@betterlu/agentlu 1.11.0 → 1.12.0

package/README.md

@@ -236,7 +236,7 @@ Plain text (throws unless `status === "completed"` with non-empty `output_text`)
 const { text } = await ai.tag.runText({ input: "summarize this" });
 ```
 
-`timeoutMs` aborts the HTTP attempt and, when `timeout_ms` is omitted, is also sent as the server-side run budget. Constructor `new AgentLu({ timeoutMs: 30_000 })` is the default for calls that omit it.
+`timeoutMs` aborts the HTTP attempt and, when `timeout_ms` is omitted, is also sent as the server-side run budget. Constructor `new AgentLu({ timeoutMs: 30_000 })` is the default for calls that omit it. The server rejects `timeout_ms` below 15 000 ms and `max_output_tokens` below 256 with a 400 naming the minimum; `/v1/chat/completions` applies the same minimum to `max_tokens` / `max_completion_tokens`. Registered defaults below either minimum are clamped up with a once-per-client warning.
 
 Upload-and-run:
 

package/dist/generated.d.ts

@@ -130,7 +130,7 @@ export interface WireCreateResponse {
     "conversation"?: string | {
         "id": string;
     };
-    /** Optional and discouraged. Omit it to use the model's own output limit; values here are applied verbatim. If the limit is reached, the HTTP 200 Response has status `incomplete`, reason `max_output_tokens`, and may retain partial output. */
+    /** Optional and discouraged. Minimum 256 tokens; omit it to use the model's own output limit; values here are applied verbatim. A registered client default below the minimum is clamped up. If the limit is reached, the HTTP 200 Response has status `incomplete`, reason `max_output_tokens`, and may retain partial output. */
     "max_output_tokens"?: number;
     "temperature"?: number;
     "text"?: {
@@ -156,13 +156,13 @@ export interface WireCreateResponse {
     "tool_choice"?: "auto" | "none" | "required";
     "metadata"?: Record<string, string>;
     "include"?: Array<"reasoning" | "rounds" | "subagents" | "artifacts">;
-    /** Which agent runs the request. The recommended general machine agent is `api`, which has no persona: `instructions` replace its system prompt. Pin `fast` for the chat-tuned version. `direct` selects the direct tier: the profile-free `api` agent with no tools and no session (see the Tiers section). `household/<slug>` runs a household agent built in the Agents studio (list them at GET /v1/agents). An `<app>/<name>` id runs an agent the caller's app declared at registration. `research` is an alias for `thorough` with Report output (a sourced report artifact). Retired ids (`mealu`, `nestlu`, `kitchen`, `waterlu`, `money`, `swarm`, `storylu`, `google-research`, `google-image`, `android`) return HTTP 400 `unknown_agent` with a pointer to their successor; the Android phone is now the `android` tool family on `assistant`. */
-    "agent"?: "auto" | "fast" | "thorough" | "assistant" | "code" | "google" | "image" | "api" | "digest" | "herald" | "cradle" | "custom" | "direct" | string | "mealu" | "nestlu" | "kitchen" | "waterlu" | "money" | "swarm" | "stage" | "roleplay" | "storylu" | "google-research" | "google-image" | "android" | "research";
+    /** Which agent runs the request. The recommended general machine agent is `api`, which has no persona: `instructions` replace its system prompt. Pin `fast` for the chat-tuned version. `direct` selects the direct tier: the profile-free `api` agent with no tools and no session (see the Tiers section). `household/<slug>` runs a household agent built in the Agents studio (list them at GET /v1/agents). An `<app>/<name>` id runs an agent the caller's app declared at registration. `research` is an alias for `thorough` with Report output (a sourced report artifact). Retired ids (`mealu`, `nestlu`, `kitchen`, `waterlu`, `money`, `code`, `image`, `swarm`, `storylu`, `google-research`, `google-image`, `android`) return HTTP 400 `unknown_agent` with a pointer to their successor; Code and Image merged into `assistant` (AgentLu). The Android phone is now the `android` tool family on `assistant`. */
+    "agent"?: "auto" | "fast" | "thorough" | "assistant" | "google" | "api" | "digest" | "herald" | "cradle" | "custom" | "direct" | string | "mealu" | "nestlu" | "kitchen" | "waterlu" | "money" | "code" | "image" | "swarm" | "stage" | "roleplay" | "storylu" | "google-research" | "google-image" | "android" | "research";
