Files
Epicure/package.json
T
Arnaud 6ec9b65c24 fix: self-heal chatbot recipe requests answered as prose, not a tool call (v0.57.1)
The system prompt already told the model to MUST call createRecipe
instead of writing the recipe out — that's a soft rule some models
(especially free-tier ones) still ignore. There was no fallback: if the
model answered in prose, that's just what got returned, no draft card.

Added a detector (looksLikeUnstructuredRecipe: 3+ numbered/bulleted
lines with no tool call) and a forced-tool retry when it fires — same
system+prompt, but toolChoice forced to createRecipe so the model can't
opt out on the second pass. Falls back to a short localized line if the
provider returns no text alongside a forced tool call (some do this by
design). Retry failure just keeps the original prose answer rather than
erroring the whole request.

Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
2026-07-20 19:33:49 +02:00

24 lines
632 B
JSON

{
"name": "epicure",
"version": "0.57.1",
"private": true,
"scripts": {
"dev": "pnpm --filter web dev",
"build": "pnpm --filter web build",
"lint": "pnpm -r lint",
"typecheck": "pnpm -r typecheck",
"db:generate": "pnpm --filter @epicure/db generate",
"db:migrate": "pnpm --filter @epicure/db migrate",
"db:seed": "pnpm --filter @epicure/db seed",
"db:backfill-usernames": "pnpm --filter @epicure/db backfill-usernames",
"db:studio": "pnpm --filter @epicure/db studio"
},
"devDependencies": {
"typescript": "^5.8.3"
},
"engines": {
"node": ">=22",
"pnpm": ">=11"
}
}