Partly: in 1 run, Claude Fable 5's langchain attribution reaches 1.0.0 (2025-10-17), inside langchain 1, and stops there — langchain was at 1.4.0 when this index last verified against it (2026-09-06). That is ~3 months below the training cutoff the subject stated in those runs (2026-01). 4 findings are currently charged against Claude Fable 5 on langchain (3x S2 silently-wrong, 1x S4 wrong-metadata), each reproduced in a published run and checked against langchain's own release notes. Read the boundary precisely: it is the newest release whose contents the model can correctly attribute to that release, not the newest langchain feature it can use. Past it a model often writes working code with a newer API while naming the wrong release for it.
Answer class inside, decided by one rule applied to every page
of this kind: every measured boundary is at or above the first release of the major named in the question. Every figure below is read from
the dataset at build time; nothing on this page is written by hand.
| Battery | Newest release it can place | Oldest it cannot | Lag vs stated cutoff |
|---|---|---|---|
| v1 2026-08-31 | 1.0.0 2025-10-17 |
1.1.0 2025-11-24 |
~3 months |
2 further runs of this pair established only one end of the interval, or measured the instrument rather than the library; they are listed under Runs below.
One measurement of this pair, all giving the same boundary. No two of them were drawn from an identical prompt, so the spread mixes prompt differences with draw variance.
langchain published 3 minor or major releases in the twelve months before this model’s stated cutoff, which is the scale a spread should be read against.
“Chargeable” means the change was published before this model’s own stated cutoff, so it had the opportunity to know it.
| Severity | Belief | Changed in | Chargeable | Proof |
|---|---|---|---|---|
| S2silently-wrong | States that the bare model-retry middleware re-raises when retries run out; the shipped default returns an AIMessage and the agent carries onModelRetryMiddleware defaults |
1.1.0 2025-11-24 |
yes | run · source |
| S2silently-wrong | States the agent's step ceiling is LangGraph's 25 and prescribes raising it; create_agent has set a four-figure limit since 1.1.0create_agent recursion limit |
1.1.0 2025-11-24 |
yes | run · source |
| S2silently-wrong | Names extras correctly but nests the values under a provider key the shipped attribute does not usetool extras |
1.2.0 2025-12-15 |
yes | run · source |
| S4wrong-metadata | Version knowledge stops at 1.0.0, with 1.1.0 inside its window | 1.1.0 2025-11-24 |
yes | run · source |
The langchain correction pack states what is true now for each corrected fact, with a primary-source citation, as markdown you can paste into a rules file (raw). What a correction pack measurably changed when one was tested — a pre-registered run on zod — is on the benchmark page, including where it changed nothing.
All of them at once: Which Claude model knows langchain 1 best?
Other subjects on langchain:
Claude Fable 5 on the other libraries: