diff --git a/docs/notebooks/Llama_Stack_Agents_Monitoring.ipynb b/docs/notebooks/Llama_Stack_Agents_Monitoring.ipynb
new file mode 100644
index 000000000..aadac6b2b
--- /dev/null
+++ b/docs/notebooks/Llama_Stack_Agents_Monitoring.ipynb
@@ -0,0 +1,422 @@
+{
+ "cells": [
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "# Llama Stack - Agents Evaluation"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 37,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "import os\n",
+ "# from llama_stack.distribution.library_client import LlamaStackAsLibraryClient\n",
+ "from llama_stack_client import LlamaStackClient\n",
+ "\n",
+ "# client = LlamaStackAsLibraryClient(\n",
+ "# \"together\", provider_data = {\"tavily_search_api_key\": os.environ['TAVILY_SEARCH_API_KEY']})\n",
+ "\n",
+ "client = LlamaStackClient(base_url=\"http://localhost:8321\")\n",
+ "# _ = client.initialize()"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "#### Building a Search Agent"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 38,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "from llama_stack_client.types.agent_create_params import AgentConfig\n",
+ "from llama_stack_client.lib.agents.agent import Agent\n",
+ "\n",
+ "model_id = \"meta-llama/Llama-3.3-70B-Instruct\"\n",
+ "\n",
+ "agent_config_with_websearch = AgentConfig(\n",
+ " model=model_id,\n",
+ " instructions=\"You are a helpful assistant that can answer questions by searching the web.\",\n",
+ " sampling_params={\n",
+ " \"strategy\": {\"type\": \"top_p\", \"temperature\": 1.0, \"top_p\": 0.9},\n",
+ " },\n",
+ " toolgroups=[\"builtin::websearch\"],\n",
+ " tool_config={\n",
+ " \"tool_choice\": \"auto\",\n",
+ " \"tool_prompt_format\": \"python_list\",\n",
+ " },\n",
+ " input_shields=[],\n",
+ " output_shields=[],\n",
+ " enable_session_persistence=False,\n",
+ ")"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 52,
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/html": [
+ "Turn(\n",
+ "│ input_messages=[\n",
+ "│ │ UserMessage(content='Who received the IEEE Frank Rosenblatt Award in 2010?', role='user', context=None)\n",
+ "│ ],\n",
+ "│ output_message=CompletionMessage(\n",
+ "│ │ content='The recipient of the IEEE Frank Rosenblatt Award in 2010 was Dr. Ronald Fagin.',\n",
+ "│ │ role='assistant',\n",
+ "│ │ stop_reason='end_of_turn',\n",
+ "│ │ tool_calls=[]\n",
+ "│ ),\n",
+ "│ session_id='3a15bc56-f736-4126-8137-a5cb87406225',\n",
+ "│ started_at=datetime.datetime(2025, 2, 26, 12, 48, 15, 774381, tzinfo=TzInfo(-08:00)),\n",
+ "│ steps=[\n",
+ "│ │ InferenceStep(\n",
+ "│ │ │ api_model_response=CompletionMessage(\n",
+ "│ │ │ │ content='The recipient of the IEEE Frank Rosenblatt Award in 2010 was Dr. Ronald Fagin.',\n",
+ "│ │ │ │ role='assistant',\n",
+ "│ │ │ │ stop_reason='end_of_turn',\n",
+ "│ │ │ │ tool_calls=[]\n",
+ "│ │ │ ),\n",
+ "│ │ │ step_id='6c660138-574e-49a9-9f8c-552ccce874fc',\n",
+ "│ │ │ step_type='inference',\n",
+ "│ │ │ turn_id='7f07185b-66a0-4701-b965-5ff74793c2c4',\n",
+ "│ │ │ completed_at=datetime.datetime(2025, 2, 26, 12, 48, 16, 689502, tzinfo=TzInfo(-08:00)),\n",
+ "│ │ │ started_at=datetime.datetime(2025, 2, 26, 12, 48, 15, 786046, tzinfo=TzInfo(-08:00))\n",
+ "│ │ )\n",
+ "│ ],\n",
+ "│ turn_id='7f07185b-66a0-4701-b965-5ff74793c2c4',\n",
+ "│ completed_at=datetime.datetime(2025, 2, 26, 12, 48, 16, 702110, tzinfo=TzInfo(-08:00)),\n",
+ "│ output_attachments=[]\n",
+ ")\n",
+ "
\n"
+ ],
+ "text/plain": [
+ "\u001b[1;35mTurn\u001b[0m\u001b[1m(\u001b[0m\n",
+ "\u001b[2;32m│ \u001b[0m\u001b[33minput_messages\u001b[0m=\u001b[1m[\u001b[0m\n",
+ "\u001b[2;32m│ │ \u001b[0m\u001b[1;35mUserMessage\u001b[0m\u001b[1m(\u001b[0m\u001b[33mcontent\u001b[0m=\u001b[32m'Who received the IEEE Frank Rosenblatt Award in 2010?'\u001b[0m, \u001b[33mrole\u001b[0m=\u001b[32m'user'\u001b[0m, \u001b[33mcontext\u001b[0m=\u001b[3;35mNone\u001b[0m\u001b[1m)\u001b[0m\n",
+ "\u001b[2;32m│ \u001b[0m\u001b[1m]\u001b[0m,\n",
+ "\u001b[2;32m│ \u001b[0m\u001b[33moutput_message\u001b[0m=\u001b[1;35mCompletionMessage\u001b[0m\u001b[1m(\u001b[0m\n",
+ "\u001b[2;32m│ │ \u001b[0m\u001b[33mcontent\u001b[0m=\u001b[32m'The recipient of the IEEE Frank Rosenblatt Award in 2010 was Dr. Ronald Fagin.'\u001b[0m,\n",
+ "\u001b[2;32m│ │ \u001b[0m\u001b[33mrole\u001b[0m=\u001b[32m'assistant'\u001b[0m,\n",
+ "\u001b[2;32m│ │ \u001b[0m\u001b[33mstop_reason\u001b[0m=\u001b[32m'end_of_turn'\u001b[0m,\n",
+ "\u001b[2;32m│ │ \u001b[0m\u001b[33mtool_calls\u001b[0m=\u001b[1m[\u001b[0m\u001b[1m]\u001b[0m\n",
+ "\u001b[2;32m│ \u001b[0m\u001b[1m)\u001b[0m,\n",
+ "\u001b[2;32m│ \u001b[0m\u001b[33msession_id\u001b[0m=\u001b[32m'3a15bc56-f736-4126-8137-a5cb87406225'\u001b[0m,\n",
+ "\u001b[2;32m│ \u001b[0m\u001b[33mstarted_at\u001b[0m=\u001b[1;35mdatetime\u001b[0m\u001b[1;35m.datetime\u001b[0m\u001b[1m(\u001b[0m\u001b[1;36m2025\u001b[0m, \u001b[1;36m2\u001b[0m, \u001b[1;36m26\u001b[0m, \u001b[1;36m12\u001b[0m, \u001b[1;36m48\u001b[0m, \u001b[1;36m15\u001b[0m, \u001b[1;36m774381\u001b[0m, \u001b[33mtzinfo\u001b[0m=\u001b[1;35mTzInfo\u001b[0m\u001b[1m(\u001b[0m\u001b[1;36m-08\u001b[0m:\u001b[1;36m00\u001b[0m\u001b[1m)\u001b[0m\u001b[1m)\u001b[0m,\n",
+ "\u001b[2;32m│ \u001b[0m\u001b[33msteps\u001b[0m=\u001b[1m[\u001b[0m\n",
+ "\u001b[2;32m│ │ \u001b[0m\u001b[1;35mInferenceStep\u001b[0m\u001b[1m(\u001b[0m\n",
+ "\u001b[2;32m│ │ │ \u001b[0m\u001b[33mapi_model_response\u001b[0m=\u001b[1;35mCompletionMessage\u001b[0m\u001b[1m(\u001b[0m\n",
+ "\u001b[2;32m│ │ │ │ \u001b[0m\u001b[33mcontent\u001b[0m=\u001b[32m'The recipient of the IEEE Frank Rosenblatt Award in 2010 was Dr. Ronald Fagin.'\u001b[0m,\n",
