> For the complete documentation index, see [llms.txt](https://docs.nansen.ai/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.nansen.ai/api/changelog/05-10-2026-agent-conversation-id.md).

# 05-10-2026: Agent Endpoints Return a Usable conversation\_id

`POST /api/v1/agent/fast` and `POST /api/v1/agent/expert` stream a final `finish` event that carries a `conversation_id`. You send that value back on your next request to continue the same conversation.

Until now `conversation_id` was only ever the value you had sent yourself, so it was `null` whenever you started a new conversation. There was no way to learn the identifier of a conversation you had just started, which meant follow-up turns were not reachable.

The `finish` event now always carries the identifier of the conversation the request belongs to:

```
data: {"type": "finish", "conversation_id": "9f2c1b7e4a8d4f0b9c3e5a1d7b6f2e80", "tool_calls": ["token_ohlcv"]}
```

What this means for your requests:

* Omit `conversation_id` to start a new conversation, as before. The `finish` event now tells you the identifier that was created for it.
* Send that identifier as `conversation_id` on a later request to continue the conversation. The agent sees the earlier turns.
* Requests that already send a `conversation_id` are unchanged. The `finish` event reports the same value you sent.
* Each request is charged at the endpoint's normal credit cost, including follow-up turns in an existing conversation.

If your client reads `conversation_id` and expects `null` on a first turn, update it to accept a string.


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation by asking a question.

Perform an HTTP GET request on the following URL with the `ask` and `goal` query parameters:

```
GET https://docs.nansen.ai/api/changelog/05-10-2026-agent-conversation-id.md?ask=<question>&goal=<user_goal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is what the user is ultimately trying to achieve, the reason they need the answer. Sharing it helps GitBook give you a better, more relevant answer. A goal is most helpful when it describes the outcome the user wants rather than restating the question. For example, with `ask=how do I create an API token`, a goal like `automate deployments from our CI pipeline` lets GitBook tailor the answer to that use case.

The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.