From c5c5154c4b68ca810fbb02bfc42f90f7e2d4b3e7 Mon Sep 17 00:00:00 2001 From: "devin-ai-integration[bot]" <158243242+devin-ai-integration[bot]@users.noreply.github.com> Date: Thu, 8 Oct 2026 18:30:27 -0700 Subject: [PATCH] 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 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 | 6 ++++++ tests/unit/proxy/client/cli/test_pi.py | 1 + 2 files changed, 7 insertions(+) diff --git a/litellm/proxy/client/cli/commands/pi.py b/litellm/proxy/client/cli/commands/pi.py index 22c9755ab8e..4cb2372e07e 100644 --- a/litellm/proxy/client/cli/commands/pi.py +++ b/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"${LITELLM_PROXY_API_KEY_ENV}", "models": [_model_entry(model_id, limits) for model_id in model_ids], } diff --git a/tests/unit/proxy/client/cli/test_pi.py b/tests/unit/proxy/client/cli/test_pi.py index 6bb49566580..ff4dc25cd0c 100644 --- a/tests/unit/proxy/client/cli/test_pi.py +++ b/tests/unit/proxy/client/cli/test_pi.py @@ -195,6 +195,7 @@ class TestProviderBlock: assert block == { "baseUrl": "http://localhost:4000/v1", "api": "openai-completions", + "compat": {"supportsStore": False, "supportsLongCacheRetention": False}, "apiKey": "$LITELLM_PROXY_API_KEY", "models": [{"id": "m-1"}, {"id": "m-2"}], }