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
Events
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 }}
workglow-dev
libs
Repository navigation
Code
Issues
68
(68)
Pull requests
4
(4)
Discussions
Actions
Projects
Security and quality
Insights
More
items
AgentTask harness: agent-eval benchmarks, loop fixes, reasoning replay, and provider parity
- #1015
#1015
Merged
sroussey
merged 13 commits into
main
workglow-dev/libs:main
from
claude/nifty-albattani-rbmooa
workglow-dev/libs:claude/nifty-albattani-rbmooa
Copy head branch name to clipboard
Oct 14, 2026
Conversation
Commits
13
(13)
Checks
Files changed
Merged
AgentTask harness: agent-eval benchmarks, loop fixes, reasoning replay, and provider parity
#1015
sroussey
merged 13 commits into
main
workglow-dev/libs:main
from
claude/nifty-albattani-rbmooa
workglow-dev/libs:claude/nifty-albattani-rbmooa
Copy head branch name to clipboard
Commits
Commits on Oct 14, 2026
feat(ai): AgentTask deadlines, time-left notices, review, reasoning and native-turn storage
Show description for b8ddd53
sroussey
committed
b8ddd53
View commit details
Copy full SHA for b8ddd53
Browse repository at this point
feat(openai,anthropic): hand a model its own turn back each round
Show description for e0e9d71
sroussey
committed
e0e9d71
View commit details
Copy full SHA for e0e9d71
Browse repository at this point
feat(providers): carry reasoning and tool-result images between rounds on cloud APIs
Show description for b6b8d1d
sroussey
committed
b6b8d1d
View commit details
Copy full SHA for b6b8d1d
Browse repository at this point
feat(providers): carry reasoning, tool calls and images between rounds on local runtimes
Show description for 4c7e0bd
sroussey
committed
4c7e0bd
View commit details
Copy full SHA for 4c7e0bd
Browse repository at this point
feat(cli,web): draw a task's reasoning apart from its answer
Show description for 81b7373
sroussey
committed
81b7373
View commit details
Copy full SHA for 81b7373
Browse repository at this point
feat(agent-eval): compare AgentTask with opencode and pi on public benchmarks
Show description for 8f58ee3
sroussey
committed
8f58ee3
View commit details
Copy full SHA for 8f58ee3
Browse repository at this point
ci: CodeQL advanced setup, excluding examples/agent-eval
Show description for ed93901
sroussey
committed
ed93901
View commit details
Copy full SHA for ed93901
Browse repository at this point
fix(agent-eval): enhance time management and credential scrubbing
Show description for 2bd2949
sroussey
committed
2bd2949
View commit details
Copy full SHA for 2bd2949
Browse repository at this point
chore: update deps
sroussey
committed
653ccf8
View commit details
Copy full SHA for 653ccf8
Browse repository at this point
chore: update ink
sroussey
committed
8b31ccb
View commit details
Copy full SHA for 8b31ccb
Browse repository at this point
chore: update deps
sroussey
committed
a6d3fc8
View commit details
Copy full SHA for a6d3fc8
Browse repository at this point
fix(anthropic): add test for handling disabled thinking in native turn
sroussey
committed
9dcb6d6
View commit details
Copy full SHA for 9dcb6d6
Browse repository at this point
fix(truncate): improve handling of newline allowance when truncating text
sroussey
committed
4a348cf
View commit details
Copy full SHA for 4a348cf
Browse repository at this point
You can’t perform that action at this time.
