feat(advisor-comparison): add AdvisorComparison models and ReportData field

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>

tests/test_advisor_comparison_models.py

@@ -0,0 +1,50 @@
+"""Tests for the AdvisorComparison Pydantic models and their default wiring."""
+from __future__ import annotations
+
+from webapp.models import AdvisorComparison, AdvisorComparisonEntry, ReportData
+
+
+def test_advisor_comparison_entry_accepts_all_statuses():
+    for status in ("resolved", "regressed", "still_triggered", "new_metric"):
+        entry = AdvisorComparisonEntry(
+            metric="faithfulness",
+            status=status,
+            previous_score=0.5,
+            previous_severity="warning",
+            current_score=0.9,
+            current_severity=None,
+        )
+        assert entry.status == status
+
+
+def test_advisor_comparison_entry_rejects_unknown_status():
+    import pydantic
+
+    try:
+        AdvisorComparisonEntry(metric="faithfulness", status="unknown_status")
+        raised = False
+    except pydantic.ValidationError:
+        raised = True
+    assert raised
+
+
+def test_advisor_comparison_defaults():
+    comparison = AdvisorComparison(
+        previous_run_id="run-1",
+        previous_finished_at="2026-01-01T00:00:00+00:00",
+    )
+    assert comparison.previous_judge_model == ""
+    assert comparison.current_judge_model == ""
+    assert comparison.judge_model_changed is False
+    assert comparison.entries == []
+
+
+def test_report_data_defaults_advisor_comparison_to_none():
+    report = ReportData()
+    assert report.advisor_comparison is None
+
+
+def test_report_data_accepts_advisor_comparison():
+    comparison = AdvisorComparison(previous_run_id="run-1", previous_finished_at="t")
+    report = ReportData(advisor_comparison=comparison)
+    assert report.advisor_comparison == comparison

webapp/models.py

@@ -3,7 +3,7 @@
 from __future__ import annotations
 
 from datetime import datetime, timezone
-from typing import Any
+from typing import Any, Literal
 
 from pydantic import BaseModel, ConfigDict, Field, field_validator
 
@@ -77,6 +77,28 @@ class SampleScore(BaseModel):
     )
 
 
+class AdvisorComparisonEntry(BaseModel):
+    """One metric's diagnosis delta between the current run and its predecessor."""
+
+    metric: str
+    status: Literal["resolved", "regressed", "still_triggered", "new_metric"]
+    previous_score: float | None = None
+    previous_severity: str | None = None
+    current_score: float | None = None
+    current_severity: str | None = None
+
+
+class AdvisorComparison(BaseModel):
+    """Advisor-diagnosis comparison against the same scenario's previous run."""
+
+    previous_run_id: str
+    previous_finished_at: str
+    previous_judge_model: str = ""
+    current_judge_model: str = ""
+    judge_model_changed: bool = False
+    entries: list[AdvisorComparisonEntry] = Field(default_factory=list)
+
+
 class ReportData(BaseModel):
     """Aggregated report payload rendered by the report detail page."""
 
@@ -103,6 +125,10 @@ class ReportData(BaseModel):
         default_factory=dict,
         description="按模型累计的 token 用量：{model: {input_tokens, output_tokens, calls}}。",
     )
+    advisor_comparison: AdvisorComparison | None = Field(
+        default=None,
+        description="相比同场景上一次运行的顾问诊断差异；无可比对象时为 None。",
+    )
 
 
 class RunDetail(BaseModel):