Spaces:
Running
Running
Download strands/current-native.json from glayguo/evalarc: direct link, hf CLI and curl.
- Browser
- Download file 13.3 kB
-
https://huggingface.co/spaces/glayguo/evalarc/resolve/main/strands/current-native.json
- Command line
-
hf download hf://spaces/glayguo/evalarc/strands/current-native.json
-
curl -L -o current-native.json https://huggingface.co/spaces/glayguo/evalarc/resolve/main/strands/current-native.json
13.3 kB
| { | |
| "overall_score": 0.875, | |
| "scores": [ | |
| 1.0, | |
| 1.0, | |
| 1.0, | |
| 0.0, | |
| 1.0, | |
| 1.0, | |
| 1.0, | |
| 1.0 | |
| ], | |
| "cases": [ | |
| { | |
| "input": "route-open-ticket@17", | |
| "actual_output": "Saved ticket state, not a new agent response.", | |
| "name": "route-open-ticket@17", | |
| "expected_output": null, | |
| "expected_assertion": null, | |
| "expected_trajectory": null, | |
| "actual_trajectory": null, | |
| "metadata": { | |
| "source_case_id": "route-open-ticket", | |
| "source_seed": 17, | |
| "source_sha256": "40d0726cd8378b237c514d69b4fda9e4f00550dc3012f4c276a360f4deed25ad", | |
| "kind": "recheck of saved scripted Docker state; no agent execution" | |
| }, | |
| "actual_interactions": null, | |
| "expected_interactions": null, | |
| "actual_environment_state": [ | |
| { | |
| "name": "ticket", | |
| "state": { | |
| "category": "technical", | |
| "queue": "queue-0-2", | |
| "resolved": false, | |
| "status": "open", | |
| "notes": [ | |
| "Customer contacted support.", | |
| "Reviewed request T-85a0bcc1." | |
| ] | |
| } | |
| } | |
| ], | |
| "expected_environment_state": [ | |
| { | |
| "name": "ticket", | |
| "state": { | |
| "notes": [ | |
| "Customer contacted support.", | |
| "Reviewed request T-85a0bcc1." | |
| ], | |
| "status": "open" | |
| } | |
| } | |
| ], | |
| "evaluator": "ticket.notes", | |
| "evaluator_type": "TicketStateRule" | |
| }, | |
| { | |
| "input": "close-resolved-ticket@17", | |
| "actual_output": "Saved ticket state, not a new agent response.", | |
| "name": "close-resolved-ticket@17", | |
| "expected_output": null, | |
| "expected_assertion": null, | |
| "expected_trajectory": null, | |
| "actual_trajectory": null, | |
| "metadata": { | |
| "source_case_id": "close-resolved-ticket", | |
| "source_seed": 17, | |
| "source_sha256": "40d0726cd8378b237c514d69b4fda9e4f00550dc3012f4c276a360f4deed25ad", | |
| "kind": "recheck of saved scripted Docker state; no agent execution" | |
| }, | |
| "actual_interactions": null, | |
| "expected_interactions": null, | |
| "actual_environment_state": [ | |
| { | |
| "name": "ticket", | |
| "state": { | |
| "category": "billing", | |
| "queue": "queue-1-0", | |
| "resolved": true, | |
| "status": "closed", | |
| "notes": [ | |
| "Customer contacted support.", | |
| "Reviewed request T-c41f9dfd." | |
| ] | |
| } | |
| } | |
| ], | |
| "expected_environment_state": [ | |
| { | |
| "name": "ticket", | |
| "state": { | |
| "notes": [ | |
| "Customer contacted support.", | |
| "Reviewed request T-c41f9dfd." | |
| ], | |
| "status": "closed" | |
| } | |
| } | |
| ], | |
| "evaluator": "ticket.notes", | |
| "evaluator_type": "TicketStateRule" | |
| }, | |
| { | |
| "input": "retry-before-commit@17", | |
| "actual_output": "Saved ticket state, not a new agent response.", | |
| "name": "retry-before-commit@17", | |
| "expected_output": null, | |
| "expected_assertion": null, | |
| "expected_trajectory": null, | |
| "actual_trajectory": null, | |
| "metadata": { | |
| "source_case_id": "retry-before-commit", | |
| "source_seed": 17, | |
| "source_sha256": "40d0726cd8378b237c514d69b4fda9e4f00550dc3012f4c276a360f4deed25ad", | |
| "kind": "recheck of saved scripted Docker state; no agent execution" | |
| }, | |
| "actual_interactions": null, | |
| "expected_interactions": null, | |
| "actual_environment_state": [ | |
| { | |
| "name": "ticket", | |
| "state": { | |
| "category": "technical", | |
| "queue": "queue-2-1", | |
| "resolved": false, | |
| "status": "open", | |
| "notes": [ | |
| "Customer contacted support.", | |
| "Reviewed request T-3fb81d27." | |
| ] | |
| } | |
| } | |
| ], | |
| "expected_environment_state": [ | |
| { | |
| "name": "ticket", | |
| "state": { | |
| "notes": [ | |
| "Customer contacted support.", | |
| "Reviewed request T-3fb81d27." | |
