judgeval 0.8.0__py3-none-any.whl → 0.9.0__py3-none-any.whl

judgeval/data/judgment_types.py

@@ -1,57 +1,129 @@
 # generated by datamodel-codegen:
-#   filename:  openapi_new.json
-#   timestamp: 2025-08-08T18:50:51+00:00
+#   filename:  .openapi.json
+#   timestamp: 2025-08-29T04:49:38+00:00
 
 from __future__ import annotations
-
 from typing import Annotated, Any, Dict, List, Optional, Union
+from pydantic import AwareDatetime, BaseModel, ConfigDict, Field, RootModel
 
-from pydantic import BaseModel, ConfigDict, Field
 
+class TraceAndSpanId(RootModel[List]):
+    root: Annotated[List, Field(max_length=2, min_length=2)]
+
+
+class EvalResultsFetch(BaseModel):
+    experiment_run_id: Annotated[str, Field(title="Experiment Run Id")]
+    project_name: Annotated[str, Field(title="Project Name")]
 
-class ValidationErrorJudgmentType(BaseModel):
-    loc: Annotated[List[Union[str, int]], Field(title="Location")]
-    msg: Annotated[str, Field(title="Message")]
-    type: Annotated[str, Field(title="Error Type")]
 
+class DatasetFetch(BaseModel):
+    dataset_alias: Annotated[str, Field(title="Dataset Alias")]
+    project_name: Annotated[str, Field(title="Project Name")]
 
-class ScorerDataJudgmentType(BaseModel):
+
+class TraceSave(BaseModel):
+    project_name: Annotated[str, Field(title="Project Name")]
+    trace_id: Annotated[str, Field(title="Trace Id")]
     name: Annotated[str, Field(title="Name")]
+    created_at: Annotated[str, Field(title="Created At")]
+    duration: Annotated[float, Field(title="Duration")]
+    offline_mode: Annotated[Optional[bool], Field(title="Offline Mode")] = False
+    has_notification: Annotated[Optional[bool], Field(title="Has Notification")] = False
+    customer_id: Annotated[Optional[str], Field(title="Customer Id")] = None
+    tags: Annotated[Optional[List[str]], Field(title="Tags")] = None
+    metadata: Annotated[Optional[Dict[str, Any]], Field(title="Metadata")] = None
+    update_id: Annotated[Optional[int], Field(title="Update Id")] = 1
+
+
+class TraceFetch(BaseModel):
+    trace_id: Annotated[str, Field(title="Trace Id")]
+
+
+class TraceAddToDataset(BaseModel):
+    trace_id: Annotated[str, Field(title="Trace Id")]
+    trace_span_id: Annotated[str, Field(title="Trace Span Id")]
+    dataset_alias: Annotated[str, Field(title="Dataset Alias")]
+    project_name: Annotated[str, Field(title="Project Name")]
+
+
+class EvaluationRunsBatchRequest(BaseModel):
+    organization_id: Annotated[str, Field(title="Organization Id")]
+    evaluation_entries: Annotated[
+        List[Dict[str, Any]], Field(title="Evaluation Entries")
+    ]
+
+
+class ProjectAdd(BaseModel):
+    project_name: Annotated[str, Field(title="Project Name")]
+
+
+class ProjectAddResponse(BaseModel):
+    project_id: Annotated[str, Field(title="Project Id")]
+
+
+class ProjectDeleteFromJudgevalResponse(BaseModel):
+    project_name: Annotated[str, Field(title="Project Name")]
+
+
+class ProjectDeleteResponse(BaseModel):
+    message: Annotated[str, Field(title="Message")]
+
+
+class ScorerExistsRequest(BaseModel):
+    name: Annotated[str, Field(title="Name")]
+
+
+class ScorerExistsResponse(BaseModel):
+    exists: Annotated[bool, Field(title="Exists")]
+
+
+class SavePromptScorerRequest(BaseModel):
+    name: Annotated[str, Field(title="Name")]
+    prompt: Annotated[str, Field(title="Prompt")]
     threshold: Annotated[float, Field(title="Threshold")]
-    success: Annotated[bool, Field(title="Success")]
-    score: Annotated[Optional[float], Field(title="Score")] = None
-    reason: Annotated[Optional[str], Field(title="Reason")] = None
-    strict_mode: Annotated[Optional[bool], Field(title="Strict Mode")] = None
-    evaluation_model: Annotated[
-        Optional[Union[List[str], str]], Field(title="Evaluation Model")
-    ] = None
-    error: Annotated[Optional[str], Field(title="Error")] = None
-    additional_metadata: Annotated[
-        Optional[Dict[str, Any]], Field(title="Additional Metadata")
-    ] = None
+    options: Annotated[Optional[Dict[str, float]], Field(title="Options")] = None
+    is_trace: Annotated[Optional[bool], Field(title="Is Trace")] = False
 
 
-class ExampleJudgmentType(BaseModel):
-    model_config = ConfigDict(
-        extra="allow",
-    )
-    example_id: Annotated[str, Field(title="Example Id")]
-    created_at: Annotated[str, Field(title="Created At")]
-    name: Annotated[Optional[str], Field(title="Name")] = None
+class SavePromptScorerResponse(BaseModel):
+    message: Annotated[str, Field(title="Message")]
+    name: Annotated[str, Field(title="Name")]
 
 
-class ScorerConfigJudgmentType(BaseModel):
-    score_type: Annotated[str, Field(title="Score Type")]
-    name: Annotated[Optional[str], Field(title="Name")] = None
-    threshold: Annotated[Optional[float], Field(title="Threshold")] = 0.5
-    strict_mode: Annotated[Optional[bool], Field(title="Strict Mode")] = False
-    required_params: Annotated[Optional[List[str]], Field(title="Required Params")] = (
-        Field(default_factory=list)
-    )
-    kwargs: Annotated[Optional[Dict[str, Any]], Field(title="Kwargs")] = None
+class FetchPromptScorerRequest(BaseModel):
+    name: Annotated[str, Field(title="Name")]
+
+
+class CustomScorerUploadPayload(BaseModel):
+    scorer_name: Annotated[str, Field(title="Scorer Name")]
+    scorer_code: Annotated[str, Field(title="Scorer Code")]
+    requirements_text: Annotated[str, Field(title="Requirements Text")]
+
 
+class CustomScorerTemplateResponse(BaseModel):
+    scorer_name: Annotated[str, Field(title="Scorer Name")]
+    status: Annotated[str, Field(title="Status")]
+    message: Annotated[str, Field(title="Message")]
 
-class BaseScorerJudgmentType(BaseModel):
+
+class ResolveProjectNameRequest(BaseModel):
+    project_name: Annotated[str, Field(title="Project Name")]
+
+
+class ResolveProjectNameResponse(BaseModel):
+    project_id: Annotated[str, Field(title="Project Id")]
+
+
+class TraceIdRequest(BaseModel):
+    trace_id: Annotated[str, Field(title="Trace Id")]
+
+
+class SpanScoreRequest(BaseModel):
+    span_id: Annotated[str, Field(title="Span Id")]
+    trace_id: Annotated[str, Field(title="Trace Id")]
+
+
+class BaseScorer(BaseModel):
     score_type: Annotated[str, Field(title="Score Type")]
     threshold: Annotated[Optional[float], Field(title="Threshold")] = 0.5
     name: Annotated[Optional[str], Field(title="Name")] = None
@@ -76,7 +148,87 @@ class BaseScorerJudgmentType(BaseModel):
     server_hosted: Annotated[Optional[bool], Field(title="Server Hosted")] = False
 
