fix(cli): pin pi compat flags so lite pi stops sending store to Anthropic models (#40739)

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

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

* fix(cli): annotate pi compatibility field

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

* fix(cli): clarify pi compatibility suppression

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

* fix(cli): drop the stale mutable-ok suppression on the pi compat block

---------

Co-authored-by: jesus <jesus@berri.ai>
Co-authored-by: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
Co-authored-by: mateo-berri <277851410+mateo-berri@users.noreply.github.com>

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

@@ -190,10 +190,16 @@ 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 {
         "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],
     }

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

@@ -195,6 +195,7 @@ 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"}],
         }