Repository navigation
Resolve native dashboard, memory lifecycle and evaluation gaps - #43
Merged
seathatflowsinourveins merged 6 commits intoSep 21, 2026
Merged
Conversation
|
You have reached your Codex usage limits for code reviews. You can see your limits in the Codex usage dashboard. |
This was referenced Sep 24, 2026
seathatflowsinourveins
deleted the
codex/dashboard-gap-resolution-20260921
branch
September 25, 2026 18:47
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
The rendered dashboard review exposed stale archives, disabled memory consolidation, an unready optional gateway, absent current Claude telemetry, malformed alert text and an echo-only evaluation. This change records the upstream resolutions and updates the portable handbook and HTML catalog with actual returned results.
Native ai-memory now qualifies both Claude and Codex SessionEnd capture through the existing Codex provider: each automatic job completed on its first attempt with persisted source attribution. The stale pinned memory decision is superseded. Scoped AgentsView refresh and the upstream FreeLLMAPI desktop bridge restore current data and passwordless access. Native ntfy template configuration fixes missing fields and line breaks. Promptfoo runs NVIDIA's unchanged four-query example through its official exec provider, with an explicitly local ranking assertion and unknown direct usage.
Validation: independent review found no remaining actionable issues after correcting one telemetry evidence label; both native client lifecycle checks passed; two unchanged ntfy tests and three local renderer cases passed; NVIDIA's four published pairs ranked first; five observability tests passed; repository integrity and generated explorer checks passed. The local evidence viewer contains eight inspected screenshots and 53 working returned-output downloads.
Retain limits: no universal SOTA or complete-foundation claim, no inferred token savings, no fresh PreCompact/active Desktop session-end test, and no fabricated production alert to test the next ntfy delivery. Raw private sessions, accounts and configuration remain outside GitHub.