fix(honcho): disable AI self-observation by default - #1
Merged
Conversation
When ai_observe_me is true, Honcho absorbs user facts from the AI's own replies into the AI peer's self-representation. Default it off across the config chain so directional mode keeps AI observeOthers without observeMe. Co-authored-by: Cursor <cursoragent@cursor.com>
Required for Hermes contributor attribution CI on PRs from this checkout. Co-authored-by: Cursor <cursoragent@cursor.com>
AI observeMe is off by default in directional mode; document the new semantics and use-case table in honcho.md and memory-providers.md. Co-authored-by: Cursor <cursoragent@cursor.com>
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
1 participant
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Upstream PR: NousResearch#48096
Summary
Default
ai_observe_metofalseacross the Honcho config chain so user facts echoed in AI replies are not stored as AI self-representation. Directional mode keepsai_observe_others: true— the AI peer still models the user from user messages.Problem
With
ai_observe_me: true, Honcho treats the AI peer's own messages as input for its self-representation. When the model answers questions about the user, it repeats user facts in its replies — and those facts land under AI Self-Representation instead of the user peer.Example: user says "I play tennis on Tuesdays" → AI replies "Got it, you play tennis on Tuesdays" → Honcho stores tennis under the AI persona, not the user.
Langfuse traces showed this pattern (tennis, haircut, calendar, etc.).
Solution
Set
ai_observe_medefault tofalsein:HonchoClientConfigdataclass default"directional"observation presetHonchoSessionManagerfallback when no config is passedAI still observes the user via
ai_observe_others: true. Opt back in explicitly:Also maps
lebedyncrsinAUTHOR_MAPfor contributor attribution CI.Test plan
scripts/run_tests.sh tests/honcho_plugin/test_client.py tests/honcho_plugin/test_session.py tests/honcho_plugin/test_empty_profile_hint.py— 207 passedtest_directional_preset_disables_ai_self_observationtest_ai_self_observation_off_without_config