fix(cli): pin pi compat flags for gateway models

Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>

litellm/proxy/client/cli/commands/pi.py

@@ -188,10 +188,13 @@ def provider_block(
 
     Real contextWindow/maxTokens matter: pi otherwise assumes 128k/16384, which
     breaks compaction thresholds and over-asks models with smaller output caps.
+    pi sniffs compat from the base URL, and one gateway URL fronts models with
+    different capabilities, so both flags are pinned off.
     """
     return {  # mutable-ok: JSON serialization requires a mutable object
         "baseUrl": base_url.rstrip("/") + "/v1",
         "api": "openai-completions",
+        "compat": {"supportsStore": False, "supportsLongCacheRetention": False},
         "apiKey": f"${LITELLM_PROXY_API_KEY_ENV}",
         "models": [_model_entry(model_id, limits) for model_id in model_ids],  # mutable-ok: JSON array
     }

tests/test_litellm/proxy/client/cli/test_pi.py

@@ -188,6 +188,7 @@ class TestProviderBlock:
         assert block == {
             "baseUrl": "http://localhost:4000/v1",
             "api": "openai-completions",
+            "compat": {"supportsStore": False, "supportsLongCacheRetention": False},
             "apiKey": "$LITELLM_PROXY_API_KEY",
             "models": [{"id": "m-1"}, {"id": "m-2"}],
         }