Review every 10 turns or 15 non-memory tool calls and save explicit corrections promptly. Invalidate outdated learning after lifecycle and history changes, and prevent older correction retries from overwriting newer corrections.
Replace capacity bars with entry and character counts, retain per-entry and model-input budgets, and migrate away from frozen snapshots. Upgrade the AgentKit package and submodule to signed release 0.15.0.
Keep previously installed starter skills as ordinary user-owned records. Provide hidden read-only Skill Creator and Skill Installer instructions, use AgentKit 0.13.0 for reviewed complete GitHub package installation, and remove skill seeding and Reset.
Move Hermes Memory below MCP, use Enabled for its switch, and localize its Chinese title as persistent memory. Preserve existing user edits and synchronize user skill packages through the existing atomic store.
Validation: AgentKit 213 tests and iOS 452 tests passed. macOS app 1183 tests passed; shared frameworks passed 231/232 with the existing SpeechWaveformViewTests PNG byte-equality failure. Related skill, sync, localization and UI checks passed. Strict Swift formatting, Chinese localization checks, and git diff --check passed.
Add opt-in GRDB memory with frozen conversation snapshots, background learning, session search, and a user-only Destroy action on both platforms. Persist and synchronize complete skill packages with the new AgentKit management tools.
Pin signed AgentKit 0.12.3 and GRDB 7.11.1. Add the V18 package migration, regression coverage, bilingual UI snapshots, and architecture records.
Validation: AgentKit and iOS suites, focused macOS skills/memory/architecture/localization tests, Swift formatting, and Chinese localization checks passed. Full macOS runs exposed intermittent existing waveform-rendering and metrics-timing failures.
Kaede Akino