Files
Agent-Native/runtime/llm/r2_regression_test.go
T
weichenandCursor 17f2a4ecfa Close the native P1 gaps the audit listed for this batch
Why: token budget let the current tool batch run, compaction could split a tool pair or race an append, writes were not crash-atomic, and several MCP and session edges only existed as comments.
Evidence: GOWORK=off go test -count=1 -race ./runtime/ ./runtime/llm/ ./runtime/session/ ./runtime/tools/ ./runtime/mcp/ ./adapters/native/ ./adapters/intentgate/ passed, including the TestR2* cases for budget, replacement, cancel, compaction, SSE, UTF-8, schema, MCP retry, session terminate, poison reload, and registry reload.
Impact: over-budget tool calls are skipped and paired; Stop.Replacement is appended to the session; the intent gate can follow Registry.Reload.
Refs: N5, N6, N7, N8, N9, N11, N12, N15, N16, N17, N18, N19, N21, I9
Co-authored-by: Cursor <cursoragent@cursor.com>
2026-10-03 13:05:58 +00:00

30 lines
502 B
Go

package llm
import (
"context"
"strings"
"testing"
)
func TestR2SSEJoinsMultilineData(t *testing.T) {
body := strings.Join([]string{
`data: {"choices":[{"delta":{"content":"hi"}`,
`data: }]}`,
``,
`data: [DONE]`,
``,
}, "\n")
var got string
for ev := range ParseSSE(context.Background(), strings.NewReader(body)) {
if ev.Kind == KindTextDelta {
got += ev.Text
}
if ev.Kind == KindError {
t.Fatal(ev.Err)
}
}
if got != "hi" {
t.Fatalf("joined content %q", got)
}
}