Merge 03f6dda330 into sapling-pr-archive-bolinfest

This commit is contained in:
Michael Bolin
2026-03-26 19:59:07 -07:00
committed by GitHub
14 changed files with 347 additions and 222 deletions

View File

@@ -86,9 +86,9 @@ jobs:
with:
path: |
~/.cache/bazel-repo-cache
key: bazel-cache-${{ matrix.os }}-${{ hashFiles('MODULE.bazel', 'codex-rs/Cargo.lock', 'codex-rs/Cargo.toml') }}
key: bazel-cache-${{ matrix.target }}-${{ hashFiles('MODULE.bazel', 'codex-rs/Cargo.lock', 'codex-rs/Cargo.toml') }}
restore-keys: |
bazel-cache-${{ matrix.os }}
bazel-cache-${{ matrix.target }}
- name: Configure Bazel startup args (Windows)
if: runner.os == 'Windows'
@@ -230,4 +230,4 @@ jobs:
with:
path: |
~/.cache/bazel-repo-cache
key: bazel-cache-${{ matrix.os }}-${{ hashFiles('MODULE.bazel', 'codex-rs/Cargo.lock', 'codex-rs/Cargo.toml') }}
key: bazel-cache-${{ matrix.target }}-${{ hashFiles('MODULE.bazel', 'codex-rs/Cargo.lock', 'codex-rs/Cargo.toml') }}

2
codex-rs/Cargo.lock generated
View File

@@ -2632,7 +2632,9 @@ dependencies = [
name = "codex-tools"
version = "0.0.0"
dependencies = [
"codex-protocol",
"pretty_assertions",
"rmcp",
"serde",
"serde_json",
]

