diff --git a/components/artifacts/steer-card.tsx b/components/artifacts/steer-card.tsx index fab2503..003710b 100644 --- a/components/artifacts/steer-card.tsx +++ b/components/artifacts/steer-card.tsx @@ -1,6 +1,6 @@ "use client"; -import { CheckIcon } from "lucide-react"; +import { CheckIcon, CircleX } from "lucide-react"; import type { ResearchResult, SubagentArtifactData, TeacherUIMessage } from "@/src/core"; import { isSubagentFailure } from "@/src/core"; import { DemoOutputCard } from "@/components/artifacts/demo-card"; @@ -27,9 +27,15 @@ import { VisualOutputCard } from "@/components/artifacts/visual-card"; export function SubagentSteerCard({ message }: { message: TeacherUIMessage }) { const artifactPart = message.parts.find((p) => p.type === "data-subagent-artifact"); const data = artifactPart?.data as SubagentArtifactData | undefined; + // The abort steer (2026-09 dock semantics): no artifact part, only the + // metadata marker — a quiet chip, mirroring the complete-badge idiom. if (!data) { + const meta = ( + message.metadata as { subagentResult?: { aborted?: boolean; kind?: string } } | undefined + )?.subagentResult; + if (meta?.aborted) return ; return ( -
+
A sub-agent finished, but its result could not be displayed.
); @@ -48,6 +54,19 @@ export function SubagentSteerCard({ message }: { message: TeacherUIMessage }) { } } +/** The aborted-job chip: mirrors the complete-badge one-liner — the + * teacher's wake turn acknowledges the abort in the lesson itself, + * this just marks what happened. */ +function AbortedBadge({ kind }: { kind: string }) { + return ( +
+ + {kind} + aborted by the learner +
+ ); +} + /** Quiet one-liner, the dispatch-settled idiom — the lesson lives in the * teacher's wake turn; the badge just marks delivery. The persisted brief * rides along in a collapsed
(the wave-1 "view full research" diff --git a/src/agent/prompts/20-jobs.md b/src/agent/prompts/20-jobs.md index 26d47f7..e1d4026 100644 --- a/src/agent/prompts/20-jobs.md +++ b/src/agent/prompts/20-jobs.md @@ -27,3 +27,7 @@ Dispatch as many research jobs as you genuinely need — in one turn or across t parallel when the questions are independent — but don't fan out on one question; the researcher searches multiple angles on its own. If research fails, you'll get a failure message: say so plainly and continue with what you can establish, flagging the uncertainty. + +A job can also be **aborted by the learner** — you'll get a one-line "was aborted" +message instead of the result. Acknowledge it in one sentence and continue teaching +without it (offering to re-dispatch is fine if the learner wants the result). diff --git a/src/agent/subagents/aborts.ts b/src/agent/subagents/aborts.ts new file mode 100644 index 0000000..af357de --- /dev/null +++ b/src/agent/subagents/aborts.ts @@ -0,0 +1,50 @@ +/** + * Job abort registry — WHO can actually kill a running sub-agent. + * + * The runner creates one AbortController per running job and registers it + * here; the abort path (src/server/jobs.ts abortJob, driven by the dock's + * END button via POST /api/jobs/[jobId]/abort) fires it through fireJobAbort. + * Two module trees meet: the runner (src/agent) and the endpoint + * (src/server) — the registry lives on globalThis for the same reason as + * the turn registry and the wake pipeline: Next dev gives each route entry + * its own module instances, so a module-level Map would be a different + * object in each. Placed under src/agent (server→agent imports are an + * established direction; agent→server is not — see chat-handler). + * + * 2026-09 abort semantics (user-decided): REAL KILL, not mark-and-abandon — + * the controller aborts the in-flight model call (agent.generate / + * generateText abortSignal); headless tool runs are best-effort (the next + * model call is where a hung one dies). The route owns the bookkeeping + * (status error "Aborted by learner" + the abort steer); the runner only unwinds. + */ + +interface LhAbortGlobal { + __lhJobAborts?: Map; +} + +function registry(): Map { + const g = globalThis as typeof globalThis & LhAbortGlobal; + return (g.__lhJobAborts ??= new Map()); +} + +/** The runner registers its controller at job start (idempotent overwrite). */ +export function registerJobAbort(jobId: string, controller: AbortController): void { + registry().set(jobId, controller); +} + +/** The runner unregisters in its finally block (job settled or unwound). */ +export function unregisterJobAbort(jobId: string): void { + registry().delete(jobId); +} + +/** Abort a running job's loop. Returns false when no controller is live — + * the job's loop is not executing (crashed, or in the delivering-result + * phase where the runner has already returned); the caller then owns the + * whole abort on the record side. */ +export function fireJobAbort(jobId: string): boolean { + const controller = registry().get(jobId); + if (!controller) return false; + registry().delete(jobId); + controller.abort(); + return true; +} diff --git a/src/agent/subagents/demo-builder.ts b/src/agent/subagents/demo-builder.ts index 37ed194..5341eae 100644 --- a/src/agent/subagents/demo-builder.ts +++ b/src/agent/subagents/demo-builder.ts @@ -1,7 +1,7 @@ import { ToolLoopAgent, stepCountIs, tool, type LanguageModel, type ToolSet } from "ai"; import { z } from "zod"; import { modelFor } from "../models.ts"; -import type { DemoResult } from "../../core/contracts.ts"; +import type { DemoResult, UsageStepLike } from "../../core/contracts.ts"; import { getHeadless, type DemoRunResult, type HeadlessApi } from "./headless.ts"; /** @@ -32,6 +32,10 @@ export interface DemoBuilderOptions { maxSteps?: number; /** Live activity-line callback (updates the job record). */ onActivity?: (line: string) => void; + /** Kills the run mid-model-call (2026-09 real-kill abort semantics). */ + abortSignal?: AbortSignal; + /** Money channel: one call per agent step, folded into JobRecord.usage. */ + onUsage?: (usage: UsageStepLike) => void; } const INSTRUCTIONS = `You are a demo builder — a specialist sub-agent inside a learning application. You @@ -189,6 +193,8 @@ export async function runDemoBuilder(input: DemoBuilderInput, opts: DemoBuilderO try { const result = await agent.generate({ prompt, + abortSignal: opts.abortSignal, + onStepFinish: ({ usage }) => opts.onUsage?.(usage), onToolExecutionStart: ({ toolCall }) => { opts.onActivity?.(toolCall.toolName); }, diff --git a/src/agent/subagents/runner.ts b/src/agent/subagents/runner.ts index 924512c..95cc3c0 100644 --- a/src/agent/subagents/runner.ts +++ b/src/agent/subagents/runner.ts @@ -1,16 +1,21 @@ import { isToolUIPart, type LanguageModel, type UIMessage } from "ai"; import { + accumulateJobUsage, buildSubagentSteer, type DemoResult, type DemoToolInput, type JobKind, type JobRecord, + type JobUsage, type ResearchResult, type ResearchToolInput, type SubagentSteerMessage, + type UsageStepLike, type VisualResult, type VisualToolInput, } from "../../core/contracts.ts"; +import { registerJobAbort, unregisterJobAbort } from "./aborts.ts"; +import { MODELS } from "../../../config.ts"; import type { ChatStore, JobStore } from "../../core/ports.ts"; import { runDemoBuilder } from "./demo-builder.ts"; import { createResearcherAgent } from "./researcher.ts"; @@ -67,16 +72,70 @@ export interface JobRunner { runJob(jobId: string, input?: ResearchToolInput | DemoToolInput | VisualToolInput): Promise; } +/** One job loop's injected machinery: the kill switch (real abort, 2026-09 + * semantics) and the usage tap (money channel — every model call folds into + * JobRecord.usage as it completes). */ +interface LoopContext { + /** Fires when abortJob kills the run; abortSignal is passed into every + * model call so the spend stops mid-call, not at the next loop check. */ + abortSignal: AbortSignal; + /** Fold one model call's usage into the job record (progress write). */ + onUsage: (step: UsageStepLike) => void; +} + +/** The OpenRouter model id for a job kind — JobUsage.model. The kind→role + * table mirrors MODELS in config.ts (research→researcher, demo→demoBuilder, + * visual→visualMaker); the id is taken from config so a price-table sync + * re-prices jobs for free. Model overrides (tests) still bill under the + * configured model — usage is what is being captured, not which instance. */ +const KIND_MODEL: Record = { + research: MODELS.researcher.model, + demo: MODELS.demoBuilder.model, + visual: MODELS.visualMaker.model, +}; + export function createJobRunner(deps: JobRunnerDeps): JobRunner { const { chatStore, jobStore, deliver } = deps; + /** Running usage totals per live job (the loop's onUsage folds here, + * then writes through the job store so the poll sees progress). */ + const usageTotals = new Map(); + + function makeLoopContext(jobId: string, kind: JobKind): LoopContext { + const model = KIND_MODEL[kind]; + // Real-kill wiring (2026-09 abort semantics): the controller is what + // the abort endpoint fires (agent/subagents/aborts.ts registry); the + // signal rides into every model call of the loop. + const controller = new AbortController(); + registerJobAbort(jobId, controller); + return { + abortSignal: controller.signal, + onUsage: (step) => { + const next = accumulateJobUsage(usageTotals.get(jobId), model, step); + usageTotals.set(jobId, next); + jobStore.updateJob(jobId, { usage: next }); // merge patch — status untouched + }, + }; + } + + /** True while the job may still write terminal state (result, error, + * steer). False once abortJob has flipped it to error ("Aborted by learner") — + * the runner then unwinds silently; the abort path owns the record and + * the abort steer. */ + function stillRunning(jobId: string): boolean { + return jobStore.getJob(jobId)?.status === "running"; + } + /** The kind→runner map: one sub-agent loop per job kind. */ // Each kind's runner narrows the union input itself (dispatch-time inputs // are kind-correct by construction; transcript fallbacks are cast after). - const KIND_RUNNERS: Record Promise> = { - research: (jobId, input) => runResearchJob(jobId, researchModelOverride.current, input), - demo: (jobId, input) => runDemoJob(jobId, demoModelOverride.current, input), - visual: (jobId, input) => runVisualJob(jobId, visualModelOverride.current, input), + const KIND_RUNNERS: Record< + JobKind, + (jobId: string, input: JobToolInput | undefined, loop: LoopContext) => Promise + > = { + research: (jobId, input, loop) => runResearchJob(jobId, researchModelOverride.current, input, loop), + demo: (jobId, input, loop) => runDemoJob(jobId, demoModelOverride.current, input, loop), + visual: (jobId, input, loop) => runVisualJob(jobId, visualModelOverride.current, input, loop), }; async function runJob(jobId: string, input?: JobToolInput): Promise { @@ -92,7 +151,17 @@ export function createJobRunner(deps: JobRunnerDeps): JobRunner { jobStore.updateJob(jobId, { status: "error", error: `unknown kind ${job.kind}`, activity: "failed" }); return; } - await run(jobId, input); + try { + await run(jobId, input, makeLoopContext(jobId, job.kind)); + } finally { + unregisterJobAbort(jobId); + // The last usage write may have been mid-flight when the loop died; + // persist what was folded (the abort path patches only status, so + // this never resurrects an aborted job — merge patch). + const usage = usageTotals.get(jobId); + if (usage) jobStore.updateJob(jobId, { usage }); + usageTotals.delete(jobId); + } } /** Resolve the job's tool input: dispatch passes it directly; only a @@ -132,6 +201,10 @@ export function createJobRunner(deps: JobRunnerDeps): JobRunner { async function finishJob(jobId: string, result: ResearchResult | DemoResult | VisualResult): Promise { const job = jobStore.getJob(jobId); if (!job) return; + // Aborted mid-run or mid-delivery (abortJob flips the record before + // the loop unwinds): no result write, no steer — the abort path owns + // the record and queues the abort steer itself. + if (job.status !== "running") return; jobStore.updateJob(jobId, { result, activity: "delivering result" }); const steer = buildSubagentSteer(job, result); try { @@ -157,7 +230,12 @@ export function createJobRunner(deps: JobRunnerDeps): JobRunner { // ─── research ─────────────────────────────────────────────────────────── - async function runResearchJob(jobId: string, model?: LanguageModel, passedInput?: JobToolInput): Promise { + async function runResearchJob( + jobId: string, + model: LanguageModel | undefined, + passedInput: JobToolInput | undefined, + loop: LoopContext, + ): Promise { const ctx = jobContext(jobId); if (!ctx) return; const { job } = ctx; @@ -181,6 +259,10 @@ export function createJobRunner(deps: JobRunnerDeps): JobRunner { jobStore.updateJob(jobId, { activity: "researching" }); const result = await agent.generate({ prompt, + abortSignal: loop.abortSignal, + // Money channel: each agent step is one model call — fold its + // usage into the record as it completes (progress write). + onStepFinish: ({ usage }) => loop.onUsage(usage), onToolExecutionStart: ({ toolCall }) => { const input = toolCall.input as { query?: string; url?: string } | undefined; if (toolCall.toolName === "web_fetch" && typeof input?.url === "string") { @@ -195,15 +277,24 @@ export function createJobRunner(deps: JobRunnerDeps): JobRunner { const research: ResearchResult = { brief, sources: parseSources(brief, fetchedUrls) }; await finishJob(jobId, research); } catch (err) { + // Real-kill abort (2026-09): the abort path flipped the record and + // queued the abort steer — unwind silently, keep the usage + // folded so far (flushed by runJob's finally). + if (loop.abortSignal.aborted) return; const reason = err instanceof Error ? err.message : String(err); - jobStore.updateJob(jobId, { error: reason }); + if (stillRunning(jobId)) jobStore.updateJob(jobId, { error: reason }); await finishJob(jobId, { brief: `Research failed: ${reason}`, sources: [] }); } } // ─── demo + visual ────────────────────────────────────────────────────── - async function runDemoJob(jobId: string, model?: LanguageModel, passedInput?: JobToolInput): Promise { + async function runDemoJob( + jobId: string, + model: LanguageModel | undefined, + passedInput: JobToolInput | undefined, + loop: LoopContext, + ): Promise { const ctx = jobContext(jobId); if (!ctx) return; const { job } = ctx; @@ -218,19 +309,28 @@ export function createJobRunner(deps: JobRunnerDeps): JobRunner { { title, brief }, { model, + abortSignal: loop.abortSignal, + onUsage: loop.onUsage, onActivity: (line) => jobStore.updateJob(jobId, { activity: line }), }, ); - if (isDemoFailure(result)) jobStore.updateJob(jobId, { error: result.notes ?? "demo build failed" }); + if (isDemoFailure(result) && stillRunning(jobId)) + jobStore.updateJob(jobId, { error: result.notes ?? "demo build failed" }); await finishJob(jobId, result); } catch (err) { + if (loop.abortSignal.aborted) return; const reason = err instanceof Error ? err.message : String(err); - jobStore.updateJob(jobId, { error: reason }); + if (stillRunning(jobId)) jobStore.updateJob(jobId, { error: reason }); await finishJob(jobId, { title, html: "", tested: true, notes: `FAILED: ${reason}` }); } } - async function runVisualJob(jobId: string, model?: LanguageModel, passedInput?: JobToolInput): Promise { + async function runVisualJob( + jobId: string, + model: LanguageModel | undefined, + passedInput: JobToolInput | undefined, + loop: LoopContext, + ): Promise { const ctx = jobContext(jobId); if (!ctx) return; const { job } = ctx; @@ -244,14 +344,18 @@ export function createJobRunner(deps: JobRunnerDeps): JobRunner { { brief }, { model, + abortSignal: loop.abortSignal, + onUsage: loop.onUsage, onActivity: (line) => jobStore.updateJob(jobId, { activity: line }), }, ); - if (isVisualFailure(result)) jobStore.updateJob(jobId, { error: result.notes ?? "visual build failed" }); + if (isVisualFailure(result) && stillRunning(jobId)) + jobStore.updateJob(jobId, { error: result.notes ?? "visual build failed" }); await finishJob(jobId, result); } catch (err) { + if (loop.abortSignal.aborted) return; const reason = err instanceof Error ? err.message : String(err); - jobStore.updateJob(jobId, { error: reason }); + if (stillRunning(jobId)) jobStore.updateJob(jobId, { error: reason }); await finishJob(jobId, { svg: "", notes: `FAILED: ${reason}` }); } } diff --git a/src/agent/subagents/visual-maker.ts b/src/agent/subagents/visual-maker.ts index df0a798..7349093 100644 --- a/src/agent/subagents/visual-maker.ts +++ b/src/agent/subagents/visual-maker.ts @@ -1,7 +1,7 @@ import { generateText, tool, type LanguageModel, type ModelMessage, type ToolResultPart } from "ai"; import { z } from "zod"; import { modelFor } from "../models.ts"; -import type { VisualResult } from "../../core/contracts.ts"; +import type { UsageStepLike, VisualResult } from "../../core/contracts.ts"; import { getHeadless, type HeadlessApi } from "./headless.ts"; /** @@ -37,6 +37,11 @@ export interface VisualMakerOptions { maxIterations?: number; /** Live activity-line callback (updates the job record). */ onActivity?: (line: string) => void; + /** Kills the run mid-model-call (2026-09 real-kill abort semantics). */ + abortSignal?: AbortSignal; + /** Money channel: one call per loop iteration (generateText), folded + * into JobRecord.usage. */ + onUsage?: (usage: UsageStepLike) => void; } const INSTRUCTIONS = `You are a visual maker — a diagram author + renderer for precise, spatial figures. You @@ -135,7 +140,15 @@ export async function runVisualMaker(input: VisualMakerInput, opts: VisualMakerO try { for (let iteration = 0; iteration < maxIterations; iteration++) { - const result = await generateText({ model: opts.model ?? modelFor("visualMaker"), system: INSTRUCTIONS, messages, tools }); + const result = await generateText({ + model: opts.model ?? modelFor("visualMaker"), + system: INSTRUCTIONS, + messages, + tools, + abortSignal: opts.abortSignal, + }); + // Money channel: each iteration is one model call. + opts.onUsage?.(result.usage); messages = [...messages, ...result.response.messages]; const toolCalls = result.toolCalls; diff --git a/src/core/contracts/jobs.ts b/src/core/contracts/jobs.ts index d2f4448..8774652 100644 --- a/src/core/contracts/jobs.ts +++ b/src/core/contracts/jobs.ts @@ -7,6 +7,7 @@ * of "ai" (safe everywhere: server, client, tests). See docs/vision.md. */ import type { UIMessage } from "ai"; +import type { CallUsage } from "./chat.ts"; // ─── Async sub-agent jobs (vision §2.5; plan.md Wave 0 protocol) ──────────── @@ -36,18 +37,64 @@ export interface JobRecord { /** A sub-agent run's accumulated usage — the same accounting shape as a * chat turn (contracts/chat.ts CallUsage), flattened to one running total - * plus a step count. */ + * plus a step count. Token fields are optional exactly like CallUsage: a + * field NO model call reported stays undefined — absent is not zero (the + * money-channel doctrine; cost renders "—", never $0). */ export interface JobUsage { /** The OpenRouter model id that ran the sub-agent. */ model: string; /** Running totals summed over the run's model calls so far. */ - inputTokens: number; - outputTokens: number; - cacheReadTokens: number; - cacheWriteTokens: number; - reasoningTokens: number; + inputTokens: number | undefined; + outputTokens: number | undefined; + cacheReadTokens: number | undefined; + cacheWriteTokens: number | undefined; + reasoningTokens: number | undefined; /** How many model calls the run has made (each bills separately). */ steps: number; + /** The MOST RECENT model call's accounting (2026-09 dock contract): the + * per-blob context line reads last-step input+output against the model's + * CONTEXT_LIMITS — never the cumulative totals. Absent until the first + * call completes; absent provider fields stay absent (never zero). */ + lastStep?: CallUsage; +} + +/** The per-model-call usage shape we fold into JobUsage — the SDK's + * LanguageModelUsage narrowed structurally (no runtime "ai" import: any + * object with these fields folds, including the real thing and test fakes). */ +export interface UsageStepLike { + inputTokens?: number | undefined; + inputTokenDetails?: { cacheReadTokens?: number; cacheWriteTokens?: number } | undefined; + outputTokens?: number | undefined; + outputTokenDetails?: { reasoningTokens?: number } | undefined; +} + +/** Fold one model call's usage into the run's running total (pure). A + * field neither the total nor the step reported stays undefined; once + * reported, later unreported calls contribute 0. The `steps` counter is + * the billing count: one per model call, reported or not. */ +export function accumulateJobUsage( + total: JobUsage | undefined, + model: string, + step: UsageStepLike, +): JobUsage { + const add = (a: number | undefined, b: number | undefined): number | undefined => + a === undefined && b === undefined ? undefined : (a ?? 0) + (b ?? 0); + return { + model, + inputTokens: add(total?.inputTokens, step.inputTokens), + outputTokens: add(total?.outputTokens, step.outputTokens), + cacheReadTokens: add(total?.cacheReadTokens, step.inputTokenDetails?.cacheReadTokens), + cacheWriteTokens: add(total?.cacheWriteTokens, step.inputTokenDetails?.cacheWriteTokens), + reasoningTokens: add(total?.reasoningTokens, step.outputTokenDetails?.reasoningTokens), + steps: (total?.steps ?? 