This PR exposes context server settings to extensions.
Extensions can use `ContextServerSettings::for_project` to get the
context server settings for the current project.
The `experimental.context_servers` setting has been removed and replaced
with the `context_servers` setting (which is now an object instead of an
array).
Release Notes:
- N/A
---------
Co-authored-by: Max Brunsfeld <maxbrunsfeld@gmail.com>
There are two issues with too/list and prompt/list at the moment. We
serialize params to `null`, which is not correct according to
context_server spec. While it IS allowed by JSON RPC spec to omit
params, it turns out some servers currently missbehave and don't respect
this. So we do two things
- We omit params if it would be a null value in json.
- We explicitly set params to {} for tool/list and prompt/list to avoid
it being omitted.
Release Notes:
- N/A
This PR does two things. It fixes some minor inconsistencies in the
protocol. This is mostly about handling JSON RPC notifications correctly
and skipping fields when set to None.
Second part is about improving the rendering of context server commands,
by passing on the description
of the command to the slash command UI and showing the name of the
argument as a CodeLabel.
Release Notes:
- N/A
This commit proposes the addition of "context serveres" and the
underlying protocol (model context protocol). Context servers allow
simple definition of slash commands in another language and running
local on the user machines. This aims to quickly prototype new commands,
and provide a way to add personal (or company wide) customizations to
the assistant panel, without having to maintain an extension. We can
use this to reuse our existing codebase, with authenticators, etc and
easily have it provide context into the assistant panel.
As such it occupies a different design space as extensions, which I
think are
more aimed towards long-term, well maintained pieces of code that can be
easily distributed.
It's implemented as a central crate for easy reusability across the
codebase
and to easily hook into the assistant panel at all points.
Design wise there are a few pieces:
1. client.rs: A simple JSON-RPC client talking over stdio to a spawned
server. This is
very close to how LSP work and likely there could be a combined client
down the line.
2. types.rs: Serialization and deserialization client for the underlying
model context protocol.
3. protocol.rs: Handling the session between client and server.
4. manager.rs: Manages settings and adding and deleting servers from a
central pool.
A server can be defined in the settings.json as:
```
"context_servers": [
{"id": "test", "executable": "python", "args": ["-m", "context_server"]
]
```
## Quick Example
A quick example of how a theoretical backend site can look like. With
roughly 100 lines
of code (nicely generated by Claude) and a bit of decorator magic (200
lines in total), one
can come up with a framework that makes it as easy as:
```python
@context_server.slash_command(name="rot13", description="Perform a rot13 transformation")
@context_server.argument(name="input", type=str, help="String to rot13")
async def rot13(input: str) -> str:
return ''.join(chr((ord(c) - 97 + 13) % 26 + 97) if c.isalpha() else c for c in echo.lower())
```
to define a new slash_command.
## Todo:
- Allow context servers to be defined in workspace settings.
- Allow passing env variables to context_servers
Release Notes:
- N/A
---------
Co-authored-by: Marshall Bowers <elliott.codes@gmail.com>
张小白
David Soria ParraandMarshall Bowers
Piotr Osiewicz