refactor: migrate legacy resource markers to predicates

planetf1 · planetf1 · commit 3b09d33d398e · 2026-03-26T14:37:23.000Z
Replace deprecated pytest markers with typed predicate functions from
test/predicates.py across all test files and example files:

- requires_gpu → require_gpu(min_vram_gb=N) with per-model VRAM estimates
- requires_heavy_ram → removed (conflated VRAM with RAM; no replacement needed)
- requires_gpu_isolation → removed (GPU isolation is now automatic)
- requires_api_key → require_api_key("VAR1", "VAR2", ...) with explicit env vars

Also removes spurious requires_gpu from ollama-backed tests (test_genslot,
test_think_budget_forcing, test_component_typing) and adds missing
integration marker to test_hook_call_sites.

VRAM estimates computed from model parameter counts using bf16 formula
(params_B × 2 × 1.2, rounded up to next even GB):
- granite-3.3-8b: 20 GB, Mistral-7B: 18 GB, granite-4.0-micro (3B): 8 GB
- Qwen3-0.6B: 4 GB (conservative for vLLM KV cache headroom)
- granite-4.0-h-micro (3B): 8 GB, alora training (3B): 12 GB
diff --git a/docs/examples/aLora/101_example.py b/docs/examples/aLora/101_example.py
@@ -1,4 +1,4 @@
-# pytest: huggingface, requires_heavy_ram, e2e
+# pytest: huggingface, e2e
 
 import time
 
diff --git a/docs/examples/aLora/102_example.py b/docs/examples/aLora/102_example.py
@@ -1,4 +1,4 @@
-# pytest: skip, huggingface, requires_heavy_ram, e2e
+# pytest: skip, huggingface, e2e
 # SKIP REASON: Requires user input; tests same functionality as 101_example.py.
 
 from stembolts_intrinsic import (
diff --git a/docs/examples/aLora/example_readme_generator.py b/docs/examples/aLora/example_readme_generator.py
@@ -1,4 +1,4 @@
-# pytest: skip, huggingface, requires_heavy_ram, e2e
+# pytest: skip, huggingface, e2e
 # SKIP REASON: documentation only.
 
 from cli.alora.readme_generator import generate_readme, make_readme_jinja_dict
diff --git a/docs/examples/aLora/make_training_data.py b/docs/examples/aLora/make_training_data.py
@@ -1,4 +1,4 @@
-# pytest: skip, huggingface, requires_heavy_ram, e2e
+# pytest: skip, huggingface, e2e
 # SKIP REASON: documentation only.import argparse
 import argparse
 import json
diff --git a/docs/examples/aLora/stembolts_intrinsic.py b/docs/examples/aLora/stembolts_intrinsic.py
@@ -1,5 +1,5 @@
 # type: ignore
-# pytest: skip, huggingface, requires_heavy_ram, e2e
+# pytest: skip, huggingface, e2e
 # SKIP REASON: needs to update.
 
 import mellea.stdlib.functional as mfuncs
diff --git a/docs/examples/image_text_models/vision_openai_examples.py b/docs/examples/image_text_models/vision_openai_examples.py
@@ -1,4 +1,4 @@
-# pytest: ollama, e2e, requires_heavy_ram
+# pytest: ollama, e2e
 
 """Examples using vision models with OpenAI backend."""
 
diff --git a/docs/examples/intrinsics/answerability.py b/docs/examples/intrinsics/answerability.py
@@ -1,4 +1,4 @@
-# pytest: huggingface, requires_heavy_ram, e2e
+# pytest: huggingface, e2e
 
 """Example usage of the answerability intrinsic for RAG applications.
 
diff --git a/docs/examples/intrinsics/citations.py b/docs/examples/intrinsics/citations.py
@@ -1,4 +1,4 @@
-# pytest: huggingface, requires_heavy_ram, e2e
+# pytest: huggingface, e2e
 
 """Example usage of the citations intrinsic for RAG applications.
 
diff --git a/docs/examples/intrinsics/context_attribution.py b/docs/examples/intrinsics/context_attribution.py
@@ -1,4 +1,4 @@
-# pytest: huggingface, requires_heavy_ram, e2e
+# pytest: huggingface, e2e
 
 """Example usage of the context attribution intrinsic.
 
diff --git a/docs/examples/intrinsics/context_relevance.py b/docs/examples/intrinsics/context_relevance.py
@@ -1,4 +1,4 @@
-# pytest: huggingface, requires_heavy_ram, e2e
+# pytest: huggingface, e2e
 
