chore: remove dead calculate_token_budget, fix hardcoded timestamp

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

app/main.py

@@ -4,7 +4,7 @@ from fastapi.responses import StreamingResponse, JSONResponse
 from contextlib import asynccontextmanager
 import httpx
 import logging
-from datetime import datetime
+from datetime import datetime, timezone
 
 from .config import config
 from .singleton import get_qdrant_service
@@ -96,7 +96,7 @@ async def api_tags():
         for name in config.cloud.models.keys():
             data["models"].append({
                 "name": name,
-                "modified_at": "2026-03-25T00:00:00Z",
+                "modified_at": datetime.now(timezone.utc).isoformat().replace("+00:00", "Z"),
                 "size": 0,
                 "digest": "cloud",
                 "details": {"family": "cloud"}

app/utils.py

@@ -83,15 +83,6 @@ def merge_memories(memories: List[Dict]) -> Dict:
         "ids": ids
     }
 
-def calculate_token_budget(total_budget: int, system_ratio: float = 0.2, 
-                           semantic_ratio: float = 0.5, context_ratio: float = 0.3) -> Dict[int, int]:
-    """Calculate token budgets for each layer."""
-    return {
-        "system": int(total_budget * system_ratio),
-        "semantic": int(total_budget * semantic_ratio),
-        "context": int(total_budget * context_ratio)
-    }
-
 def load_system_prompt() -> str:
     """Load system prompt from prompts directory."""
     import logging

tests/test_utils.py

@@ -201,37 +201,6 @@ class TestMergeMemories:
         assert len(result["ids"]) == 2
 
 
-class TestCalculateTokenBudget:
-    """Tests for calculate_token_budget function."""
-
-    def test_default_ratios_sum(self):
-        """Default ratios should sum to 1.0 (system+semantic+context)."""
-        from app.utils import calculate_token_budget
-
-        result = calculate_token_budget(1000)
-        assert result["system"] + result["semantic"] + result["context"] == 1000
-
-    def test_custom_ratios(self):
-        """Custom ratios should produce correct proportional budgets."""
-        from app.utils import calculate_token_budget
-
-        result = calculate_token_budget(
-            100, system_ratio=0.1, semantic_ratio=0.6, context_ratio=0.3
-        )
-        assert result["system"] == 10
-        assert result["semantic"] == 60
-        assert result["context"] == 30
-
-    def test_zero_budget(self):
-        """Zero total budget yields all zeros."""
-        from app.utils import calculate_token_budget
-
-        result = calculate_token_budget(0)
-        assert result["system"] == 0
-        assert result["semantic"] == 0
-        assert result["context"] == 0
-
-
 class TestBuildAugmentedMessages:
     """Tests for build_augmented_messages function (mocked I/O)."""