Skip to content

feat: InputArgs屏蔽字段新增5个 #516

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

Merged
shijinpjlab merged 2 commits into from
Oct 20, 2026
Merged

feat: InputArgs屏蔽字段新增5个 #516

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
550f1b1
feat: InputArgs屏蔽字段新增5个
shijinpjlab Oct 19, 2026
0467c83
feat: 改成add模式
shijinpjlab Oct 19, 2026
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
141 changes: 122 additions & 19 deletions dingo/config/input_args.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -197,24 +197,127 @@ class InputArgs(BaseModel):
evaluator: List[EvalPipline] = []

def to_dict(self) -> Dict[str, Any]:
"""Return a config snapshot, recursively excluding sensitive fields."""
"""Return a config snapshot containing only explicitly approved fields."""
# Security allowlist: fields omitted here are excluded by default.
safe_serialization_fields: Dict[str, Any] = {
"task_id": ...,
"task_name": ...,
"input_path": ...,
"output_path": ...,
"log_level": ...,
"dataset": {
"source": ...,
"format": ...,
"hf_config": {
"huggingface_split",
"huggingface_config_name",
},
"s3_config": {
"s3_endpoint_url",
"s3_bucket",
"s3_addressing_style",
},
"sql_config": {
"dialect",
"driver",
"username",
"host",
"port",
"database",
"connect_args",
"engine_args",
},
"excel_config": {"sheet_name", "has_header"},
"csv_config": {
"has_header",
"encoding",
"dialect",
"delimiter",
"quotechar",
},
"parquet_config": {"batch_size", "columns"},
"mineru_config": {"include_types"},
},
"executor": {
"start_index": ...,
"end_index": ...,
"max_workers": ...,
"batch_size": ...,
"multi_turn_mode": ...,
"result_save": {
"bad",
"good",
"all_labels",
"raw",
"merge",
"limit",
"field_list",
"full_field_sample_count",
},
"retrieval": {
"backend": ...,
"api_url": ...,
"limit": ...,
"retrieval_mode": ...,
"sub_queries": ...,
"search_type": ...,
"sort_by": ...,
"freshness_boost": ...,
"filters": ...,
"max_queries": ...,
"title_fuzzy_enabled": ...,
"title_fuzzy_threshold": ...,
"title_fuzzy_margin": ...,
"title_fuzzy_min_len": ...,
"title_fuzzy_max_candidates": ...,
"timeout": ...,
"rate_limit": ...,
"max_retries": ...,
"max_workers": ...,
"open_eval": {
"enabled",
"model",
"api_url",
"top_k",
"aggregate",
"max_workers",
"prompt_mode",
"expected_criteria",
},
"input_queries": ...,
},
},
"evaluator": {
"__all__": {
"fields": ...,
"evals": {
"__all__": {
"name": ...,
"config": {
"threshold": ...,
"pattern": ...,
"key_list": ...,
"refer_path": ...,
"model": ...,
"api_url": ...,
"embedding_config": {"model", "api_url"},
"custom_metric": {
"metric",
"description",
"criteria",
"input_fields",
},
},
},
},
},
},
}

model_dump = getattr(self, "model_dump", None)
if callable(model_dump):
data = model_dump()
else:
data = self.dict()

excluded = {"key"}
pending = [data]
while pending:
value = pending.pop()
if isinstance(value, dict):
for key in list(value):
if key in excluded:
del value[key]
else:
pending.append(value[key])
elif isinstance(value, list):
pending.extend(value)

return data
return model_dump(
include=safe_serialization_fields,
serialize_as_any=True,
)
return self.dict(include=safe_serialization_fields)
28 changes: 28 additions & 0 deletions test/scripts/io/test_summary_model.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -83,13 +83,33 @@ def test_input_args_are_serialized(self):

def test_input_args_to_dict_recursively_excludes_fields(self):
input_args = InputArgs(**{
"dataset": {
"s3_config": {
"s3_ak": "access-key",
"s3_sk": "secret-key",
"s3_bucket": "test-bucket",
},
"sql_config": {
"username": "test-user",
"password": "secret-password",
},
},
"executor": {
"retrieval": {
"api_token": "secret-token",
},
},
"evaluator": [{
"fields": {"content": "content"},
"evals": [{
"name": "LLMTextQualityV7",
"config": {
"model": "test-model",
"key": "secret-key",
"tool_config": {
"API_KEY": "secret-tool-key",
},
"new_config_field": "not-approved-yet",
},
}],
}],
Expand All @@ -98,7 +118,15 @@ def test_input_args_to_dict_recursively_excludes_fields(self):
serialized = input_args.to_dict()
config = serialized["evaluator"][0]["evals"][0]["config"]

assert "s3_ak" not in serialized["dataset"]["s3_config"]
assert "s3_sk" not in serialized["dataset"]["s3_config"]
assert serialized["dataset"]["s3_config"]["s3_bucket"] == "test-bucket"
assert "password" not in serialized["dataset"]["sql_config"]
assert serialized["dataset"]["sql_config"]["username"] == "test-user"
assert "api_token" not in serialized["executor"]["retrieval"]
assert "key" not in config
assert "tool_config" not in config
assert "new_config_field" not in config
assert config["model"] == "test-model"

def test_add_metric_score_single(self):
Expand Down
Loading