Filter simulation personas to agent-eligible entities - #760
Closed
samrusani wants to merge 1 commit into
Closed
Conversation
Author
|
Closing this to reduce my stale contributor backlog. This draft never developed a maintainer review path and would need a fresh scope check against current |
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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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
Fixes #759 by filtering graph entities before they are promoted into simulation personas.
The simulation prepare flow now builds its roster from agent-eligible person entities only, so non-person graph nodes such as project names, companies, topics, or sentence fragments do not become interviewable agents. The same filtered roster is passed to both profile generation and simulation config generation.
The standalone profile generation endpoint also applies the persona filter by default, with an explicit
allow_group_accountsopt-in for callers that intentionally want institution/group accounts.Root Cause
ZepEntityReader.filter_defined_entities()only removed default-only graph nodes. Any node with a custom label could then flow intogenerate_profiles_from_entities()andSimulationConfigGenerator.generate_config(), where it was treated as an agent candidate.That allowed entities like
MiroFishormarket eventto become simulated participants even when the simulation requirement expected individual people.Validation
cd backend uv run pytest testsResult:
133 passed.