 """Example usage of the context relevance intrinsic for RAG applications.
 
diff --git a/docs/examples/intrinsics/factuality_correction.py b/docs/examples/intrinsics/factuality_correction.py
@@ -1,4 +1,4 @@
-# pytest: huggingface, requires_heavy_ram, e2e
+# pytest: huggingface, e2e
 
 """Example usage of the factuality correction intrinsic.
 
diff --git a/docs/examples/intrinsics/factuality_detection.py b/docs/examples/intrinsics/factuality_detection.py
@@ -1,4 +1,4 @@
-# pytest: huggingface, requires_heavy_ram, e2e
+# pytest: huggingface, e2e
 
 """Example usage of the factuality detection intrinsic.
 
diff --git a/docs/examples/intrinsics/guardian_core.py b/docs/examples/intrinsics/guardian_core.py
@@ -1,4 +1,4 @@
-# pytest: huggingface, requires_heavy_ram, e2e
+# pytest: huggingface, e2e
 
 """Example usage of the guardian-core intrinsic for safety and hallucination detection.
 
diff --git a/docs/examples/intrinsics/hallucination_detection.py b/docs/examples/intrinsics/hallucination_detection.py
@@ -1,4 +1,4 @@
-# pytest: huggingface, requires_heavy_ram, e2e
+# pytest: huggingface, e2e
 
 """Example usage of the hallucination detection intrinsic for RAG applications.
 
diff --git a/docs/examples/intrinsics/intrinsics.py b/docs/examples/intrinsics/intrinsics.py
@@ -1,4 +1,4 @@
-# pytest: huggingface, requires_heavy_ram, e2e
+# pytest: huggingface, e2e
 
 import mellea.stdlib.functional as mfuncs
 from mellea.backends.adapters.adapter import AdapterType, IntrinsicAdapter
diff --git a/docs/examples/intrinsics/policy_guardrails.py b/docs/examples/intrinsics/policy_guardrails.py
@@ -1,4 +1,4 @@
-# pytest: huggingface, requires_heavy_ram, e2e
+# pytest: huggingface, e2e
 
 """Example usage of the policy_guardrails intrinsic.
 
diff --git a/docs/examples/intrinsics/query_clarification.py b/docs/examples/intrinsics/query_clarification.py
@@ -1,4 +1,4 @@
-# pytest: huggingface, requires_heavy_ram, e2e
+# pytest: huggingface, e2e
 """
 Example usage of the query clarification intrinsic for RAG applications.
 
diff --git a/docs/examples/intrinsics/query_rewrite.py b/docs/examples/intrinsics/query_rewrite.py
@@ -1,4 +1,4 @@
-# pytest: huggingface, requires_heavy_ram, e2e
+# pytest: huggingface, e2e
 
 """Example usage of the query rewrite intrinsic for RAG applications.
 
diff --git a/docs/examples/intrinsics/requirement_check.py b/docs/examples/intrinsics/requirement_check.py
@@ -1,4 +1,4 @@
-# pytest: huggingface, requires_heavy_ram, e2e
+# pytest: huggingface, e2e
 
 """Example usage of the requirement check intrinsic.
 
diff --git a/docs/examples/intrinsics/uncertainty.py b/docs/examples/intrinsics/uncertainty.py
@@ -1,4 +1,4 @@
-# pytest: huggingface, requires_heavy_ram, e2e
+# pytest: huggingface, e2e
 
 """Example usage of the uncertainty/certainty intrinsic.
 
diff --git a/docs/examples/mify/rich_document_advanced.py b/docs/examples/mify/rich_document_advanced.py
@@ -1,4 +1,4 @@
-# pytest: skip, huggingface, requires_heavy_ram, e2e
+# pytest: skip, huggingface, e2e
 # SKIP REASON: CXXABI_1.3.15 not found - conda environment issue on HPC systems with old glibc
 
 # ruff: noqa E402
diff --git a/docs/examples/safety/guardian_huggingface.py b/docs/examples/safety/guardian_huggingface.py
@@ -1,4 +1,4 @@
-# pytest: ollama, huggingface, requires_heavy_ram, e2e
+# pytest: ollama, huggingface, e2e
 
