add deep agent

[ks6088ts]

What this PR does / why we need it

• add deep agent

Which issue(s) this PR fixes:

Fixes #86

Does this introduce a breaking change?

[ ] Yes
[x] No

Pull Request Type

What kind of change does this Pull Request introduce?

[ ] Bugfix
[x] Feature
[ ] Code style update (formatting, local variables)
[ ] Refactoring (no functional changes, no api changes)
[ ] Documentation content changes
[ ] Other... Please describe:

How to Test

• Get the code

ORGANIZATION=<organization-name>
REPOSITORY=<repository-name>

git clone [email protected]:$ORGANIZATION/$REPOSITORY.git
cd $REPOSITORY

• Test the code

make ci-test

What to Check

Verify that the following are valid

• ...

Additional Information

[Copilot]

Pull Request Overview

This PR adds a new "deep agent" capability to the template, which provides a sophisticated research agent framework with sub-agent orchestration, file management, and task tracking features. The implementation is based on the langchain-ai/deepagents project.

Key changes:

• Adds a complete deep agent core framework with state management, tools, and sub-agent coordination
• Implements a research-focused agent that can conduct thorough research and generate detailed reports
• Integrates the new agent into the LangGraph configuration for deployment

Reviewed Changes

Copilot reviewed 9 out of 9 changed files in this pull request and generated 2 comments.

File	Description
template_langgraph/agents/demo_agents/research_deep_agent.py	Main entry point defining research and critique sub-agents with detailed prompts
template_langgraph/agents/demo_agents/deep_agent_core/	Core framework providing state management, tools, and agent orchestration
langgraph.json	Registers the new deep agent in the application configuration
docs/references.md	Adds documentation references to the deep agents project

Comments suppressed due to low confidence (1)

template_langgraph/agents/demo_agents/deep_agent_core/tools.py:14

• The parameter names 'l' and 'r' are ambiguous single-letter variables. Consider renaming to 'left' and 'right' or 'current' and 'new' for better readability.

from template_langgraph.agents.demo_agents.deep_agent_core.state import DeepAgentState, Todo

---

_{Tip: Customize your code reviews with copilot-instructions.md. Create the file or learn how to get started.}

[Copilot]

There is a spelling error in 'infomration'. It should be 'information'.

Suggested change

	"description": "Used to critique the final report. Give this agent some infomration about how you want it to critique the report.",
	"description": "Used to critique the final report. Give this agent some information about how you want it to critique the report.",

[Copilot]

There is a typo in the docstring: 'deep_agent_coretate' should be 'deep_agent_core.state'.

Suggested change

	state_schema: The schema of the deep agent. Should subclass from template_langgraph.agents.demo_agents.deep_agent_coretate
	state_schema: The schema of the deep agent. Should subclass from template_langgraph.agents.demo_agents.deep_agent_core.state

[ks6088ts]

ref.

• 1. https://www.youtube.com/watch?v=ALCHslbskXM
• 2. final output: https://www.youtube.com/watch?v=-pW9IXuOwAM