2 Commits

Author	SHA1	Message	Date
shinchan-zhai	3f1dd71f2b	fix: context propagation in LLM calls, SSE error handling, security hardening ... - Propagate request context through MCP client (Request.Ctx field) — Client disconnects now cancel in-flight LLM API calls (both streaming and non-streaming) — Prevents wasted LLM tokens when user navigates away mid-response - proxyBinance: use http.NewRequestWithContext for context-aware upstream calls — Client disconnects cancel Binance proxy requests — Distinguishes client cancellation from upstream failures - Fix SSE parse bug in AgentChatPage: catch block was swallowing error events — throw new Error(data) for 'error' events was caught by the same try/catch — Now parse JSON separately, then handle events outside try/catch - Add io.LimitReader to Hyperliquid coins.go JSON decoder (4MB limit) - Use safe.ReadAllLimited in batch ticker handler for consistency - Sanitize URL validation error in handler_ai_model.go (was leaking raw error) - Cache agent tool definitions (built once, reused per message) - Sort trade history by exit time for consistent ordering	2026-03-23 15:37:36 +08:00
tinkle-community	8e294a5eed	refactor: restructure project directories for better modularity ... - Delete llm/ dead code (3 files, zero references) - Split mcp/ into sub-packages: mcp/provider/ (8 providers) and mcp/payment/ (4 payment clients) with registry pattern - Export Client internal fields and ClientHooks interface for sub-package access - Split api/server.go (3892 lines) into 8 domain-specific handler files - Split trader/auto_trader.go (2296 lines) into 5 focused files - Reorganize web/src/components/ flat files into auth/, charts/, trader/, common/, modals/, backtest/ subdirectories - Update all consumer imports to use registry-based provider creation	2026-03-11 23:58:13 +08:00