0) + 1, + lastStep: { + inputTokens: step.inputTokens, + outputTokens: step.outputTokens, + cacheReadTokens: step.inputTokenDetails?.cacheReadTokens, + cacheWriteTokens: step.inputTokenDetails?.cacheWriteTokens, + reasoningTokens: step.outputTokenDetails?.reasoningTokens, + }, + }; } /** @@ -155,6 +202,11 @@ export interface SubagentResultMeta { jobId: string; kind: JobKind; toolCallId: string; + /** Present only on an abort steer (2026-09 abort semantics): the + * learner aborted the job (it lands as error "Aborted by learner"); + * the teacher is told so its promise of a result doesn't hang + * silently in the lesson. */ + aborted?: true; } /** The data-subagent-artifact part payload: what the UI renders. */ @@ -178,6 +230,20 @@ export interface SubagentSteerMessage extends UIMessage { ]; } +/** The abort steer: user-role like any steer, but NO artifact part — + * there is no result to render, only the teacher-facing text. Shares the + * result steer's deterministic id space (`steer_${jobId}`): steerDelivered + * matches on metadata jobId, so an abort and a (racing) result steer + * can never BOTH deliver — exactly one wakes the teacher. */ +export interface AbortSteerMessage extends UIMessage { + role: "user"; + metadata: { subagentResult: SubagentResultMeta & { aborted: true } }; + parts: [{ type: "text"; text: string }]; +} + +/** Anything the wake pipeline may queue and deliver. */ +export type SteerMessage = SubagentSteerMessage | AbortSteerMessage; + /** Whether a result is the failure shape (html/svg empty, failure brief). */ export function isSubagentFailure(kind: JobKind, result: ResearchResult | DemoResult | VisualResult): boolean { if (kind === "research") { @@ -234,6 +300,32 @@ export function buildSubagentSteer( }; } +/** Build the abort steer for an aborted job (pure — shared by the + * abort path in src/server/jobs.ts and tests). Same id space as the result + * steer; see AbortSteerMessage. */ +export function buildAbortSteer( + job: Pick, +): AbortSteerMessage { + return { + id: `steer_${job.id}`, + role: "user", + metadata: { + subagentResult: { jobId: job.id, kind: job.kind, toolCallId: job.toolCallId, aborted: true }, + }, + parts: [{ type: "text", text: abortText(job.kind) }], + }; +} + +/** What the teacher reads: one line telling it the result is not coming, + * how to acknowledge, and that re-dispatching is allowed. */ +function abortText(kind: JobKind): string { + if (kind === "research") + return "Research aborted — the learner aborted the research job, so no brief is coming. Acknowledge it in one line and continue teaching without it (or offer to re-dispatch it)."; + if (kind === "demo") + return "The demo job was aborted by the learner — no demo is coming. Acknowledge it in one line and teach the topic in prose instead (a re-dispatch is fine if the learner wants it)."; + return "The figure job was aborted by the learner — no figure is coming. Acknowledge it in one line and teach without it (a re-dispatch is fine if the learner wants it)."; +} + /** True when the transcript already carries this job's steer (idempotent delivery). */ export function steerDelivered(messages: UIMessage[], jobId: string): boolean { return messages.some( diff --git a/src/server/jobs.ts b/src/server/jobs.ts index 780d6c5..f3a1778 100644 --- a/src/server/jobs.ts +++ b/src/server/jobs.ts @@ -33,13 +33,15 @@ import type { UIMessage } from "ai"; import { + buildAbortSteer, buildSubagentSteer, isSubagentFailure, steerDelivered, type JobRecord, - type SubagentSteerMessage, + type SteerMessage, } from "../core/contracts.ts"; import { findPendingToolCall } from "../core/pending.ts"; +import { fireJobAbort } from "../agent/subagents/aborts.ts"; import { stores } from "./stores.ts"; import { isTurnRunning } from "./turn-liveness.ts"; @@ -50,7 +52,7 @@ export type TurnRunner = (chatId: string, messages: UIMessage[]) => Promise void; interface QueuedSteer { - steer: SubagentSteerMessage; + steer: SteerMessage; resolve: () => void; reject: (reason: Error) => void; } @@ -108,7 +110,7 @@ function delay(ms: number): Promise { return new Promise((resolve) => setTimeout(resolve, ms)); } -function jobIdOf(steer: SubagentSteerMessage): string { +function jobIdOf(steer: SteerMessage): string { return (steer.metadata as { subagentResult: { jobId: string } }).subagentResult.jobId; } @@ -117,7 +119,7 @@ function jobIdOf(steer: SubagentSteerMessage): string { * has completed (and the job status flipped); rejects when delivery fails * unrecoverably. Never rejects for queueing itself. */ -export function deliverJobResult(steer: SubagentSteerMessage): Promise { +export function deliverJobResult(steer: SteerMessage): Promise { return new Promise((resolve, reject) => { const s = state(); const chatId = chatIdOf(steer); @@ -145,13 +147,13 @@ export function deliverJobResult(steer: SubagentSteerMessage): Promise { * before firing, so a claim racing the pump converges to exactly one * delivery either way. */ -export function claimSteers(chatId: string): SubagentSteerMessage[] { +export function claimSteers(chatId: string): SteerMessage[] { const s = state(); const queue = s.queues.get(chatId); if (!queue || queue.length === 0) return []; const record = stores.chatStore.getChat(chatId); if (!record) return []; // the handler validated the chat; defensive only - const claimed: SubagentSteerMessage[] = []; + const claimed: SteerMessage[] = []; for (const entry of queue) { const jobId = jobIdOf(entry.steer); if (steerDelivered(record.messages, jobId)) { @@ -167,7 +169,66 @@ export function claimSteers(chatId: string): SubagentSteerMessage[] { return claimed; } -function chatIdOf(steer: SubagentSteerMessage): string { +/** Result of an abort attempt — the endpoint maps these to HTTP. */ +export interface AbortOutcome { + ok: boolean; + reason?: "not_found" | "not_running"; +} + +/** + * ABORT (2026-09 dock semantics, user-decided): real kill, error with + * reason, the teacher still learns. The dock's END button reaches this + * through POST /api/activity/abort (body {kind: "job", id: jobId}); the + * route is master's thin composition — this is the job-side mechanism. + * Four