Not by version attribution: in 2 runs, Claude Fable 5 places its prisma boundary at 6.7.0 (2025-04-29) — below prisma 7.0.0 (2025-11-19), the first release of prisma 7. That is ~8 months below the training cutoff the subject stated in those runs (2026-01). 12 findings are currently charged against Claude Fable 5 on prisma (7x S1 breaks-build, 2x S2 silently-wrong, 1x S3 deprecated, 2x S4 wrong-metadata), each reproduced in a published run and checked against prisma'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 prisma 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 below, decided by one rule applied to every page
of this kind: every measured boundary is below 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.
2 measurements 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.
prisma published 21 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 |
|---|---|---|---|---|
| S1breaks-build | Constructs the client with no arguments in every runnable artefactnew PrismaClient() |
7.0.0 2025-11-19 |
yes | run · source |
| S1breaks-build | Generator block with no output pathgenerator client { output } |
7.0.0 2025-11-19 |
yes | run · source |
| S1breaks-build | Imports PrismaClient from @prisma/clientimport { PrismaClient } from '@prisma/client' |
7.0.0 2025-11-19 |
yes | run · source |
| S1breaks-build | No config file in the project it sets up; the datasource URL stays in the schemaprisma.config.ts |
7.0.0 2025-11-19 |
yes | run · source |
| S1breaks-build | Seed command in package.json, with the implicit-run promisepackage.json prisma key |
7.0.0 2025-11-19 |
yes | run · source |
| S1breaks-build | Recommends prisma generate --no-engineprisma generate --no-engine |
7.0.0 2025-11-19 |
yes | run · source |
| S1breaks-build | migrate diff with the removed --from-url / --to-schema-datamodel flagsprisma migrate diff |
7.0.0 2025-11-19 |
yes | run · source |
| S2silently-wrong | States the CLI loads .env itself — then contradicts it in the belief probeautomatic .env loading |
7.0.0 2025-11-19 |
yes | run · source |
| S2silently-wrong | Deployment advice organised around matching engine binaries to the container's libcengineType |
7.0.0 2025-11-19 |
yes | run · source |
| S3deprecated | Uses the superseded generator provider in every schemaprovider = "prisma-client-js" |
7.0.0 2025-11-19 |
yes | run · source |
| S4wrong-metadata | Knowledge stops at 6.7.0 — eight months before its own stated cutoff, and six months earlier than the same model's boundary on four other libraries | 6.8.0 2025-05-15 |
yes | run · source |
| S4wrong-metadata | Sets a MongoDB team up on the current major, which dropped MongoDBMongoDB support |
7.0.0 2025-11-19 |
yes | run · source |
The prisma 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 prisma 7 best?
Other subjects on prisma:
Claude Fable 5 on the other libraries: