@loomcycle/client 1.96.0 → 1.97.0

package/README.md

@@ -197,30 +197,23 @@ console.log(`restored memory rows: ${result.memory_restored}`);
 
 | Method | Returns | Notes |
 |---|---|---|
-| `registerHook(opts: RegisterHookOptions)` | `Promise<RegisterHookResponse>` | Register a pre- or post-tool webhook. Re-registering the same `(owner, name)` replaces in-place with a fresh id. Raises `InvalidArgumentError` on 400 (bad URL / phase / missing field). |
-| `listHooks()` | `Promise<Hook[]>` | Every registered hook. **In-memory only — empty after a loomcycle restart.** |
-| `deleteHook(id)` | `Promise<void>` | Raises `HookNotFoundError` on 404. |
+| `hookDef(input)` | `Promise<SubstrateToolResponse>` | Reusable hook definitions (create / fork / get / list / promote / retire / verify / delete). An agent attaches hooks in its own definition (`tools` entries `{name, hooks}` and `hooks`). |
 
-Hook registration is one side; the other side is the **callback receiver** — a small HTTP endpoint your app runs at the URL you registered. The adapter exports the wire shapes (`PreHookCall` / `PostHookCall` / `PreHookResult` / `PostHookResult`) so you can type the handler against the same JSON loomcycle posts.
+A hook is attached in the agent's definition — a tool entry `{name, hooks}` or the agent's own `hooks` — and loomcycle posts to its URL during the agent's runs. The other side is the **callback receiver**, a small HTTP endpoint your app runs at that URL. The adapter exports the wire shapes (`PreHookCall` / `PostHookCall` / `PreHookResult` / `PostHookResult`) so you can type the handler against the same JSON loomcycle posts.
 
-**Register from your app's startup:**
+**Attach it in the agent's definition:**
 
 ```ts
-import { LoomcycleClient } from "@loomcycle/client";
-
-const client = new LoomcycleClient({
-  baseUrl: process.env.LOOMCYCLE_BASE_URL!,
-  authToken: process.env.LOOMCYCLE_AUTH_TOKEN,
-});
-
-await client.registerHook({
-  owner: "jobember-web",                     // (owner, name) is the identity tuple
-  name: "scan-webfetch",                     // re-registering same pair replaces in place
-  phase: "post",                             // "pre" or "post"
-  tools: ["WebFetch"],                       // empty/omitted = all tools
-  callbackUrl: "https://jobember.example/hooks/scan",
-  failMode: "open",                          // "open" = errors pass through; "closed" = errors fail the tool call
-  timeoutMs: 3000,                           // 0 = registry default (5s)
+await client.agentDef({
+  op: "fork",
+  name: "researcher",
+  overlay: {
+    tools: [
+      "Read",
+      { name: "WebFetch", hooks: { post: [{ name: "scan-webfetch", url: "https://jobember.example/hooks/scan", fail_mode: "open", timeout_ms: 3000 }] } },
+    ],
+  },
+  promote: true,
 });
 ```
 

package/dist/cjs/client.js

@@ -1115,55 +1115,6 @@ class LoomcycleClient {
             signal: opts?.signal,
         });
     }
-    // ---- Hook management (hooks-connector series, PR C) ----
-    /** Register a pre- or post-tool hook. Its body is a webhook — the
-     *  callback_url must be an http:// or https:// endpoint the CONSUMER
-     *  runs; loomcycle POSTs PreHookCall / PostHookCall payloads to it —
-     *  or a code-js body (`code`), run in-process by loomcycle. Set
-     *  exactly one. This method manages registration only; a webhook's
-     *  receiver is the consumer's own HTTP framework (Express, Next.js,
-     *  etc.).
-     *
-     *  Re-registering the same (owner, name) replaces the prior entry
-     *  with a fresh id (idempotent app-restart contract).
-     *
-     *  Raises InvalidArgumentError on 400 (bad URL / phase / missing
-     *  required fields). */
-    async registerHook(opts) {
-        const body = {
-            owner: opts.owner,
-            name: opts.name,
-            phase: opts.phase,
-        };
-        if (opts.callbackUrl !== undefined)
-            body.callback_url = opts.callbackUrl;
-        if (opts.code !== undefined)
-            body.code = opts.code;
-        if (opts.agents !== undefined)
-            body.agents = opts.agents;
-        if (opts.tools !== undefined)
-            body.tools = opts.tools;
-        if (opts.failMode !== undefined)
-            body.fail_mode = opts.failMode;
-        if (opts.timeoutMs !== undefined && opts.timeoutMs > 0) {
-            body.timeout_ms = opts.timeoutMs;
-        }
-        return (0, fetch_helpers_js_1.postJSON)(this.ctx, "/v1/hooks", body, opts);
-    }
-    /** List every currently-registered hook. Returns the array
-     *  unwrapped (the wire envelope is `{hooks: [...]}` — we strip
-     *  the envelope to match listUserAgents). In-memory only — empty
-     *  after a loomcycle restart. */
-    async listHooks(opts) {
-        const resp = await (0, fetch_helpers_js_1.jsonFetch)(this.ctx, "/v1/hooks", opts);
-        return resp.hooks ?? [];
-    }
-    /** Delete a registered hook by id. Raises HookNotFoundError on
-     *  404. Returns void on success (the HTTP 200 body `{deleted: id}`
-     *  is dropped — callers already know the id they passed). */
-    async deleteHook(id, opts) {
-        await (0, fetch_helpers_js_1.deleteRequest)(this.ctx, `/v1/hooks/${encodeURIComponent(id)}`, opts);
-    }
     // ---- v0.8.22 substrate admin (AgentDef + SkillDef) ----
     /** Invoke the AgentDef substrate tool over HTTP. Mirrors the
      *  MCP `agentdef` meta-tool and the in-band agent tool_use of

package/dist/cjs/errors.js

@@ -19,7 +19,7 @@
  * to raise typed errors via `raiseFromResponse`.
  */
 Object.defineProperty(exports, "__esModule", { value: true });
-exports.SubstrateToolRefusedError = exports.ChannelCursorRegressionError = exports.HookNotFoundError = exports.SnapshotVersionError = exports.SnapshotTooLargeError = exports.SnapshotNotFoundError = exports.NotPausedError = exports.AlreadyPausingError = exports.PauseNotConfiguredError = exports.InvalidArgumentError = exports.UnavailableError = exports.AuthError = exports.PerUserQuotaExhaustedError = exports.BackpressureError = exports.AgentIDInUseError = exports.SessionBusyError = exports.SessionNotFoundError = exports.AgentNotFoundError = exports.NotFoundError = exports.LoomcycleError = void 0;
+exports.SubstrateToolRefusedError = exports.ChannelCursorRegressionError = exports.SnapshotVersionError = exports.SnapshotTooLargeError = exports.SnapshotNotFoundError = exports.NotPausedError = exports.AlreadyPausingError = exports.PauseNotConfiguredError = exports.InvalidArgumentError = exports.UnavailableError = exports.AuthError = exports.PerUserQuotaExhaustedError = exports.BackpressureError = exports.AgentIDInUseError = exports.SessionBusyError = exports.SessionNotFoundError = exports.AgentNotFoundError = exports.NotFoundError = exports.LoomcycleError = void 0;
 class LoomcycleError extends Error {
     status;
     bodyText;
@@ -196,17 +196,6 @@ class SnapshotVersionError extends LoomcycleError {
     }
 }
 exports.SnapshotVersionError = SnapshotVersionError;
-/** HookNotFoundError — raised by deleteHook when no hook has the
- *  supplied id (HTTP 404 with "hook" in the body). Extends
- *  NotFoundError so consumers catching the broader category get this
- *  one too. */
-class HookNotFoundError extends NotFoundError {
-    constructor(message, opts) {
-        super(message, opts);
-        this.name = "HookNotFoundError";
-    }
-}
-exports.HookNotFoundError = HookNotFoundError;
 /** ChannelCursorRegressionError — raised by `client.ackChannel()`
  *  when the caller-supplied cursor is older than the currently-
  *  committed cursor for the (channel, scope, scope_id) tuple. HTTP

package/dist/cjs/fetch-helpers.js

@@ -169,7 +169,6 @@ async function deleteJSON(ctx, path, opts) {
  *   401         → AuthError
  *   404 + "snapshot"   → SnapshotNotFoundError ────────┐
  *   404 + "session"    → SessionNotFoundError          │  All extend
- *   404 + "hook"       → HookNotFoundError             │  NotFoundError —
  *   404 + "agent"      → AgentNotFoundError            │  callers can
  *   404 + (other)      → NotFoundError (base)          │  catch any 404
  *                                                      │  with one
@@ -223,9 +222,6 @@ async function raiseFromResponse(resp) {
             // Priority: most-specific keyword wins.
             // - "snapshot" → SnapshotNotFoundError
             // - "session"  → SessionNotFoundError
-            // - "hook"     → HookNotFoundError (must precede "agent" — the
-            //                hooks 404 body is `no hook with id "..."`,
-            //                doesn't mention "agent")
             // - "agent" or "agent_id" → AgentNotFoundError
             // - otherwise → NotFoundError (base) — e.g. memory rows, interrupts,
             //   or any future 404-returning endpoint that doesn't fit the
@@ -234,8 +230,6 @@ async function raiseFromResponse(resp) {
                 throw new errors_js_1.SnapshotNotFoundError(msg, opts);
             if (bodyLower.includes("session"))
                 throw new errors_js_1.SessionNotFoundError(msg, opts);
-            if (bodyLower.includes("hook"))
-                throw new errors_js_1.HookNotFoundError(msg, opts);
             if (bodyLower.includes("agent"))
                 throw new errors_js_1.AgentNotFoundError(msg, opts);
             throw new errors_js_1.NotFoundError(msg, opts);

