Commit graph

6 commits

Author SHA1 Message Date
Bennet Bo Fenner
6801b9137f
context_server: Make notifications type safe (#32396)
Follow up to #32254 

Release Notes:

- N/A
2025-06-09 15:11:01 +00:00
Bennet Bo Fenner
4ff41ba62e
context_server: Update types to reflect latest protocol version (2025-03-26) (#32377)
This updates the `types.rs` file to reflect the latest version of the
MCP spec. Next up is making use of some of these new capabilities. Would
also be great to add support for [Streamable HTTP
Transport](https://modelcontextprotocol.io/specification/2025-03-26/basic/transports#streamable-http)

Release Notes:

- N/A
2025-06-09 13:03:47 +02:00
Bennet Bo Fenner
95d78ff8d5
context server: Make requests type safe (#32254)
This changes the context server crate so that the input/output for a
request are encoded at the type level, similar to how it is done for LSP
requests.

This also makes it easier to write tests that mock context servers, e.g.
you can write something like this now when using the `test-support`
feature of the `context-server` crate:

```rust
create_fake_transport("mcp-1", cx.background_executor())
    .on_request::<context_server::types::request::PromptsList>(|_params| {
        PromptsListResponse {
            prompts: vec![/* some prompts */],
            ..
        }
    })
```

Release Notes:

- N/A
2025-06-06 17:47:21 +02:00
Kirill Bulatov
16366cf9f2
Use anyhow more idiomatically (#31052)
https://github.com/zed-industries/zed/issues/30972 brought up another
case where our context is not enough to track the actual source of the
issue: we get a general top-level error without inner error.

The reason for this was `.ok_or_else(|| anyhow!("failed to read HEAD
SHA"))?; ` on the top level.

The PR finally reworks the way we use anyhow to reduce such issues (or
at least make it simpler to bubble them up later in a fix).
On top of that, uses a few more anyhow methods for better readability.

* `.ok_or_else(|| anyhow!("..."))`, `map_err` and other similar error
conversion/option reporting cases are replaced with `context` and
`with_context` calls
* in addition to that, various `anyhow!("failed to do ...")` are
stripped with `.context("Doing ...")` messages instead to remove the
parasitic `failed to` text
* `anyhow::ensure!` is used instead of `if ... { return Err(...); }`
calls
* `anyhow::bail!` is used instead of `return Err(anyhow!(...));`

Release Notes:

- N/A
2025-05-20 23:06:07 +00:00
Bennet Bo Fenner
9cb5ffac25
context_store: Refactor state management (#29910)
Because we instantiated `ContextServerManager` both in `agent` and
`assistant-context-editor`, and these two entities track the running MCP
servers separately, we were effectively running every MCP server twice.

This PR moves the `ContextServerManager` into the project crate (now
called `ContextServerStore`). The store can be accessed via a project
instance. This ensures that we only instantiate one `ContextServerStore`
per project.

Also, this PR adds a bunch of tests to ensure that the
`ContextServerStore` behaves correctly (Previously there were none).

Closes #28714
Closes #29530

Release Notes:

- N/A
2025-05-05 21:36:12 +02:00
Marshall Bowers
3901d46101
Factor tool definitions out of assistant (#21189)
This PR factors the tool definitions out of the `assistant` crate so
that they can be shared between `assistant` and `assistant2`.

`ToolWorkingSet` now lives in `assistant_tool`. The tool definitions
themselves live in `assistant_tools`, with the exception of the
`ContextServerTool`, which has been moved to the `context_server` crate.

As part of this refactoring I needed to extract the
`ContextServerSettings` to a separate `context_server_settings` crate so
that the `extension_host`—which is referenced by the `remote_server`—can
name the `ContextServerSettings` type without pulling in some undesired
dependencies.

Release Notes:

- N/A
2024-11-25 18:26:34 -05:00
Renamed from crates/context_servers/src/protocol.rs (Browse further)