@columenlabs/lumen-ai 0.1.223 → 0.1.224

package/README.md

@@ -103,7 +103,7 @@ app.all('/api/assistant/*', (c) => routes(c.req.raw));
 - **Hand off and advice.** The `escalate` tool hands one task to a higher tier (the person sets next, any or only when asked); Anthropic's advisor tool lets a higher tier send a plan, at most two an answer.
 - **Chats** run on the agent (`./agent`, `LumenAgent`, below): the app routes `POST /chat` and each chat's reads, cards and Undo to its own agent, and `assistantRoutes` answers `POST /chat` with 410 `moved`. Chats saved by the old turn loop stay readable (`GET /chats`, `GET|DELETE /chats/:id`) until `assistant.purge()` drops them 30 days after their last message.
 - **Screen moves**: while the person's Settings ▸ Screen is Move (the default), the panel sends its page map (`AssistantMessage.screen`: routes, nav pages, Settings sections, cards on screen, rows to open) and `LumenAgent` gives the model a `screen` tool (`./agent` `screen.ts`). Each call's moves (go, settings, chart, open, point) are checked against the map, kept in the chat and streamed as a `screen` event; the panel runs them through `AssistantScreenProvider` (mounted by `LumenShell`) with an Undo chip, and their outcomes go back with the next message (`outcomes`). Nothing is saved by a move.
-- **Background work** an app runs for a person (a score, a summary) is `assistant.complete(caller, { task, system, prompt, images?, maxTokens })`: one answer on the task's tier (`tasks`, so the person picks its model in Settings ▸ Models), no chat and no tools (`images`, base64 with their media type, are read with the prompt: a scanned page, a screenshot), billed to their payer and counted in their spend and allowance like a chat turn. `maxTokens` (default 1,000) goes up to `COMPLETE_MAX_TOKENS` (32,000, thinking included); the answer is streamed, so a long one keeps its connection, and `cut: true` says it stopped at the cap before it ended (the app can ask again, shorter, or continue). It throws `AssistantError` `not_connected`, `app_cap` or `own_cap` when nobody can pay, so the caller waits and tries later. It returns the answer's `usd`, `model` and `usage` (tokens in, cache reads, out, per model). `run: { id, title }` makes the calls that share an `id` one line of the person's usage history (every round of one rebuild); without it a task's calls that day share a line.
+- **Background work** an app runs for a person (a score, a summary) is `assistant.complete(caller, { task, system, prompt, images?, maxTokens })`: one answer on the task's tier (`tasks`, so the person picks its model in Settings ▸ Models), no chat and no tools (`images`, base64 with their media type, are read with the prompt: a scanned page, a screenshot), billed to their payer and counted in their spend and allowance like a chat turn. `maxTokens` (default 1,000) goes up to `COMPLETE_MAX_TOKENS` (32,000, thinking included); the answer is streamed, so a long one keeps its connection, and `cut: true` says it stopped at the cap before it ended (the app can ask again, shorter, or continue). It throws `AssistantError` `not_connected`, `app_cap` or `own_cap` when nobody can pay, so the caller waits and tries later. It returns the answer's `usd`, `model` and `usage` (tokens in, cache reads, out, per model). `effort` sets how hard the model thinks on that one call (`low` to `max`; on an OpenAI or xAI model it is the request's reasoning effort), over what the person saved for the tier. `run: { id, title }` makes the calls that share an `id` one line of the person's usage history (every round of one rebuild); without it a task's calls that day share a line.
 - **Usage history.** Each chat (`agentTurn` with `chat`) and each run of background work is one line of the person's month (`usage:YYYY-MM`, the newest 300): its title, first and last use, tokens, cost and its parts per tier and model. `GET /usage?month=YYYY-MM` returns it beside that month's spend and the months that have any; `LumenAssistant`'s footer shows this month's total and opens it (`UsageHistoryView`).
 
