v0.2.0-rc.2: P0 hardening — Pi headless, test state isolation, advice fixes (#21)

P0 (correctness):

1. PEPA_HEADLESS=1 guard in extensions/mineflayer-bridge.ts. When `pi -p`
   spawns a subprocess (banter, coach, planner, reflect, auto-patch), the
   bridge no longer attempts a second MC connect — the hybrid runtime
   already owns the nickname. runtime/pi-bridge.js sets the env var on
   every spawn. Root cause of the "two pepa_bot's racing for the slot"
   bug seen in reply-pi stderr.

2. Test state isolation in runtime/config.js. When running under the node
   test runner (detected via execArgv/argv) — or when PEPA_STATE_DIR is
   set — stateDir redirects to /tmp/pepa-test-state-<pid>/. log.js,
   scenario-memory, world-journal, and knowledge.db all follow.
   `npm test` no longer pollutes live scenarios.jsonl, world-journal.jsonl,
   or daily log files. Verified empirically: post-fix run added 0 test
   rows to the live scenarios file. Cleaned ~550 historical test rows
   from live state in the same change.

3. defendReflex outcome reporting (runtime/reflex.js). Previously a
   creeper-rule override marked the lesson succeeded=false BEFORE the
   flee skill returned. Now dispatchDefendFlee accepts {lessonId} and
   the onComplete fires reportAdviceOutcome with the actual flee result.

4. Mode-name → skill-id translation in runtime/coach/advice.js. Pi-coach
   occasionally returns prefer_skill values that are mode names
   ("night_shelter", "self_preservation", "hunger"). normalisePreferSkill
   maps these to SAFE_OVERRIDES entries before dispatch. Also handles
   "tunnel-out", "survive_flee", "survive flee" shapes.

New behavior:

5. Self-reflection loop (runtime/coach/reflect.js). Every 30 min, the
   bot asks Pi: "Are you making progress, or stuck in a loop? What
   should you do differently?" Pi answers with a verdict
   (progress/loop/recovering/idle/emergency), summary, next-action, and
   0-N new lessons. The reflection is written to
   state/<host>/reflections/<ts>.md and lessons land in the DB with
   source="pi-reflect". Rate-limited to 2 calls/hour. Wired through
   bot.js with the existing askPi + lastSnapshot accessor.

Tests: 246/246 green (+9 new: 6 advice mode-name + 4 reflect).

Co-authored-by: Yuriy Mayatnikov <mayatnikov@me.com>
Co-authored-by: Claude Opus 4.7 <noreply@anthropic.com>

runtime/coach/advice.test.js

@@ -8,7 +8,7 @@ import { initKnowledge, record } from "../knowledge/index.js";
 import { __resetForTests, isAvailable, closeStore } from "../knowledge/store.js";
 import { consult, reportOutcome, __testing } from "./advice.js";
 
-const { SAFE_OVERRIDES } = __testing;
+const { SAFE_OVERRIDES, MODE_TO_SKILL, normalisePreferSkill } = __testing;
 
 async function bootstrap() {
 	__resetForTests();
@@ -95,3 +95,48 @@ test("SAFE_OVERRIDES: only contains known reflex skills", () => {
 		assert.ok(typeof id === "string" && id.includes("."), `${id} looks like a real skill id`);
 	}
 });
+
+test("normalisePreferSkill: mode names translate to skill ids", () => {
+	assert.equal(normalisePreferSkill("self_preservation"), "survive.flee");
+	assert.equal(normalisePreferSkill("night_shelter"), "survive.sleep");
+	assert.equal(normalisePreferSkill("hunger"), "survive.eat");
+	assert.equal(normalisePreferSkill("shelter"), "village.build-shelter");
+	assert.equal(normalisePreferSkill("flee"), "survive.flee");
+	assert.equal(normalisePreferSkill("eat"), "survive.eat");
+	assert.equal(normalisePreferSkill("tunnel-out"), "recovery.tunnel-out");
+	assert.equal(normalisePreferSkill("tunnel_out"), "recovery.tunnel-out");
+});
+
+test("normalisePreferSkill: 'survive_flee' shape gets translated to dot form", () => {
+	assert.equal(normalisePreferSkill("survive_flee"), "survive.flee");
+	assert.equal(normalisePreferSkill("survive sleep"), "survive.sleep");
+});
+
+test("normalisePreferSkill: passes through known dot-form skills unchanged", () => {
+	assert.equal(normalisePreferSkill("survive.flee"), "survive.flee");
+	assert.equal(normalisePreferSkill("explore.far"), "explore.far");
+});
+
+test("normalisePreferSkill: unknown values returned as-is", () => {
+	assert.equal(normalisePreferSkill("some.unknown.skill"), "some.unknown.skill");
+	assert.equal(normalisePreferSkill(null), null);
+	assert.equal(normalisePreferSkill(""), "");
+});
+
+test("consult: Pi-style mode-name prefer is normalised to override target", async () => {
+	const tmp = await bootstrap();
+	if (!isAvailable()) { cleanup(tmp); return; }
+	const { id } = (await import("../knowledge/index.js")).record({
+		text: "After a death at night, prefer shelter.",
+		category: "survival",
+		triggerSkill: "gather.logs",
+		avoidSkill: "gather.logs",
+		preferSkill: "night_shelter", // Pi gave a mode name, not a skill id
+		confidence: 0.9,
+		source: "test",
+	});
+	const res = consult({ plannedSkillId: "gather.logs", snapshot: {} });
+	assert.equal(res.action, "override");
+	assert.equal(res.overrideSkillId, "survive.sleep", "night_shelter mapped to survive.sleep");
+	cleanup(tmp);
+});