[LEADS-225] Align lint checks with LSC

Makefile

@@ -23,10 +23,10 @@ update-deps: ## Check pyproject.toml for changes, update the lock file if needed
 	uv sync --group dev
 
 check-types: ## Checks type hints in sources
-	uv run mypy --explicit-package-bases --disallow-untyped-calls --disallow-untyped-defs --disallow-incomplete-defs src/ lsc_agent_eval/src/ tests
+	uv run mypy src/ lsc_agent_eval/src/ tests
 
 black-check:
-	uv run black src tests script lsc_agent_eval --check
+	uv run black --check src tests script lsc_agent_eval
 
 black-format:
 	uv run black src tests script lsc_agent_eval
@@ -118,7 +118,7 @@ shellcheck: ## Run shellcheck
 
 pylint:
 	uv run pylint src
-	uv run pylint --disable=R0801 lsc_agent_eval/src tests
+	uv run pylint lsc_agent_eval/src tests
 
 pyright:
 	uv run pyright src lsc_agent_eval/src tests
@@ -130,4 +130,4 @@ ruff:
 	uv run ruff check src tests script lsc_agent_eval
 
 bandit: ## Security scanning with Bandit
-	uv run bandit -r src/lightspeed_evaluation -ll
+	uv run bandit -c pyproject.toml -r src/lightspeed_evaluation -ll

lsc_agent_eval/src/lsc_agent_eval/core/agent_goal_eval/evaluator.py

@@ -6,7 +6,7 @@
 from ..utils.exceptions import AgentAPIError, JudgeModelError, ScriptExecutionError
 from ..utils.prompt import ANSWER_CORRECTNESS_PROMPT, INTENT_DETECTION_PROMPT
 from .tool_call_eval import compare_tool_calls
-from .utils import create_evaluation_results
+from .utils import EvalResultItem, create_evaluation_results
 
 if TYPE_CHECKING:
     from ..utils.api_client import AgentHttpClient
@@ -42,12 +42,13 @@ def run_evaluation(  # pylint: disable=too-many-arguments,too-many-positional-ar
         """Run multiple evaluations based on configuration."""
         try:
             # Query the agent once
-            api_input = {
+            api_input: dict[str, str] = {
                 "query": data_config.eval_query,
                 "provider": agent_provider,
                 "model": agent_model,
-                "conversation_id": conversation_id,
             }
+            if conversation_id is not None:
+                api_input["conversation_id"] = conversation_id
 
             if endpoint_type == "streaming":
                 agent_response = self.agent_client.streaming_query_agent(api_input)
@@ -61,7 +62,7 @@ def run_evaluation(  # pylint: disable=too-many-arguments,too-many-positional-ar
             tool_calls = agent_response.get("tool_calls", [])
 
             # Run all evaluations
-            evaluation_results = []
+            evaluation_results: list[EvalResultItem] = []
             for eval_type in data_config.eval_types:
                 try:
                     success = self._evaluate_single_type(

lsc_agent_eval/src/lsc_agent_eval/core/agent_goal_eval/results.py

@@ -2,7 +2,7 @@
 
 import json
 import logging
-from datetime import datetime
+from datetime import UTC, datetime
 from pathlib import Path
 
 import pandas as pd
@@ -32,7 +32,7 @@ def save_results(self, result_dir: str) -> None:
             output_dir = Path(result_dir)
             output_dir.mkdir(parents=True, exist_ok=True)
 
-            timestamp = datetime.now().strftime("%Y%m%d_%H%M%S")
+            timestamp = datetime.now(UTC).strftime("%Y%m%d_%H%M%S")
             csv_file = output_dir / f"agent_goal_eval_results_{timestamp}.csv"
             json_file = output_dir / f"agent_goal_eval_summary_{timestamp}.json"
 

pyproject.toml

@@ -66,6 +66,7 @@ dev = [
     "pytest-cov>=6.0.0,<=6.2.1",
     "pytest-mock==3.15.1",
     "pytest-timeout==2.4.0",
+    "types-PyYAML>=6.0.0",
 ]
 
 [project.scripts]
@@ -75,32 +76,39 @@ generate_answers = "generate_answers.generate_answers:main"
 # Note: torch[cpu] variant configuration removed for uv compatibility
 # Modern PyTorch versions are available on PyPI directly
 
-[tool.isort]
-src_paths = ["src", "tests"]
-
 [tool.black]
 line-length = 88
 
 [tool.pydocstyle]
 convention = "google"
 
 [tool.mypy]
-disable_error_code = ["union-attr", "return-value", "arg-type", "import-untyped"]
-ignore_missing_imports = true
 plugins = ["pydantic.mypy"]
+explicit_package_bases = true
+disallow_untyped_calls = true
+disallow_untyped_defs = true
+disallow_incomplete_defs = true
+ignore_missing_imports = true
 