 
-class TraceUsageJudgmentType(BaseModel):
+class ScorerConfig(BaseModel):
+    score_type: Annotated[str, Field(title="Score Type")]
+    name: Annotated[Optional[str], Field(title="Name")] = None
+    threshold: Annotated[Optional[float], Field(title="Threshold")] = 0.5
+    strict_mode: Annotated[Optional[bool], Field(title="Strict Mode")] = False
+    required_params: Annotated[Optional[List[str]], Field(title="Required Params")] = []
+    kwargs: Annotated[Optional[Dict[str, Any]], Field(title="Kwargs")] = None
+
+
+class Example(BaseModel):
+    model_config = ConfigDict(
+        extra="allow",
+    )
+    example_id: Annotated[str, Field(title="Example Id")]
+    created_at: Annotated[str, Field(title="Created At")]
+    name: Annotated[Optional[str], Field(title="Name")] = None
+
+
+class ValidationError(BaseModel):
+    loc: Annotated[List[Union[str, int]], Field(title="Location")]
+    msg: Annotated[str, Field(title="Message")]
+    type: Annotated[str, Field(title="Error Type")]
+
+
+class SpanBatchItem(BaseModel):
+    span_id: Annotated[str, Field(title="Span Id")]
+    trace_id: Annotated[str, Field(title="Trace Id")]
+    function: Annotated[str, Field(title="Function")]
+    created_at: Annotated[Any, Field(title="Created At")] = None
+    parent_span_id: Annotated[Optional[str], Field(title="Parent Span Id")] = None
+    span_type: Annotated[Optional[str], Field(title="Span Type")] = "span"
+    inputs: Annotated[Optional[Dict[str, Any]], Field(title="Inputs")] = None
+    output: Annotated[Any, Field(title="Output")] = None
+    error: Annotated[Optional[Dict[str, Any]], Field(title="Error")] = None
+    usage: Annotated[Optional[Dict[str, Any]], Field(title="Usage")] = None
+    duration: Annotated[Optional[float], Field(title="Duration")] = None
+    expected_tools: Annotated[
+        Optional[List[Dict[str, Any]]], Field(title="Expected Tools")
+    ] = None
+    additional_metadata: Annotated[
+        Optional[Dict[str, Any]], Field(title="Additional Metadata")
+    ] = None
+    has_evaluation: Annotated[Optional[bool], Field(title="Has Evaluation")] = False
+    agent_name: Annotated[Optional[str], Field(title="Agent Name")] = None
+    class_name: Annotated[Optional[str], Field(title="Class Name")] = None
+    state_before: Annotated[Optional[Dict[str, Any]], Field(title="State Before")] = (
+        None
+    )
+    state_after: Annotated[Optional[Dict[str, Any]], Field(title="State After")] = None
+    span_state: Annotated[str, Field(title="Span State")]
+    update_id: Annotated[Optional[int], Field(title="Update Id")] = 1
+    queued_at: Annotated[float, Field(title="Queued At")]
+
+
+class PromptScorer(BaseModel):
+    name: Annotated[str, Field(title="Name")]
+    prompt: Annotated[str, Field(title="Prompt")]
+    threshold: Annotated[float, Field(title="Threshold")]
+    options: Annotated[Optional[Dict[str, float]], Field(title="Options")] = None
+    created_at: Annotated[Optional[AwareDatetime], Field(title="Created At")] = None
+    updated_at: Annotated[Optional[AwareDatetime], Field(title="Updated At")] = None
+    is_trace: Annotated[Optional[bool], Field(title="Is Trace")] = False
+
+
+class ScorerData(BaseModel):
+    name: Annotated[str, Field(title="Name")]
+    threshold: Annotated[float, Field(title="Threshold")]
+    success: Annotated[bool, Field(title="Success")]
+    score: Annotated[Optional[float], Field(title="Score")] = None
+    reason: Annotated[Optional[str], Field(title="Reason")] = None
+    strict_mode: Annotated[Optional[bool], Field(title="Strict Mode")] = None
+    evaluation_model: Annotated[
+        Optional[Union[List[str], str]], Field(title="Evaluation Model")
+    ] = None
+    error: Annotated[Optional[str], Field(title="Error")] = None
+    additional_metadata: Annotated[
+        Optional[Dict[str, Any]], Field(title="Additional Metadata")
+    ] = None
+
+
+class TraceUsage(BaseModel):
     prompt_tokens: Annotated[Optional[int], Field(title="Prompt Tokens")] = None
     completion_tokens: Annotated[Optional[int], Field(title="Completion Tokens")] = None
     cache_creation_input_tokens: Annotated[
@@ -96,7 +248,7 @@ class TraceUsageJudgmentType(BaseModel):
     model_name: Annotated[Optional[str], Field(title="Model Name")] = None
 