 """Example of using GuardianCheck with HuggingFace backend for direct model inference
 
diff --git a/docs/examples/safety/repair_with_guardian.py b/docs/examples/safety/repair_with_guardian.py
@@ -1,4 +1,4 @@
-# pytest: ollama, huggingface, requires_heavy_ram, e2e
+# pytest: ollama, huggingface, e2e
 
 """RepairTemplateStrategy Example with Actual Function Call Validation
 Demonstrates how RepairTemplateStrategy repairs responses using actual function calls.
diff --git a/docs/examples/sofai/sofai_graph_coloring.py b/docs/examples/sofai/sofai_graph_coloring.py
@@ -1,4 +1,4 @@
-# pytest: ollama, qualitative, e2e, requires_heavy_ram
+# pytest: ollama, qualitative, e2e
 
 """SOFAI Sampling Strategy Example: Graph Coloring Problem.
 
diff --git a/docs/examples/tutorial/document_mobject.py b/docs/examples/tutorial/document_mobject.py
@@ -1,4 +1,4 @@
-# pytest: ollama, qualitative, e2e, requires_heavy_ram
+# pytest: ollama, qualitative, e2e
 
 from mellea.backends import model_ids
 from mellea.backends.model_ids import IBM_GRANITE_4_HYBRID_MICRO
diff --git a/test/backends/test_huggingface.py b/test/backends/test_huggingface.py
@@ -13,13 +13,13 @@
 import pytest
 import torch
 
+from test.predicates import require_gpu
+
 # Mark all tests in this module with backend and resource requirements
 pytestmark = [
     pytest.mark.huggingface,
     pytest.mark.e2e,
-    pytest.mark.requires_gpu,
-    pytest.mark.requires_heavy_ram,
-    pytest.mark.requires_gpu_isolation,  # Activate GPU memory isolation
+    require_gpu(min_vram_gb=20),
     # Skip entire module in CI since 17/18 tests are qualitative
     pytest.mark.skipif(
         int(os.environ.get("CICD", 0)) == 1,
diff --git a/test/backends/test_huggingface_tools.py b/test/backends/test_huggingface_tools.py
@@ -3,14 +3,13 @@
 import pytest
 
 from mellea.backends.tools import MelleaTool
+from test.predicates import require_gpu
 
 # Skip entire module in CI since the single test is qualitative
 pytestmark = [
     pytest.mark.huggingface,
     pytest.mark.e2e,
-    pytest.mark.requires_gpu,
-    pytest.mark.requires_heavy_ram,
-    pytest.mark.requires_gpu_isolation,
+    require_gpu(min_vram_gb=18),
     pytest.mark.skipif(
         int(os.environ.get("CICD", 0)) == 1,
         reason="Skipping HuggingFace tools tests in CI - qualitative test",
diff --git a/test/backends/test_litellm_watsonx.py b/test/backends/test_litellm_watsonx.py
@@ -2,12 +2,14 @@
 
 import pytest
 
+from test.predicates import require_api_key
+
 # Mark all tests in this module as requiring Watsonx via LiteLLM
 pytestmark = [
     pytest.mark.litellm,
     pytest.mark.watsonx,
     pytest.mark.e2e,
-    pytest.mark.requires_api_key,
+    require_api_key("WATSONX_API_KEY", "WATSONX_URL", "WATSONX_PROJECT_ID"),
 ]
 
 from mellea import MelleaSession
diff --git a/test/backends/test_openai_vllm.py b/test/backends/test_openai_vllm.py
@@ -9,13 +9,14 @@
 import pytest
 import requests
 
+from test.predicates import require_gpu
+
 # Mark all tests in this module with backend and resource requirements
 pytestmark = [
     pytest.mark.openai,
     pytest.mark.e2e,
     pytest.mark.vllm,
-    pytest.mark.requires_gpu,
-    pytest.mark.requires_heavy_ram,
+    require_gpu(min_vram_gb=8),
     # Skip entire module in CI since all 8 tests are qualitative
     pytest.mark.skipif(
         int(os.environ.get("CICD", 0)) == 1,
diff --git a/test/backends/test_vllm.py b/test/backends/test_vllm.py
@@ -5,13 +5,13 @@
 import pydantic
 import pytest
 
