Add @override to methods flagged by ty missing-override-decorator

src/bcbench/agent/shared/mcp_gateway.py

@@ -19,7 +19,7 @@
 import time
 from http.client import HTTPConnection
 from http.server import BaseHTTPRequestHandler, ThreadingHTTPServer
-from typing import cast
+from typing import cast, override
 from urllib.parse import urlsplit
 
 from bcbench_core.container import ContainerConfig
@@ -236,6 +236,7 @@ def _build_handler(gateway: BcMcpGateway) -> type[BaseHTTPRequestHandler]:
     class _ProxyHandler(BaseHTTPRequestHandler):
         protocol_version = "HTTP/1.1"
 
+        @override
         def log_message(self, format: str, *args: object) -> None:  # match stdlib signature; silence access log
             pass
 

src/bcbench/commands/evaluate.py

@@ -1,7 +1,7 @@
 import logging
 import random
 from pathlib import Path
-from typing import Annotated, cast
+from typing import Annotated, cast, override
 
 import typer
 from bcbench_core.filesystem import prepare_run_dir
@@ -346,12 +346,15 @@ class MockEvaluationPipeline(EvaluationPipeline[BaseDatasetEntry]):
     It randomly generates different scenarios to test result handling and serialization.
     """
 
+    @override
     def setup_workspace(self, entry: BaseDatasetEntry, repo_path: Path) -> None:
         logger.info("Mock pipeline: Skipping workspace setup")
 
+    @override
     def setup(self, context: EvaluationContext[BaseDatasetEntry]) -> None:
         logger.info("Mock pipeline: Skipping setup")
 
+    @override
     def run_agent(self, context: EvaluationContext[BaseDatasetEntry], agent_runner: AgentRunner[BaseDatasetEntry]) -> None:
         """Generate random agent metrics and experiment configuration."""
         logger.info("Mock pipeline: Generating random metrics and experiment configuration")
@@ -382,6 +385,7 @@ def run_agent(self, context: EvaluationContext[BaseDatasetEntry], agent_runner:
         logger.info(f"Using agent metrics: {context.metrics}")
         logger.info(f"Using experiment configuration: {context.experiment}")
 
+    @override
     def evaluate(self, context: EvaluationContext[BaseDatasetEntry]) -> None:
         """Create random evaluation result to test different outcome scenarios."""
         logger.info("Mock pipeline: Generating random evaluation result")

src/bcbench/dataset/codereview.py

@@ -1,7 +1,7 @@
 from __future__ import annotations
 
 from enum import StrEnum
-from typing import Annotated, Self
+from typing import Annotated, Self, override
 
 from pydantic import BaseModel, ConfigDict, Field, field_validator, model_validator
 
@@ -81,6 +81,7 @@ def _coerce_severity(cls, value: object) -> Severity | None:
     def severity_label(self) -> str:
         return self.severity.value if self.severity is not None else "unspecified"
 
+    @override
     def __str__(self) -> str:
         loc = f"{self.file}:{self.line_start}"
         if self.line_end and self.line_end != self.line_start:
@@ -129,9 +130,11 @@ def _validate_article_annotations(self) -> Self:
             )
         return self
 
+    @override
     def get_task(self) -> str:
         return self.patch
 
+    @override
     def get_expected_output(self) -> str:
         return "\n".join(str(c) for c in self.expected_comments)
 

src/bcbench/dataset/dataset_entry.py

@@ -4,7 +4,7 @@
 import re
 from abc import abstractmethod
 from pathlib import Path
-from typing import Annotated, Literal, Self
+from typing import Annotated, Literal, Self, override
 
 from bcbench_core.dataset import TestEntry
 from pydantic import BaseModel, ConfigDict, Field, model_validator
@@ -118,13 +118,15 @@ class RepoGroundedEntry(BaseDatasetEntry):
     patch: Annotated[str, Field(min_length=1, pattern=r"^[^\x00]*$")]
 
     @property
+    @override
     def customization_profile(self) -> str:
         return self.repo.replace("/", "-")
 
     @property
     def problem_statement_dir(self) -> Path:
         return _config.paths.problem_statement_dir / self.instance_id
 
+    @override
     def get_task(self) -> str:
         readme_path = self.problem_statement_dir / _config.file_patterns.problem_statement_readme
         return readme_path.read_text(encoding="utf-8")
@@ -158,13 +160,15 @@ def validate_baseapp_patches_are_w1_only(self) -> Self:
 class BugFixEntry(_BugFixTestGenBase):
     """Dataset entry for the bug-fix category."""
 