 [tool.pydantic-mypy]
 init_forbid_extra = true
 init_typed = true
 warn_required_dynamic_aliases = true
 
 [tool.pylint.MASTER]
+source-roots = ["src", "script", "tests"]
 load-plugins = ["pylint_pydantic"]
 init-hook = "import sys; sys.path.append('.')"
+[tool.pylint."MESSAGES CONTROL"]
+disable = ["R0801"]
+
+[tool.pyright]
+extraPaths = ["./src"]
 
 [tool.ruff]
+line-length = 88
 [tool.ruff.lint]
-extend-select = ["TID251"]
+extend-select = ["TID251", "UP006", "UP007", "UP010", "UP017", "UP035", "RUF100", "B009", "B010", "DTZ005", "D202", "I001", "PLR1733"]
 [tool.ruff.lint.flake8-tidy-imports.banned-api]
 unittest = { msg = "use pytest instead of unittest" }
 "unittest.mock" = { msg = "use pytest-mock instead of unittest.mock" }

requirements-all-extras.txt

@@ -117,13 +117,13 @@ googleapis-common-protos==1.75.0
     #   grpcio-status
 greenlet==3.5.1 ; platform_machine == 'AMD64' or platform_machine == 'WIN32' or platform_machine == 'aarch64' or platform_machine == 'amd64' or platform_machine == 'ppc64le' or platform_machine == 'win32' or platform_machine == 'x86_64'
     # via sqlalchemy
-grpcio==1.80.0
+grpcio==1.81.0
     # via
     #   deepeval
     #   google-ai-generativelanguage
     #   google-api-core
     #   grpcio-status
-grpcio-status==1.80.0
+grpcio-status==1.81.0
     # via google-api-core
 h11==0.16.0
     # via httpcore
@@ -148,7 +148,7 @@ huggingface-hub==1.16.1
     #   sentence-transformers
     #   tokenizers
     #   transformers
-idna==3.16
+idna==3.17
     # via
     #   anyio
     #   httpx
@@ -210,7 +210,7 @@ langchain-huggingface==1.2.2
     # via langchain
 langchain-openai==1.1.10
     # via ragas
-langchain-protocol==0.0.15
+langchain-protocol==0.0.16
     # via langchain-core
 langgraph==1.1.10
     # via langchain
@@ -222,7 +222,7 @@ langgraph-prebuilt==1.0.13
     # via langgraph
 langgraph-sdk==0.3.15
     # via langgraph
-langsmith==0.8.5
+langsmith==0.8.8
     # via
     #   langchain-community
     #   langchain-core
@@ -338,7 +338,7 @@ proto-plus==1.28.0
     # via
     #   google-ai-generativelanguage
     #   google-api-core
-protobuf==6.33.6
+protobuf==7.35.0
     # via
     #   google-ai-generativelanguage
     #   google-api-core
@@ -455,7 +455,7 @@ rich==14.3.4
     #   typer
 rouge-score==0.1.2
     # via lightspeed-evaluation
-rpds-py==0.30.0
+rpds-py==2026.5.1
     # via
     #   jsonschema
     #   referencing
@@ -477,7 +477,7 @@ seaborn==0.13.2
     # via lightspeed-evaluation
 sentence-transformers==5.2.3
     # via lightspeed-evaluation
-sentry-sdk==2.60.0
+sentry-sdk==2.61.1
     # via deepeval
 setuptools==82.0.1
     # via
@@ -534,7 +534,7 @@ tqdm==4.67.1
     #   transformers
 transformers==5.9.0
     # via sentence-transformers
-typer==0.26.1
+typer==0.26.5
     # via
     #   deepeval
     #   huggingface-hub
@@ -578,6 +578,8 @@ uuid-utils==0.16.0
     # via
     #   langchain-core
     #   langsmith
+websockets==16.0
+    # via langsmith
 wheel==0.47.0
     # via deepeval
 xxhash==3.7.0

