mirror of
https://github.com/proffesor-for-testing/agentic-qe.git
synced 2026-09-19 08:45:47 +08:00
bd938c5597
* fix(kernel): resolve relative dbPath to prevent split-brain dual-database writes UnifiedPersistenceManager and HybridMemoryBackend pass static relative path '.agentic-qe/memory.db' to UnifiedMemoryManager, which overrides the resolved absolute path in the constructor via spread. When CWD differs from project root (e.g. tests running from v3/), this creates a duplicate database at v3/.agentic-qe/memory.db, splitting dream/concept data from patterns/KV data. Fix: resolve any relative dbPath through findProjectRoot() in the constructor, ensuring all callers converge on the single project-root database. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> * release(v3.6.8): fix MCP auto-init, experience persistence, DB isolation, and missing deps - Fleet auto-initializes on MCP server startup (no manual fleet_init needed) - ExperienceReplay unified to read from captured_experiences table - Data migrator writes to captured_experiences instead of removed experiences table - Added fast-json-patch and jose to root package.json (fixes #262) - Wrapped MinCut dispose saveSnapshot in try/catch for test resilience - Kernel initializes UnifiedPersistence with temp DB for in-memory backend - All 6 MCP handler test files use memoryBackend:'memory' and resetUnifiedPersistence() - domain-handlers and wrapped-domain-handlers use beforeAll to prevent OOM Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> * docs: add RVF integration plan, ADRs, and benchmark script - RVF integration implementation plan and Six Hats analyses - Phase 0 gate report for RVF integration readiness - ADR-065: RVF integration hybrid architecture - ADR-066: RVF pattern store progressive HNSW - ADR-067: Agent memory branching with RVF copy-on-write - AQE baseline benchmark script Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> * fix(tests): restore fleet after dispose in wrapped-domain-handlers beforeAll tests The "not initialized" tests call disposeFleet() but with beforeAll the fleet is only initialized once. Subsequent tests failed because the fleet was never re-initialized. Add handleFleetInit() after each dispose-based test to restore state for later tests. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> --------- Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
1.4 KiB
1.4 KiB
v3.6.8 Release Notes
Release Date: 2026-02-15
Highlights
MCP server now works out of the box — fleet auto-initializes on startup, experience learning is unified, and missing runtime dependencies are resolved.
Fixed
- MCP tools failing with "Fleet not initialized" — Every MCP tool call required a prior
fleet_initcall, which Claude Code doesn't do automatically. Fleet now auto-initializes on MCP server startup with default configuration (hierarchical topology, hybrid memory). - Experience persistence gap — Learning system (
ExperienceReplay) read from a separateexperiencestable while the capture middleware wrote tocaptured_experiences, so new experiences were never visible to the learning system. Unified to usecaptured_experiencesas the single source of truth. - Split-brain database from relative dbPath —
UnifiedMemoryManageraccepted relative paths which could create duplicate databases when CWD differed from project root. Now resolves relative paths throughfindProjectRoot(). - Missing runtime dependency
fast-json-patch(#262) — Package was marked as external in the MCP esbuild bundle but not listed in rootpackage.json, causingERR_MODULE_NOT_FOUNDon fresh installs. Addedfast-json-patchandjoseto root dependencies.
Changed
- Data migrator — v2-to-v3 migration now writes to
captured_experiencestable instead of the removedexperiencestable.