From ec337534c50cc152d442256347b95ce9042471ce Mon Sep 17 00:00:00 2001
From: Mason Daugherty <mason@langchain.dev>
Date: Wed, 22 Apr 2026 17:28:04 -0400
Subject: [PATCH] chore(partners): standardize integration test invocation
 (#36958)

Standardize the `integration_tests` Makefile target across all 15
partner packages in `libs/partners/`, mirroring the deepagents
`libs/evals` pattern (`-v --tb=short`). Previously each partner had its
own ad-hoc flag stack (some missing `-n auto`, some with `-vvv`, others
with nothing), and every partner that used `-n auto` was emitting a
`PytestBenchmarkWarning` because `pytest-benchmark` is pulled in
transitively via `langchain-tests` even though no partner has benchmark
tests.
---
 libs/partners/anthropic/Makefile   | 2 +-
 libs/partners/chroma/Makefile      | 2 +-
 libs/partners/deepseek/Makefile    | 2 +-
 libs/partners/exa/Makefile         | 7 +++++--
 libs/partners/fireworks/Makefile   | 2 +-
 libs/partners/groq/Makefile        | 2 +-
 libs/partners/huggingface/Makefile | 2 +-
 libs/partners/mistralai/Makefile   | 2 +-
 libs/partners/nomic/Makefile       | 7 +++++--
 libs/partners/ollama/Makefile      | 2 +-
 libs/partners/openai/Makefile      | 2 +-
 libs/partners/openrouter/Makefile  | 2 +-
 libs/partners/perplexity/Makefile  | 2 +-
 libs/partners/qdrant/Makefile      | 2 +-
 libs/partners/xai/Makefile         | 2 +-
 15 files changed, 23 insertions(+), 17 deletions(-)

diff --git a/libs/partners/anthropic/Makefile b/libs/partners/anthropic/Makefile
index 56428235c71..275e3470510 100644
--- a/libs/partners/anthropic/Makefile
+++ b/libs/partners/anthropic/Makefile
@@ -15,7 +15,7 @@ test tests:
 	uv run --group test pytest -vvv $(PYTEST_EXTRA) --disable-socket --allow-unix-socket $(TEST_FILE)
 
 integration_test integration_tests:
-	uv run --group test --group test_integration pytest -n auto -vvv --timeout 30 $(TEST_FILE)
+	uv run --group test --group test_integration pytest -v --tb=short -p no:benchmark -n auto --timeout 30 $(TEST_FILE)
 
 test_watch:
 	uv run --group test ptw --snapshot-update --now . -- -vv $(TEST_FILE)
diff --git a/libs/partners/chroma/Makefile b/libs/partners/chroma/Makefile
index 14eb48f6240..0617411c2ab 100644
--- a/libs/partners/chroma/Makefile
+++ b/libs/partners/chroma/Makefile
@@ -15,7 +15,7 @@ test tests:
 	uv run --group test pytest $(PYTEST_EXTRA) --disable-socket --allow-unix-socket $(TEST_FILE)
 
 integration_test integration_tests:
-	uv run --group test --group test_integration pytest $(TEST_FILE)
+	uv run --group test --group test_integration pytest -v --tb=short -p no:benchmark -n auto $(TEST_FILE)
 
 test_watch:
 	uv run --group test ptw --snapshot-update --now . -- -vv $(TEST_FILE)
diff --git a/libs/partners/deepseek/Makefile b/libs/partners/deepseek/Makefile
index 908f2da3628..0f85160ded5 100644
--- a/libs/partners/deepseek/Makefile
+++ b/libs/partners/deepseek/Makefile
@@ -21,7 +21,7 @@ test_watch:
 
 # integration tests are run without the --disable-socket flag to allow network calls
 integration_test integration_tests:
-	uv run --group test --group test_integration pytest --timeout=30 $(TEST_FILE)
+	uv run --group test --group test_integration pytest -v --tb=short -p no:benchmark -n auto --timeout=30 $(TEST_FILE)
 
 ######################
 # LINTING AND FORMATTING
diff --git a/libs/partners/exa/Makefile b/libs/partners/exa/Makefile
index ad85605b0a7..ca5a8a619e4 100644
--- a/libs/partners/exa/Makefile
+++ b/libs/partners/exa/Makefile
@@ -10,11 +10,14 @@ UV_FROZEN = true
 TEST_FILE ?= tests/unit_tests/
 PYTEST_EXTRA ?=
 
-integration_tests: TEST_FILE=tests/integration_tests/
+integration_test integration_tests: TEST_FILE=tests/integration_tests/
 
