From f9d111d0a79a07815d476356e98a28df3a0000ba Mon Sep 17 00:00:00 2001
From: Josh Lehman <josh@martian.engineering>
Date: Wed, 4 Mar 2026 11:54:17 -0800
Subject: [PATCH] docs: add changelog note for failed-turn token usage fix

---
 CHANGELOG.md | 1 +
 1 file changed, 1 insertion(+)

diff --git a/CHANGELOG.md b/CHANGELOG.md
index 88e3788d842..282a0cc1f1a 100644
--- a/CHANGELOG.md
+++ b/CHANGELOG.md
@@ -16,6 +16,7 @@ Docs: https://docs.openclaw.ai
 
 ### Fixes
 
+- Agents/session usage tracking: preserve accumulated usage metadata on embedded Pi runner error exits so failed turns still update session `totalTokens` from real usage instead of stale prior values. (#34275) thanks @RealKai42.
 - Nodes/system.run approval hardening: use explicit argv-mutation signaling when regenerating prepared `rawCommand`, and cover the `system.run.prepare -> system.run` handoff so direct PATH-based `nodes.run` commands no longer fail with `rawCommand does not match command`. (#33137) thanks @Sid-Qin.
 - Models/custom provider headers: propagate `models.providers.<name>.headers` across inline, fallback, and registry-found model resolution so header-authenticated proxies consistently receive configured request headers. (#27490) thanks @Sid-Qin.
 - Ollama/custom provider headers: forward resolved model headers into native Ollama stream requests so header-authenticated Ollama proxies receive configured request headers. (#24337) thanks @echoVic.