---
title: "Create Job"
method: POST
path: "/jobs"
tags: ["jobs"]
---

# Create Job

`POST /jobs`

Create a job for a project run and enqueue it for processing.

## Request body

- CreateJobRequest
  - `resource_limits` TaskResourceLimits
    - `cpu_time` integer
    - `memory_mb` integer
  - `project_id` string, uuid4, required
  - `run_id` string, uuid4, required
  - `job_id` string, uuid4, nullable
  - `job_name` string
  - `should_retry` boolean
  - `user_id` string, uuid4, nullable
  - `task_type` 13 | 15 | 16 | 17 | 18 — Valid task types for modeling. We store these as ints instead of strings because we will be looking this up in the database frequently.
  - `labels` union
    - array[]
      - string[]
    - string[]
  - `ner_labels` string[], nullable
  - `tasks` string[], nullable
  - `non_inference_logged` boolean
  - `migration_name` string, nullable
  - `process_existing_inference_runs` boolean
  - `feature_names` string[], nullable
  - `prompt_dataset_id` string, uuid4, nullable
  - `dataset_id` string, uuid4, nullable
  - `dataset_version_index` integer, nullable
  - `prompt_template_version_id` string, uuid4, nullable
  - `monitor_batch_id` string, uuid4, nullable
  - `protect_trace_id` string, uuid4, nullable
  - `protect_scorer_payload` string, binary, nullable
  - `prompt_settings` PromptRunSettingsInput — Prompt run settings.
    - `logprobs` boolean
    - `top_logprobs` integer
    - `echo` boolean
    - `n` integer
    - `reasoning_effort` string
    - `verbosity` string
    - `deployment_name` string, nullable
    - `model_alias` string
    - `temperature` number, nullable
    - `max_tokens` integer
    - `stop_sequences` string[], nullable
    - `top_p` number
    - `top_k` integer
    - `frequency_penalty` number
    - `presence_penalty` number
    - `tools` object[], nullable
    - `tool_choice` union
      - string
      - OpenAIToolChoice
        - `type` string
        - `function` OpenAIFunction, required
          - `name` string, required
    - `response_format` object, nullable
    - `known_models` Model[]
      - `name` string, required
      - `alias` string, required
      - `integration` 'anthropic' | 'aws_bedrock' | 'aws_sagemaker' | 'azure' | 'custom' | 'databricks' | 'mistral' | 'nvidia' | 'openai' | 'vegas_gateway' | 'vertex_ai' | 'writer'
      - `lifecycle_state` 'active' | 'deprecated' | 'retired'
      - `replacement_alias` string, nullable
      - `deprecation_date` string, date, nullable
      - `retirement_date` string, date, nullable
      - `user_role` string, nullable
      - `assistant_role` string, nullable
      - `system_supported` boolean
      - `input_modalities` ContentModality[] — Input modalities that the model can accept.
      - `alternative_names` string[] — Alternative names for the model, used for matching with various current, versioned or legacy names.
      - `input_token_limit` integer, nullable
      - `output_token_limit` integer, nullable
      - `token_limit` integer, nullable
      - `cost_by` 'tokens' | 'characters'
      - `is_chat` boolean
      - `provides_log_probs` boolean
      - `formatting_tokens` integer
      - `response_prefix_tokens` integer
      - `api_version` string, nullable
      - `legacy_mistral_prompt_format` boolean
      - `requires_max_tokens` boolean
      - `max_top_p` number, nullable
      - `params_map` RunParamsMap — Maps the internal settings parameters (left) to the serialized parameters (right) we want to send in the API requests.
        - `model` string, nullable
        - `temperature` string, nullable
        - `max_tokens` string, nullable
        - `stop_sequences` string, nullable
        - `top_p` string, nullable
        - `top_k` string, nullable
        - `frequency_penalty` string, nullable
        - `presence_penalty` string, nullable
        - `echo` string, nullable
        - `logprobs` string, nullable
        - `top_logprobs` string, nullable
        - `n` string, nullable
        - `api_version` string, nullable
        - `tools` string, nullable
        - `tool_choice` string, nullable
        - `response_format` string, nullable
        - `reasoning_effort` string, nullable
        - `verbosity` string, nullable
        - `deployment_name` string, nullable
      - `output_map` OutputMap
        - `response` string, required
        - `token_count` string, nullable
        - `input_token_count` string, nullable
        - `output_token_count` string, nullable
        - `completion_reason` string, nullable
      - `input_map` InputMap
        - `prompt` string, required
        - `prefix` string
        - `suffix` string
  - `scorers` union — For G2.0 we send all scorers as ScorerConfig, for G1.0 we send preset scorers as GalileoScorer
    - RuntimeScorerConfig[]
      - `id` string, uuid4, required
      - `scorer_version_id` string, uuid4, nullable
      - `filters` union[], nullable — List of filters to apply to the scorer.
        - union
          - NodeNameFilter — Filters on node names in scorer jobs.
            - `name` 'node_name'
            - `operator` 'eq' | 'ne' | 'contains' | 'one_of' | 'not_in', required
            - `value` union, required
              - …
            - `case_sensitive` boolean
          - MetadataFilter — Filters on metadata key-value pairs in scorer jobs.
            - `name` 'metadata'
            - `operator` 'one_of' | 'not_in' | 'eq' | 'ne', required
            - `key` string, required
            - `value` union, required
              - …
          - ModalityFilter — Filters on content modalities in scorer jobs. Matches if at least one of the specified modalities is present.
            - `name` 'modality'
            - `operator` 'eq' | 'ne' | 'one_of' | 'not_in', required
            - `value` union, required
              - …
      - `roll_up_method` 'average' | 'sum' | 'max' | 'min' | 'category_count' | 'percentage_true' | 'percentage_false' — Display options for roll up methods when showing rolled up metrics in the UI. Separates display intent from computation methods. The computation methods (NumericRollUpMethod, CategoricalRollUpMethod) control what aggregations are available. This enum controls how the UI displays the selected roll-up value for a scorer.
      - `name` string, nullable
      - `scorer_type` 'llm' | 'code' | 'luna' | 'preset'
      - `model_name` string, nullable
      - `num_judges` integer, nullable
      - `scorer_version` BaseScorerVersionDB — Scorer version from the scorer_versions table.
        - `id` string, uuid4, required
        - `version` integer, required
        - `scorer_id` string, uuid4, required
        - `generated_scorer` BaseGeneratedScorerDB
          - `id` string, uuid4, required
          - `name` string, required
          - `instructions` string, nullable
          - `chain_poll_template` ChainPollTemplate, required — Template for a chainpoll metric prompt, containing all the info necessary to send a chainpoll prompt.
            - `metric_system_prompt` string, nullable — System prompt for the metric.
            - `metric_description` string, nullable — Description of what the metric should do.
            - `value_field_name` string — Field name to look for in the chainpoll response, for the rating.
            - `explanation_field_name` string — Field name to look for in the chainpoll response, for the explanation.
            - `template` string, required — Chainpoll prompt template.
            - `metric_few_shot_examples` FewShotExample[] — Few-shot examples for the metric.
              - …
            - `response_schema` object, nullable — Response schema for the output
          - `user_prompt` string, nullable
        - `registered_scorer` BaseRegisteredScorerDB
          - `id` string, uuid4, required
          - `name` string, required
          - `score_type` string, nullable
        - `finetuned_scorer` BaseFinetunedScorerDB
          - `id` string, uuid4, required
          - `name` string, required
          - `lora_task_id` integer, required
          - `lora_weights_path` string, nullable
          - `prompt` string, required
          - `luna_input_type` 'span' | 'trace_object' | 'trace_input_output_only'
          - `luna_output_type` 'float' | 'string' | 'string_list' | 'bool_list'
          - `class_name_to_vocab_ix` union
            - object
            - object
          - `executor` 'action_completion_luna' | 'action_advancement_luna' | 'agentic_session_success' | 'agentic_session_success' | 'action_completion_vision' | 'action_completion_audio' | 'agentic_workflow_success' | 'agentic_workflow_success' | 'agent_efficiency' | 'agent_flow' | 'agent_flow_vision' | 'agent_flow_audio' | 'chunk_attribution_utilization_luna' | 'chunk_attribution_utilization' | 'chunk_relevance' | 'chunk_relevance_luna' | 'context_precision' | 'precision_at_k' | 'completeness_luna' | 'completeness' | 'context_adherence' | 'context_adherence_luna' | 'context_adherence_vision' | 'context_adherence_audio' | 'context_relevance' | 'context_relevance_luna' | 'conversation_quality' | 'conversation_quality_vision' | 'conversation_quality_audio' | 'correctness' | 'correctness_vision' | 'correctness_audio' | 'ground_truth_adherence' | 'ground_truth_adherence_vision' | 'ground_truth_adherence_audio' | 'visual_fidelity' | 'visual_quality' | 'input_pii' | 'input_pii_gpt' | 'input_sexist' | 'input_sexist' | 'input_sexist_vision' | 'input_sexist_audio' | 'input_sexist_luna' | 'input_sexist_luna' | 'input_tone' | 'input_tone_gpt' | 'input_toxicity' | 'input_toxicity_luna' | 'input_toxicity_vision' | 'input_toxicity_audio' | 'instruction_adherence' | 'instruction_adherence_vision' | 'instruction_adherence_audio' | 'output_pii' | 'output_pii_gpt' | 'output_sexist' | 'output_sexist' | 'output_sexist_vision' | 'output_sexist_audio' | 'output_sexist_luna' | 'output_sexist_luna' | 'output_tone' | 'output_tone_gpt' | 'output_toxicity' | 'output_toxicity_luna' | 'output_toxicity_vision' | 'output_toxicity_audio' | 'prompt_injection' | 'prompt_injection_vision' | 'prompt_injection_audio' | 'prompt_injection_luna' | 'reasoning_coherence' | 'reasoning_coherence_vision' | 'reasoning_coherence_audio' | 'sql_efficiency' | 'sql_adherence' | 'sql_injection' | 'sql_correctness' | 'tool_error_rate' | 'tool_error_rate_luna' | 'tool_selection_quality' | 'tool_selection_quality_vision' | 'tool_selection_quality_audio' | 'tool_selection_quality_luna' | 'user_intent_change' | 'user_intent_change_vision' | 'user_intent_change_audio' | 'interruption_detection'
        - `model_name` string, nullable
        - `num_judges` integer, nullable
        - `cot_enabled` boolean, nullable — Whether to enable chain of thought for this scorer. Defaults to False for llm scorers.
      - `scoreable_node_types` string[], nullable — List of node types that can be scored by this scorer. Defaults to llm/chat.
      - `cot_enabled` boolean, nullable — Whether to enable chain of thought for this scorer. Defaults to False for llm scorers.
      - `output_type` 'boolean' | 'categorical' | 'count' | 'discrete' | 'freeform' | 'percentage' | 'multilabel' | 'retrieved_chunk_list_boolean' | 'boolean_multilabel' — Enumeration of output types.
      - `input_type` 'basic' | 'llm_spans' | 'retriever_spans' | 'sessions_normalized' | 'sessions_trace_io_only' | 'tool_spans' | 'trace_input_only' | 'trace_io_only' | 'trace_normalized' | 'trace_output_only' | 'agent_spans' | 'workflow_spans' — Enumeration of input types.
      - `multimodal_capabilities` MultimodalCapability[], nullable — Multimodal capabilities which this scorer can utilize in its evaluation.
      - `roll_up_config` BaseMetricRollUpConfigDB — Configuration for rolling up metrics to parent/trace/session.
        - `roll_up_methods` union, required — List of roll up methods to apply to the metric. For numeric scorers we support doing multiple roll up types per metric.
          - NumericRollUpMethod[]
          - CategoricalRollUpMethod[]
      - `score_type` string, nullable — Return type of code scorers (e.g., 'bool', 'int', 'float', 'str').
    - union[]
      - union
        - AgenticWorkflowSuccessScorer
          - `name` 'agentic_workflow_success'
          - `filters` union[], nullable — List of filters to apply to the scorer.
            - union
              - …
          - `type` 'luna' | 'plus'
          - `model_name` string, nullable — Alias of the model to use for the scorer.
          - `num_judges` integer, nullable — Number of judges for the scorer.
        - AgenticSessionSuccessScorer
          - `name` 'agentic_session_success'
          - `filters` union[], nullable — List of filters to apply to the scorer.
            - union
              - …
          - `type` 'luna' | 'plus'
          - `model_name` string, nullable — Alias of the model to use for the scorer.
          - `num_judges` integer, nullable — Number of judges for the scorer.
        - ChunkAttributionUtilizationScorer
          - `name` 'chunk_attribution_utilization'
          - `filters` union[], nullable — List of filters to apply to the scorer.
            - union
              - …
          - `type` 'luna' | 'plus'
          - `model_name` string, nullable — Alias of the model to use for the scorer.
        - CompletenessScorer
          - `name` 'completeness'
          - `filters` union[], nullable — List of filters to apply to the scorer.
            - union
              - …
          - `type` 'luna' | 'plus'
          - `model_name` string, nullable — Alias of the model to use for the scorer.
          - `num_judges` integer, nullable — Number of judges for the scorer.
        - ContextAdherenceScorer
          - `name` 'context_adherence'
          - `filters` union[], nullable — List of filters to apply to the scorer.
            - union
              - …
          - `type` 'luna' | 'plus'
          - `model_name` string, nullable — Alias of the model to use for the scorer.
          - `num_judges` integer, nullable — Number of judges for the scorer.
        - ContextRelevanceScorer
          - `name` 'context_relevance'
          - `filters` union[], nullable — List of filters to apply to the scorer.
            - union
              - …
        - CorrectnessScorer
          - `name` 'correctness'
          - `filters` union[], nullable — List of filters to apply to the scorer.
            - union
              - …
          - `type` 'plus'
          - `model_name` string, nullable — Alias of the model to use for the scorer.
          - `num_judges` integer, nullable — Number of judges for the scorer.
        - GroundTruthAdherenceScorer
          - `name` 'ground_truth_adherence'
          - `filters` union[], nullable — List of filters to apply to the scorer.
            - union
              - …
          - `type` 'plus'
          - `model_name` string, nullable — Alias of the model to use for the scorer.
          - `num_judges` integer, nullable — Number of judges for the scorer.
        - InputPIIScorer
          - `name` 'input_pii'
          - `filters` union[], nullable — List of filters to apply to the scorer.
            - union
              - …
        - InputSexistScorer
          - `name` 'input_sexist'
          - `filters` union[], nullable — List of filters to apply to the scorer.
            - union
              - …
          - `type` 'luna' | 'plus'
          - `model_name` string, nullable — Alias of the model to use for the scorer.
          - `num_judges` integer, nullable — Number of judges for the scorer.
        - InputToneScorer
          - `name` 'input_tone'
          - `filters` union[], nullable — List of filters to apply to the scorer.
            - union
              - …
        - InputToxicityScorer
          - `name` 'input_toxicity'
          - `filters` union[], nullable — List of filters to apply to the scorer.
            - union
              - …
          - `type` 'luna' | 'plus'
          - `model_name` string, nullable — Alias of the model to use for the scorer.
          - `num_judges` integer, nullable — Number of judges for the scorer.
        - InstructionAdherenceScorer
          - `name` 'instruction_adherence'
          - `filters` union[], nullable — List of filters to apply to the scorer.
            - union
              - …
          - `type` 'plus'
          - `model_name` string, nullable — Alias of the model to use for the scorer.
          - `num_judges` integer, nullable — Number of judges for the scorer.
        - OutputPIIScorer
          - `name` 'output_pii'
          - `filters` union[], nullable — List of filters to apply to the scorer.
            - union
              - …
        - OutputSexistScorer
          - `name` 'output_sexist'
          - `filters` union[], nullable — List of filters to apply to the scorer.
            - union
              - …
          - `type` 'luna' | 'plus'
          - `model_name` string, nullable — Alias of the model to use for the scorer.
          - `num_judges` integer, nullable — Number of judges for the scorer.
        - OutputToneScorer
          - `name` 'output_tone'
          - `filters` union[], nullable — List of filters to apply to the scorer.
            - union
              - …
        - OutputToxicityScorer
          - `name` 'output_toxicity'
          - `filters` union[], nullable — List of filters to apply to the scorer.
            - union
              - …
          - `type` 'luna' | 'plus'
          - `model_name` string, nullable — Alias of the model to use for the scorer.
          - `num_judges` integer, nullable — Number of judges for the scorer.
        - PromptInjectionScorer
          - `name` 'prompt_injection'
          - `filters` union[], nullable — List of filters to apply to the scorer.
            - union
              - …
          - `type` 'luna' | 'plus'
          - `model_name` string, nullable — Alias of the model to use for the scorer.
          - `num_judges` integer, nullable — Number of judges for the scorer.
        - ToolErrorRateScorer
          - `name` 'tool_error_rate'
          - `filters` union[], nullable — List of filters to apply to the scorer.
            - union
              - …
          - `type` 'luna' | 'plus'
          - `model_name` string, nullable — Alias of the model to use for the scorer.
        - ToolSelectionQualityScorer
          - `name` 'tool_selection_quality'
          - `filters` union[], nullable — List of filters to apply to the scorer.
            - union
              - …
          - `type` 'luna' | 'plus'
          - `model_name` string, nullable — Alias of the model to use for the scorer.
          - `num_judges` integer, nullable — Number of judges for the scorer.
  - `prompt_registered_scorers_configuration` RegisteredScorer[], nullable
    - `id` string, uuid4, nullable
    - `name` string, nullable
    - `filters` union[], nullable
      - union
        - NodeNameFilter — Filters on node names in scorer jobs.
          - `name` 'node_name'
          - `operator` 'eq' | 'ne' | 'contains' | 'one_of' | 'not_in', required
          - `value` union, required
            - string
            - string[]
          - `case_sensitive` boolean
        - MetadataFilter — Filters on metadata key-value pairs in scorer jobs.
          - `name` 'metadata'
          - `operator` 'one_of' | 'not_in' | 'eq' | 'ne', required
          - `key` string, required
          - `value` union, required
            - string
            - string[]
        - ModalityFilter — Filters on content modalities in scorer jobs. Matches if at least one of the specified modalities is present.
          - `name` 'modality'
          - `operator` 'eq' | 'ne' | 'one_of' | 'not_in', required
          - `value` union, required
            - string — Single enum value - specific options depend on the concrete enum type used
            - string[] — Array of enum values
  - `prompt_generated_scorers_configuration` string[], nullable
  - `prompt_finetuned_scorers_configuration` FineTunedScorer[], nullable
    - `id` string, uuid4, nullable
    - `name` string, nullable
    - `filters` union[], nullable
      - union
        - NodeNameFilter — Filters on node names in scorer jobs.
          - `name` 'node_name'
          - `operator` 'eq' | 'ne' | 'contains' | 'one_of' | 'not_in', required
          - `value` union, required
            - string
            - string[]
          - `case_sensitive` boolean
        - MetadataFilter — Filters on metadata key-value pairs in scorer jobs.
          - `name` 'metadata'
          - `operator` 'one_of' | 'not_in' | 'eq' | 'ne', required
          - `key` string, required
          - `value` union, required
            - string
            - string[]
        - ModalityFilter — Filters on content modalities in scorer jobs. Matches if at least one of the specified modalities is present.
          - `name` 'modality'
          - `operator` 'eq' | 'ne' | 'one_of' | 'not_in', required
          - `value` union, required
            - string — Single enum value - specific options depend on the concrete enum type used
            - string[] — Array of enum values
  - `prompt_scorers_configuration` ScorersConfiguration — Configure which scorers to enable for a particular prompt run. The keys here are sorted by their approximate execution time to execute the scorers that we anticipate will be the fastest first, and the slowest last.
