fix: clarify memory selection semantics

2026-07-14 13:13:59 +02:00
parent 1e3c5a1e99
commit c7d586aaf7
10 changed files with 205 additions and 24 deletions
@@ -0,0 +1,18 @@
+const test = require("node:test");
+const assert = require("node:assert");
+const { memorySelectionWidgetProps } = require("../../tht-gate.js");
+
+test("F2 preseleziona solo le memory raccomandate e parla di applicazione", () => {
+  assert.deepEqual(
+    memorySelectionWidgetProps([
+      { id: "recommended", label: "Memory A", recommended: true },
+      { id: "optional", label: "Memory B" },
+    ]),
+    {
+      title: "Seleziona le memory da applicare alla domanda",
+      selected: ["recommended"],
+      selectionLabel: "memory da applicare",
+      confirmLabel: "Applica le memory selezionate",
+    },
+  );
+});
@@ -7,6 +7,13 @@ const { createFakePi } = require("./fake_pi_runtime.js");
 const installGate = require("../../tht-gate.js").default ?? require("../../tht-gate.js");

 test("con THT_SESSION il kickoff usa l'id fornito e NON crea la sessione", async () => {
+  const tmp = fs.mkdtempSync(path.join(os.tmpdir(), "tht-gate-no-pack-"));
+  const bin = path.join(tmp, "bin");
+  fs.mkdirSync(bin);
+  const tht = path.join(bin, "tht");
+  fs.writeFileSync(tht, "#!/bin/sh\nexit 1\n", { mode: 0o755 });
+  const oldPath = process.env.PATH;
+  process.env.PATH = bin + ":" + oldPath;
  process.env.THT_SESSION = "2026-06-27-100000-test";
  try {
    const { pi, ctx } = createFakePi();
@@ -19,13 +26,15 @@ test("con THT_SESSION il kickoff usa l'id fornito e NON crea la sessione", async
    assert.doesNotMatch(text, /tht session new/);
    assert.match(text, /retrieval pack non era ancora disponibile/i);
    assert.match(text, /tht search pack/);
-    assert.doesNotMatch(text, /<retrieval-pack>/);
+    assert.doesNotMatch(text, /<retrieval-pack>\s*# Retrieval pack/);
    assert.match(text, /<tht-sessione-skill>/);
    assert.match(text, /# Thoth session workflow \(phases 1-8\)/);
    assert.match(text, /non esplorare il repository/i);
    assert.doesNotMatch(text, /Carica la skill leggendo/);
  } finally {
+    process.env.PATH = oldPath;
    delete process.env.THT_SESSION;
+    fs.rmSync(tmp, { recursive: true, force: true });
  }
 });

@@ -61,6 +61,7 @@ function buildSelectRequest({
 // `allowEmpty:false` with zero options is a broken widget and throws.
 function buildMultiselectRequest({
  id, phase, title, options, content = null, selected = [], allowEmpty = false,
+  selectionLabel, confirmLabel,
 }) {
  requireString(title, "title", "multiselect");
  const opts = requireArray(options, "options", "multiselect");
@@ -77,10 +78,12 @@ function buildMultiselectRequest({
    widget: "multiselect",
    title,
    allow_empty: allowEmpty,
-    options: [...opts],
+    options: opts.map((option) => ({ ...option, selected: selected.includes(option.id) })),
    selected: [...selected],
    content,
    reserved: RESERVED,
+    ...(selectionLabel ? { selection_label: selectionLabel } : {}),
+    ...(confirmLabel ? { confirm_label: confirmLabel } : {}),
  };
 }

@@ -386,6 +386,17 @@ export function shouldSkipEmptyDecide({ meritCount, allowEmpty, advance }) {
 	return meritCount === 0 && !!allowEmpty && !!advance;
 }