 
-class ToolJudgmentType(BaseModel):
+class Tool(BaseModel):
     tool_name: Annotated[str, Field(title="Tool Name")]
     parameters: Annotated[Optional[Dict[str, Any]], Field(title="Parameters")] = None
     agent_name: Annotated[Optional[str], Field(title="Agent Name")] = None
@@ -109,45 +261,75 @@ class ToolJudgmentType(BaseModel):
     require_all: Annotated[Optional[bool], Field(title="Require All")] = None
 
 
-class HTTPValidationErrorJudgmentType(BaseModel):
-    detail: Annotated[
-        Optional[List[ValidationErrorJudgmentType]], Field(title="Detail")
-    ] = None
-
-
-class EvaluationRunJudgmentType(BaseModel):
+class ExampleEvaluationRun(BaseModel):
     id: Annotated[Optional[str], Field(title="Id")] = None
     project_name: Annotated[Optional[str], Field(title="Project Name")] = None
     eval_name: Annotated[Optional[str], Field(title="Eval Name")] = None
-    examples: Annotated[List[ExampleJudgmentType], Field(title="Examples")]
     custom_scorers: Annotated[
-        Optional[List[BaseScorerJudgmentType]], Field(title="Custom Scorers")
-    ] = Field(default_factory=list)
+        Optional[List[BaseScorer]], Field(title="Custom Scorers")
+    ] = []
     judgment_scorers: Annotated[
-        Optional[List[ScorerConfigJudgmentType]], Field(title="Judgment Scorers")
-    ] = Field(default_factory=list)
+        Optional[List[ScorerConfig]], Field(title="Judgment Scorers")
+    ] = []
     model: Annotated[str, Field(title="Model")]
+    created_at: Annotated[Optional[str], Field(title="Created At")] = None
+    examples: Annotated[List[Example], Field(title="Examples")]
     trace_span_id: Annotated[Optional[str], Field(title="Trace Span Id")] = None
     trace_id: Annotated[Optional[str], Field(title="Trace Id")] = None
+
+
+class HTTPValidationError(BaseModel):
+    detail: Annotated[Optional[List[ValidationError]], Field(title="Detail")] = None
+
+
+class TraceEvaluationRun(BaseModel):
+    id: Annotated[Optional[str], Field(title="Id")] = None
+    project_name: Annotated[Optional[str], Field(title="Project Name")] = None
+    eval_name: Annotated[Optional[str], Field(title="Eval Name")] = None
+    custom_scorers: Annotated[
+        Optional[List[BaseScorer]], Field(title="Custom Scorers")
+    ] = []
+    judgment_scorers: Annotated[
+        Optional[List[ScorerConfig]], Field(title="Judgment Scorers")
+    ] = []
+    model: Annotated[str, Field(title="Model")]
     created_at: Annotated[Optional[str], Field(title="Created At")] = None
+    trace_and_span_ids: Annotated[
+        List[TraceAndSpanId], Field(title="Trace And Span Ids")
+    ]
+    is_offline: Annotated[Optional[bool], Field(title="Is Offline")] = False
+
+
+class DatasetInsertExamples(BaseModel):
+    dataset_alias: Annotated[str, Field(title="Dataset Alias")]
+    examples: Annotated[List[Example], Field(title="Examples")]
+    project_name: Annotated[str, Field(title="Project Name")]
+
 
+class SpansBatchRequest(BaseModel):
+    spans: Annotated[List[SpanBatchItem], Field(title="Spans")]
+    organization_id: Annotated[str, Field(title="Organization Id")]
 