View File

@@ -46,7 +46,8 @@ use codex_protocol::openai_models::WebSearchToolType;
use codex_protocol::protocol::SandboxPolicy;
use codex_protocol::protocol::SessionSource;
use codex_protocol::protocol::SubAgentSource;
pub use codex_tools::parse_tool_input_schema;
use codex_tools::parse_dynamic_tool;
use codex_tools::parse_mcp_tool;
use codex_utils_absolute_path::AbsolutePathBuf;
use serde::Deserialize;
use serde::Serialize;
@@ -58,6 +59,9 @@ use std::path::PathBuf;
pub type JsonSchema = codex_tools::JsonSchema;
#[cfg(test)]
pub(crate) use codex_tools::mcp_call_tool_result_output_schema;
const TOOL_SEARCH_DESCRIPTION_TEMPLATE: &str =
include_str!("../../templates/search_tool/tool_description.md");
const TOOL_SUGGEST_DESCRIPTION_TEMPLATE: &str =
@@ -2362,15 +2366,15 @@ pub(crate) fn mcp_tool_to_openai_tool(
fully_qualified_name: String,
tool: rmcp::model::Tool,
) -> Result<ResponsesApiTool, serde_json::Error> {
let (description, input_schema, output_schema) = mcp_tool_to_openai_tool_parts(tool)?;
let parsed_tool = parse_mcp_tool(&tool)?;
Ok(ResponsesApiTool {
name: fully_qualified_name,
description,
description: parsed_tool.description,
strict: false,
defer_loading: None,
parameters: input_schema,
output_schema,
parameters: parsed_tool.input_schema,
output_schema: Some(parsed_tool.output_schema),
})
}
@@ -2378,14 +2382,14 @@ pub(crate) fn mcp_tool_to_deferred_openai_tool(
name: String,
tool: rmcp::model::Tool,
) -> Result<ResponsesApiTool, serde_json::Error> {
let (description, input_schema, _) = mcp_tool_to_openai_tool_parts(tool)?;
let parsed_tool = parse_mcp_tool(&tool)?;
Ok(ResponsesApiTool {
name,
description,
description: parsed_tool.description,
strict: false,
defer_loading: Some(true),
parameters: input_schema,
parameters: parsed_tool.input_schema,
output_schema: None,
})
}
@@ -2393,73 +2397,18 @@ pub(crate) fn mcp_tool_to_deferred_openai_tool(
fn dynamic_tool_to_openai_tool(
tool: &DynamicToolSpec,
) -> Result<ResponsesApiTool, serde_json::Error> {
let input_schema = parse_tool_input_schema(&tool.input_schema)?;
let parsed_tool = parse_dynamic_tool(tool)?;
Ok(ResponsesApiTool {
name: tool.name.clone(),
description: tool.description.clone(),
description: parsed_tool.description,
strict: false,
defer_loading: None,
parameters: input_schema,
defer_loading: parsed_tool.defer_loading.then_some(true),
parameters: parsed_tool.input_schema,
output_schema: None,
})
}
fn mcp_tool_to_openai_tool_parts(
tool: rmcp::model::Tool,
) -> Result<(String, JsonSchema, Option<JsonValue>), serde_json::Error> {
let rmcp::model::Tool {
description,
input_schema,
output_schema,
..
} = tool;
let mut serialized_input_schema = serde_json::Value::Object(input_schema.as_ref().clone());
// OpenAI models mandate the "properties" field in the schema. Some MCP
// servers omit it (or set it to null), so we insert an empty object to
// match the behavior of the Agents SDK.
if let serde_json::Value::Object(obj) = &mut serialized_input_schema
&& obj.get("properties").is_none_or(serde_json::Value::is_null)
{
obj.insert(
"properties".to_string(),
serde_json::Value::Object(serde_json::Map::new()),
);
}
let input_schema = parse_tool_input_schema(&serialized_input_schema)?;
let structured_content_schema = output_schema
.map(|output_schema| serde_json::Value::Object(output_schema.as_ref().clone()))
.unwrap_or_else(|| JsonValue::Object(serde_json::Map::new()));
let output_schema = Some(mcp_call_tool_result_output_schema(
structured_content_schema,
));
let description = description.map(Into::into).unwrap_or_default();
Ok((description, input_schema, output_schema))
}
fn mcp_call_tool_result_output_schema(structured_content_schema: JsonValue) -> JsonValue {
json!({
"type": "object",
"properties": {
"content": {
"type": "array",
"items": {}
},
"structuredContent": structured_content_schema,
"isError": {
"type": "boolean"
},
"_meta": {}
},
"required": ["content"],
"additionalProperties": false
})
}
/// Builds the tool registry builder while collecting tool specs for later serialization.
#[cfg(test)]
pub(crate) fn build_specs(