+    @override
     def get_expected_output(self) -> str:
         return self.patch
 
 
 class TestGenEntry(_BugFixTestGenBase):
     """Dataset entry for the test-generation category."""
 
+    @override
     def get_expected_output(self) -> str:
         return self.test_patch
 
@@ -178,12 +182,15 @@ class NL2ALEntry(BaseDatasetEntry):
     audience: Literal["Business", "Technical", "Both"]
 
     @property
+    @override
     def customization_profile(self) -> str:
         return "nl2al"
 
+    @override
     def get_task(self) -> str:
         return self.nl_prompt
 
+    @override
     def get_expected_output(self) -> Checklist:
         return {"assertions": self.expected}
 
@@ -204,11 +211,14 @@ class DataQueryEntry(BaseDatasetEntry):
     ordered: bool = False
 
     @property
+    @override
     def customization_profile(self) -> str:
         return "dataquery"
 
+    @override
     def get_task(self) -> str:
         return self.nl_prompt
 
+    @override
     def get_expected_output(self) -> str:
         return self.gold_query

src/bcbench/dataset/extensibility_request.py

@@ -1,6 +1,6 @@
 from __future__ import annotations
 
-from typing import Annotated, Literal
+from typing import Annotated, Literal, override
 
 from pydantic import Field
 
@@ -20,12 +20,14 @@ class ExtRequestAdvisorEntry(RepoGroundedEntry):
     comments: str = ""
     expected: Annotated[list[ChecklistAssertion], Field(min_length=1)]
 
+    @override
     def get_task(self) -> str:
         sections = [f"# {self.title}", "", self.description.rstrip()]
         if self.comments.strip():
             sections += ["", "## Additional requester context", "", self.comments.rstrip()]
         return "\n".join(sections)
 
+    @override
     def get_expected_output(self) -> Checklist:
         return {"assertions": self.expected}
 
@@ -43,6 +45,7 @@ class ExtRequestImplementEntry(RepoGroundedEntry):
     # LLM-judge checklist: expected event/signature/placement and expected layer propagation.
     expected: Annotated[list[ChecklistAssertion], Field(min_length=1)]
 
+    @override
     def get_expected_output(self) -> Checklist:
         return {"assertions": self.expected}
 
@@ -83,6 +86,7 @@ class ExtRequestTriageEntry(RepoGroundedEntry):
     # LLM-judge checklist: expected labels_to_set, issue_state and advisory-comment substance.
     expected: Annotated[list[ChecklistAssertion], Field(min_length=1)]
 
+    @override
     def get_task(self) -> str:
         sections = [f"# {self.title}", "", self.description.rstrip()]
         if self.current_labels:
@@ -91,5 +95,6 @@ def get_task(self) -> str:
             sections += ["", "## Follow-up conversation", "", self.comments.rstrip()]
         return "\n".join(sections)
 
+    @override
     def get_expected_output(self) -> Checklist:
         return {"assertions": self.expected}

src/bcbench/evaluate/bugfix.py

@@ -1,5 +1,6 @@
 import logging
 from pathlib import Path
+from typing import override
 
 from bcbench_core.bc import build_and_publish_projects
 from bcbench_core.exceptions import BuildError, TestExecutionError
@@ -21,11 +22,13 @@
 class BugFixPipeline(EvaluationPipeline[BugFixEntry]):
     """Pipeline for bug-fix evaluation category."""
 