+from test.predicates import require_gpu
+
 # Mark all tests in this module with backend and resource requirements
 pytestmark = [
     pytest.mark.vllm,
     pytest.mark.e2e,
-    pytest.mark.requires_gpu,
-    pytest.mark.requires_heavy_ram,
-    pytest.mark.requires_gpu_isolation,  # Activate GPU memory isolation
+    require_gpu(min_vram_gb=4),
     # Skip entire module in CI since all 8 tests are qualitative
     pytest.mark.skipif(
         int(os.environ.get("CICD", 0)) == 1,
diff --git a/test/backends/test_vllm_tools.py b/test/backends/test_vllm_tools.py
@@ -3,14 +3,13 @@
 import pytest
 
 from mellea.backends.tools import MelleaTool
+from test.predicates import require_gpu
 
 # Skip entire module in CI since the single test is qualitative
 pytestmark = [
     pytest.mark.vllm,
     pytest.mark.e2e,
-    pytest.mark.requires_gpu,
-    pytest.mark.requires_heavy_ram,
-    pytest.mark.requires_gpu_isolation,
+    require_gpu(min_vram_gb=18),
     pytest.mark.skipif(
         int(os.environ.get("CICD", 0)) == 1,
         reason="Skipping vLLM tools tests in CI - qualitative test",
diff --git a/test/backends/test_watsonx.py b/test/backends/test_watsonx.py
@@ -5,11 +5,13 @@
 import pydantic
 import pytest
 
+from test.predicates import require_api_key
+
 # Mark all tests in this module with backend and auth requirements
 pytestmark = [
     pytest.mark.watsonx,
     pytest.mark.e2e,
-    pytest.mark.requires_api_key,
+    require_api_key("WATSONX_API_KEY", "WATSONX_URL", "WATSONX_PROJECT_ID"),
     # Skip entire module in CI since 8/9 tests are qualitative
     pytest.mark.skipif(
         int(os.environ.get("CICD", 0)) == 1,
diff --git a/test/cli/test_alora_train_integration.py b/test/cli/test_alora_train_integration.py
@@ -14,11 +14,12 @@
 import torch
 from transformers import AutoTokenizer
 
+from test.predicates import require_gpu
+
 pytestmark = [
     pytest.mark.huggingface,
     pytest.mark.e2e,
-    pytest.mark.requires_gpu,
-    pytest.mark.requires_heavy_ram,
+    require_gpu(min_vram_gb=12),
     # Skip entire module in CI since 17/18 tests are qualitative
     pytest.mark.skipif(
         int(os.environ.get("CICD", 0)) == 1,
diff --git a/test/core/test_component_typing.py b/test/core/test_component_typing.py
@@ -120,7 +120,6 @@ def test_incorrect_type_override():
 # Uses granite4:micro-h (3B hybrid, lightweight) in local mode
 @pytest.mark.qualitative
 @pytest.mark.ollama
-@pytest.mark.requires_gpu
 @pytest.mark.e2e
 async def test_generating(session):
     m = session
@@ -163,8 +162,6 @@ async def test_generating(session):
 
 @pytest.mark.qualitative
 @pytest.mark.ollama
-@pytest.mark.requires_gpu
-@pytest.mark.requires_heavy_ram
 @pytest.mark.e2e
 def test_message_typing(session):
     m = session
@@ -180,8 +177,6 @@ def test_message_typing(session):
 
 @pytest.mark.qualitative
 @pytest.mark.ollama
-@pytest.mark.requires_gpu
-@pytest.mark.requires_heavy_ram
 @pytest.mark.e2e
 async def test_generating_with_sampling(session):
     m = session
diff --git a/test/plugins/test_hook_call_sites.py b/test/plugins/test_hook_call_sites.py
@@ -16,6 +16,8 @@
 
 import pytest
 
+pytestmark = pytest.mark.integration
+
 pytest.importorskip("cpex.framework")
 
 from mellea.core.backend import Backend
diff --git a/test/stdlib/components/intrinsic/test_core.py b/test/stdlib/components/intrinsic/test_core.py
@@ -12,6 +12,7 @@
 from mellea.stdlib.components import Document, Message
 from mellea.stdlib.components.intrinsic import core
 from mellea.stdlib.context import ChatContext
+from test.predicates import require_gpu
 from test.stdlib.components.intrinsic.test_rag import (
     _read_input_json as _read_rag_input_json,
     _read_output_json as _read_rag_output_json,
@@ -24,8 +25,7 @@
         reason="Skipping core intrinsic tests in CI - all qualitative tests",
     ),
     pytest.mark.huggingface,
-    pytest.mark.requires_gpu,
-    pytest.mark.requires_heavy_ram,
+    require_gpu(min_vram_gb=8),
     pytest.mark.e2e,
 ]
 
diff --git a/test/stdlib/components/intrinsic/test_guardian.py b/test/stdlib/components/intrinsic/test_guardian.py
@@ -13,6 +13,7 @@
 from mellea.stdlib.components import Message
 from mellea.stdlib.components.intrinsic import guardian
 from mellea.stdlib.context import ChatContext
+from test.predicates import require_gpu
 