    - `latency` boolean
    - `cost` boolean
    - `pii` boolean
    - `input_pii` boolean
    - `protect_status` boolean
    - `context_relevance` boolean
    - `toxicity` boolean
    - `input_toxicity` boolean
    - `tone` boolean
    - `input_tone` boolean
    - `sexist` boolean
    - `input_sexist` boolean
    - `prompt_injection` boolean
    - `adherence_nli` boolean
    - `chunk_attribution_utilization_nli` boolean
    - `context_adherence_luna` boolean
    - `context_relevance_luna` boolean
    - `chunk_relevance_luna` boolean
    - `completeness_luna` boolean
    - `completeness_nli` boolean
    - `tool_error_rate_luna` boolean
    - `tool_selection_quality_luna` boolean
    - `action_completion_luna` boolean
    - `action_advancement_luna` boolean
    - `factuality` boolean
    - `groundedness` boolean
    - `chunk_attribution_utilization_gpt` boolean
    - `completeness_gpt` boolean
    - `instruction_adherence` boolean
    - `ground_truth_adherence` boolean
    - `tool_selection_quality` boolean
    - `tool_error_rate` boolean
    - `agentic_session_success` boolean
    - `agentic_workflow_success` boolean
    - `prompt_injection_gpt` boolean
    - `sexist_gpt` boolean
    - `input_sexist_gpt` boolean
    - `toxicity_gpt` boolean
    - `input_toxicity_gpt` boolean
  - `prompt_customized_scorers_configuration` union[], nullable
    - union
      - CustomizedAgenticSessionSuccessGPTScorer
        - `scorer_name` '_customized_agentic_session_success'
        - `model_alias` string
        - `num_judges` integer
        - `name` 'agentic_session_success'
        - `scores` unknown[], nullable
          - unknown
        - `indices` integer[], nullable
        - `aggregates` object, nullable
        - `aggregate_keys` string[]
        - `extra` object, nullable
        - `sub_scorers` PromptgalileoSchemasScorerNameScorerName[]
        - `filters` union[], nullable
          - union
            - NodeNameFilter — Filters on node names in scorer jobs.
              - …
            - MetadataFilter — Filters on metadata key-value pairs in scorer jobs.
              - …
            - ModalityFilter — Filters on content modalities in scorer jobs. Matches if at least one of the specified modalities is present.
              - …
        - `metric_name` string, nullable
        - `description` string, nullable
        - `chainpoll_template` AgenticSessionSuccessTemplate — Template for the agentic session success metric, containing all the info necessary to send the agentic session success prompt.
          - `metric_system_prompt` string
          - `metric_description` string
          - `value_field_name` string
          - `explanation_field_name` string — Field name to look for in the chainpoll response, for the explanation.
          - `template` string
          - `metric_few_shot_examples` FewShotExample[]
            - `generation_prompt_and_response` string, required
            - `evaluating_response` string, required
          - `response_schema` object, nullable — Response schema for the output
        - `default_model_alias` string, nullable
        - `ground_truth` boolean, nullable
        - `regex_field` string
        - `registered_scorer_id` string, uuid4, nullable
        - `generated_scorer_id` string, uuid4, nullable
        - `scorer_version_id` string, uuid4, nullable
        - `user_code` string, nullable
        - `can_copy_to_llm` boolean, nullable
        - `scoreable_node_types` NodeType[], nullable
        - `cot_enabled` boolean, nullable
        - `output_type` 'boolean' | 'categorical' | 'count' | 'discrete' | 'freeform' | 'percentage' | 'multilabel' | 'retrieved_chunk_list_boolean' | 'boolean_multilabel' — Enumeration of output types.
        - `input_type` 'basic' | 'llm_spans' | 'retriever_spans' | 'sessions_normalized' | 'sessions_trace_io_only' | 'tool_spans' | 'trace_input_only' | 'trace_io_only' | 'trace_normalized' | 'trace_output_only' | 'agent_spans' | 'workflow_spans' — Enumeration of input types.
        - `multimodal_capabilities` MultimodalCapability[], nullable
        - `requires_tools_in_llm_span` boolean
        - `required_scorers` string[], nullable
        - `required_metric_ids` string[], nullable
        - `roll_up_strategy` 'avg' | 'sum' | 'first' | 'last' | 'none' — Strategies for rolling metrics up the Session/Trace/Span hierarchy.
        - `roll_up_methods` union
          - NumericRollUpMethod[]
          - CategoricalRollUpMethod[]
        - `prompt` string, nullable
        - `lora_task_id` integer, nullable
        - `lora_weights_path` string, nullable
        - `luna_input_type` 'span' | 'trace_object' | 'trace_input_output_only'
        - `luna_output_type` 'float' | 'string' | 'string_list' | 'bool_list'
        - `class_name_to_vocab_ix` union
          - object
          - object
        - `scorer_path_name` string, nullable
      - CustomizedAgenticWorkflowSuccessGPTScorer
        - `scorer_name` '_customized_agentic_workflow_success'
        - `model_alias` string
        - `num_judges` integer
        - `name` 'agentic_workflow_success'
        - `scores` unknown[], nullable
          - unknown
        - `indices` integer[], nullable
        - `aggregates` object, nullable
        - `aggregate_keys` string[]
        - `extra` object, nullable
        - `sub_scorers` PromptgalileoSchemasScorerNameScorerName[]
        - `filters` union[], nullable
          - union
            - NodeNameFilter — Filters on node names in scorer jobs.
              - …
            - MetadataFilter — Filters on metadata key-value pairs in scorer jobs.
              - …
            - ModalityFilter — Filters on content modalities in scorer jobs. Matches if at least one of the specified modalities is present.
              - …
        - `metric_name` string, nullable
        - `description` string, nullable
        - `chainpoll_template` AgenticWorkflowSuccessTemplate — Template for the agentic workflow success metric, containing all the info necessary to send the agentic workflow success prompt.
          - `metric_system_prompt` string
          - `metric_description` string
          - `value_field_name` string
          - `explanation_field_name` string — Field name to look for in the chainpoll response, for the explanation.
          - `template` string
          - `metric_few_shot_examples` FewShotExample[]
            - `generation_prompt_and_response` string, required
            - `evaluating_response` string, required
          - `response_schema` object, nullable — Response schema for the output
        - `default_model_alias` string, nullable
        - `ground_truth` boolean, nullable
        - `regex_field` string
        - `registered_scorer_id` string, uuid4, nullable
        - `generated_scorer_id` string, uuid4, nullable
        - `scorer_version_id` string, uuid4, nullable
        - `user_code` string, nullable
        - `can_copy_to_llm` boolean, nullable
        - `scoreable_node_types` NodeType[], nullable
        - `cot_enabled` boolean, nullable
        - `output_type` 'boolean' | 'categorical' | 'count' | 'discrete' | 'freeform' | 'percentage' | 'multilabel' | 'retrieved_chunk_list_boolean' | 'boolean_multilabel' — Enumeration of output types.
        - `input_type` 'basic' | 'llm_spans' | 'retriever_spans' | 'sessions_normalized' | 'sessions_trace_io_only' | 'tool_spans' | 'trace_input_only' | 'trace_io_only' | 'trace_normalized' | 'trace_output_only' | 'agent_spans' | 'workflow_spans' — Enumeration of input types.
        - `multimodal_capabilities` MultimodalCapability[], nullable
        - `requires_tools_in_llm_span` boolean
        - `required_scorers` string[], nullable
        - `required_metric_ids` string[], nullable
        - `roll_up_strategy` 'avg' | 'sum' | 'first' | 'last' | 'none' — Strategies for rolling metrics up the Session/Trace/Span hierarchy.
        - `roll_up_methods` union
          - NumericRollUpMethod[]
          - CategoricalRollUpMethod[]
        - `prompt` string, nullable
        - `lora_task_id` integer, nullable
        - `lora_weights_path` string, nullable
        - `luna_input_type` 'span' | 'trace_object' | 'trace_input_output_only'
        - `luna_output_type` 'float' | 'string' | 'string_list' | 'bool_list'
        - `class_name_to_vocab_ix` union
          - object
          - object
        - `scorer_path_name` string, nullable
      - CustomizedChunkAttributionUtilizationGPTScorer
        - `scorer_name` '_customized_chunk_attribution_utilization_gpt'
        - `model_alias` string
        - `num_judges` integer
        - `name` 'chunk_attribution_utilization'
        - `scores` unknown[], nullable
          - unknown
        - `indices` integer[], nullable
        - `aggregates` object, nullable
        - `aggregate_keys` string[]
        - `extra` object, nullable
        - `sub_scorers` PromptgalileoSchemasScorerNameScorerName[]
        - `filters` union[], nullable
          - union
            - NodeNameFilter — Filters on node names in scorer jobs.
              - …
            - MetadataFilter — Filters on metadata key-value pairs in scorer jobs.
              - …
            - ModalityFilter — Filters on content modalities in scorer jobs. Matches if at least one of the specified modalities is present.
              - …
        - `metric_name` string, nullable
        - `description` string, nullable
        - `chainpoll_template` ChunkAttributionUtilizationTemplate
          - `metric_system_prompt` string, nullable — System prompt for the metric.
          - `metric_description` string, nullable — Description of what the metric should do.
          - `value_field_name` string — Field name to look for in the chainpoll response, for the rating.
          - `explanation_field_name` string — Field name to look for in the chainpoll response, for the explanation.
          - `template` string
          - `metric_few_shot_examples` FewShotExample[] — Few-shot examples for the metric.
            - `generation_prompt_and_response` string, required
            - `evaluating_response` string, required
          - `response_schema` object, nullable — Response schema for the output
        - `default_model_alias` string, nullable
        - `ground_truth` boolean, nullable
        - `regex_field` string
        - `registered_scorer_id` string, uuid4, nullable
        - `generated_scorer_id` string, uuid4, nullable
        - `scorer_version_id` string, uuid4, nullable
        - `user_code` string, nullable
        - `can_copy_to_llm` boolean, nullable
        - `scoreable_node_types` NodeType[], nullable
        - `cot_enabled` boolean, nullable
        - `output_type` 'boolean' | 'categorical' | 'count' | 'discrete' | 'freeform' | 'percentage' | 'multilabel' | 'retrieved_chunk_list_boolean' | 'boolean_multilabel' — Enumeration of output types.
        - `input_type` 'basic' | 'llm_spans' | 'retriever_spans' | 'sessions_normalized' | 'sessions_trace_io_only' | 'tool_spans' | 'trace_input_only' | 'trace_io_only' | 'trace_normalized' | 'trace_output_only' | 'agent_spans' | 'workflow_spans' — Enumeration of input types.
        - `multimodal_capabilities` MultimodalCapability[], nullable
        - `requires_tools_in_llm_span` boolean
        - `required_scorers` string[], nullable
        - `required_metric_ids` string[], nullable
        - `roll_up_strategy` 'avg' | 'sum' | 'first' | 'last' | 'none' — Strategies for rolling metrics up the Session/Trace/Span hierarchy.
        - `roll_up_methods` union
          - NumericRollUpMethod[]
          - CategoricalRollUpMethod[]
        - `prompt` string, nullable
        - `lora_task_id` integer, nullable
        - `lora_weights_path` string, nullable
        - `luna_input_type` 'span' | 'trace_object' | 'trace_input_output_only'
        - `luna_output_type` 'float' | 'string' | 'string_list' | 'bool_list'
        - `class_name_to_vocab_ix` union
          - object
          - object
        - `scorer_path_name` string, nullable
      - CustomizedCompletenessGPTScorer
        - `scorer_name` '_customized_completeness_gpt'
        - `model_alias` string
        - `num_judges` integer
        - `name` 'completeness'
        - `scores` unknown[], nullable
          - unknown
        - `indices` integer[], nullable
        - `aggregates` object, nullable
        - `aggregate_keys` string[]
        - `extra` object, nullable
        - `sub_scorers` PromptgalileoSchemasScorerNameScorerName[]
        - `filters` union[], nullable
          - union
            - NodeNameFilter — Filters on node names in scorer jobs.
              - …
            - MetadataFilter — Filters on metadata key-value pairs in scorer jobs.
              - …
            - ModalityFilter — Filters on content modalities in scorer jobs. Matches if at least one of the specified modalities is present.
              - …
        - `metric_name` string, nullable
        - `description` string, nullable
        - `chainpoll_template` CompletenessTemplate
          - `metric_system_prompt` string, nullable — System prompt for the metric.
          - `metric_description` string, nullable — Description of what the metric should do.
          - `value_field_name` string
          - `explanation_field_name` string — Field name to look for in the chainpoll response, for the explanation.
          - `template` string
          - `metric_few_shot_examples` FewShotExample[] — Few-shot examples for the metric.
            - `generation_prompt_and_response` string, required
            - `evaluating_response` string, required
          - `response_schema` object, nullable — Response schema for the output
        - `default_model_alias` string, nullable
        - `ground_truth` boolean, nullable
        - `regex_field` string
        - `registered_scorer_id` string, uuid4, nullable
        - `generated_scorer_id` string, uuid4, nullable
        - `scorer_version_id` string, uuid4, nullable
        - `user_code` string, nullable
        - `can_copy_to_llm` boolean, nullable
        - `scoreable_node_types` NodeType[], nullable
        - `cot_enabled` boolean, nullable
        - `output_type` 'boolean' | 'categorical' | 'count' | 'discrete' | 'freeform' | 'percentage' | 'multilabel' | 'retrieved_chunk_list_boolean' | 'boolean_multilabel' — Enumeration of output types.
        - `input_type` 'basic' | 'llm_spans' | 'retriever_spans' | 'sessions_normalized' | 'sessions_trace_io_only' | 'tool_spans' | 'trace_input_only' | 'trace_io_only' | 'trace_normalized' | 'trace_output_only' | 'agent_spans' | 'workflow_spans' — Enumeration of input types.
        - `multimodal_capabilities` MultimodalCapability[], nullable
        - `requires_tools_in_llm_span` boolean
        - `required_scorers` string[], nullable
        - `required_metric_ids` string[], nullable
        - `roll_up_strategy` 'avg' | 'sum' | 'first' | 'last' | 'none' — Strategies for rolling metrics up the Session/Trace/Span hierarchy.
        - `roll_up_methods` union
          - NumericRollUpMethod[]
          - CategoricalRollUpMethod[]
        - `prompt` string, nullable
        - `lora_task_id` integer, nullable
        - `lora_weights_path` string, nullable
        - `luna_input_type` 'span' | 'trace_object' | 'trace_input_output_only'
        - `luna_output_type` 'float' | 'string' | 'string_list' | 'bool_list'
        - `class_name_to_vocab_ix` union
          - object
          - object
        - `scorer_path_name` string, nullable
      - CustomizedFactualityGPTScorer
        - `scorer_name` '_customized_factuality'
        - `model_alias` string
        - `num_judges` integer
        - `name` 'correctness'
        - `scores` unknown[], nullable
          - unknown
        - `indices` integer[], nullable
        - `aggregates` object, nullable
        - `aggregate_keys` string[]
        - `extra` object, nullable
        - `sub_scorers` PromptgalileoSchemasScorerNameScorerName[]
        - `filters` union[], nullable
          - union
            - NodeNameFilter — Filters on node names in scorer jobs.
              - …
            - MetadataFilter — Filters on metadata key-value pairs in scorer jobs.
              - …
            - ModalityFilter — Filters on content modalities in scorer jobs. Matches if at least one of the specified modalities is present.
              - …
        - `metric_name` string, nullable
        - `description` string, nullable
        - `chainpoll_template` FactualityTemplate
          - `metric_system_prompt` string
          - `metric_description` string, nullable — Description of what the metric should do.
          - `value_field_name` string
          - `explanation_field_name` string — Field name to look for in the chainpoll response, for the explanation.
          - `template` string
          - `metric_few_shot_examples` FewShotExample[]
            - `generation_prompt_and_response` string, required
            - `evaluating_response` string, required
          - `response_schema` object, nullable — Response schema for the output
        - `default_model_alias` string, nullable
        - `ground_truth` boolean, nullable
        - `regex_field` string
        - `registered_scorer_id` string, uuid4, nullable
        - `generated_scorer_id` string, uuid4, nullable
        - `scorer_version_id` string, uuid4, nullable
        - `user_code` string, nullable
        - `can_copy_to_llm` boolean, nullable
        - `scoreable_node_types` NodeType[], nullable
        - `cot_enabled` boolean, nullable
        - `output_type` 'boolean' | 'categorical' | 'count' | 'discrete' | 'freeform' | 'percentage' | 'multilabel' | 'retrieved_chunk_list_boolean' | 'boolean_multilabel' — Enumeration of output types.
        - `input_type` 'basic' | 'llm_spans' | 'retriever_spans' | 'sessions_normalized' | 'sessions_trace_io_only' | 'tool_spans' | 'trace_input_only' | 'trace_io_only' | 'trace_normalized' | 'trace_output_only' | 'agent_spans' | 'workflow_spans' — Enumeration of input types.
        - `multimodal_capabilities` MultimodalCapability[], nullable
        - `requires_tools_in_llm_span` boolean
        - `required_scorers` string[], nullable
        - `required_metric_ids` string[], nullable
        - `roll_up_strategy` 'avg' | 'sum' | 'first' | 'last' | 'none' — Strategies for rolling metrics up the Session/Trace/Span hierarchy.
        - `roll_up_methods` union
          - NumericRollUpMethod[]
          - CategoricalRollUpMethod[]
        - `prompt` string, nullable
        - `lora_task_id` integer, nullable
        - `lora_weights_path` string, nullable
        - `luna_input_type` 'span' | 'trace_object' | 'trace_input_output_only'
        - `luna_output_type` 'float' | 'string' | 'string_list' | 'bool_list'
        - `class_name_to_vocab_ix` union
          - object
          - object
        - `scorer_path_name` string, nullable
        - `function_explanation_param_name` string
      - CustomizedGroundednessGPTScorer
        - `scorer_name` '_customized_groundedness'
        - `model_alias` string
        - `num_judges` integer
        - `name` 'context_adherence'
        - `scores` unknown[], nullable
          - unknown
        - `indices` integer[], nullable
        - `aggregates` object, nullable
        - `aggregate_keys` string[]
        - `extra` object, nullable
        - `sub_scorers` PromptgalileoSchemasScorerNameScorerName[]
        - `filters` union[], nullable
          - union
            - NodeNameFilter — Filters on node names in scorer jobs.
              - …
            - MetadataFilter — Filters on metadata key-value pairs in scorer jobs.
              - …
            - ModalityFilter — Filters on content modalities in scorer jobs. Matches if at least one of the specified modalities is present.
              - …
        - `metric_name` string, nullable
        - `description` string, nullable
        - `chainpoll_template` GroundednessTemplate — Template for the groundedness metric, containing all the info necessary to send the groundedness prompt.
          - `metric_system_prompt` string
          - `metric_description` string
          - `value_field_name` string
          - `explanation_field_name` string — Field name to look for in the chainpoll response, for the explanation.
          - `template` string
          - `metric_few_shot_examples` FewShotExample[]
            - `generation_prompt_and_response` string, required
            - `evaluating_response` string, required
          - `response_schema` object, nullable — Response schema for the output
        - `default_model_alias` string, nullable
        - `ground_truth` boolean, nullable
        - `regex_field` string
        - `registered_scorer_id` string, uuid4, nullable
        - `generated_scorer_id` string, uuid4, nullable
        - `scorer_version_id` string, uuid4, nullable
        - `user_code` string, nullable
        - `can_copy_to_llm` boolean, nullable
        - `scoreable_node_types` NodeType[], nullable
        - `cot_enabled` boolean, nullable
        - `output_type` 'boolean' | 'categorical' | 'count' | 'discrete' | 'freeform' | 'percentage' | 'multilabel' | 'retrieved_chunk_list_boolean' | 'boolean_multilabel' — Enumeration of output types.
        - `input_type` 'basic' | 'llm_spans' | 'retriever_spans' | 'sessions_normalized' | 'sessions_trace_io_only' | 'tool_spans' | 'trace_input_only' | 'trace_io_only' | 'trace_normalized' | 'trace_output_only' | 'agent_spans' | 'workflow_spans' — Enumeration of input types.
        - `multimodal_capabilities` MultimodalCapability[], nullable
        - `requires_tools_in_llm_span` boolean
        - `required_scorers` string[], nullable
        - `required_metric_ids` string[], nullable
        - `roll_up_strategy` 'avg' | 'sum' | 'first' | 'last' | 'none' — Strategies for rolling metrics up the Session/Trace/Span hierarchy.
        - `roll_up_methods` union
          - NumericRollUpMethod[]
          - CategoricalRollUpMethod[]
        - `prompt` string, nullable
        - `lora_task_id` integer, nullable
        - `lora_weights_path` string, nullable
        - `luna_input_type` 'span' | 'trace_object' | 'trace_input_output_only'
        - `luna_output_type` 'float' | 'string' | 'string_list' | 'bool_list'
        - `class_name_to_vocab_ix` union
          - object
          - object
        - `scorer_path_name` string, nullable
      - CustomizedInstructionAdherenceGPTScorer
        - `scorer_name` '_customized_instruction_adherence'
        - `model_alias` string
        - `num_judges` integer
        - `name` 'instruction_adherence'
        - `scores` unknown[], nullable
          - unknown
        - `indices` integer[], nullable
        - `aggregates` object, nullable
        - `aggregate_keys` string[]
        - `extra` object, nullable
        - `sub_scorers` PromptgalileoSchemasScorerNameScorerName[]
        - `filters` union[], nullable
          - union
            - NodeNameFilter — Filters on node names in scorer jobs.
              - …
            - MetadataFilter — Filters on metadata key-value pairs in scorer jobs.
              - …
            - ModalityFilter — Filters on content modalities in scorer jobs. Matches if at least one of the specified modalities is present.
              - …
        - `metric_name` string, nullable
        - `description` string, nullable
        - `chainpoll_template` InstructionAdherenceTemplate
          - `metric_system_prompt` string
          - `metric_description` string
          - `value_field_name` string
          - `explanation_field_name` string — Field name to look for in the chainpoll response, for the explanation.
          - `template` string
          - `metric_few_shot_examples` FewShotExample[]
            - `generation_prompt_and_response` string, required
            - `evaluating_response` string, required
          - `response_schema` object, nullable — Response schema for the output
        - `default_model_alias` string, nullable
        - `ground_truth` boolean, nullable
        - `regex_field` string
        - `registered_scorer_id` string, uuid4, nullable
        - `generated_scorer_id` string, uuid4, nullable
        - `scorer_version_id` string, uuid4, nullable
        - `user_code` string, nullable
        - `can_copy_to_llm` boolean, nullable
        - `scoreable_node_types` NodeType[], nullable
        - `cot_enabled` boolean, nullable
        - `output_type` 'boolean' | 'categorical' | 'count' | 'discrete' | 'freeform' | 'percentage' | 'multilabel' | 'retrieved_chunk_list_boolean' | 'boolean_multilabel' — Enumeration of output types.
        - `input_type` 'basic' | 'llm_spans' | 'retriever_spans' | 'sessions_normalized' | 'sessions_trace_io_only' | 'tool_spans' | 'trace_input_only' | 'trace_io_only' | 'trace_normalized' | 'trace_output_only' | 'agent_spans' | 'workflow_spans' — Enumeration of input types.
        - `multimodal_capabilities` MultimodalCapability[], nullable
        - `requires_tools_in_llm_span` boolean
        - `required_scorers` string[], nullable
        - `required_metric_ids` string[], nullable
        - `roll_up_strategy` 'avg' | 'sum' | 'first' | 'last' | 'none' — Strategies for rolling metrics up the Session/Trace/Span hierarchy.
        - `roll_up_methods` union
          - NumericRollUpMethod[]
          - CategoricalRollUpMethod[]
        - `prompt` string, nullable
        - `lora_task_id` integer, nullable
        - `lora_weights_path` string, nullable
        - `luna_input_type` 'span' | 'trace_object' | 'trace_input_output_only'
        - `luna_output_type` 'float' | 'string' | 'string_list' | 'bool_list'
        - `class_name_to_vocab_ix` union
          - object
          - object
        - `scorer_path_name` string, nullable
        - `function_explanation_param_name` string
      - CustomizedGroundTruthAdherenceGPTScorer
        - `scorer_name` '_customized_ground_truth_adherence'
        - `model_alias` string
        - `num_judges` integer
        - `name` 'ground_truth_adherence'
        - `scores` unknown[], nullable
          - unknown
        - `indices` integer[], nullable
        - `aggregates` object, nullable
        - `aggregate_keys` string[]
        - `extra` object, nullable
        - `sub_scorers` PromptgalileoSchemasScorerNameScorerName[]
        - `filters` union[], nullable
          - union
            - NodeNameFilter — Filters on node names in scorer jobs.
              - …
            - MetadataFilter — Filters on metadata key-value pairs in scorer jobs.
              - …
            - ModalityFilter — Filters on content modalities in scorer jobs. Matches if at least one of the specified modalities is present.
              - …
        - `metric_name` string, nullable
        - `description` string, nullable
        - `chainpoll_template` GroundTruthAdherenceTemplate
          - `metric_system_prompt` string
          - `metric_description` string
          - `value_field_name` string
          - `explanation_field_name` string — Field name to look for in the chainpoll response, for the explanation.
          - `template` string
          - `metric_few_shot_examples` FewShotExample[] — Few-shot examples for the metric.
            - `generation_prompt_and_response` string, required
            - `evaluating_response` string, required
          - `response_schema` object, nullable — Response schema for the output
        - `default_model_alias` string, nullable
        - `ground_truth` boolean, nullable
        - `regex_field` string
        - `registered_scorer_id` string, uuid4, nullable
        - `generated_scorer_id` string, uuid4, nullable
        - `scorer_version_id` string, uuid4, nullable
        - `user_code` string, nullable
        - `can_copy_to_llm` boolean, nullable
        - `scoreable_node_types` NodeType[], nullable
        - `cot_enabled` boolean, nullable
        - `output_type` 'boolean' | 'categorical' | 'count' | 'discrete' | 'freeform' | 'percentage' | 'multilabel' | 'retrieved_chunk_list_boolean' | 'boolean_multilabel' — Enumeration of output types.
        - `input_type` 'basic' | 'llm_spans' | 'retriever_spans' | 'sessions_normalized' | 'sessions_trace_io_only' | 'tool_spans' | 'trace_input_only' | 'trace_io_only' | 'trace_normalized' | 'trace_output_only' | 'agent_spans' | 'workflow_spans' — Enumeration of input types.
        - `multimodal_capabilities` MultimodalCapability[], nullable
        - `requires_tools_in_llm_span` boolean
        - `required_scorers` string[], nullable
        - `required_metric_ids` string[], nullable
        - `roll_up_strategy` 'avg' | 'sum' | 'first' | 'last' | 'none' — Strategies for rolling metrics up the Session/Trace/Span hierarchy.
        - `roll_up_methods` union
          - NumericRollUpMethod[]
          - CategoricalRollUpMethod[]
        - `prompt` string, nullable
        - `lora_task_id` integer, nullable
        - `lora_weights_path` string, nullable
        - `luna_input_type` 'span' | 'trace_object' | 'trace_input_output_only'
        - `luna_output_type` 'float' | 'string' | 'string_list' | 'bool_list'
        - `class_name_to_vocab_ix` union
          - object
          - object
        - `scorer_path_name` string, nullable
      - CustomizedPromptInjectionGPTScorer
        - `scorer_name` '_customized_prompt_injection_gpt'
        - `model_alias` string
        - `num_judges` integer
        - `name` 'prompt_injection'
        - `scores` unknown[], nullable
          - unknown
        - `indices` integer[], nullable
        - `aggregates` object, nullable
        - `aggregate_keys` string[]
        - `extra` object, nullable
        - `sub_scorers` PromptgalileoSchemasScorerNameScorerName[]
        - `filters` union[], nullable
          - union
            - NodeNameFilter — Filters on node names in scorer jobs.
              - …
            - MetadataFilter — Filters on metadata key-value pairs in scorer jobs.
              - …
            - ModalityFilter — Filters on content modalities in scorer jobs. Matches if at least one of the specified modalities is present.
              - …
        - `metric_name` string, nullable
        - `description` string, nullable
        - `chainpoll_template` PromptInjectionTemplate — Template for the prompt injection metric, containing all the info necessary to send the prompt injection prompt.
          - `metric_system_prompt` string
          - `metric_description` string
          - `value_field_name` string
          - `explanation_field_name` string — Field name to look for in the chainpoll response, for the explanation.
          - `template` string
          - `metric_few_shot_examples` FewShotExample[]
            - `generation_prompt_and_response` string, required
            - `evaluating_response` string, required
          - `response_schema` object, nullable — Response schema for the output
        - `default_model_alias` string, nullable
        - `ground_truth` boolean, nullable
        - `regex_field` string
        - `registered_scorer_id` string, uuid4, nullable
        - `generated_scorer_id` string, uuid4, nullable
        - `scorer_version_id` string, uuid4, nullable
        - `user_code` string, nullable
        - `can_copy_to_llm` boolean, nullable
        - `scoreable_node_types` NodeType[], nullable
        - `cot_enabled` boolean, nullable
        - `output_type` 'boolean' | 'categorical' | 'count' | 'discrete' | 'freeform' | 'percentage' | 'multilabel' | 'retrieved_chunk_list_boolean' | 'boolean_multilabel' — Enumeration of output types.
        - `input_type` 'basic' | 'llm_spans' | 'retriever_spans' | 'sessions_normalized' | 'sessions_trace_io_only' | 'tool_spans' | 'trace_input_only' | 'trace_io_only' | 'trace_normalized' | 'trace_output_only' | 'agent_spans' | 'workflow_spans' — Enumeration of input types.
        - `multimodal_capabilities` MultimodalCapability[], nullable
        - `requires_tools_in_llm_span` boolean
        - `required_scorers` string[], nullable
        - `required_metric_ids` string[], nullable
        - `roll_up_strategy` 'avg' | 'sum' | 'first' | 'last' | 'none' — Strategies for rolling metrics up the Session/Trace/Span hierarchy.
        - `roll_up_methods` union
          - NumericRollUpMethod[]
          - CategoricalRollUpMethod[]
        - `prompt` string, nullable
        - `lora_task_id` integer, nullable
        - `lora_weights_path` string, nullable
        - `luna_input_type` 'span' | 'trace_object' | 'trace_input_output_only'
        - `luna_output_type` 'float' | 'string' | 'string_list' | 'bool_list'
        - `class_name_to_vocab_ix` union
          - object
          - object
        - `scorer_path_name` string, nullable
      - CustomizedSexistGPTScorer
        - `scorer_name` '_customized_sexist_gpt'
        - `model_alias` string
        - `num_judges` integer
        - `name` 'output_sexist'
        - `scores` unknown[], nullable
          - unknown
        - `indices` integer[], nullable
        - `aggregates` object, nullable
        - `aggregate_keys` string[]
        - `extra` object, nullable
        - `sub_scorers` PromptgalileoSchemasScorerNameScorerName[]
        - `filters` union[], nullable
          - union
            - NodeNameFilter — Filters on node names in scorer jobs.
              - …
            - MetadataFilter — Filters on metadata key-value pairs in scorer jobs.
              - …
            - ModalityFilter — Filters on content modalities in scorer jobs. Matches if at least one of the specified modalities is present.
              - …
        - `metric_name` string, nullable
        - `description` string, nullable
        - `chainpoll_template` SexistTemplate — Template for the sexism metric, containing all the info necessary to send the sexism prompt.
          - `metric_system_prompt` string
          - `metric_description` string
          - `value_field_name` string
          - `explanation_field_name` string — Field name to look for in the chainpoll response, for the explanation.
          - `template` string
          - `metric_few_shot_examples` FewShotExample[]
            - `generation_prompt_and_response` string, required
            - `evaluating_response` string, required
          - `response_schema` object, nullable — Response schema for the output
        - `default_model_alias` string, nullable
        - `ground_truth` boolean, nullable
        - `regex_field` string
        - `registered_scorer_id` string, uuid4, nullable
        - `generated_scorer_id` string, uuid4, nullable
        - `scorer_version_id` string, uuid4, nullable
        - `user_code` string, nullable
        - `can_copy_to_llm` boolean, nullable
        - `scoreable_node_types` NodeType[], nullable
        - `cot_enabled` boolean, nullable
        - `output_type` 'boolean' | 'categorical' | 'count' | 'discrete' | 'freeform' | 'percentage' | 'multilabel' | 'retrieved_chunk_list_boolean' | 'boolean_multilabel' — Enumeration of output types.
        - `input_type` 'basic' | 'llm_spans' | 'retriever_spans' | 'sessions_normalized' | 'sessions_trace_io_only' | 'tool_spans' | 'trace_input_only' | 'trace_io_only' | 'trace_normalized' | 'trace_output_only' | 'agent_spans' | 'workflow_spans' — Enumeration of input types.
        - `multimodal_capabilities` MultimodalCapability[], nullable
        - `requires_tools_in_llm_span` boolean
        - `required_scorers` string[], nullable
        - `required_metric_ids` string[], nullable
        - `roll_up_strategy` 'avg' | 'sum' | 'first' | 'last' | 'none' — Strategies for rolling metrics up the Session/Trace/Span hierarchy.
        - `roll_up_methods` union
          - NumericRollUpMethod[]
          - CategoricalRollUpMethod[]
        - `prompt` string, nullable
        - `lora_task_id` integer, nullable
        - `lora_weights_path` string, nullable
        - `luna_input_type` 'span' | 'trace_object' | 'trace_input_output_only'
        - `luna_output_type` 'float' | 'string' | 'string_list' | 'bool_list'
        - `class_name_to_vocab_ix` union
          - object
          - object
        - `scorer_path_name` string, nullable
      - CustomizedInputSexistGPTScorer
        - `scorer_name` '_customized_input_sexist_gpt'
        - `model_alias` string
        - `num_judges` integer
        - `name` 'input_sexist'
        - `scores` unknown[], nullable
          - unknown
        - `indices` integer[], nullable
        - `aggregates` object, nullable
        - `aggregate_keys` string[]
        - `extra` object, nullable
        - `sub_scorers` PromptgalileoSchemasScorerNameScorerName[]
        - `filters` union[], nullable
          - union
            - NodeNameFilter — Filters on node names in scorer jobs.
              - …
            - MetadataFilter — Filters on metadata key-value pairs in scorer jobs.
              - …
            - ModalityFilter — Filters on content modalities in scorer jobs. Matches if at least one of the specified modalities is present.
              - …
        - `metric_name` string, nullable
        - `description` string, nullable
        - `chainpoll_template` InputSexistTemplate — Template for the sexism metric, containing all the info necessary to send the sexism prompt.
          - `metric_system_prompt` string
          - `metric_description` string
          - `value_field_name` string
          - `explanation_field_name` string — Field name to look for in the chainpoll response, for the explanation.
          - `template` string
          - `metric_few_shot_examples` FewShotExample[]
            - `generation_prompt_and_response` string, required
            - `evaluating_response` string, required
          - `response_schema` object, nullable — Response schema for the output
        - `default_model_alias` string, nullable
        - `ground_truth` boolean, nullable
        - `regex_field` string
        - `registered_scorer_id` string, uuid4, nullable
        - `generated_scorer_id` string, uuid4, nullable
        - `scorer_version_id` string, uuid4, nullable
        - `user_code` string, nullable
        - `can_copy_to_llm` boolean, nullable
        - `scoreable_node_types` NodeType[], nullable
        - `cot_enabled` boolean, nullable
        - `output_type` 'boolean' | 'categorical' | 'count' | 'discrete' | 'freeform' | 'percentage' | 'multilabel' | 'retrieved_chunk_list_boolean' | 'boolean_multilabel' — Enumeration of output types.
        - `input_type` 'basic' | 'llm_spans' | 'retriever_spans' | 'sessions_normalized' | 'sessions_trace_io_only' | 'tool_spans' | 'trace_input_only' | 'trace_io_only' | 'trace_normalized' | 'trace_output_only' | 'agent_spans' | 'workflow_spans' — Enumeration of input types.
        - `multimodal_capabilities` MultimodalCapability[], nullable
        - `requires_tools_in_llm_span` boolean
        - `required_scorers` string[], nullable
        - `required_metric_ids` string[], nullable
        - `roll_up_strategy` 'avg' | 'sum' | 'first' | 'last' | 'none' — Strategies for rolling metrics up the Session/Trace/Span hierarchy.
        - `roll_up_methods` union
          - NumericRollUpMethod[]
          - CategoricalRollUpMethod[]
        - `prompt` string, nullable
        - `lora_task_id` integer, nullable
        - `lora_weights_path` string, nullable
        - `luna_input_type` 'span' | 'trace_object' | 'trace_input_output_only'
        - `luna_output_type` 'float' | 'string' | 'string_list' | 'bool_list'
        - `class_name_to_vocab_ix` union
          - object
          - object
        - `scorer_path_name` string, nullable
      - CustomizedToolSelectionQualityGPTScorer
        - `scorer_name` '_customized_tool_selection_quality'
        - `model_alias` string
        - `num_judges` integer
        - `name` 'tool_selection_quality'
        - `scores` unknown[], nullable
          - unknown
        - `indices` integer[], nullable
        - `aggregates` object, nullable
        - `aggregate_keys` string[]
        - `extra` object, nullable
        - `sub_scorers` PromptgalileoSchemasScorerNameScorerName[]
        - `filters` union[], nullable
          - union
            - NodeNameFilter — Filters on node names in scorer jobs.
              - …
            - MetadataFilter — Filters on metadata key-value pairs in scorer jobs.
              - …
            - ModalityFilter — Filters on content modalities in scorer jobs. Matches if at least one of the specified modalities is present.
              - …
        - `metric_name` string, nullable
        - `description` string, nullable
        - `chainpoll_template` ToolSelectionQualityTemplate — Template for the tool selection quality metric, containing all the info necessary to send the tool selection quality prompt.
          - `metric_system_prompt` string
          - `metric_description` string
          - `value_field_name` string
          - `explanation_field_name` string — Field name to look for in the chainpoll response, for the explanation.
          - `template` string
          - `metric_few_shot_examples` FewShotExample[]
            - `generation_prompt_and_response` string, required
            - `evaluating_response` string, required
          - `response_schema` object, nullable — Response schema for the output
        - `default_model_alias` string, nullable
        - `ground_truth` boolean, nullable
        - `regex_field` string
        - `registered_scorer_id` string, uuid4, nullable
        - `generated_scorer_id` string, uuid4, nullable
        - `scorer_version_id` string, uuid4, nullable
        - `user_code` string, nullable
        - `can_copy_to_llm` boolean, nullable
        - `scoreable_node_types` NodeType[], nullable
        - `cot_enabled` boolean, nullable
        - `output_type` 'boolean' | 'categorical' | 'count' | 'discrete' | 'freeform' | 'percentage' | 'multilabel' | 'retrieved_chunk_list_boolean' | 'boolean_multilabel' — Enumeration of output types.
        - `input_type` 'basic' | 'llm_spans' | 'retriever_spans' | 'sessions_normalized' | 'sessions_trace_io_only' | 'tool_spans' | 'trace_input_only' | 'trace_io_only' | 'trace_normalized' | 'trace_output_only' | 'agent_spans' | 'workflow_spans' — Enumeration of input types.
        - `multimodal_capabilities` MultimodalCapability[], nullable
        - `requires_tools_in_llm_span` boolean
        - `required_scorers` string[], nullable
        - `required_metric_ids` string[], nullable
        - `roll_up_strategy` 'avg' | 'sum' | 'first' | 'last' | 'none' — Strategies for rolling metrics up the Session/Trace/Span hierarchy.
        - `roll_up_methods` union
          - NumericRollUpMethod[]
          - CategoricalRollUpMethod[]
        - `prompt` string, nullable
        - `lora_task_id` integer, nullable
        - `lora_weights_path` string, nullable
        - `luna_input_type` 'span' | 'trace_object' | 'trace_input_output_only'
        - `luna_output_type` 'float' | 'string' | 'string_list' | 'bool_list'
        - `class_name_to_vocab_ix` union
          - object
          - object
        - `scorer_path_name` string, nullable
      - CustomizedToolErrorRateGPTScorer
        - `scorer_name` '_customized_tool_error_rate'
        - `model_alias` string
        - `num_judges` integer
        - `name` 'tool_error_rate'
        - `scores` unknown[], nullable
          - unknown
        - `indices` integer[], nullable
        - `aggregates` object, nullable
        - `aggregate_keys` string[]
        - `extra` object, nullable
        - `sub_scorers` PromptgalileoSchemasScorerNameScorerName[]
        - `filters` union[], nullable
          - union
            - NodeNameFilter — Filters on node names in scorer jobs.
              - …
            - MetadataFilter — Filters on metadata key-value pairs in scorer jobs.
              - …
            - ModalityFilter — Filters on content modalities in scorer jobs. Matches if at least one of the specified modalities is present.
              - …
        - `metric_name` string, nullable
        - `description` string, nullable
        - `chainpoll_template` ToolErrorRateTemplate — Template for the tool error rate metric, containing all the info necessary to send the tool error rate prompt.
          - `metric_system_prompt` string
          - `metric_description` string
          - `value_field_name` string
          - `explanation_field_name` string — Field name to look for in the chainpoll response, for the explanation.
