feat: add standalone Worker protocol SDK and ACK-loss regression

2026-09-17 13:59:33 +08:00
parent cd0dc7011b
commit 1753fcbccb
19 changed files with 1995 additions and 16 deletions
--- a/sdk/go/worker_codec.go
+++ b/sdk/go/worker_codec.go
@@ -0,0 +1,138 @@
+package orbit
+
+import (
+	"bytes"
+	"encoding/json"
+	"io"
+	"strconv"
+	"unicode/utf8"
+
+	"github.com/coder/websocket"
+)
+
+func parseWorkerFrame(kind websocket.MessageType, raw []byte) (workerFrame, error) {
+	var f workerFrame
+	if kind != websocket.MessageText || len(raw) > 512<<10 || validateWorkerJSON(raw) != nil {
+		return f, ErrWorkerProtocol
+	}
+	// Envelope 字段严格区分大小写，防止 encoding/json 的大小写别名覆盖控制字段。
+	var fields map[string]json.RawMessage
+	if json.Unmarshal(raw, &fields) != nil || fields == nil {
+		return f, ErrWorkerProtocol
+	}
+	for k := range fields {
+		switch k {
+		case "protocol_version", "type", "message_id", "reply_to", "session_id", "body", "error":
+		default:
+			return f, ErrWorkerProtocol
+		}
+	}
+	if json.Unmarshal(raw, &f) != nil || f.Version != "1" || !validID(f.MessageID) || f.ReplyTo != "" && !validID(f.ReplyTo) || f.SessionID != "" && !validID(f.SessionID) {
+		return f, ErrWorkerProtocol
+	}
+	if f.Type == "error" {
+		if f.Error == nil || !workerName(f.Error.Code, 64) || len(f.Error.Message) > 1024 || len(f.Body) > 0 {
+			return f, ErrWorkerProtocol
+		}
+	} else if f.Error != nil || len(f.Body) == 0 || bytes.Equal(f.Body, []byte("null")) {
+		return f, ErrWorkerProtocol
+	}
+	return f, nil
+}
+
+// validateWorkerJSON 拒绝重复键、过深嵌套及非法 Unicode，保留数字原文。
+// 数值的业务范围仍由服务端规范化器最终验证；SDK 不经由 float64 重编码。
+func validateWorkerJSON(raw []byte) error {
+	if len(raw) == 0 || !utf8.Valid(raw) || !json.Valid(raw) || !workerUnicode(raw) {
+		return ErrWorkerProtocol
+	}
+	d := json.NewDecoder(bytes.NewReader(raw))
+	d.UseNumber()
+	var value func(int) error
+	value = func(depth int) error {
+		if depth > 32 {
+			return ErrWorkerProtocol
+		}
+		t, err := d.Token()
+		if err != nil {
+			return err
+		}
+		switch t {
+		case json.Delim('{'):
+			keys := map[string]bool{}
+			for d.More() {
+				k, err := d.Token()
+				if err != nil {
+					return err
+				}
+				s, ok := k.(string)
+				if !ok || keys[s] {
+					return ErrWorkerProtocol
+				}
+				keys[s] = true
+				if err := value(depth + 1); err != nil {
+					return err
+				}
+			}
+			_, err = d.Token()
+			return err
+		case json.Delim('['):
+			for d.More() {
+				if err := value(depth + 1); err != nil {
+					return err
+				}
+			}
+			_, err = d.Token()
+			return err
+		}
+		return nil
+	}
+	if err := value(0); err != nil {
+		return err
+	}
+	if _, err := d.Token(); err != io.EOF {
+		return ErrWorkerProtocol
+	}
+	return nil
+}
+
+// JSON 的未配对 UTF-16 转义不能被静默替换为 U+FFFD。
+func workerUnicode(raw []byte) bool {
+	inside := false
+	for i := 0; i < len(raw); i++ {
+		if raw[i] == '"' {
+			inside = !inside
+			continue
+		}
+		if !inside || raw[i] != '\\' {
+			continue
+		}
+		i++
+		if i >= len(raw) {
+			return false
+		}
+		if raw[i] != 'u' {
+			continue
+		}
+		if i+4 >= len(raw) {
+			return false
+		}
+		n, err := strconv.ParseUint(string(raw[i+1:i+5]), 16, 16)
+		if err != nil {
+			return false
+		}
+		i += 4
+		if n < 0xd800 || n > 0xdfff {
+			continue
+		}
+		if n > 0xdbff || i+6 >= len(raw) || raw[i+1] != '\\' || raw[i+2] != 'u' {
+			return false
+		}
+		low, err := strconv.ParseUint(string(raw[i+3:i+7]), 16, 16)
+		if err != nil || low < 0xdc00 || low > 0xdfff {
+			return false
+		}
+		i += 6
+	}
+	return !inside
+}