mirror of
https://github.com/openai/codex.git
synced 2026-04-24 22:54:54 +00:00
3de8790714
- This PR is to make it on path for truncating by tokens. This path will be initially used by unified exec and context manager (responsible for MCP calls mainly). - We are exposing new config `calls_output_max_tokens` - Use `tokens` as the main budget unit but truncate based on the model family by Introducing `TruncationPolicy`. - Introduce `truncate_text` as a router for truncation based on the mode. In next PRs: - remove truncate_with_line_bytes_budget - Add the ability to the model to override the token budget.
78 lines
2.3 KiB
Rust
78 lines
2.3 KiB
Rust
//! Session-wide mutable state.
|
|
|
|
use codex_protocol::models::ResponseItem;
|
|
|
|
use crate::codex::SessionConfiguration;
|
|
use crate::context_manager::ContextManager;
|
|
use crate::protocol::RateLimitSnapshot;
|
|
use crate::protocol::TokenUsage;
|
|
use crate::protocol::TokenUsageInfo;
|
|
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>,
|
|
}
|
|
|
|
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,
|
|
}
|
|
}
|
|
|
|
// 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(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);
|
|
}
|
|
}
|