-test integration_tests:
+test:
 	uv run --group test --group test_integration pytest $(PYTEST_EXTRA) $(TEST_FILE)
 
+integration_test integration_tests:
+	uv run --group test --group test_integration pytest -v --tb=short -p no:benchmark -n auto $(PYTEST_EXTRA) $(TEST_FILE)
+
 tests:
 	uv run --group test pytest $(PYTEST_EXTRA) $(TEST_FILE)
 
diff --git a/libs/partners/fireworks/Makefile b/libs/partners/fireworks/Makefile
index 16d84d2af79..8749d427b3b 100644
--- a/libs/partners/fireworks/Makefile
+++ b/libs/partners/fireworks/Makefile
@@ -15,7 +15,7 @@ test tests:
 	uv run --group test pytest $(PYTEST_EXTRA) --disable-socket --allow-unix-socket $(TEST_FILE)
 
 integration_test integration_tests:
-	uv run --group test --group test_integration pytest -n auto $(TEST_FILE)
+	uv run --group test --group test_integration pytest -v --tb=short -p no:benchmark -n auto $(TEST_FILE)
 
 test_watch:
 	uv run --group test ptw --snapshot-update --now . -- -vv $(TEST_FILE)
diff --git a/libs/partners/groq/Makefile b/libs/partners/groq/Makefile
index b2ee3e49cae..345f2381bde 100644
--- a/libs/partners/groq/Makefile
+++ b/libs/partners/groq/Makefile
@@ -16,7 +16,7 @@ test tests:
 	uv run --group test pytest $(PYTEST_EXTRA) --disable-socket --allow-unix-socket $(TEST_FILE)
 
 integration_test integration_tests:
-	uv run --group test --group test_integration pytest --retries 3 --retry-delay 1 $(TEST_FILE)
+	uv run --group test --group test_integration pytest -v --tb=short -p no:benchmark -n auto --retries 3 --retry-delay 1 $(TEST_FILE)
 
 test_watch:
 	uv run --group test ptw --snapshot-update --now . -- -vv $(TEST_FILE)
diff --git a/libs/partners/huggingface/Makefile b/libs/partners/huggingface/Makefile
index fcc48416c38..7e32e2e0bf0 100644
--- a/libs/partners/huggingface/Makefile
+++ b/libs/partners/huggingface/Makefile
@@ -16,7 +16,7 @@ test tests:
 	uv run --group test pytest $(PYTEST_EXTRA) --disable-socket --allow-unix-socket $(TEST_FILE)
 
 integration_test integration_tests:
-	uv run --group test --group test_integration pytest $(TEST_FILE)
+	uv run --group test --group test_integration pytest -v --tb=short -p no:benchmark -n auto $(TEST_FILE)
 
 test_watch:
 	uv run --group test ptw --snapshot-update --now . -- -vv $(TEST_FILE)
diff --git a/libs/partners/mistralai/Makefile b/libs/partners/mistralai/Makefile
index d5d94e46c3c..b7fa018b6eb 100644
--- a/libs/partners/mistralai/Makefile
+++ b/libs/partners/mistralai/Makefile
@@ -21,7 +21,7 @@ test_watch:
 
 
 integration_test integration_tests:
-	uv run --group test --group test_integration pytest $(TEST_FILE)
+	uv run --group test --group test_integration pytest -v --tb=short -p no:benchmark -n auto $(TEST_FILE)
 
 
 ######################
diff --git a/libs/partners/nomic/Makefile b/libs/partners/nomic/Makefile
index 14c3bc07ac8..8b99758fe30 100644
--- a/libs/partners/nomic/Makefile
+++ b/libs/partners/nomic/Makefile
@@ -10,11 +10,14 @@ UV_FROZEN = true
 TEST_FILE ?= tests/unit_tests/
 PYTEST_EXTRA ?=
 
-integration_tests: TEST_FILE = tests/integration_tests/
+integration_test integration_tests: TEST_FILE = tests/integration_tests/
 
-test integration_tests:
+test:
 	uv run --group test --group test_integration pytest $(PYTEST_EXTRA) $(TEST_FILE)
 
+integration_test integration_tests:
+	uv run --group test --group test_integration pytest -v --tb=short -p no:benchmark -n auto $(PYTEST_EXTRA) $(TEST_FILE)
+
 tests:
 	uv run --group test pytest $(PYTEST_EXTRA) $(TEST_FILE)
 
diff --git a/libs/partners/ollama/Makefile b/libs/partners/ollama/Makefile
index fecb6fe66c2..f3e8952e115 100644
--- a/libs/partners/ollama/Makefile
+++ b/libs/partners/ollama/Makefile
@@ -27,7 +27,7 @@ test_watch:
 
