refactor: source thinking levels from pi and make the gauge dynamic

Depend on @earendil-works/pi-agent-core so the ThinkingLevel union has a single source of truth (re-exported via shared/thinkingLevels). Wire/data fields use string and the parser is lenient, so an unknown level from a newer pi runtime is still listed, selectable, and rendered gracefully instead of throwing. The composer gauge now derives its bar count from the levels available for the current model and fills by rank. Adds compile-time drift guards (satisfies + Exclude check) and unit tests so a changed pi level set fails fast in development.

package.json

@@ -75,6 +75,7 @@
   },
   "devDependencies": {
     "@changesets/cli": "^2.31.0",
+    "@earendil-works/pi-agent-core": "^0.79.1",
     "@earendil-works/pi-ai": "^0.79.1",
     "@earendil-works/pi-coding-agent": "^0.79.1",
     "@eslint/js": "^10.0.1",
@@ -105,6 +106,7 @@
   "homepage": "https://pi-web.dev/",
   "packageManager": "[email protected]",
   "peerDependencies": {
+    "@earendil-works/pi-agent-core": ">=0.78.0 <1",
     "@earendil-works/pi-ai": ">=0.78.0 <1",
     "@earendil-works/pi-coding-agent": ">=0.78.0 <1"
   },