+// Phase 2 uses a single positive checkbox meaning: apply this memory now.
+// Candidates not checked by the reviewer remain undecided and may be shown again.
+export function memorySelectionWidgetProps(options) {
+	return {
+		title: "Seleziona le memory da applicare alla domanda",
+		selected: options.filter((option) => option.recommended).map((option) => option.id),
+		selectionLabel: "memory da applicare",
+		confirmLabel: "Applica le memory selezionate",
+	};
+}
+
 // --- F8 memory-promotion gate: pure candidate->widget mapping (L1-tested) ------
 // The candidates come from `tht memory promote --preview --json` (deterministic,
 // reviewer-approved decisions only); the model never authors them.
@@ -730,10 +741,10 @@ export default function (pi) {
 			const widget = buildMultiselectRequest({
 				id: `u${Date.now()}`,
 				phase,
-				title,
+				title: phase === "F2" ? memorySelectionWidgetProps(opts).title : title,
 				allowEmpty: params.allow_empty ?? false,
 				options: meritOptions,
-				recommended: opts.find((o) => o.recommended)?.id ?? null,
+				...(phase === "F2" ? memorySelectionWidgetProps(opts) : {}),
 			});
 			const resp = await emitAndWait(ctx, widget);
 			if (resp.control === "freetext") {
@@ -215,21 +215,21 @@ Prerequisite: Phase 1 closed.
   allow_empty:true)`. Rules: at most **5** candidates; ONLY the 3 reusable types
   (`concept_clarified`, `table_promoted`, `table_excluded`) — query-specific
   decisions (`question_rewritten`, `sql_approved`, …) are NOT transferable, never
-   propose them. Each option carries `mem_id:"mem-<id>"` plus `type`/`subject`/
-   `rationale`. Selected options are applied (register the decision citing the
-   `mem_id` in the rationale); deselected ones are recorded as `memory_rejected` by
-   the gate (so the next `tht memory search --session` won't re-propose them). The
-   checklist starts pre-selected with the recommended memories. With `allow_empty:true`
-   an empty selection is accepted (no memory applied; deselected still recorded) and
-   the phase advances — no separate gate.
+   propose them. Each option carries `type`/`subject`/`rationale`; cite the source
+   memory id (`mem-<id>`) in its rationale when applying it. Every option describes a
+   candidate memory; never create an opposite "do not use" option. Only
+   `recommended:true` options start checked. A
+   deselected candidate is **not applied now**, not rejected, and may be considered
+   again if Phase 2 is reopened. With `allow_empty:true` an empty selection is accepted
+   (no memory applied) and the phase advances — no separate gate.
   When the memory search returned **zero** candidates, still issue the single
   `reviewer_decide(multi:true, advance:true, allow_empty:true)` with an empty merito list: the gate
   detects the empty+advance case, shows the reviewer an info notice ("Nessuna memory
   riutilizzabile … passo alla fase successiva") and auto-advances F2 — it does NOT present
   an empty checklist, and you do NOT add a separate `reviewer_confirm kind:"phase"`.
-4. Closing: if memories were applied or rejected (substantive decisions), `advance:true`
-   no-ops — close with `reviewer_confirm kind:"phase"`. Only a truly empty memory phase
-   (nothing applied, nothing rejected) auto-advances via `advance:true`.
+4. Closing: if one or more memories were applied (substantive decisions), `advance:true`
+   no-ops — close with `reviewer_confirm kind:"phase"`. If none is applied, F2
+   auto-advances via `advance:true`.
 5. Memories are promoted at the END of the workflow (Phase 8, the
   `reviewer_memory_promote` gate) — never promote from here, never run
   `tht memory promote`/`save-one` yourself (the gate blocks them).
@@ -24,14 +24,13 @@ Rules:
  (e.g. `question_rewritten`, `sql_approved`) are NOT to be proposed: they don't
  transfer to other questions.
 - All candidate memories go in **a single** `reviewer_decide(multi:true,
-  advance:true, allow_empty:true)`: each selected option is applied (register the
-  decision with the appropriate type, citing the memory id in the rationale), each
-  deselected option is **recorded as `memory_rejected` by the gate** (so the next
-  `tht memory search --session` won't re-propose it). To enable this, EVERY memory
-  option MUST carry the field `mem_id:"mem-<id>"` (besides `type`/`subject`/
-  `rationale`). The checklist starts pre-selected with the recommended memories.
-  With `allow_empty:true` an **empty selection is accepted** (no memory applied; the
-  deselected ones are still recorded as rejected) and the phase advances — no
+  advance:true, allow_empty:true)`: every option describes a candidate memory, never
+  an opposite action such as "do not use it". Each selected option is applied
+  (register the decision with the appropriate type, citing the memory id in the
+  rationale). Mark `recommended:true` ONLY on memories proposed for use: those, and
+  only those, start checked. An unchecked memory is **not applied now**; it is not a
+  rejection and may be considered again if Phase 2 is reopened. With `allow_empty:true`
+  an **empty selection is accepted** (no memory applied) and the phase advances — no
  separate gate.
 - For "inspect": show the memory's full JSON record in the prose before presenting
  the checklist, if the reviewer asks.