     /** Thinking level. Explicit `effort: "off"` is honored; other requests are clamped to the selected model's supported capabilities. The SDK does not promise provider benchmark parity. */
     "reasoning"?: {
         "effort"?: "off" | "minimal" | "low" | "medium" | "high" | "xhigh" | "max";
     };
-    /** Wall clock for this run. Default: the use-case tier's (45s instant / 180s standard / 600s deep). */
+    /** Wall clock for this run. Minimum 15000 ms (15 s); a registered client default below it is clamped up. Default: the use-case tier's (45s instant / 180s standard / 600s deep). */
     "timeout_ms"?: number;
     /** Provider attempts for this run (1 = none). Bounds model-chain fallbacks. Default: the use-case tier's (instant 1, standard 2, deep 3) when the client declares a profile; without one the run keeps the pre-tier budget (the direct tier walks its whole chain, the agent tier does not fall back). */
     "attempts"?: number;
@@ -235,9 +235,9 @@ export interface WireRegisterClientRequest {
     /** Run defaults applied when a request omits the field: request > registered client default > use-case tier > agent/profile default. The built-in `store` default is true. Register one client per use-case (e.g. mealu-enrich) with its system prompt and tools baked in. */
     "defaults"?: {
         "backend"?: "pi";
-        "agent"?: "auto" | "fast" | "thorough" | "assistant" | "code" | "google" | "image" | "api" | "digest" | "herald" | "cradle" | "custom" | "direct" | string | "mealu" | "nestlu" | "kitchen" | "waterlu" | "money" | "swarm" | "stage" | "roleplay" | "storylu" | "google-research" | "google-image" | "android" | "research";
+        "agent"?: "auto" | "fast" | "thorough" | "assistant" | "google" | "api" | "digest" | "herald" | "cradle" | "custom" | "direct" | string | "mealu" | "nestlu" | "kitchen" | "waterlu" | "money" | "code" | "image" | "swarm" | "stage" | "roleplay" | "storylu" | "google-research" | "google-image" | "android" | "research";
         "model"?: string;
-        "modelRoute"?: "chat.quick" | "chat.household" | "chat.deep" | "chat.code" | "device" | "background.digest" | "utility" | "memory.extract" | "memory.judge" | "memory.consolidate";
+        "modelRoute"?: "chat.quick" | "chat.household" | "chat.deep" | "device" | "background.digest" | "utility" | "memory.extract" | "memory.judge" | "memory.consolidate";
         "instructions"?: string;
         "temperature"?: number;
         "store"?: boolean;
@@ -286,12 +286,12 @@ export interface WireRegisterClientRequest {
 /** Run defaults applied when a request omits the field: request > registered client default > use-case tier > agent/profile default. The built-in `store` default is true. Register one client per use-case (e.g. mealu-enrich) with its system prompt and tools baked in. */
 export interface WireClientDefaults {
     "backend"?: "pi";
-    /** Which agent runs the request. The recommended general machine agent is `api`, which has no persona: `instructions` replace its system prompt. Pin `fast` for the chat-tuned version. `direct` selects the direct tier: the profile-free `api` agent with no tools and no session (see the Tiers section). `household/<slug>` runs a household agent built in the Agents studio (list them at GET /v1/agents). An `<app>/<name>` id runs an agent the caller's app declared at registration. `research` is an alias for `thorough` with Report output (a sourced report artifact). Retired ids (`mealu`, `nestlu`, `kitchen`, `waterlu`, `money`, `swarm`, `storylu`, `google-research`, `google-image`, `android`) return HTTP 400 `unknown_agent` with a pointer to their successor; the Android phone is now the `android` tool family on `assistant`. */
-    "agent"?: "auto" | "fast" | "thorough" | "assistant" | "code" | "google" | "image" | "api" | "digest" | "herald" | "cradle" | "custom" | "direct" | string | "mealu" | "nestlu" | "kitchen" | "waterlu" | "money" | "swarm" | "stage" | "roleplay" | "storylu" | "google-research" | "google-image" | "android" | "research";
