Files
llmx/codex-rs/core/src/state/session.rs
pakrym-oai 1b8f2543ac Filter out reasoning items from previous turns (#5857)
Reduces request size and prevents 400 errors when switching between API
orgs.

Based on Responses API behavior described in
https://cookbook.openai.com/examples/responses_api/reasoning_items#caching
2025-10-28 11:39:34 -07:00

72 lines
2.1 KiB
Rust

//! Session-wide mutable state.
use codex_protocol::models::ResponseItem;
use crate::codex::SessionConfiguration;
use crate::conversation_history::ConversationHistory;
use crate::protocol::RateLimitSnapshot;
use crate::protocol::TokenUsage;
use crate::protocol::TokenUsageInfo;
/// Persistent, session-scoped state previously stored directly on `Session`.
pub(crate) struct SessionState {
pub(crate) session_configuration: SessionConfiguration,
pub(crate) history: ConversationHistory,
pub(crate) latest_rate_limits: Option<RateLimitSnapshot>,
}
impl SessionState {
/// Create a new session state mirroring previous `State::default()` semantics.
pub(crate) fn new(session_configuration: SessionConfiguration) -> Self {
Self {
session_configuration,
history: ConversationHistory::new(),
latest_rate_limits: None,
}
}
// History helpers
pub(crate) fn record_items<I>(&mut self, items: I)
where
I: IntoIterator,
I::Item: std::ops::Deref<Target = ResponseItem>,
{
self.history.record_items(items)
}
pub(crate) fn clone_history(&self) -> ConversationHistory {
self.history.clone()
}
pub(crate) fn replace_history(&mut self, items: Vec<ResponseItem>) {
self.history.replace(items);
}
// 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(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);
}
}