fix: context overflow compaction and subagent announce improvements (#11664) (thanks @tyler6204)

* initial commit

* feat: implement deriveSessionTotalTokens function and update usage tests

* Added deriveSessionTotalTokens function to calculate total tokens based on usage and context tokens.
* Updated usage tests to include cases for derived session total tokens.
* Refactored session usage calculations in multiple files to utilize the new function for improved accuracy.

* fix: restore overflow truncation fallback + changelog/test hardening (#11551) (thanks @tyler6204)

CHANGELOG.md

@@ -11,6 +11,7 @@ Docs: https://docs.openclaw.ai
 ### Fixes
 
 - Cron: route text-only isolated agent announces through the shared subagent announce flow; add exponential backoff for repeated errors; preserve future `nextRunAtMs` on restart; include current-boundary schedule matches; prevent stale threadId reuse across targets; and add per-job execution timeout. (#11641) Thanks @tyler6204.
+- Subagents: stabilize announce timing, preserve compaction metrics across retries, clamp overflow-prone long timeouts, and cap impossible context usage token totals. (#11551) Thanks @tyler6204.
 - Agents: recover from context overflow caused by oversized tool results (pre-emptive capping + fallback truncation). (#11579) Thanks @tyler6204.
 - Gateway/CLI: when `gateway.bind=lan`, use a LAN IP for probe URLs and Control UI links. (#11448) Thanks @AnonO6.
 - Memory: set Voyage embeddings `input_type` for improved retrieval. (#10818) Thanks @mcinteerj.