shinchan-zhai c014724896 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

2026-03-25 01:05:54 +08:00

..

coins.go

fix: context propagation in LLM calls, SSE error handling, security hardening

2026-03-25 01:05:54 +08:00

kline_test.go

feat: add xyz dex balance calculation, market data providers, and UI improvements

2025-12-29 22:16:48 +08:00

kline.go

security: add safe.ReadAllLimited — bound all HTTP response body reads to 10MB

2026-03-25 01:05:54 +08:00