> For the complete documentation index, see [llms.txt](https://dnotifier.gitbook.io/product-docs/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://dnotifier.gitbook.io/product-docs/appendix/changelog/changelog-python.md).

# Python SDK

Release notes for [dnotifier](https://pypi.org/project/dnotifier/) on PyPI.

{% hint style="info" %}
Install the latest version with `pip install dnotifier`. Pin a specific version for reproducible builds: `pip install dnotifier==1.0.10`.
{% endhint %}

Cross-SDK feature table: [Changelog](https://dnotifier.gitbook.io/product-docs/appendix/changelog.md).

***

## 1.0.10

### Listen / MCP / A2A checkpoint resume

* Remote invokes on a listening agent accept `sessionId`, `state`, `resume` / `mode`, and `fromCheckpointId`.
* The host resumes from that checkpoint (merging any provided `state`) and returns session / checkpoint ids on the result when available.

→ [Checkpoints, sessions & resume](https://dnotifier.gitbook.io/product-docs/workflows-and-agents/checkpoints.md) · [Serve agents over MCP](https://dnotifier.gitbook.io/product-docs/workflows-and-agents/mcp-server.md) · [A2A](https://dnotifier.gitbook.io/product-docs/workflows-and-agents/a2a.md)

***

## 1.0.9

### Checkpoints, sessions & resume

* Pass `session_id` on `run_agent` / `run_workflow` to keep conversation and workflow state across turns.
* Resume, retry, or replay a run with `resume`, `mode`, and optional `from_checkpoint_id`.
* Optional in-memory checkpointer for local tests; cloud storage when you pass a `session_id`.

→ [Checkpoints, sessions & resume](https://dnotifier.gitbook.io/product-docs/workflows-and-agents/checkpoints.md) · [Python examples](https://dnotifier.gitbook.io/product-docs/workflows-and-agents/checkpoints/python.md)

***

## 1.0.8

### Middleware

* Agent middleware: hooks around the full run and around model / tool steps (`before_agent`, `after_agent`, `before_model`, `after_model`, `wrap_model_call`, `before_tool`, `after_tool`, `wrap_tool_call`, `on_error`).
* Workflow middleware: hooks around `entry` (`before_workflow`, `after_workflow`, `on_error`, `on_complete`).
* Register with `middleware` on `define_agent` or `Workflow` (snake\_case preferred; camelCase accepted).

→ [Middleware](https://dnotifier.gitbook.io/product-docs/workflows-and-agents/middleware.md) · [Python examples](https://dnotifier.gitbook.io/product-docs/workflows-and-agents/middleware/python.md)

***

## 1.0.7

### MCP server capability

* `capabilities={"mcpServer": True}` on agents and workflows.
* Listen so Claude, Cursor, and other MCP clients can discover and call your agent through DNotifier.

→ [Serve agents over MCP](https://dnotifier.gitbook.io/product-docs/workflows-and-agents/mcp-server.md)

### A2A capability

* `capabilities={"a2a": True}` on agents and workflows.
* Expose agents over the open Agent2Agent protocol (Agent Card + JSON-RPC).

→ [Agent-to-agent (A2A)](https://dnotifier.gitbook.io/product-docs/workflows-and-agents/a2a.md)

### Capabilities

* Declare what an agent or workflow supports: `mcpServer`, `a2a`, `tools`, `rag`, `memory`, `workflows`, `humanApproval`, `subagents`.

→ [Define an agent](https://dnotifier.gitbook.io/product-docs/workflows-and-agents/define-agent.md)

***

## 1.0.5

### Vector stores & embeddings

* Choose knowledge-base storage and embedding model via `server_config` or per call (`vector_store` / `embedding`).

→ [Vector stores and embeddings](https://dnotifier.gitbook.io/product-docs/ai/vector-stores.md)

***

## 1.0.3

### Agent tools & MCP client

* `notifier.tools.register` for local tools; `notifier.mcp.connect` for HTTP MCP servers.
* Tool agents via `define_agent(..., tools=..., instructions=..., permissions=...)`.
* Standalone `notifier.run_agent(agent, input=...)` for tool agents.
* `permission_enforcement` and `on_agent_event` constructor options.
* Workflow observability records tool-agent runs in the dashboard.

→ [Tools & MCP agents](https://dnotifier.gitbook.io/product-docs/workflows-and-agents/tools-and-mcp.md) · [Local tool example](https://dnotifier.gitbook.io/product-docs/workflows-and-agents/example-tool-agent.md) · [MCP example](https://dnotifier.gitbook.io/product-docs/workflows-and-agents/example-mcp-agent.md)

### Multi-model providers

* Pass `provider` and `model` on `send_ai` and agent defaults.

→ [Multi-model providers](https://dnotifier.gitbook.io/product-docs/ai/multi-models.md)

### License

* Package license remains proprietary (`LICENSE` + `pyproject.toml`).

***

## 1.0.2

### Remote agents

* Register a remote agent by `receiver_id` on a workflow and call it with `ctx.run_agent` the same way as a local agent.
* Requires WebSocket transport for request/reply across servers.

→ [Remote agents](https://dnotifier.gitbook.io/product-docs/workflows-and-agents/remote-agents.md)

***

## 1.0.0

### Initial release

* Async-first Python SDK with parity to JavaScript and Dart packages.
* WebSocket and HTTP transports.
* Realtime 1:1 messaging with automatic chunking and reassembly.
* Chat history: `fetch_chat_history`, `delete_chat_history_message`.
* AI: `send_ai`, sessions via `session_id`, AI history fetch/delete.
* Knowledge base (RAG): document CRUD, semantic `search`.
* Workflows: `define_agent`, `Workflow`, `WorkflowContext`, `run_workflow`.
* Optional workflow observability when `observability=True`.
* Session logging with `logs=True`.

→ [Install — Python](https://dnotifier.gitbook.io/product-docs/getting-started/installation/python.md)\
→ [Workflows overview](https://dnotifier.gitbook.io/product-docs/workflows-and-agents/overview.md)

### Requirements

* Python 3.9+
* Dependencies: `httpx`, `websockets`

***

## Related

* [Changelog](https://dnotifier.gitbook.io/product-docs/appendix/changelog.md)
* [Changelog — JavaScript SDK](https://dnotifier.gitbook.io/product-docs/appendix/changelog/changelog-javascript.md)
* [Changelog — Dart SDK](https://dnotifier.gitbook.io/product-docs/appendix/changelog/changelog-dart.md)
* [Support & links](https://dnotifier.gitbook.io/product-docs/appendix/support.md)
