feat: trust scoring with feedback API#725
Merged
Merged
Conversation
Add helpful/unhelpful feedback mechanism to adjust memory importance:
Core (uteke-core):
- Uteke::feedback_helpful() → importance += 0.05
- Uteke::feedback_unhelpful() → importance -= 0.10
- Asymmetric: penalty > reward (adopted from Hermes trust scoring)
- Clamped to [0.0, 1.0], returns new importance value
CLI:
- uteke feedback <id> helpful|unhelpful
- JSON and human-readable output
- FeedbackAction enum (Helpful, Unhelpful)
Server API:
- POST /memory/feedback { id, feedback }
- Validates UUID, returns { id, feedback, delta, importance }
Closes #718
🔍 Cora AI Code Review❌ Blocked — critical issues found. 🔴 Error (1)
Review powered by cora-cli · BYOK · MIT |
| .store | ||
| .conn | ||
| .query_row( | ||
| "SELECT importance FROM memories WHERE id = ?1", |
This was referenced Jul 17, 2026
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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
Add helpful/unhelpful feedback mechanism for trust scoring (#718).
Problem
Uteke memories have an
importancefield (0.0–1.0, default 0.5) used by salience boost and orphan detection. Currently importance can only be set directly or recomputed globally — there's no way to signal that a specific memory was useful or not in a given context. Hermes solves this with a feedback loop: +0.05 for helpful, -0.10 for unhelpful (asymmetric — penalizing bad memories more than rewarding good ones).Changes
uteke-core/src/lib.rsUteke::feedback_helpful(id)→ importance += 0.05, returns new valueUteke::feedback_unhelpful(id)→ importance -= 0.10, returns new valuefeedback_adjust(id, delta)with clamp to [0.0, 1.0]uteke-cli/src/cli.rsuteke feedback <id> {helpful|unhelpful}subcommandFeedbackActionenumuteke-cli/src/commands/mod.rs--json) and human-readable outpututeke-server/src/{handlers.rs, types.rs, main.rs}POST /memory/feedback—{ id, feedback: "helpful"|"unhelpful" }{ id, feedback, delta, importance }Usage
CLI:
API:
Design Decisions
Closes #718