2 Commits

Author	SHA1	Message	Date
diegosouzapw	592ca9b5c4	fix: remove hardcoded localhost default arg from GET /api/keys, unify coverage to single coverage/ dir, fix test to pass explicit Request ... - Remove `new Request('http://localhost/api/keys')` default arg from GET handler in src/app/api/keys/route.ts (line 26) - Fix api-key-reveal-route.test.mjs to pass explicit Request instead of calling GET() with no args - Add --output-dir coverage to all c8 scripts in package.json - Add coverage.reportsDirectory: 'coverage' to vitest.config.ts and vitest.mcp.config.ts - Fix CHANGELOG.md structure (# Changelog + [Unreleased] to top) - Remove 30+ stale coverage-* directories from project root - Coverage: Statements 78.76% | Branches 72.75% | Functions 80.93% | Lines 78.76% (all thresholds passed)	2026-04-05 23:21:08 -03:00
oyi77	e6e54822f5	feat: add Memory & Skill Injection from Proxy (Network Level) ... Implements transparent memory and skill injection at the proxy layer, enabling AI agents connecting through OmniRoute to automatically inherit memory and tool capabilities without client-side code changes. Memory System: - SQLite-backed memory store with 4 types: factual, episodic, procedural, semantic - Token budget retrieval with configurable max tokens (default 2000) - Memory injection into chat requests (system message + message prefix) - Memory fact extraction from responses - Dashboard page: /dashboard/memory - MCP tools: omniroute_memory_search, omniroute_memory_add, omniroute_memory_clear Skills System: - Skill registry with semver resolution (^, ~, >=, etc.) - Docker sandbox runner with resource constraints (CPU 100ms, RAM 256MB) - Skill executor with timeout handling - Built-in skills: file_read, file_write, http_request, web_search, eval_code, execute_command - Skill schema injection for OpenAI, Claude, Gemini formats - Tool call interception and execution - Dashboard page: /dashboard/skills - MCP tools: omniroute_skills_list, omniroute_skills_enable, omniroute_skills_execute Advanced Features: - Browser automation skill (Playwright-based) - A2A memory-aware routing skill - Hybrid execution mode (direct/sandbox/auto-upgrade) - Custom skill registration API - Integration tests - Memory caching layer - Memory summarization - Performance benchmarks Resolves: GitHub Issue #812	2026-04-01 09:26:37 +07:00