          - `template` string
          - `metric_few_shot_examples` FewShotExample[]
            - `generation_prompt_and_response` string, required
            - `evaluating_response` string, required
          - `response_schema` object, nullable — Response schema for the output
        - `default_model_alias` string, nullable
        - `ground_truth` boolean, nullable
        - `regex_field` string
        - `registered_scorer_id` string, uuid4, nullable
        - `generated_scorer_id` string, uuid4, nullable
        - `scorer_version_id` string, uuid4, nullable
        - `user_code` string, nullable
        - `can_copy_to_llm` boolean, nullable
        - `scoreable_node_types` NodeType[], nullable
        - `cot_enabled` boolean, nullable
        - `output_type` 'boolean' | 'categorical' | 'count' | 'discrete' | 'freeform' | 'percentage' | 'multilabel' | 'retrieved_chunk_list_boolean' | 'boolean_multilabel' — Enumeration of output types.
        - `input_type` 'basic' | 'llm_spans' | 'retriever_spans' | 'sessions_normalized' | 'sessions_trace_io_only' | 'tool_spans' | 'trace_input_only' | 'trace_io_only' | 'trace_normalized' | 'trace_output_only' | 'agent_spans' | 'workflow_spans' — Enumeration of input types.
        - `multimodal_capabilities` MultimodalCapability[], nullable
        - `requires_tools_in_llm_span` boolean
        - `required_scorers` string[], nullable
        - `required_metric_ids` string[], nullable
        - `roll_up_strategy` 'avg' | 'sum' | 'first' | 'last' | 'none' — Strategies for rolling metrics up the Session/Trace/Span hierarchy.
        - `roll_up_methods` union
          - NumericRollUpMethod[]
          - CategoricalRollUpMethod[]
        - `prompt` string, nullable
        - `lora_task_id` integer, nullable
        - `lora_weights_path` string, nullable
        - `luna_input_type` 'span' | 'trace_object' | 'trace_input_output_only'
        - `luna_output_type` 'float' | 'string' | 'string_list' | 'bool_list'
        - `class_name_to_vocab_ix` union
          - object
          - object
        - `scorer_path_name` string, nullable
      - CustomizedToxicityGPTScorer
        - `scorer_name` '_customized_toxicity_gpt'
        - `model_alias` string
        - `num_judges` integer
        - `name` 'output_toxicity'
        - `scores` unknown[], nullable
          - unknown
        - `indices` integer[], nullable
        - `aggregates` object, nullable
        - `aggregate_keys` string[]
        - `extra` object, nullable
        - `sub_scorers` PromptgalileoSchemasScorerNameScorerName[]
        - `filters` union[], nullable
          - union
            - NodeNameFilter — Filters on node names in scorer jobs.
              - …
            - MetadataFilter — Filters on metadata key-value pairs in scorer jobs.
              - …
            - ModalityFilter — Filters on content modalities in scorer jobs. Matches if at least one of the specified modalities is present.
              - …
        - `metric_name` string, nullable
        - `description` string, nullable
        - `chainpoll_template` ToxicityTemplate — Template for the toxicity metric, containing all the info necessary to send the toxicity prompt.
          - `metric_system_prompt` string
          - `metric_description` string
          - `value_field_name` string
          - `explanation_field_name` string — Field name to look for in the chainpoll response, for the explanation.
          - `template` string
          - `metric_few_shot_examples` FewShotExample[]
            - `generation_prompt_and_response` string, required
            - `evaluating_response` string, required
          - `response_schema` object, nullable — Response schema for the output
        - `default_model_alias` string, nullable
        - `ground_truth` boolean, nullable
        - `regex_field` string
        - `registered_scorer_id` string, uuid4, nullable
        - `generated_scorer_id` string, uuid4, nullable
        - `scorer_version_id` string, uuid4, nullable
        - `user_code` string, nullable
        - `can_copy_to_llm` boolean, nullable
        - `scoreable_node_types` NodeType[], nullable
        - `cot_enabled` boolean, nullable
        - `output_type` 'boolean' | 'categorical' | 'count' | 'discrete' | 'freeform' | 'percentage' | 'multilabel' | 'retrieved_chunk_list_boolean' | 'boolean_multilabel' — Enumeration of output types.
        - `input_type` 'basic' | 'llm_spans' | 'retriever_spans' | 'sessions_normalized' | 'sessions_trace_io_only' | 'tool_spans' | 'trace_input_only' | 'trace_io_only' | 'trace_normalized' | 'trace_output_only' | 'agent_spans' | 'workflow_spans' — Enumeration of input types.
        - `multimodal_capabilities` MultimodalCapability[], nullable
        - `requires_tools_in_llm_span` boolean
        - `required_scorers` string[], nullable
        - `required_metric_ids` string[], nullable
        - `roll_up_strategy` 'avg' | 'sum' | 'first' | 'last' | 'none' — Strategies for rolling metrics up the Session/Trace/Span hierarchy.
        - `roll_up_methods` union
          - NumericRollUpMethod[]
          - CategoricalRollUpMethod[]
        - `prompt` string, nullable
        - `lora_task_id` integer, nullable
        - `lora_weights_path` string, nullable
        - `luna_input_type` 'span' | 'trace_object' | 'trace_input_output_only'
        - `luna_output_type` 'float' | 'string' | 'string_list' | 'bool_list'
        - `class_name_to_vocab_ix` union
          - object
          - object
        - `scorer_path_name` string, nullable
      - CustomizedInputToxicityGPTScorer
        - `scorer_name` '_customized_input_toxicity_gpt'
        - `model_alias` string
        - `num_judges` integer
        - `name` 'input_toxicity'
        - `scores` unknown[], nullable
          - unknown
        - `indices` integer[], nullable
        - `aggregates` object, nullable
        - `aggregate_keys` string[]
        - `extra` object, nullable
        - `sub_scorers` PromptgalileoSchemasScorerNameScorerName[]
        - `filters` union[], nullable
          - union
            - NodeNameFilter — Filters on node names in scorer jobs.
              - …
            - MetadataFilter — Filters on metadata key-value pairs in scorer jobs.
              - …
            - ModalityFilter — Filters on content modalities in scorer jobs. Matches if at least one of the specified modalities is present.
              - …
        - `metric_name` string, nullable
        - `description` string, nullable
        - `chainpoll_template` InputToxicityTemplate — Template for the toxicity metric, containing all the info necessary to send the toxicity prompt.
          - `metric_system_prompt` string
          - `metric_description` string
          - `value_field_name` string
          - `explanation_field_name` string — Field name to look for in the chainpoll response, for the explanation.
          - `template` string
          - `metric_few_shot_examples` FewShotExample[]
            - `generation_prompt_and_response` string, required
            - `evaluating_response` string, required
          - `response_schema` object, nullable — Response schema for the output
        - `default_model_alias` string, nullable
        - `ground_truth` boolean, nullable
        - `regex_field` string
        - `registered_scorer_id` string, uuid4, nullable
        - `generated_scorer_id` string, uuid4, nullable
        - `scorer_version_id` string, uuid4, nullable
        - `user_code` string, nullable
        - `can_copy_to_llm` boolean, nullable
        - `scoreable_node_types` NodeType[], nullable
        - `cot_enabled` boolean, nullable
        - `output_type` 'boolean' | 'categorical' | 'count' | 'discrete' | 'freeform' | 'percentage' | 'multilabel' | 'retrieved_chunk_list_boolean' | 'boolean_multilabel' — Enumeration of output types.
        - `input_type` 'basic' | 'llm_spans' | 'retriever_spans' | 'sessions_normalized' | 'sessions_trace_io_only' | 'tool_spans' | 'trace_input_only' | 'trace_io_only' | 'trace_normalized' | 'trace_output_only' | 'agent_spans' | 'workflow_spans' — Enumeration of input types.
        - `multimodal_capabilities` MultimodalCapability[], nullable
        - `requires_tools_in_llm_span` boolean
        - `required_scorers` string[], nullable
        - `required_metric_ids` string[], nullable
        - `roll_up_strategy` 'avg' | 'sum' | 'first' | 'last' | 'none' — Strategies for rolling metrics up the Session/Trace/Span hierarchy.
        - `roll_up_methods` union
          - NumericRollUpMethod[]
          - CategoricalRollUpMethod[]
        - `prompt` string, nullable
        - `lora_task_id` integer, nullable
        - `lora_weights_path` string, nullable
        - `luna_input_type` 'span' | 'trace_object' | 'trace_input_output_only'
        - `luna_output_type` 'float' | 'string' | 'string_list' | 'bool_list'
        - `class_name_to_vocab_ix` union
          - object
          - object
        - `scorer_path_name` string, nullable
  - `prompt_scorer_settings` BaseScorer
    - `scorer_name` string
    - `name` string
    - `scores` unknown[], nullable
      - unknown
    - `indices` integer[], nullable
    - `aggregates` object, nullable
    - `aggregate_keys` string[], nullable
    - `extra` object, nullable
    - `sub_scorers` PromptgalileoSchemasScorerNameScorerName[]
    - `filters` union[], nullable
      - union
        - NodeNameFilter — Filters on node names in scorer jobs.
          - `name` 'node_name'
          - `operator` 'eq' | 'ne' | 'contains' | 'one_of' | 'not_in', required
          - `value` union, required
            - string
            - string[]
          - `case_sensitive` boolean
        - MetadataFilter — Filters on metadata key-value pairs in scorer jobs.
          - `name` 'metadata'
          - `operator` 'one_of' | 'not_in' | 'eq' | 'ne', required
          - `key` string, required
          - `value` union, required
            - string
            - string[]
        - ModalityFilter — Filters on content modalities in scorer jobs. Matches if at least one of the specified modalities is present.
          - `name` 'modality'
          - `operator` 'eq' | 'ne' | 'one_of' | 'not_in', required
          - `value` union, required
            - string — Single enum value - specific options depend on the concrete enum type used
            - string[] — Array of enum values
    - `metric_name` string, nullable
    - `description` string, nullable
    - `chainpoll_template` ChainPollTemplate — Template for a chainpoll metric prompt, containing all the info necessary to send a chainpoll prompt.
      - `metric_system_prompt` string, nullable — System prompt for the metric.
      - `metric_description` string, nullable — Description of what the metric should do.
      - `value_field_name` string — Field name to look for in the chainpoll response, for the rating.
      - `explanation_field_name` string — Field name to look for in the chainpoll response, for the explanation.
      - `template` string, required — Chainpoll prompt template.
      - `metric_few_shot_examples` FewShotExample[] — Few-shot examples for the metric.
        - `generation_prompt_and_response` string, required
        - `evaluating_response` string, required
      - `response_schema` object, nullable — Response schema for the output
    - `model_alias` string, nullable
    - `num_judges` integer, nullable
    - `default_model_alias` string, nullable
    - `ground_truth` boolean, nullable
    - `regex_field` string
    - `registered_scorer_id` string, uuid4, nullable
    - `generated_scorer_id` string, uuid4, nullable
    - `scorer_version_id` string, uuid4, nullable
    - `user_code` string, nullable
    - `can_copy_to_llm` boolean, nullable
    - `scoreable_node_types` NodeType[], nullable
    - `cot_enabled` boolean, nullable
    - `output_type` 'boolean' | 'categorical' | 'count' | 'discrete' | 'freeform' | 'percentage' | 'multilabel' | 'retrieved_chunk_list_boolean' | 'boolean_multilabel' — Enumeration of output types.
    - `input_type` 'basic' | 'llm_spans' | 'retriever_spans' | 'sessions_normalized' | 'sessions_trace_io_only' | 'tool_spans' | 'trace_input_only' | 'trace_io_only' | 'trace_normalized' | 'trace_output_only' | 'agent_spans' | 'workflow_spans' — Enumeration of input types.
    - `multimodal_capabilities` MultimodalCapability[], nullable
    - `requires_tools_in_llm_span` boolean
    - `required_scorers` string[], nullable
    - `required_metric_ids` string[], nullable
    - `roll_up_strategy` 'avg' | 'sum' | 'first' | 'last' | 'none' — Strategies for rolling metrics up the Session/Trace/Span hierarchy.
    - `roll_up_methods` union
      - NumericRollUpMethod[]
      - CategoricalRollUpMethod[]
    - `prompt` string, nullable
    - `lora_task_id` integer, nullable
    - `lora_weights_path` string, nullable
    - `luna_input_type` 'span' | 'trace_object' | 'trace_input_output_only'
    - `luna_output_type` 'float' | 'string' | 'string_list' | 'bool_list'
    - `class_name_to_vocab_ix` union
      - object
      - object
    - `scorer_path_name` string, nullable
  - `scorer_config` RuntimeScorerConfig — Hydrated scorer config used at runtime. Never persisted directly. Produced by hydrate_scorer_config from a StoredScorerConfig + live DB rows.
    - `id` string, uuid4, required
    - `scorer_version_id` string, uuid4, nullable
    - `filters` union[], nullable — List of filters to apply to the scorer.
      - union
        - NodeNameFilter — Filters on node names in scorer jobs.
          - `name` 'node_name'
          - `operator` 'eq' | 'ne' | 'contains' | 'one_of' | 'not_in', required
          - `value` union, required
            - string
            - string[]
          - `case_sensitive` boolean
        - MetadataFilter — Filters on metadata key-value pairs in scorer jobs.
          - `name` 'metadata'
          - `operator` 'one_of' | 'not_in' | 'eq' | 'ne', required
          - `key` string, required
          - `value` union, required
            - string
            - string[]
        - ModalityFilter — Filters on content modalities in scorer jobs. Matches if at least one of the specified modalities is present.
          - `name` 'modality'
          - `operator` 'eq' | 'ne' | 'one_of' | 'not_in', required
          - `value` union, required
            - string — Single enum value - specific options depend on the concrete enum type used
            - string[] — Array of enum values
    - `roll_up_method` 'average' | 'sum' | 'max' | 'min' | 'category_count' | 'percentage_true' | 'percentage_false' — Display options for roll up methods when showing rolled up metrics in the UI. Separates display intent from computation methods. The computation methods (NumericRollUpMethod, CategoricalRollUpMethod) control what aggregations are available. This enum controls how the UI displays the selected roll-up value for a scorer.
    - `name` string, nullable
    - `scorer_type` 'llm' | 'code' | 'luna' | 'preset'
    - `model_name` string, nullable
    - `num_judges` integer, nullable
    - `scorer_version` BaseScorerVersionDB — Scorer version from the scorer_versions table.
      - `id` string, uuid4, required
      - `version` integer, required
      - `scorer_id` string, uuid4, required
      - `generated_scorer` BaseGeneratedScorerDB
        - `id` string, uuid4, required
        - `name` string, required
        - `instructions` string, nullable
        - `chain_poll_template` ChainPollTemplate, required — Template for a chainpoll metric prompt, containing all the info necessary to send a chainpoll prompt.
          - `metric_system_prompt` string, nullable — System prompt for the metric.
          - `metric_description` string, nullable — Description of what the metric should do.
          - `value_field_name` string — Field name to look for in the chainpoll response, for the rating.
          - `explanation_field_name` string — Field name to look for in the chainpoll response, for the explanation.
          - `template` string, required — Chainpoll prompt template.
          - `metric_few_shot_examples` FewShotExample[] — Few-shot examples for the metric.
            - `generation_prompt_and_response` string, required
            - `evaluating_response` string, required
          - `response_schema` object, nullable — Response schema for the output
        - `user_prompt` string, nullable
      - `registered_scorer` BaseRegisteredScorerDB
        - `id` string, uuid4, required
        - `name` string, required
        - `score_type` string, nullable
      - `finetuned_scorer` BaseFinetunedScorerDB
        - `id` string, uuid4, required
        - `name` string, required
        - `lora_task_id` integer, required
        - `lora_weights_path` string, nullable
        - `prompt` string, required
        - `luna_input_type` 'span' | 'trace_object' | 'trace_input_output_only'
        - `luna_output_type` 'float' | 'string' | 'string_list' | 'bool_list'
        - `class_name_to_vocab_ix` union
          - object
          - object
        - `executor` 'action_completion_luna' | 'action_advancement_luna' | 'agentic_session_success' | 'agentic_session_success' | 'action_completion_vision' | 'action_completion_audio' | 'agentic_workflow_success' | 'agentic_workflow_success' | 'agent_efficiency' | 'agent_flow' | 'agent_flow_vision' | 'agent_flow_audio' | 'chunk_attribution_utilization_luna' | 'chunk_attribution_utilization' | 'chunk_relevance' | 'chunk_relevance_luna' | 'context_precision' | 'precision_at_k' | 'completeness_luna' | 'completeness' | 'context_adherence' | 'context_adherence_luna' | 'context_adherence_vision' | 'context_adherence_audio' | 'context_relevance' | 'context_relevance_luna' | 'conversation_quality' | 'conversation_quality_vision' | 'conversation_quality_audio' | 'correctness' | 'correctness_vision' | 'correctness_audio' | 'ground_truth_adherence' | 'ground_truth_adherence_vision' | 'ground_truth_adherence_audio' | 'visual_fidelity' | 'visual_quality' | 'input_pii' | 'input_pii_gpt' | 'input_sexist' | 'input_sexist' | 'input_sexist_vision' | 'input_sexist_audio' | 'input_sexist_luna' | 'input_sexist_luna' | 'input_tone' | 'input_tone_gpt' | 'input_toxicity' | 'input_toxicity_luna' | 'input_toxicity_vision' | 'input_toxicity_audio' | 'instruction_adherence' | 'instruction_adherence_vision' | 'instruction_adherence_audio' | 'output_pii' | 'output_pii_gpt' | 'output_sexist' | 'output_sexist' | 'output_sexist_vision' | 'output_sexist_audio' | 'output_sexist_luna' | 'output_sexist_luna' | 'output_tone' | 'output_tone_gpt' | 'output_toxicity' | 'output_toxicity_luna' | 'output_toxicity_vision' | 'output_toxicity_audio' | 'prompt_injection' | 'prompt_injection_vision' | 'prompt_injection_audio' | 'prompt_injection_luna' | 'reasoning_coherence' | 'reasoning_coherence_vision' | 'reasoning_coherence_audio' | 'sql_efficiency' | 'sql_adherence' | 'sql_injection' | 'sql_correctness' | 'tool_error_rate' | 'tool_error_rate_luna' | 'tool_selection_quality' | 'tool_selection_quality_vision' | 'tool_selection_quality_audio' | 'tool_selection_quality_luna' | 'user_intent_change' | 'user_intent_change_vision' | 'user_intent_change_audio' | 'interruption_detection'
      - `model_name` string, nullable
      - `num_judges` integer, nullable
      - `cot_enabled` boolean, nullable — Whether to enable chain of thought for this scorer. Defaults to False for llm scorers.
    - `scoreable_node_types` string[], nullable — List of node types that can be scored by this scorer. Defaults to llm/chat.
    - `cot_enabled` boolean, nullable — Whether to enable chain of thought for this scorer. Defaults to False for llm scorers.
    - `output_type` 'boolean' | 'categorical' | 'count' | 'discrete' | 'freeform' | 'percentage' | 'multilabel' | 'retrieved_chunk_list_boolean' | 'boolean_multilabel' — Enumeration of output types.
    - `input_type` 'basic' | 'llm_spans' | 'retriever_spans' | 'sessions_normalized' | 'sessions_trace_io_only' | 'tool_spans' | 'trace_input_only' | 'trace_io_only' | 'trace_normalized' | 'trace_output_only' | 'agent_spans' | 'workflow_spans' — Enumeration of input types.
    - `multimodal_capabilities` MultimodalCapability[], nullable — Multimodal capabilities which this scorer can utilize in its evaluation.
    - `roll_up_config` BaseMetricRollUpConfigDB — Configuration for rolling up metrics to parent/trace/session.
      - `roll_up_methods` union, required — List of roll up methods to apply to the metric. For numeric scorers we support doing multiple roll up types per metric.
        - NumericRollUpMethod[]
        - CategoricalRollUpMethod[]
    - `score_type` string, nullable — Return type of code scorers (e.g., 'bool', 'int', 'float', 'str').
  - `sub_scorers` PromptgalileoSchemasScorerNameScorerName[]
  - `luna_model` string, nullable
  - `segment_filters` SegmentFilter[], nullable
    - `filter` union — Filter to apply to the segment. By default sample on all data.
      - NodeNameFilter — Filters on node names in scorer jobs.
        - `name` 'node_name'
        - `operator` 'eq' | 'ne' | 'contains' | 'one_of' | 'not_in', required
        - `value` union, required
          - string
          - string[]
        - `case_sensitive` boolean
      - MetadataFilter — Filters on metadata key-value pairs in scorer jobs.