+    @override
     def setup_workspace(self, entry: BugFixEntry, repo_path: Path) -> None:
         setup_repo_prebuild(entry, repo_path)
         copy_problem_statement_folder(entry, repo_path)
         set_runtime_version(repo_path, entry.project_paths)
 
+    @override
     def setup(self, context: EvaluationContext[BugFixEntry]) -> None:
         setup_repo_prebuild(context.entry, context.repo_path)
 
@@ -39,10 +42,12 @@ def setup(self, context: EvaluationContext[BugFixEntry]) -> None:
         copy_problem_statement_folder(context.entry, context.repo_path)
         set_runtime_version(context.repo_path, context.entry.project_paths)
 
+    @override
     def run_agent(self, context: EvaluationContext[BugFixEntry], agent_runner: AgentRunner[BugFixEntry]) -> None:
         with github_log_group(f"{context.agent_name} -- Entry: {context.entry.instance_id}"):
             context.metrics, context.experiment = agent_runner(context)
 
+    @override
     def evaluate(self, context: EvaluationContext[BugFixEntry]) -> None:
         container = context.get_container()
         test_projects, _app_projects = categorize_projects(context.entry.project_paths)

src/bcbench/evaluate/codereview.py

@@ -1,6 +1,7 @@
 import logging
 import subprocess
 from pathlib import Path
+from typing import override
 
 from bcbench_core.git import apply_patch, fetch_commit_if_missing
 
@@ -31,6 +32,7 @@ class CodeReviewPipeline(EvaluationPipeline[CodeReviewEntry]):
     as local git changes so the agent can review the branch diff directly.
     """
 
+    @override
     def setup_workspace(self, entry: CodeReviewEntry, repo_path: Path) -> None:
         """Setup workspace for code review by applying the entry patch as local changes."""
         # Code-review base commits are pre-squash PR commits, so they might be missing from local dev setups.
@@ -48,13 +50,16 @@ def setup_workspace(self, entry: CodeReviewEntry, repo_path: Path) -> None:
                 check=True,
             )
 
+    @override
     def setup(self, context: EvaluationContext[CodeReviewEntry]) -> None:
         self.setup_workspace(context.entry, context.repo_path)
 
+    @override
     def run_agent(self, context: EvaluationContext[CodeReviewEntry], agent_runner: AgentRunner[CodeReviewEntry]) -> None:
         with github_log_group(f"{context.agent_name} -- Entry: {context.entry.instance_id}"):
             context.metrics, context.experiment = agent_runner(context)
 
+    @override
     def evaluate(self, context: EvaluationContext[CodeReviewEntry]) -> None:
         review_output_file: Path = context.repo_path / REVIEW_OUTPUT_FILE
 

src/bcbench/evaluate/dataquery.py

@@ -3,6 +3,7 @@
 from collections.abc import Callable, Mapping, Sequence
 from decimal import Decimal, InvalidOperation
 from pathlib import Path
+from typing import override
 
 from bcbench_core.filesystem import clear_directory
 
@@ -94,17 +95,21 @@ class DataQueryPipeline(EvaluationPipeline[DataQueryEntry]):
     genuinely querying the environment.
     """
 
+    @override
     def setup_workspace(self, entry: DataQueryEntry, repo_path: Path) -> None:
         # The workspace is shared into the running container, so its contents are cleared in place.
         clear_directory(repo_path)
 
+    @override
     def setup(self, context: EvaluationContext[DataQueryEntry]) -> None:
         self.setup_workspace(context.entry, context.repo_path)
 
+    @override
     def run_agent(self, context: EvaluationContext[DataQueryEntry], agent_runner: Callable) -> None:
         with github_log_group(f"{context.agent_name} -- Entry: {context.entry.instance_id}"):
             context.metrics, context.experiment = agent_runner(context)
 
+    @override
     def evaluate(self, context: EvaluationContext[DataQueryEntry]) -> None:
         query_file = context.repo_path / GENERATED_QUERY_FILE
         # query.al is only an inspection artifact now; scoring is on the data the agent retrieved.

src/bcbench/evaluate/ext_request_advisor.py

@@ -1,5 +1,6 @@
 import logging
 from pathlib import Path
+from typing import override
 
 from bcbench.dataset import ExtRequestAdvisorEntry
 from bcbench.evaluate.base import AgentRunner, EvaluationPipeline
@@ -18,17 +19,21 @@
 class ExtRequestAdvisorPipeline(EvaluationPipeline[ExtRequestAdvisorEntry]):
     """Offline single-shot proxy for the interactive extensibility advisor."""
 
