feat(kernel): three-tier ack detection for verbose GPT narration (#1349)#1353
Merged
feat(kernel): three-tier ack detection for verbose GPT narration (#1349)#1353
Conversation
GPT models produce 3000+ char architectural analyses without calling tools, evading the 2000-char ack detector limit. Add two new detection tiers inspired by Triggerfish's quality classifier: - Tier 2 (TrailingIntent): check last 600 chars of long responses - Tier 3 (DenseNarration): detect 5+ intent phrases = planning essay - AckKind enum with differentiated nudge messages per tier - 5 new Chinese conditional-offering patterns - 12 new tests (42 total) Closes #1349
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Summary
GPT models produce 3000+ char architectural analyses without calling tools, evading the 2000-char ack detector limit. Adds two new detection tiers inspired by Triggerfish's quality classifier:
AckKindenum with differentiated nudge messages per tier.Open-source survey: hermes-agent, aider, Mullet, Triggerfish, Batty, OpenHands, Infinidev — Triggerfish's trailing-intent + dense-narration approach was the best fit.
Type of change
enhancementComponent
coreCloses
Closes #1349
Test plan
cargo check -p rara-kernelpassescargo test -p rara-kernel -- ack_detector— 42 tests pass