Deep Research Multi-turn (Interactions)

Continue a Deep Research interaction across turns. Each response carries an interaction_id; the next turn references it via previous_interaction_id so only the new user message is sent on the wire. The server already has the prior research and its citations.

Persisting the interaction ID requires a database. The assistant message stores it under provider_data, and the next turn reads it back.

Code

1from kern.agent import Agent
2from kern.db.sqlite import SqliteDb
3from kern.models.google import GeminiInteractions
4
5agent = Agent(
6    model=GeminiInteractions(
7        agent="deep-research-preview-04-2026",
8        thinking_summaries="auto",
9    ),
10    add_history_to_context=True,
11    db=SqliteDb(db_file="tmp/data.db"),
12    markdown=True,
13)
14
15if __name__ == "__main__":
16    agent.print_response(
17        "Research the current state of solid-state battery commercialization "
18        "and summarize the leading approaches."
19    )
20
21    agent.print_response(
22        "Dive deeper into the sulfide-electrolyte approach: who the leading "
23        "labs and companies are, and what their reported milestones look like."
24    )
25
26    agent.print_response(
27        "Based on everything we've covered, which approach has the clearest "
28        "path to mass-market EV deployment in the next five years?"
29    )

Usage

Set up your virtual environment

1uv venv --python 3.12
2source .venv/bin/activate

1uv venv --python 3.12
2.venv\Scripts\activate

Set your API key

1export GOOGLE_API_KEY=xxx

Install dependencies

1uv pip install -U "google-genai>=2.0" kern-ai

Run Agent

1python cookbook/90_models/google/gemini_interactions/deep_research_multi_turn.py