Skip to content

fix: accept Claude native trajectories #52

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
vincentkoc wants to merge 1 commit into
base: main
Choose a base branch
from
+13 −1
Open

fix: accept Claude native trajectories #52

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
2 changes: 1 addition & 1 deletion scripts/native_eval/models.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -99,7 +99,7 @@ def to_dict(self) -> dict[str, object]:

NODE_VERSION = "22.23.1"
LITELLM_VERSION = "1.93.0"
REAL_TRAJECTORY_HARNESSES = frozenset({"openclaw", "hermes", "codex"})
REAL_TRAJECTORY_HARNESSES = frozenset({"openclaw", "hermes", "codex", "claude-code"})


def model_by_slug(slug: str) -> ModelSpec:
Expand Down
12 changes: 12 additions & 0 deletions tests/test_native_eval_runner.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -29,6 +29,7 @@
MODELS,
RunSpec,
build_matrix_plan,
trajectory_mode_for_harness,
)
from scripts.native_eval import plan as native_plan
from scripts.native_eval.proxy import JUDGE_PROXY_MODEL_NAME, write_proxy_config
Expand Down Expand Up @@ -59,6 +60,17 @@ def test_matrix_plan_contains_only_requested_models_and_harnesses() -> None:
assert {run.repetition for run in plan} == {1, 2, 3}


def test_all_native_harnesses_emit_real_trajectories() -> None:
assert {
harness.name: trajectory_mode_for_harness(harness.name) for harness in HARNESSES
} == {
"openclaw": "real_harness_events",
"hermes": "real_harness_events",
"codex": "real_harness_events",
"claude-code": "real_harness_events",
}


def test_run_index_records_agent_and_judge_reasoning(
tmp_path: Path,
monkeypatch,
Expand Down
Loading