issues Search Results · language:Dune language:Python linked:pr language:JavaScript language:HTML language:Java
Filter by
6.3M results
Problem
Memory recall adoption is 0.9% (13 recalls / 328 sessions, 2026-06-09 trend log). The store is written 2.5× more than it
is read; 33% of facts are cold. The SessionStart CTA approach ( run memory ...
enhancement
knowledge-base
P1
jwj2002
Problem
For a config whose goal is code quality, there are no quantified standards anywhere: no coverage floor, no defined ruff
ruleset, no type-checking policy. PATCH can drop coverage 10% with nothing ...
agent-discipline
enhancement
P1
Problem
/quick (TRIVIAL/SIMPLE work) bypasses every quality gate: no behavioral evals, no eval-file-mapping match, no
enum/component pre-checks, and it hard-codes complexity= TRIVIAL into telemetry regardless ...
agent-discipline
enhancement
P1
New SN OPEN_BOUNTY detected:
1505292 Memes 2 574 1000 3 7.9 51481 4041 recent@Memes|top@Memes OPEN_BOUNTY,LOW_COMP,SIGNAL Meme Bounty - Thanks to REUTERS
bounty
radar
sn
github-actions[bot]
Live GWAY-003 post-burn validation found gaps that were not covered by PR 8608:
- Satellite image had OCPP_AUTHORIZATION_POLICY=open in arthexis.env, but Django settings did not expose that env var, ...
arthexis
Description
Update copilot instructions file and add a new agent.md file to the repository.
How to test / Verify
!-- Optional: brief verification steps, acceptance criteria, or CI checks to confirm ...
enhancement
felixnagele
Problem
The repo that enforces quality gates on every other project has no code-quality CI on itself.
.github/workflows/validate.yml checks shell syntax, JSON validity, and hook paths — it never runs ...
enhancement
P1
tests
Problem
All 15 behavioral evals (E01–E15) are prose checklists executed from LLM memory during PROVE. Reliability depends on
model attention; there is no mechanical floor. At least five are mechanically ...
agent-discipline
enhancement
P1
tests
Problem
PROVE produces high-quality verdict artifacts (status: PASS|FAIL|BLOCKED, ac_audit arrays) but nothing enforces them at
ship time. /ship does not read the PROVE artifact; a FAIL verdict is purely ...
agent-discipline
enhancement
P0
Critérios:
- [ ] Perfis
- [ ] ADMIN
- [ ] PARTICIPANT
- [ ] Senhas
- [ ] Criptografadas
- [ ] Usar autorização por
- [ ] Anotações
- [ ] Regra de configuração
Tarefas: ...
araujofs
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.
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.