things happen, in order: + * + * 1. KILL the spend: fire the job's registered AbortController (the + * runner registered it at loop start) — the in-flight model call + * aborts, not just the next loop check. The runner unwinds silently + * (its catch checks abortSignal.aborted; finishJob checks status). + * 2. DROP any queued result steer for this job (the delivering-result + * phase): resolve its entry without firing the wake. If the wake + * turn is ALREADY in flight (the pump shifted the entry), it's too + * late — the result steer lands, and the cancellation steer dedupes + * against it via steerDelivered (same jobId metadata). + * 3. FLIP the record to error "Aborted by learner" immediately — the + * poll reflects the user's action at once (the user chose + * error-with-reason over a distinct cancelled status). finalizeJob + * never overwrites a non-running status, so the flip is terminal no + * matter what the wake does. + * 4. STEER the teacher: a one-line abort note (buildAbortSteer) through + * the same wake pipeline, so the teacher's promise of a result + * doesn't hang silently in the lesson. + * + * The runner writes the usage folded so far in its finally (merge patch), + * so an aborted job's money record survives the kill. + */ +export function abortJob(jobId: string): AbortOutcome { + const job = stores.jobStore.getJob(jobId); + if (!job) return { ok: false, reason: "not_found" }; + if (job.status !== "running") return { ok: false, reason: "not_running" }; + + fireJobAbort(jobId); // no-op when the loop already returned (delivering) + + // Drop any queued steers for this job (their deliver() resolves unfired). + const queue = state().queues.get(job.chatId); + if (queue) { + const remaining = queue.filter((e) => jobIdOf(e.steer) !== jobId); + if (remaining.length === 0) state().queues.delete(job.chatId); + else state().queues.set(job.chatId, remaining); + for (const entry of queue) { + if (jobIdOf(entry.steer) === jobId) entry.resolve(); + } + } + + stores.jobStore.updateJob(jobId, { status: "error", error: "Aborted by learner", activity: "aborted" }); + void deliverJobResult(buildAbortSteer(job)).catch(() => { + /* deliverJobResult marks the job error on unrecoverable failure */ + }); + return { ok: true }; +} + +function chatIdOf(steer: SteerMessage): string { // The chat is resolvable from the job record; the steer's metadata // carries jobId, which indexes the store. const jobId = jobIdOf(steer); @@ -285,6 +346,11 @@ function finalizeJob(jobId: string): void { } function failJob(jobId: string, err: Error): void { + // An aborted job stays aborted even when its (abort) steer + // delivery fails — the user's action is the terminal fact, not the + // delivery error. Non-running records are never overwritten here. + const job = stores.jobStore.getJob(jobId); + if (!job || job.status !== "running") return; stores.jobStore.updateJob(jobId, { status: "error", error: err.message, activity: "delivery failed" }); } diff --git a/tests/demos.test.tsx b/tests/demos.test.tsx index 84c151b..69c3ad8 100644 --- a/tests/demos.test.tsx +++ b/tests/demos.test.tsx @@ -49,7 +49,7 @@ import { runDemoBuilder } from "../src/agent/subagents/demo-builder.ts"; import { headlessOverride, type DemoRunResult, type HeadlessApi } from "../src/agent/subagents/headless.ts"; import { createJobRunner, demoModelOverride, visualModelOverride } from "../src/agent/subagents/runner.ts"; import { runVisualMaker } from "../src/agent/subagents/visual-maker.ts"; -import { buildSubagentSteer, isSubagentFailure, type SubagentSteerMessage } from "../src/core/contracts.ts"; +import { buildAbortSteer, buildSubagentSteer, isSubagentFailure, type SubagentSteerMessage } from "../src/core/contracts.ts"; import type { JobRecord } from "../src/core/contracts.ts"; import { createTeacherTools } from "../src/agent/tools.ts"; import { chatStore } from "../src/store/chats.ts"; @@ -342,6 +342,18 @@ describe("steer card rendering (the delivered artifact)", () => { assert.ok(!html.includes("Looking at the render"), "model-facing notes never render"); }); + it("renders the abort chip for an aborted job's steer (2026-09 dock semantics)", () => { + const steer = buildAbortSteer({ id: "jc", kind: "research", toolCallId: "cc" }); + assert.equal(steer.metadata.subagentResult.aborted, true); + assert.equal(steer.parts.length, 1, "no artifact part on an abort"); + const html = renderToStaticMarkup(); + assert.match(html, /job-aborted-badge/); + assert.match(html, /research/, "the job's kind, lower-cased like the complete-badge idiom"); + assert.match(html, /aborted by the learner/); + // the teacher-facing protocol text never renders for the learner + assert.ok(!html.includes("no brief is coming"), "no protocol glue in the chip"); + }); + it("renders a quiet Research-complete one-liner whose collapsed
