5e98445b22
Key changes: - Upgrade model mapping: Opus 4.5 → Opus 4.6-thinking with precise matching - Unified rate limiting: scope-level → model-level with Redis snapshot sync - Load-balanced scheduling by call count with smart retry mechanism - Force cache billing support - Model identity injection in prompts with leak prevention - Thinking mode auto-handling (max_tokens/budget_tokens fix) - Frontend: whitelist mode toggle, model mapping validation, status indicators - Gemini session fallback with Redis Trie O(L) matching - Ops: enhanced concurrency monitoring, account availability, retry logic - Migration scripts: 049-051 for model mapping unification
100 lines
2.4 KiB
Go
100 lines
2.4 KiB
Go
package service
|
|
|
|
import (
|
|
"encoding/json"
|
|
"testing"
|
|
)
|
|
|
|
func TestIsSensitiveKey_TokenBudgetKeysNotRedacted(t *testing.T) {
|
|
t.Parallel()
|
|
|
|
for _, key := range []string{
|
|
"max_tokens",
|
|
"max_output_tokens",
|
|
"max_input_tokens",
|
|
"max_completion_tokens",
|
|
"max_tokens_to_sample",
|
|
"budget_tokens",
|
|
"prompt_tokens",
|
|
"completion_tokens",
|
|
"input_tokens",
|
|
"output_tokens",
|
|
"total_tokens",
|
|
"token_count",
|
|
} {
|
|
if isSensitiveKey(key) {
|
|
t.Fatalf("expected key %q to NOT be treated as sensitive", key)
|
|
}
|
|
}
|
|
|
|
for _, key := range []string{
|
|
"authorization",
|
|
"Authorization",
|
|
"access_token",
|
|
"refresh_token",
|
|
"id_token",
|
|
"session_token",
|
|
"token",
|
|
"client_secret",
|
|
"private_key",
|
|
"signature",
|
|
} {
|
|
if !isSensitiveKey(key) {
|
|
t.Fatalf("expected key %q to be treated as sensitive", key)
|
|
}
|
|
}
|
|
}
|
|
|
|
func TestSanitizeAndTrimRequestBody_PreservesTokenBudgetFields(t *testing.T) {
|
|
t.Parallel()
|
|
|
|
raw := []byte(`{"model":"claude-3","max_tokens":123,"thinking":{"type":"enabled","budget_tokens":456},"access_token":"abc","messages":[{"role":"user","content":"hi"}]}`)
|
|
out, _, _ := sanitizeAndTrimRequestBody(raw, 10*1024)
|
|
if out == "" {
|
|
t.Fatalf("expected non-empty sanitized output")
|
|
}
|
|
|
|
var decoded map[string]any
|
|
if err := json.Unmarshal([]byte(out), &decoded); err != nil {
|
|
t.Fatalf("unmarshal sanitized output: %v", err)
|
|
}
|
|
|
|
if got, ok := decoded["max_tokens"].(float64); !ok || got != 123 {
|
|
t.Fatalf("expected max_tokens=123, got %#v", decoded["max_tokens"])
|
|
}
|
|
|
|
thinking, ok := decoded["thinking"].(map[string]any)
|
|
if !ok || thinking == nil {
|
|
t.Fatalf("expected thinking object to be preserved, got %#v", decoded["thinking"])
|
|
}
|
|
if got, ok := thinking["budget_tokens"].(float64); !ok || got != 456 {
|
|
t.Fatalf("expected thinking.budget_tokens=456, got %#v", thinking["budget_tokens"])
|
|
}
|
|
|
|
if got := decoded["access_token"]; got != "[REDACTED]" {
|
|
t.Fatalf("expected access_token to be redacted, got %#v", got)
|
|
}
|
|
}
|
|
|
|
func TestShrinkToEssentials_IncludesThinking(t *testing.T) {
|
|
t.Parallel()
|
|
|
|
root := map[string]any{
|
|
"model": "claude-3",
|
|
"max_tokens": 100,
|
|
"thinking": map[string]any{
|
|
"type": "enabled",
|
|
"budget_tokens": 200,
|
|
},
|
|
"messages": []any{
|
|
map[string]any{"role": "user", "content": "first"},
|
|
map[string]any{"role": "user", "content": "last"},
|
|
},
|
|
}
|
|
|
|
out := shrinkToEssentials(root)
|
|
if _, ok := out["thinking"]; !ok {
|
|
t.Fatalf("expected thinking to be included in essentials: %#v", out)
|
|
}
|
|
}
|