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

mcp/request.go

@@ -1,5 +1,7 @@
 package mcp
 
+import "context"
+
 // Message represents a conversation message.
 // Supports plain messages (Role+Content), assistant tool-call messages (ToolCalls),
 // and tool result messages (Role="tool", ToolCallID, Content).
@@ -62,6 +64,11 @@ type Request struct {
 	// Advanced features
 	Tools      []Tool `json:"tools,omitempty"`       // Available tools list
 	ToolChoice string `json:"tool_choice,omitempty"` // Tool choice strategy ("auto", "none", {"type": "function", "function": {"name": "xxx"}})
+
+	// Context for cancellation — not serialized to JSON.
+	// If set, HTTP requests use this as the parent context so client disconnects
+	// propagate and cancel in-flight LLM calls.
+	Ctx context.Context `json:"-"`
 }
 
 // NewMessage creates a message