carries the full brief", () => { const steer = buildSubagentSteer( { id: "jr", kind: "research", toolCallId: "cr" }, diff --git a/tests/jobs.test.ts b/tests/jobs.test.ts index 49590da..66ec4e8 100644 --- a/tests/jobs.test.ts +++ b/tests/jobs.test.ts @@ -31,18 +31,23 @@ import type { UIMessage } from "ai"; import { MockLanguageModelV4, simulateReadableStream } from "ai/test"; import type { LanguageModelV4StreamPart } from "@ai-sdk/provider"; import { + accumulateJobUsage, + buildAbortSteer, buildSubagentSteer, isSubagentFailure, steerDelivered, type DemoResult, + type JobUsage, type ResearchResult, + type SteerMessage, type SubagentSteerMessage, type VisualResult, } from "../src/core/contracts.ts"; import { composeInstructions, createTeacherAgent } from "../src/agent/teacher-agent.ts"; import { createTeacherTools } from "../src/agent/tools.ts"; import { handleChatRequest } from "../src/server/chat-handler.ts"; -import { claimSteers, deliverJobResult, setTurnRunner } from "../src/server/jobs.ts"; +import { abortJob, claimSteers, deliverJobResult, setTurnRunner } from "../src/server/jobs.ts"; +import { beginTurn, endTurn } from "../src/server/turn-liveness.ts"; import { persistTurn, withMessageIds } from "../src/server/turn-service.ts"; import { chatStore } from "../src/store/chats.ts"; import { jobStore } from "../src/store/jobs.ts"; @@ -170,6 +175,57 @@ describe("steer helpers (contracts.ts)", () => { assert.deepEqual(data.data.result, research); }); + it("accumulateJobUsage: sums per model call; fields NO call reported stay undefined (absent is not zero)", () => { + let total: JobUsage | undefined = undefined; + total = accumulateJobUsage(total, "z-ai/glm-5.3-flash", { + inputTokens: 10, + outputTokens: 5, + inputTokenDetails: { cacheReadTokens: 4 }, + }); + assert.deepEqual(total, { + model: "z-ai/glm-5.3-flash", + inputTokens: 10, + outputTokens: 5, + cacheReadTokens: 4, + cacheWriteTokens: undefined, + reasoningTokens: undefined, + steps: 1, + lastStep: { + inputTokens: 10, + outputTokens: 5, + cacheReadTokens: 4, + cacheWriteTokens: undefined, + reasoningTokens: undefined, + }, + }, "lastStep is the most recent call's accounting, not cumulative"); + // a later call that reports nothing new keeps reported fields summing + // (unreported contributes 0) and bumps the billing step count. + total = accumulateJobUsage(total, "z-ai/glm-5.3-flash", { inputTokens: 20, outputTokens: 0 }); + assert.equal(total.inputTokens, 30); + assert.equal(total.outputTokens, 5); + assert.equal(total.cacheReadTokens, 4, "unreported after reported contributes 0"); + assert.equal(total.cacheWriteTokens, undefined, "never reported stays absent — never zero"); + assert.equal(total.reasoningTokens, undefined); + assert.equal(total.steps, 2, "one step per model call, reported or not"); + assert.deepEqual(total.lastStep, { + inputTokens: 20, + outputTokens: 0, + cacheReadTokens: undefined, + cacheWriteTokens: undefined, + reasoningTokens: undefined, + }, "lastStep always mirrors the LATEST call, never the sums"); + }); + + it("buildAbortSteer: metadata-aborted, text-only (no artifact), same deterministic id space as the result steer", () => { + const steer = buildAbortSteer({ id: "job_c", kind: "demo", toolCallId: "call-c" }); + assert.equal(steer.id, "steer_job_c", "same id space — steerDelivered treats either as delivered"); + assert.equal(steer.role, "user"); + assert.equal(steer.metadata.subagentResult.aborted, true); + assert.equal(steer.metadata.subagentResult.jobId, "job_c"); + assert.equal(steer.parts.length, 1); + assert.ok(steer.parts[0]!.type === "text" && /aborted/.test(steer.parts[0].text)); + }); + it("isSubagentFailure: failure shapes only (empty html/svg, failure brief)", () => { assert.equal(isSubagentFailure("research", research), false); assert.equal(isSubagentFailure("research", { brief: "Research failed: x", sources: [] }), true); @@ -836,3 +892,192 @@ describe("prompt composition", () => { assert.ok(composeInstructions().length <= 60_000, "composed system prompt over the 60k guard"); }); }); + +// ─── abort (2026-09 semantics: real kill, cancelled status, teacher told) ─── + +describe("abort (src/server/jobs.ts abortJob)", () => { + /** A hanging model that only settles when its abort signal fires — the + * real-kill path: the in-flight call itself is killed. */ + function hangingModel(): MockLanguageModelV4 { + return new MockLanguageModelV4({ + doGenerate: ({ abortSignal }) => + new Promise((_resolve, reject) => { + // an ALREADY-aborted signal never fires the event — real + // providers reject an aborted fetch at once, the mock must too + if (abortSignal?.aborted) { + reject(new DOMException("The operation was aborted", "AbortError")); + return; + } + abortSignal?.addEventListener("abort", () => { + reject(new DOMException("The operation was aborted", "AbortError")); + }); + }), + }); + } + + /** One step (with usage) then a hang — proves usage-so-far survives the kill. */ + function oneStepThenHangModel(): MockLanguageModelV4 { + let turn = 0; + return new MockLanguageModelV4({ + doGenerate: ({ abortSignal }) => { + turn++; + if (turn === 1) { + return Promise.resolve({ + content: [ + { + type: "tool-call" as const, + toolCallId: "ws1", + toolName: "web_search", + input: JSON.stringify({ query: "anything" }), + }, + ], + finishReason: { unified: "tool-calls" as const, raw: "tool-calls" }, + usage: usage(), + warnings: [], + }); + } + return new Promise((_resolve, reject) => { + if (abortSignal?.aborted) { + reject(new DOMException("The operation was aborted", "AbortError")); + return; + } + abortSignal?.addEventListener("abort", () => { + reject(new DOMException("The operation was aborted", "AbortError")); + }); + }); + }, + }); + } + + function newChatWithResearchJob(label: string, toolCallId: string): { chatId: string; jobId: string } { + const chat = chatStore.createChat(`Test: ${label}`); + trackChat(chat.id); + chatStore.saveMessages(chat.id, [ + { id: "u1", role: "user", parts: [{ type: "text", text: "hi" }] }, + { + id: "a1", + role: "assistant", + parts: [ + { type: "text", text: "Checking." }, + { type: "tool-research", toolCallId, state: "output-available", input: RESEARCH_INPUT, output: "Dispatched." }, + ], + }, + ] as never); + const job = jobStore.createJob({ kind: "research", chatId: chat.id, toolCallId }); + trackJob(job.id); + return { chatId: chat.id, jobId: job.id }; + } + + it("kills the running loop: error \"Aborted by learner\" immediately, loop unwinds silently, teacher gets the abort steer", async () => { + const { jobId } = newChatWithResearchJob("abort running job", "call-abort1"); + const fired: SteerMessage[] = []; + setTurnRunner(async (_cid, messages) => { + fired.push(messages[messages.length - 1] as SteerMessage); + return 200; + }); + researchModelOverride.current = hangingModel(); + const runner = createJobRunner({ + chatStore, + jobStore, + deliver: async () => { + throw new Error("a cancelled job must never deliver a result steer"); + }, + }); + try { + const settled = runner.runJob(jobId, RESEARCH_INPUT); + await waitFor(() => jobStore.getJob(jobId)!.activity === "researching", 8000, "loop started"); + + const outcome = abortJob(jobId); + assert.ok(outcome.ok); + const killed = jobStore.getJob(jobId)!; + assert.equal(killed.status, "error", "flipped synchronously — the poll sees it at once"); + assert.equal(killed.error, "Aborted by learner", "abort reads as an error with a reason, not a failure"); + assert.equal(killed.activity, "aborted"); + + await settled; // unwinds — no hang + assert.equal(jobStore.getJob(jobId)!.status, "error", "the runner never overwrites the flip"); + assert.equal(jobStore.getJob(jobId)!.error, "Aborted by learner"); + assert.equal(jobStore.getJob(jobId)!.result, undefined, "no result on an aborted job"); + + await waitFor(() => fired.length > 0, 8000, "abort wake fired"); + const last = fired[0]!; + assert.equal(last.metadata.subagentResult.aborted, true); + assert.equal(last.id, `steer_${jobId}`); + assert.equal(last.parts.length, 1, "text only — no artifact part"); + // aborted is terminal: the wake completing must not flip it + assert.equal(jobStore.getJob(jobId)!.status, "error", "terminal after the wake"); + } finally { + researchModelOverride.current = undefined; + } + }); + + it("the usage folded so far survives the kill (money channel outlives the abort)", async () => { + const restoreFetch = stubFetch(); + try { + const { jobId } = newChatWithResearchJob("abort keeps usage", "call-abort2"); + setTurnRunner(async () => 200); + researchModelOverride.current = oneStepThenHangModel(); + const runner = createJobRunner({ chatStore, jobStore, deliver: async () => {} }); + try { + const settled = runner.runJob(jobId, RESEARCH_INPUT); + await waitFor(() => (jobStore.getJob(jobId)!.usage?.steps ?? 0) === 1, 8000, "first step folded"); + abortJob(jobId); + await settled; + const job = jobStore.getJob(jobId)!; + assert.equal(job.status, "error"); + assert.equal(job.error, "Aborted by learner"); + assert.equal(job.usage!.steps, 1, "usage-so-far persisted by the runner's finally"); + assert.equal(job.usage!.model, "z-ai/glm-5.3-flash", "the config role's OpenRouter id"); + assert.equal(job.usage!.inputTokens, 10); + assert.equal(job.usage!.outputTokens, 5); + } finally { + researchModelOverride.current = undefined; + } + } finally { + restoreFetch(); + } + }); + + it("aborting a delivering job drops the queued result steer and wakes with the abort note instead", async () => { + const chat = chatStore.createChat("Test: abort delivering job"); + trackChat(chat.id); + chatStore.saveMessages(chat.id, [{ id: "u1", role: "user", parts: [{ type: "text", text: "hello" }] }] as never); + const job = jobStore.createJob({ kind: "research", chatId: chat.id, toolCallId: "call-abort3" }); + trackJob(job.id); + const result: ResearchResult = { brief: "Done: it works.", sources: [{ title: "s", url: "https://x.test" }] }; + jobStore.updateJob(job.id, { result, activity: "delivering result" }); + + // Block the pump's idle gates so the result steer sits QUEUED, not in flight. + assert.ok(beginTurn(chat.id)); + const fired: SteerMessage[] = []; + setTurnRunner(async (_cid, messages) => { + fired.push(messages[messages.length - 1] as SteerMessage); + return 200; + }); + void deliverJobResult(buildSubagentSteer(job, result)).catch(() => { + /* dropped by the abort below */ + }); + await waitFor(() => jobStore.getJob(job.id)!.activity === "delivering result", 8000, "queued"); + + const outcome = abortJob(job.id); + assert.ok(outcome.ok); + assert.equal(jobStore.getJob(job.id)!.status, "error"); + assert.equal(jobStore.getJob(job.id)!.error, "Aborted by learner"); + + endTurn(chat.id); // gates open — whatever is left in the queue fires + await waitFor(() => fired.length > 0, 8000, "wake fired"); + assert.equal(fired.length, 1, "exactly one delivery — the result steer was dropped"); + assert.equal(fired[0]!.metadata.subagentResult.aborted, true, "the abort steer, not the result"); + assert.equal(jobStore.getJob(job.id)!.status, "error", "terminal after the wake"); + }); + + it("outcome reasons: not_found for unknown, not_running for settled jobs", () => { + assert.deepEqual(abortJob("job_does_not_exist"), { ok: false, reason: "not_found" }); + const chat = chatStore.createChat("Test: abort settled job"); + trackChat(chat.id); + const job = jobStore.createJob({ kind: "research", chatId: chat.id, toolCallId: "call-abort4" }); + trackJob(job.id); + jobStore.updateJob(job.id, { status: "done", activity: "delivered" }); + assert.deepEqual(abortJob(job.id), { ok: false, reason: "not_running" }); + }); +});