+    @override
     def setup_workspace(self, entry: ExtRequestAdvisorEntry, repo_path: Path) -> None:
         setup_repo_prebuild(entry, repo_path)
         (repo_path / ADVISOR_RESULT_FILE).unlink(missing_ok=True)
 
+    @override
     def setup(self, context: EvaluationContext[ExtRequestAdvisorEntry]) -> None:
         self.setup_workspace(context.entry, context.repo_path)
 
+    @override
     def run_agent(self, context: EvaluationContext[ExtRequestAdvisorEntry], agent_runner: AgentRunner[ExtRequestAdvisorEntry]) -> None:
         with github_log_group(f"{context.agent_name} -- Entry: {context.entry.instance_id}"):
             context.metrics, context.experiment = agent_runner(context)
 
+    @override
     def evaluate(self, context: EvaluationContext[ExtRequestAdvisorEntry]) -> None:
         result_path = context.repo_path / ADVISOR_RESULT_FILE
         raw = result_path.read_text(encoding="utf-8").strip() if result_path.exists() else ""

src/bcbench/evaluate/ext_request_implement.py

@@ -1,5 +1,6 @@
 import logging
 from pathlib import Path
+from typing import override
 
 from bcbench_core.exceptions import EmptyDiffError
 from bcbench_core.git import stage_and_get_diff
@@ -24,18 +25,22 @@ class ExtRequestImplementPipeline(EvaluationPipeline[ExtRequestImplementEntry]):
     by an LLM judge against the entry checklist.
     """
 
+    @override
     def setup_workspace(self, entry: ExtRequestImplementEntry, repo_path: Path) -> None:
         setup_repo_prebuild(entry, repo_path)
         copy_problem_statement_folder(entry, repo_path)
         set_runtime_version(repo_path, entry.project_paths)
 
+    @override
     def setup(self, context: EvaluationContext[ExtRequestImplementEntry]) -> None:
         self.setup_workspace(context.entry, context.repo_path)
 
+    @override
     def run_agent(self, context: EvaluationContext[ExtRequestImplementEntry], agent_runner: AgentRunner[ExtRequestImplementEntry]) -> None:
         with github_log_group(f"{context.agent_name} -- Entry: {context.entry.instance_id}"):
             context.metrics, context.experiment = agent_runner(context)
 
+    @override
     def evaluate(self, context: EvaluationContext[ExtRequestImplementEntry]) -> None:
         try:
             generated_patch = stage_and_get_diff(context.repo_path, exclude=("**/app.json", "*.docx", "*.md"))

src/bcbench/evaluate/ext_request_triage.py

@@ -10,6 +10,7 @@
 
 import logging
 from pathlib import Path
+from typing import override
 
 from bcbench.dataset import ExtRequestTriageEntry
 from bcbench.evaluate.base import AgentRunner, EvaluationPipeline
@@ -28,17 +29,21 @@
 class ExtRequestTriagePipeline(EvaluationPipeline[ExtRequestTriageEntry]):
     """Pipeline for the extensibility-request-triage category — no BC container, no build, no tests."""
 
+    @override
     def setup_workspace(self, entry: ExtRequestTriageEntry, repo_path: Path) -> None:
         setup_repo_prebuild(entry, repo_path)
         (repo_path / TRIAGE_RESULT_FILE).unlink(missing_ok=True)
 
+    @override
     def setup(self, context: EvaluationContext[ExtRequestTriageEntry]) -> None:
         self.setup_workspace(context.entry, context.repo_path)
 
+    @override
     def run_agent(self, context: EvaluationContext[ExtRequestTriageEntry], agent_runner: AgentRunner[ExtRequestTriageEntry]) -> None:
         with github_log_group(f"{context.agent_name} -- Entry: {context.entry.instance_id}"):
             context.metrics, context.experiment = agent_runner(context)
 
+    @override
     def evaluate(self, context: EvaluationContext[ExtRequestTriageEntry]) -> None:
         result_path = context.repo_path / TRIAGE_RESULT_FILE
         raw = result_path.read_text(encoding="utf-8").strip() if result_path.exists() else ""