Workflow to ensure codebase integrity

.github/workflows/restore_cost_benefit.yml

@@ -1,97 +1,89 @@
-name: Restore src/cost_benefit.py on every commit
+# .github/workflows/restore_cost_benefit.yml
+name: Restore src/cost_benefit.py
 
 on:
   push:
-    branches:
-      - main
+    branches: [main]
   pull_request:
-    branches:
-      - main
+    branches: [main]
 
 jobs:
-  restore-file:
+  restore:
     runs-on: ubuntu-latest
+    # allow the GITHUB_TOKEN to push a commit back
+    permissions:
+      contents: write
 
     steps:
-      - name: Checkout repo
+      - name: Checkout repository
         uses: actions/checkout@v3
+        with:
+          # you need the token available for the later push
+          token: ${{ secrets.GITHUB_TOKEN }}
 
       - name: Recreate src/cost_benefit.py
         run: |
           mkdir -p src
-          cat <<EOF > src/cost_benefit.py
-import argparse
-
-import subprocess
-
-import time
-
-import requests
-
-def detect_available_budget(runtime_env: str) -> int:
-    import torch
-    if "local" in runtime_env and torch.cuda.is_available():
-        total_vram_mb = torch.cuda.get_device_properties(0).total_memory // (1024 ** 2)
-        return min(total_vram_mb, 100)
-    else:
-        return 100
-
-def get_best_model(runtime_env: str, use_local_only=False, use_api_only=False) -> dict:
-    static_costs = {
-        "llama3.2": {"size": 20, "token_cost": 0.0001, "tokens_sec": 30, "type": "local"},
-        "mistral": {"size": 40, "token_cost": 0.0002, "tokens_sec": 50, "type": "local"},
-        "gemini-2.0-flash": {"size": 60, "token_cost": 0.0005, "tokens_sec": 60, "type": "api"},
-        "gemini-2.5-pro-preview-03-25": {"size": 80, "token_cost": 0.002, "tokens_sec": 45, "type": "api"}
-    }
-
-    def detect_available_budget(runtime_env: str) -> int:
-        import torch
-        if "local" in runtime_env and torch.cuda.is_available():
-            total_vram_mb = torch.cuda.get_device_properties(0).total_memory // (1024 ** 2)
-            return min(total_vram_mb, 100)
-        else:
-            return 100
-
-    budget = detect_available_budget(runtime_env)
-
-    best_model = None
-    best_speed = -1
-
-    for model, info in static_costs.items():
-        if info["size"] > budget:
-            continue
-        if use_local_only and info["type"] != "local":
-            continue
-        if use_api_only and info["type"] != "api":
-            continue
-        if info["tokens_sec"] > best_speed:
-            best_model = model
-            best_speed = info["tokens_sec"]
-
-    if not best_model:
-        return {
-            "model": "llama3.2",
-            "token_cost": static_costs["llama3.2"]["token_cost"],
-            "tokens_sec": static_costs["llama3.2"]["tokens_sec"],
-            "note": "Defaulted due to no models fitting filters"
-        }
-
-    return {
-        "model": best_model,
-        "token_cost": static_costs[best_model]["token_cost"],
-        "tokens_sec": static_costs[best_model]["tokens_sec"]
-    }
-EOF
-
-      - name: Commit and push if src/cost_benefit.py changed
+          cat > src/cost_benefit.py <<'PY'
+          import argparse
+          import subprocess
+          import time
+          import requests
+          
+          def detect_available_budget(runtime_env: str) -> int:
+              """
+              Return an approximate VRAM‑based budget (MB) when running locally,
+              else default to 100.
+              """
+              import torch
+              if "local" in runtime_env and torch.cuda.is_available():
+                  total_vram_mb = torch.cuda.get_device_properties(0).total_memory // (1024 ** 2)
+                  return min(total_vram_mb, 100)
+              return 100
+          
+          def get_best_model(runtime_env: str, *, use_local_only: bool = False, use_api_only: bool = False) -> dict:
+              """
+              Pick the fastest model that fits in the detected budget while
+              respecting the locality filters.
+              """
+              static_costs = {
+                  "llama3.2":  {"size": 20, "token_cost": 0.0001, "tokens_sec": 30, "type": "local"},
+                  "mistral":   {"size": 40, "token_cost": 0.0002, "tokens_sec": 50, "type": "local"},
+                  "gemini-2.0-flash":            {"size": 60, "token_cost": 0.0005, "tokens_sec": 60, "type": "api"},
+                  "gemini-2.5-pro-preview-03-25": {"size": 80, "token_cost": 0.002 , "tokens_sec": 45, "type": "api"},
+              }
+          
+              budget = detect_available_budget(runtime_env)
+              best_model, best_speed = None, -1
+          
+              for model, info in static_costs.items():
+                  if info["size"] > budget:
+                      continue
+                  if use_local_only and info["type"] != "local":
+                      continue
+                  if use_api_only and info["type"] != "api":
+                      continue
+                  if info["tokens_sec"] > best_speed:
+                      best_model, best_speed = model, info["tokens_sec"]
+          
+              chosen = best_model or "llama3.2"  # sensible default
+              return {
+                  "model": chosen,
+                  "token_cost": static_costs[chosen]["token_cost"],
+                  "tokens_sec": static_costs[chosen]["tokens_sec"],
+                  "note": None if best_model else "Defaulted because no model met the constraints",
+              }
+          PY
+
+      # only push when the workflow is triggered by a direct push to main
+      - name: Commit & push if the file changed
+        if: github.event_name == 'push' && github.ref == 'refs/heads/main'
         run: |
-          git config user.name "github-actions"
+          git config user.name  "github-actions"
           git config user.email "github-actions@github.com"
-
           if ! git diff --quiet src/cost_benefit.py; then
-            git add src/cost_benefit.py
-            git commit -m "Auto-restore src/cost_benefit.py"
-            git push
+            git add  src/cost_benefit.py
+            git commit -m "chore(ci): auto‑restore src/cost_benefit.py [skip ci]"
+            git push origin HEAD:main
           else
-            echo "No changes to src/cost_benefit.py"
-          fi
+            echo "No changes detected"