+    /** Which agent runs the request. The recommended general machine agent is `api`, which has no persona: `instructions` replace its system prompt. Pin `fast` for the chat-tuned version. `direct` selects the direct tier: the profile-free `api` agent with no tools and no session (see the Tiers section). `household/<slug>` runs a household agent built in the Agents studio (list them at GET /v1/agents). An `<app>/<name>` id runs an agent the caller's app declared at registration. `research` is an alias for `thorough` with Report output (a sourced report artifact). Retired ids (`mealu`, `nestlu`, `kitchen`, `waterlu`, `money`, `code`, `image`, `swarm`, `storylu`, `google-research`, `google-image`, `android`) return HTTP 400 `unknown_agent` with a pointer to their successor; Code and Image merged into `assistant` (AgentLu). The Android phone is now the `android` tool family on `assistant`. */
+    "agent"?: "auto" | "fast" | "thorough" | "assistant" | "google" | "api" | "digest" | "herald" | "cradle" | "custom" | "direct" | string | "mealu" | "nestlu" | "kitchen" | "waterlu" | "money" | "code" | "image" | "swarm" | "stage" | "roleplay" | "storylu" | "google-research" | "google-image" | "android" | "research";
     /** ModelConfig id (GET /v1/models). Stock clients may also use an agent name here; prefer explicit `agent` for machine calls. */
     "model"?: string;
     /** Task route whose pool order and effort apply to automatic model selection. Mutually exclusive with model. Explicit request models, builtin chat agents, and agent model pins win; app-owned and api agents inherit the client route. */
-    "modelRoute"?: "chat.quick" | "chat.household" | "chat.deep" | "chat.code" | "device" | "background.digest" | "utility" | "memory.extract" | "memory.judge" | "memory.consolidate";
+    "modelRoute"?: "chat.quick" | "chat.household" | "chat.deep" | "device" | "background.digest" | "utility" | "memory.extract" | "memory.judge" | "memory.consolidate";
     /** System prompt for every run of this client. */
     "instructions"?: string;
     "temperature"?: number;
@@ -322,8 +322,9 @@ export interface WireClientDefaults {
         "url": string;
         "allowed_tools"?: string[];
     }>;
+    /** Default wall clock when the request omits `timeout_ms`. Values below 15000 ms are clamped up at run time (with a once-per-client warning). */
     "timeoutMs"?: number;
-    /** Default output cap when the request omits `max_output_tokens`. The use-case tier supplies one when this is unset (instant 2048, deep 8192, standard none); requests always win. Honored for defaults written after this release: a value stored earlier stays inert until the app re-declares its defaults (or the console edits them), so a re-enable can never silently cap runs that used to complete. */
+    /** Default output cap when the request omits `max_output_tokens`. Values below 256 tokens are clamped up at run time (with a once-per-client warning). The use-case tier supplies one when this is unset (instant 2048, deep 8192, standard none); requests always win. Honored for defaults written after this release: a value stored earlier stays inert until the app re-declares its defaults (or the console edits them), so a re-enable can never silently cap runs that used to complete. */
     "maxOutputTokens"?: number;
     /** Provider attempts per run (1 = none). Bounds model-chain fallbacks, and is the background queue's retry budget. Defaults to the tier's (instant 1, standard 2, deep 3) when `use_case_profile.priority` is declared; without one the run keeps the pre-tier budget. */
     "attempts"?: number;
@@ -352,7 +353,7 @@ export interface WireAppAgentDeclaration {
 }
 export interface WireCreateThreadRequest {
     "title"?: string;
-    "agent"?: "auto" | "fast" | "thorough" | "assistant" | "code" | "google" | "image" | "api" | "digest" | "herald" | "cradle" | "custom" | "research" | string;
+    "agent"?: "auto" | "fast" | "thorough" | "assistant" | "google" | "api" | "digest" | "herald" | "cradle" | "custom" | "research" | string;
     "model"?: string;
     "person"?: string | null;
     "owner"?: "client" | "person";
@@ -388,7 +389,7 @@ export interface WireResponse {
     "created_at": number;
     "status": "queued" | "in_progress" | "completed" | "failed" | "incomplete" | "cancelled";
     "backend": "pi";
-    "agent": "auto" | "fast" | "thorough" | "assistant" | "code" | "google" | "image" | "api" | "digest" | "herald" | "cradle" | "custom";
+    "agent": "auto" | "fast" | "thorough" | "assistant" | "google" | "api" | "digest" | "herald" | "cradle" | "custom";
     "model": string;
     "conversation"?: {
         "id": string;
@@ -458,7 +459,7 @@ export interface WireResponse {
         "thread_id"?: string | null;
         "retries"?: number;
