamItem, LLMChatToolCall, LLMChatUsage, LLMTool, LLMEmbeddingItem, LLMEmbeddingsOptions, LLMEmbeddingsResponse, LLMEmbeddingsUsage, UsageDimension, UsageAggregate, UsageReportResponse, CapabilityInertInfo, LimitInfo, ErrorInfo, CallFormat, CallRef, HookDecisionInfo, EffectiveConfigResponse, EffectiveConfigSource, EffectiveValue, RetuneRunResponse, RunConfigRecord, SubagentHoldInfo, RunConfigResponse, RunPromptResponse, RunPromptSnapshot, PromptBlock, TokenLimit, TokenLimitsResponse, ConfigResponse, ConfigProvider, ConfigModel, ConfigSearch, ConfigInstance, SetTokenLimitRequest, CredentialScope, CredentialMeta, CredentialListResponse, DecideRequest, DecideResponse, DecisionQuestion, DecisionChoiceQuestion, DecisionNoulQuestion, DecisionScoreQuestion, DecisionAnswer, DecisionChoiceAnswer, DecisionNoulAnswer, DecisionScoreAnswer, DecisionModel, DecisionModelsResponse, } from "./types.js";
+export type { AgentEvent, ClientOptions, ContinueOptions, EventType, HostWidening, ImageMediaType, ParentContext, PromptContent, PromptSegment, RetryInfo, RunOptions, SamplingOptions, CompactionOptions, ContextOptions, ToolUse, Usage, CallTiming, Agent, AgentStatus, AwaitedState, AgentUsage, RunResult, RunSpec, RunSpecTeam, ConfiguredRun, ConfiguredRunPatch, ToolChoiceOptions, OutputFormatOptions, CancelAgentResult, ListAgentsResponse, WalkRunsPage, RunBatchOptions, RunBatchResult, SpawnRunResult, CompactRunResult, DirectoryBudget, DirectoryInspection, DirectoryTenant, DirectoryUser, ErasureReport, ErasureResidue, ErasureResult, ErasureTier, CancelTurnResult, ReviewRunResult, TranscriptEvent, TranscriptResponse, HealthResponse, ListUsersResponse, UserSummary, UserRecord, CreateUserBody, UpdateUserBody, MintedUserToken, UserTokenMeta, ListUserTokensResponse, RunnableAgent, RunnableAgentsResponse, WhoamiResponse, PauseResult, ResumeResult, RuntimeStateResponse, RuntimeStateStatus, ResolverMatrix, ResolverModelStatus, ResolverProviderAvailability, CreateSnapshotOptions, SnapshotCreateResponse, SnapshotDescriptor, SnapshotEnvelope, SnapshotListResponse, SnapshotRestoreResponse, MemoryEntriesResponse, MemoryEntry, MemoryEntryResponse, MemoryScopeIDsResponse, MemoryScopeIDSummary, MemoryScopeKind, MemoryScopesResponse, 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, PathToolInput, PathToolResponse, DocumentToolInput, DocumentToolResponse, HistoryToolInput, HistoryToolResponse, VolumeMode, PersistentVolumeEntry, PersistentVolumesResponse, EphemeralVolumeEntry, EphemeralVolumesResponse, SystemPromptPayload, UserInputPayload, ChannelDescriptor, ListChannelsResponse, RunStateEvent, RunStateStreamClose, RunStateStreamItem, RunStateStreamOpen, StreamUserRunStatesOptions, 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, HookEvent, InlineWebhook, HookEntry, EventHooks, ToolEntry, ToolHooksByTool, EnsureCodeAgentOptions, EnsureCodeAgentResult, LibraryAgentDefinition, LibraryEntry, LibraryListResponse, LibraryMcpServerDefinition, LibrarySkillDefinition, LLMChatContent, LLMChatMessage, LLMChatOptions, LLMChatResponse, LLMChatStreamDelta, LLMChatStreamItem, LLMChatToolCall, LLMChatUsage, LLMTool, LLMEmbeddingItem, LLMEmbeddingsOptions, LLMEmbeddingsResponse, LLMEmbeddingsUsage, UsageDimension, UsageAggregate, UsageReportResponse, CapabilityInertInfo, LimitInfo, ErrorInfo, CallFormat, CallRef, HookDecisionInfo, TeamDecisionInfo, EffectiveConfigResponse, EffectiveConfigSource, EffectiveValue, RetuneRunResponse, RunConfigRecord, SubagentHoldInfo, RunConfigResponse, RunPromptResponse, RunPromptSnapshot, PromptBlock, TokenLimit, TokenLimitsResponse, ConfigResponse, ConfigProvider, ConfigModel, ConfigSearch, ConfigInstance, SetTokenLimitRequest, CredentialScope, CredentialMeta, CredentialListResponse, DecideRequest, DecideResponse, DecisionQuestion, DecisionChoiceQuestion, DecisionNoulQuestion, DecisionScoreQuestion, DecisionAnswer, DecisionChoiceAnswer, DecisionNoulAnswer, DecisionScoreAnswer, DecisionModel, DecisionModelsResponse, } from "./types.js";