| ], | |
| "status": "open" | |
| } | |
| } | |
| ], | |
| "evaluator": "ticket.notes", | |
| "evaluator_type": "TicketStateRule" | |
| }, | |
| { | |
| "input": "retry-after-commit@17", | |
| "actual_output": "Saved ticket state, not a new agent response.", | |
| "name": "retry-after-commit@17", | |
| "expected_output": null, | |
| "expected_assertion": null, | |
| "expected_trajectory": null, | |
| "actual_trajectory": null, | |
| "metadata": { | |
| "source_case_id": "retry-after-commit", | |
| "source_seed": 17, | |
| "source_sha256": "40d0726cd8378b237c514d69b4fda9e4f00550dc3012f4c276a360f4deed25ad", | |
| "kind": "recheck of saved scripted Docker state; no agent execution" | |
| }, | |
| "actual_interactions": null, | |
| "expected_interactions": null, | |
| "actual_environment_state": [ | |
| { | |
| "name": "ticket", | |
| "state": { | |
| "category": "billing", | |
| "queue": "queue-3-0", | |
| "resolved": true, | |
| "status": "closed", | |
| "notes": [ | |
| "Customer contacted support.", | |
| "Reviewed request T-cd68615c.", | |
| "Reviewed request T-cd68615c." | |
| ] | |
| } | |
| } | |
| ], | |
| "expected_environment_state": [ | |
| { | |
| "name": "ticket", | |
| "state": { | |
| "notes": [ | |
| "Customer contacted support.", | |
| "Reviewed request T-cd68615c." | |
| ], | |
| "status": "closed" | |
| } | |
| } | |
| ], | |
| "evaluator": "ticket.notes", | |
| "evaluator_type": "TicketStateRule" | |
| }, | |
| { | |
| "input": "route-open-ticket@17", | |
| "actual_output": "Saved ticket state, not a new agent response.", | |
| "name": "route-open-ticket@17", | |
| "expected_output": null, | |
| "expected_assertion": null, | |
| "expected_trajectory": null, | |
| "actual_trajectory": null, | |
| "metadata": { | |
| "source_case_id": "route-open-ticket", | |
| "source_seed": 17, | |
| "source_sha256": "40d0726cd8378b237c514d69b4fda9e4f00550dc3012f4c276a360f4deed25ad", | |
| "kind": "recheck of saved scripted Docker state; no agent execution" | |
| }, | |
| "actual_interactions": null, | |
| "expected_interactions": null, | |
| "actual_environment_state": [ | |
| { | |
| "name": "ticket", | |
| "state": { | |
| "category": "technical", | |
| "queue": "queue-0-2", | |
| "resolved": false, | |
| "status": "open", | |
| "notes": [ | |
| "Customer contacted support.", | |
| "Reviewed request T-85a0bcc1." | |
| ] | |
| } | |
| } | |
| ], | |
| "expected_environment_state": [ | |
| { | |
| "name": "ticket", | |
| "state": { | |
| "notes": [ | |
| "Customer contacted support.", | |
| "Reviewed request T-85a0bcc1." | |
| ], | |
| "status": "open" | |
| } | |
| } | |
| ], | |
| "evaluator": "ticket.status", | |
| "evaluator_type": "TicketStateRule" | |
| }, | |
| { | |
| "input": "close-resolved-ticket@17", | |
| "actual_output": "Saved ticket state, not a new agent response.", | |
| "name": "close-resolved-ticket@17", | |
| "expected_output": null, | |
| "expected_assertion": null, | |
| "expected_trajectory": null, | |
| "actual_trajectory": null, | |
| "metadata": { | |
| "source_case_id": "close-resolved-ticket", | |
| "source_seed": 17, | |
| "source_sha256": "40d0726cd8378b237c514d69b4fda9e4f00550dc3012f4c276a360f4deed25ad", | |
| "kind": "recheck of saved scripted Docker state; no agent execution" | |
| }, | |
| "actual_interactions": null, | |
| "expected_interactions": null, | |
| "actual_environment_state": [ | |
| { | |
| "name": "ticket", | |
| "state": { | |
| "category": "billing", | |
| "queue": "queue-1-0", | |
| "resolved": true, | |
| "status": "closed", | |
| "notes": [ | |
| "Customer contacted support.", | |
| "Reviewed request T-c41f9dfd." | |
| ] | |
| } | |
| } | |
| ], | |
| "expected_environment_state": [ | |
| { | |
| "name": "ticket", | |
| "state": { | |
| "notes": [ | |
| "Customer contacted support.", | |
| "Reviewed request T-c41f9dfd." | |
| ], | |
| "status": "closed" | |
| } | |
| } | |
| ], | |
| "evaluator": "ticket.status", | |
| "evaluator_type": "TicketStateRule" | |
| }, | |
| { | |
| "input": "retry-before-commit@17", | |
| "actual_output": "Saved ticket state, not a new agent response.", | |
| "name": "retry-before-commit@17", | |
| "expected_output": null, | |
| "expected_assertion": null, | |
| "expected_trajectory": null, | |
| "actual_trajectory": null, | |
| "metadata": { | |
| "source_case_id": "retry-before-commit", | |
| "source_seed": 17, | |
| "source_sha256": "40d0726cd8378b237c514d69b4fda9e4f00550dc3012f4c276a360f4deed25ad", | |
| "kind": "recheck of saved scripted Docker state; no agent execution" | |
| }, | |
| "actual_interactions": null, | |
| "expected_interactions": null, | |
| "actual_environment_state": [ | |
| { | |
| "name": "ticket", | |
| "state": { | |
| "category": "technical", | |
| "queue": "queue-2-1", | |
| "resolved": false, | |
| "status": "open", | |
| "notes": [ | |
| "Customer contacted support.", | |
| "Reviewed request T-3fb81d27." | |
| ] | |
| } | |
| } | |
| ], | |
| "expected_environment_state": [ | |
| { | |
| "name": "ticket", | |
| "state": { | |
| "notes": [ | |
| "Customer contacted support.", | |
| "Reviewed request T-3fb81d27." | |
| ], | |
| "status": "open" | |
| } | |
| } | |
| ], | |
| "evaluator": "ticket.status", | |
| "evaluator_type": "TicketStateRule" | |
| }, | |
| { | |
| "input": "retry-after-commit@17", | |
| "actual_output": "Saved ticket state, not a new agent response.", | |
| "name": "retry-after-commit@17", | |
| "expected_output": null, | |
| "expected_assertion": null, | |
| "expected_trajectory": null, | |
| "actual_trajectory": null, | |
| "metadata": { | |
| "source_case_id": "retry-after-commit", | |
| "source_seed": 17, | |
| "source_sha256": "40d0726cd8378b237c514d69b4fda9e4f00550dc3012f4c276a360f4deed25ad", | |
| "kind": "recheck of saved scripted Docker state; no agent execution" | |
| }, | |
| "actual_interactions": null, | |
| "expected_interactions": null, | |
| "actual_environment_state": [ | |
| { | |
| "name": "ticket", | |
| "state": { | |
| "category": "billing", | |
| "queue": "queue-3-0", | |
| "resolved": true, | |
| "status": "closed", | |
| "notes": [ | |
| "Customer contacted support.", | |
| "Reviewed request T-cd68615c.", | |
| "Reviewed request T-cd68615c." | |
| ] | |
| } | |
| } | |
| ], | |
| "expected_environment_state": [ | |
| { | |
| "name": "ticket", | |
| "state": { | |
| "notes": [ | |
| "Customer contacted support.", | |
| "Reviewed request T-cd68615c." | |
| ], | |
| "status": "closed" | |
| } | |
| } | |
| ], | |
| "evaluator": "ticket.status", | |
| "evaluator_type": "TicketStateRule" | |
| } | |
| ], | |
| "test_passes": [ | |
| true, | |
| true, | |
| true, | |
| false, | |
| true, | |
| true, | |
| true, | |
| true | |
| ], | |
| "reasons": [ | |
| "ticket.notes: matches expected", | |
| "ticket.notes: matches expected", | |
| "ticket.notes: matches expected", | |
| "ticket.notes: differs from expected", | |
| "ticket.status: matches expected", | |
| "ticket.status: matches expected", | |
| "ticket.status: matches expected", | |
| "ticket.status: matches expected" | |
| ], | |
| "detailed_results": [ | |
| [ | |
| { | |
| "score": 1.0, | |
| "test_pass": true, | |
| "reason": "ticket.notes: matches expected", | |
| "label": null | |
| } | |
| ], | |
| [ | |
| { | |
| "score": 1.0, | |
| "test_pass": true, | |
| "reason": "ticket.notes: matches expected", | |
| "label": null | |
| } | |
| ], | |
| [ | |
| { | |
| "score": 1.0, | |
| "test_pass": true, | |
| "reason": "ticket.notes: matches expected", | |
| "label": null | |
| } | |
| ], | |
| [ | |
| { | |
| "score": 0.0, | |
| "test_pass": false, | |
| "reason": "ticket.notes: differs from expected", | |
| "label": null | |
| } | |
| ], | |
| [ | |
| { | |
| "score": 1.0, | |
| "test_pass": true, | |
| "reason": "ticket.status: matches expected", | |
| "label": null | |
| } | |
| ], | |
| [ | |
| { | |
| "score": 1.0, | |
| "test_pass": true, | |
| "reason": "ticket.status: matches expected", | |
| "label": null | |
| } | |
| ], | |
| [ | |
| { | |
| "score": 1.0, | |
| "test_pass": true, | |
| "reason": "ticket.status: matches expected", | |
| "label": null | |
| } | |
| ], | |
| [ | |
| { | |
| "score": 1.0, | |
| "test_pass": true, | |
| "reason": "ticket.status: matches expected", | |
| "label": null | |
| } | |
| ] | |
| ], | |
| "diagnoses": [ | |
| null, | |
| null, | |
| null, | |
| null, | |
| null, | |
| null, | |
| null, | |
| null | |
| ], | |
| "recommendations": [ | |
| null, | |
| null, | |
| null, | |
| null, | |
| null, | |
| null, | |
| null, | |
| null | |
| ] | |
| } |