Control automatic relationship evaluation frequency - #724
Merged
Conversation
RANGROO
marked this pull request as ready for review
August 22, 2026 21:29
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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
Relationship Update Chancesetting from 0 to 100 in thePrompt & Rechatsettings tab, defaulting to50relationshipscolumn to an LLM; runtime prompt/update context remains sourced fromextended_data.relationshipsJSONBehavior
0: no new automatic relationship evaluation calls are queued; stored JSON relationship context is still injected1-99: each eligible completed NPC response independently queues at the configured percentage100: preserves the current every-eligible-response behaviorBuild with AIevent-history flow remains available and already writes the JSON relationship mapCompatibility
50; explicitly saved values remain unchangedValidation
RelationshipTypeValidationTest.php: 9 tests, 25 assertionsOghmaSettingsTest.php: 2 tests, 15 assertionsconf_schema.jsonparsed and the integer/default/scope contract passedgit diff --checkpassedPerformance
At
N%, new background evaluations are expected to be queued for approximately N of every 100 eligible responses;0queues none and100retains the existing rate. The default is50. Automatic legacy text-to-JSON LLM initialization is eliminated. No live connector/token benchmark was run.Review size
131 changed lines (99 additions, 32 deletions) across 10 focused source/test files; no generated or binary artifacts.
Local deployment and limits
a15bd0f9to WSL/var/www/html/HerikaServer; all 10 changed-file hashes match sourcePrompt & Rechat, absent fromGlobal Connectors, and renderstype=number,value=50,min=0, andmax=100RelationshipTypeValidationTest.php: 9 tests, 25 assertions, including the legacy-text no-LLM regression