+ "\u001b[2;32m│ │ │ │ \u001b[0m\u001b[33mrole\u001b[0m=\u001b[32m'assistant'\u001b[0m,\n",
+ "\u001b[2;32m│ │ │ │ \u001b[0m\u001b[33mstop_reason\u001b[0m=\u001b[32m'end_of_turn'\u001b[0m,\n",
+ "\u001b[2;32m│ │ │ │ \u001b[0m\u001b[33mtool_calls\u001b[0m=\u001b[1m[\u001b[0m\u001b[1m]\u001b[0m\n",
+ "\u001b[2;32m│ │ │ \u001b[0m\u001b[1m)\u001b[0m,\n",
+ "\u001b[2;32m│ │ │ \u001b[0m\u001b[33mstep_id\u001b[0m=\u001b[32m'6c660138-574e-49a9-9f8c-552ccce874fc'\u001b[0m,\n",
+ "\u001b[2;32m│ │ │ \u001b[0m\u001b[33mstep_type\u001b[0m=\u001b[32m'inference'\u001b[0m,\n",
+ "\u001b[2;32m│ │ │ \u001b[0m\u001b[33mturn_id\u001b[0m=\u001b[32m'7f07185b-66a0-4701-b965-5ff74793c2c4'\u001b[0m,\n",
+ "\u001b[2;32m│ │ │ \u001b[0m\u001b[33mcompleted_at\u001b[0m=\u001b[1;35mdatetime\u001b[0m\u001b[1;35m.datetime\u001b[0m\u001b[1m(\u001b[0m\u001b[1;36m2025\u001b[0m, \u001b[1;36m2\u001b[0m, \u001b[1;36m26\u001b[0m, \u001b[1;36m12\u001b[0m, \u001b[1;36m48\u001b[0m, \u001b[1;36m16\u001b[0m, \u001b[1;36m689502\u001b[0m, \u001b[33mtzinfo\u001b[0m=\u001b[1;35mTzInfo\u001b[0m\u001b[1m(\u001b[0m\u001b[1;36m-08\u001b[0m:\u001b[1;36m00\u001b[0m\u001b[1m)\u001b[0m\u001b[1m)\u001b[0m,\n",
+ "\u001b[2;32m│ │ │ \u001b[0m\u001b[33mstarted_at\u001b[0m=\u001b[1;35mdatetime\u001b[0m\u001b[1;35m.datetime\u001b[0m\u001b[1m(\u001b[0m\u001b[1;36m2025\u001b[0m, \u001b[1;36m2\u001b[0m, \u001b[1;36m26\u001b[0m, \u001b[1;36m12\u001b[0m, \u001b[1;36m48\u001b[0m, \u001b[1;36m15\u001b[0m, \u001b[1;36m786046\u001b[0m, \u001b[33mtzinfo\u001b[0m=\u001b[1;35mTzInfo\u001b[0m\u001b[1m(\u001b[0m\u001b[1;36m-08\u001b[0m:\u001b[1;36m00\u001b[0m\u001b[1m)\u001b[0m\u001b[1m)\u001b[0m\n",
+ "\u001b[2;32m│ │ \u001b[0m\u001b[1m)\u001b[0m\n",
+ "\u001b[2;32m│ \u001b[0m\u001b[1m]\u001b[0m,\n",
+ "\u001b[2;32m│ \u001b[0m\u001b[33mturn_id\u001b[0m=\u001b[32m'7f07185b-66a0-4701-b965-5ff74793c2c4'\u001b[0m,\n",
+ "\u001b[2;32m│ \u001b[0m\u001b[33mcompleted_at\u001b[0m=\u001b[1;35mdatetime\u001b[0m\u001b[1;35m.datetime\u001b[0m\u001b[1m(\u001b[0m\u001b[1;36m2025\u001b[0m, \u001b[1;36m2\u001b[0m, \u001b[1;36m26\u001b[0m, \u001b[1;36m12\u001b[0m, \u001b[1;36m48\u001b[0m, \u001b[1;36m16\u001b[0m, \u001b[1;36m702110\u001b[0m, \u001b[33mtzinfo\u001b[0m=\u001b[1;35mTzInfo\u001b[0m\u001b[1m(\u001b[0m\u001b[1;36m-08\u001b[0m:\u001b[1;36m00\u001b[0m\u001b[1m)\u001b[0m\u001b[1m)\u001b[0m,\n",
+ "\u001b[2;32m│ \u001b[0m\u001b[33moutput_attachments\u001b[0m=\u001b[1m[\u001b[0m\u001b[1m]\u001b[0m\n",
+ "\u001b[1m)\u001b[0m\n"
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "data": {
+ "text/html": [
+ "Turn(\n",
+ "│ input_messages=[\n",
+ "│ │ UserMessage(\n",
+ "│ │ │ content=\"Who was awarded the Oceanography Society's Jerlov Award in 2018?\",\n",
+ "│ │ │ role='user',\n",
+ "│ │ │ context=None\n",
+ "│ │ )\n",
+ "│ ],\n",
+ "│ output_message=CompletionMessage(\n",
+ "│ │ content=\"The Oceanography Society's Jerlov Award for 2018 was awarded to Dr. Emmanuel Boss.\",\n",
+ "│ │ role='assistant',\n",
+ "│ │ stop_reason='end_of_turn',\n",
+ "│ │ tool_calls=[]\n",
+ "│ ),\n",
+ "│ session_id='d0dfe88d-f75c-448c-892a-067aff1c1b72',\n",
+ "│ started_at=datetime.datetime(2025, 2, 26, 12, 48, 16, 740702, tzinfo=TzInfo(-08:00)),\n",
+ "│ steps=[\n",
+ "│ │ InferenceStep(\n",
+ "│ │ │ api_model_response=CompletionMessage(\n",
+ "│ │ │ │ content=\"The Oceanography Society's Jerlov Award for 2018 was awarded to Dr. Emmanuel Boss.\",\n",
+ "│ │ │ │ role='assistant',\n",
+ "│ │ │ │ stop_reason='end_of_turn',\n",
+ "│ │ │ │ tool_calls=[]\n",
+ "│ │ │ ),\n",
+ "│ │ │ step_id='c9c7ede1-94af-4f28-9068-8817dd675392',\n",
+ "│ │ │ step_type='inference',\n",
+ "│ │ │ turn_id='f701695e-389c-4078-9a4f-228479cf4d6a',\n",
+ "│ │ │ completed_at=datetime.datetime(2025, 2, 26, 12, 48, 17, 505687, tzinfo=TzInfo(-08:00)),\n",
+ "│ │ │ started_at=datetime.datetime(2025, 2, 26, 12, 48, 16, 752172, tzinfo=TzInfo(-08:00))\n",
+ "│ │ )\n",
+ "│ ],\n",
+ "│ turn_id='f701695e-389c-4078-9a4f-228479cf4d6a',\n",
+ "│ completed_at=datetime.datetime(2025, 2, 26, 12, 48, 17, 516772, tzinfo=TzInfo(-08:00)),\n",
+ "│ output_attachments=[]\n",
+ ")\n",
+ "
\n"
+ ],
+ "text/plain": [
+ "\u001b[1;35mTurn\u001b[0m\u001b[1m(\u001b[0m\n",
+ "\u001b[2;32m│ \u001b[0m\u001b[33minput_messages\u001b[0m=\u001b[1m[\u001b[0m\n",
+ "\u001b[2;32m│ │ \u001b[0m\u001b[1;35mUserMessage\u001b[0m\u001b[1m(\u001b[0m\n",
+ "\u001b[2;32m│ │ │ \u001b[0m\u001b[33mcontent\u001b[0m=\u001b[32m\"Who\u001b[0m\u001b[32m was awarded the Oceanography Society's Jerlov Award in 2018?\"\u001b[0m,\n",
+ "\u001b[2;32m│ │ │ \u001b[0m\u001b[33mrole\u001b[0m=\u001b[32m'user'\u001b[0m,\n",
+ "\u001b[2;32m│ │ │ \u001b[0m\u001b[33mcontext\u001b[0m=\u001b[3;35mNone\u001b[0m\n",
+ "\u001b[2;32m│ │ \u001b[0m\u001b[1m)\u001b[0m\n",
+ "\u001b[2;32m│ \u001b[0m\u001b[1m]\u001b[0m,\n",
+ "\u001b[2;32m│ \u001b[0m\u001b[33moutput_message\u001b[0m=\u001b[1;35mCompletionMessage\u001b[0m\u001b[1m(\u001b[0m\n",
+ "\u001b[2;32m│ │ \u001b[0m\u001b[33mcontent\u001b[0m=\u001b[32m\"The\u001b[0m\u001b[32m Oceanography Society's Jerlov Award for 2018 was awarded to Dr. Emmanuel Boss.\"\u001b[0m,\n",
+ "\u001b[2;32m│ │ \u001b[0m\u001b[33mrole\u001b[0m=\u001b[32m'assistant'\u001b[0m,\n",
+ "\u001b[2;32m│ │ \u001b[0m\u001b[33mstop_reason\u001b[0m=\u001b[32m'end_of_turn'\u001b[0m,\n",
+ "\u001b[2;32m│ │ \u001b[0m\u001b[33mtool_calls\u001b[0m=\u001b[1m[\u001b[0m\u001b[1m]\u001b[0m\n",
+ "\u001b[2;32m│ \u001b[0m\u001b[1m)\u001b[0m,\n",
+ "\u001b[2;32m│ \u001b[0m\u001b[33msession_id\u001b[0m=\u001b[32m'd0dfe88d-f75c-448c-892a-067aff1c1b72'\u001b[0m,\n",
