Understanding levels: closed five-word scale, schema-enforced

The extractor's per-session understanding notes were free-form strings;
the model freely appended em-dash justifications ('shaky — the learner
could state the headline distinction but calls the machinery behind it
foggy'), which overflowed the detail card's session rows and squeezed
the session names.

The note becomes a CLOSED named-word scale — solid / shaky / accepted /
resisted / not yet engaged (DECIDED 2026-09-08, no numbers) — enforced
by the zod enum in propositionSchema: a wrong-shaped note is rejected
at parse time and the agent retries. Justifications are dropped, not
stored (user decision: not necessary). Extractor and auditor
instructions updated to demand exactly one word.

Renderer: the session row keeps the session NAME as the main thing
(flex-1, truncates) and the level chip is bounded (max-w-28,
whitespace-nowrap, truncate) — overflow impossible even for legacy
prose notes in old ledgers.

Vision doc: §1 extractor bullet + event-ledger line updated; state
model line notes the five-class derivation was removed; amendments
table row added.

docs/vision.md

@@ -43,15 +43,15 @@ Every node records every **(chat, message) point** where it came up; every edge
 
 Three stages, one pipeline — the sole graph writer:
 
-- **Extractor (LLM) — session-only scope.** Sees ONLY the session transcript (tree-blind, with message ids). Reports freely, with verbatim evidence: propositions from anywhere in the session (one reasoning step each; prose counts as much as anything the teacher formalized), edges as the transcript articulates them, message-granular provenance, retroactive quiz attribution, and per proposition an **understanding note** — how strongly the learner accepted/understood it in this session, a small named-word scale, no numbers. The notes are data for the future state model; their treatment is TBD.
+- **Extractor (LLM) — session-only scope.** Sees ONLY the session transcript (tree-blind, with message ids). Reports freely, with verbatim evidence: propositions from anywhere in the session (one reasoning step each; prose counts as much as anything the teacher formalized), edges as the transcript articulates them, message-granular provenance, retroactive quiz attribution, and per proposition an **understanding level** — how strongly the learner accepted/understood it in this session, a CLOSED named-word scale (`solid` / `shaky` / `accepted` / `resisted` / `not yet engaged`; 2026-09-08: schema-enforced — exactly one word, no numbers, no justifications, which are dropped rather than stored). The levels are data for the future state model; their treatment is TBD.
 - **Auditor (LLM) — the global-graph scope.** Sees the extractor's output AND the existing graph. Two jobs: the faithfulness net (every candidate verified against verbatim evidence — unchanged), and the **identity judgment**: link each proposition to an existing node (recording the session's phrasing as an alias) or create it new. Conservative: duplicates over wrong merges.
 - **Merger (deterministic).** Append-only ledger writes; quiz event kinds/refs rebuilt mechanically from quiz tool parts. Every judgment is an LLM's; everything mechanical stays code.
 
-**Event ledger (amended):** quiz outcomes are rebuilt deterministically from quiz tool parts (correct / miss / don't-know, plus the learner's note). **There is no `taught` event** — no marking-things-done. The extractor's per-proposition understanding notes join the ledger as session-scoped observations. Identity is no longer exact-string matching — it is the auditor's judgment, with aliases as the phrasing record.
+**Event ledger (amended):** quiz outcomes are rebuilt deterministically from quiz tool parts (correct / miss / don't-know, plus the learner's note). **There is no `taught` event** — no marking-things-done. The extractor's per-proposition understanding levels join the ledger as session-scoped observations (one closed-scale word per node per session). Identity is no longer exact-string matching — it is the auditor's judgment, with aliases as the phrasing record.
 
 ### Understanding is derived (amended 2026-09-02)
 
-Known vs. understood, event ledger as source of truth, derived state recomputed on read — carried over from the design doc in spirit. The state model itself is now an explicit design discussion: **node states should be session-independent and computed from the depth and strength of dependencies** (the `follows`/`supports` topology) plus quiz events and understanding notes. That redesign is pending ideation; the current five-class derivation (taught / known / missed / don't-know / candidate) is transitional. The anchored calibration rubric stays parked until real data.
+Known vs. understood, event ledger as source of truth, derived state recomputed on read — carried over from the design doc in spirit. The state model itself is now an explicit design discussion: **node states should be session-independent and computed from the depth and strength of dependencies** (the `follows`/`supports` topology) plus quiz events and understanding notes. That redesign is pending ideation; the transitional five-class derivation (taught / known / missed / don't-know / candidate) was **removed** (2026-09-08) — the graph view renders state-neutral nodes until the state model is designed. The anchored calibration rubric stays parked until real data.
 
 ### Rendering (DECIDED — research report 2026-08-22)
 
@@ -224,6 +224,7 @@ The teacher's context window and attention are precious — it has the lesson to
 | Misconception nodes as first-class structure | No node `kind`: every node is a true proposition; misconceptions enter as true corrections, wrongness lives in the event ledger |
 | `requires` edges | `follows` / `supports` — derivability vs. grounding; strength derived at read time, never stored |
 | `taught` events (marking things done) | Dropped; the extractor records per-proposition understanding notes (named-word scale) as session-scoped observations instead |
+| Understanding scale standardized (2026-09-08) | The note becomes a closed five-word scale (`solid`/`shaky`/`accepted`/`resisted`/`not yet engaged`), enforced by the extraction schema — no numbers, no prose; agent justifications are dropped |
 | Chat-granular node/edge provenance | Message-granular (chat, message) provenance on nodes and edges — the exact derivation points |
 | `name` + `statement` on nodes | `statement` (minimal proposition, the rendering label) + `description` (required elaboration) + `aliases` (verbatim phrasings) |
 | `statement` + `description` (2026-09-02) | `name` (very short label, the rendering handle) + `statement` (full precision, identity anchor, detail card); `description` dropped — full-sentence canvas labels cluttered the graph (2026-09-08, seeing real extracted data) |

src/agent/subagents/extraction.ts

@@ -118,11 +118,12 @@ const propositionSchema = z.object({
 	messages: messagesField,
 	evidence,
 	understanding: z
-		.string()
+		.enum(["solid", "shaky", "accepted", "resisted", "not yet engaged"])
 		.optional()
 		.describe(
-			'One note about THIS session\'s evidence of the learner\'s grasp of this proposition, on a named-word scale ' +
+			"ONE word — the learner's grasp of this proposition in THIS session, from the fixed scale " +
-				'("solid", "shaky", "accepted", "resisted", "not yet engaged") — no numbers, no predictions.',
+				'"solid" | "shaky" | "accepted" | "resisted" | "not yet engaged". Nothing else: no numbers, ' +
+				"no justification, no explanation.",
 		),
 });
 
@@ -180,8 +181,9 @@ quiz outcomes carry that the learner believed the wrong version.
    - One reasoning step per proposition: never a topic blob, never a sub-step.
    - "messages": the [id] tags of every message where the proposition came up — provenance, report it.
    - "aliases": verbatim phrasings this session used for the same proposition.
-   - "understanding": ONE named-word-scale note on the evidence of the learner's grasp, for this session
+   - "understanding": ONE word from the fixed scale — "solid", "shaky", "accepted", "resisted", or
-     only ("solid", "shaky", "accepted", "resisted", "not yet engaged"). No numbers, no predictions.
+     "not yet engaged" — judging the learner's grasp of the proposition in THIS session. Strictly one
+     word, no numbers, no justification, no explanation (a wrong-shaped note is rejected by the schema).
 
 2. EDGES between propositions:
    - "follows": to is DERIVABLE from from (understanding from makes understanding to achievable).
@@ -256,8 +258,9 @@ FAITHFULNESS — verify every candidate against the transcript:
   direction-swapped or speculative edges.
 - ATTRIBUTION: the QUIZ line's question must genuinely test the attributed proposition. Drop wrong
   attributions to null, or re-point them to the proposition the question actually tests.
-- UNDERSTANDING notes: verify against the quiz outcomes and the session's evidence; reword to a named-word
+- UNDERSTANDING levels: verify against the quiz outcomes and the session's evidence; each note must be
-  scale or drop.
+  exactly one word from the fixed scale ("solid", "shaky", "accepted", "resisted", "not yet engaged") —
+  reword or drop anything else. No justifications.
 
 IDENTITY — link-or-create, per proposition:
 - You see the current graph (every node: id, name, statement, aliases). For each verified proposition,

src/core/contracts/graph.ts

@@ -102,7 +102,8 @@ export interface LedgerEvent {
 	 *  understanding observations — re-emission of the same chat must never
 	 *  double-record an event. */
 	ref?: string;
-	/** The learner's quiz note — diagnostic gold (vision §1 calibration). */
+	/** The learner's quiz note (diagnostic gold), or the understanding
+	 *  LEVEL word for observations — a session-relative judgment. */
 	note?: string;
 	/** The quiz question text, when nodeId is null (later attribution input). */
 	question?: string;
@@ -138,6 +139,16 @@ export interface LedgerEvent {
 
 // ─── Extraction findings (extractor output → audit → merger input) ───────────
 
+/**
+ * The extractor's standardized per-session understanding scale (DECIDED
+ * 2026-09-08): a CLOSED named-word list — no numbers, no prose, no
+ * justifications (a justification, if the agent wants one, is dropped;
+ * it is not stored). The level is session- and extraction-run-relative
+ * judgment about the learner, shown next to its session — never a node
+ * property.
+ */
+export type UnderstandingLevel = "solid" | "shaky" | "accepted" | "resisted" | "not yet engaged";
+
 /** One proposed proposition — a node candidate (or a re-encounter of one). */
 export interface ExtractedProposition {
 	/** Extractor-local id ("p1", …) referenced by edges + attribution. */
@@ -158,11 +169,11 @@ export interface ExtractedProposition {
 	messages: string[];
 	/** Verbatim transcript quotes backing the proposition. */
 	evidence: string[];
-	/** The extractor's understanding note for this proposition IN THIS
+	/** The extractor's understanding level for this proposition IN THIS
-	 *  session — a named-word scale ("solid", "shaky", "accepted",
+	 *  session — one word from the UnderstandingLevel scale. Joins the
-	 *  "resisted"), no numbers. Joins the ledger as an observation event;
+	 *  ledger as an observation event (note = the level word); treatment
-	 *  treatment pending the state-model ideation. */
+	 *  pending the state-model ideation. */
-	understanding?: string;
+	understanding?: UnderstandingLevel;
 }
 
 /** One proposed relation between two propositions. */

tests/graph.test.ts

@@ -172,7 +172,7 @@ function fixtureAudit(): AuditResult {
 				aliases: ["alpha feel"],
 				messages: ["a1", "a3"],
 				evidence: ["fixture evidence"],
-				understanding: "solid after the check",
+				understanding: "solid",
 			},
 			{
 				id: "p2",
@@ -295,7 +295,7 @@ describe("the merger (mergeFindings)", () => {
 		const observation = byRef.get("obs:p1")!;
 		assert.equal(observation.kind, "observation");
 		assert.equal(observation.nodeId, idByStatement.get("Alpha intuition"));
-		assert.equal(observation.note, "solid after the check");
+		assert.equal(observation.note, "solid");
 
 		// The dismissed quiz and the ask question became nothing.
 		assert.equal([...byRef.keys()].filter((r) => r === "call-6" || r === "call-7").length, 0);
@@ -380,9 +380,9 @@ describe("the merger (mergeFindings)", () => {
 		assert.deepEqual(snap.nodeSessions[idByStatement.get("Gamma application")!], [chat1.id]);
 
 		// Understanding observations: (node → chat → the extractor's note).
-		// Alpha carries chat1's "solid after the check"; chat2's q1 has no note.
+		// Alpha carries chat1's "solid" level; chat2's q1 has no level.
 		const alphaObs = snap.nodeObservations[idByStatement.get("Alpha intuition")!] ?? {};
-		assert.equal(alphaObs[chat1.id], "solid after the check");
+		assert.equal(alphaObs[chat1.id], "solid");
 		assert.equal(alphaObs[chat2Id], undefined);
 	});