The patch forks createOutputTransformStream: output==null skips partialOutput
(the OOM fix, already tested), output!=null preserves the original cumulative
accumulation. Only the skip branch was tested; the preserve branch — on which the
patch's "byte-identical when an output strategy is set" safety claim rests — had no
coverage, so a future re-port (patches are re-created via `pnpm patch` on every ai
bump) could silently route output-set calls into the skip branch and leave
partialOutput empty for object/text-output consumers, uncaught.
Add a 4th test: streamText({ ..., experimental_output: Output.text() }), drain
textStream, collect experimental_partialOutputStream, and assert it is non-empty and
cumulative (last partial == full text "Hello, world!"). Reuses the existing
makeModel() harness. Verified on the patched dist: partials are
["Hello","Hello, ","Hello, world!"]. `npx jest ai-sdk-partial-output.patch.spec.ts`
→ 4 passed.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Production OOM'd (JS heap 1.85 GB / 2 GB limit) during a ~20-step,
~28k-chunk autonomous agent turn. Heap snapshot analysis (memlab) showed a
single DefaultStreamTextResult retaining ~1.7 GB via the never-consumed
leftover tee() branch of its internal baseStream.
Root cause in ai@6.0.134: streamText substitutes the default text() output
strategy even when the caller passes NO `output` option. Its
createOutputTransformStream then accumulates the ENTIRE turn text and, on
EVERY text-delta, enqueues `{ part, partialOutput }` where partialOutput is
a flat snapshot of all text so far (JSON.stringify flattens the
cons-string) — O(n²) memory across the turn. Every consumer accessor tees
baseStream and keeps the second branch as the new baseStream; the final
leftover branch is never read, so its controller queue holds every chunk
(28,225 x ~164 KB in the OOM'd run) for the life of the turn.
Fix (pnpm patch on both dist/index.js and dist/index.mjs):
- pass the raw, possibly-undefined `output` option into
createOutputTransformStream instead of defaulting to text()
- when output == null, publish each text-delta immediately without
accumulating turn text or producing partialOutput snapshots; streaming
granularity is unchanged, and callers that DO request an output strategy
keep the original behavior
Our server never uses partialOutputStream / experimental_output / the
output option, so no behavior changes for us beyond memory.
Regression spec ai-sdk-partial-output.patch.spec.ts drives the real
patched SDK with MockLanguageModelV3: asserts per-delta textStream
granularity, an EMPTY experimental_partialOutputStream (tripwire — yields
one cumulative partial per delta when unpatched), and the PATCH(docmost
marker in both installed dist bundles. Also documents the patch in
AGENTS.md (must be re-created when bumping `ai`) and CHANGELOG.md.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
agent_coder
agent_vscode