 # integration tests are run without the --disable-socket flag to allow network calls
 integration_test:
-	OLLAMA_TEST_MODEL=$(OLLAMA_TEST_MODEL) OLLAMA_REASONING_TEST_MODEL=$(OLLAMA_REASONING_TEST_MODEL) uv run --group test --group test_integration pytest $(TEST_FILE)
+	OLLAMA_TEST_MODEL=$(OLLAMA_TEST_MODEL) OLLAMA_REASONING_TEST_MODEL=$(OLLAMA_REASONING_TEST_MODEL) uv run --group test --group test_integration pytest -v --tb=short -p no:benchmark -n auto $(TEST_FILE)
 
 # CI integration tests - disabled until ollama service is configured in CI
 
diff --git a/libs/partners/openai/Makefile b/libs/partners/openai/Makefile
index 2bf160b45ed..7ba6631f0c5 100644
--- a/libs/partners/openai/Makefile
+++ b/libs/partners/openai/Makefile
@@ -25,7 +25,7 @@ test tests:
 	TIKTOKEN_CACHE_DIR=tiktoken_cache uv run --group test pytest $(PYTEST_EXTRA) --disable-socket --allow-unix-socket $(TEST_FILE)
 
 integration_test integration_tests:
-	uv run --group test --group test_integration pytest -n auto $(TEST_FILE)
+	uv run --group test --group test_integration pytest -v --tb=short -p no:benchmark -n auto $(TEST_FILE)
 
 # Run VCR cassette-backed integration tests in playback-only mode (no API keys needed).
 # Catches stale cassettes caused by test input changes without re-recording.
diff --git a/libs/partners/openrouter/Makefile b/libs/partners/openrouter/Makefile
index eff6f358884..b6c362021e5 100644
--- a/libs/partners/openrouter/Makefile
+++ b/libs/partners/openrouter/Makefile
@@ -21,7 +21,7 @@ test_watch:
 
 # integration tests are run without the --disable-socket flag to allow network calls
 integration_test integration_tests:
-	uv run --group test --group test_integration pytest --timeout=120 $(TEST_FILE)
+	uv run --group test --group test_integration pytest -v --tb=short -p no:benchmark -n auto --timeout=120 $(TEST_FILE)
 
 ######################
 # LINTING AND FORMATTING
diff --git a/libs/partners/perplexity/Makefile b/libs/partners/perplexity/Makefile
index bc3581a23b0..0e06499ba84 100644
--- a/libs/partners/perplexity/Makefile
+++ b/libs/partners/perplexity/Makefile
@@ -19,7 +19,7 @@ test_watch:
 	uv run --group test ptw --snapshot-update --now . -- -vv $(TEST_FILE)
 
 integration_test integration_tests:
-	uv run --group test --group test_integration pytest $(TEST_FILE)
+	uv run --group test --group test_integration pytest -v --tb=short -p no:benchmark -n auto $(TEST_FILE)
 
 ######################
 # LINTING AND FORMATTING
diff --git a/libs/partners/qdrant/Makefile b/libs/partners/qdrant/Makefile
index 3cd8c7989d0..8c79429edac 100644
--- a/libs/partners/qdrant/Makefile
+++ b/libs/partners/qdrant/Makefile
@@ -16,7 +16,7 @@ test tests:
 	uv run --group test pytest $(PYTEST_EXTRA) --disable-socket --allow-unix-socket $(TEST_FILE)
 
 integration_test integration_tests:
-	uv run --group test --group test_integration pytest $(TEST_FILE)
+	uv run --group test --group test_integration pytest -v --tb=short -p no:benchmark -n auto $(TEST_FILE)
 
 test_watch:
 	uv run --group test ptw --snapshot-update --now . -- -vv $(TEST_FILE)
diff --git a/libs/partners/xai/Makefile b/libs/partners/xai/Makefile
index 93729819edc..bd41b6a2e83 100644
--- a/libs/partners/xai/Makefile
+++ b/libs/partners/xai/Makefile
@@ -19,7 +19,7 @@ test_watch:
 	uv run --group test ptw --snapshot-update --now . -- -vv $(TEST_FILE)
 
 integration_test integration_tests:
-	uv run --group test --group test_integration pytest $(TEST_FILE)
+	uv run --group test --group test_integration pytest -v --tb=short -p no:benchmark -n auto $(TEST_FILE)
 
 ######################
 # LINTING AND FORMATTING