Files
codex/codex-rs/core/src/state/session.rs
T
Anton Panasenko becc3a0424 feat: search_tool (#10657)
**Why We Did This**
- The goal is to reduce MCP tool context pollution by not exposing the
full MCP tool list up front
- It forces an explicit discovery step (`search_tool_bm25`) so the model
narrows tool scope before making MCP calls, which helps relevance and
lowers prompt/tool clutter.

**What It Changed**
- Added a new experimental feature flag `search_tool` in
`core/src/features.rs:90` and `core/src/features.rs:430`.
- Added config/schema support for that flag in
`core/config.schema.json:214` and `core/config.schema.json:1235`.
- Added BM25 dependency (`bm25`) in `Cargo.toml:129` and
`core/Cargo.toml:23`.
- Added new tool handler `search_tool_bm25` in
`core/src/tools/handlers/search_tool_bm25.rs:18`.
- Registered the handler and tool spec in
`core/src/tools/handlers/mod.rs:11` and `core/src/tools/spec.rs:780` and
`core/src/tools/spec.rs:1344`.
- Extended `ToolsConfig` to carry `search_tool` enablement in
`core/src/tools/spec.rs:32` and `core/src/tools/spec.rs:56`.
- Injected dedicated developer instructions for tool-discovery workflow
in `core/src/codex.rs:483` and `core/src/codex.rs:1976`, using
`core/templates/search_tool/developer_instructions.md:1`.
- Added session state to store one-shot selected MCP tools in
`core/src/state/session.rs:27` and `core/src/state/session.rs:131`.
- Added filtering so when feature is enabled, only selected MCP tools
are exposed on the next request (then consumed) in
`core/src/codex.rs:3800` and `core/src/codex.rs:3843`.
- Added E2E suite coverage for
enablement/instructions/hide-until-search/one-turn-selection in
`core/tests/suite/search_tool.rs:72`,
`core/tests/suite/search_tool.rs:109`,
`core/tests/suite/search_tool.rs:147`, and
`core/tests/suite/search_tool.rs:218`.
- Refactored test helper utilities to support config-driven tool
collection in `core/tests/suite/tools.rs:281`.

**Net Behavioral Effect**
- With `search_tool` **off**: existing MCP behavior (tools exposed
normally).
- With `search_tool` **on**: MCP tools start hidden, model must call
`search_tool_bm25`, and only returned `selected_tools` are available for
the next model call.
2026-02-09 12:53:50 -08:00