package/dist/cjs/index.js

@@ -125,7 +125,7 @@
  * See `adapters/ts/README.md` for usage examples.
  */
 Object.defineProperty(exports, "__esModule", { value: true });
-exports.UnavailableError = exports.SubstrateToolRefusedError = exports.SnapshotVersionError = exports.SnapshotTooLargeError = exports.SnapshotNotFoundError = exports.SessionNotFoundError = exports.SessionBusyError = exports.PerUserQuotaExhaustedError = exports.PauseNotConfiguredError = exports.NotPausedError = exports.LoomcycleError = exports.ChannelCursorRegressionError = exports.InvalidArgumentError = exports.NotFoundError = exports.HookNotFoundError = exports.BackpressureError = exports.AuthError = exports.AlreadyPausingError = exports.AgentNotFoundError = exports.AgentIDInUseError = exports.CLIENT_TOOL_SUBPROTOCOL = exports.clientToolsURL = exports.ClientToolHost = exports.InteractiveSession = exports.LoomcycleClient = void 0;
+exports.UnavailableError = exports.SubstrateToolRefusedError = exports.SnapshotVersionError = exports.SnapshotTooLargeError = exports.SnapshotNotFoundError = exports.SessionNotFoundError = exports.SessionBusyError = exports.PerUserQuotaExhaustedError = exports.PauseNotConfiguredError = exports.NotPausedError = exports.LoomcycleError = exports.ChannelCursorRegressionError = exports.InvalidArgumentError = exports.NotFoundError = exports.BackpressureError = exports.AuthError = exports.AlreadyPausingError = exports.AgentNotFoundError = exports.AgentIDInUseError = exports.CLIENT_TOOL_SUBPROTOCOL = exports.clientToolsURL = exports.ClientToolHost = exports.InteractiveSession = exports.LoomcycleClient = void 0;
 var client_js_1 = require("./client.js");
 Object.defineProperty(exports, "LoomcycleClient", { enumerable: true, get: function () { return client_js_1.LoomcycleClient; } });
 var interactive_js_1 = require("./interactive.js");
@@ -140,7 +140,6 @@ Object.defineProperty(exports, "AgentNotFoundError", { enumerable: true, get: fu
 Object.defineProperty(exports, "AlreadyPausingError", { enumerable: true, get: function () { return errors_js_1.AlreadyPausingError; } });
 Object.defineProperty(exports, "AuthError", { enumerable: true, get: function () { return errors_js_1.AuthError; } });
 Object.defineProperty(exports, "BackpressureError", { enumerable: true, get: function () { return errors_js_1.BackpressureError; } });
-Object.defineProperty(exports, "HookNotFoundError", { enumerable: true, get: function () { return errors_js_1.HookNotFoundError; } });
 Object.defineProperty(exports, "NotFoundError", { enumerable: true, get: function () { return errors_js_1.NotFoundError; } });
 Object.defineProperty(exports, "InvalidArgumentError", { enumerable: true, get: function () { return errors_js_1.InvalidArgumentError; } });
 Object.defineProperty(exports, "ChannelCursorRegressionError", { enumerable: true, get: function () { return errors_js_1.ChannelCursorRegressionError; } });