-class TraceSpanJudgmentType(BaseModel):
+
+class FetchPromptScorerResponse(BaseModel):
+    scorer: PromptScorer
+
+
+class TraceSpan(BaseModel):
     span_id: Annotated[str, Field(title="Span Id")]
     trace_id: Annotated[str, Field(title="Trace Id")]
     function: Annotated[str, Field(title="Function")]
-    depth: Annotated[int, Field(title="Depth")]
     created_at: Annotated[Any, Field(title="Created At")] = None
     parent_span_id: Annotated[Optional[str], Field(title="Parent Span Id")] = None
     span_type: Annotated[Optional[str], Field(title="Span Type")] = "span"
     inputs: Annotated[Optional[Dict[str, Any]], Field(title="Inputs")] = None
     error: Annotated[Optional[Dict[str, Any]], Field(title="Error")] = None
     output: Annotated[Any, Field(title="Output")] = None
-    usage: Optional[TraceUsageJudgmentType] = None
+    usage: Optional[TraceUsage] = None
     duration: Annotated[Optional[float], Field(title="Duration")] = None
-    expected_tools: Annotated[
-        Optional[List[ToolJudgmentType]], Field(title="Expected Tools")
-    ] = None
+    expected_tools: Annotated[Optional[List[Tool]], Field(title="Expected Tools")] = (
+        None
+    )
     additional_metadata: Annotated[
         Optional[Dict[str, Any]], Field(title="Additional Metadata")
     ] = None
@@ -161,54 +343,56 @@ class TraceSpanJudgmentType(BaseModel):
     update_id: Annotated[Optional[int], Field(title="Update Id")] = 1
 
 
-class TraceJudgmentType(BaseModel):
+class Trace(BaseModel):
     trace_id: Annotated[str, Field(title="Trace Id")]
     name: Annotated[str, Field(title="Name")]
     created_at: Annotated[str, Field(title="Created At")]
     duration: Annotated[float, Field(title="Duration")]
-    trace_spans: Annotated[List[TraceSpanJudgmentType], Field(title="Trace Spans")]
+    trace_spans: Annotated[List[TraceSpan], Field(title="Trace Spans")]
     offline_mode: Annotated[Optional[bool], Field(title="Offline Mode")] = False
-    rules: Annotated[Optional[Dict[str, Any]], Field(title="Rules")] = Field(
-        default_factory=dict
-    )
+    rules: Annotated[Optional[Dict[str, Any]], Field(title="Rules")] = {}
     has_notification: Annotated[Optional[bool], Field(title="Has Notification")] = False
     customer_id: Annotated[Optional[str], Field(title="Customer Id")] = None
-    tags: Annotated[Optional[List[str]], Field(title="Tags")] = Field(
-        default_factory=list
-    )
-    metadata: Annotated[Optional[Dict[str, Any]], Field(title="Metadata")] = Field(
-        default_factory=dict
-    )
+    tags: Annotated[Optional[List[str]], Field(title="Tags")] = []
+    metadata: Annotated[Optional[Dict[str, Any]], Field(title="Metadata")] = {}
     update_id: Annotated[Optional[int], Field(title="Update Id")] = 1
 
 
-class ScoringResultJudgmentType(BaseModel):
+class ScoringResult(BaseModel):
     success: Annotated[bool, Field(title="Success")]
-    scorers_data: Annotated[
-        Optional[List[ScorerDataJudgmentType]], Field(title="Scorers Data")
-    ] = None
+    scorers_data: Annotated[Optional[List[ScorerData]], Field(title="Scorers Data")] = (
+        None
+    )
     name: Annotated[Optional[str], Field(title="Name")] = None
     data_object: Annotated[
-        Optional[Union[TraceSpanJudgmentType, ExampleJudgmentType]],
-        Field(title="Data Object"),
+        Optional[Union[TraceSpan, Example]], Field(title="Data Object")
     ] = None
     trace_id: Annotated[Optional[str], Field(title="Trace Id")] = None
     run_duration: Annotated[Optional[float], Field(title="Run Duration")] = None
     evaluation_cost: Annotated[Optional[float], Field(title="Evaluation Cost")] = None
 
 
-class TraceRunJudgmentType(BaseModel):
+class TraceRun(BaseModel):
     project_name: Annotated[Optional[str], Field(title="Project Name")] = None
     eval_name: Annotated[Optional[str], Field(title="Eval Name")] = None
-    traces: Annotated[List[TraceJudgmentType], Field(title="Traces")]
-    scorers: Annotated[List[ScorerConfigJudgmentType], Field(title="Scorers")]
+    traces: Annotated[List[Trace], Field(title="Traces")]
+    scorers: Annotated[List[ScorerConfig], Field(title="Scorers")]
     model: Annotated[str, Field(title="Model")]
     trace_span_id: Annotated[Optional[str], Field(title="Trace Span Id")] = None
     tools: Annotated[Optional[List[Dict[str, Any]]], Field(title="Tools")] = None
 
 
-class EvalResultsJudgmentType(BaseModel):
-    results: Annotated[List[ScoringResultJudgmentType], Field(title="Results")]
-    run: Annotated[
-        Union[TraceRunJudgmentType, EvaluationRunJudgmentType], Field(title="Run")
-    ]
+class EvalResults(BaseModel):
+    results: Annotated[List[ScoringResult], Field(title="Results")]
+    run: Annotated[Union[ExampleEvaluationRun, TraceEvaluationRun], Field(title="Run")]
+
+
+class DatasetPush(BaseModel):
+    dataset_alias: Annotated[str, Field(title="Dataset Alias")]
+    comments: Annotated[Optional[str], Field(title="Comments")] = None
+    source_file: Annotated[Optional[str], Field(title="Source File")] = None
+    examples: Annotated[Optional[List[Example]], Field(title="Examples")] = None
+    traces: Annotated[Optional[List[Trace]], Field(title="Traces")] = None
+    is_trace: Annotated[Optional[bool], Field(title="Is Trace")] = False
+    project_name: Annotated[str, Field(title="Project Name")]
+    overwrite: Annotated[Optional[bool], Field(title="Overwrite")] = False

judgeval/data/result.py

@@ -1,10 +1,10 @@
 from typing import List, Union
 from judgeval.data import ScorerData, Example
 from judgeval.data.trace import TraceSpan
-from judgeval.data.judgment_types import ScoringResultJudgmentType
+from judgeval.data.judgment_types import ScoringResult as JudgmentScoringResult
 
 
-class ScoringResult(ScoringResultJudgmentType):
+class ScoringResult(JudgmentScoringResult):
     """
     A ScoringResult contains the output of one or more scorers applied to a single example.
     Ie: One input, one actual_output, one expected_output, etc..., and 1+ scorer (Faithfulness, Hallucination, Summarization, etc...)
@@ -17,9 +17,8 @@ class ScoringResult(ScoringResultJudgmentType):
 
     """
 
-    data_object: (
-        Example  # Need to override this so that it uses this repo's Example class
-    )
+    # Need to override this so that it uses this repo's Example class
+    data_object: Example
 
     def model_dump(self, **kwargs):
         data = super().model_dump(**kwargs)

judgeval/data/scorer_data.py

@@ -4,12 +4,14 @@ Implementation of the ScorerData class.
 ScorerData holds the information related to a single, completed Scorer evaluation run.
 """
 
-from judgeval.data.judgment_types import ScorerDataJudgmentType
+from __future__ import annotations
+
+from judgeval.data.judgment_types import ScorerData as JudgmentScorerData
 from judgeval.scorers import BaseScorer
 from typing import List
 
 
-class ScorerData(ScorerDataJudgmentType):
+class ScorerData(JudgmentScorerData):
     """
     ScorerData holds the information related to a single, completed Scorer evaluation run.
 

judgeval/data/tool.py

@@ -1,5 +1,5 @@
-from judgeval.data.judgment_types import ToolJudgmentType
+from judgeval.data.judgment_types import Tool as JudgmentTool
 
 
-class Tool(ToolJudgmentType):
+class Tool(JudgmentTool):
     pass

judgeval/data/trace.py

@@ -1,24 +1,21 @@
-import threading
 from datetime import datetime, timezone
 from judgeval.data.judgment_types import (
-    TraceUsageJudgmentType,
-    TraceSpanJudgmentType,
-    TraceJudgmentType,
+    TraceUsage as JudgmentTraceUsage,
+    TraceSpan as JudgmentTraceSpan,
+    Trace as JudgmentTrace,
 )
-from judgeval.constants import SPAN_LIFECYCLE_END_UPDATE_ID
-from judgeval.common.api.json_encoder import json_encoder
+from judgeval.utils.serialize import json_encoder
 
 
-class TraceUsage(TraceUsageJudgmentType):
+class TraceUsage(JudgmentTraceUsage):
     pass
 
 
-class TraceSpan(TraceSpanJudgmentType):
+class TraceSpan(JudgmentTraceSpan):
     def model_dump(self, **kwargs):
         return {
             "span_id": self.span_id,
             "trace_id": self.trace_id,
-            "depth": self.depth,
             "created_at": datetime.fromtimestamp(
                 self.created_at, tz=timezone.utc
             ).isoformat(),
@@ -32,52 +29,12 @@ class TraceSpan(TraceSpanJudgmentType):
             "usage": self.usage.model_dump() if self.usage else None,
             "has_evaluation": self.has_evaluation,
             "agent_name": self.agent_name,
-            "class_name": self.class_name,
             "state_before": self.state_before,
             "state_after": self.state_after,
             "additional_metadata": json_encoder(self.additional_metadata),
             "update_id": self.update_id,
         }
 
-    def __init__(self, **data):
-        super().__init__(**data)
-        # Initialize thread lock for thread-safe update_id increment
-        self._update_id_lock = threading.Lock()
 
-    def increment_update_id(self) -> int:
-        """
-        Thread-safe method to increment the update_id counter.
-        Returns:
-            int: The new update_id value after incrementing
-        """
-        with self._update_id_lock:
-            self.update_id += 1
-            return self.update_id
-
-    def set_update_id_to_ending_number(
-        self, ending_number: int = SPAN_LIFECYCLE_END_UPDATE_ID
-    ) -> int:
-        """
-        Thread-safe method to set the update_id to a predetermined ending number.
-
-        Args:
-            ending_number (int): The number to set update_id to. Defaults to SPAN_LIFECYCLE_END_UPDATE_ID.
-
-        Returns:
-            int: The new update_id value after setting
-        """
-        with self._update_id_lock:
-            self.update_id = ending_number
-            return self.update_id
-
-    def print_span(self):
-        """Print the span with proper formatting and parent relationship information."""
-        indent = "  " * self.depth
-        parent_info = (
-            f" (parent_id: {self.parent_span_id})" if self.parent_span_id else ""
-        )
-        print(f"{indent}→ {self.function} (id: {self.span_id}){parent_info}")
-
-
-class Trace(TraceJudgmentType):
+class Trace(JudgmentTrace):
     pass

judgeval/data/trace_run.py

@@ -2,8 +2,7 @@ from pydantic import BaseModel
 from typing import List, Optional, Dict, Any, Union
 from judgeval.data import Trace
 from judgeval.scorers import APIScorerConfig, BaseScorer
-from judgeval.rules import Rule
-from judgeval.constants import DEFAULT_GPT_MODEL
+from judgeval.env import JUDGMENT_DEFAULT_GPT_MODEL
 
 
 class TraceRun(BaseModel):
@@ -27,9 +26,13 @@ class TraceRun(BaseModel):
     eval_name: Optional[str] = None
     traces: Optional[List[Trace]] = None
     scorers: List[Union[APIScorerConfig, BaseScorer]]
-    model: Optional[str] = DEFAULT_GPT_MODEL
+    model: Optional[str] = JUDGMENT_DEFAULT_GPT_MODEL
     trace_span_id: Optional[str] = None
-    rules: Optional[List[Rule]] = None
+    append: Optional[bool] = False
+    override: Optional[bool] = False
+
+    # TODO: ?
+    rules: Any = None
     tools: Optional[List[Dict[str, Any]]] = None
 
     class Config: