d1e9bb6ae3
OpenAI's Chat Completions name field requires ^[a-zA-Z0-9_-]{1,64}$.
Real-world sender IDs (Discord alice#1234, numeric Telegram IDs, Slack
U07AB12C3DEF, free-form CLI names) often violate this, so a sanitizer
sits between the raw inbound ID and any wire payload.
Disallowed characters collapse into a single underscore, leading and
trailing underscores are trimmed, and the result is byte-safely
truncated to 64 (output is pure ASCII).
This helper will be wired into the agent pipeline in a later commit.
Refs #2702.
70 lines
2.3 KiB
Go
70 lines
2.3 KiB
Go
package messageutil
|
|
|
|
import (
|
|
"regexp"
|
|
"strings"
|
|
|
|
"github.com/sipeed/picoclaw/pkg/providers/protocoltypes"
|
|
)
|
|
|
|
// nameSanitizer matches characters that are not valid in the OpenAI Chat
|
|
// Completions `name` field. The OpenAI spec requires `^[a-zA-Z0-9_-]{1,64}$`.
|
|
var nameSanitizer = regexp.MustCompile(`[^a-zA-Z0-9_-]+`)
|
|
|
|
// maxMessageNameLen mirrors the OpenAI Chat Completions hard limit on the
|
|
// `name` field. Values longer than this are truncated.
|
|
const maxMessageNameLen = 64
|
|
|
|
// SanitizeMessageName normalizes a raw sender identifier into a value safe
|
|
// for the OpenAI Chat Completions `name` field and stable across providers.
|
|
// Disallowed characters are coalesced into a single underscore; leading and
|
|
// trailing underscores are trimmed; the result is truncated to 64 bytes.
|
|
//
|
|
// Returns "" when raw is empty or collapses to nothing after sanitization.
|
|
// The output is pure ASCII so the truncation is byte-safe.
|
|
func SanitizeMessageName(raw string) string {
|
|
raw = strings.TrimSpace(raw)
|
|
if raw == "" {
|
|
return ""
|
|
}
|
|
cleaned := nameSanitizer.ReplaceAllString(raw, "_")
|
|
cleaned = strings.Trim(cleaned, "_")
|
|
if cleaned == "" {
|
|
return ""
|
|
}
|
|
if len(cleaned) > maxMessageNameLen {
|
|
cleaned = cleaned[:maxMessageNameLen]
|
|
}
|
|
return cleaned
|
|
}
|
|
|
|
// IsTransientAssistantThoughtMessage reports whether msg is an invalid
|
|
// reasoning-only assistant history record. These "hanging" thought messages
|
|
// are not a canonical persisted format and should be discarded instead of
|
|
// replayed or reconstructed.
|
|
func IsTransientAssistantThoughtMessage(msg protocoltypes.Message) bool {
|
|
return msg.Role == "assistant" &&
|
|
strings.TrimSpace(msg.Content) == "" &&
|
|
strings.TrimSpace(msg.ReasoningContent) != "" &&
|
|
len(msg.ToolCalls) == 0 &&
|
|
len(msg.Media) == 0 &&
|
|
len(msg.Attachments) == 0 &&
|
|
strings.TrimSpace(msg.ToolCallID) == ""
|
|
}
|
|
|
|
// FilterInvalidHistoryMessages removes invalid persisted history records such
|
|
// as transient assistant thought-only messages.
|
|
func FilterInvalidHistoryMessages(history []protocoltypes.Message) []protocoltypes.Message {
|
|
if len(history) == 0 {
|
|
return []protocoltypes.Message{}
|
|
}
|
|
|
|
filtered := make([]protocoltypes.Message, 0, len(history))
|
|
for _, msg := range history {
|
|
if IsTransientAssistantThoughtMessage(msg) {
|
|
continue
|
|
}
|
|
filtered = append(filtered, msg)
|
|
}
|
|
return filtered
|
|
}
|