+ "\u001b[2;32m│ \u001b[0m\u001b[33mstarted_at\u001b[0m=\u001b[1;35mdatetime\u001b[0m\u001b[1;35m.datetime\u001b[0m\u001b[1m(\u001b[0m\u001b[1;36m2025\u001b[0m, \u001b[1;36m2\u001b[0m, \u001b[1;36m26\u001b[0m, \u001b[1;36m12\u001b[0m, \u001b[1;36m48\u001b[0m, \u001b[1;36m16\u001b[0m, \u001b[1;36m740702\u001b[0m, \u001b[33mtzinfo\u001b[0m=\u001b[1;35mTzInfo\u001b[0m\u001b[1m(\u001b[0m\u001b[1;36m-08\u001b[0m:\u001b[1;36m00\u001b[0m\u001b[1m)\u001b[0m\u001b[1m)\u001b[0m,\n",
+ "\u001b[2;32m│ \u001b[0m\u001b[33msteps\u001b[0m=\u001b[1m[\u001b[0m\n",
+ "\u001b[2;32m│ │ \u001b[0m\u001b[1;35mInferenceStep\u001b[0m\u001b[1m(\u001b[0m\n",
+ "\u001b[2;32m│ │ │ \u001b[0m\u001b[33mapi_model_response\u001b[0m=\u001b[1;35mCompletionMessage\u001b[0m\u001b[1m(\u001b[0m\n",
+ "\u001b[2;32m│ │ │ │ \u001b[0m\u001b[33mcontent\u001b[0m=\u001b[32m\"The\u001b[0m\u001b[32m Oceanography Society's Jerlov Award for 2018 was awarded to Dr. Emmanuel Boss.\"\u001b[0m,\n",
+ "\u001b[2;32m│ │ │ │ \u001b[0m\u001b[33mrole\u001b[0m=\u001b[32m'assistant'\u001b[0m,\n",
+ "\u001b[2;32m│ │ │ │ \u001b[0m\u001b[33mstop_reason\u001b[0m=\u001b[32m'end_of_turn'\u001b[0m,\n",
+ "\u001b[2;32m│ │ │ │ \u001b[0m\u001b[33mtool_calls\u001b[0m=\u001b[1m[\u001b[0m\u001b[1m]\u001b[0m\n",
+ "\u001b[2;32m│ │ │ \u001b[0m\u001b[1m)\u001b[0m,\n",
+ "\u001b[2;32m│ │ │ \u001b[0m\u001b[33mstep_id\u001b[0m=\u001b[32m'c9c7ede1-94af-4f28-9068-8817dd675392'\u001b[0m,\n",
+ "\u001b[2;32m│ │ │ \u001b[0m\u001b[33mstep_type\u001b[0m=\u001b[32m'inference'\u001b[0m,\n",
+ "\u001b[2;32m│ │ │ \u001b[0m\u001b[33mturn_id\u001b[0m=\u001b[32m'f701695e-389c-4078-9a4f-228479cf4d6a'\u001b[0m,\n",
+ "\u001b[2;32m│ │ │ \u001b[0m\u001b[33mcompleted_at\u001b[0m=\u001b[1;35mdatetime\u001b[0m\u001b[1;35m.datetime\u001b[0m\u001b[1m(\u001b[0m\u001b[1;36m2025\u001b[0m, \u001b[1;36m2\u001b[0m, \u001b[1;36m26\u001b[0m, \u001b[1;36m12\u001b[0m, \u001b[1;36m48\u001b[0m, \u001b[1;36m17\u001b[0m, \u001b[1;36m505687\u001b[0m, \u001b[33mtzinfo\u001b[0m=\u001b[1;35mTzInfo\u001b[0m\u001b[1m(\u001b[0m\u001b[1;36m-08\u001b[0m:\u001b[1;36m00\u001b[0m\u001b[1m)\u001b[0m\u001b[1m)\u001b[0m,\n",
+ "\u001b[2;32m│ │ │ \u001b[0m\u001b[33mstarted_at\u001b[0m=\u001b[1;35mdatetime\u001b[0m\u001b[1;35m.datetime\u001b[0m\u001b[1m(\u001b[0m\u001b[1;36m2025\u001b[0m, \u001b[1;36m2\u001b[0m, \u001b[1;36m26\u001b[0m, \u001b[1;36m12\u001b[0m, \u001b[1;36m48\u001b[0m, \u001b[1;36m16\u001b[0m, \u001b[1;36m752172\u001b[0m, \u001b[33mtzinfo\u001b[0m=\u001b[1;35mTzInfo\u001b[0m\u001b[1m(\u001b[0m\u001b[1;36m-08\u001b[0m:\u001b[1;36m00\u001b[0m\u001b[1m)\u001b[0m\u001b[1m)\u001b[0m\n",
+ "\u001b[2;32m│ │ \u001b[0m\u001b[1m)\u001b[0m\n",
+ "\u001b[2;32m│ \u001b[0m\u001b[1m]\u001b[0m,\n",
+ "\u001b[2;32m│ \u001b[0m\u001b[33mturn_id\u001b[0m=\u001b[32m'f701695e-389c-4078-9a4f-228479cf4d6a'\u001b[0m,\n",
+ "\u001b[2;32m│ \u001b[0m\u001b[33mcompleted_at\u001b[0m=\u001b[1;35mdatetime\u001b[0m\u001b[1;35m.datetime\u001b[0m\u001b[1m(\u001b[0m\u001b[1;36m2025\u001b[0m, \u001b[1;36m2\u001b[0m, \u001b[1;36m26\u001b[0m, \u001b[1;36m12\u001b[0m, \u001b[1;36m48\u001b[0m, \u001b[1;36m17\u001b[0m, \u001b[1;36m516772\u001b[0m, \u001b[33mtzinfo\u001b[0m=\u001b[1;35mTzInfo\u001b[0m\u001b[1m(\u001b[0m\u001b[1;36m-08\u001b[0m:\u001b[1;36m00\u001b[0m\u001b[1m)\u001b[0m\u001b[1m)\u001b[0m,\n",
+ "\u001b[2;32m│ \u001b[0m\u001b[33moutput_attachments\u001b[0m=\u001b[1m[\u001b[0m\u001b[1m]\u001b[0m\n",
+ "\u001b[1m)\u001b[0m\n"
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "data": {
+ "text/html": [
+ "Turn(\n",
+ "│ input_messages=[\n",
+ "│ │ UserMessage(\n",
+ "│ │ │ content=\"What's the name of the women's liberal arts college in Cambridge, Massachusetts?\",\n",
+ "│ │ │ role='user',\n",
+ "│ │ │ context=None\n",
+ "│ │ )\n",
+ "│ ],\n",
+ "│ output_message=CompletionMessage(\n",
+ "│ │ content=\"The women's liberal arts college in Cambridge, Massachusetts is Radcliffe College. However, it's important to note that Radcliffe College merged with Harvard University in 1999 and is now known as the Radcliffe Institute for Advanced Study at Harvard University. The institute still offers programs and resources for women, but it is no longer an independent college.\",\n",
+ "│ │ role='assistant',\n",
+ "│ │ stop_reason='end_of_turn',\n",
+ "│ │ tool_calls=[]\n",
+ "│ ),\n",
+ "│ session_id='2424c5ca-afb2-4cc4-a5f5-f7ce0ec473d5',\n",
+ "│ started_at=datetime.datetime(2025, 2, 26, 12, 48, 17, 560298, tzinfo=TzInfo(-08:00)),\n",
+ "│ steps=[\n",
+ "│ │ InferenceStep(\n",
+ "│ │ │ api_model_response=CompletionMessage(\n",
+ "│ │ │ │ content=\"The women's liberal arts college in Cambridge, Massachusetts is Radcliffe College. However, it's important to note that Radcliffe College merged with Harvard University in 1999 and is now known as the Radcliffe Institute for Advanced Study at Harvard University. The institute still offers programs and resources for women, but it is no longer an independent college.\",\n",
+ "│ │ │ │ role='assistant',\n",
+ "│ │ │ │ stop_reason='end_of_turn',\n",
+ "│ │ │ │ tool_calls=[]\n",
+ "│ │ │ ),\n",
+ "│ │ │ step_id='2cbf44bc-d836-4449-99f6-a5fe72c2d8a0',\n",
+ "│ │ │ step_type='inference',\n",
+ "│ │ │ turn_id='0b4040e7-7aa6-4f86-a072-31333ffa29be',\n",
+ "│ │ │ completed_at=datetime.datetime(2025, 2, 26, 12, 48, 19, 269112, tzinfo=TzInfo(-08:00)),\n",
+ "│ │ │ started_at=datetime.datetime(2025, 2, 26, 12, 48, 17, 571880, tzinfo=TzInfo(-08:00))\n",
+ "│ │ )\n",
+ "│ ],\n",
+ "│ turn_id='0b4040e7-7aa6-4f86-a072-31333ffa29be',\n",
+ "│ completed_at=datetime.datetime(2025, 2, 26, 12, 48, 19, 282118, tzinfo=TzInfo(-08:00)),\n",
+ "│ output_attachments=[]\n",
+ ")\n",
+ "
\n"
+ ],
+ "text/plain": [
+ "\u001b[1;35mTurn\u001b[0m\u001b[1m(\u001b[0m\n",