        - `name` 'metadata'
        - `operator` 'one_of' | 'not_in' | 'eq' | 'ne', required
        - `key` string, required
        - `value` union, required
          - string
          - string[]
      - ModalityFilter — Filters on content modalities in scorer jobs. Matches if at least one of the specified modalities is present.
        - `name` 'modality'
        - `operator` 'eq' | 'ne' | 'one_of' | 'not_in', required
        - `value` union, required
          - string — Single enum value - specific options depend on the concrete enum type used
          - string[] — Array of enum values
    - `sample_rate` number, required — The fraction of the data to sample. Must be between 0 and 1, inclusive.
    - `llm_scorers` boolean — Whether to sample only on LLM scorers.
    - `multimodal_scorers` boolean — Whether to sample only on multimodal scorers.
  - `is_session` boolean, nullable
  - `validation_config` object, nullable
  - `upload_data_in_separate_task` boolean
  - `log_metric_computing_records` boolean
  - `stream_metrics` boolean
  - `multijudge_average_boolean_metrics` boolean
  - `store_metric_ids` boolean
  - `trace_ids` string[]

## Response `200`

Successful Response

- CreateJobResponse
  - `resource_limits` TaskResourceLimits
    - `cpu_time` integer
    - `memory_mb` integer
  - `project_id` string, uuid4, required
  - `run_id` string, uuid4, required
  - `job_id` string, uuid4, nullable
  - `job_name` string
  - `should_retry` boolean
  - `user_id` string, uuid4, nullable
  - `task_type` 13 | 15 | 16 | 17 | 18 — Valid task types for modeling. We store these as ints instead of strings because we will be looking this up in the database frequently.
  - `labels` union
    - array[]
      - string[]
    - string[]
  - `ner_labels` string[], nullable
  - `tasks` string[], nullable
  - `non_inference_logged` boolean
  - `migration_name` string, nullable
  - `process_existing_inference_runs` boolean
  - `feature_names` string[], nullable
  - `prompt_dataset_id` string, uuid4, nullable
  - `dataset_id` string, uuid4, nullable
  - `dataset_version_index` integer, nullable
  - `prompt_template_version_id` string, uuid4, nullable
  - `batch_id` string, uuid4, nullable
  - `protect_trace_id` string, uuid4, nullable
  - `protect_scorer_payload` string, binary, nullable
  - `prompt_settings` PromptRunSettingsOutput — Prompt run settings.
    - `logprobs` boolean
    - `top_logprobs` integer
    - `echo` boolean
    - `n` integer
    - `reasoning_effort` string
    - `verbosity` string
    - `deployment_name` string, nullable
    - `model_alias` string
    - `temperature` number, nullable
    - `max_tokens` integer
    - `stop_sequences` string[], nullable
    - `top_p` number
    - `top_k` integer
    - `frequency_penalty` number
    - `presence_penalty` number
    - `tools` string
    - `tool_choice` union
      - string
      - OpenAIToolChoice
        - `type` string
        - `function` OpenAIFunction, required
          - `name` string, required
    - `response_format` object, nullable
  - `scorers` union — For G2.0 we send all scorers as ScorerConfig, for G1.0 we send preset scorers as GalileoScorer
    - RuntimeScorerConfig[]
      - `id` string, uuid4, required
      - `scorer_version_id` string, uuid4, nullable
      - `filters` union[], nullable — List of filters to apply to the scorer.
        - union
          - NodeNameFilter — Filters on node names in scorer jobs.
            - `name` 'node_name'
            - `operator` 'eq' | 'ne' | 'contains' | 'one_of' | 'not_in', required
            - `value` union, required
              - …
            - `case_sensitive` boolean
          - MetadataFilter — Filters on metadata key-value pairs in scorer jobs.
            - `name` 'metadata'
            - `operator` 'one_of' | 'not_in' | 'eq' | 'ne', required
            - `key` string, required
            - `value` union, required
              - …
          - ModalityFilter — Filters on content modalities in scorer jobs. Matches if at least one of the specified modalities is present.
            - `name` 'modality'
            - `operator` 'eq' | 'ne' | 'one_of' | 'not_in', required
            - `value` union, required
              - …
      - `roll_up_method` 'average' | 'sum' | 'max' | 'min' | 'category_count' | 'percentage_true' | 'percentage_false' — Display options for roll up methods when showing rolled up metrics in the UI. Separates display intent from computation methods. The computation methods (NumericRollUpMethod, CategoricalRollUpMethod) control what aggregations are available. This enum controls how the UI displays the selected roll-up value for a scorer.
      - `name` string, nullable
      - `scorer_type` 'llm' | 'code' | 'luna' | 'preset'
      - `model_name` string, nullable
      - `num_judges` integer, nullable
      - `scorer_version` BaseScorerVersionDB — Scorer version from the scorer_versions table.
        - `id` string, uuid4, required
        - `version` integer, required
        - `scorer_id` string, uuid4, required
        - `generated_scorer` BaseGeneratedScorerDB
          - `id` string, uuid4, required
          - `name` string, required
          - `instructions` string, nullable
          - `chain_poll_template` ChainPollTemplate, required — Template for a chainpoll metric prompt, containing all the info necessary to send a chainpoll prompt.
            - `metric_system_prompt` string, nullable — System prompt for the metric.
            - `metric_description` string, nullable — Description of what the metric should do.
            - `value_field_name` string — Field name to look for in the chainpoll response, for the rating.
            - `explanation_field_name` string — Field name to look for in the chainpoll response, for the explanation.
            - `template` string, required — Chainpoll prompt template.
            - `metric_few_shot_examples` FewShotExample[] — Few-shot examples for the metric.
              - …
            - `response_schema` object, nullable — Response schema for the output
          - `user_prompt` string, nullable
        - `registered_scorer` BaseRegisteredScorerDB
          - `id` string, uuid4, required
          - `name` string, required
          - `score_type` string, nullable
        - `finetuned_scorer` BaseFinetunedScorerDB
          - `id` string, uuid4, required
          - `name` string, required
          - `lora_task_id` integer, required
          - `lora_weights_path` string, nullable
          - `prompt` string, required
          - `luna_input_type` 'span' | 'trace_object' | 'trace_input_output_only'
          - `luna_output_type` 'float' | 'string' | 'string_list' | 'bool_list'
          - `class_name_to_vocab_ix` union
            - object
            - object
          - `executor` 'action_completion_luna' | 'action_advancement_luna' | 'agentic_session_success' | 'agentic_session_success' | 'action_completion_vision' | 'action_completion_audio' | 'agentic_workflow_success' | 'agentic_workflow_success' | 'agent_efficiency' | 'agent_flow' | 'agent_flow_vision' | 'agent_flow_audio' | 'chunk_attribution_utilization_luna' | 'chunk_attribution_utilization' | 'chunk_relevance' | 'chunk_relevance_luna' | 'context_precision' | 'precision_at_k' | 'completeness_luna' | 'completeness' | 'context_adherence' | 'context_adherence_luna' | 'context_adherence_vision' | 'context_adherence_audio' | 'context_relevance' | 'context_relevance_luna' | 'conversation_quality' | 'conversation_quality_vision' | 'conversation_quality_audio' | 'correctness' | 'correctness_vision' | 'correctness_audio' | 'ground_truth_adherence' | 'ground_truth_adherence_vision' | 'ground_truth_adherence_audio' | 'visual_fidelity' | 'visual_quality' | 'input_pii' | 'input_pii_gpt' | 'input_sexist' | 'input_sexist' | 'input_sexist_vision' | 'input_sexist_audio' | 'input_sexist_luna' | 'input_sexist_luna' | 'input_tone' | 'input_tone_gpt' | 'input_toxicity' | 'input_toxicity_luna' | 'input_toxicity_vision' | 'input_toxicity_audio' | 'instruction_adherence' | 'instruction_adherence_vision' | 'instruction_adherence_audio' | 'output_pii' | 'output_pii_gpt' | 'output_sexist' | 'output_sexist' | 'output_sexist_vision' | 'output_sexist_audio' | 'output_sexist_luna' | 'output_sexist_luna' | 'output_tone' | 'output_tone_gpt' | 'output_toxicity' | 'output_toxicity_luna' | 'output_toxicity_vision' | 'output_toxicity_audio' | 'prompt_injection' | 'prompt_injection_vision' | 'prompt_injection_audio' | 'prompt_injection_luna' | 'reasoning_coherence' | 'reasoning_coherence_vision' | 'reasoning_coherence_audio' | 'sql_efficiency' | 'sql_adherence' | 'sql_injection' | 'sql_correctness' | 'tool_error_rate' | 'tool_error_rate_luna' | 'tool_selection_quality' | 'tool_selection_quality_vision' | 'tool_selection_quality_audio' | 'tool_selection_quality_luna' | 'user_intent_change' | 'user_intent_change_vision' | 'user_intent_change_audio' | 'interruption_detection'
        - `model_name` string, nullable
        - `num_judges` integer, nullable
        - `cot_enabled` boolean, nullable — Whether to enable chain of thought for this scorer. Defaults to False for llm scorers.
      - `scoreable_node_types` string[], nullable — List of node types that can be scored by this scorer. Defaults to llm/chat.
      - `cot_enabled` boolean, nullable — Whether to enable chain of thought for this scorer. Defaults to False for llm scorers.
      - `output_type` 'boolean' | 'categorical' | 'count' | 'discrete' | 'freeform' | 'percentage' | 'multilabel' | 'retrieved_chunk_list_boolean' | 'boolean_multilabel' — Enumeration of output types.
      - `input_type` 'basic' | 'llm_spans' | 'retriever_spans' | 'sessions_normalized' | 'sessions_trace_io_only' | 'tool_spans' | 'trace_input_only' | 'trace_io_only' | 'trace_normalized' | 'trace_output_only' | 'agent_spans' | 'workflow_spans' — Enumeration of input types.
      - `multimodal_capabilities` MultimodalCapability[], nullable — Multimodal capabilities which this scorer can utilize in its evaluation.
      - `roll_up_config` BaseMetricRollUpConfigDB — Configuration for rolling up metrics to parent/trace/session.
        - `roll_up_methods` union, required — List of roll up methods to apply to the metric. For numeric scorers we support doing multiple roll up types per metric.
          - NumericRollUpMethod[]
          - CategoricalRollUpMethod[]
      - `score_type` string, nullable — Return type of code scorers (e.g., 'bool', 'int', 'float', 'str').
    - union[]
      - union
        - AgenticWorkflowSuccessScorer
          - `name` 'agentic_workflow_success'
          - `filters` union[], nullable — List of filters to apply to the scorer.
            - union
              - …
          - `type` 'luna' | 'plus'
          - `model_name` string, nullable — Alias of the model to use for the scorer.
          - `num_judges` integer, nullable — Number of judges for the scorer.
        - AgenticSessionSuccessScorer
          - `name` 'agentic_session_success'
          - `filters` union[], nullable — List of filters to apply to the scorer.
            - union
              - …
          - `type` 'luna' | 'plus'
          - `model_name` string, nullable — Alias of the model to use for the scorer.
          - `num_judges` integer, nullable — Number of judges for the scorer.
        - ChunkAttributionUtilizationScorer
          - `name` 'chunk_attribution_utilization'
          - `filters` union[], nullable — List of filters to apply to the scorer.
            - union
              - …
          - `type` 'luna' | 'plus'
          - `model_name` string, nullable — Alias of the model to use for the scorer.
        - CompletenessScorer
          - `name` 'completeness'
          - `filters` union[], nullable — List of filters to apply to the scorer.
            - union
              - …
          - `type` 'luna' | 'plus'
          - `model_name` string, nullable — Alias of the model to use for the scorer.
          - `num_judges` integer, nullable — Number of judges for the scorer.
        - ContextAdherenceScorer
          - `name` 'context_adherence'
          - `filters` union[], nullable — List of filters to apply to the scorer.
            - union
              - …
          - `type` 'luna' | 'plus'
          - `model_name` string, nullable — Alias of the model to use for the scorer.
          - `num_judges` integer, nullable — Number of judges for the scorer.
        - ContextRelevanceScorer
          - `name` 'context_relevance'
          - `filters` union[], nullable — List of filters to apply to the scorer.
            - union
              - …
        - CorrectnessScorer
          - `name` 'correctness'
          - `filters` union[], nullable — List of filters to apply to the scorer.
            - union
              - …
          - `type` 'plus'
          - `model_name` string, nullable — Alias of the model to use for the scorer.
          - `num_judges` integer, nullable — Number of judges for the scorer.
        - GroundTruthAdherenceScorer
          - `name` 'ground_truth_adherence'
          - `filters` union[], nullable — List of filters to apply to the scorer.
            - union
              - …
          - `type` 'plus'
          - `model_name` string, nullable — Alias of the model to use for the scorer.
          - `num_judges` integer, nullable — Number of judges for the scorer.
        - InputPIIScorer
          - `name` 'input_pii'
          - `filters` union[], nullable — List of filters to apply to the scorer.
            - union
              - …
        - InputSexistScorer
          - `name` 'input_sexist'
          - `filters` union[], nullable — List of filters to apply to the scorer.
            - union
              - …
          - `type` 'luna' | 'plus'
          - `model_name` string, nullable — Alias of the model to use for the scorer.
          - `num_judges` integer, nullable — Number of judges for the scorer.
        - InputToneScorer
          - `name` 'input_tone'
          - `filters` union[], nullable — List of filters to apply to the scorer.
            - union
              - …
        - InputToxicityScorer
          - `name` 'input_toxicity'
          - `filters` union[], nullable — List of filters to apply to the scorer.
            - union
              - …
          - `type` 'luna' | 'plus'
          - `model_name` string, nullable — Alias of the model to use for the scorer.
          - `num_judges` integer, nullable — Number of judges for the scorer.
        - InstructionAdherenceScorer
          - `name` 'instruction_adherence'
          - `filters` union[], nullable — List of filters to apply to the scorer.
            - union
              - …
          - `type` 'plus'
          - `model_name` string, nullable — Alias of the model to use for the scorer.
          - `num_judges` integer, nullable — Number of judges for the scorer.
        - OutputPIIScorer
          - `name` 'output_pii'
          - `filters` union[], nullable — List of filters to apply to the scorer.
            - union
              - …
        - OutputSexistScorer
          - `name` 'output_sexist'
          - `filters` union[], nullable — List of filters to apply to the scorer.
            - union
              - …
          - `type` 'luna' | 'plus'
          - `model_name` string, nullable — Alias of the model to use for the scorer.
          - `num_judges` integer, nullable — Number of judges for the scorer.
        - OutputToneScorer
          - `name` 'output_tone'
          - `filters` union[], nullable — List of filters to apply to the scorer.
            - union
              - …
        - OutputToxicityScorer
          - `name` 'output_toxicity'
          - `filters` union[], nullable — List of filters to apply to the scorer.
            - union
              - …
          - `type` 'luna' | 'plus'
          - `model_name` string, nullable — Alias of the model to use for the scorer.
          - `num_judges` integer, nullable — Number of judges for the scorer.
        - PromptInjectionScorer
          - `name` 'prompt_injection'
          - `filters` union[], nullable — List of filters to apply to the scorer.
            - union
              - …
          - `type` 'luna' | 'plus'
          - `model_name` string, nullable — Alias of the model to use for the scorer.
          - `num_judges` integer, nullable — Number of judges for the scorer.
        - ToolErrorRateScorer
          - `name` 'tool_error_rate'
          - `filters` union[], nullable — List of filters to apply to the scorer.
            - union
              - …
          - `type` 'luna' | 'plus'
          - `model_name` string, nullable — Alias of the model to use for the scorer.
        - ToolSelectionQualityScorer
          - `name` 'tool_selection_quality'
          - `filters` union[], nullable — List of filters to apply to the scorer.
            - union
              - …
          - `type` 'luna' | 'plus'
          - `model_name` string, nullable — Alias of the model to use for the scorer.
          - `num_judges` integer, nullable — Number of judges for the scorer.
  - `prompt_registered_scorers_configuration` RegisteredScorer[], nullable
    - `id` string, uuid4, nullable
    - `name` string, nullable
    - `filters` union[], nullable
      - union
        - NodeNameFilter — Filters on node names in scorer jobs.
          - `name` 'node_name'
          - `operator` 'eq' | 'ne' | 'contains' | 'one_of' | 'not_in', required
          - `value` union, required
            - string
            - string[]
          - `case_sensitive` boolean
        - MetadataFilter — Filters on metadata key-value pairs in scorer jobs.
          - `name` 'metadata'
          - `operator` 'one_of' | 'not_in' | 'eq' | 'ne', required
          - `key` string, required
          - `value` union, required
            - string
            - string[]
        - ModalityFilter — Filters on content modalities in scorer jobs. Matches if at least one of the specified modalities is present.
          - `name` 'modality'
          - `operator` 'eq' | 'ne' | 'one_of' | 'not_in', required
          - `value` union, required
            - string — Single enum value - specific options depend on the concrete enum type used
            - string[] — Array of enum values
  - `prompt_generated_scorers_configuration` string[], nullable
  - `prompt_finetuned_scorers_configuration` FineTunedScorer[], nullable
    - `id` string, uuid4, nullable
    - `name` string, nullable
    - `filters` union[], nullable
      - union
        - NodeNameFilter — Filters on node names in scorer jobs.
          - `name` 'node_name'
          - `operator` 'eq' | 'ne' | 'contains' | 'one_of' | 'not_in', required
          - `value` union, required
            - string
            - string[]
          - `case_sensitive` boolean
        - MetadataFilter — Filters on metadata key-value pairs in scorer jobs.
          - `name` 'metadata'
          - `operator` 'one_of' | 'not_in' | 'eq' | 'ne', required
          - `key` string, required
          - `value` union, required
            - string
            - string[]
        - ModalityFilter — Filters on content modalities in scorer jobs. Matches if at least one of the specified modalities is present.
          - `name` 'modality'
          - `operator` 'eq' | 'ne' | 'one_of' | 'not_in', required
          - `value` union, required
            - string — Single enum value - specific options depend on the concrete enum type used
            - string[] — Array of enum values
  - `prompt_scorers_configuration` ScorersConfiguration — Configure which scorers to enable for a particular prompt run. The keys here are sorted by their approximate execution time to execute the scorers that we anticipate will be the fastest first, and the slowest last.
    - `latency` boolean
    - `cost` boolean
    - `pii` boolean
    - `input_pii` boolean
    - `protect_status` boolean
    - `context_relevance` boolean
    - `toxicity` boolean
    - `input_toxicity` boolean
    - `tone` boolean
    - `input_tone` boolean
    - `sexist` boolean
    - `input_sexist` boolean
    - `prompt_injection` boolean
    - `adherence_nli` boolean
    - `chunk_attribution_utilization_nli` boolean
    - `context_adherence_luna` boolean
    - `context_relevance_luna` boolean
    - `chunk_relevance_luna` boolean
    - `completeness_luna` boolean
    - `completeness_nli` boolean
    - `tool_error_rate_luna` boolean
    - `tool_selection_quality_luna` boolean
    - `action_completion_luna` boolean
    - `action_advancement_luna` boolean
    - `factuality` boolean
    - `groundedness` boolean
    - `chunk_attribution_utilization_gpt` boolean
    - `completeness_gpt` boolean
    - `instruction_adherence` boolean
    - `ground_truth_adherence` boolean
    - `tool_selection_quality` boolean
    - `tool_error_rate` boolean
    - `agentic_session_success` boolean
    - `agentic_workflow_success` boolean
    - `prompt_injection_gpt` boolean
    - `sexist_gpt` boolean
    - `input_sexist_gpt` boolean
    - `toxicity_gpt` boolean
    - `input_toxicity_gpt` boolean
  - `prompt_customized_scorers_configuration` union[], nullable
    - union
      - CustomizedAgenticSessionSuccessGPTScorer
        - `scorer_name` '_customized_agentic_session_success'
        - `model_alias` string
        - `num_judges` integer
        - `name` 'agentic_session_success'
        - `scores` unknown[], nullable
          - unknown
        - `indices` integer[], nullable
        - `aggregates` object, nullable
        - `aggregate_keys` string[]
        - `extra` object, nullable
        - `sub_scorers` PromptgalileoSchemasScorerNameScorerName[]
        - `filters` union[], nullable
          - union
            - NodeNameFilter — Filters on node names in scorer jobs.
              - …
            - MetadataFilter — Filters on metadata key-value pairs in scorer jobs.
              - …
            - ModalityFilter — Filters on content modalities in scorer jobs. Matches if at least one of the specified modalities is present.
