microsoft / microsoft/fabric_data_agent_client

Conversation history is not being passed between calls with the same thread.

Open
#13 0 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

Dominant language
Python
Stars
36
Forks
17
PR merge metrics
No merged PRs in 30d

Description

With the code below I call the dataagent twice with the same thread name. but the data agent is unavare of the privious call:

🔐 Starting authentication...
A browser window will open for you to sign in to your Microsoft account.
🔄 Refreshing authentication token...
✅ Token obtained, expires at: Mon Dec 8 13:43:23 2025
✅ Authentication successful!

Asking: What is the temp in my spa
⏳ Status: queued
⏳ Status: in_progress
✅ Final status: completed
Answer: The current temperature in your spa is 39°C, based on the latest available data.

Asking: *What did I ask about before?
⏳ Status: queued
✅ Final status: completed
Answer: I don’t have access to previous conversation history in this session, so I can’t see what you asked about before. If you let me know your earlier question or topic, I can help you continue from there!

`
import os
import uuid

from dotenv import load_dotenv

from fabric_data_agent_client import FabricDataAgentClient

--------- Config & client setup ----------

load_dotenv() # reads TENANT_ID and DATA_AGENT_URL from .env

TENANT_ID = os.getenv("TENANT_ID")
DATA_AGENT_URL = os.getenv("DATA_AGENT_URL")

def get_client():
# On first use, this will open a browser window for interactive login.
return FabricDataAgentClient(
tenant_id=TENANT_ID,
data_agent_url=DATA_AGENT_URL,
)

client = get_client()

thread_name = "data_session" # fixed thread name for testing

answer = client.ask(
"What is the temp in my spa",
thread_name=thread_name, # keep context
)
print("Answer:", answer)

answer = client.ask(
"*What did I ask about before?",
thread_name=thread_name, # keep context
)
print("Answer:", answer)

--------- End ----------

`

Contributor guide

No contributing guide indexed for this repository

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

Research direction

Start by reproducing the inline Python example with FabricDataAgentClient.ask and the same thread_name value on both calls. Trace how thread_name is handled between requests. Done means the second question can access the first question's conversation history, or the issue clearly documents why that is not supported.

Written by the indexing model from the issue text.

Assessment

Tech stack
python
Domain
api, backend
Issue type
Bug
Difficulty
3/5
Estimated time
1-2 days
Activity status
Stale
Clarity
Mostly clear
Newbie friendliness
45/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.