Attach an API spec to a Jira workflow validator: what the CogniRunner AI rule never reads
Attach an API spec to a Jira workflow validator: what the CogniRunner AI rule never reads Key takeaways END STATE: a validator that reads your own schema before deciding, with the verdict provably different because of it, and a measured figure for what never reached the model. The prompt ceiling is a hard substring(0, 30000) — it cuts mid-string, not on a document boundary. A 40KB schema arrives…
Attach a JSON schema, an API spec, or a field-mapping table to a Jira workflow validator using CogniRunner AI. Confirm the verdict changes by running the same input with and without the added document. The validator should read the attached schema before deciding, with the verdict different. The prompt ceiling is a hard substring(0, 30000) - it cuts mid-string, not on a document boundary.
After adding the document to the library, attach it to the rule so its id appears in selectedDocIds. Measure what actually arrived in the prompt. The code knows what it dropped. Split reference documents so each is under ~25,000 characters and place the decisive rule near the top.
Written by urgent.news from Dev.to's reporting — not their text. Machine-written — may contain errors; check the original before relying on it.
