applied-cli 0.5.64__tar.gz → 0.5.66__tar.gz

{applied_cli-0.5.64 → applied_cli-0.5.66}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: applied-cli
-Version: 0.5.64
+Version: 0.5.66
 Summary: CLI and shared client library for Applied Labs AI support agents
 Author: Applied Labs
 License-Expression: MIT

{applied_cli-0.5.64 → applied_cli-0.5.66}/applied_cli/cli.py

@@ -1310,6 +1310,9 @@ def scenario_runs(
     benchmark_id: str = typer.Option(
         None, "--benchmark-id", help="Filter by benchmark ID"
     ),
+    bulk_job_id: str = typer.Option(
+        None, "--bulk-job-id", help="Filter by bulk run job ID"
+    ),
     latest: bool = typer.Option(
         True, "--latest/--all", help="Only show the latest run per scenario"
     ),
@@ -1325,6 +1328,7 @@ def scenario_runs(
             client,
             scenario_id=scenario_id,
             benchmark_id=benchmark_id,
+            bulk_job_id=bulk_job_id,
             latest=latest,
             output_format=format,
         )
@@ -1403,6 +1407,9 @@ def scenario_bulk_run(
 @app.command("scenario-bulk-status")
 def scenario_bulk_status(
     job_id: str = typer.Argument(..., help="Bulk run job ID"),
+    include_runs: bool = typer.Option(
+        False, "--include-runs", help="Include per-run details with scenario mappings"
+    ),
     shop_id: str = typer.Option(None, "--shop-id", help="Override shop ID"),
     format: str = typer.Option(
         "text", "--format", "-f", help="Output format: text or json"
@@ -1411,7 +1418,9 @@ def scenario_bulk_status(
     """Get status for a bulk scenario rerun job."""
     client = get_client(shop_id=shop_id)
     result = asyncio.run(
-        tools.scenario_bulk_status(client, job_id=job_id, output_format=format)
+        tools.scenario_bulk_status(
+            client, job_id=job_id, include_runs=include_runs, output_format=format
+        )
     )
     typer.echo(result)
 

{applied_cli-0.5.64 → applied_cli-0.5.66}/applied_cli/client.py

@@ -1850,6 +1850,7 @@ class AppliedClient:
         self,
         scenario_id: str | None = None,
         benchmark_id: str | None = None,
+        bulk_job_id: str | None = None,
         latest: bool = False,
         limit: int = 50,
     ) -> list[dict]:
@@ -1859,6 +1860,8 @@ class AppliedClient:
             params["scenario_id"] = scenario_id
         if benchmark_id:
             params["benchmark_id"] = benchmark_id
+        if bulk_job_id:
+            params["bulk_job_id"] = bulk_job_id
         if latest:
             params["latest"] = "true"
         data = await self._request("GET", "/v1/scenario-runs/", params=params)
@@ -1881,6 +1884,7 @@ class AppliedClient:
         scenario_ids: list[str] | None = None,
         benchmark_id: str | None = None,
         target_agent_id: str | None = None,
+        contact_override: dict | None = None,
     ) -> dict:
         """Run multiple scenarios at once.
 
@@ -1888,6 +1892,8 @@ class AppliedClient:
             scenario_ids: List of scenario UUIDs to run
             benchmark_id: Run all scenarios in this benchmark
             target_agent_id: Optional agent to run against (for A/B testing)
+            contact_override: Optional contact override dict, e.g.
+                {"mode": "contact", "contact_id": "<uuid>"}
         """
         body: dict[str, Any] = {}
         if scenario_ids:
@@ -1896,6 +1902,8 @@ class AppliedClient:
             body["benchmark_id"] = benchmark_id
         if target_agent_id:
             body["target_agent_id"] = target_agent_id
+        if contact_override:
+            body["contact_override"] = contact_override
         return await self._request("POST", "/v1/scenario-runs/bulk-run/", body=body)
 
     async def get_scenario_bulk_run_status(self, job_id: str) -> dict:

{applied_cli-0.5.64 → applied_cli-0.5.66}/applied_cli/tools.py

@@ -200,7 +200,15 @@ def _project_scenario_payload(
 
 
 def _project_scenario_run_payload(run: dict) -> dict:
-    scenario = run.get("scenario") or {}
+    # scenario can be a UUID string (PK) or a nested dict
+    scenario_raw = run.get("scenario")
+    if isinstance(scenario_raw, dict):
+        scenario_id = scenario_raw.get("id")
+        scenario_name = scenario_raw.get("name")
+    else:
+        scenario_id = scenario_raw
+        scenario_name = run.get("scenario_name")
+
     evaluated_by = run.get("evaluated_by") or {}
     return {
         "id": run.get("id"),
@@ -219,8 +227,8 @@ def _project_scenario_run_payload(run: dict) -> dict:
         "evaluated_by_id": evaluated_by.get("id"),
         "evaluated_by_name": evaluated_by.get("name"),
         "scenario": {
-            "id": scenario.get("id"),
-            "name": scenario.get("name"),
+            "id": scenario_id,
+            "name": scenario_name,
         },
         "output_conversation": _project_embedded_conversation(
             run.get("output_conversation")
@@ -4786,6 +4794,7 @@ async def scenario_run_list(
     client: AppliedClient,
     scenario_id: str | None = None,
     benchmark_id: str | None = None,
+    bulk_job_id: str | None = None,
     latest: bool = True,
     output_format: str = "csv",
 ) -> str:
@@ -4796,19 +4805,30 @@ async def scenario_run_list(
         client: Authenticated AppliedClient
         scenario_id: Optional - filter by scenario UUID
         benchmark_id: Optional - filter by benchmark UUID
+        bulk_job_id: Optional - filter by bulk run job UUID
         latest: If True, show only the most recent run per scenario (default True)
         output_format: 'csv' or 'json'
 
     Returns:
-        List of scenario runs with id, scenario_name, pass_status, csat_score
+        List of scenario runs with id, scenario_id, scenario_name, pass_status, output_conversation_id
     """
     runs = await client.list_scenario_runs(
-        scenario_id=scenario_id, benchmark_id=benchmark_id, latest=latest
+        scenario_id=scenario_id,
+        benchmark_id=benchmark_id,
+        bulk_job_id=bulk_job_id,
+        latest=latest,
     )
+    def _extract_scenario_fields(r: dict) -> tuple:
+        scenario_raw = r.get("scenario")
+        if isinstance(scenario_raw, dict):
+            return scenario_raw.get("id", ""), scenario_raw.get("name", "")
+        return scenario_raw or "", r.get("scenario_name", "")
+
     mapped = [
         {
             "id": r.get("id"),
-            "scenario_name": r.get("scenario", {}).get("name", ""),
+            "scenario_id": _extract_scenario_fields(r)[0],
+            "scenario_name": _extract_scenario_fields(r)[1],
             "status": r.get("status"),
             "pass_status": r.get("pass_status", "unrated"),
             "csat_score": r.get("csat_score"),
@@ -4825,6 +4845,7 @@ async def scenario_run_list(
             mapped,
             [
                 "id",
+                "scenario_id",
                 "scenario_name",
                 "status",
                 "pass_status",
@@ -4917,6 +4938,7 @@ async def scenario_bulk_run(
     scenario_ids: list[str] | None = None,
     benchmark_id: str | None = None,
     target_agent_id: str | None = None,
+    contact_override: dict | None = None,
     output_format: str = "text",
 ) -> str:
     """
@@ -4927,6 +4949,7 @@ async def scenario_bulk_run(
         scenario_ids: List of scenario UUIDs to run
         benchmark_id: Run all scenarios in this benchmark
         target_agent_id: Optional agent to run against (for A/B testing)
+        contact_override: Optional contact override, e.g. {"mode": "contact", "contact_id": "<uuid>"}
 
