eklavya 1.84.0 → 1.85.0

package/README.md

@@ -52,13 +52,13 @@ Code's learning loop.
 |---|---|
 | Learner state and concepts | `get_learner_profile`, `log_session_concepts`, `upsert_concepts`, `get_concept_graph` |
 | Questions and assessment (automatic questions wait for a code change, not a `git pull`; see `quiz.only_on_changes`) | `get_session_quiz_plan`, `record_attempt`, `get_gate_status` |
-| Quiz side panel (experimental) | `present_question` for the model; `panel_sync` and `panel_answer`, called only by the panel mod, never by the model; its header stacks the mark above the topic in a pane under 60 cells wide |
+| Quiz side panel (experimental) | `present_question` for the model; `panel_sync` and `panel_answer`, called only by the panel mod, never by the model; its header stacks the mark above the topic in a pane under 60 cells wide; on the desktop app each option's note is its own line under the option, and a click on the option picks it |
 | Settings | `get_config`, `set_config` |
 | Find and read memory (`memory_status` includes a `health` verdict with reasons) | `memory_search`, `memory_get`, `memory_timeline`, `memory_file_history`, `memory_status` |
 | Maintain memory | `memory_write`, `memory_correct`, `memory_delete`, `memory_collections` |
 | Inspect code | `code_outline`, `code_find_symbol` |
 
-`log_session_concepts` and `upsert_concepts` take a concept name of 1 to 3 words, a `description` of up to 400 characters and up to 5 `tags`. A new concept that resembles existing ones is not created: the response lists it under `needs_decision` with candidates, and you reuse a candidate's slug or repeat the slug with `new: true`. `log_session_concepts` creates a new concept with the domain and tier you pass, or domain `general` and tier 2 when you pass none. Pass `prerequisites` (up to 5 slugs, existing or in the same call) and each becomes a `prerequisite_of` edge; a slug it cannot find is reported under `prerequisites_not_found`, and the response lists the created concepts that still have no edge under `unlinked`. `upsert_concepts` sets the domain and tier of a model-created concept that still has domain `general`, adds tags to any concept, fills in or refines the description of a model-created concept, and adds edges. It never rewrites the description or domain of a concept from the seed or a pack, or of one that already has a domain (the one it was logged with, or its first tag). Its response lists the concepts it changed under `updated`. `get_concept_graph` returns each concept's `tags`.
+`log_session_concepts` and `upsert_concepts` take a concept name of 1 to 3 words (a longer name fails the whole call's input check), a `description` of up to 400 characters and up to 5 `tags`. A new concept that resembles existing ones is not created: the response lists it under `needs_decision` with candidates, and you reuse a candidate's slug or repeat the slug with `new: true`. `log_session_concepts` creates a new concept with the domain and tier you pass, or domain `general` and tier 2 when you pass none. Pass `prerequisites` (up to 5 slugs, existing or in the same call) and each becomes a `prerequisite_of` edge; a slug it cannot find is reported under `prerequisites_not_found`, and the response lists the created concepts that still have no edge under `unlinked`. `upsert_concepts` sets the domain and tier of a model-created concept that still has domain `general`, adds tags to any concept, fills in or refines the description of a model-created concept, and adds edges. It never rewrites the description or domain of a concept from the seed or a pack, or of one that already has a domain (the one it was logged with, or its first tag). Its response lists the concepts it changed under `updated`. `get_concept_graph` returns each concept's `tags`.
 
 `memory_collections` applies a saved filter the same way with or without a
 query, and its members are live entries only: a member deleted or corrected

package/dist/assets/tutor/SKILL.md

@@ -49,7 +49,7 @@ actual decision in the actual file.
 - Good: `"set httpOnly on the refresh cookie in auth.ts:42"`
 - Useless: `"used cookies"`
 
-A concept is a topic, not a fact: `name` it in 1–3 words ("Flutter animation",
+A concept is a topic, not a fact: `name` it in 1–3 words, never 4 or more ("Flutter animation",
 not "dispose the controller in pulse.dart"), say what it is in `description`,
 add `tags`. Reuse what exists. If the response has `needs_decision`, nothing was
 logged for those: call again with a candidate's `slug` when it is the same idea,
@@ -57,8 +57,8 @@ or the same slug with `new: true` when none is. Give each concept an honest `tie
 or `prereqs_unmet` stays empty and the fairness check silently passes. Any
 `unlinked` slug in the response still owes an edge: `upsert_concepts`.
 
-Logging is silent — never narrate it or pause the work to announce it. On
-`as-you-go` cadence, the default, the log call may come straight back with a
+Logging is silent — never narrate it or pause the work. On
+`as-you-go` cadence, the default, the call may come back with a
 checkpoint.
 