View File

@@ -8,6 +8,7 @@ use crate::tools::ToolRouter;
use crate::tools::registry::ConfiguredToolSpec;
use crate::tools::router::ToolRouterParams;
use codex_app_server_protocol::AppInfo;
use codex_protocol::dynamic_tools::DynamicToolSpec;
use codex_protocol::openai_models::InputModality;
use codex_protocol::openai_models::ModelInfo;
use codex_protocol::openai_models::ModelsResponse;
@@ -63,139 +64,6 @@ fn search_capable_model_info() -> ModelInfo {
model_info
}
#[test]
fn mcp_tool_to_openai_tool_inserts_empty_properties() {
let mut schema = rmcp::model::JsonObject::new();
schema.insert("type".to_string(), serde_json::json!("object"));
let tool = rmcp::model::Tool {
name: "no_props".to_string().into(),
title: None,
description: Some("No properties".to_string().into()),
input_schema: std::sync::Arc::new(schema),
output_schema: None,
annotations: None,
execution: None,
icons: None,
meta: None,
};
let openai_tool =
mcp_tool_to_openai_tool("server/no_props".to_string(), tool).expect("convert tool");
let parameters = serde_json::to_value(openai_tool.parameters).expect("serialize schema");
assert_eq!(parameters.get("properties"), Some(&serde_json::json!({})));
}
#[test]
fn mcp_tool_to_openai_tool_preserves_top_level_output_schema() {
let mut input_schema = rmcp::model::JsonObject::new();
input_schema.insert("type".to_string(), serde_json::json!("object"));
let mut output_schema = rmcp::model::JsonObject::new();
output_schema.insert(
"properties".to_string(),
serde_json::json!({
"result": {
"properties": {
"nested": {}
}
}
}),
);
output_schema.insert("required".to_string(), serde_json::json!(["result"]));
let tool = rmcp::model::Tool {
name: "with_output".to_string().into(),
title: None,
description: Some("Has output schema".to_string().into()),
input_schema: std::sync::Arc::new(input_schema),
output_schema: Some(std::sync::Arc::new(output_schema)),
annotations: None,
execution: None,
icons: None,
meta: None,
};
let openai_tool = mcp_tool_to_openai_tool("mcp__server__with_output".to_string(), tool)
.expect("convert tool");
assert_eq!(
openai_tool.output_schema,
Some(serde_json::json!({
"type": "object",
"properties": {
"content": {
"type": "array",
"items": {}
},
"structuredContent": {
"properties": {
"result": {
"properties": {
"nested": {}
}
}
},
"required": ["result"]
},
"isError": {
"type": "boolean"
},
"_meta": {}
},
"required": ["content"],
"additionalProperties": false
}))
);
}
#[test]
fn mcp_tool_to_openai_tool_preserves_output_schema_without_inferred_type() {
let mut input_schema = rmcp::model::JsonObject::new();
input_schema.insert("type".to_string(), serde_json::json!("object"));
let mut output_schema = rmcp::model::JsonObject::new();
output_schema.insert("enum".to_string(), serde_json::json!(["ok", "error"]));
let tool = rmcp::model::Tool {
name: "with_enum_output".to_string().into(),
title: None,
description: Some("Has enum output schema".to_string().into()),
input_schema: std::sync::Arc::new(input_schema),
output_schema: Some(std::sync::Arc::new(output_schema)),
annotations: None,
execution: None,
icons: None,
meta: None,
};
let openai_tool = mcp_tool_to_openai_tool("mcp__server__with_enum_output".to_string(), tool)
.expect("convert tool");
assert_eq!(
openai_tool.output_schema,
Some(serde_json::json!({
"type": "object",
"properties": {
"content": {
"type": "array",
"items": {}
},
"structuredContent": {
"enum": ["ok", "error"]
},
"isError": {
"type": "boolean"
},
"_meta": {}
},
"required": ["content"],
"additionalProperties": false
}))
);
}
#[test]
fn search_tool_deferred_tools_always_set_defer_loading_true() {
let tool = mcp_tool(
@@ -259,6 +127,27 @@ fn deferred_responses_api_tool_serializes_with_defer_loading() {
);
}
#[test]
fn dynamic_tool_preserves_defer_loading() {
let tool = DynamicToolSpec {
name: "lookup_order".to_string(),
description: "Look up an order".to_string(),
input_schema: serde_json::json!({
"type": "object",
"properties": {
"order_id": {"type": "string"}
},
"required": ["order_id"],
"additionalProperties": false,
}),
defer_loading: true,
};
let openai_tool = dynamic_tool_to_openai_tool(&tool).expect("convert dynamic tool");
assert_eq!(openai_tool.defer_loading, Some(true));
}
fn tool_name(tool: &ToolSpec) -> &str {
match tool {
ToolSpec::Function(ResponsesApiTool { name, .. }) => name,