requirements-local-embeddings.txt

@@ -113,13 +113,13 @@ googleapis-common-protos==1.75.0
     #   grpcio-status
 greenlet==3.5.1 ; platform_machine == 'AMD64' or platform_machine == 'WIN32' or platform_machine == 'aarch64' or platform_machine == 'amd64' or platform_machine == 'ppc64le' or platform_machine == 'win32' or platform_machine == 'x86_64'
     # via sqlalchemy
-grpcio==1.80.0
+grpcio==1.81.0
     # via
     #   deepeval
     #   google-ai-generativelanguage
     #   google-api-core
     #   grpcio-status
-grpcio-status==1.80.0
+grpcio-status==1.81.0
     # via google-api-core
 h11==0.16.0
     # via httpcore
@@ -144,7 +144,7 @@ huggingface-hub==1.16.1
     #   sentence-transformers
     #   tokenizers
     #   transformers
-idna==3.16
+idna==3.17
     # via
     #   anyio
     #   httpx
@@ -204,7 +204,7 @@ langchain-huggingface==1.2.2
     # via langchain
 langchain-openai==1.1.10
     # via ragas
-langchain-protocol==0.0.15
+langchain-protocol==0.0.16
     # via langchain-core
 langgraph==1.1.10
     # via langchain
@@ -216,7 +216,7 @@ langgraph-prebuilt==1.0.13
     # via langgraph
 langgraph-sdk==0.3.15
     # via langgraph
-langsmith==0.8.5
+langsmith==0.8.8
     # via
     #   langchain-community
     #   langchain-core
@@ -324,7 +324,7 @@ proto-plus==1.28.0
     # via
     #   google-ai-generativelanguage
     #   google-api-core
-protobuf==6.33.6
+protobuf==7.35.0
     # via
     #   google-ai-generativelanguage
     #   google-api-core
@@ -435,7 +435,7 @@ rich==14.3.4
     #   instructor
     #   ragas
     #   typer
-rpds-py==0.30.0
+rpds-py==2026.5.1
     # via
     #   jsonschema
     #   referencing
@@ -455,7 +455,7 @@ seaborn==0.13.2
     # via lightspeed-evaluation
 sentence-transformers==5.2.3
     # via lightspeed-evaluation
-sentry-sdk==2.60.0
+sentry-sdk==2.61.1
     # via deepeval
 setuptools==82.0.1
     # via
@@ -508,7 +508,7 @@ tqdm==4.67.1
     #   transformers
 transformers==5.9.0
     # via sentence-transformers
-typer==0.26.1
+typer==0.26.5
     # via
     #   deepeval
     #   huggingface-hub
@@ -552,6 +552,8 @@ uuid-utils==0.16.0
     # via
     #   langchain-core
     #   langsmith
+websockets==16.0
+    # via langsmith
 wheel==0.47.0
     # via deepeval
 xxhash==3.7.0

requirements-nlp-metrics.txt

@@ -115,13 +115,13 @@ googleapis-common-protos==1.75.0
     #   grpcio-status
 greenlet==3.5.1 ; platform_machine == 'AMD64' or platform_machine == 'WIN32' or platform_machine == 'aarch64' or platform_machine == 'amd64' or platform_machine == 'ppc64le' or platform_machine == 'win32' or platform_machine == 'x86_64'
     # via sqlalchemy
-grpcio==1.80.0
+grpcio==1.81.0
     # via
     #   deepeval
     #   google-ai-generativelanguage
     #   google-api-core
     #   grpcio-status
-grpcio-status==1.80.0
+grpcio-status==1.81.0
     # via google-api-core
 h11==0.16.0
     # via httpcore
@@ -144,7 +144,7 @@ huggingface-hub==1.16.1
     #   datasets
     #   langchain-huggingface
     #   tokenizers
-idna==3.16
+idna==3.17
     # via
     #   anyio
     #   httpx
@@ -203,7 +203,7 @@ langchain-huggingface==1.2.2
     # via langchain
 langchain-openai==1.1.10
     # via ragas
-langchain-protocol==0.0.15
+langchain-protocol==0.0.16
     # via langchain-core
 langgraph==1.1.10
     # via langchain
@@ -215,7 +215,7 @@ langgraph-prebuilt==1.0.13
     # via langgraph
 langgraph-sdk==0.3.15
     # via langgraph
-langsmith==0.8.5
+langsmith==0.8.8
     # via
     #   langchain-community
     #   langchain-core
@@ -323,7 +323,7 @@ proto-plus==1.28.0
     # via
     #   google-ai-generativelanguage
     #   google-api-core
-protobuf==6.33.6
+protobuf==7.35.0
     # via
     #   google-ai-generativelanguage
     #   google-api-core
@@ -438,7 +438,7 @@ rich==14.3.4
     #   typer
 rouge-score==0.1.2
     # via lightspeed-evaluation
-rpds-py==0.30.0
+rpds-py==2026.5.1
     # via
     #   jsonschema
     #   referencing
@@ -452,7 +452,7 @@ scipy==1.16.2
     #   scikit-network
 seaborn==0.13.2
     # via lightspeed-evaluation
-sentry-sdk==2.60.0
+sentry-sdk==2.61.1
     # via deepeval
 setuptools==82.0.1
     # via deepeval
@@ -498,7 +498,7 @@ tqdm==4.67.1
     #   nltk
     #   openai
     #   ragas
-typer==0.26.1
+typer==0.26.5
     # via
     #   deepeval
     #   huggingface-hub
@@ -539,6 +539,8 @@ uuid-utils==0.16.0
     # via
     #   langchain-core
     #   langsmith
+websockets==16.0
+    # via langsmith
 wheel==0.47.0
     # via deepeval
 xxhash==3.7.0