 ## Which one is asking

package/dist/plugin/.claude-plugin/plugin.json

@@ -1,7 +1,7 @@
 {
   "name": "eklavya",
   "displayName": "Eklavya",
-  "version": "1.84.0",
+  "version": "1.85.0",
   "description": "Learn while your agent works. Turns coding-agent generation time into adaptive, Socratic learning grounded in the code being written.",
   "author": {
     "name": "Ajay Kumar"

package/dist/plugin/hooks/panel/register.tsx

@@ -434,7 +434,7 @@ export const register: Register = on => {
         ))}
       </Box>
     )
-    // One answer: a bordered block. The Button holds the whole answer text, so a press anywhere on it
+    // One answer: a bordered block. The Button holds the answer text, so a press on it
     // selects; the border and fill show the pick, and nothing implies it is
     // right. The desktop app gives the text more room inside the border; the padding itself is not
     // pressable, since a Button takes none. The terminal keeps its tight cards.
@@ -501,11 +501,12 @@ export const register: Register = on => {
     const locked = s.step === 'grading'
     // Submit looks disabled until there is something to send; pressing it then does nothing.
     const hasDraft = s.draft.other ? s.draft.text.trim().length > 0 : s.draft.picked !== null
-    // The answer and its note are the Button's own inline Text, so a press anywhere on them selects.
+    // In the terminal the answer and its note are the Button's own inline Text, so a press anywhere on them
+    // selects. The desktop app draws only a Button's label (docs/verified-schemas.md row 17), so there the
+    // note is a Text under the Button and only the answer selects.
     // Markdown marks cannot show inside a Button, so the code and bold marks are dropped from both.
     // The pick shows by the card's border and fill, never a mark in the text, so picking moves nothing.
-    // On the desktop app the note starts where the answer does; the terminal indents it under the `1: `
-    // its plain Button draws.
+    // The terminal indents the note under the `1: ` its plain Button draws.
     // `wrap` asks the app to wrap a long answer rather than cut it off.
     const answer = (id: string, key: string, hotkey: string, label: string, chosen: boolean, note?: string) => (
       <Button
@@ -516,7 +517,7 @@ export const register: Register = on => {
         onPress={() => (locked ? undefined : id === 'other' ? chooseOther($) : pick($, id))}
       >
         <Text wrap="wrap" bold={chosen} color={chosen && id !== 'other' ? PICKED.text : undefined}>{label}</Text>
-        {note ? <Text wrap="wrap" dimColor={!chosen} color={chosen ? PICKED.note : undefined}>{`\n${app ? '' : '   '}${note}`}</Text> : null}
+        {note && !app ? <Text wrap="wrap" dimColor={!chosen} color={chosen ? PICKED.note : undefined}>{`\n   ${note}`}</Text> : null}
       </Button>
     )
     const options = q.options.map((o, i) => {
@@ -525,7 +526,10 @@ export const register: Register = on => {
         o.id,
         chosen,
         answer(o.id, `opt-${o.id}`, String(i + 1), plainLabel(o.label), chosen, o.note ? plainLabel(o.note) : undefined),
-        [],
+        // The desktop app draws only a Button's label, not its inline children, so there the note sits under the button.
+        app && o.note
+          ? [<Text key={`note-${o.id}`} wrap="wrap" dimColor={!chosen} color={chosen ? PICKED.note : undefined}>{plainLabel(o.note)}</Text>]
+          : [],
       )
     })
 

package/dist/plugin/skills/tutor/SKILL.md

@@ -49,7 +49,7 @@ actual decision in the actual file.
 - Good: `"set httpOnly on the refresh cookie in auth.ts:42"`
 - Useless: `"used cookies"`
 
-A concept is a topic, not a fact: `name` it in 1–3 words ("Flutter animation",
+A concept is a topic, not a fact: `name` it in 1–3 words, never 4 or more ("Flutter animation",
 not "dispose the controller in pulse.dart"), say what it is in `description`,
 add `tags`. Reuse what exists. If the response has `needs_decision`, nothing was
 logged for those: call again with a candidate's `slug` when it is the same idea,
@@ -57,8 +57,8 @@ or the same slug with `new: true` when none is. Give each concept an honest `tie
 or `prereqs_unmet` stays empty and the fairness check silently passes. Any
 `unlinked` slug in the response still owes an edge: `upsert_concepts`.
 
-Logging is silent — never narrate it or pause the work to announce it. On
-`as-you-go` cadence, the default, the log call may come straight back with a
+Logging is silent — never narrate it or pause the work. On
+`as-you-go` cadence, the default, the call may come back with a
 checkpoint.
 
 ## Which one is asking

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "eklavya",
-  "version": "1.84.0",
+  "version": "1.85.0",
   "description": "Learn while your agent works — local knowledge graph, spaced repetition, and quiz gating for agent-assisted development.",
   "license": "MIT",
   "repository": {