package/dist/client.d.ts

@@ -25,7 +25,7 @@
  */
 import { InteractiveSession } from "./interactive.js";
 import { ClientToolHost, type ConnectClientToolsOptions } from "./client-tools.js";
-import type { CredentialListResponse, CredentialMeta, CredentialScope, DirectoryInspection, DirectoryTenant, DirectoryUser, ErasureReport, ErasureResult, Agent, AgentEvent, AgentStatus, CancelAgentResult, ClientOptions, ContinueOptions, RunOverrideOptions, EffectiveConfigResponse, RetuneRunResponse, RunConfigResponse, RunPromptResponse, CreateSnapshotOptions, EnsureCodeAgentOptions, EnsureCodeAgentResult, EnsureMcpServerOptions, EnsureMcpServerResult, HealthResponse, Hook, InterruptListResponse, InterruptStatus, AckChannelOptions, AwaitChannelsOptions, BroadcastChannelsOptions, ChannelAckResult, ChannelAwaitResult, ChannelBroadcastResult, ChannelDescriptor, ChannelPeekResult, ChannelPublishResult, ChannelPurgeResult, ChannelReleaseResult, ChannelSubscribeResult, CreateChannelOptions, ListChannelsResponse, PeekChannelOptions, PublishChannelOptions, ReleaseChannelOptions, SetMemoryEntryOptions, SetMemoryEntryResponse, SubscribeChannelOptions, UpdateChannelOptions, LibraryAgentDefinition, LibraryListResponse, LibraryMcpServerDefinition, LibrarySkillDefinition, ListUsersResponse, UserRecord, CreateUserBody, UpdateUserBody, MintedUserToken, ListUserTokensResponse, RunnableAgentsResponse, LLMChatOptions, LLMChatResponse, LLMChatStreamItem, LLMEmbeddingsOptions, LLMEmbeddingsResponse, MCPServerDefVerifyResult, MemoryEmbedStatsResponse, MemoryEntriesResponse, MemoryEntryResponse, MemoryBackfillResponse, MemoryPurgeResponse, MemoryReembedResponse, MemoryScopeIDsResponse, MemoryScopesResponse, MemorySearchInput, MemorySearchResponse, PauseResult, PersistentVolumesResponse, EphemeralVolumesResponse, RegisterHookOptions, RegisterHookResponse, ResolveInterruptOptions, ResumeResult, ResolverMatrix, CompactRunResult, ReplaySessionResult, CancelTurnResult, ReviewRunResult, RunBatchOptions, RunBatchResult, RunOptions, ConfiguredRun, ConfiguredRunPatch, RunStateStreamItem, RuntimeStateResponse, SnapshotCreateResponse, SnapshotDescriptor, SnapshotEnvelope, SnapshotRestoreResponse, StreamUserRunStatesOptions, SubstrateToolInput, SubstrateToolResponse, CreatedTeam, ListTeamsResponse, PromotedTeam, RetiredTeam, TeamBreakpoints, TeamDefDetail, TeamRunDetached, TeamRunTarget, TeamVerification, TeamVersionList, TeamDiagram, TeamRunResult, PathToolInput, PathToolResponse, DocumentToolInput, DocumentToolResponse, HistoryToolInput, HistoryToolResponse, TranscriptResponse, WhoamiResponse, UsageDimension, UsageReportResponse, TokenLimit, TokenLimitsResponse, ConfigResponse, SetTokenLimitRequest } from "./types.js";
+import type { CredentialListResponse, CredentialMeta, CredentialScope, DirectoryInspection, DirectoryTenant, DirectoryUser, ErasureReport, ErasureResult, Agent, AgentEvent, AgentStatus, CancelAgentResult, ClientOptions, ContinueOptions, RunOverrideOptions, EffectiveConfigResponse, RetuneRunResponse, RunConfigResponse, RunPromptResponse, CreateSnapshotOptions, EnsureCodeAgentOptions, EnsureCodeAgentResult, EnsureMcpServerOptions, EnsureMcpServerResult, HealthResponse, InterruptListResponse, InterruptStatus, AckChannelOptions, AwaitChannelsOptions, BroadcastChannelsOptions, ChannelAckResult, ChannelAwaitResult, ChannelBroadcastResult, ChannelDescriptor, ChannelPeekResult, ChannelPublishResult, ChannelPurgeResult, ChannelReleaseResult, ChannelSubscribeResult, CreateChannelOptions, ListChannelsResponse, PeekChannelOptions, PublishChannelOptions, ReleaseChannelOptions, SetMemoryEntryOptions, SetMemoryEntryResponse, SubscribeChannelOptions, UpdateChannelOptions, LibraryAgentDefinition, LibraryListResponse, LibraryMcpServerDefinition, LibrarySkillDefinition, ListUsersResponse, UserRecord, CreateUserBody, UpdateUserBody, MintedUserToken, ListUserTokensResponse, RunnableAgentsResponse, LLMChatOptions, LLMChatResponse, LLMChatStreamItem, LLMEmbeddingsOptions, LLMEmbeddingsResponse, MCPServerDefVerifyResult, MemoryEmbedStatsResponse, MemoryEntriesResponse, MemoryEntryResponse, MemoryBackfillResponse, MemoryPurgeResponse, MemoryReembedResponse, MemoryScopeIDsResponse, MemoryScopesResponse, MemorySearchInput, MemorySearchResponse, PauseResult, PersistentVolumesResponse, EphemeralVolumesResponse, ResolveInterruptOptions, ResumeResult, ResolverMatrix, CompactRunResult, ReplaySessionResult, CancelTurnResult, ReviewRunResult, RunBatchOptions, RunBatchResult, RunOptions, ConfiguredRun, ConfiguredRunPatch, RunStateStreamItem, RuntimeStateResponse, SnapshotCreateResponse, SnapshotDescriptor, SnapshotEnvelope, SnapshotRestoreResponse, StreamUserRunStatesOptions, SubstrateToolInput, SubstrateToolResponse, CreatedTeam, ListTeamsResponse, PromotedTeam, RetiredTeam, TeamBreakpoints, TeamDefDetail, TeamRunDetached, TeamRunTarget, TeamVerification, TeamVersionList, TeamDiagram, TeamRunResult, PathToolInput, PathToolResponse, DocumentToolInput, DocumentToolResponse, HistoryToolInput, HistoryToolResponse, TranscriptResponse, WhoamiResponse, UsageDimension, UsageReportResponse, TokenLimit, TokenLimitsResponse, ConfigResponse, SetTokenLimitRequest } from "./types.js";
 export declare class LoomcycleClient {
     private ctx;
     constructor(opts?: ClientOptions);
@@ -696,35 +696,6 @@ export declare class LoomcycleClient {
         resolvedBy?: string;
         signal?: AbortSignal;
     }): Promise<unknown>;
-    /** Register a pre- or post-tool hook. Its body is a webhook — the
-     *  callback_url must be an http:// or https:// endpoint the CONSUMER
-     *  runs; loomcycle POSTs PreHookCall / PostHookCall payloads to it —
-     *  or a code-js body (`code`), run in-process by loomcycle. Set
-     *  exactly one. This method manages registration only; a webhook's
-     *  receiver is the consumer's own HTTP framework (Express, Next.js,
-     *  etc.).
-     *
-     *  Re-registering the same (owner, name) replaces the prior entry
-     *  with a fresh id (idempotent app-restart contract).
-     *
-     *  Raises InvalidArgumentError on 400 (bad URL / phase / missing
-     *  required fields). */
-    registerHook(opts: RegisterHookOptions & {
-        signal?: AbortSignal;
-    }): Promise<RegisterHookResponse>;
-    /** List every currently-registered hook. Returns the array
-     *  unwrapped (the wire envelope is `{hooks: [...]}` — we strip
-     *  the envelope to match listUserAgents). In-memory only — empty
-     *  after a loomcycle restart. */
-    listHooks(opts?: {
-        signal?: AbortSignal;
-    }): Promise<Hook[]>;
-    /** Delete a registered hook by id. Raises HookNotFoundError on
-     *  404. Returns void on success (the HTTP 200 body `{deleted: id}`
-     *  is dropped — callers already know the id they passed). */
-    deleteHook(id: string, opts?: {
-        signal?: AbortSignal;
-    }): Promise<void>;
     /** Invoke the AgentDef substrate tool over HTTP. Mirrors the
      *  MCP `agentdef` meta-tool and the in-band agent tool_use of
      *  the same name — different transport, identical semantics.

package/dist/client.js

@@ -1112,55 +1112,6 @@ export class LoomcycleClient {
             signal: opts?.signal,
         });
     }
-    // ---- Hook management (hooks-connector series, PR C) ----
-    /** Register a pre- or post-tool hook. Its body is a webhook — the
-     *  callback_url must be an http:// or https:// endpoint the CONSUMER
-     *  runs; loomcycle POSTs PreHookCall / PostHookCall payloads to it —
-     *  or a code-js body (`code`), run in-process by loomcycle. Set
-     *  exactly one. This method manages registration only; a webhook's
-     *  receiver is the consumer's own HTTP framework (Express, Next.js,
-     *  etc.).
-     *
-     *  Re-registering the same (owner, name) replaces the prior entry
-     *  with a fresh id (idempotent app-restart contract).
-     *
-     *  Raises InvalidArgumentError on 400 (bad URL / phase / missing
-     *  required fields). */
-    async registerHook(opts) {
-        const body = {
-            owner: opts.owner,
-            name: opts.name,
-            phase: opts.phase,
-        };
-        if (opts.callbackUrl !== undefined)
-            body.callback_url = opts.callbackUrl;
-        if (opts.code !== undefined)
-            body.code = opts.code;
-        if (opts.agents !== undefined)
-            body.agents = opts.agents;
-        if (opts.tools !== undefined)
-            body.tools = opts.tools;
-        if (opts.failMode !== undefined)
-            body.fail_mode = opts.failMode;
-        if (opts.timeoutMs !== undefined && opts.timeoutMs > 0) {
-            body.timeout_ms = opts.timeoutMs;
-        }
-        return postJSON(this.ctx, "/v1/hooks", body, opts);
-    }
-    /** List every currently-registered hook. Returns the array
-     *  unwrapped (the wire envelope is `{hooks: [...]}` — we strip
-     *  the envelope to match listUserAgents). In-memory only — empty
-     *  after a loomcycle restart. */
-    async listHooks(opts) {
-        const resp = await jsonFetch(this.ctx, "/v1/hooks", opts);
-        return resp.hooks ?? [];
-    }
-    /** Delete a registered hook by id. Raises HookNotFoundError on
-     *  404. Returns void on success (the HTTP 200 body `{deleted: id}`
-     *  is dropped — callers already know the id they passed). */
-    async deleteHook(id, opts) {
-        await deleteRequest(this.ctx, `/v1/hooks/${encodeURIComponent(id)}`, opts);
-    }
     // ---- v0.8.22 substrate admin (AgentDef + SkillDef) ----
     /** Invoke the AgentDef substrate tool over HTTP. Mirrors the
      *  MCP `agentdef` meta-tool and the in-band agent tool_use of

package/dist/errors.d.ts

@@ -173,16 +173,6 @@ export declare class SnapshotVersionError extends LoomcycleError {
         bodyText?: string;
     });
 }
-/** HookNotFoundError — raised by deleteHook when no hook has the
- *  supplied id (HTTP 404 with "hook" in the body). Extends
- *  NotFoundError so consumers catching the broader category get this
- *  one too. */
-export declare class HookNotFoundError extends NotFoundError {
-    constructor(message: string, opts?: {
-        status?: number;
-        bodyText?: string;
-    });
-}
 /** ChannelCursorRegressionError — raised by `client.ackChannel()`
  *  when the caller-supplied cursor is older than the currently-
  *  committed cursor for the (channel, scope, scope_id) tuple. HTTP

package/dist/errors.js

@@ -176,16 +176,6 @@ export class SnapshotVersionError extends LoomcycleError {
         this.name = "SnapshotVersionError";
     }
 }
-/** HookNotFoundError — raised by deleteHook when no hook has the
- *  supplied id (HTTP 404 with "hook" in the body). Extends
- *  NotFoundError so consumers catching the broader category get this
- *  one too. */
-export class HookNotFoundError extends NotFoundError {
-    constructor(message, opts) {
-        super(message, opts);
-        this.name = "HookNotFoundError";
-    }
-}
 /** ChannelCursorRegressionError — raised by `client.ackChannel()`
  *  when the caller-supplied cursor is older than the currently-
  *  committed cursor for the (channel, scope, scope_id) tuple. HTTP

package/dist/fetch-helpers.d.ts

@@ -79,7 +79,6 @@ export declare function deleteJSON<T>(ctx: _FetchContext, path: string, opts?: {
  *   401         → AuthError
  *   404 + "snapshot"   → SnapshotNotFoundError ────────┐
  *   404 + "session"    → SessionNotFoundError          │  All extend
- *   404 + "hook"       → HookNotFoundError             │  NotFoundError —
  *   404 + "agent"      → AgentNotFoundError            │  callers can
  *   404 + (other)      → NotFoundError (base)          │  catch any 404
  *                                                      │  with one

package/dist/fetch-helpers.js

@@ -9,7 +9,7 @@
  * Method-level code in client.ts stays focused on URL + body shape;
  * the boring fetch + error-translation machinery lives here.
  */
-import { AgentIDInUseError, AgentNotFoundError, AlreadyPausingError, AuthError, BackpressureError, ChannelCursorRegressionError, HookNotFoundError, InvalidArgumentError, LoomcycleError, NotFoundError, NotPausedError, PauseNotConfiguredError, PerUserQuotaExhaustedError, SessionBusyError, SessionNotFoundError, SnapshotNotFoundError, SnapshotTooLargeError, SnapshotVersionError, SubstrateToolRefusedError, UnavailableError, } from "./errors.js";
+import { AgentIDInUseError, AgentNotFoundError, AlreadyPausingError, AuthError, BackpressureError, ChannelCursorRegressionError, InvalidArgumentError, LoomcycleError, NotFoundError, NotPausedError, PauseNotConfiguredError, PerUserQuotaExhaustedError, SessionBusyError, SessionNotFoundError, SnapshotNotFoundError, SnapshotTooLargeError, SnapshotVersionError, SubstrateToolRefusedError, UnavailableError, } from "./errors.js";
 /** authHeaders builds the standard request header set: JSON Accept
  *  + Bearer token when the client was constructed with one. The
  *  caller adds Content-Type when posting a body. */
@@ -159,7 +159,6 @@ export async function deleteJSON(ctx, path, opts) {
  *   401         → AuthError
  *   404 + "snapshot"   → SnapshotNotFoundError ────────┐
  *   404 + "session"    → SessionNotFoundError          │  All extend
- *   404 + "hook"       → HookNotFoundError             │  NotFoundError —
  *   404 + "agent"      → AgentNotFoundError            │  callers can
  *   404 + (other)      → NotFoundError (base)          │  catch any 404
  *                                                      │  with one
@@ -213,9 +212,6 @@ export async function raiseFromResponse(resp) {
             // Priority: most-specific keyword wins.
             // - "snapshot" → SnapshotNotFoundError
             // - "session"  → SessionNotFoundError
-            // - "hook"     → HookNotFoundError (must precede "agent" — the
-            //                hooks 404 body is `no hook with id "..."`,
-            //                doesn't mention "agent")
             // - "agent" or "agent_id" → AgentNotFoundError
             // - otherwise → NotFoundError (base) — e.g. memory rows, interrupts,
             //   or any future 404-returning endpoint that doesn't fit the
@@ -224,8 +220,6 @@ export async function raiseFromResponse(resp) {
                 throw new SnapshotNotFoundError(msg, opts);
             if (bodyLower.includes("session"))
                 throw new SessionNotFoundError(msg, opts);
-            if (bodyLower.includes("hook"))
-                throw new HookNotFoundError(msg, opts);
             if (bodyLower.includes("agent"))
                 throw new AgentNotFoundError(msg, opts);
             throw new NotFoundError(msg, opts);

package/dist/index.d.ts

@@ -128,5 +128,5 @@ 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, Agent, AgentStatus, AgentUsage, RunResult, RunSpec, ConfiguredRun, ConfiguredRunPatch, ToolChoiceOptions, OutputFormatOptions, CancelAgentResult, ListAgentsResponse, 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, Hook, HookFailMode, HookPhase, HookToolCall, HookToolResult, ListHooksResponse, PostHookCall, PostHookResult, PreHookCall, PreHookResult, RegisterHookOptions, RegisterHookResponse, SubstrateToolInput, SubstrateToolResponse, TeamNameSummary, ListTeamsResponse, TeamDiagram, CreatedTeam, PromotedTeam, RetiredTeam, TeamDefDetail, TeamVerification, 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, 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, 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, EffectiveConfigResponse, EffectiveConfigSource, EffectiveValue, RetuneRunResponse, RunConfigRecord, RunConfigResponse, RunPromptResponse, RunPromptSnapshot, PromptBlock, TokenLimit, TokenLimitsResponse, ConfigResponse, ConfigProvider, ConfigModel, ConfigSearch, ConfigInstance, SetTokenLimitRequest, CredentialScope, CredentialMeta, CredentialListResponse, } from "./types.js";
-export { AgentIDInUseError, AgentNotFoundError, AlreadyPausingError, AuthError, BackpressureError, HookNotFoundError, NotFoundError, InvalidArgumentError, ChannelCursorRegressionError, LoomcycleError, NotPausedError, PauseNotConfiguredError, PerUserQuotaExhaustedError, SessionBusyError, SessionNotFoundError, SnapshotNotFoundError, SnapshotTooLargeError, SnapshotVersionError, SubstrateToolRefusedError, UnavailableError, } from "./errors.js";
+export type { AgentEvent, ClientOptions, ContinueOptions, EventType, HostWidening, ImageMediaType, ParentContext, PromptContent, PromptSegment, RetryInfo, RunOptions, SamplingOptions, CompactionOptions, ContextOptions, ToolUse, Usage, Agent, AgentStatus, AgentUsage, RunResult, RunSpec, ConfiguredRun, ConfiguredRunPatch, ToolChoiceOptions, OutputFormatOptions, CancelAgentResult, ListAgentsResponse, 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, HookFailMode, HookPhase, HookToolCall, HookToolResult, PostHookCall, PostHookResult, PreHookCall, PreHookResult, SubstrateToolInput, SubstrateToolResponse, TeamNameSummary, ListTeamsResponse, TeamDiagram, CreatedTeam, PromotedTeam, RetiredTeam, TeamDefDetail, TeamVerification, 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, 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, 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, EffectiveConfigResponse, EffectiveConfigSource, EffectiveValue, RetuneRunResponse, RunConfigRecord, RunConfigResponse, RunPromptResponse, RunPromptSnapshot, PromptBlock, TokenLimit, TokenLimitsResponse, ConfigResponse, ConfigProvider, ConfigModel, ConfigSearch, ConfigInstance, SetTokenLimitRequest, CredentialScope, CredentialMeta, CredentialListResponse, } from "./types.js";
+export { AgentIDInUseError, AgentNotFoundError, AlreadyPausingError, AuthError, BackpressureError, NotFoundError, InvalidArgumentError, ChannelCursorRegressionError, LoomcycleError, NotPausedError, PauseNotConfiguredError, PerUserQuotaExhaustedError, SessionBusyError, SessionNotFoundError, SnapshotNotFoundError, SnapshotTooLargeError, SnapshotVersionError, SubstrateToolRefusedError, UnavailableError, } from "./errors.js";

package/dist/index.js

@@ -126,4 +126,4 @@
 export { LoomcycleClient } from "./client.js";
 export { InteractiveSession } from "./interactive.js";
 export { ClientToolHost, clientToolsURL, CLIENT_TOOL_SUBPROTOCOL } from "./client-tools.js";
-export { AgentIDInUseError, AgentNotFoundError, AlreadyPausingError, AuthError, BackpressureError, HookNotFoundError, NotFoundError, InvalidArgumentError, ChannelCursorRegressionError, LoomcycleError, NotPausedError, PauseNotConfiguredError, PerUserQuotaExhaustedError, SessionBusyError, SessionNotFoundError, SnapshotNotFoundError, SnapshotTooLargeError, SnapshotVersionError, SubstrateToolRefusedError, UnavailableError, } from "./errors.js";
+export { AgentIDInUseError, AgentNotFoundError, AlreadyPausingError, AuthError, BackpressureError, NotFoundError, InvalidArgumentError, ChannelCursorRegressionError, LoomcycleError, NotPausedError, PauseNotConfiguredError, PerUserQuotaExhaustedError, SessionBusyError, SessionNotFoundError, SnapshotNotFoundError, SnapshotTooLargeError, SnapshotVersionError, SubstrateToolRefusedError, UnavailableError, } from "./errors.js";

