Merge pull request #146 from Yif-Yang/fix/codex-token-tracker-isolation

fix(model): prevent Codex token double counting

skillopt/model/codex_backend.py

@@ -12,13 +12,13 @@ import uuid
 from typing import Any
 from urllib.parse import unquote, urlparse
 
+from skillopt.model.backend_config import get_codex_exec_config
 from skillopt.model.common import (
     CompatAssistantMessage,
     CompatToolCall,
     CompatToolFunction,
-    tracker,
+    TokenTracker,
 )
-from skillopt.model.backend_config import get_codex_exec_config
 
 
 CODEX_BIN = os.environ.get("CODEX_CLI_BIN", "codex")
@@ -29,6 +29,7 @@ OPTIMIZER_DEPLOYMENT = os.environ.get("OPTIMIZER_DEPLOYMENT", "gpt-4o")
 TARGET_DEPLOYMENT = os.environ.get("TARGET_DEPLOYMENT", "gpt-4o")
 
 REASONING_EFFORT: str | None = None
+tracker = TokenTracker()
 
 
 def _default_working_directory() -> str:

tests/test_codex_optimizer_backend.py

@@ -251,6 +251,35 @@ def test_token_summary_merges_codex_once_with_existing_backends(
     assert summary["_total"]["total_tokens"] == 36
 
 
+def test_codex_usage_is_not_double_counted_by_shared_tracker(
+    isolate_backend_state: tuple[Any, Any, Any, Any],
+) -> None:
+    model_module, _backend_config, codex_backend, _azure_openai = isolate_backend_state
+    from skillopt.model import claude_backend
+
+    model_module.reset_token_tracker()
+    try:
+        assert codex_backend.tracker is not claude_backend.tracker
+
+        codex_backend.tracker.record("optimizer", 11, 13)
+        summary = model_module.get_token_summary()
+
+        assert summary["optimizer"] == {
+            "calls": 1,
+            "prompt_tokens": 11,
+            "completion_tokens": 13,
+            "total_tokens": 24,
+        }
+        assert summary["_total"] == {
+            "calls": 1,
+            "prompt_tokens": 11,
+            "completion_tokens": 13,
+            "total_tokens": 24,
+        }
+    finally:
+        model_module.reset_token_tracker()
+
+
 def test_reset_token_tracker_resets_codex_and_existing_backends(
     monkeypatch: pytest.MonkeyPatch,
     isolate_backend_state: tuple[Any, Any, Any, Any],