fix(security): redact secrets from context compaction (PR #9200) - #13228
Merged
Conversation
Three-layer defense against secrets leaking into compaction summaries: 1. Input redaction: redact_sensitive_text() on message content and tool call arguments in _serialize_for_summary() before sending to summarizer 2. Prompt instructions: NEVER include API keys/tokens/passwords in the summarizer preamble, template Critical Context section, and focus topic 3. Output redaction: redact_sensitive_text() on the summary output and _previous_summary for iterative updates Reuses existing agent/redact.py patterns (sk-*, ghp_*, key=value, etc). Cherry-picked from PR #9200 by @entropidelic.
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Summary
Redacts secrets before context compaction so API keys stop leaking into summaries.
Cherry-picked from PR #9200 by @entropidelic onto current main, merge conflicts resolved (language instruction preserved alongside new redaction instructions).
Changes
agent/context_compressor.py: +17/-6 — three-layer defense:redact_sensitive_text()on message content and tool call arguments in_serialize_for_summary()redact_sensitive_text()on summary result and_previous_summaryTests from the original PR were not included (vacuously true assertions — test data contained pre-redacted values).
Closes #9200.