Files
codex/codex-rs/core/src/tools/context.rs
T
Michael Bolin 66447d5d2c feat: replace custom mcp-types crate with equivalents from rmcp (#10349)
We started working with MCP in Codex before
https://crates.io/crates/rmcp was mature, so we had our own crate for
MCP types that was generated from the MCP schema:


https://github.com/openai/codex/blob/8b95d3e082376f4cb23e92641705a22afb28a9da/codex-rs/mcp-types/README.md

Now that `rmcp` is more mature, it makes more sense to use their MCP
types in Rust, as they handle details (like the `_meta` field) that our
custom version ignored. Though one advantage that our custom types had
is that our generated types implemented `JsonSchema` and `ts_rs::TS`,
whereas the types in `rmcp` do not. As such, part of the work of this PR
is leveraging the adapters between `rmcp` types and the serializable
types that are API for us (app server and MCP) introduced in #10356.

Note this PR results in a number of changes to
`codex-rs/app-server-protocol/schema`, which merit special attention
during review. We must ensure that these changes are still
backwards-compatible, which is possible because we have:

```diff
- export type CallToolResult = { content: Array<ContentBlock>, isError?: boolean, structuredContent?: JsonValue, };
+ export type CallToolResult = { content: Array<JsonValue>, structuredContent?: JsonValue, isError?: boolean, _meta?: JsonValue, };
```

so `ContentBlock` has been replaced with the more general `JsonValue`.
Note that `ContentBlock` was defined as:

```typescript
export type ContentBlock = TextContent | ImageContent | AudioContent | ResourceLink | EmbeddedResource;
```

so the deletion of those individual variants should not be a cause of
great concern.

Similarly, we have the following change in
`codex-rs/app-server-protocol/schema/typescript/Tool.ts`:

```
- export type Tool = { annotations?: ToolAnnotations, description?: string, inputSchema: ToolInputSchema, name: string, outputSchema?: ToolOutputSchema, title?: string, };
+ export type Tool = { name: string, title?: string, description?: string, inputSchema: JsonValue, outputSchema?: JsonValue, annotations?: JsonValue, icons?: Array<JsonValue>, _meta?: JsonValue, };
```

so:

- `annotations?: ToolAnnotations` ➡️ `JsonValue`
- `inputSchema: ToolInputSchema` ➡️ `JsonValue`
- `outputSchema?: ToolOutputSchema` ➡️ `JsonValue`

and two new fields: `icons?: Array<JsonValue>, _meta?: JsonValue`

---
[//]: # (BEGIN SAPLING FOOTER)
Stack created with [Sapling](https://sapling-scm.com). Best reviewed
with [ReviewStack](https://reviewstack.dev/openai/codex/pull/10349).
* #10357
* __->__ #10349
* #10356
2026-02-02 17:41:55 -08:00