View File

@@ -19,14 +19,6 @@ const MACOS_SEATBELT_BASE_POLICY: &str = include_str!("seatbelt_base_policy.sbpl
const MACOS_SEATBELT_NETWORK_POLICY: &str = include_str!("seatbelt_network_policy.sbpl");
const MACOS_RESTRICTED_READ_ONLY_PLATFORM_DEFAULTS: &str =
include_str!("restricted_read_only_platform_defaults.sbpl");
const MACOS_DEFAULT_PREFERENCES_POLICY: &str = r#"; allow readonly user preferences
(allow ipc-posix-shm-read* (ipc-posix-name-prefix "apple.cfprefs."))
(allow mach-lookup
(global-name "com.apple.cfprefsd.daemon")
(global-name "com.apple.cfprefsd.agent")
(local-name "com.apple.cfprefsd.agent"))
(allow user-preference-read)
"#;
/// When working with `sandbox-exec`, only consider `sandbox-exec` in `/usr/bin`
/// to defend against an attacker trying to inject a malicious version on the
@@ -476,7 +468,6 @@ pub fn create_seatbelt_command_args_for_policies(
let include_platform_defaults = file_system_sandbox_policy.include_platform_defaults();
let mut policy_sections = vec![
MACOS_SEATBELT_BASE_POLICY.to_string(),
MACOS_DEFAULT_PREFERENCES_POLICY.to_string(),
file_read_policy,
file_write_policy,
network_policy,

View File

@@ -106,3 +106,11 @@
; PTYs created before entering seatbelt may lack the extension; allow ioctl
; on those slave ttys so interactive shells detect a TTY and remain functional.
(allow file-ioctl (regex #"^/dev/ttys[0-9]+"))
; allow readonly user preferences
(allow ipc-posix-shm-read* (ipc-posix-name-prefix "apple.cfprefs."))
(allow mach-lookup
(global-name "com.apple.cfprefsd.daemon")
(global-name "com.apple.cfprefsd.agent")
(local-name "com.apple.cfprefsd.agent"))
(allow user-preference-read)

View File

@@ -953,14 +953,6 @@ fn create_seatbelt_args_for_cwd_as_git_repo() {
// - write access to WRITABLE_ROOT_0 (but not its .git or .codex), WRITABLE_ROOT_1, and cwd as WRITABLE_ROOT_2.
let expected_policy = format!(
r#"{MACOS_SEATBELT_BASE_POLICY}
; allow readonly user preferences
(allow ipc-posix-shm-read* (ipc-posix-name-prefix "apple.cfprefs."))
(allow mach-lookup
(global-name "com.apple.cfprefsd.daemon")
(global-name "com.apple.cfprefsd.agent")
(local-name "com.apple.cfprefsd.agent"))
(allow user-preference-read)
; allow read-only file operations
(allow file-read*)
(allow file-write*

View File

@@ -8,6 +8,13 @@ version.workspace = true
workspace = true
[dependencies]
codex-protocol = { workspace = true }
rmcp = { workspace = true, default-features = false, features = [
"base64",
"macros",
"schemars",
"server",
] }
serde = { workspace = true, features = ["derive"] }
serde_json = { workspace = true }

View File

@@ -4,12 +4,17 @@
shared across multiple crates and does not need to stay coupled to
`codex-core`.
Today this crate is intentionally small. It only owns the shared tool input
schema model and parser that were previously defined in `core/src/tools/spec.rs`:
Today this crate is intentionally small. It currently owns the shared tool
schema primitives that no longer need to live in `core/src/tools/spec.rs`:
- `JsonSchema`
- `AdditionalProperties`
- `parse_tool_input_schema()`
- `ParsedDynamicTool`
- `parse_dynamic_tool()`
- `ParsedMcpTool`
- `parse_mcp_tool()`
- `mcp_call_tool_result_output_schema()`
That extraction is the first step in a longer migration. The goal is not to
move all of `core/src/tools` into this crate in one shot. Instead, the plan is

View File

@@ -0,0 +1,24 @@
use crate::JsonSchema;
use crate::parse_tool_input_schema;
use codex_protocol::dynamic_tools::DynamicToolSpec;
/// Parsed dynamic tool metadata and schemas that can be adapted into a
/// higher-level tool spec by downstream crates.
#[derive(Debug, PartialEq)]
pub struct ParsedDynamicTool {
pub description: String,
pub input_schema: JsonSchema,
pub defer_loading: bool,
}
pub fn parse_dynamic_tool(tool: &DynamicToolSpec) -> Result<ParsedDynamicTool, serde_json::Error> {
Ok(ParsedDynamicTool {
description: tool.description.clone(),
input_schema: parse_tool_input_schema(&tool.input_schema)?,
defer_loading: tool.defer_loading,
})
}
#[cfg(test)]
#[path = "dynamic_tool_tests.rs"]
mod tests;

View File

@@ -0,0 +1,66 @@
use super::ParsedDynamicTool;
use super::parse_dynamic_tool;
use crate::JsonSchema;
use codex_protocol::dynamic_tools::DynamicToolSpec;
use pretty_assertions::assert_eq;
use std::collections::BTreeMap;
#[test]
fn parse_dynamic_tool_sanitizes_input_schema() {
let tool = DynamicToolSpec {
name: "lookup_ticket".to_string(),
description: "Fetch a ticket".to_string(),
input_schema: serde_json::json!({
"properties": {
"id": {
"description": "Ticket identifier"
}
}
}),
defer_loading: false,
};
assert_eq!(
parse_dynamic_tool(&tool).expect("parse dynamic tool"),
ParsedDynamicTool {
description: "Fetch a ticket".to_string(),
input_schema: JsonSchema::Object {
properties: BTreeMap::from([(
"id".to_string(),
JsonSchema::String {
description: Some("Ticket identifier".to_string()),
},
)]),
required: None,
additional_properties: None,
},
defer_loading: false,
}
);
}
#[test]
fn parse_dynamic_tool_preserves_defer_loading() {
let tool = DynamicToolSpec {
name: "lookup_ticket".to_string(),
description: "Fetch a ticket".to_string(),
input_schema: serde_json::json!({
"type": "object",
"properties": {}
}),
defer_loading: true,
};
assert_eq!(
parse_dynamic_tool(&tool).expect("parse dynamic tool"),
ParsedDynamicTool {
description: "Fetch a ticket".to_string(),
input_schema: JsonSchema::Object {
properties: BTreeMap::new(),
required: None,
additional_properties: None,
},
defer_loading: true,
}
);
}

View File

@@ -1,7 +1,14 @@
//! Shared tool-schema parsing primitives that can live outside `codex-core`.
mod dynamic_tool;
mod json_schema;
mod mcp_tool;
pub use dynamic_tool::ParsedDynamicTool;
pub use dynamic_tool::parse_dynamic_tool;
pub use json_schema::AdditionalProperties;
pub use json_schema::JsonSchema;
pub use json_schema::parse_tool_input_schema;
pub use mcp_tool::ParsedMcpTool;
pub use mcp_tool::mcp_call_tool_result_output_schema;
pub use mcp_tool::parse_mcp_tool;

View File

@@ -0,0 +1,65 @@
use crate::JsonSchema;
use crate::parse_tool_input_schema;
use serde_json::Value as JsonValue;
use serde_json::json;
/// Parsed MCP tool metadata and schemas that can be adapted into a higher-level
/// tool spec by downstream crates.
#[derive(Debug, PartialEq)]
pub struct ParsedMcpTool {
pub description: String,
pub input_schema: JsonSchema,
pub output_schema: JsonValue,
}
pub fn parse_mcp_tool(tool: &rmcp::model::Tool) -> Result<ParsedMcpTool, serde_json::Error> {
let mut serialized_input_schema = serde_json::Value::Object(tool.input_schema.as_ref().clone());
// OpenAI models mandate the "properties" field in the schema. Some MCP
// servers omit it (or set it to null), so we insert an empty object to
// match the behavior of the Agents SDK.
if let serde_json::Value::Object(obj) = &mut serialized_input_schema
&& obj.get("properties").is_none_or(serde_json::Value::is_null)
{
obj.insert(
"properties".to_string(),
serde_json::Value::Object(serde_json::Map::new()),
);
}
let input_schema = parse_tool_input_schema(&serialized_input_schema)?;
let structured_content_schema = tool
.output_schema
.as_ref()
.map(|output_schema| serde_json::Value::Object(output_schema.as_ref().clone()))
.unwrap_or_else(|| JsonValue::Object(serde_json::Map::new()));
Ok(ParsedMcpTool {
description: tool.description.clone().map(Into::into).unwrap_or_default(),
input_schema,
output_schema: mcp_call_tool_result_output_schema(structured_content_schema),
})
}
pub fn mcp_call_tool_result_output_schema(structured_content_schema: JsonValue) -> JsonValue {
json!({
"type": "object",
"properties": {
"content": {
"type": "array",
"items": {}
},
"structuredContent": structured_content_schema,
"isError": {
"type": "boolean"
},
"_meta": {}
},
"required": ["content"],
"additionalProperties": false
})
}
#[cfg(test)]
#[path = "mcp_tool_tests.rs"]
mod tests;

