#16602: agents: cap persisted tool results to protect session context
agents
stale
size: XS
Cluster:
Context Management Enhancements
## Summary
- apply a stricter hard cap to tool-result text at session-persistence time
- prevent single large exec/tool outputs from dominating transcript size and blowing context on the next turn
- extend guard test expectations to verify the tighter persisted-size bound
## Issue
- Fixes #16574
Made with [Cursor](https://cursor.com)
Most Similar PRs
#16261: feat(agents): add two-tier tool output truncation and excludeFromCo...
by ProgramCaiCai · 2026-02-14
70.8%
#5057: fix: add per-tool-result hard cap to prevent context overflow
by hanxiao · 2026-01-31
68.7%
#10915: fix: prevent session bloat from oversized tool results and improve ...
by DukeDeSouth · 2026-02-07
63.6%
#12260: fix: redact secrets in tool results before persisting to session tr...
by Yida-Dev · 2026-02-09
62.8%
#8888: fix: increase tool result/error context limits
by joetomasone · 2026-02-04
62.0%
#22011: fix(transcript): drop empty toolCallId toolResults during persisten...
by sauerdaniel · 2026-02-20
61.8%
#3622: fix(agents): drop orphan tool results
by mickobizzle · 2026-01-28
61.3%
#16856: feat(agents): add tool execution duration tracking with configurabl...
by EunHyeokJung · 2026-02-15
60.4%
#17345: feat: Memory kernel rebuild with token budgeting, summary sidecar, ...
by markmusson · 2026-02-15
60.2%
#4852: fix(agents): sanitize tool pairing after compaction and history tru...
by lailoo · 2026-01-30
59.7%