feat: release 2.4.0 with original cases and automatic human review

apps/admin_console/database/repositories/session_repository.py

@@ -15,6 +15,7 @@
 import json
 import logging
 import os
+import re
 import sqlite3
 import time
 from typing import Any
@@ -235,6 +236,47 @@ class SessionRepository:
             rows = cursor.fetchall()
             return [r[0] for r in rows if r and r[0]]
 
+    def get_recorded_model_info_map(self, session_ids: list[str]) -> dict[str, dict[str, str]]:
+        """Read each session's own requested model from its earliest diagnostics.
+
+        Prefer operator/Flash requests over auxiliary roles. Older sessions may
+        have no model diagnostics; do not replace their missing data with the
+        current global configuration.
+        """
+        result: dict[str, dict[str, str]] = {}
+        safe_payload = "CASE WHEN json_valid(t.payload) THEN t.payload ELSE '{}' END"
+        valid_model = f"json_type({safe_payload}, '$.model') = 'text'"
+        role = f"lower(json_extract({safe_payload}, '$.role'))"
+        with db_session(self.db_path) as conn:
+            for offset in range(0, len(session_ids), 500):
+                batch = session_ids[offset : offset + 500]
+                placeholders = ",".join("?" for _ in batch)
+                rows = conn.execute(
+                    "SELECT s.session_id, COALESCE("
+                    " (SELECT t.payload FROM traces t WHERE t.session_id = s.session_id"
+                    f" AND t.type = 'llm_diagnostic' AND {valid_model}"
+                    f" AND {role} IN ('operator', 'flashrunner')"
+                    " ORDER BY t.timestamp ASC LIMIT 1),"
+                    " (SELECT t.payload FROM traces t WHERE t.session_id = s.session_id"
+                    f" AND t.type = 'llm_diagnostic' AND {valid_model}"
+                    " ORDER BY t.timestamp ASC LIMIT 1)"
+                    ") AS model_payload FROM sessions s"
+                    f" WHERE s.session_id IN ({placeholders})",
+                    batch,
+                ).fetchall()
+                for row in rows:
+                    if not row[1]:
+                        continue
+                    payload = json.loads(row[1])
+                    model = payload.get("model")
+                    if isinstance(model, str) and model.strip():
+                        provider = payload.get("provider")
+                        result[str(row[0])] = {
+                            "id": model,
+                            "provider": provider if isinstance(provider, str) else "",
+                        }
+        return result
+
     def get_llm_traces_for_profiles_map(
         self, session_ids: list[str] | None = None, limit: int = 3
     ) -> dict[str, list[str]]:
@@ -349,7 +391,22 @@ class SessionRepository:
                 total += t
                 cached += _int(payload.get("cached_tokens"))
                 node = str(payload.get("node") or "").strip().lower()
-                model_name = str(payload.get("model") or "unknown")
+                model_name = payload.get("model")
+                if not model_name:
+                    # Older gateway traces carry the model in their own endpoint key.
+                    source = str(payload.get("source") or "")
+                    source_parts = source.split(":", 2)
+                    if len(source_parts) == 3 and source_parts[0] == "openai":
+                        # Model aliases can contain colons. The HTTP(S) base URL
+                        # marks the boundary; an ambiguous key stays unknown.
+                        match = re.match(r"^openai:(.+?):https?://", source)
+                        model_name = match[1] if match else None
+                    elif len(source_parts) == 3 and source_parts[:2] in (
+                        ["lens", "visual_transition"],
+                        ["lens", "step_capsule"],
+                    ):
+                        model_name = source_parts[2] if source_parts[2] != "fallback" else None
+                model_name = str(model_name or "unknown")
                 group = by_node_model.setdefault(
                     (node, model_name),
                     {

apps/admin_console/database/repositories/step_repository.py

@@ -220,6 +220,41 @@ class StepRepository:
         # recovering, waiting, completed, and terminal outcomes. Other tools
         # retain the historical compact payload to avoid sending large blobs.
         res = payload_obj.get("result")
+        if trace_type == "tool" and trace_name == "android_file":
+            # Preserve host-written file receipts, not file contents. A file's
+            # checksum is not a screenshot-store image ID.
+            if isinstance(res, str):
+                try:
+                    res = json.loads(res)
+                except ValueError:
+                    res = None
+            if isinstance(res, dict) and "outcome" in res:
+                res = res["outcome"]
+                if isinstance(res, str):
+                    try:
+                        res = json.loads(res)
+                    except ValueError:
+                        res = None
+            if isinstance(res, dict):
+                result_payload["result"] = {
+                    key: self._clean_value(res[key])
+                    for key in (
+                        "ok",
+                        "action",
+                        "path",
+                        "trace_path",
+                        "device_path",
+                        "bytes",
+                        "sha256",
+                        "verified",
+                        "width",
+                        "height",
+                        "captured_at",
+                        "device_serial",
+                    )
+                    if key in res
+                }
+            return result_payload
         is_video_analysis = str(trace_name or "").lower() in {
             "video_analysis",
             "video_analyzer",