+ "\u001b[2;32m│ \u001b[0m\u001b[33minput_messages\u001b[0m=\u001b[1m[\u001b[0m\n",
+ "\u001b[2;32m│ │ \u001b[0m\u001b[1;35mUserMessage\u001b[0m\u001b[1m(\u001b[0m\n",
+ "\u001b[2;32m│ │ │ \u001b[0m\u001b[33mcontent\u001b[0m=\u001b[32m\"What\u001b[0m\u001b[32m's the name of the women's liberal arts college in Cambridge, Massachusetts?\"\u001b[0m,\n",
+ "\u001b[2;32m│ │ │ \u001b[0m\u001b[33mrole\u001b[0m=\u001b[32m'user'\u001b[0m,\n",
+ "\u001b[2;32m│ │ │ \u001b[0m\u001b[33mcontext\u001b[0m=\u001b[3;35mNone\u001b[0m\n",
+ "\u001b[2;32m│ │ \u001b[0m\u001b[1m)\u001b[0m\n",
+ "\u001b[2;32m│ \u001b[0m\u001b[1m]\u001b[0m,\n",
+ "\u001b[2;32m│ \u001b[0m\u001b[33moutput_message\u001b[0m=\u001b[1;35mCompletionMessage\u001b[0m\u001b[1m(\u001b[0m\n",
+ "\u001b[2;32m│ │ \u001b[0m\u001b[33mcontent\u001b[0m=\u001b[32m\"The\u001b[0m\u001b[32m women's liberal arts college in Cambridge, Massachusetts is Radcliffe College. However, it's important to note that Radcliffe College merged with Harvard University in 1999 and is now known as the Radcliffe Institute for Advanced Study at Harvard University. The institute still offers programs and resources for women, but it is no longer an independent college.\"\u001b[0m,\n",
+ "\u001b[2;32m│ │ \u001b[0m\u001b[33mrole\u001b[0m=\u001b[32m'assistant'\u001b[0m,\n",
+ "\u001b[2;32m│ │ \u001b[0m\u001b[33mstop_reason\u001b[0m=\u001b[32m'end_of_turn'\u001b[0m,\n",
+ "\u001b[2;32m│ │ \u001b[0m\u001b[33mtool_calls\u001b[0m=\u001b[1m[\u001b[0m\u001b[1m]\u001b[0m\n",
+ "\u001b[2;32m│ \u001b[0m\u001b[1m)\u001b[0m,\n",
+ "\u001b[2;32m│ \u001b[0m\u001b[33msession_id\u001b[0m=\u001b[32m'2424c5ca-afb2-4cc4-a5f5-f7ce0ec473d5'\u001b[0m,\n",
+ "\u001b[2;32m│ \u001b[0m\u001b[33mstarted_at\u001b[0m=\u001b[1;35mdatetime\u001b[0m\u001b[1;35m.datetime\u001b[0m\u001b[1m(\u001b[0m\u001b[1;36m2025\u001b[0m, \u001b[1;36m2\u001b[0m, \u001b[1;36m26\u001b[0m, \u001b[1;36m12\u001b[0m, \u001b[1;36m48\u001b[0m, \u001b[1;36m17\u001b[0m, \u001b[1;36m560298\u001b[0m, \u001b[33mtzinfo\u001b[0m=\u001b[1;35mTzInfo\u001b[0m\u001b[1m(\u001b[0m\u001b[1;36m-08\u001b[0m:\u001b[1;36m00\u001b[0m\u001b[1m)\u001b[0m\u001b[1m)\u001b[0m,\n",
+ "\u001b[2;32m│ \u001b[0m\u001b[33msteps\u001b[0m=\u001b[1m[\u001b[0m\n",
+ "\u001b[2;32m│ │ \u001b[0m\u001b[1;35mInferenceStep\u001b[0m\u001b[1m(\u001b[0m\n",
+ "\u001b[2;32m│ │ │ \u001b[0m\u001b[33mapi_model_response\u001b[0m=\u001b[1;35mCompletionMessage\u001b[0m\u001b[1m(\u001b[0m\n",
+ "\u001b[2;32m│ │ │ │ \u001b[0m\u001b[33mcontent\u001b[0m=\u001b[32m\"The\u001b[0m\u001b[32m women's liberal arts college in Cambridge, Massachusetts is Radcliffe College. However, it's important to note that Radcliffe College merged with Harvard University in 1999 and is now known as the Radcliffe Institute for Advanced Study at Harvard University. The institute still offers programs and resources for women, but it is no longer an independent college.\"\u001b[0m,\n",
+ "\u001b[2;32m│ │ │ │ \u001b[0m\u001b[33mrole\u001b[0m=\u001b[32m'assistant'\u001b[0m,\n",
+ "\u001b[2;32m│ │ │ │ \u001b[0m\u001b[33mstop_reason\u001b[0m=\u001b[32m'end_of_turn'\u001b[0m,\n",
+ "\u001b[2;32m│ │ │ │ \u001b[0m\u001b[33mtool_calls\u001b[0m=\u001b[1m[\u001b[0m\u001b[1m]\u001b[0m\n",
+ "\u001b[2;32m│ │ │ \u001b[0m\u001b[1m)\u001b[0m,\n",
+ "\u001b[2;32m│ │ │ \u001b[0m\u001b[33mstep_id\u001b[0m=\u001b[32m'2cbf44bc-d836-4449-99f6-a5fe72c2d8a0'\u001b[0m,\n",
+ "\u001b[2;32m│ │ │ \u001b[0m\u001b[33mstep_type\u001b[0m=\u001b[32m'inference'\u001b[0m,\n",
+ "\u001b[2;32m│ │ │ \u001b[0m\u001b[33mturn_id\u001b[0m=\u001b[32m'0b4040e7-7aa6-4f86-a072-31333ffa29be'\u001b[0m,\n",
+ "\u001b[2;32m│ │ │ \u001b[0m\u001b[33mcompleted_at\u001b[0m=\u001b[1;35mdatetime\u001b[0m\u001b[1;35m.datetime\u001b[0m\u001b[1m(\u001b[0m\u001b[1;36m2025\u001b[0m, \u001b[1;36m2\u001b[0m, \u001b[1;36m26\u001b[0m, \u001b[1;36m12\u001b[0m, \u001b[1;36m48\u001b[0m, \u001b[1;36m19\u001b[0m, \u001b[1;36m269112\u001b[0m, \u001b[33mtzinfo\u001b[0m=\u001b[1;35mTzInfo\u001b[0m\u001b[1m(\u001b[0m\u001b[1;36m-08\u001b[0m:\u001b[1;36m00\u001b[0m\u001b[1m)\u001b[0m\u001b[1m)\u001b[0m,\n",
+ "\u001b[2;32m│ │ │ \u001b[0m\u001b[33mstarted_at\u001b[0m=\u001b[1;35mdatetime\u001b[0m\u001b[1;35m.datetime\u001b[0m\u001b[1m(\u001b[0m\u001b[1;36m2025\u001b[0m, \u001b[1;36m2\u001b[0m, \u001b[1;36m26\u001b[0m, \u001b[1;36m12\u001b[0m, \u001b[1;36m48\u001b[0m, \u001b[1;36m17\u001b[0m, \u001b[1;36m571880\u001b[0m, \u001b[33mtzinfo\u001b[0m=\u001b[1;35mTzInfo\u001b[0m\u001b[1m(\u001b[0m\u001b[1;36m-08\u001b[0m:\u001b[1;36m00\u001b[0m\u001b[1m)\u001b[0m\u001b[1m)\u001b[0m\n",
+ "\u001b[2;32m│ │ \u001b[0m\u001b[1m)\u001b[0m\n",
+ "\u001b[2;32m│ \u001b[0m\u001b[1m]\u001b[0m,\n",
+ "\u001b[2;32m│ \u001b[0m\u001b[33mturn_id\u001b[0m=\u001b[32m'0b4040e7-7aa6-4f86-a072-31333ffa29be'\u001b[0m,\n",
+ "\u001b[2;32m│ \u001b[0m\u001b[33mcompleted_at\u001b[0m=\u001b[1;35mdatetime\u001b[0m\u001b[1;35m.datetime\u001b[0m\u001b[1m(\u001b[0m\u001b[1;36m2025\u001b[0m, \u001b[1;36m2\u001b[0m, \u001b[1;36m26\u001b[0m, \u001b[1;36m12\u001b[0m, \u001b[1;36m48\u001b[0m, \u001b[1;36m19\u001b[0m, \u001b[1;36m282118\u001b[0m, \u001b[33mtzinfo\u001b[0m=\u001b[1;35mTzInfo\u001b[0m\u001b[1m(\u001b[0m\u001b[1;36m-08\u001b[0m:\u001b[1;36m00\u001b[0m\u001b[1m)\u001b[0m\u001b[1m)\u001b[0m,\n",
+ "\u001b[2;32m│ \u001b[0m\u001b[33moutput_attachments\u001b[0m=\u001b[1m[\u001b[0m\u001b[1m]\u001b[0m\n",
+ "\u001b[1m)\u001b[0m\n"
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ }
+ ],
+ "source": [
+ "import uuid\n",
+ "from datasets import load_dataset\n",
+ "from rich.pretty import pprint\n",
+ "\n",
+ "# 0. Create an agent\n",
+ "agent = Agent(client, agent_config_with_websearch)\n",
+ "\n",