     Returns:
         Summary of runs created
@@ -4954,6 +4977,7 @@ async def scenario_bulk_run(
         result = await client.bulk_run_scenarios(
             scenario_ids=resolved_scenario_ids,
             target_agent_id=target_agent_id,
+            contact_override=contact_override,
         )
     except AppliedAPIError as e:
         return _format_error(e)
@@ -4987,12 +5011,14 @@ async def scenario_bulk_run(
         output += f"scenario_run_ids: {preview_ids}\n"
         if len(run_ids) > 10:
             output += f"more_runs: {len(run_ids) - 10}\n"
+    output += f"\nTip: use scenario_bulk_status(job_id, include_runs=True) or scenario_run_list(bulk_job_id=job_id) to get per-run details with scenario mappings."
     return output
 
 
 async def scenario_bulk_status(
     client: AppliedClient,
     job_id: str,
+    include_runs: bool = False,
     output_format: str = "text",
 ) -> str:
     """
@@ -5001,10 +5027,11 @@ async def scenario_bulk_status(
     Args:
         client: Authenticated AppliedClient
         job_id: The bulk run job UUID
+        include_runs: If True, include per-run details (scenario_id, output_conversation_id, status)
         output_format: 'text' (default) or 'json'
 
     Returns:
-        Counts, timing information, and failed run details
+        Counts, timing information, failed run details, and optionally per-run details
     """
     try:
         result = await client.get_scenario_bulk_run_status(job_id)
@@ -5012,7 +5039,10 @@ async def scenario_bulk_status(
         return _format_error(e)
 
     if output_format == "json":
-        return to_json(result)
+        payload = dict(result)
+        if not include_runs:
+            payload.pop("runs", None)
+        return to_json(payload)
 
     counts = result.get("counts") or {}
     output = "# Bulk Run Status\n"
@@ -5034,6 +5064,20 @@ async def scenario_bulk_status(
         output += f"\n# Failed Runs ({len(failed)})\n"
         output += to_json(failed)
 
+    runs_detail = result.get("runs") or []
+    if include_runs and runs_detail:
+        output += f"\n\n# Per-Run Details ({len(runs_detail)})\n"
+        output += to_csv(
+            runs_detail,
+            [
+                "id",
+                "scenario_id",
+                "status",
+                "pass_status",
+                "output_conversation_id",
+            ],
+        )
+
     return output
 
 

{applied_cli-0.5.64 → applied_cli-0.5.66}/applied_cli.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: applied-cli
-Version: 0.5.64
+Version: 0.5.66
 Summary: CLI and shared client library for Applied Labs AI support agents
 Author: Applied Labs
 License-Expression: MIT

{applied_cli-0.5.64 → applied_cli-0.5.66}/pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "applied-cli"
-version = "0.5.64"
+version = "0.5.66"
 description = "CLI and shared client library for Applied Labs AI support agents"
 readme = "README.md"
 requires-python = ">=3.11"

{applied_cli-0.5.64 → applied_cli-0.5.66}/tests/test_benchmark_scenario_tools.py

@@ -231,11 +231,13 @@ class FakeScenarioClient:
         scenario_ids=None,
         benchmark_id=None,
         target_agent_id=None,
+        contact_override=None,
     ):
         self.bulk_run_kwargs = {
             "scenario_ids": scenario_ids,
             "benchmark_id": benchmark_id,
             "target_agent_id": target_agent_id,
+            "contact_override": contact_override,
         }
         return {
             "job_id": "job-1",
@@ -351,6 +353,7 @@ async def test_scenario_bulk_run_resolves_ids_from_benchmark():
         "scenario_ids": ["scenario-1"],
         "benchmark_id": None,
         "target_agent_id": "agent-2",
+        "contact_override": None,
     }
     assert payload["benchmark_id"] == "bench-1"
     assert payload["scenario_run_ids"] == ["scenario-run-1"]