Add retained chat and API request diagnostics

backend/app/models/models.py

@@ -4,7 +4,7 @@ from decimal import Decimal
 from typing import Annotated, Optional
 
 from pydantic import PlainSerializer
-from sqlalchemy import JSON, Column, UniqueConstraint
+from sqlalchemy import JSON, Column, Text, UniqueConstraint
 from sqlalchemy.dialects.postgresql import JSONB
 from sqlmodel import Field, Relationship, SQLModel
 
@@ -566,3 +566,35 @@ class ChatThreadSnapshot(SQLModel, table=True):
         default=None, sa_column=Column(JSON_OR_JSONB, nullable=True)
     )
     updated_at: datetime = Field(default_factory=utcnow)
+
+
+# --- Assistant Chat Run Audit ---
+
+
+class ChatRunLog(SQLModel, table=True):
+    """Append-only diagnostic record for an AG-UI agent/run request.
+
+    Thread snapshots are mutable conversation state. This table instead keeps
+    the request, model, tool activity, and final emitted answer for a bounded
+    retention period so individual assistant runs can be investigated later.
+    """
+
+    id: Optional[int] = Field(default=None, primary_key=True)
+    request_id: str = Field(index=True, unique=True)
+    agui_run_id: Optional[str] = Field(default=None, index=True)
+    requested_thread_id: Optional[str] = Field(default=None, index=True)
+    response_thread_id: Optional[str] = Field(default=None, index=True)
+    model: str
+    user_prompt: Optional[str] = Field(default=None, sa_column=Column(Text, nullable=True))
+    tool_calls: list = Field(
+        default_factory=list,
+        sa_column=Column(JSON_OR_JSONB, nullable=False, server_default="[]"),
+    )
+    assistant_response: Optional[str] = Field(
+        default=None, sa_column=Column(Text, nullable=True)
+    )
+    status: str = Field(default="started", index=True)
+    error: Optional[str] = Field(default=None, sa_column=Column(Text, nullable=True))
+    started_at: datetime = Field(default_factory=utcnow)
+    completed_at: Optional[datetime] = Field(default=None)
+    expires_at: datetime = Field(index=True)