+ "# 2. Send it a couple of questions in the sesison. Here, we get the first 10 questions from the Simple QA dataset.\n",
+ "ds = load_dataset(\"llamastack/evals\", \"evals__simpleqa\")\n",
+ "questions = []\n",
+ "answers = []\n",
+ "for idx, x in enumerate(ds[\"train\"]):\n",
+ " if idx >= 3:\n",
+ " break\n",
+ " questions.append(x[\"input_query\"])\n",
+ " answers.append(x[\"expected_answer\"])\n",
+ "\n",
+ "for query in questions:\n",
+ " # create a new session for each question\n",
+ " session_id = agent.create_session(f\"{uuid.uuid4().hex}\")\n",
+ " response = agent.create_turn(\n",
+ " [\n",
+ " {\n",
+ " \"role\": \"user\",\n",
+ " \"content\": query,\n",
+ " }\n",
+ " ], \n",
+ " session_id=session_id,\n",
+ " stream=False\n",
+ " )\n",
+ " pprint(response)"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "### Examine agent logs"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 53,
+ "metadata": {},
+ "outputs": [
+ {
+ "ename": "InternalServerError",
+ "evalue": "Error code: 500 - {'detail': 'Internal server error: An unexpected error occurred.'}",
+ "output_type": "error",
+ "traceback": [
+ "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
+ "\u001b[0;31mInternalServerError\u001b[0m Traceback (most recent call last)",
+ "Cell \u001b[0;32mIn[53], line 6\u001b[0m\n\u001b[1;32m 3\u001b[0m agent_id \u001b[38;5;241m=\u001b[39m agent\u001b[38;5;241m.\u001b[39magent_id\n\u001b[1;32m 5\u001b[0m \u001b[38;5;66;03m# print(session_ids)\u001b[39;00m\n\u001b[0;32m----> 6\u001b[0m response \u001b[38;5;241m=\u001b[39m \u001b[43mclient\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43magents\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43msession\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mretrieve\u001b[49m\u001b[43m(\u001b[49m\n\u001b[1;32m 7\u001b[0m \u001b[43m \u001b[49m\u001b[43msession_id\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43md1cb76fb-cd59-4dd9-afe5-0ce7ede630a9\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m,\u001b[49m\n\u001b[1;32m 8\u001b[0m \u001b[43m \u001b[49m\u001b[43magent_id\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43magent_id\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 9\u001b[0m \u001b[43m)\u001b[49m\n\u001b[1;32m 10\u001b[0m \u001b[38;5;28mprint\u001b[39m(response)\n\u001b[1;32m 11\u001b[0m \u001b[38;5;66;03m# client.agents.turn.retrieve(\u001b[39;00m\n\u001b[1;32m 12\u001b[0m \u001b[38;5;66;03m# session_id=\"89459cef-7494-4a37-8278-59343b6174a3\",\u001b[39;00m\n\u001b[1;32m 13\u001b[0m \u001b[38;5;66;03m# agent_id=agent_id,\u001b[39;00m\n\u001b[0;32m (...)\u001b[0m\n\u001b[1;32m 22\u001b[0m \n\u001b[1;32m 23\u001b[0m \u001b[38;5;66;03m# pprint(session2turns)\u001b[39;00m\n",
+ "File \u001b[0;32m~/Desktop/meta-llama/llama-stack-client-python/src/llama_stack_client/resources/agents/session.py:110\u001b[0m, in \u001b[0;36mSessionResource.retrieve\u001b[0;34m(self, session_id, agent_id, turn_ids, extra_headers, extra_query, extra_body, timeout)\u001b[0m\n\u001b[1;32m 108\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m session_id:\n\u001b[1;32m 109\u001b[0m \u001b[38;5;28;01mraise\u001b[39;00m \u001b[38;5;167;01mValueError\u001b[39;00m(\u001b[38;5;124mf\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mExpected a non-empty value for `session_id` but received \u001b[39m\u001b[38;5;132;01m{\u001b[39;00msession_id\u001b[38;5;132;01m!r}\u001b[39;00m\u001b[38;5;124m\"\u001b[39m)\n\u001b[0;32m--> 110\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_get\u001b[49m\u001b[43m(\u001b[49m\n\u001b[1;32m 111\u001b[0m \u001b[43m \u001b[49m\u001b[38;5;124;43mf\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43m/v1/agents/\u001b[39;49m\u001b[38;5;132;43;01m{\u001b[39;49;00m\u001b[43magent_id\u001b[49m\u001b[38;5;132;43;01m}\u001b[39;49;00m\u001b[38;5;124;43m/session/\u001b[39;49m\u001b[38;5;132;43;01m{\u001b[39;49;00m\u001b[43msession_id\u001b[49m\u001b[38;5;132;43;01m}\u001b[39;49;00m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m,\u001b[49m\n\u001b[1;32m 112\u001b[0m \u001b[43m \u001b[49m\u001b[43moptions\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mmake_request_options\u001b[49m\u001b[43m(\u001b[49m\n\u001b[1;32m 113\u001b[0m \u001b[43m \u001b[49m\u001b[43mextra_headers\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mextra_headers\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 114\u001b[0m \u001b[43m \u001b[49m\u001b[43mextra_query\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mextra_query\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 115\u001b[0m \u001b[43m \u001b[49m\u001b[43mextra_body\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mextra_body\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 116\u001b[0m \u001b[43m \u001b[49m\u001b[43mtimeout\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mtimeout\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 117\u001b[0m \u001b[43m \u001b[49m\u001b[43mquery\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mmaybe_transform\u001b[49m\u001b[43m(\u001b[49m\u001b[43m{\u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mturn_ids\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m:\u001b[49m\u001b[43m \u001b[49m\u001b[43mturn_ids\u001b[49m\u001b[43m}\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43msession_retrieve_params\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mSessionRetrieveParams\u001b[49m\u001b[43m)\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 118\u001b[0m \u001b[43m \u001b[49m\u001b[43m)\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 119\u001b[0m \u001b[43m \u001b[49m\u001b[43mcast_to\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mSession\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 120\u001b[0m \u001b[43m\u001b[49m\u001b[43m)\u001b[49m\n",
