StillMe system status accuracy#139
Closed
anhmtk wants to merge 1 commit into
Closed
Conversation
This commit introduces detection for system status queries and integrates real-time telemetry from the RSS fetcher. It ensures that these queries are answered directly with accurate, up-to-date information rather than relying on potentially stale knowledge or hallucinated responses. Key changes include: - A new `SystemStatusDetector` to identify system status-related questions. - Early return in `query_router` for system status queries, bypassing LLM processing. - Injection of synthetic telemetry documents into RAG context for system status queries. - Updates to citation validation to enforce specific citation policies for system status answers. - Enhanced `RSSFetcher` to provide more detailed real-time statistics, including failing feed domains and errors. - Integration of RSS fetcher stats into the `SystemMonitor`. This ensures greater accuracy and reliability when users inquire about the system's operational status and learning sources. Co-authored-by: anh.nguyen.nk86 <anh.nguyen.nk86@gmail.com>
|
Cursor Agent can help with this pull request. Just |
Test Results (Python 3.12)55 tests ±0 42 ✅ ±0 17s ⏱️ -1s For more details on these failures and errors, see this check. Results for commit ee056b1. ± Comparison against base commit b85ade9. |
Test Results (Python 3.11)55 tests ±0 42 ✅ ±0 12s ⏱️ -1s For more details on these failures and errors, see this check. Results for commit ee056b1. ± Comparison against base commit b85ade9. |
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Ensures StillMe provides accurate, real-time system status and learning source information.
This PR implements a "3-layer defense" to prevent StillMe from "lying" about system health. It introduces an early-return handler for system status queries, injects real-time telemetry into the prompt and RAG context, and enforces strict citation validation to forbid
[general knowledge]for status answers, requiring[system telemetry]instead.