Remove legacy online mining tools
This commit is contained in:
wuyang6
@@ -237,142 +237,6 @@ def build_data_agent_tools(handlers: Mapping[str, ToolHandler]) -> list[AgentToo
|
||||
},
|
||||
handler=resolve_handler(handlers, 'data_agent_render_source_context', 'data-agent'),
|
||||
),
|
||||
AgentTool(
|
||||
name='data_agent_profile_router_sessions',
|
||||
description=(
|
||||
'Profile local router_session_parquet date partitions before mining online sessions. '
|
||||
'Returns schema, sampled row count, distributions, and example sessions.'
|
||||
),
|
||||
parameters={
|
||||
'type': 'object',
|
||||
'properties': {
|
||||
'dates': {
|
||||
'type': 'array',
|
||||
'items': {'type': 'string'},
|
||||
'description': 'Date partitions such as ["20260428"]. Resolved under router_session_parquet/date=YYYYMMDD.',
|
||||
},
|
||||
'paths': {
|
||||
'type': 'array',
|
||||
'items': {'type': 'string'},
|
||||
'description': 'Parquet files or date directories. Relative paths resolve from workspace root; absolute paths are allowed for external online data.',
|
||||
},
|
||||
'max_files': {'type': 'integer', 'minimum': 1, 'maximum': 200},
|
||||
'max_rows_per_file': {'type': 'integer', 'minimum': 1, 'maximum': 100000},
|
||||
'examples_limit': {'type': 'integer', 'minimum': 0, 'maximum': 20},
|
||||
},
|
||||
},
|
||||
handler=resolve_handler(handlers, 'data_agent_profile_router_sessions', 'data-agent'),
|
||||
),
|
||||
AgentTool(
|
||||
name='data_agent_search_router_sessions',
|
||||
description=(
|
||||
'Search local router_session_parquet data with reviewable filters such as device, domain, intent, func, '
|
||||
'query keywords, regex, turn count, and match scope. Returns turn-level candidates with prev turns.'
|
||||
),
|
||||
parameters={
|
||||
'type': 'object',
|
||||
'properties': {
|
||||
'dates': {
|
||||
'type': 'array',
|
||||
'items': {'type': 'string'},
|
||||
'description': 'Date partitions such as ["20260428"]. Resolved under router_session_parquet/date=YYYYMMDD.',
|
||||
},
|
||||
'paths': {
|
||||
'type': 'array',
|
||||
'items': {'type': 'string'},
|
||||
'description': 'Parquet files or date directories. Relative paths resolve from workspace root; absolute paths are allowed for external online data.',
|
||||
},
|
||||
'devices': {'type': 'array', 'items': {'type': 'string'}},
|
||||
'domains': {'type': 'array', 'items': {'type': 'string'}},
|
||||
'intents': {'type': 'array', 'items': {'type': 'string'}},
|
||||
'funcs': {'type': 'array', 'items': {'type': 'string'}},
|
||||
'query_keywords': {'type': 'array', 'items': {'type': 'string'}},
|
||||
'keyword_match_mode': {'type': 'string', 'enum': ['any', 'all']},
|
||||
'query_regex': {'type': 'string'},
|
||||
'match_scope': {'type': 'string', 'enum': ['any_turn', 'last_turn']},
|
||||
'turn_count_min': {'type': 'integer', 'minimum': 1},
|
||||
'turn_count_max': {'type': 'integer', 'minimum': 1},
|
||||
'max_files': {'type': 'integer', 'minimum': 1, 'maximum': 200},
|
||||
'max_rows_per_file': {'type': 'integer', 'minimum': 1, 'maximum': 100000},
|
||||
'max_candidates': {'type': 'integer', 'minimum': 1, 'maximum': 5000},
|
||||
},
|
||||
},
|
||||
handler=resolve_handler(handlers, 'data_agent_search_router_sessions', 'data-agent'),
|
||||
),
|
||||
AgentTool(
|
||||
name='data_agent_sample_router_candidates',
|
||||
description=(
|
||||
'Sample router session candidates for human review and return candidate-level summary statistics. '
|
||||
'Use after data_agent_search_router_sessions.'
|
||||
),
|
||||
parameters={
|
||||
'type': 'object',
|
||||
'properties': {
|
||||
'candidates': {
|
||||
'oneOf': [
|
||||
{'type': 'array'},
|
||||
{'type': 'object'},
|
||||
{'type': 'string'},
|
||||
],
|
||||
'description': 'Candidates array, search result object, or JSON string containing candidates.',
|
||||
},
|
||||
'sample_size': {'type': 'integer', 'minimum': 1, 'maximum': 1000},
|
||||
'strategy': {'type': 'string', 'enum': ['random', 'first', 'stride']},
|
||||
'seed': {'type': 'integer'},
|
||||
},
|
||||
'required': ['candidates'],
|
||||
},
|
||||
handler=resolve_handler(handlers, 'data_agent_sample_router_candidates', 'data-agent'),
|
||||
),
|
||||
AgentTool(
|
||||
name='data_agent_convert_router_candidates_to_records',
|
||||
description=(
|
||||
'Convert reviewed online router session candidates directly into canonical data-agent records. '
|
||||
'Use this when the user wants to keep mined online data as samples; do not use generation-plan tools for this path.'
|
||||
),
|
||||
parameters={
|
||||
'type': 'object',
|
||||
'properties': {
|
||||
'candidates': {
|
||||
'oneOf': [
|
||||
{'type': 'array'},
|
||||
{'type': 'object'},
|
||||
{'type': 'string'},
|
||||
],
|
||||
'description': 'Candidates array, search/sample result object, or JSON string containing candidates.',
|
||||
},
|
||||
'dataset_label': {'type': 'string'},
|
||||
'default_target': {
|
||||
'type': 'string',
|
||||
'description': 'Target label used for included candidates unless review_decisions provides a target.',
|
||||
},
|
||||
'default_complex': {
|
||||
'type': 'boolean',
|
||||
'description': 'Default complex dimension for included candidates unless review_decisions provides complex.',
|
||||
},
|
||||
'review_decisions': {
|
||||
'type': 'array',
|
||||
'description': 'Optional include/exclude/uncertain decisions keyed by semantic_session_id or req_id.',
|
||||
'items': {
|
||||
'type': 'object',
|
||||
'properties': {
|
||||
'semantic_session_id': {'type': 'string'},
|
||||
'req_id': {'type': 'string'},
|
||||
'matched_turn_index': {'type': 'integer'},
|
||||
'decision': {'type': 'string', 'enum': ['include', 'exclude', 'uncertain']},
|
||||
'target': {'type': 'string'},
|
||||
'complex': {'type': 'boolean'},
|
||||
'notes': {'type': 'string'},
|
||||
},
|
||||
},
|
||||
},
|
||||
'batch_id': {'type': 'string'},
|
||||
'include_uncertain': {'type': 'boolean'},
|
||||
},
|
||||
'required': ['candidates', 'dataset_label'],
|
||||
},
|
||||
handler=resolve_handler(handlers, 'data_agent_convert_router_candidates_to_records', 'data-agent'),
|
||||
),
|
||||
AgentTool(
|
||||
name='data_agent_show_generation_plan',
|
||||
description='Show a data-agent generation plan for human review.',
|
||||
|
||||
Reference in New Issue
Block a user