 ### Commands, `@` and `#`

package/dist/assistant/engine.d.ts

@@ -1,4 +1,4 @@
-import type { AllowanceRequest, AllowanceState, AllowanceUnit, AssistantAccess, AssistantChat, AssistantChatRow, AssistantMessage, AssistantOwnWay, AssistantProvider, AssistantStatus, UsagePart } from '@columenlabs/lumen-ui-types/assistant';
+import type { AllowanceRequest, AllowanceState, AllowanceUnit, AssistantAccess, AssistantChat, AssistantChatRow, AssistantEffort, AssistantMessage, AssistantOwnWay, AssistantProvider, AssistantStatus, UsagePart } from '@columenlabs/lumen-ui-types/assistant';
 import type { AgentTurnEnd, AgentTurnPlan } from '../agent/agent.js';
 import { type BearingsExtra, type BearingsNow } from './bearings.js';
 import { type ModelDef, type TaskDef, type TierDef } from './models.js';
@@ -306,6 +306,12 @@ export declare class Assistant {
         images?: CompleteImage[];
         /** The answer's token cap, thinking included (default 1,000, at most COMPLETE_MAX_TOKENS). */
         maxTokens?: number;
+        /**
+         * How hard the model thinks on this one call, whatever the person saved for the tier. On an
+         * OpenAI or xAI model it is the request's reasoning effort (`max` asks for `high`); left out,
+         * those models run at their own default.
+         */
+        effort?: AssistantEffort;
         signal?: AbortSignal;
         /**
          * The run this call belongs to, as one line of the person's usage history (`GET /usage`):

package/dist/assistant/engine.js

@@ -831,7 +831,7 @@ export class Assistant {
      * events like the chat loop, because a ChatGPT plan sign-in answers only streamed calls, takes no
      * output cap and may send its words only as deltas.
      */
-    async openaiOnce(clients, s, instructions, input, max, signal, images) {
+    async openaiOnce(clients, s, instructions, input, max, signal, images, effort) {
         // xAI's API is OpenAI's Responses API at another address.
         const xai = s.model.provider === 'xai';
         const client = (xai ? clients.xai : clients.openai);
@@ -861,6 +861,8 @@ export class Assistant {
                 store: false,
                 stream: true,
                 ...(plan ? {} : { max_output_tokens: max }),
+                ...(effort &&
+                    effort !== 'default' && { reasoning: { effort: effort === 'max' ? 'high' : effort } }),
             }, signal ? { signal } : {});
             for await (const e of stream) {
                 if (e.type === 'response.output_text.delta' && typeof e.delta === 'string')
@@ -921,7 +923,7 @@ export class Assistant {
         try {
             if ((s.model.provider === 'openai' && clients.openai) ||
                 (s.model.provider === 'xai' && clients.xai)) {
-                ({ text, cut } = await this.openaiOnce(clients, s, o.system, o.prompt, max, o.signal, o.images));
+                ({ text, cut } = await this.openaiOnce(clients, s, o.system, o.prompt, max, o.signal, o.images, o.effort));
             }
             else if (clients.anthropic) {
                 // Streamed and read whole: a long answer (minutes at a high cap) keeps its connection alive,
@@ -949,7 +951,7 @@ export class Assistant {
                                 : o.prompt,
                         },
                     ],
-                    ...effortParams(s.effort),
+                    ...effortParams(o.effort ?? s.effort),
                 }, o.signal ? { signal: o.signal } : undefined)
                     .finalMessage();
                 s.meter.add(msg.usage);

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@columenlabs/lumen-ai",
-  "version": "0.1.223",
+  "version": "0.1.224",
   "description": "Lumen's assistant and agent parts: a chat assistant's server (Claude tiers, tools over MCP, the web, hand off, spend caps), serving an MCP server from a Worker, read-only tool sets and metered tool calls.",
   "license": "MIT",
   "type": "module",
@@ -52,8 +52,8 @@
     "@ai-sdk/openai": "4.0.108",
     "@anthropic-ai/sdk": "0.133.0",
     "@cloudflare/think": "0.23.0",
-    "@columenlabs/lumen-ops": "0.1.223",
-    "@columenlabs/lumen-ui-types": "0.1.223",
+    "@columenlabs/lumen-ops": "0.1.224",
+    "@columenlabs/lumen-ui-types": "0.1.224",
     "agents": "0.32.0",
     "ai": "7.0.162",
     "just-bash": "3.6.0",