View File

@@ -0,0 +1,120 @@
use super::ParsedMcpTool;
use super::mcp_call_tool_result_output_schema;
use super::parse_mcp_tool;
use crate::JsonSchema;
use pretty_assertions::assert_eq;
use std::collections::BTreeMap;
fn mcp_tool(name: &str, description: &str, input_schema: serde_json::Value) -> rmcp::model::Tool {
rmcp::model::Tool {
name: name.to_string().into(),
title: None,
description: Some(description.to_string().into()),
input_schema: std::sync::Arc::new(rmcp::model::object(input_schema)),
output_schema: None,
annotations: None,
execution: None,
icons: None,
meta: None,
}
}
#[test]
fn parse_mcp_tool_inserts_empty_properties() {
let tool = mcp_tool(
"no_props",
"No properties",
serde_json::json!({
"type": "object"
}),
);
assert_eq!(
parse_mcp_tool(&tool).expect("parse MCP tool"),
ParsedMcpTool {
description: "No properties".to_string(),
input_schema: JsonSchema::Object {
properties: BTreeMap::new(),
required: None,
additional_properties: None,
},
output_schema: mcp_call_tool_result_output_schema(serde_json::json!({})),
}
);
}
#[test]
fn parse_mcp_tool_preserves_top_level_output_schema() {
let mut tool = mcp_tool(
"with_output",
"Has output schema",
serde_json::json!({
"type": "object"
}),
);
tool.output_schema = Some(std::sync::Arc::new(rmcp::model::object(
serde_json::json!({
"properties": {
"result": {
"properties": {
"nested": {}
}
}
},
"required": ["result"]
}),
)));
assert_eq!(
parse_mcp_tool(&tool).expect("parse MCP tool"),
ParsedMcpTool {
description: "Has output schema".to_string(),
input_schema: JsonSchema::Object {
properties: BTreeMap::new(),
required: None,
additional_properties: None,
},
output_schema: mcp_call_tool_result_output_schema(serde_json::json!({
"properties": {
"result": {
"properties": {
"nested": {}
}
}
},
"required": ["result"]
})),
}
);
}
#[test]
fn parse_mcp_tool_preserves_output_schema_without_inferred_type() {
let mut tool = mcp_tool(
"with_enum_output",
"Has enum output schema",
serde_json::json!({
"type": "object"
}),
);
tool.output_schema = Some(std::sync::Arc::new(rmcp::model::object(
serde_json::json!({
"enum": ["ok", "error"]
}),
)));
assert_eq!(
parse_mcp_tool(&tool).expect("parse MCP tool"),
ParsedMcpTool {
description: "Has enum output schema".to_string(),
input_schema: JsonSchema::Object {
properties: BTreeMap::new(),
required: None,
additional_properties: None,
},
output_schema: mcp_call_tool_result_output_schema(serde_json::json!({
"enum": ["ok", "error"]
})),
}
);
}