         "effective_model"?: string | null;
-        "model_route"?: "chat.quick" | "chat.household" | "chat.deep" | "chat.code" | "device" | "background.digest" | "utility" | "memory.extract" | "memory.judge" | "memory.consolidate";
+        "model_route"?: "chat.quick" | "chat.household" | "chat.deep" | "device" | "background.digest" | "utility" | "memory.extract" | "memory.judge" | "memory.consolidate";
         "service_tier"?: "standard" | "priority";
         "execution_path"?: string | null;
         "queue_wait_ms"?: number | null;
@@ -578,7 +579,7 @@ export interface WireThread {
     "created_at": number;
     "updated_at": number;
     "title": string;
-    "agent": "auto" | "fast" | "thorough" | "assistant" | "code" | "google" | "image" | "api" | "digest" | "herald" | "cradle" | "custom";
+    "agent": "auto" | "fast" | "thorough" | "assistant" | "google" | "api" | "digest" | "herald" | "cradle" | "custom";
     "model": string | null;
     /** "api" for threads created through /v1; "chat" when a human started it. */
     "origin": string;
@@ -617,9 +618,9 @@ export interface WireClient {
     "allow_person_threads"?: boolean;
     "defaults"?: {
         "backend"?: "pi";
-        "agent"?: "auto" | "fast" | "thorough" | "assistant" | "code" | "google" | "image" | "api" | "digest" | "herald" | "cradle" | "custom" | "direct" | string | "mealu" | "nestlu" | "kitchen" | "waterlu" | "money" | "swarm" | "stage" | "roleplay" | "storylu" | "google-research" | "google-image" | "android" | "research";
+        "agent"?: "auto" | "fast" | "thorough" | "assistant" | "google" | "api" | "digest" | "herald" | "cradle" | "custom" | "direct" | string | "mealu" | "nestlu" | "kitchen" | "waterlu" | "money" | "code" | "image" | "swarm" | "stage" | "roleplay" | "storylu" | "google-research" | "google-image" | "android" | "research";
         "model"?: string;
-        "modelRoute"?: "chat.quick" | "chat.household" | "chat.deep" | "chat.code" | "device" | "background.digest" | "utility" | "memory.extract" | "memory.judge" | "memory.consolidate";
+        "modelRoute"?: "chat.quick" | "chat.household" | "chat.deep" | "device" | "background.digest" | "utility" | "memory.extract" | "memory.judge" | "memory.consolidate";
         "instructions"?: string;
         "temperature"?: number;
         "store"?: boolean;
@@ -743,7 +744,7 @@ export interface WireResponseList {
         "created_at": number;
         "status": "queued" | "in_progress" | "completed" | "failed" | "incomplete" | "cancelled";
         "backend": "pi";
-        "agent": "auto" | "fast" | "thorough" | "assistant" | "code" | "google" | "image" | "api" | "digest" | "herald" | "cradle" | "custom";
+        "agent": "auto" | "fast" | "thorough" | "assistant" | "google" | "api" | "digest" | "herald" | "cradle" | "custom";
         "model": string;
         "conversation"?: {
             "id": string;
@@ -808,7 +809,7 @@ export interface WireResponseList {
             "thread_id"?: string | null;
             "retries"?: number;
             "effective_model"?: string | null;
-            "model_route"?: "chat.quick" | "chat.household" | "chat.deep" | "chat.code" | "device" | "background.digest" | "utility" | "memory.extract" | "memory.judge" | "memory.consolidate";
+            "model_route"?: "chat.quick" | "chat.household" | "chat.deep" | "device" | "background.digest" | "utility" | "memory.extract" | "memory.judge" | "memory.consolidate";
             "service_tier"?: "standard" | "priority";
             "execution_path"?: string | null;
             "queue_wait_ms"?: number | null;
@@ -878,7 +879,7 @@ export interface WireThreadList {
         "created_at": number;
         "updated_at": number;
         "title": string;
-        "agent": "auto" | "fast" | "thorough" | "assistant" | "code" | "google" | "image" | "api" | "digest" | "herald" | "cradle" | "custom";
+        "agent": "auto" | "fast" | "thorough" | "assistant" | "google" | "api" | "digest" | "herald" | "cradle" | "custom";
         "model": string | null;
         "origin": string;
         "end_user"?: string | null;

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@betterlu/agentlu",
-  "version": "1.11.0",
+  "version": "1.12.0",
   "description": "Client for the agentlu service API (/v1). Or just use the openai SDK pointed at http://localhost:8912/v1.",
   "type": "module",
   "main": "./dist/index.js",