fix

apps/api/internal/processing/openai_api_error.go

@@ -0,0 +1,110 @@
+package processing
+
+import (
+	"fmt"
+	"strings"
+)
+
+// openAIErrorBody is the error object returned by OpenAI-compatible APIs.
+type openAIErrorBody struct {
+	Message string `json:"message"`
+	Type    string `json:"type"`
+	Code    any    `json:"code"` // string or number depending on provider
+	Param   string `json:"param"`
+}
+
+func (e *openAIErrorBody) codeString() string {
+	if e == nil {
+		return ""
+	}
+	switch v := e.Code.(type) {
+	case string:
+		return strings.TrimSpace(v)
+	case float64:
+		if v == float64(int64(v)) {
+			return fmt.Sprintf("%d", int64(v))
+		}
+		return fmt.Sprintf("%g", v)
+	case int:
+		return fmt.Sprintf("%d", v)
+	default:
+		return ""
+	}
+}
+
+// formatOpenAIHTTPError turns an upstream HTTP error into a short, secret-safe
+// operator message. Intentionally avoids embedding model ids (gpt-…) so
+// TruncateError / mapPublicErrorCode do not collapse useful validation text to
+// "processing_failed".
+func formatOpenAIHTTPError(status int, errObj *openAIErrorBody) string {
+	msg := ""
+	code := ""
+	param := ""
+	typ := ""
+	if errObj != nil {
+		msg = strings.TrimSpace(errObj.Message)
+		code = errObj.codeString()
+		param = strings.TrimSpace(errObj.Param)
+		typ = strings.TrimSpace(errObj.Type)
+	}
+	lower := strings.ToLower(msg)
+	codeLower := strings.ToLower(code)
+	paramLower := strings.ToLower(param)
+
+	switch {
+	case status == 401 || codeLower == "invalid_api_key" ||
+		strings.Contains(lower, "invalid api key") ||
+		strings.Contains(lower, "incorrect api key"):
+		return "AI provider rejected the API key"
+	case status == 403:
+		return "AI provider forbidden the request"
+	case status == 429 || codeLower == "rate_limit_exceeded":
+		return "AI provider rate limited — retry later"
+	case codeLower == "insufficient_quota" || strings.Contains(lower, "insufficient_quota") ||
+		strings.Contains(lower, "exceeded your current quota"):
+		return "OpenAI quota exceeded — check billing"
+	case strings.Contains(lower, "does not exist") || strings.Contains(lower, "do not have access") ||
+		codeLower == "model_not_found":
+		return "model not found or API key lacks access — check model name and project permissions"
+	case strings.Contains(lower, "max_tokens") && strings.Contains(lower, "max_completion"):
+		return "model requires completion-token budget (legacy token cap unsupported)"
+	case paramLower == "temperature" || strings.Contains(lower, "temperature"):
+		return "model rejects custom temperature — omit temperature for reasoning chat models"
+	case paramLower == "max_tokens" || (strings.Contains(lower, "unsupported parameter") && strings.Contains(lower, "max_tokens")):
+		return "model rejects legacy token cap — use completion-token budget"
+	case paramLower == "reasoning_effort" || strings.Contains(lower, "reasoning_effort"):
+		return "model rejected reasoning effort — try none/low or omit"
+	case strings.Contains(lower, "unsupported parameter") || strings.Contains(lower, "unsupported value"):
+		if param != "" {
+			return fmt.Sprintf("unsupported chat parameter %q", param)
+		}
+		return "unsupported chat parameter for this model"
+	case status >= 500:
+		return "AI provider temporarily unavailable (server error)"
+	}
+
+	// Prefer structured fields over raw message (raw often embeds model ids / urls).
+	if code != "" && param != "" {
+		return fmt.Sprintf("provider http %d (%s param=%s)", status, code, param)
+	}
+	if code != "" {
+		return fmt.Sprintf("provider http %d (%s)", status, code)
+	}
+	if typ != "" {
+		return fmt.Sprintf("provider http %d (%s)", status, typ)
+	}
+	if status > 0 {
+		return fmt.Sprintf("provider http %d", status)
+	}
+	return "provider request failed"
+}
+
+// ProbeCompleteOptions is the Chat Completions budget for admin connection tests.
+// Explicit max_completion_tokens + reasoning_effort=none avoids GPT-5.6 defaults
+// spending the budget on hidden reasoning for a one-token "ok" reply.
+func ProbeCompleteOptions() CompleteOptions {
+	return CompleteOptions{
+		MaxTokens:       64,
+		ReasoningEffort: "none",
+	}
+}