package/dist/types.d.ts

@@ -1796,60 +1796,6 @@ export interface ResolveInterruptOptions {
  *  the failure's classification in the payload. */
 export type HookPhase = "pre" | "post" | "post_failure" | "agent_start" | "agent_stop" | "subagent_start" | "subagent_stop" | "pre_compact" | "post_compact" | "run_end";
 export type HookFailMode = "open" | "closed";
-/** Hook is the full descriptor returned by listHooks. The id +
- *  registered_at are loomcycle-assigned; the rest mirrors what was
- *  POSTed to registerHook. Field names use snake_case to match the
- *  Go server's JSON output. */
-export interface Hook {
-    id: string;
-    owner: string;
-    name: string;
-    phase: HookPhase;
-    agents: string[];
-    tools: string[];
-    callback_url: string;
-    fail_mode: HookFailMode;
-    timeout_ms: number;
-    registered_at: string;
-    /** The code-js body, when the hook has one instead of a callback_url. */
-    code?: string;
-}
-/** RegisterHookOptions uses camelCase (JS norm for method parameters)
- *  and is translated to snake_case in the request body — same split as
- *  RunOptions / CreateSnapshotOptions. */
-export interface RegisterHookOptions {
-    /** App UID; (owner, name) is the identity tuple. Re-registering the
-     *  same pair replaces the prior entry with a fresh id. */
-    owner: string;
-    name: string;
-    phase: HookPhase;
-    /** Agent name globs (exact match or trailing-* prefix). Empty list
-     *  matches every agent (equivalent to ["*"]). */
-    agents?: string[];
-    /** Tool name globs (same syntax). Empty matches every tool. */
-    tools?: string[];
-    /** http:// or https:// URL loomcycle POSTs PreHookCall /
-     *  PostHookCall payloads to. Set this or `code`. */
-    callbackUrl?: string;
-    /** A code-js body in place of a webhook: JavaScript defining a
-     *  top-level `hook(ev)` that returns the decision. Its only tool is
-     *  `Interruption` (ask, notify). Needs code hooks enabled on the
-     *  server. Set this or `callbackUrl`. */
-    code?: string;
-    /** "open" (default) — webhook errors pass through. "closed" — webhook
-     *  errors fail the tool call with IsError=true. */
-    failMode?: HookFailMode;
-    /** Per-call timeout. 0 / omitted = registry default (5 s; 50 ms for a
-     *  code body, where it bounds each run of the code, capped at 1 s). */
-    timeoutMs?: number;
-}
-export interface RegisterHookResponse {
-    /** Loomcycle-assigned id. Use it on deleteHook. */
-    id: string;
-}
-export interface ListHooksResponse {
-    hooks: Hook[];
-}
 export interface HookToolCall {
     id: string;
     name: string;
@@ -2872,6 +2818,30 @@ export interface AgentInterruptionACL {
     kinds?: string[];
     max_pending?: number;
 }
+/** A hook event: a tool call's `pre` / `post` / `post_failure`, or a point in
+ *  the run. */
+export type HookEvent = "pre" | "post" | "post_failure" | "agent_start" | "agent_stop" | "subagent_start" | "subagent_stop" | "pre_compact" | "post_compact" | "run_end";
+/** A webhook written into the definition that attaches it. */
+export interface InlineWebhook {
+    name: string;
+    url: string;
+    fail_mode?: HookFailMode;
+    timeout_ms?: number;
+    /** Sent with each call. A value may name a credential as `$cred:<name>`,
+     *  resolved for the run when the hook is called — keep secrets there, not in
+     *  the URL or a literal value. */
+    headers?: Record<string, string>;
+}
+/** One hook an agent carries: a HookDef name (`"gate"`, or `"gate@3"` pinned)
+ *  or an inline webhook. */
+export type HookEntry = string | InlineWebhook;
+/** Hooks per event, in chain order. */
+export type EventHooks = Partial<Record<HookEvent, HookEntry[]>>;
+/** A `tools` entry that carries that tool's own hooks. */
+export interface ToolEntry {
+    name: string;
+    hooks: Partial<Record<"pre" | "post" | "post_failure", HookEntry[]>>;
+}
 export interface AgentDefOverlay {
     provider?: string;
     model?: string;
@@ -2889,7 +2859,14 @@ export interface AgentDefOverlay {
     max_iterations?: number;
     max_concurrent_children?: number;
     system_prompt?: string;
-    tools?: string[];
+    /** Tool names; an entry may be `{name, hooks}` to give that tool its own
+     *  pre / post hooks (stored as the name plus a `tool_hooks` entry). */
+    tools?: (string | ToolEntry)[];
+    /** The agent's own hooks: run events, and tool events for every tool. A run
+     *  takes these verbatim. */
+    hooks?: EventHooks;
+    /** Each tool's own hooks, by tool name. */
+    tool_hooks?: Record<string, Partial<Record<"pre" | "post" | "post_failure", HookEntry[]>>>;
     skills?: string[];
     memory_scopes?: string[];
     /** RFC DF: recall attaches the conversation TURN each fact was distilled from,

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@loomcycle/client",
-  "version": "1.96.0",
+  "version": "1.97.0",
   "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",