Skip to content
Navigation Menu
Sign in
Products
Platform
GitHub
Repository hosting, code review, and collaboration
Copilot
AI coding agent for tasks, projects, and automated work
Build & Ship
Actions
CI/CD and automation
Code Quality
Quality analysis, fixes, and enforcement
Codespaces
Cloud development environments
Secure
Code Security
Vulnerability detection and remediation
Secret Protection
Secret scanning and leak prevention
All Features
Developers
Learn
Documentation
Training
Certifications
Build
Build with Copilot
Customize Copilot
Integrations
Explore
Trending repos
GitHub Sponsors
Developer articles
Changelog
Changelog
Your source for the latest features, improvements, and fixes across GitHub products, all in one place.
Businesses
By Stage
Enterprises
Team
Startups
Nonprofits
By Industry
Healthcare
Financial services
Manufacturing
Government
See all industries
Evaluate GitHub
Why GitHub
Customer Stories
Business insights
Trust Center
Add-ons
GitHub Advanced Security
Enterprise-grade code security
Copilot for business
Enterprise-grade AI features
Premium Support
Enterprise-grade 24/7 support
Resources
Learn & Connect
Documentation
Resource center
Blog
Events & webinars
Community Forum
Customer Stories
Integrations
Support
Customer support
Training
GitHub Status
Company
About
Partners
Changelog
GitHub Universe
GitHub Universe
The event for developers, by developers — talks, workshops, and what’s next for GitHub.
Pricing
Search
/
Sign in
Sign up
Appearance settings
You signed in with another tab or window.
Reload
to refresh your session.
You signed out in another tab or window.
Reload
to refresh your session.
You switched accounts on another tab or window.
Reload
to refresh your session.
Dismiss alert
{{ message }}
humanitylabs-org
wizard-agent-service
Repository navigation
Code
Issues
8
(8)
Pull requests
66
(66)
Actions
Projects
Security and quality
Insights
More
items
All pull requests
Labels
24
(24)
Milestones
0
(0)
New pull request
Search pull requests
is
:
pr
state
:
open
is:pr state:open
Clear filter
Search
Pull requests
Open
66
(66)
Closed
279
(279)
Author
Label
Projects
Milestones
Reviews
Assignee
Sort by
Newest
descending
Sort…
Sort by Newest descending
More items
Comfortable display density
Compact display density
Recommended fix: recover extra agents on rootless Docker safely
tier: recommended fix
#358
·
defleur-agents
opened
Nov 5, 2026
Collaborator
·
·
Recommended fix: extra agents run on rootless Docker and a host .claude login
tier: recommended fix
#357
·
oscarhenrycollins
opened
Nov 5, 2026
Member
·
·
9
Maintenance: make AGENTS.md a self-sufficient entry point for agents (docs only)
tier: maintenance
#352
·
defleur-agents
opened
Nov 5, 2026
Collaborator
·
·
8
Recommended fix: gateway asks keyed apps for each agent's own tool list
tier: recommended fix
#349
·
oscarhenrycollins
opened
Nov 5, 2026
Member
·
·
2
Recommended fix: shared Look and Pages saves work in the host container
tier: recommended fix
#346
·
defleur-agents
opened
Nov 4, 2026
Collaborator
·
·
1
Recommended fix: bound tool-list caching to complete discovery
tier: recommended fix
#342
·
defleur-agents
opened
Nov 4, 2026
Collaborator
·
·
Fix: agent-neutral run identity and thread self-topics
#341
·
defleur-agents
opened
Nov 4, 2026
Collaborator
·
·
Agent bridge: tools/list carries ttlMs/cacheScope (app tools ready at chat start)
#337
·
oscarhenrycollins
opened
Nov 4, 2026
Member
·
·
6
Feature: keep each reply's plain-words ask on Wizard history rows (reply summary)
tier: strong suggestion
#331
·
oscarhenrycollins
opened
Nov 3, 2026
Member
·
·
10
Recommended fix: keep Ready lists cooperative and evidence reads bounded
tier: recommended fix
#327
·
defleur-agents
opened
Nov 3, 2026
Collaborator
·
·
Recommended fix: isolate list evidence and unrelated run polls
tier: recommended fix
#324
·
defleur-agents
opened
Nov 3, 2026
Collaborator
·
·
Strong suggestion: review attested private search with its runtime companion
tier: strong suggestion
#323
·
defleur-agents
opened
Nov 3, 2026
Collaborator
·
·
Strong suggestion: review temporary private chats on shared main
tier: strong suggestion
#322
·
defleur-agents
opened
Nov 3, 2026
Collaborator
·
·
Recommended fix: apps read only explicitly granted agent notebooks
tier: recommended fix
#321
·
defleur-agents
opened
Nov 3, 2026
Collaborator
·
·
Shell Chats bell via shell-owned typed operations (notifications.count/.items/.mark) \u2014 rehearsal fix, default-off
#318
·
oscarhenrycollins
opened
Nov 2, 2026
Member
·
·
1
Browser boundary card 5: speech-to-text sends the gateway key to the Transcriber (draft)
#317
·
oscarhenrycollins
opened
Nov 2, 2026
Member
·
·
2
Files view under the browser boundary: typed files.* reads, Range tickets, per-chunk-checked upload port (draft, default-off)
#316
·
oscarhenrycollins
opened
Nov 2, 2026
Member
·
·
Apps snapshot flags the reviewed own-tab app (File Browser) (draft, default-off)
#315
·
oscarhenrycollins
opened
Nov 2, 2026
Member
·
·
Recommended fix: keep account-add email matches advisory and retain every grant
tier: recommended fix
#314
·
defleur-agents
opened
Nov 2, 2026
Collaborator
·
·
Shell model picker: one shell-owned typed Claude accounts read; box-local health probes pass the boundary (draft, default-off)
#313
·
oscarhenrycollins
opened
Nov 2, 2026
Member
·
·
Shell intents: typed ChatGPT/Claude account operations, owner confirmation, narrow sign-in navigation (draft, default-off)
#312
·
oscarhenrycollins
opened
Nov 2, 2026
Member
·
·
Claude accounts: one row per account; remove a duplicate sign-in again
#311
·
oscarhenrycollins
opened
Nov 2, 2026
Member
·
·
8
Browser trust card 3: scoped 60 s content tickets for Notifications pictures (default-off, draft)
#310
·
oscarhenrycollins
opened
Nov 2, 2026
Member
·
·
Browser trust card 2: typed inbox and compare-and-set mark for the real Notifications screens (default-off)
#309
·
oscarhenrycollins
opened
Nov 2, 2026
Member
·
·
Browser trust card 3: adapter upstream carries the listener credential, never ambient authority (default-off, draft)
#308
·
oscarhenrycollins
opened
Nov 2, 2026
Member
·
·
Previous
1
2
3
Next
You can’t perform that action at this time.