← All notes

Short answer

When an agent compacts its context, standing user instructions ("do not delete anything until I confirm") can be lost. One study found compactors kept only 17% of injected constraints on average, and an inbox agent deleted emails without approval in 30 of 100 sessions after compaction. Keeping constraints in a separate list and re-appending them after each compaction restored over 90% retention. [S1]

Practice

• Store standing constraints outside the summary and re-insert them verbatim. [S1]
• Decide deliberately when to compact and what working state to keep; learned compaction policies improved coding-agent pass rates. [S2]

Claims

• id: C1 claim: Compactors retained only 17% of injected side constraints on average. source: S1 evidence: "The evaluated compactors retain only 17% of injected SCs on average."
• id: C2 claim: Keeping constraints separate from the summary reached over 90% retention. source: S1 evidence: "maintains constraints separately from the task summary and appends them to the compacted context"
• id: C3 claim: Agents must decide when to compact and what state to preserve. source: S2 evidence: "an agent must decide when to compact, what working state to preserve"
• id: C4 claim: A judge reviewed compaction decisions to build training data. source: S2 evidence: "use a judge to review its compaction decisions, summaries, and actions after compaction"

Sources

• [S1] [2608.11242] Lost in Context Compaction: When LLM Systems Drop Side Constraints. arXiv. https://arxiv.org/abs/2608.11242 . License: CC BY 4.0. Accessed 2026-11-04.
• [S2] [2610.02163] AutoCompact: Learning When to Compact Context in Long-Horizon Coding Agents. arXiv. https://arxiv.org/abs/2610.02163 . License: CC BY 4.0. Accessed 2026-11-04.

License: this note is CC BY 4.0 (https://creativecommons.org/licenses/by/4.0/). Summary by iinventedlight (AI-assisted).

@misc{iil_note_qdc4t88c,
  author = {{iinventedlight}},
  title = {{Context compaction can silently drop user constraints}},
  howpublished = {iinventedlight Library},
  year = {2026},
  date = {2026-11-04},
  url = {https://iinventedlight.com/library/notes/ao-compaction-side-constraints/},
  note = {Permanent ID iil:note:qdc4t88c. License: CC-BY-4.0.},
}

Markdown

Spotted a mistake? Use the MCP feedback tool or email hello@iinventedlight.com.

For language models and agents: start at /llms.txt. This page in Markdown: /library/notes/ao-compaction-side-constraints.md.