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
I searched existing issues and did not find a duplicate.
I am describing a concrete problem or use case, not just a vague idea.
Area
apps/server
Problem or use case
T3 Code is doing an amazing job creating a unified API across fast-moving coding-agent harnesses. Projects that need the same session, turn, approval, and event normalization otherwise have to copy and maintain that integration work themselves.
Proposed solution
Would you consider publishing the existing provider contracts and runtime as experimental packages? They can version in lockstep with T3 Code and make breaking changes freely while this ecosystem is moving quickly.
Why this matters
This follows the UnJS philosophy: build a strong, product-independent primitive once and let the ecosystem compose it. Projects such as ViteHub could delete substantial duplicated integration code while provider compatibility work and fixes stay in one shared implementation.
Smallest useful scope
One installable package with the existing provider contracts, runtime, and a documented entry point. No new protocol, plugin system, UI package, or stability promise is needed.
This discussion was converted from issue #6666 on August 15, 2026 09:55.
Heading
Bold
Italic
Quote
Code
Link
Numbered list
Unordered list
Task list
Attach files
Mention
Reference
Menu
reacted with thumbs up emoji reacted with thumbs down emoji reacted with laugh emoji reacted with hooray emoji reacted with confused emoji reacted with heart emoji reacted with rocket emoji reacted with eyes emoji
Uh oh!
There was an error while loading. Please reload this page.
Uh oh!
There was an error while loading. Please reload this page.
Before submitting
Area
apps/server
Problem or use case
T3 Code is doing an amazing job creating a unified API across fast-moving coding-agent harnesses. Projects that need the same session, turn, approval, and event normalization otherwise have to copy and maintain that integration work themselves.
Proposed solution
Would you consider publishing the existing provider contracts and runtime as experimental packages? They can version in lockstep with T3 Code and make breaking changes freely while this ecosystem is moving quickly.
Why this matters
This follows the UnJS philosophy: build a strong, product-independent primitive once and let the ecosystem compose it. Projects such as ViteHub could delete substantial duplicated integration code while provider compatibility work and fixes stay in one shared implementation.
Smallest useful scope
One installable package with the existing provider contracts, runtime, and a documented entry point. No new protocol, plugin system, UI package, or stability promise is needed.
Contribution
All reactions