Prefill: classify unknown cultivars into a reference group so the ledger still computes

The extraction schema gains cultivarGroup (typica/bourbon/ethiopian/
hybrid, classified by the LLM from coffee genetics); when the named
variety isn't in the cultivar table, deriveFields now falls back to the
group's first-crack anchor (number still comes only from the reference
table) instead of leaving 1.4 blank and breaking every downstream
calculation. deriveFields exported + unit-tested.

Co-Authored-By: Claude Fable 5 <[email protected]>

server/prefill.js

@@ -24,6 +24,7 @@ Schema:
 {
   "coffeeName": string|null,
   "cultivar": string|null,           // e.g. "Bourbon", "Gesha" — the single named variety, if any
+  "cultivarGroup": string|null,      // one of: "typica","bourbon","ethiopian","hybrid" — the variety's genetic/roast-behavior family. Use your knowledge of coffee genetics to classify the named variety even when it is obscure (e.g. Wush Wush -> "ethiopian", Villa Sarchi -> "bourbon", Ruiru 11 -> "hybrid"). null only if no variety is stated or you genuinely cannot classify it
   "origin": string|null,             // country/region as stated
   "producer": string|null,
   "process": string|null,            // one of: "washed","yellow-honey","red-black-honey","natural","anaerobic" — pick the closest match, or null
@@ -132,8 +133,9 @@ function parseModelJson(raw) {
 }
 
 /** Deterministic mapping from extracted page facts -> worksheet field IDs. The model never
- * supplies a time/duration directly — every number here comes from shared/reference-data.js. */
-function deriveFields(extracted) {
+ * supplies a time/duration directly — every number here comes from shared/reference-data.js.
+ * Exported for unit tests. */
+export function deriveFields(extracted) {
   const fields = {};
   const provenance = {};
   const warnings = [];
@@ -159,7 +161,20 @@ function deriveFields(extracted) {
       set("1.7", formatSigned(row.devModS), "cultivar-table");
     } else {
       set("1.1", extracted.cultivar, "page");
-      warnings.push(`Cultivar "${extracted.cultivar}" is not in the reference table — fields 1.2/1.4/1.5/1.7 left blank; pick the nearest group by hand.`);
+      // Unknown cultivar: fall back to its GROUP's first-crack anchor so the ledger still
+      // computes, instead of leaving 1.4 blank and silently breaking every downstream number.
+      // The group comes from the model's genetics classification, but the NUMBER still only
+      // ever comes from the reference table.
+      const group = findGroup(extracted.cultivarGroup);
+      const groupAnchorS = group ? parseRangeMidpoint(group.fcAnchor) : null;
+      if (group && groupAnchorS !== null) {
+        set("1.2", group.key, "group-table");
+        set("1.4", formatDuration(groupAnchorS), "group-table");
+        set("1.7", "+0:00", "group-table");
+        warnings.push(`Cultivar "${extracted.cultivar}" is not in the reference table — using the ${group.label} group anchor (${group.fcAnchor}) as the first-crack target. Adjust field 1.4 if you know this variety behaves differently.`);
+      } else {
+        warnings.push(`Cultivar "${extracted.cultivar}" is not in the reference table — fields 1.2/1.4/1.5/1.7 left blank; pick the nearest group by hand.`);
+      }
     }
   }
 

test/prefill-derive.test.js

@@ -0,0 +1,61 @@
+import test from "node:test";
+import assert from "node:assert/strict";
+import { deriveFields } from "../server/prefill.js";
+import { computeLedger } from "../shared/ledger.js";
+
+const base = {
+	coffeeName: "Test Coffee",
+	cultivar: null,
+	cultivarGroup: null,
+	origin: "Colombia",
+	producer: null,
+	process: "washed",
+	roastLevel: "light",
+	tastingNotes: [],
+	altitudeMasl: null,
+	screen: null,
+	moisturePct: null,
+	isBlend: false,
+	blendComponents: [],
+};
+
+test("known cultivar uses the cultivar table row", () => {
+	const { fields, provenance } = deriveFields({ ...base, cultivar: "Gesha" });
+	assert.equal(fields["1.1"], "Gesha");
+	assert.equal(fields["1.2"], "ethiopian");
+	assert.equal(fields["1.4"], "7:30");
+	assert.equal(provenance["1.4"], "cultivar-table");
+});
+
+test("unknown cultivar with a classified group falls back to the group anchor so the ledger computes", () => {
+	const { fields, provenance, warnings } = deriveFields({
+		...base,
+		cultivar: "Wush Wush",
+		cultivarGroup: "ethiopian",
+	});
+	assert.equal(fields["1.1"], "Wush Wush");
+	assert.equal(fields["1.2"], "ethiopian");
+	assert.equal(fields["1.4"], "7:25"); // midpoint of the ethiopian group anchor 7:20-7:30
+	assert.equal(provenance["1.4"], "group-table");
+	assert.match(warnings.join(" "), /group anchor/);
+	// The whole point: first crack is now computable
+	const ledger = computeLedger({ fields });
+	assert.equal(ledger.A !== null, true);
+});
+
+test("unknown cultivar in the unparseable hybrid group still degrades gracefully", () => {
+	const { fields, warnings } = deriveFields({
+		...base,
+		cultivar: "Mystery F1",
+		cultivarGroup: "hybrid", // group anchor is "follows parent" — not a number
+	});
+	assert.equal(fields["1.1"], "Mystery F1");
+	assert.equal(fields["1.4"], undefined);
+	assert.match(warnings.join(" "), /pick the nearest group by hand/);
+});
+
+test("unknown cultivar with no group keeps the old blank-fields warning", () => {
+	const { fields, warnings } = deriveFields({ ...base, cultivar: "Zebra SP" });
+	assert.equal(fields["1.4"], undefined);
+	assert.match(warnings.join(" "), /pick the nearest group by hand/);
+});