              - …
        - `metric_name` string, nullable
        - `description` string, nullable
        - `chainpoll_template` AgenticSessionSuccessTemplate — Template for the agentic session success metric, containing all the info necessary to send the agentic session success prompt.
          - `metric_system_prompt` string
          - `metric_description` string
          - `value_field_name` string
          - `explanation_field_name` string — Field name to look for in the chainpoll response, for the explanation.
          - `template` string
          - `metric_few_shot_examples` FewShotExample[]
            - `generation_prompt_and_response` string, required
            - `evaluating_response` string, required
          - `response_schema` object, nullable — Response schema for the output
        - `default_model_alias` string, nullable
        - `ground_truth` boolean, nullable
        - `regex_field` string
        - `registered_scorer_id` string, uuid4, nullable
        - `generated_scorer_id` string, uuid4, nullable
        - `scorer_version_id` string, uuid4, nullable
        - `user_code` string, nullable
        - `can_copy_to_llm` boolean, nullable
        - `scoreable_node_types` NodeType[], nullable
        - `cot_enabled` boolean, nullable
        - `output_type` 'boolean' | 'categorical' | 'count' | 'discrete' | 'freeform' | 'percentage' | 'multilabel' | 'retrieved_chunk_list_boolean' | 'boolean_multilabel' — Enumeration of output types.
        - `input_type` 'basic' | 'llm_spans' | 'retriever_spans' | 'sessions_normalized' | 'sessions_trace_io_only' | 'tool_spans' | 'trace_input_only' | 'trace_io_only' | 'trace_normalized' | 'trace_output_only' | 'agent_spans' | 'workflow_spans' — Enumeration of input types.
        - `multimodal_capabilities` MultimodalCapability[], nullable
        - `requires_tools_in_llm_span` boolean
        - `required_scorers` string[], nullable
        - `required_metric_ids` string[], nullable
        - `roll_up_strategy` 'avg' | 'sum' | 'first' | 'last' | 'none' — Strategies for rolling metrics up the Session/Trace/Span hierarchy.
        - `roll_up_methods` union
          - NumericRollUpMethod[]
          - CategoricalRollUpMethod[]
        - `prompt` string, nullable
        - `lora_task_id` integer, nullable
        - `lora_weights_path` string, nullable
        - `luna_input_type` 'span' | 'trace_object' | 'trace_input_output_only'
        - `luna_output_type` 'float' | 'string' | 'string_list' | 'bool_list'
        - `class_name_to_vocab_ix` union
          - object
          - object
        - `scorer_path_name` string, nullable
      - CustomizedAgenticWorkflowSuccessGPTScorer
        - `scorer_name` '_customized_agentic_workflow_success'
        - `model_alias` string
        - `num_judges` integer
        - `name` 'agentic_workflow_success'
        - `scores` unknown[], nullable
          - unknown
        - `indices` integer[], nullable
        - `aggregates` object, nullable
        - `aggregate_keys` string[]
        - `extra` object, nullable
        - `sub_scorers` PromptgalileoSchemasScorerNameScorerName[]
        - `filters` union[], nullable
          - union
            - NodeNameFilter — Filters on node names in scorer jobs.
              - …
            - MetadataFilter — Filters on metadata key-value pairs in scorer jobs.
              - …
            - ModalityFilter — Filters on content modalities in scorer jobs. Matches if at least one of the specified modalities is present.
              - …
        - `metric_name` string, nullable
        - `description` string, nullable
        - `chainpoll_template` AgenticWorkflowSuccessTemplate — Template for the agentic workflow success metric, containing all the info necessary to send the agentic workflow success prompt.
          - `metric_system_prompt` string
          - `metric_description` string
          - `value_field_name` string
          - `explanation_field_name` string — Field name to look for in the chainpoll response, for the explanation.
          - `template` string
          - `metric_few_shot_examples` FewShotExample[]
            - `generation_prompt_and_response` string, required
            - `evaluating_response` string, required
          - `response_schema` object, nullable — Response schema for the output
        - `default_model_alias` string, nullable
        - `ground_truth` boolean, nullable
        - `regex_field` string
        - `registered_scorer_id` string, uuid4, nullable
        - `generated_scorer_id` string, uuid4, nullable
        - `scorer_version_id` string, uuid4, nullable
        - `user_code` string, nullable
        - `can_copy_to_llm` boolean, nullable
        - `scoreable_node_types` NodeType[], nullable
        - `cot_enabled` boolean, nullable
        - `output_type` 'boolean' | 'categorical' | 'count' | 'discrete' | 'freeform' | 'percentage' | 'multilabel' | 'retrieved_chunk_list_boolean' | 'boolean_multilabel' — Enumeration of output types.
        - `input_type` 'basic' | 'llm_spans' | 'retriever_spans' | 'sessions_normalized' | 'sessions_trace_io_only' | 'tool_spans' | 'trace_input_only' | 'trace_io_only' | 'trace_normalized' | 'trace_output_only' | 'agent_spans' | 'workflow_spans' — Enumeration of input types.
        - `multimodal_capabilities` MultimodalCapability[], nullable
        - `requires_tools_in_llm_span` boolean
        - `required_scorers` string[], nullable
        - `required_metric_ids` string[], nullable
        - `roll_up_strategy` 'avg' | 'sum' | 'first' | 'last' | 'none' — Strategies for rolling metrics up the Session/Trace/Span hierarchy.
        - `roll_up_methods` union
          - NumericRollUpMethod[]
          - CategoricalRollUpMethod[]
        - `prompt` string, nullable
        - `lora_task_id` integer, nullable
        - `lora_weights_path` string, nullable
        - `luna_input_type` 'span' | 'trace_object' | 'trace_input_output_only'
        - `luna_output_type` 'float' | 'string' | 'string_list' | 'bool_list'
        - `class_name_to_vocab_ix` union
          - object
          - object
        - `scorer_path_name` string, nullable
      - CustomizedChunkAttributionUtilizationGPTScorer
        - `scorer_name` '_customized_chunk_attribution_utilization_gpt'
        - `model_alias` string
        - `num_judges` integer
        - `name` 'chunk_attribution_utilization'
        - `scores` unknown[], nullable
          - unknown
        - `indices` integer[], nullable
        - `aggregates` object, nullable
        - `aggregate_keys` string[]
        - `extra` object, nullable
        - `sub_scorers` PromptgalileoSchemasScorerNameScorerName[]
        - `filters` union[], nullable
          - union
            - NodeNameFilter — Filters on node names in scorer jobs.
              - …
            - MetadataFilter — Filters on metadata key-value pairs in scorer jobs.
              - …
            - ModalityFilter — Filters on content modalities in scorer jobs. Matches if at least one of the specified modalities is present.
              - …
        - `metric_name` string, nullable
        - `description` string, nullable
        - `chainpoll_template` ChunkAttributionUtilizationTemplate
          - `metric_system_prompt` string, nullable — System prompt for the metric.
          - `metric_description` string, nullable — Description of what the metric should do.
          - `value_field_name` string — Field name to look for in the chainpoll response, for the rating.
          - `explanation_field_name` string — Field name to look for in the chainpoll response, for the explanation.
          - `template` string
          - `metric_few_shot_examples` FewShotExample[] — Few-shot examples for the metric.
            - `generation_prompt_and_response` string, required
            - `evaluating_response` string, required
          - `response_schema` object, nullable — Response schema for the output
        - `default_model_alias` string, nullable
        - `ground_truth` boolean, nullable
        - `regex_field` string
        - `registered_scorer_id` string, uuid4, nullable
        - `generated_scorer_id` string, uuid4, nullable
        - `scorer_version_id` string, uuid4, nullable
        - `user_code` string, nullable
        - `can_copy_to_llm` boolean, nullable
        - `scoreable_node_types` NodeType[], nullable
        - `cot_enabled` boolean, nullable
        - `output_type` 'boolean' | 'categorical' | 'count' | 'discrete' | 'freeform' | 'percentage' | 'multilabel' | 'retrieved_chunk_list_boolean' | 'boolean_multilabel' — Enumeration of output types.
        - `input_type` 'basic' | 'llm_spans' | 'retriever_spans' | 'sessions_normalized' | 'sessions_trace_io_only' | 'tool_spans' | 'trace_input_only' | 'trace_io_only' | 'trace_normalized' | 'trace_output_only' | 'agent_spans' | 'workflow_spans' — Enumeration of input types.
        - `multimodal_capabilities` MultimodalCapability[], nullable
        - `requires_tools_in_llm_span` boolean
        - `required_scorers` string[], nullable
        - `required_metric_ids` string[], nullable
        - `roll_up_strategy` 'avg' | 'sum' | 'first' | 'last' | 'none' — Strategies for rolling metrics up the Session/Trace/Span hierarchy.
        - `roll_up_methods` union
          - NumericRollUpMethod[]
          - CategoricalRollUpMethod[]
        - `prompt` string, nullable
        - `lora_task_id` integer, nullable
        - `lora_weights_path` string, nullable
        - `luna_input_type` 'span' | 'trace_object' | 'trace_input_output_only'
        - `luna_output_type` 'float' | 'string' | 'string_list' | 'bool_list'
        - `class_name_to_vocab_ix` union
          - object
          - object
        - `scorer_path_name` string, nullable
      - CustomizedCompletenessGPTScorer
        - `scorer_name` '_customized_completeness_gpt'
        - `model_alias` string
        - `num_judges` integer
        - `name` 'completeness'
        - `scores` unknown[], nullable
          - unknown
        - `indices` integer[], nullable
        - `aggregates` object, nullable
        - `aggregate_keys` string[]
        - `extra` object, nullable
        - `sub_scorers` PromptgalileoSchemasScorerNameScorerName[]
        - `filters` union[], nullable
          - union
            - NodeNameFilter — Filters on node names in scorer jobs.
              - …
            - MetadataFilter — Filters on metadata key-value pairs in scorer jobs.
              - …
            - ModalityFilter — Filters on content modalities in scorer jobs. Matches if at least one of the specified modalities is present.
              - …
        - `metric_name` string, nullable
        - `description` string, nullable
        - `chainpoll_template` CompletenessTemplate
          - `metric_system_prompt` string, nullable — System prompt for the metric.
          - `metric_description` string, nullable — Description of what the metric should do.
          - `value_field_name` string
          - `explanation_field_name` string — Field name to look for in the chainpoll response, for the explanation.
          - `template` string
          - `metric_few_shot_examples` FewShotExample[] — Few-shot examples for the metric.
            - `generation_prompt_and_response` string, required
            - `evaluating_response` string, required
          - `response_schema` object, nullable — Response schema for the output
        - `default_model_alias` string, nullable
        - `ground_truth` boolean, nullable
        - `regex_field` string
        - `registered_scorer_id` string, uuid4, nullable
        - `generated_scorer_id` string, uuid4, nullable
        - `scorer_version_id` string, uuid4, nullable
        - `user_code` string, nullable
        - `can_copy_to_llm` boolean, nullable
        - `scoreable_node_types` NodeType[], nullable
        - `cot_enabled` boolean, nullable
        - `output_type` 'boolean' | 'categorical' | 'count' | 'discrete' | 'freeform' | 'percentage' | 'multilabel' | 'retrieved_chunk_list_boolean' | 'boolean_multilabel' — Enumeration of output types.
        - `input_type` 'basic' | 'llm_spans' | 'retriever_spans' | 'sessions_normalized' | 'sessions_trace_io_only' | 'tool_spans' | 'trace_input_only' | 'trace_io_only' | 'trace_normalized' | 'trace_output_only' | 'agent_spans' | 'workflow_spans' — Enumeration of input types.
        - `multimodal_capabilities` MultimodalCapability[], nullable
        - `requires_tools_in_llm_span` boolean
        - `required_scorers` string[], nullable
        - `required_metric_ids` string[], nullable
        - `roll_up_strategy` 'avg' | 'sum' | 'first' | 'last' | 'none' — Strategies for rolling metrics up the Session/Trace/Span hierarchy.
        - `roll_up_methods` union
          - NumericRollUpMethod[]
          - CategoricalRollUpMethod[]
        - `prompt` string, nullable
        - `lora_task_id` integer, nullable
        - `lora_weights_path` string, nullable
        - `luna_input_type` 'span' | 'trace_object' | 'trace_input_output_only'
        - `luna_output_type` 'float' | 'string' | 'string_list' | 'bool_list'
        - `class_name_to_vocab_ix` union
          - object
          - object
        - `scorer_path_name` string, nullable
      - CustomizedFactualityGPTScorer
        - `scorer_name` '_customized_factuality'
        - `model_alias` string
        - `num_judges` integer
        - `name` 'correctness'
        - `scores` unknown[], nullable
          - unknown
        - `indices` integer[], nullable
        - `aggregates` object, nullable
        - `aggregate_keys` string[]
        - `extra` object, nullable
        - `sub_scorers` PromptgalileoSchemasScorerNameScorerName[]
        - `filters` union[], nullable
          - union
            - NodeNameFilter — Filters on node names in scorer jobs.
              - …
            - MetadataFilter — Filters on metadata key-value pairs in scorer jobs.
              - …
            - ModalityFilter — Filters on content modalities in scorer jobs. Matches if at least one of the specified modalities is present.
              - …
        - `metric_name` string, nullable
        - `description` string, nullable
        - `chainpoll_template` FactualityTemplate
          - `metric_system_prompt` string
          - `metric_description` string, nullable — Description of what the metric should do.
          - `value_field_name` string
          - `explanation_field_name` string — Field name to look for in the chainpoll response, for the explanation.
          - `template` string
          - `metric_few_shot_examples` FewShotExample[]
            - `generation_prompt_and_response` string, required
            - `evaluating_response` string, required
          - `response_schema` object, nullable — Response schema for the output
        - `default_model_alias` string, nullable
        - `ground_truth` boolean, nullable
        - `regex_field` string
        - `registered_scorer_id` string, uuid4, nullable
        - `generated_scorer_id` string, uuid4, nullable
        - `scorer_version_id` string, uuid4, nullable
        - `user_code` string, nullable
        - `can_copy_to_llm` boolean, nullable
        - `scoreable_node_types` NodeType[], nullable
        - `cot_enabled` boolean, nullable
        - `output_type` 'boolean' | 'categorical' | 'count' | 'discrete' | 'freeform' | 'percentage' | 'multilabel' | 'retrieved_chunk_list_boolean' | 'boolean_multilabel' — Enumeration of output types.
        - `input_type` 'basic' | 'llm_spans' | 'retriever_spans' | 'sessions_normalized' | 'sessions_trace_io_only' | 'tool_spans' | 'trace_input_only' | 'trace_io_only' | 'trace_normalized' | 'trace_output_only' | 'agent_spans' | 'workflow_spans' — Enumeration of input types.
        - `multimodal_capabilities` MultimodalCapability[], nullable
        - `requires_tools_in_llm_span` boolean
        - `required_scorers` string[], nullable
        - `required_metric_ids` string[], nullable
        - `roll_up_strategy` 'avg' | 'sum' | 'first' | 'last' | 'none' — Strategies for rolling metrics up the Session/Trace/Span hierarchy.
        - `roll_up_methods` union
          - NumericRollUpMethod[]
          - CategoricalRollUpMethod[]
        - `prompt` string, nullable
        - `lora_task_id` integer, nullable
        - `lora_weights_path` string, nullable
        - `luna_input_type` 'span' | 'trace_object' | 'trace_input_output_only'
        - `luna_output_type` 'float' | 'string' | 'string_list' | 'bool_list'
        - `class_name_to_vocab_ix` union
          - object
          - object
        - `scorer_path_name` string, nullable
        - `function_explanation_param_name` string
      - CustomizedGroundednessGPTScorer
        - `scorer_name` '_customized_groundedness'
        - `model_alias` string
        - `num_judges` integer
        - `name` 'context_adherence'
        - `scores` unknown[], nullable
          - unknown
        - `indices` integer[], nullable
        - `aggregates` object, nullable
        - `aggregate_keys` string[]
        - `extra` object, nullable
        - `sub_scorers` PromptgalileoSchemasScorerNameScorerName[]
        - `filters` union[], nullable
          - union
            - NodeNameFilter — Filters on node names in scorer jobs.
              - …
            - MetadataFilter — Filters on metadata key-value pairs in scorer jobs.
              - …
            - ModalityFilter — Filters on content modalities in scorer jobs. Matches if at least one of the specified modalities is present.
              - …
        - `metric_name` string, nullable
        - `description` string, nullable
        - `chainpoll_template` GroundednessTemplate — Template for the groundedness metric, containing all the info necessary to send the groundedness prompt.
          - `metric_system_prompt` string
          - `metric_description` string
          - `value_field_name` string
          - `explanation_field_name` string — Field name to look for in the chainpoll response, for the explanation.
          - `template` string
          - `metric_few_shot_examples` FewShotExample[]
            - `generation_prompt_and_response` string, required
            - `evaluating_response` string, required
          - `response_schema` object, nullable — Response schema for the output
        - `default_model_alias` string, nullable
        - `ground_truth` boolean, nullable
        - `regex_field` string
        - `registered_scorer_id` string, uuid4, nullable
        - `generated_scorer_id` string, uuid4, nullable
        - `scorer_version_id` string, uuid4, nullable
        - `user_code` string, nullable
        - `can_copy_to_llm` boolean, nullable
        - `scoreable_node_types` NodeType[], nullable
        - `cot_enabled` boolean, nullable
        - `output_type` 'boolean' | 'categorical' | 'count' | 'discrete' | 'freeform' | 'percentage' | 'multilabel' | 'retrieved_chunk_list_boolean' | 'boolean_multilabel' — Enumeration of output types.
        - `input_type` 'basic' | 'llm_spans' | 'retriever_spans' | 'sessions_normalized' | 'sessions_trace_io_only' | 'tool_spans' | 'trace_input_only' | 'trace_io_only' | 'trace_normalized' | 'trace_output_only' | 'agent_spans' | 'workflow_spans' — Enumeration of input types.
        - `multimodal_capabilities` MultimodalCapability[], nullable
        - `requires_tools_in_llm_span` boolean
        - `required_scorers` string[], nullable
        - `required_metric_ids` string[], nullable
        - `roll_up_strategy` 'avg' | 'sum' | 'first' | 'last' | 'none' — Strategies for rolling metrics up the Session/Trace/Span hierarchy.
        - `roll_up_methods` union
          - NumericRollUpMethod[]
          - CategoricalRollUpMethod[]
        - `prompt` string, nullable
        - `lora_task_id` integer, nullable
        - `lora_weights_path` string, nullable
        - `luna_input_type` 'span' | 'trace_object' | 'trace_input_output_only'
        - `luna_output_type` 'float' | 'string' | 'string_list' | 'bool_list'
        - `class_name_to_vocab_ix` union
          - object
          - object
        - `scorer_path_name` string, nullable
      - CustomizedInstructionAdherenceGPTScorer
        - `scorer_name` '_customized_instruction_adherence'
        - `model_alias` string
        - `num_judges` integer
        - `name` 'instruction_adherence'
        - `scores` unknown[], nullable
          - unknown
        - `indices` integer[], nullable
        - `aggregates` object, nullable
        - `aggregate_keys` string[]
        - `extra` object, nullable
        - `sub_scorers` PromptgalileoSchemasScorerNameScorerName[]
        - `filters` union[], nullable
          - union
            - NodeNameFilter — Filters on node names in scorer jobs.
              - …
            - MetadataFilter — Filters on metadata key-value pairs in scorer jobs.
              - …
            - ModalityFilter — Filters on content modalities in scorer jobs. Matches if at least one of the specified modalities is present.
              - …
        - `metric_name` string, nullable
        - `description` string, nullable
        - `chainpoll_template` InstructionAdherenceTemplate
          - `metric_system_prompt` string
          - `metric_description` string
          - `value_field_name` string
          - `explanation_field_name` string — Field name to look for in the chainpoll response, for the explanation.
          - `template` string
          - `metric_few_shot_examples` FewShotExample[]
            - `generation_prompt_and_response` string, required
            - `evaluating_response` string, required
          - `response_schema` object, nullable — Response schema for the output
        - `default_model_alias` string, nullable
        - `ground_truth` boolean, nullable
        - `regex_field` string
        - `registered_scorer_id` string, uuid4, nullable
        - `generated_scorer_id` string, uuid4, nullable
        - `scorer_version_id` string, uuid4, nullable
        - `user_code` string, nullable
        - `can_copy_to_llm` boolean, nullable
        - `scoreable_node_types` NodeType[], nullable
        - `cot_enabled` boolean, nullable
        - `output_type` 'boolean' | 'categorical' | 'count' | 'discrete' | 'freeform' | 'percentage' | 'multilabel' | 'retrieved_chunk_list_boolean' | 'boolean_multilabel' — Enumeration of output types.