262 lines
8.5 KiB
Rust

//! Session-wide mutable state.
use codex_protocol::models::ResponseItem;
use std::collections::HashMap;
use std::collections::HashSet;
use crate::codex::SessionConfiguration;
use crate::context_manager::ContextManager;
use crate::protocol::RateLimitSnapshot;
use crate::protocol::TokenUsage;
use crate::protocol::TokenUsageInfo;
use crate::tasks::RegularTask;
use crate::truncate::TruncationPolicy;
/// Persistent, session-scoped state previously stored directly on `Session`.
pub(crate) struct SessionState {
pub(crate) session_configuration: SessionConfiguration,
pub(crate) history: ContextManager,
pub(crate) latest_rate_limits: Option<RateLimitSnapshot>,
pub(crate) server_reasoning_included: bool,
pub(crate) dependency_env: HashMap<String, String>,
pub(crate) mcp_dependency_prompted: HashSet<String>,
/// Whether the session's initial context has been seeded into history.
///
/// TODO(owen): This is a temporary solution to avoid updating a thread's updated_at
/// timestamp when resuming a session. Remove this once SQLite is in place.
pub(crate) initial_context_seeded: bool,
/// Previous rollout model for one-shot model-switch handling on first turn after resume.
pub(crate) pending_resume_previous_model: Option<String>,
/// Startup regular task pre-created during session initialization.
pub(crate) startup_regular_task: Option<RegularTask>,
pub(crate) active_mcp_tool_selection: Option<Vec<String>>,
}
impl SessionState {
/// Create a new session state mirroring previous `State::default()` semantics.
pub(crate) fn new(session_configuration: SessionConfiguration) -> Self {
let history = ContextManager::new();
Self {
session_configuration,
history,
latest_rate_limits: None,
server_reasoning_included: false,
dependency_env: HashMap::new(),
mcp_dependency_prompted: HashSet::new(),
initial_context_seeded: false,
pending_resume_previous_model: None,
startup_regular_task: None,
active_mcp_tool_selection: None,
}
}
// History helpers
pub(crate) fn record_items<I>(&mut self, items: I, policy: TruncationPolicy)
where
I: IntoIterator,
I::Item: std::ops::Deref<Target = ResponseItem>,
{
self.history.record_items(items, policy);
}
pub(crate) fn clone_history(&self) -> ContextManager {
self.history.clone()
}
pub(crate) fn replace_history(&mut self, items: Vec<ResponseItem>) {
self.history.replace(items);
}
pub(crate) fn set_token_info(&mut self, info: Option<TokenUsageInfo>) {
self.history.set_token_info(info);
}
// Token/rate limit helpers
pub(crate) fn update_token_info_from_usage(
&mut self,
usage: &TokenUsage,
model_context_window: Option<i64>,
) {
self.history.update_token_info(usage, model_context_window);
}
pub(crate) fn token_info(&self) -> Option<TokenUsageInfo> {
self.history.token_info()
}
pub(crate) fn set_rate_limits(&mut self, snapshot: RateLimitSnapshot) {
self.latest_rate_limits = Some(merge_rate_limit_fields(
self.latest_rate_limits.as_ref(),
snapshot,
));
}
pub(crate) fn token_info_and_rate_limits(
&self,
) -> (Option<TokenUsageInfo>, Option<RateLimitSnapshot>) {
(self.token_info(), self.latest_rate_limits.clone())
}
pub(crate) fn set_token_usage_full(&mut self, context_window: i64) {
self.history.set_token_usage_full(context_window);
}
pub(crate) fn get_total_token_usage(&self, server_reasoning_included: bool) -> i64 {
self.history
.get_total_token_usage(server_reasoning_included)
}
pub(crate) fn set_server_reasoning_included(&mut self, included: bool) {
self.server_reasoning_included = included;
}
pub(crate) fn server_reasoning_included(&self) -> bool {
self.server_reasoning_included
}
pub(crate) fn record_mcp_dependency_prompted<I>(&mut self, names: I)
where
I: IntoIterator<Item = String>,
{
self.mcp_dependency_prompted.extend(names);
}
pub(crate) fn mcp_dependency_prompted(&self) -> HashSet<String> {
self.mcp_dependency_prompted.clone()
}
pub(crate) fn set_dependency_env(&mut self, values: HashMap<String, String>) {
for (key, value) in values {
self.dependency_env.insert(key, value);
}
}
pub(crate) fn dependency_env(&self) -> HashMap<String, String> {
self.dependency_env.clone()
}
pub(crate) fn set_startup_regular_task(&mut self, task: RegularTask) {
self.startup_regular_task = Some(task);
}
pub(crate) fn take_startup_regular_task(&mut self) -> Option<RegularTask> {
self.startup_regular_task.take()
}
pub(crate) fn merge_mcp_tool_selection(&mut self, tool_names: Vec<String>) -> Vec<String> {
if tool_names.is_empty() {
return self.active_mcp_tool_selection.clone().unwrap_or_default();
}
let mut merged = self.active_mcp_tool_selection.take().unwrap_or_default();
let mut seen: HashSet<String> = merged.iter().cloned().collect();
for tool_name in tool_names {
if seen.insert(tool_name.clone()) {
merged.push(tool_name);
}
}
self.active_mcp_tool_selection = Some(merged.clone());
merged
}
pub(crate) fn get_mcp_tool_selection(&self) -> Option<Vec<String>> {
self.active_mcp_tool_selection.clone()
}
pub(crate) fn clear_mcp_tool_selection(&mut self) {
self.active_mcp_tool_selection = None;
}
}
// Sometimes new snapshots don't include credits or plan information.
fn merge_rate_limit_fields(
previous: Option<&RateLimitSnapshot>,
mut snapshot: RateLimitSnapshot,
) -> RateLimitSnapshot {
if snapshot.credits.is_none() {
snapshot.credits = previous.and_then(|prior| prior.credits.clone());
}
if snapshot.plan_type.is_none() {
snapshot.plan_type = previous.and_then(|prior| prior.plan_type);
}
snapshot
}
#[cfg(test)]
mod tests {
use super::*;
use crate::codex::make_session_configuration_for_tests;
use pretty_assertions::assert_eq;
#[tokio::test]
async fn merge_mcp_tool_selection_deduplicates_and_preserves_order() {
let session_configuration = make_session_configuration_for_tests().await;
let mut state = SessionState::new(session_configuration);
let merged = state.merge_mcp_tool_selection(vec![
"mcp__rmcp__echo".to_string(),
"mcp__rmcp__image".to_string(),
"mcp__rmcp__echo".to_string(),
]);
assert_eq!(
merged,
vec![
"mcp__rmcp__echo".to_string(),
"mcp__rmcp__image".to_string(),
]
);
let merged = state.merge_mcp_tool_selection(vec![
"mcp__rmcp__image".to_string(),
"mcp__rmcp__search".to_string(),
]);
assert_eq!(
merged,
vec![
"mcp__rmcp__echo".to_string(),
"mcp__rmcp__image".to_string(),
"mcp__rmcp__search".to_string(),
]
);
}
#[tokio::test]
async fn merge_mcp_tool_selection_empty_input_is_noop() {
let session_configuration = make_session_configuration_for_tests().await;
let mut state = SessionState::new(session_configuration);
state.merge_mcp_tool_selection(vec![
"mcp__rmcp__echo".to_string(),
"mcp__rmcp__image".to_string(),
]);
let merged = state.merge_mcp_tool_selection(Vec::new());
assert_eq!(
merged,
vec![
"mcp__rmcp__echo".to_string(),
"mcp__rmcp__image".to_string(),
]
);
assert_eq!(
state.get_mcp_tool_selection(),
Some(vec![
"mcp__rmcp__echo".to_string(),
"mcp__rmcp__image".to_string(),
])
);
}
#[tokio::test]
async fn clear_mcp_tool_selection_removes_selection() {
let session_configuration = make_session_configuration_for_tests().await;
let mut state = SessionState::new(session_configuration);
state.merge_mcp_tool_selection(vec!["mcp__rmcp__echo".to_string()]);
state.clear_mcp_tool_selection();
assert_eq!(state.get_mcp_tool_selection(), None);
}
}