+ "File \u001b[0;32m~/Desktop/meta-llama/llama-stack-client-python/src/llama_stack_client/_base_client.py:1219\u001b[0m, in \u001b[0;36mSyncAPIClient.get\u001b[0;34m(self, path, cast_to, options, stream, stream_cls)\u001b[0m\n\u001b[1;32m 1216\u001b[0m opts \u001b[38;5;241m=\u001b[39m FinalRequestOptions\u001b[38;5;241m.\u001b[39mconstruct(method\u001b[38;5;241m=\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mget\u001b[39m\u001b[38;5;124m\"\u001b[39m, url\u001b[38;5;241m=\u001b[39mpath, \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39moptions)\n\u001b[1;32m 1217\u001b[0m \u001b[38;5;66;03m# cast is required because mypy complains about returning Any even though\u001b[39;00m\n\u001b[1;32m 1218\u001b[0m \u001b[38;5;66;03m# it understands the type variables\u001b[39;00m\n\u001b[0;32m-> 1219\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m cast(ResponseT, \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mrequest\u001b[49m\u001b[43m(\u001b[49m\u001b[43mcast_to\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mopts\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mstream\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mstream\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mstream_cls\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mstream_cls\u001b[49m\u001b[43m)\u001b[49m)\n",
+ "File \u001b[0;32m~/Desktop/meta-llama/llama-stack-client-python/src/llama_stack_client/_base_client.py:965\u001b[0m, in \u001b[0;36mSyncAPIClient.request\u001b[0;34m(self, cast_to, options, remaining_retries, stream, stream_cls)\u001b[0m\n\u001b[1;32m 962\u001b[0m \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[1;32m 963\u001b[0m retries_taken \u001b[38;5;241m=\u001b[39m \u001b[38;5;241m0\u001b[39m\n\u001b[0;32m--> 965\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_request\u001b[49m\u001b[43m(\u001b[49m\n\u001b[1;32m 966\u001b[0m \u001b[43m \u001b[49m\u001b[43mcast_to\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mcast_to\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 967\u001b[0m \u001b[43m \u001b[49m\u001b[43moptions\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43moptions\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 968\u001b[0m \u001b[43m \u001b[49m\u001b[43mstream\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mstream\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 969\u001b[0m \u001b[43m \u001b[49m\u001b[43mstream_cls\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mstream_cls\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 970\u001b[0m \u001b[43m \u001b[49m\u001b[43mretries_taken\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mretries_taken\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 971\u001b[0m \u001b[43m\u001b[49m\u001b[43m)\u001b[49m\n",
+ "File \u001b[0;32m~/Desktop/meta-llama/llama-stack-client-python/src/llama_stack_client/_base_client.py:1053\u001b[0m, in \u001b[0;36mSyncAPIClient._request\u001b[0;34m(self, cast_to, options, retries_taken, stream, stream_cls)\u001b[0m\n\u001b[1;32m 1051\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m remaining_retries \u001b[38;5;241m>\u001b[39m \u001b[38;5;241m0\u001b[39m \u001b[38;5;129;01mand\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_should_retry(err\u001b[38;5;241m.\u001b[39mresponse):\n\u001b[1;32m 1052\u001b[0m err\u001b[38;5;241m.\u001b[39mresponse\u001b[38;5;241m.\u001b[39mclose()\n\u001b[0;32m-> 1053\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_retry_request\u001b[49m\u001b[43m(\u001b[49m\n\u001b[1;32m 1054\u001b[0m \u001b[43m \u001b[49m\u001b[43minput_options\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 1055\u001b[0m \u001b[43m \u001b[49m\u001b[43mcast_to\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 1056\u001b[0m \u001b[43m \u001b[49m\u001b[43mretries_taken\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mretries_taken\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 1057\u001b[0m \u001b[43m \u001b[49m\u001b[43mresponse_headers\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43merr\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mresponse\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mheaders\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 1058\u001b[0m \u001b[43m \u001b[49m\u001b[43mstream\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mstream\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 1059\u001b[0m \u001b[43m \u001b[49m\u001b[43mstream_cls\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mstream_cls\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 1060\u001b[0m \u001b[43m \u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 1062\u001b[0m \u001b[38;5;66;03m# If the response is streamed then we need to explicitly read the response\u001b[39;00m\n\u001b[1;32m 1063\u001b[0m \u001b[38;5;66;03m# to completion before attempting to access the response text.\u001b[39;00m\n\u001b[1;32m 1064\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m err\u001b[38;5;241m.\u001b[39mresponse\u001b[38;5;241m.\u001b[39mis_closed:\n",
+ "File \u001b[0;32m~/Desktop/meta-llama/llama-stack-client-python/src/llama_stack_client/_base_client.py:1102\u001b[0m, in \u001b[0;36mSyncAPIClient._retry_request\u001b[0;34m(self, options, cast_to, retries_taken, response_headers, stream, stream_cls)\u001b[0m\n\u001b[1;32m 1098\u001b[0m \u001b[38;5;66;03m# In a synchronous context we are blocking the entire thread. Up to the library user to run the client in a\u001b[39;00m\n\u001b[1;32m 1099\u001b[0m \u001b[38;5;66;03m# different thread if necessary.\u001b[39;00m\n\u001b[1;32m 1100\u001b[0m time\u001b[38;5;241m.\u001b[39msleep(timeout)\n\u001b[0;32m-> 1102\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_request\u001b[49m\u001b[43m(\u001b[49m\n\u001b[1;32m 1103\u001b[0m \u001b[43m \u001b[49m\u001b[43moptions\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43moptions\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 1104\u001b[0m \u001b[43m \u001b[49m\u001b[43mcast_to\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mcast_to\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 1105\u001b[0m \u001b[43m \u001b[49m\u001b[43mretries_taken\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mretries_taken\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m+\u001b[39;49m\u001b[43m \u001b[49m\u001b[38;5;241;43m1\u001b[39;49m\u001b[43m,\u001b[49m\n\u001b[1;32m 1106\u001b[0m \u001b[43m \u001b[49m\u001b[43mstream\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mstream\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 1107\u001b[0m \u001b[43m \u001b[49m\u001b[43mstream_cls\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mstream_cls\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 1108\u001b[0m \u001b[43m\u001b[49m\u001b[43m)\u001b[49m\n",
+ "File \u001b[0;32m~/Desktop/meta-llama/llama-stack-client-python/src/llama_stack_client/_base_client.py:1053\u001b[0m, in \u001b[0;36mSyncAPIClient._request\u001b[0;34m(self, cast_to, options, retries_taken, stream, stream_cls)\u001b[0m\n\u001b[1;32m 1051\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m remaining_retries \u001b[38;5;241m>\u001b[39m \u001b[38;5;241m0\u001b[39m \u001b[38;5;129;01mand\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_should_retry(err\u001b[38;5;241m.\u001b[39mresponse):\n\u001b[1;32m 1052\u001b[0m err\u001b[38;5;241m.\u001b[39mresponse\u001b[38;5;241m.\u001b[39mclose()\n\u001b[0;32m-> 1053\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_retry_request\u001b[49m\u001b[43m(\u001b[49m\n\u001b[1;32m 1054\u001b[0m \u001b[43m \u001b[49m\u001b[43minput_options\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 1055\u001b[0m \u001b[43m \u001b[49m\u001b[43mcast_to\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 1056\u001b[0m \u001b[43m \u001b[49m\u001b[43mretries_taken\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mretries_taken\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 1057\u001b[0m \u001b[43m \u001b[49m\u001b[43mresponse_headers\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43merr\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mresponse\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mheaders\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 1058\u001b[0m \u001b[43m \u001b[49m\u001b[43mstream\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mstream\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 1059\u001b[0m \u001b[43m \u001b[49m\u001b[43mstream_cls\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mstream_cls\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 1060\u001b[0m \u001b[43m \u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 1062\u001b[0m \u001b[38;5;66;03m# If the response is streamed then we need to explicitly read the response\u001b[39;00m\n\u001b[1;32m 1063\u001b[0m \u001b[38;5;66;03m# to completion before attempting to access the response text.\u001b[39;00m\n\u001b[1;32m 1064\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m err\u001b[38;5;241m.\u001b[39mresponse\u001b[38;5;241m.\u001b[39mis_closed:\n",
+ "File \u001b[0;32m~/Desktop/meta-llama/llama-stack-client-python/src/llama_stack_client/_base_client.py:1102\u001b[0m, in \u001b[0;36mSyncAPIClient._retry_request\u001b[0;34m(self, options, cast_to, retries_taken, response_headers, stream, stream_cls)\u001b[0m\n\u001b[1;32m 1098\u001b[0m \u001b[38;5;66;03m# In a synchronous context we are blocking the entire thread. Up to the library user to run the client in a\u001b[39;00m\n\u001b[1;32m 1099\u001b[0m \u001b[38;5;66;03m# different thread if necessary.\u001b[39;00m\n\u001b[1;32m 1100\u001b[0m time\u001b[38;5;241m.\u001b[39msleep(timeout)\n\u001b[0;32m-> 1102\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_request\u001b[49m\u001b[43m(\u001b[49m\n\u001b[1;32m 1103\u001b[0m \u001b[43m \u001b[49m\u001b[43moptions\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43moptions\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 1104\u001b[0m \u001b[43m \u001b[49m\u001b[43mcast_to\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mcast_to\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 1105\u001b[0m \u001b[43m \u001b[49m\u001b[43mretries_taken\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mretries_taken\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m+\u001b[39;49m\u001b[43m \u001b[49m\u001b[38;5;241;43m1\u001b[39;49m\u001b[43m,\u001b[49m\n\u001b[1;32m 1106\u001b[0m \u001b[43m \u001b[49m\u001b[43mstream\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mstream\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 1107\u001b[0m \u001b[43m \u001b[49m\u001b[43mstream_cls\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mstream_cls\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 1108\u001b[0m \u001b[43m\u001b[49m\u001b[43m)\u001b[49m\n",
+ "File \u001b[0;32m~/Desktop/meta-llama/llama-stack-client-python/src/llama_stack_client/_base_client.py:1068\u001b[0m, in \u001b[0;36mSyncAPIClient._request\u001b[0;34m(self, cast_to, options, retries_taken, stream, stream_cls)\u001b[0m\n\u001b[1;32m 1065\u001b[0m err\u001b[38;5;241m.\u001b[39mresponse\u001b[38;5;241m.\u001b[39mread()\n\u001b[1;32m 1067\u001b[0m log\u001b[38;5;241m.\u001b[39mdebug(\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mRe-raising status error\u001b[39m\u001b[38;5;124m\"\u001b[39m)\n\u001b[0;32m-> 1068\u001b[0m \u001b[38;5;28;01mraise\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_make_status_error_from_response(err\u001b[38;5;241m.\u001b[39mresponse) \u001b[38;5;28;01mfrom\u001b[39;00m \u001b[38;5;28;01mNone\u001b[39;00m\n\u001b[1;32m 1070\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_process_response(\n\u001b[1;32m 1071\u001b[0m cast_to\u001b[38;5;241m=\u001b[39mcast_to,\n\u001b[1;32m 1072\u001b[0m options\u001b[38;5;241m=\u001b[39moptions,\n\u001b[0;32m (...)\u001b[0m\n\u001b[1;32m 1076\u001b[0m retries_taken\u001b[38;5;241m=\u001b[39mretries_taken,\n\u001b[1;32m 1077\u001b[0m )\n",
+ "\u001b[0;31mInternalServerError\u001b[0m: Error code: 500 - {'detail': 'Internal server error: An unexpected error occurred.'}"
+ ]
+ }
+ ],
+ "source": [
+ "# get the agent session ids\n",
+ "session_ids = agent.sessions\n",
+ "agent_id = agent.agent_id\n",
+ "\n",
+ "# print(session_ids)\n",
+ "response = client.agents.session.retrieve(\n",
+ " session_id=\"d1cb76fb-cd59-4dd9-afe5-0ce7ede630a9\",\n",
+ " agent_id=agent_id,\n",
+ ")\n",
+ "print(response)\n",
+ "# client.agents.turn.retrieve(\n",
+ "# session_id=\"89459cef-7494-4a37-8278-59343b6174a3\",\n",
+ "# agent_id=agent_id,\n",
+ "# turn_id=\"f1e09cd5-a2af-483b-9dfa-cc374528bcd7\",\n",
+ "# )\n",
+ "# session2turns = {}\n",
+ "# for session_id in session_ids:\n",
+ "# session2turns[session_id] = client.agents.session.retrieve(\n",
+ "# session_id=session_id,\n",
+ "# agent_id=agent_id,\n",
+ "# )\n",
+ "\n",
+ "# pprint(session2turns)"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": []
+ }
+ ],
+ "metadata": {
+ "kernelspec": {
+ "display_name": "master",
+ "language": "python",
+ "name": "python3"
+ },
+ "language_info": {
+ "codemirror_mode": {
+ "name": "ipython",
+ "version": 3
+ },
+ "file_extension": ".py",
+ "mimetype": "text/x-python",
+ "name": "python",
+ "nbconvert_exporter": "python",
+ "pygments_lexer": "ipython3",
+ "version": "3.10.16"
+ }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}
diff --git a/llama_stack/providers/inline/agents/meta_reference/agents.py b/llama_stack/providers/inline/agents/meta_reference/agents.py
index 72c1a0f34..d8edb1de1 100644
--- a/llama_stack/providers/inline/agents/meta_reference/agents.py
+++ b/llama_stack/providers/inline/agents/meta_reference/agents.py
@@ -194,20 +194,22 @@ class MetaReferenceAgentsImpl(Agents):
yield event
async def get_agents_turn(self, agent_id: str, session_id: str, turn_id: str) -> Turn:
- turn = await self.persistence_store.get(f"session:{agent_id}:{session_id}:{turn_id}")
- turn = json.loads(turn)
- turn = Turn(**turn)
- return turn
+ pass
+ # turn = await self.persistence_store.get(f"session:{agent_id}:{session_id}:{turn_id}")
+ # turn = json.loads(turn)
+ # turn = Turn(**turn)
+ # return turn
async def get_agents_step(self, agent_id: str, session_id: str, turn_id: str, step_id: str) -> AgentStepResponse:
- turn = await self.persistence_store.get(f"session:{agent_id}:{session_id}:{turn_id}")
- turn = json.loads(turn)
- turn = Turn(**turn)
- steps = turn.steps
- for step in steps:
- if step.step_id == step_id:
- return AgentStepResponse(step=step)
- raise ValueError(f"Provided step_id {step_id} could not be found")
+ pass
+ # turn = await self.persistence_store.get(f"session:{agent_id}:{session_id}:{turn_id}")
+ # turn = json.loads(turn)
+ # turn = Turn(**turn)
+ # steps = turn.steps
+ # for step in steps:
+ # if step.step_id == step_id:
+ # return AgentStepResponse(step=step)
+ # raise ValueError(f"Provided step_id {step_id} could not be found")
async def get_agents_session(
self,
@@ -215,20 +217,17 @@ class MetaReferenceAgentsImpl(Agents):
session_id: str,
turn_ids: Optional[List[str]] = None,
) -> Session:
- session = await self.persistence_store.get(f"session:{agent_id}:{session_id}")
- session = Session(**json.loads(session), turns=[])
- turns = []
+ agent = await self.get_agent(agent_id)
+ session_info = await agent.storage.get_session_info(session_id)
+ print(session_info)
+ turns = await agent.storage.get_session_turns(session_id)
if turn_ids:
- for turn_id in turn_ids:
- turn = await self.persistence_store.get(f"session:{agent_id}:{session_id}:{turn_id}")
- turn = json.loads(turn)
- turn = Turn(**turn)
- turns.append(turn)
+ turns = [turn for turn in turns if turn.turn_id in turn_ids]
return Session(
- session_name=session.session_name,
+ session_name=session_info.session_name,
session_id=session_id,
- turns=turns if turns else [],
- started_at=session.started_at,
+ turns=turns,
+ started_at=session_info.started_at,
)
async def delete_agents_session(self, agent_id: str, session_id: str) -> None:
diff --git a/llama_stack/providers/inline/agents/meta_reference/persistence.py b/llama_stack/providers/inline/agents/meta_reference/persistence.py
index 3c3866873..94b7cbf42 100644
--- a/llama_stack/providers/inline/agents/meta_reference/persistence.py
+++ b/llama_stack/providers/inline/agents/meta_reference/persistence.py
@@ -21,6 +21,7 @@ log = logging.getLogger(__name__)
class AgentSessionInfo(BaseModel):
session_id: str
session_name: str
+ # TODO: is this used anywhere?
vector_db_id: Optional[str] = None
started_at: datetime
@@ -31,6 +32,7 @@ class AgentPersistence:
self.kvstore = kvstore
async def create_session(self, name: str) -> str:
+ print("CREATE SESSION PERSISTANCE", name)
session_id = str(uuid.uuid4())
session_info = AgentSessionInfo(
session_id=session_id,