Files
odysseus/src
Kevin Fiddick 681cd0b865 Isolate untrusted context from visible user prompts (#3584)
Prevent untrusted source/context guard text from being merged into the current visible user request during provider message sanitization.

Changes:
- Detect untrusted context blocks during LLM message sanitization
- Insert a short assistant boundary before the current user request
- Keep the visible user prompt as its own user message
- Preserve normal consecutive user-message merging for non-untrusted cases
- Strengthen prompt-security wording to avoid mentioning guard wrappers
- Add regression coverage for untrusted context followed by a user prompt

Notes:
- Untrusted context remains role:user for safety
- This does not add prompt debug logging
- This does not change frontend draft persistence
2026-06-27 13:50:04 +01:00
..
2026-05-31 23:58:26 +09:00
2026-06-21 11:08:50 +00:00
2026-05-31 23:58:26 +09:00
2026-05-31 23:58:26 +09:00
2026-05-31 23:58:26 +09:00
2026-05-31 23:58:26 +09:00
2026-06-21 11:02:35 +00:00