 export { AgentIDInUseError, AgentNotFoundError, AlreadyPausingError, AuthError, BackpressureError, NotFoundError, InvalidArgumentError, ChannelCursorRegressionError, LoomcycleError, NotPausedError, PauseNotConfiguredError, PerUserQuotaExhaustedError, PromptTooLargeError, RequestTooLargeError, SessionBusyError, SessionNotFoundError, SnapshotNotFoundError, SnapshotTooLargeError, SnapshotVersionError, SubstrateToolRefusedError, TokenLimitExceededError, UnavailableError, } from "./errors.js";

package/dist/types.d.ts

@@ -7,7 +7,7 @@
  * `client.ts` for the input shapes (RunOptions, CreateSnapshotOptions,
  * etc.) — those are translated to snake_case in the request body.
  */
-export type EventType = "started" | "text" | "tool_call" | "tool_result" | "usage" | "done" | "error" | "retry" | "host_widened" | "session" | "agent" | "awaiting_input" | "awaiting_review" | "subagent_hold" | "awaiting_children" | "children_note" | "steer" | "context_compaction" | "capability_inert" | "hook_decision" | "limit" | "override" | "context_recap" | "context_state" | "context_distill_declined" | "context_exhausted" | "thinking" | "turn_cancelled" | "provider_fallback" | "fallback_suppressed" | "model_downgraded" | "cache_invalidated" | "reasoning_invalidated" | "channel_publish" | "channel_delivery" | "interruption_pending" | "spawn_child_started" | "spawn_child_result" | "spawn_child_read" | "prompt_snapshot" | "_meta";
+export type EventType = "started" | "text" | "tool_call" | "tool_result" | "usage" | "done" | "error" | "retry" | "host_widened" | "session" | "agent" | "awaiting_input" | "awaiting_review" | "subagent_hold" | "awaiting_children" | "children_note" | "steer" | "context_compaction" | "capability_inert" | "hook_decision" | "limit" | "override" | "context_recap" | "context_state" | "context_distill_declined" | "context_exhausted" | "thinking" | "team_decision" | "turn_cancelled" | "provider_fallback" | "fallback_suppressed" | "model_downgraded" | "cache_invalidated" | "reasoning_invalidated" | "channel_publish" | "channel_delivery" | "interruption_pending" | "spawn_child_started" | "spawn_child_result" | "spawn_child_read" | "prompt_snapshot" | "_meta";
 export interface ToolUse {
     id: string;
     name: string;
@@ -311,6 +311,28 @@ export interface ErrorInfo {
      *  shape may be the cause. */
     correct_call_format?: CallFormat;
 }
+/** One visit of a team walk to a `decision` state (the `team_decision`
+ *  payload), recorded on the walk's own run. A decision state starts no
+ *  member run, and a walk started with `mode: "detach"` returns no steps, so
+ *  this is where a client holding the walk's `run_id` finds the answer. */
+export interface TeamDecisionInfo {
+    /** The decision state's id. */
+    state: string;
+    /** The walk's ordinal of state visits at this one: 1 for the walk's first
+     *  state, never reused, and the number a member run of the walk carries as
+     *  `parent_context.state_visit`. Two passes through one state are two
+     *  events with different visits. */
+    visit: number;
+    /** The transition the walk took out of the state: `conditional:<option>`,
+     *  `conditional:true` / `conditional:false`, or `success` when the answer
+     *  had no transition of its own or the state routes on nothing. */
+    edge: string;
+    /** The state that transition leads to. */
+    next: string;
+    /** What the model answered: the object a waited-for walk's step carries as
+     *  `answer`. */
+    answer: TeamDecisionAnswer;
+}