239 lines
7.2 KiB
Rust

use crate::codex::Session;
use crate::codex::TurnContext;
use crate::tools::TELEMETRY_PREVIEW_MAX_BYTES;
use crate::tools::TELEMETRY_PREVIEW_MAX_LINES;
use crate::tools::TELEMETRY_PREVIEW_TRUNCATION_NOTICE;
use crate::turn_diff_tracker::TurnDiffTracker;
use codex_protocol::mcp::CallToolResult;
use codex_protocol::models::FunctionCallOutputContentItem;
use codex_protocol::models::FunctionCallOutputPayload;
use codex_protocol::models::ResponseInputItem;
use codex_protocol::models::ShellToolCallParams;
use codex_utils_string::take_bytes_at_char_boundary;
use std::borrow::Cow;
use std::sync::Arc;
use tokio::sync::Mutex;
pub type SharedTurnDiffTracker = Arc<Mutex<TurnDiffTracker>>;
#[derive(Clone)]
pub struct ToolInvocation {
pub session: Arc<Session>,
pub turn: Arc<TurnContext>,
pub tracker: SharedTurnDiffTracker,
pub call_id: String,
pub tool_name: String,
pub payload: ToolPayload,
}
#[derive(Clone, Debug)]
pub enum ToolPayload {
Function {
arguments: String,
},
Custom {
input: String,
},
LocalShell {
params: ShellToolCallParams,
},
Mcp {
server: String,
tool: String,
raw_arguments: String,
},
}
impl ToolPayload {
pub fn log_payload(&self) -> Cow<'_, str> {
match self {
ToolPayload::Function { arguments } => Cow::Borrowed(arguments),
ToolPayload::Custom { input } => Cow::Borrowed(input),
ToolPayload::LocalShell { params } => Cow::Owned(params.command.join(" ")),
ToolPayload::Mcp { raw_arguments, .. } => Cow::Borrowed(raw_arguments),
}
}
}
#[derive(Clone)]
pub enum ToolOutput {
Function {
// Plain text representation of the tool output.
content: String,
// Some tool calls such as MCP calls may return structured content that can get parsed into an array of polymorphic content items.
content_items: Option<Vec<FunctionCallOutputContentItem>>,
success: Option<bool>,
},
Mcp {
result: Result<CallToolResult, String>,
},
}
impl ToolOutput {
pub fn log_preview(&self) -> String {
match self {
ToolOutput::Function { content, .. } => telemetry_preview(content),
ToolOutput::Mcp { result } => format!("{result:?}"),
}
}
pub fn success_for_logging(&self) -> bool {
match self {
ToolOutput::Function { success, .. } => success.unwrap_or(true),
ToolOutput::Mcp { result } => result.is_ok(),
}
}
pub fn into_response(self, call_id: &str, payload: &ToolPayload) -> ResponseInputItem {
match self {
ToolOutput::Function {
content,
content_items,
success,
} => {
if matches!(payload, ToolPayload::Custom { .. }) {
ResponseInputItem::CustomToolCallOutput {
call_id: call_id.to_string(),
output: content,
}
} else {
ResponseInputItem::FunctionCallOutput {
call_id: call_id.to_string(),
output: FunctionCallOutputPayload {
content,
content_items,
success,
},
}
}
}
ToolOutput::Mcp { result } => ResponseInputItem::McpToolCallOutput {
call_id: call_id.to_string(),
result,
},
}
}
}
fn telemetry_preview(content: &str) -> String {
let truncated_slice = take_bytes_at_char_boundary(content, TELEMETRY_PREVIEW_MAX_BYTES);
let truncated_by_bytes = truncated_slice.len() < content.len();
let mut preview = String::new();
let mut lines_iter = truncated_slice.lines();
for idx in 0..TELEMETRY_PREVIEW_MAX_LINES {
match lines_iter.next() {
Some(line) => {
if idx > 0 {
preview.push('\n');
}
preview.push_str(line);
}
None => break,
}
}
let truncated_by_lines = lines_iter.next().is_some();
if !truncated_by_bytes && !truncated_by_lines {
return content.to_string();
}
if preview.len() < truncated_slice.len()
&& truncated_slice
.as_bytes()
.get(preview.len())
.is_some_and(|byte| *byte == b'\n')
{
preview.push('\n');
}
if !preview.is_empty() && !preview.ends_with('\n') {
preview.push('\n');
}
preview.push_str(TELEMETRY_PREVIEW_TRUNCATION_NOTICE);
preview
}
#[cfg(test)]
mod tests {
use super::*;
use pretty_assertions::assert_eq;
#[test]
fn custom_tool_calls_should_roundtrip_as_custom_outputs() {
let payload = ToolPayload::Custom {
input: "patch".to_string(),
};
let response = ToolOutput::Function {
content: "patched".to_string(),
content_items: None,
success: Some(true),
}
.into_response("call-42", &payload);
match response {
ResponseInputItem::CustomToolCallOutput { call_id, output } => {
assert_eq!(call_id, "call-42");
assert_eq!(output, "patched");
}
other => panic!("expected CustomToolCallOutput, got {other:?}"),
}
}
#[test]
fn function_payloads_remain_function_outputs() {
let payload = ToolPayload::Function {
arguments: "{}".to_string(),
};
let response = ToolOutput::Function {
content: "ok".to_string(),
content_items: None,
success: Some(true),
}
.into_response("fn-1", &payload);
match response {
ResponseInputItem::FunctionCallOutput { call_id, output } => {
assert_eq!(call_id, "fn-1");
assert_eq!(output.content, "ok");
assert!(output.content_items.is_none());
assert_eq!(output.success, Some(true));
}
other => panic!("expected FunctionCallOutput, got {other:?}"),
}
}
#[test]
fn telemetry_preview_returns_original_within_limits() {
let content = "short output";
assert_eq!(telemetry_preview(content), content);
}
#[test]
fn telemetry_preview_truncates_by_bytes() {
let content = "x".repeat(TELEMETRY_PREVIEW_MAX_BYTES + 8);
let preview = telemetry_preview(&content);
assert!(preview.contains(TELEMETRY_PREVIEW_TRUNCATION_NOTICE));
assert!(
preview.len()
<= TELEMETRY_PREVIEW_MAX_BYTES + TELEMETRY_PREVIEW_TRUNCATION_NOTICE.len() + 1
);
}
#[test]
fn telemetry_preview_truncates_by_lines() {
let content = (0..(TELEMETRY_PREVIEW_MAX_LINES + 5))
.map(|idx| format!("line {idx}"))
.collect::<Vec<_>>()
.join("\n");
let preview = telemetry_preview(&content);
let lines: Vec<&str> = preview.lines().collect();
assert!(lines.len() <= TELEMETRY_PREVIEW_MAX_LINES + 1);
assert_eq!(lines.last(), Some(&TELEMETRY_PREVIEW_TRUNCATION_NOTICE));
}
}