 # Skip entire module in CI since all tests are qualitative
 pytestmark = [
@@ -21,8 +22,7 @@
         reason="Skipping Guardian tests in CI - all qualitative tests",
     ),
     pytest.mark.huggingface,
-    pytest.mark.requires_gpu,
-    pytest.mark.requires_heavy_ram,
+    require_gpu(min_vram_gb=8),
     pytest.mark.e2e,
 ]
 
diff --git a/test/stdlib/components/intrinsic/test_rag.py b/test/stdlib/components/intrinsic/test_rag.py
@@ -13,6 +13,7 @@
 from mellea.stdlib.components import Document, Message
 from mellea.stdlib.components.intrinsic import rag
 from mellea.stdlib.context import ChatContext
+from test.predicates import require_gpu
 
 # Skip entire module in CI since all 7 tests are qualitative
 pytestmark = [
@@ -21,8 +22,7 @@
         reason="Skipping RAG tests in CI - all qualitative tests",
     ),
     pytest.mark.huggingface,
-    pytest.mark.requires_gpu,
-    pytest.mark.requires_heavy_ram,  # 3B model + document processing needs ~30-35GB
+    require_gpu(min_vram_gb=8),
     pytest.mark.e2e,
 ]
 
diff --git a/test/stdlib/components/test_genslot.py b/test/stdlib/components/test_genslot.py
@@ -18,7 +18,7 @@
 from mellea.stdlib.sampling import RejectionSamplingStrategy
 
 # Module-level markers: Uses granite4:micro-h (3B hybrid, lightweight) in local mode
-pytestmark = [pytest.mark.ollama, pytest.mark.requires_gpu, pytest.mark.e2e]
+pytestmark = [pytest.mark.ollama, pytest.mark.e2e]
 
 
 @pytest.fixture(scope="module")
diff --git a/test/stdlib/sampling/test_think_budget_forcing.py b/test/stdlib/sampling/test_think_budget_forcing.py
@@ -11,13 +11,7 @@
 MODEL_ID = OPENAI_GPT_OSS_20B
 
 # Module-level markers: gpt-oss:20b is a 20B model requiring heavy resources
-pytestmark = [
-    pytest.mark.ollama,
-    pytest.mark.requires_gpu,
-    pytest.mark.requires_heavy_ram,
-    pytest.mark.e2e,
-    pytest.mark.qualitative,
-]
+pytestmark = [pytest.mark.ollama, pytest.mark.e2e, pytest.mark.qualitative]
 
 
 @pytest.fixture(scope="module")
diff --git a/test/stdlib/test_session.py b/test/stdlib/test_session.py
diff --git a/test/stdlib/test_spans.py b/test/stdlib/test_spans.py
diff --git a/test/telemetry/test_metrics_backend.py b/test/telemetry/test_metrics_backend.py

Original file line number	Diff line number	Diff line change
`@@ -1,4 +1,4 @@`
`1`		`-# pytest: huggingface, requires_heavy_ram, e2e`
	`1`	`+# pytest: huggingface, e2e`
`2`	`2`
`3`	`3`	`import time`
`4`	`4`
Original file line number	Diff line number	Diff line change
`@@ -1,4 +1,4 @@`
`1`		`-# pytest: skip, huggingface, requires_heavy_ram, e2e`
	`1`	`+# pytest: skip, huggingface, e2e`
`2`	`2`	`# SKIP REASON: Requires user input; tests same functionality as 101_example.py.`
`3`	`3`
`4`	`4`	`from stembolts_intrinsic import (`
Original file line number	Diff line number	Diff line change
`@@ -1,4 +1,4 @@`
`1`		`-# pytest: ollama, e2e, requires_heavy_ram`
	`1`	`+# pytest: ollama, e2e`
`2`	`2`
`3`	`3`	`"""Examples using vision models with OpenAI backend."""`
`4`	`4`