 /** What one hook did to one call, or to the run (the `hook_decision`
  *  payload). */
 export interface HookDecisionInfo {
@@ -597,6 +619,11 @@ export interface AgentEvent {
     capability_inert?: CapabilityInertInfo;
     /** Payload on `event: hook_decision`. */
     hook_decision?: HookDecisionInfo;
+    /** Payload on `event: team_decision`: one visit of a team walk to a
+     *  decision state. Read it from the WALK's run, with
+     *  {@link LoomcycleClient.streamRunByID}: while the walk runs, and after
+     *  it has ended. */
+    team_decision?: TeamDecisionInfo;
     /** Set on `event: override` frames — what the operator changed, and from
      *  what to what. */
     override?: OverrideInfo;
@@ -1069,7 +1096,14 @@ export interface ParentContext {
      *  agent within the walk rather than merely inside it — a fan-out of N
      *  agents shares one `wave_id` and differs only by `wave_index`.
      *
-     *  Absent on any run no team walk spawned. */
+     *  A run a member starts (a sub-agent, at any depth) carries the member's
+     *  `walk_id`, `state` and `state_visit` too, so it is in
+     *  {@link LoomcycleClient.listWalkRuns} and on the walk-filtered stream.
+     *  It is told from a member by `parent_run_id`: a member's is the walk's
+     *  run id, a sub-agent's is the run that started it. The wave fields stay
+     *  the member's alone.
+     *
+     *  Absent on any run outside a team walk. */
     walk_id?: string;
     wave_id?: string;
     /** Position within the wave, 0-based. Sent even when 0 (unlike the string
@@ -1078,7 +1112,8 @@ export interface ParentContext {
     wave_index?: number;
     /** Which state of the walk ran this run — set on EVERY run a team walk
      *  spawns (agent, parallel, consolidator and starter members alike), where
-     *  the wave fields are a starter's alone. */
+     *  the wave fields are a starter's alone. A member's sub-agent carries the
+     *  member's. */
     state?: string;
     /** The walk's own ordinal of state visits (1, 2, …): the runs of one visit
      *  share it, and a revisit of the same state gets a new one. Absent outside
@@ -3309,6 +3344,10 @@ export interface RunStateStreamOpen {
      *  are a stream that stays quiet. Comparing this to what you sent tells the
      *  two apart before you wait on an empty stream. Empty when unfiltered. */
     filter_walk_id?: string;
+    /** The parent-run filter the server applied, echoed back like
+     *  `filter_walk_id`. Empty when unfiltered, absent on a server that
+     *  predates the filter (which then streams every run). */
+    filter_parent_run_id?: string;
     keepalive_interval: number;
 }
 /** Yielded by {@link LoomcycleClient.streamUserRunStates}.
@@ -3349,6 +3388,13 @@ export interface StreamUserRunStatesOptions {
      *  callback sees. The server echoes it back on the open frame as
      *  {@link RunStateStreamOpen.filter_walk_id}. */
     walkId?: string;
+    /** SERVER-side filter: only one run's direct children, the events whose
+     *  `parent_run_id` is this run id. The run's own transitions are not in
+     *  it, nor its grandchildren's. It is the live twin of
+     *  {@link LoomcycleClient.listChildRuns}. With `walkId`, an event must pass
+     *  both. Echoed on the open frame as
+     *  {@link RunStateStreamOpen.filter_parent_run_id}. */
+    parentRunId?: string;
     /** v0.9.x — client-side filter on the run's parent_agent_id.
      *  Useful for "show me only the sub-runs spawned by agent X."
      *  The filter is applied AFTER the SSE frame is parsed, so this

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@loomcycle/client",
-  "version": "1.109.0",
+  "version": "1.111.0",
   "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",