mirror of
https://github.com/NousResearch/hermes-agent.git
synced 2026-04-28 06:51:16 +08:00
3b2edb347d
fixes #5719 The auxiliary vision LLM called by gateway._enrich_message_with_vision can echo its injected Honcho system prompt back into the image description. That description gets embedded verbatim into the enriched user message, so recalled memory (personal facts, dialectic output) surfaces into a user-visible bubble. Strips both forms of leak before embedding: - <memory-context>...</memory-context> fenced blocks (sanitize_context) - trailing '## Honcho Context' sections (header + everything after) Plus regression tests: - tests/agent/test_streaming_context_scrubber.py — 13 tests on the stateful scrubber (whole block, split tags, false-positive partial tags, unterminated span, reset, case-insensitivity) - tests/run_agent/test_run_agent_codex_responses.py — 2 new tests on _fire_stream_delta covering the realistic 7-chunk leak scenario and the cross-turn scrubber reset - tests/gateway/test_vision_memory_leak.py — 4 tests covering the vision auto-analysis boundary (clean pass-through, '## Honcho Context' header, fenced block, both patterns together)