issues Search Results · language:Dune language:JavaScript language:JavaScript linked:pr language:HTML language:JavaScript
Filter by
105k results
Problem
Currently the supervisor has two divergent implementations:
- Claude Code (bin/on-stop.mjs, 384 lines): lightweight 6-category classifier via direct Anthropic API
- OpenCode (opencode/supervisor-impl.ts, ...
Summary
When rendering a same-repo source whose local Helm chart directory contains a symlink to a directory, copyDir aborts the
whole run with:
❌ failed to render application via repo server: error= ...
Lab audit: mcs-multi-agent
Audited live against the product as a redeemed workshop user during the bootcamp audit (run 2026-06-18T1231Z-b55b,
against origin/main@c0a71b6).
Findings: 3 (1 High / 0 Medium ...
lab:mcs-multi-agent
lab-audit
severity:high
Summary
In v0.5.4, valid Perplexity API keys can be marked as invalid because provider validation and model listing still call:
https://api.perplexity.ai/models
That endpoint now returns 404. Perplexity ...
Lab audit: mcs-governance
Audit run 2026-06-18T1231Z-b55b (audited revision c0a71b6). This lab creates the same agent three times (Green, Yellow,
Red zones), each using the deprecated Home ** What would ...
lab:mcs-governance
lab-audit
severity:high
Lab audit: mcs-tools
Audit run 2026-06-18T1231Z-b55b (audited revision c0a71b6).
This lab creates five agents across four use cases plus extra credit, and every one uses the OLD agent-creation flow ( ...
lab:mcs-tools
lab-audit
severity:high
No project is created even when all necessary data are filled in.
bug
Frontend
Goal
Redesign the Atlas frontend so it feels like a current TSC system instead of a generic admin panel or old desktop OS.
Why it matters
Atlas needs to feel alive, premium, and rooted in the TSC identity ...
Lab audit: mcs-alm
Audited revision c0a71b6 (run 2026-06-18T1231Z-b55b). Findings below; a fix PR accompanies this issue (scoped to agent
creation only).
High — Obsolete describe-driven agent-creation ...
lab:mcs-alm
lab-audit
severity:high
Summary
Audit of lab autonomous-account-news (Architecture Bootcamp) found 4 finding(s): 2 High / 0 Medium / 2 Low. Audited live
as a redeemed workshop user during run 2026-06-18T1231Z-b55b, against origin/main@c0a71b6. ...
lab:autonomous-account-news
lab-audit
severity:high

Learn how you can use GitHub Issues to plan and track your work.
Save views for sprints, backlogs, teams, or releases. Rank, sort, and filter issues to suit the occasion. The possibilities are endless.Learn more about GitHub IssuesProTip! Restrict your search to the title by using the in:title qualifier.