        - `input_type` 'basic' | 'llm_spans' | 'retriever_spans' | 'sessions_normalized' | 'sessions_trace_io_only' | 'tool_spans' | 'trace_input_only' | 'trace_io_only' | 'trace_normalized' | 'trace_output_only' | 'agent_spans' | 'workflow_spans' — Enumeration of input types.
        - `multimodal_capabilities` MultimodalCapability[], nullable
        - `requires_tools_in_llm_span` boolean
        - `required_scorers` string[], nullable
        - `required_metric_ids` string[], nullable
        - `roll_up_strategy` 'avg' | 'sum' | 'first' | 'last' | 'none' — Strategies for rolling metrics up the Session/Trace/Span hierarchy.
        - `roll_up_methods` union
          - NumericRollUpMethod[]
          - CategoricalRollUpMethod[]
        - `prompt` string, nullable
        - `lora_task_id` integer, nullable
        - `lora_weights_path` string, nullable
        - `luna_input_type` 'span' | 'trace_object' | 'trace_input_output_only'
        - `luna_output_type` 'float' | 'string' | 'string_list' | 'bool_list'
        - `class_name_to_vocab_ix` union
          - object
          - object
        - `scorer_path_name` string, nullable
        - `function_explanation_param_name` string
      - CustomizedGroundTruthAdherenceGPTScorer
        - `scorer_name` '_customized_ground_truth_adherence'
        - `model_alias` string
        - `num_judges` integer
        - `name` 'ground_truth_adherence'
        - `scores` unknown[], nullable
          - unknown
        - `indices` integer[], nullable
        - `aggregates` object, nullable
        - `aggregate_keys` string[]
        - `extra` object, nullable
        - `sub_scorers` PromptgalileoSchemasScorerNameScorerName[]
        - `filters` union[], nullable
          - union
            - NodeNameFilter — Filters on node names in scorer jobs.
              - …
            - MetadataFilter — Filters on metadata key-value pairs in scorer jobs.
              - …
            - ModalityFilter — Filters on content modalities in scorer jobs. Matches if at least one of the specified modalities is present.
              - …
        - `metric_name` string, nullable
        - `description` string, nullable
        - `chainpoll_template` GroundTruthAdherenceTemplate
          - `metric_system_prompt` string
          - `metric_description` string
          - `value_field_name` string
          - `explanation_field_name` string — Field name to look for in the chainpoll response, for the explanation.
          - `template` string
          - `metric_few_shot_examples` FewShotExample[] — Few-shot examples for the metric.
            - `generation_prompt_and_response` string, required
            - `evaluating_response` string, required
          - `response_schema` object, nullable — Response schema for the output
        - `default_model_alias` string, nullable
        - `ground_truth` boolean, nullable
        - `regex_field` string
        - `registered_scorer_id` string, uuid4, nullable
        - `generated_scorer_id` string, uuid4, nullable
        - `scorer_version_id` string, uuid4, nullable
        - `user_code` string, nullable
        - `can_copy_to_llm` boolean, nullable
        - `scoreable_node_types` NodeType[], nullable
        - `cot_enabled` boolean, nullable
        - `output_type` 'boolean' | 'categorical' | 'count' | 'discrete' | 'freeform' | 'percentage' | 'multilabel' | 'retrieved_chunk_list_boolean' | 'boolean_multilabel' — Enumeration of output types.
        - `input_type` 'basic' | 'llm_spans' | 'retriever_spans' | 'sessions_normalized' | 'sessions_trace_io_only' | 'tool_spans' | 'trace_input_only' | 'trace_io_only' | 'trace_normalized' | 'trace_output_only' | 'agent_spans' | 'workflow_spans' — Enumeration of input types.
        - `multimodal_capabilities` MultimodalCapability[], nullable
        - `requires_tools_in_llm_span` boolean
        - `required_scorers` string[], nullable
        - `required_metric_ids` string[], nullable
        - `roll_up_strategy` 'avg' | 'sum' | 'first' | 'last' | 'none' — Strategies for rolling metrics up the Session/Trace/Span hierarchy.
        - `roll_up_methods` union
          - NumericRollUpMethod[]
          - CategoricalRollUpMethod[]
        - `prompt` string, nullable
        - `lora_task_id` integer, nullable
        - `lora_weights_path` string, nullable
        - `luna_input_type` 'span' | 'trace_object' | 'trace_input_output_only'
        - `luna_output_type` 'float' | 'string' | 'string_list' | 'bool_list'
        - `class_name_to_vocab_ix` union
          - object
          - object
        - `scorer_path_name` string, nullable
      - CustomizedPromptInjectionGPTScorer
        - `scorer_name` '_customized_prompt_injection_gpt'
        - `model_alias` string
        - `num_judges` integer
        - `name` 'prompt_injection'
        - `scores` unknown[], nullable
          - unknown
        - `indices` integer[], nullable
        - `aggregates` object, nullable
        - `aggregate_keys` string[]
        - `extra` object, nullable
        - `sub_scorers` PromptgalileoSchemasScorerNameScorerName[]
        - `filters` union[], nullable
          - union
            - NodeNameFilter — Filters on node names in scorer jobs.
              - …
            - MetadataFilter — Filters on metadata key-value pairs in scorer jobs.
              - …
            - ModalityFilter — Filters on content modalities in scorer jobs. Matches if at least one of the specified modalities is present.
              - …
        - `metric_name` string, nullable
        - `description` string, nullable
        - `chainpoll_template` PromptInjectionTemplate — Template for the prompt injection metric, containing all the info necessary to send the prompt injection prompt.
          - `metric_system_prompt` string
          - `metric_description` string
          - `value_field_name` string
          - `explanation_field_name` string — Field name to look for in the chainpoll response, for the explanation.
          - `template` string
          - `metric_few_shot_examples` FewShotExample[]
            - `generation_prompt_and_response` string, required
            - `evaluating_response` string, required
          - `response_schema` object, nullable — Response schema for the output
        - `default_model_alias` string, nullable
        - `ground_truth` boolean, nullable
        - `regex_field` string
        - `registered_scorer_id` string, uuid4, nullable
        - `generated_scorer_id` string, uuid4, nullable
        - `scorer_version_id` string, uuid4, nullable
        - `user_code` string, nullable
        - `can_copy_to_llm` boolean, nullable
        - `scoreable_node_types` NodeType[], nullable
        - `cot_enabled` boolean, nullable
        - `output_type` 'boolean' | 'categorical' | 'count' | 'discrete' | 'freeform' | 'percentage' | 'multilabel' | 'retrieved_chunk_list_boolean' | 'boolean_multilabel' — Enumeration of output types.
        - `input_type` 'basic' | 'llm_spans' | 'retriever_spans' | 'sessions_normalized' | 'sessions_trace_io_only' | 'tool_spans' | 'trace_input_only' | 'trace_io_only' | 'trace_normalized' | 'trace_output_only' | 'agent_spans' | 'workflow_spans' — Enumeration of input types.
        - `multimodal_capabilities` MultimodalCapability[], nullable
        - `requires_tools_in_llm_span` boolean
        - `required_scorers` string[], nullable
        - `required_metric_ids` string[], nullable
        - `roll_up_strategy` 'avg' | 'sum' | 'first' | 'last' | 'none' — Strategies for rolling metrics up the Session/Trace/Span hierarchy.
        - `roll_up_methods` union
          - NumericRollUpMethod[]
          - CategoricalRollUpMethod[]
        - `prompt` string, nullable
        - `lora_task_id` integer, nullable
        - `lora_weights_path` string, nullable
        - `luna_input_type` 'span' | 'trace_object' | 'trace_input_output_only'
        - `luna_output_type` 'float' | 'string' | 'string_list' | 'bool_list'
        - `class_name_to_vocab_ix` union
          - object
          - object
        - `scorer_path_name` string, nullable
      - CustomizedSexistGPTScorer
        - `scorer_name` '_customized_sexist_gpt'
        - `model_alias` string
        - `num_judges` integer
        - `name` 'output_sexist'
        - `scores` unknown[], nullable
          - unknown
        - `indices` integer[], nullable
        - `aggregates` object, nullable
        - `aggregate_keys` string[]
        - `extra` object, nullable
        - `sub_scorers` PromptgalileoSchemasScorerNameScorerName[]
        - `filters` union[], nullable
          - union
            - NodeNameFilter — Filters on node names in scorer jobs.
              - …
            - MetadataFilter — Filters on metadata key-value pairs in scorer jobs.
              - …
            - ModalityFilter — Filters on content modalities in scorer jobs. Matches if at least one of the specified modalities is present.
              - …
        - `metric_name` string, nullable
        - `description` string, nullable
        - `chainpoll_template` SexistTemplate — Template for the sexism metric, containing all the info necessary to send the sexism prompt.
          - `metric_system_prompt` string
          - `metric_description` string
          - `value_field_name` string
          - `explanation_field_name` string — Field name to look for in the chainpoll response, for the explanation.
          - `template` string
          - `metric_few_shot_examples` FewShotExample[]
            - `generation_prompt_and_response` string, required
            - `evaluating_response` string, required
          - `response_schema` object, nullable — Response schema for the output
        - `default_model_alias` string, nullable
        - `ground_truth` boolean, nullable
        - `regex_field` string
        - `registered_scorer_id` string, uuid4, nullable
        - `generated_scorer_id` string, uuid4, nullable
        - `scorer_version_id` string, uuid4, nullable
        - `user_code` string, nullable
        - `can_copy_to_llm` boolean, nullable
        - `scoreable_node_types` NodeType[], nullable
        - `cot_enabled` boolean, nullable
        - `output_type` 'boolean' | 'categorical' | 'count' | 'discrete' | 'freeform' | 'percentage' | 'multilabel' | 'retrieved_chunk_list_boolean' | 'boolean_multilabel' — Enumeration of output types.
        - `input_type` 'basic' | 'llm_spans' | 'retriever_spans' | 'sessions_normalized' | 'sessions_trace_io_only' | 'tool_spans' | 'trace_input_only' | 'trace_io_only' | 'trace_normalized' | 'trace_output_only' | 'agent_spans' | 'workflow_spans' — Enumeration of input types.
        - `multimodal_capabilities` MultimodalCapability[], nullable
        - `requires_tools_in_llm_span` boolean
        - `required_scorers` string[], nullable
        - `required_metric_ids` string[], nullable
        - `roll_up_strategy` 'avg' | 'sum' | 'first' | 'last' | 'none' — Strategies for rolling metrics up the Session/Trace/Span hierarchy.
        - `roll_up_methods` union
          - NumericRollUpMethod[]
          - CategoricalRollUpMethod[]
        - `prompt` string, nullable
        - `lora_task_id` integer, nullable
        - `lora_weights_path` string, nullable
        - `luna_input_type` 'span' | 'trace_object' | 'trace_input_output_only'
        - `luna_output_type` 'float' | 'string' | 'string_list' | 'bool_list'
        - `class_name_to_vocab_ix` union
          - object
          - object
        - `scorer_path_name` string, nullable
      - CustomizedInputSexistGPTScorer
        - `scorer_name` '_customized_input_sexist_gpt'
        - `model_alias` string
        - `num_judges` integer
        - `name` 'input_sexist'
        - `scores` unknown[], nullable
          - unknown
        - `indices` integer[], nullable
        - `aggregates` object, nullable
        - `aggregate_keys` string[]
        - `extra` object, nullable
        - `sub_scorers` PromptgalileoSchemasScorerNameScorerName[]
        - `filters` union[], nullable
          - union
            - NodeNameFilter — Filters on node names in scorer jobs.
              - …
            - MetadataFilter — Filters on metadata key-value pairs in scorer jobs.
              - …
            - ModalityFilter — Filters on content modalities in scorer jobs. Matches if at least one of the specified modalities is present.
              - …
        - `metric_name` string, nullable
        - `description` string, nullable
        - `chainpoll_template` InputSexistTemplate — Template for the sexism metric, containing all the info necessary to send the sexism prompt.
          - `metric_system_prompt` string
          - `metric_description` string
          - `value_field_name` string
          - `explanation_field_name` string — Field name to look for in the chainpoll response, for the explanation.
          - `template` string
          - `metric_few_shot_examples` FewShotExample[]
            - `generation_prompt_and_response` string, required
            - `evaluating_response` string, required
          - `response_schema` object, nullable — Response schema for the output
        - `default_model_alias` string, nullable
        - `ground_truth` boolean, nullable
        - `regex_field` string
        - `registered_scorer_id` string, uuid4, nullable
        - `generated_scorer_id` string, uuid4, nullable
        - `scorer_version_id` string, uuid4, nullable
        - `user_code` string, nullable
        - `can_copy_to_llm` boolean, nullable
        - `scoreable_node_types` NodeType[], nullable
        - `cot_enabled` boolean, nullable
        - `output_type` 'boolean' | 'categorical' | 'count' | 'discrete' | 'freeform' | 'percentage' | 'multilabel' | 'retrieved_chunk_list_boolean' | 'boolean_multilabel' — Enumeration of output types.
        - `input_type` 'basic' | 'llm_spans' | 'retriever_spans' | 'sessions_normalized' | 'sessions_trace_io_only' | 'tool_spans' | 'trace_input_only' | 'trace_io_only' | 'trace_normalized' | 'trace_output_only' | 'agent_spans' | 'workflow_spans' — Enumeration of input types.
        - `multimodal_capabilities` MultimodalCapability[], nullable
        - `requires_tools_in_llm_span` boolean
        - `required_scorers` string[], nullable
        - `required_metric_ids` string[], nullable
        - `roll_up_strategy` 'avg' | 'sum' | 'first' | 'last' | 'none' — Strategies for rolling metrics up the Session/Trace/Span hierarchy.
        - `roll_up_methods` union
          - NumericRollUpMethod[]
          - CategoricalRollUpMethod[]
        - `prompt` string, nullable
        - `lora_task_id` integer, nullable
        - `lora_weights_path` string, nullable
        - `luna_input_type` 'span' | 'trace_object' | 'trace_input_output_only'
        - `luna_output_type` 'float' | 'string' | 'string_list' | 'bool_list'
        - `class_name_to_vocab_ix` union
          - object
          - object
        - `scorer_path_name` string, nullable
      - CustomizedToolSelectionQualityGPTScorer
        - `scorer_name` '_customized_tool_selection_quality'
        - `model_alias` string
        - `num_judges` integer
        - `name` 'tool_selection_quality'
        - `scores` unknown[], nullable
          - unknown
        - `indices` integer[], nullable
        - `aggregates` object, nullable
        - `aggregate_keys` string[]
        - `extra` object, nullable
        - `sub_scorers` PromptgalileoSchemasScorerNameScorerName[]
        - `filters` union[], nullable
          - union
            - NodeNameFilter — Filters on node names in scorer jobs.
              - …
            - MetadataFilter — Filters on metadata key-value pairs in scorer jobs.
              - …
            - ModalityFilter — Filters on content modalities in scorer jobs. Matches if at least one of the specified modalities is present.
              - …
        - `metric_name` string, nullable
        - `description` string, nullable
        - `chainpoll_template` ToolSelectionQualityTemplate — Template for the tool selection quality metric, containing all the info necessary to send the tool selection quality prompt.
          - `metric_system_prompt` string
          - `metric_description` string
          - `value_field_name` string
          - `explanation_field_name` string — Field name to look for in the chainpoll response, for the explanation.
          - `template` string
          - `metric_few_shot_examples` FewShotExample[]
            - `generation_prompt_and_response` string, required
            - `evaluating_response` string, required
          - `response_schema` object, nullable — Response schema for the output
        - `default_model_alias` string, nullable
        - `ground_truth` boolean, nullable
        - `regex_field` string
        - `registered_scorer_id` string, uuid4, nullable
        - `generated_scorer_id` string, uuid4, nullable
        - `scorer_version_id` string, uuid4, nullable
        - `user_code` string, nullable
        - `can_copy_to_llm` boolean, nullable
        - `scoreable_node_types` NodeType[], nullable
        - `cot_enabled` boolean, nullable
        - `output_type` 'boolean' | 'categorical' | 'count' | 'discrete' | 'freeform' | 'percentage' | 'multilabel' | 'retrieved_chunk_list_boolean' | 'boolean_multilabel' — Enumeration of output types.
        - `input_type` 'basic' | 'llm_spans' | 'retriever_spans' | 'sessions_normalized' | 'sessions_trace_io_only' | 'tool_spans' | 'trace_input_only' | 'trace_io_only' | 'trace_normalized' | 'trace_output_only' | 'agent_spans' | 'workflow_spans' — Enumeration of input types.
        - `multimodal_capabilities` MultimodalCapability[], nullable
        - `requires_tools_in_llm_span` boolean
        - `required_scorers` string[], nullable
        - `required_metric_ids` string[], nullable
        - `roll_up_strategy` 'avg' | 'sum' | 'first' | 'last' | 'none' — Strategies for rolling metrics up the Session/Trace/Span hierarchy.
        - `roll_up_methods` union
          - NumericRollUpMethod[]
          - CategoricalRollUpMethod[]
        - `prompt` string, nullable
        - `lora_task_id` integer, nullable
        - `lora_weights_path` string, nullable
        - `luna_input_type` 'span' | 'trace_object' | 'trace_input_output_only'
        - `luna_output_type` 'float' | 'string' | 'string_list' | 'bool_list'
        - `class_name_to_vocab_ix` union
          - object
          - object
        - `scorer_path_name` string, nullable
      - CustomizedToolErrorRateGPTScorer
        - `scorer_name` '_customized_tool_error_rate'
        - `model_alias` string
        - `num_judges` integer
        - `name` 'tool_error_rate'
        - `scores` unknown[], nullable
          - unknown
        - `indices` integer[], nullable
        - `aggregates` object, nullable
        - `aggregate_keys` string[]
        - `extra` object, nullable
        - `sub_scorers` PromptgalileoSchemasScorerNameScorerName[]
        - `filters` union[], nullable
          - union
            - NodeNameFilter — Filters on node names in scorer jobs.
              - …
            - MetadataFilter — Filters on metadata key-value pairs in scorer jobs.
              - …
            - ModalityFilter — Filters on content modalities in scorer jobs. Matches if at least one of the specified modalities is present.
              - …
        - `metric_name` string, nullable
        - `description` string, nullable
        - `chainpoll_template` ToolErrorRateTemplate — Template for the tool error rate metric, containing all the info necessary to send the tool error rate prompt.
          - `metric_system_prompt` string
          - `metric_description` string
          - `value_field_name` string
          - `explanation_field_name` string — Field name to look for in the chainpoll response, for the explanation.
          - `template` string
          - `metric_few_shot_examples` FewShotExample[]
            - `generation_prompt_and_response` string, required
            - `evaluating_response` string, required
          - `response_schema` object, nullable — Response schema for the output
        - `default_model_alias` string, nullable
        - `ground_truth` boolean, nullable
        - `regex_field` string
        - `registered_scorer_id` string, uuid4, nullable
        - `generated_scorer_id` string, uuid4, nullable
        - `scorer_version_id` string, uuid4, nullable
        - `user_code` string, nullable
        - `can_copy_to_llm` boolean, nullable
        - `scoreable_node_types` NodeType[], nullable
        - `cot_enabled` boolean, nullable
        - `output_type` 'boolean' | 'categorical' | 'count' | 'discrete' | 'freeform' | 'percentage' | 'multilabel' | 'retrieved_chunk_list_boolean' | 'boolean_multilabel' — Enumeration of output types.
        - `input_type` 'basic' | 'llm_spans' | 'retriever_spans' | 'sessions_normalized' | 'sessions_trace_io_only' | 'tool_spans' | 'trace_input_only' | 'trace_io_only' | 'trace_normalized' | 'trace_output_only' | 'agent_spans' | 'workflow_spans' — Enumeration of input types.
        - `multimodal_capabilities` MultimodalCapability[], nullable
        - `requires_tools_in_llm_span` boolean
        - `required_scorers` string[], nullable
        - `required_metric_ids` string[], nullable
        - `roll_up_strategy` 'avg' | 'sum' | 'first' | 'last' | 'none' — Strategies for rolling metrics up the Session/Trace/Span hierarchy.
