fix: scope e2e CI triggers, add temperature=0, fail on missing snapshots

- Scope e2e workflow to only trigger on pushes to e2e-tests branch
  (not every branch push)
- Add temperature=0 to remaining snapshot test chat calls for
  deterministic output
- Make assert_snapshot fail when no baseline exists instead of silently
  creating one — baselines must be explicitly generated with
  UPDATE_SNAPSHOTS=1

Co-Authored-By: Claude Opus 4.6 <[email protected]>

.github/workflows/e2e.yml

@@ -2,6 +2,8 @@ name: e2e-tests
 
 on:
   push:
+    branches:
+      - e2e-tests
   pull_request:
     branches:
       - staging

e2e/snapshot.py

@@ -1,8 +1,11 @@
 """Snapshot testing infrastructure for E2E tests.
 
 Provides deterministic regression testing by comparing inference output
-against saved snapshots. On first run, snapshots are created automatically.
-Set UPDATE_SNAPSHOTS=1 to regenerate snapshots when output intentionally changes.
+against committed baseline snapshots. Tests FAIL if no baseline exists —
+baselines must be explicitly generated and committed.
+
+Generate baselines: UPDATE_SNAPSHOTS=1 python3 e2e/run_all.py --slow
+Update after intentional changes: UPDATE_SNAPSHOTS=1 python3 e2e/run_all.py --slow
 
 Snapshots are stored per-architecture (e.g. snapshots/x86_64/, snapshots/arm64/)
 since floating-point results differ between CPU architectures.
@@ -40,7 +43,19 @@ def assert_snapshot(
     snapshot_file = SNAPSHOTS_DIR / f"{name}.json"
     update = os.environ.get("UPDATE_SNAPSHOTS") == "1"
 
-    if snapshot_file.exists() and not update:
+    if update:
+        # Explicitly regenerate snapshot
+        SNAPSHOTS_DIR.mkdir(parents=True, exist_ok=True)
+        snapshot_data = {**metadata, "arch": ARCH, "content": content}
+        snapshot_file.write_text(json.dumps(snapshot_data, indent=2) + "\n")
+        print(f"  Updated snapshot: {ARCH}/{snapshot_file.name}")
+    elif not snapshot_file.exists():
+        raise AssertionError(
+            f"No baseline snapshot for '{name}' on {ARCH}.\n"
+            f"Expected file: {snapshot_file}\n\n"
+            f"Generate baselines with: UPDATE_SNAPSHOTS=1 python3 e2e/run_all.py --slow"
+        )
+    else:
         snapshot = json.loads(snapshot_file.read_text())
         expected = snapshot["content"]
         if content != expected:
@@ -58,12 +73,6 @@ def assert_snapshot(
                 f"{diff}\n\n"
                 f"Expected: {expected!r}\n"
                 f"Actual:   {content!r}\n\n"
-                f"To update: UPDATE_SNAPSHOTS=1 python3 e2e/run_all.py"
+                f"To update: UPDATE_SNAPSHOTS=1 python3 e2e/run_all.py --slow"
             )
         print(f"  Output matches snapshot ({ARCH}/{snapshot_file.name})")
-    else:
-        SNAPSHOTS_DIR.mkdir(parents=True, exist_ok=True)
-        snapshot_data = {**metadata, "arch": ARCH, "content": content}
-        snapshot_file.write_text(json.dumps(snapshot_data, indent=2) + "\n")
-        action = "Updated" if update else "Created"
-        print(f"  {action} snapshot: {ARCH}/{snapshot_file.name}")

e2e/test_inference_snapshot.py

@@ -36,6 +36,7 @@ async def main():
             model=MODEL,
             messages=[{"role": "user", "content": PROMPT}],
             seed=SEED,
+            temperature=0,
             max_tokens=MAX_TOKENS,
         )
 

e2e/test_snapshot_multi_model.py

@@ -46,6 +46,7 @@ async def main():
                 model=model,
                 messages=[{"role": "user", "content": PROMPT}],
                 seed=SEED,
+                temperature=0,
                 max_tokens=MAX_TOKENS,
             )