fix(chat-state): reasoning estimate and calibration reseed on every rewrite
A Reasoning item counted its text and its encrypted blob as two separate payloads, inflating the estimate for retained reasoning; the estimate now takes the larger of the two (base64 runs 4/3 over the raw bytes). Only compaction carried the provider-confirmed ratio into the reseeded total; a rewind or a non-compaction replace sprang the context meter back to the raw estimate. reseed_total_tokens applies the ratio (capped at the pre-rewrite total) to every rewrite, and the truncate path uses it too. Ported from upstream 1.0.1x (grok-build xai-chat-state actor/state.rs, mutations.rs, queries.rs). Claude-Session: https://claude.ai/code/session_01RUqV8HVGXcAETyYbZ2tPQ4
This commit is contained in:
1 parent
00a5e318bb
commit
fc7113ba3c
4 files changed
+73
-33
No files matched your search
@@ -390,14 +390,24 @@ impl ChatStateActor {
|
||||
});
|
||||
}
|
||||
|
||||
/// Replace the entire conversation, persist, re-estimate `total_tokens`,
|
||||
/// and emit reset + token-update events.
|
||||
///
|
||||
/// Compaction replaces carry the provider-side overhead forward as a
|
||||
/// *ratio* (`base_estimate × provider_total ÷ estimate_at_last_response`,
|
||||
/// capped at the pre-compaction total; `base_estimate` when that estimate is
|
||||
/// 0) so the reseed neither springs back nor over-counts (see
|
||||
/// `COMPACTION.md`).
|
||||
/// Reseed after a rewrite: the raw estimate scaled by the provider-confirmed ratio, capped at the pre-rewrite total (see COMPACTION.md).
|
||||
pub(super) fn reseed_total_tokens(&self, base_estimate: u64) -> u64 {
|
||||
let pre_replace_total = self.state.total_tokens;
|
||||
let mut estimated_tokens =
|
||||
if pre_replace_total > 0 && self.state.estimate_at_last_response > 0 {
|
||||
let ratio = pre_replace_total as f64 / self.state.estimate_at_last_response as f64;
|
||||
(base_estimate as f64 * ratio).round() as u64
|
||||
} else {
|
||||
base_estimate
|
||||
};
|
||||
// Over-counting fires premature compaction; an under-count self-heals on the next response.
|
||||
if pre_replace_total > 0 {
|
||||
estimated_tokens = estimated_tokens.min(pre_replace_total);
|
||||
}
|
||||
estimated_tokens
|
||||
}
|
||||
|
||||
/// Replace the conversation, persist, reseed `total_tokens` and emit reset + token events; `is_compaction` only marks the turn capture.
|
||||
pub(super) fn replace_conversation(
|
||||
&mut self,
|
||||
items: Vec<ConversationItem>,
|
||||
@@ -407,28 +417,16 @@ impl ChatStateActor {
|
||||
if is_compaction && let Some(cap) = &mut self.state.turn_capture {
|
||||
cap.compaction_occurred = true;
|
||||
}
|
||||
let pre_replace_total = self.state.total_tokens;
|
||||
// `harness_trace_buffer` / `harness_trace_turns` intentionally untouched:
|
||||
// the planner/verifier subagents ran, so their sealed trace turns survive
|
||||
// a conversation replace (same intent as the `TruncateToPromptIndex` arm).
|
||||
self.persistence.replace_history(&items);
|
||||
let base_estimate = super::state::estimate_conversation_tokens(&items);
|
||||
let mut estimated_tokens =
|
||||
if is_compaction && pre_replace_total > 0 && self.state.estimate_at_last_response > 0 {
|
||||
let ratio = pre_replace_total as f64 / self.state.estimate_at_last_response as f64;
|
||||
(base_estimate as f64 * ratio).round() as u64
|
||||
} else {
|
||||
base_estimate
|
||||
};
|
||||
// Compaction must never appear to increase usage.
|
||||
if is_compaction && pre_replace_total > 0 {
|
||||
estimated_tokens = estimated_tokens.min(pre_replace_total);
|
||||
}
|
||||
let estimated_tokens = self.reseed_total_tokens(base_estimate);
|
||||
self.state.conversation = items;
|
||||
self.state.estimated_tokens_since_model = 0;
|
||||
self.state.total_tokens = estimated_tokens;
|
||||
self.state.estimate_at_last_response =
|
||||
super::state::estimate_conversation_tokens(&self.state.conversation);
|
||||
self.state.estimate_at_last_response = base_estimate;
|
||||
self.rebase_turn_capture_offset();
|
||||
self.send_event(ChatStateEvent::ConversationReset {
|
||||
new_len: self.state.conversation.len(),
|
||||
|
||||
Reference in new issue
Block a user