        - `roll_up_methods` union
          - NumericRollUpMethod[]
          - CategoricalRollUpMethod[]
        - `prompt` string, nullable
        - `lora_task_id` integer, nullable
        - `lora_weights_path` string, nullable
        - `luna_input_type` 'span' | 'trace_object' | 'trace_input_output_only'
        - `luna_output_type` 'float' | 'string' | 'string_list' | 'bool_list'
        - `class_name_to_vocab_ix` union
          - object
          - object
        - `scorer_path_name` string, nullable
      - CustomizedToxicityGPTScorer
        - `scorer_name` '_customized_toxicity_gpt'
        - `model_alias` string
        - `num_judges` integer
        - `name` 'output_toxicity'
        - `scores` unknown[], nullable
          - unknown
        - `indices` integer[], nullable
        - `aggregates` object, nullable
        - `aggregate_keys` string[]
        - `extra` object, nullable
        - `sub_scorers` PromptgalileoSchemasScorerNameScorerName[]
        - `filters` union[], nullable
          - union
            - NodeNameFilter — Filters on node names in scorer jobs.
              - …
            - MetadataFilter — Filters on metadata key-value pairs in scorer jobs.
              - …
            - ModalityFilter — Filters on content modalities in scorer jobs. Matches if at least one of the specified modalities is present.
              - …
        - `metric_name` string, nullable
        - `description` string, nullable
        - `chainpoll_template` ToxicityTemplate — Template for the toxicity metric, containing all the info necessary to send the toxicity prompt.
          - `metric_system_prompt` string
          - `metric_description` string
          - `value_field_name` string
          - `explanation_field_name` string — Field name to look for in the chainpoll response, for the explanation.
          - `template` string
          - `metric_few_shot_examples` FewShotExample[]
            - `generation_prompt_and_response` string, required
            - `evaluating_response` string, required
          - `response_schema` object, nullable — Response schema for the output
        - `default_model_alias` string, nullable
        - `ground_truth` boolean, nullable
        - `regex_field` string
        - `registered_scorer_id` string, uuid4, nullable
        - `generated_scorer_id` string, uuid4, nullable
        - `scorer_version_id` string, uuid4, nullable
        - `user_code` string, nullable
        - `can_copy_to_llm` boolean, nullable
        - `scoreable_node_types` NodeType[], nullable
        - `cot_enabled` boolean, nullable
        - `output_type` 'boolean' | 'categorical' | 'count' | 'discrete' | 'freeform' | 'percentage' | 'multilabel' | 'retrieved_chunk_list_boolean' | 'boolean_multilabel' — Enumeration of output types.
        - `input_type` 'basic' | 'llm_spans' | 'retriever_spans' | 'sessions_normalized' | 'sessions_trace_io_only' | 'tool_spans' | 'trace_input_only' | 'trace_io_only' | 'trace_normalized' | 'trace_output_only' | 'agent_spans' | 'workflow_spans' — Enumeration of input types.
        - `multimodal_capabilities` MultimodalCapability[], nullable
        - `requires_tools_in_llm_span` boolean
        - `required_scorers` string[], nullable
        - `required_metric_ids` string[], nullable
        - `roll_up_strategy` 'avg' | 'sum' | 'first' | 'last' | 'none' — Strategies for rolling metrics up the Session/Trace/Span hierarchy.
        - `roll_up_methods` union
          - NumericRollUpMethod[]
          - CategoricalRollUpMethod[]
        - `prompt` string, nullable
        - `lora_task_id` integer, nullable
        - `lora_weights_path` string, nullable
        - `luna_input_type` 'span' | 'trace_object' | 'trace_input_output_only'
        - `luna_output_type` 'float' | 'string' | 'string_list' | 'bool_list'
        - `class_name_to_vocab_ix` union
          - object
          - object
        - `scorer_path_name` string, nullable
      - CustomizedInputToxicityGPTScorer
        - `scorer_name` '_customized_input_toxicity_gpt'
        - `model_alias` string
        - `num_judges` integer
        - `name` 'input_toxicity'
        - `scores` unknown[], nullable
          - unknown
        - `indices` integer[], nullable
        - `aggregates` object, nullable
        - `aggregate_keys` string[]
        - `extra` object, nullable
        - `sub_scorers` PromptgalileoSchemasScorerNameScorerName[]
        - `filters` union[], nullable
          - union
            - NodeNameFilter — Filters on node names in scorer jobs.
              - …
            - MetadataFilter — Filters on metadata key-value pairs in scorer jobs.
              - …
            - ModalityFilter — Filters on content modalities in scorer jobs. Matches if at least one of the specified modalities is present.
              - …
        - `metric_name` string, nullable
        - `description` string, nullable
        - `chainpoll_template` InputToxicityTemplate — Template for the toxicity metric, containing all the info necessary to send the toxicity prompt.
          - `metric_system_prompt` string
          - `metric_description` string
          - `value_field_name` string
          - `explanation_field_name` string — Field name to look for in the chainpoll response, for the explanation.
          - `template` string
          - `metric_few_shot_examples` FewShotExample[]
            - `generation_prompt_and_response` string, required
            - `evaluating_response` string, required
          - `response_schema` object, nullable — Response schema for the output
        - `default_model_alias` string, nullable
        - `ground_truth` boolean, nullable
        - `regex_field` string
        - `registered_scorer_id` string, uuid4, nullable
        - `generated_scorer_id` string, uuid4, nullable
        - `scorer_version_id` string, uuid4, nullable
        - `user_code` string, nullable
        - `can_copy_to_llm` boolean, nullable
        - `scoreable_node_types` NodeType[], nullable
        - `cot_enabled` boolean, nullable
        - `output_type` 'boolean' | 'categorical' | 'count' | 'discrete' | 'freeform' | 'percentage' | 'multilabel' | 'retrieved_chunk_list_boolean' | 'boolean_multilabel' — Enumeration of output types.
        - `input_type` 'basic' | 'llm_spans' | 'retriever_spans' | 'sessions_normalized' | 'sessions_trace_io_only' | 'tool_spans' | 'trace_input_only' | 'trace_io_only' | 'trace_normalized' | 'trace_output_only' | 'agent_spans' | 'workflow_spans' — Enumeration of input types.
        - `multimodal_capabilities` MultimodalCapability[], nullable
        - `requires_tools_in_llm_span` boolean
        - `required_scorers` string[], nullable
        - `required_metric_ids` string[], nullable
        - `roll_up_strategy` 'avg' | 'sum' | 'first' | 'last' | 'none' — Strategies for rolling metrics up the Session/Trace/Span hierarchy.
        - `roll_up_methods` union
          - NumericRollUpMethod[]
          - CategoricalRollUpMethod[]
        - `prompt` string, nullable
        - `lora_task_id` integer, nullable
        - `lora_weights_path` string, nullable
        - `luna_input_type` 'span' | 'trace_object' | 'trace_input_output_only'
        - `luna_output_type` 'float' | 'string' | 'string_list' | 'bool_list'
        - `class_name_to_vocab_ix` union
          - object
          - object
        - `scorer_path_name` string, nullable
  - `prompt_scorer_settings` BaseScorer
    - `scorer_name` string
    - `name` string
    - `scores` unknown[], nullable
      - unknown
    - `indices` integer[], nullable
    - `aggregates` object, nullable
    - `aggregate_keys` string[], nullable
    - `extra` object, nullable
    - `sub_scorers` PromptgalileoSchemasScorerNameScorerName[]
    - `filters` union[], nullable
      - union
        - NodeNameFilter — Filters on node names in scorer jobs.
          - `name` 'node_name'
          - `operator` 'eq' | 'ne' | 'contains' | 'one_of' | 'not_in', required
          - `value` union, required
            - string
            - string[]
          - `case_sensitive` boolean
        - MetadataFilter — Filters on metadata key-value pairs in scorer jobs.
          - `name` 'metadata'
          - `operator` 'one_of' | 'not_in' | 'eq' | 'ne', required
          - `key` string, required
          - `value` union, required
            - string
            - string[]
        - ModalityFilter — Filters on content modalities in scorer jobs. Matches if at least one of the specified modalities is present.
          - `name` 'modality'
          - `operator` 'eq' | 'ne' | 'one_of' | 'not_in', required
          - `value` union, required
            - string — Single enum value - specific options depend on the concrete enum type used
            - string[] — Array of enum values
    - `metric_name` string, nullable
    - `description` string, nullable
    - `chainpoll_template` ChainPollTemplate — Template for a chainpoll metric prompt, containing all the info necessary to send a chainpoll prompt.
      - `metric_system_prompt` string, nullable — System prompt for the metric.
      - `metric_description` string, nullable — Description of what the metric should do.
      - `value_field_name` string — Field name to look for in the chainpoll response, for the rating.
      - `explanation_field_name` string — Field name to look for in the chainpoll response, for the explanation.
      - `template` string, required — Chainpoll prompt template.
      - `metric_few_shot_examples` FewShotExample[] — Few-shot examples for the metric.
        - `generation_prompt_and_response` string, required
        - `evaluating_response` string, required
      - `response_schema` object, nullable — Response schema for the output
    - `model_alias` string, nullable
    - `num_judges` integer, nullable
    - `default_model_alias` string, nullable
    - `ground_truth` boolean, nullable
    - `regex_field` string
    - `registered_scorer_id` string, uuid4, nullable
    - `generated_scorer_id` string, uuid4, nullable
    - `scorer_version_id` string, uuid4, nullable
    - `user_code` string, nullable
    - `can_copy_to_llm` boolean, nullable
    - `scoreable_node_types` NodeType[], nullable
    - `cot_enabled` boolean, nullable
    - `output_type` 'boolean' | 'categorical' | 'count' | 'discrete' | 'freeform' | 'percentage' | 'multilabel' | 'retrieved_chunk_list_boolean' | 'boolean_multilabel' — Enumeration of output types.
    - `input_type` 'basic' | 'llm_spans' | 'retriever_spans' | 'sessions_normalized' | 'sessions_trace_io_only' | 'tool_spans' | 'trace_input_only' | 'trace_io_only' | 'trace_normalized' | 'trace_output_only' | 'agent_spans' | 'workflow_spans' — Enumeration of input types.
    - `multimodal_capabilities` MultimodalCapability[], nullable
    - `requires_tools_in_llm_span` boolean
    - `required_scorers` string[], nullable
    - `required_metric_ids` string[], nullable
    - `roll_up_strategy` 'avg' | 'sum' | 'first' | 'last' | 'none' — Strategies for rolling metrics up the Session/Trace/Span hierarchy.
    - `roll_up_methods` union
      - NumericRollUpMethod[]
      - CategoricalRollUpMethod[]
    - `prompt` string, nullable
    - `lora_task_id` integer, nullable
    - `lora_weights_path` string, nullable
    - `luna_input_type` 'span' | 'trace_object' | 'trace_input_output_only'
    - `luna_output_type` 'float' | 'string' | 'string_list' | 'bool_list'
    - `class_name_to_vocab_ix` union
      - object
      - object
    - `scorer_path_name` string, nullable
  - `scorer_config` RuntimeScorerConfig — Hydrated scorer config used at runtime. Never persisted directly. Produced by hydrate_scorer_config from a StoredScorerConfig + live DB rows.
    - `id` string, uuid4, required
    - `scorer_version_id` string, uuid4, nullable
    - `filters` union[], nullable — List of filters to apply to the scorer.
      - union
        - NodeNameFilter — Filters on node names in scorer jobs.
          - `name` 'node_name'
          - `operator` 'eq' | 'ne' | 'contains' | 'one_of' | 'not_in', required
          - `value` union, required
            - string
            - string[]
          - `case_sensitive` boolean
        - MetadataFilter — Filters on metadata key-value pairs in scorer jobs.
          - `name` 'metadata'
          - `operator` 'one_of' | 'not_in' | 'eq' | 'ne', required
          - `key` string, required
          - `value` union, required
            - string
            - string[]
        - ModalityFilter — Filters on content modalities in scorer jobs. Matches if at least one of the specified modalities is present.
          - `name` 'modality'
          - `operator` 'eq' | 'ne' | 'one_of' | 'not_in', required
          - `value` union, required
            - string — Single enum value - specific options depend on the concrete enum type used
            - string[] — Array of enum values
    - `roll_up_method` 'average' | 'sum' | 'max' | 'min' | 'category_count' | 'percentage_true' | 'percentage_false' — Display options for roll up methods when showing rolled up metrics in the UI. Separates display intent from computation methods. The computation methods (NumericRollUpMethod, CategoricalRollUpMethod) control what aggregations are available. This enum controls how the UI displays the selected roll-up value for a scorer.
    - `name` string, nullable
    - `scorer_type` 'llm' | 'code' | 'luna' | 'preset'
    - `model_name` string, nullable
    - `num_judges` integer, nullable
    - `scorer_version` BaseScorerVersionDB — Scorer version from the scorer_versions table.
      - `id` string, uuid4, required
      - `version` integer, required
      - `scorer_id` string, uuid4, required
      - `generated_scorer` BaseGeneratedScorerDB
        - `id` string, uuid4, required
        - `name` string, required
        - `instructions` string, nullable
        - `chain_poll_template` ChainPollTemplate, required — Template for a chainpoll metric prompt, containing all the info necessary to send a chainpoll prompt.
          - `metric_system_prompt` string, nullable — System prompt for the metric.
          - `metric_description` string, nullable — Description of what the metric should do.
          - `value_field_name` string — Field name to look for in the chainpoll response, for the rating.
          - `explanation_field_name` string — Field name to look for in the chainpoll response, for the explanation.
          - `template` string, required — Chainpoll prompt template.
          - `metric_few_shot_examples` FewShotExample[] — Few-shot examples for the metric.
            - `generation_prompt_and_response` string, required
            - `evaluating_response` string, required
          - `response_schema` object, nullable — Response schema for the output
        - `user_prompt` string, nullable
      - `registered_scorer` BaseRegisteredScorerDB
        - `id` string, uuid4, required
        - `name` string, required
        - `score_type` string, nullable
      - `finetuned_scorer` BaseFinetunedScorerDB
        - `id` string, uuid4, required
        - `name` string, required
        - `lora_task_id` integer, required
        - `lora_weights_path` string, nullable
        - `prompt` string, required
        - `luna_input_type` 'span' | 'trace_object' | 'trace_input_output_only'
        - `luna_output_type` 'float' | 'string' | 'string_list' | 'bool_list'
        - `class_name_to_vocab_ix` union
          - object
          - object
        - `executor` 'action_completion_luna' | 'action_advancement_luna' | 'agentic_session_success' | 'agentic_session_success' | 'action_completion_vision' | 'action_completion_audio' | 'agentic_workflow_success' | 'agentic_workflow_success' | 'agent_efficiency' | 'agent_flow' | 'agent_flow_vision' | 'agent_flow_audio' | 'chunk_attribution_utilization_luna' | 'chunk_attribution_utilization' | 'chunk_relevance' | 'chunk_relevance_luna' | 'context_precision' | 'precision_at_k' | 'completeness_luna' | 'completeness' | 'context_adherence' | 'context_adherence_luna' | 'context_adherence_vision' | 'context_adherence_audio' | 'context_relevance' | 'context_relevance_luna' | 'conversation_quality' | 'conversation_quality_vision' | 'conversation_quality_audio' | 'correctness' | 'correctness_vision' | 'correctness_audio' | 'ground_truth_adherence' | 'ground_truth_adherence_vision' | 'ground_truth_adherence_audio' | 'visual_fidelity' | 'visual_quality' | 'input_pii' | 'input_pii_gpt' | 'input_sexist' | 'input_sexist' | 'input_sexist_vision' | 'input_sexist_audio' | 'input_sexist_luna' | 'input_sexist_luna' | 'input_tone' | 'input_tone_gpt' | 'input_toxicity' | 'input_toxicity_luna' | 'input_toxicity_vision' | 'input_toxicity_audio' | 'instruction_adherence' | 'instruction_adherence_vision' | 'instruction_adherence_audio' | 'output_pii' | 'output_pii_gpt' | 'output_sexist' | 'output_sexist' | 'output_sexist_vision' | 'output_sexist_audio' | 'output_sexist_luna' | 'output_sexist_luna' | 'output_tone' | 'output_tone_gpt' | 'output_toxicity' | 'output_toxicity_luna' | 'output_toxicity_vision' | 'output_toxicity_audio' | 'prompt_injection' | 'prompt_injection_vision' | 'prompt_injection_audio' | 'prompt_injection_luna' | 'reasoning_coherence' | 'reasoning_coherence_vision' | 'reasoning_coherence_audio' | 'sql_efficiency' | 'sql_adherence' | 'sql_injection' | 'sql_correctness' | 'tool_error_rate' | 'tool_error_rate_luna' | 'tool_selection_quality' | 'tool_selection_quality_vision' | 'tool_selection_quality_audio' | 'tool_selection_quality_luna' | 'user_intent_change' | 'user_intent_change_vision' | 'user_intent_change_audio' | 'interruption_detection'
      - `model_name` string, nullable
      - `num_judges` integer, nullable
      - `cot_enabled` boolean, nullable — Whether to enable chain of thought for this scorer. Defaults to False for llm scorers.
    - `scoreable_node_types` string[], nullable — List of node types that can be scored by this scorer. Defaults to llm/chat.
    - `cot_enabled` boolean, nullable — Whether to enable chain of thought for this scorer. Defaults to False for llm scorers.
    - `output_type` 'boolean' | 'categorical' | 'count' | 'discrete' | 'freeform' | 'percentage' | 'multilabel' | 'retrieved_chunk_list_boolean' | 'boolean_multilabel' — Enumeration of output types.
    - `input_type` 'basic' | 'llm_spans' | 'retriever_spans' | 'sessions_normalized' | 'sessions_trace_io_only' | 'tool_spans' | 'trace_input_only' | 'trace_io_only' | 'trace_normalized' | 'trace_output_only' | 'agent_spans' | 'workflow_spans' — Enumeration of input types.
    - `multimodal_capabilities` MultimodalCapability[], nullable — Multimodal capabilities which this scorer can utilize in its evaluation.
    - `roll_up_config` BaseMetricRollUpConfigDB — Configuration for rolling up metrics to parent/trace/session.
      - `roll_up_methods` union, required — List of roll up methods to apply to the metric. For numeric scorers we support doing multiple roll up types per metric.
        - NumericRollUpMethod[]
        - CategoricalRollUpMethod[]
    - `score_type` string, nullable — Return type of code scorers (e.g., 'bool', 'int', 'float', 'str').
  - `sub_scorers` PromptgalileoSchemasScorerNameScorerName[]
  - `luna_model` string, nullable
  - `segment_filters` SegmentFilter[], nullable
    - `filter` union — Filter to apply to the segment. By default sample on all data.
      - NodeNameFilter — Filters on node names in scorer jobs.
        - `name` 'node_name'
        - `operator` 'eq' | 'ne' | 'contains' | 'one_of' | 'not_in', required
        - `value` union, required
          - string
          - string[]
        - `case_sensitive` boolean
      - MetadataFilter — Filters on metadata key-value pairs in scorer jobs.
        - `name` 'metadata'
        - `operator` 'one_of' | 'not_in' | 'eq' | 'ne', required
        - `key` string, required
        - `value` union, required
          - string
          - string[]
      - ModalityFilter — Filters on content modalities in scorer jobs. Matches if at least one of the specified modalities is present.
        - `name` 'modality'
        - `operator` 'eq' | 'ne' | 'one_of' | 'not_in', required
        - `value` union, required
          - string — Single enum value - specific options depend on the concrete enum type used
          - string[] — Array of enum values
    - `sample_rate` number, required — The fraction of the data to sample. Must be between 0 and 1, inclusive.
    - `llm_scorers` boolean — Whether to sample only on LLM scorers.
    - `multimodal_scorers` boolean — Whether to sample only on multimodal scorers.
  - `is_session` boolean, nullable
  - `validation_config` object, nullable
  - `upload_data_in_separate_task` boolean
  - `log_metric_computing_records` boolean
  - `stream_metrics` boolean
  - `multijudge_average_boolean_metrics` boolean
  - `store_metric_ids` boolean
  - `trace_ids` string[]
  - `message` string, required
  - `link` string, required

## Other responses

- `422` — Validation Error

---

[API](https://skmtc.net/galileo/apis/galileo-api-server.md) · [All operations](https://skmtc.net/galileo/apis/galileo-api-server/llms.txt) · [OpenAPI document](https://skmtc-service-staging.skmtc.workers.dev/v1/apis/galileo/galileo-api-server/revisions/035e923935c1/schema)