harness: auto-skill general + memory spesifik + lossless compaction

Memory balik spesifik per-project (keep paths, THIS repo), general jadi
skill auto-create ke ~/.shiro-neko/skills/auto-*.md. Compaction lossless
dengan head preserved + droppedSpan normalized + retained note. Learner
throttled tiap 3 turn / delta 8, pakai subagentModel (learnerModel) dan
ceiling guard, hash dedup, JSON fallback, TTL tiap 6 turn.

test/compact.test.ts

@@ -365,6 +365,7 @@ test('lossless compaction appends a retained note when tool content was dropped'
   const session = new Session({
     messages: [...messages],
     compactThreshold: 1500,
+    disableAutoLearn: true,
     model: new MockLanguageModelV4({
       doStream: async () => stream(text('ok')),
       doGenerate: async () => {
@@ -386,6 +387,7 @@ test('no retained note when history fits', async () => {
   const session = new Session({
     messages: [...bulkyExchange(0)],
     compactThreshold: 1_000_000,
+    disableAutoLearn: true,
     model: new MockLanguageModelV4({
       doStream: async () => stream(text('ok')),
       doGenerate: async () => {
@@ -405,6 +407,7 @@ test('a failing retained-note model does not break the turn', async () => {
   const session = new Session({
     messages: [...messages],
     compactThreshold: 1000,
+    disableAutoLearn: true,
     model: new MockLanguageModelV4({
       doStream: async () => stream(text('ok')),
       doGenerate: async () => { throw new Error('down'); },