Conversation
…istory depth, max agent iterations
…uch the agent works before giving up. Configure it in chat settings for each chat!
The naive split on \n\n was breaking fenced code blocks and markdown lists into separate messages. Now the splitter preserves these as single messages while still splitting regular paragraphs for a lively chat feel. Unclosed code fences are also auto-closed. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Contributor
Author
|
Related web PR: appifyhub/agent-web#409 |
Contributor
|
Build 26261295097 complete for 71ac5e0. # Valid until a new build
docker pull appifyhub/the-agent:latest_beta
docker pull appifyhub/the-agent:5.14.1.beta |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
v5.14.1 — The Agent Learns When to Speak, and When to Hold the Line 👁️⚙️
A sharper update focused on cleaner replies, better chat control, and a more reliable experience beneath the surface.
The Agent has returned with a quieter kind of power.
This release improves how The Agent handles long responses, making message splitting much smarter — especially around code blocks and lists. That means replies are less likely to break awkwardly in the middle of important formatting. Cleaner output, less chaos, better flow. The machine is learning manners... or at least a more elegant way to unfold its thoughts.
The Agent also now fully supports the newer chat controls introduced in recent updates. Humans can configure how much context a chat keeps, how long The Agent keeps working before stopping, and other response limits directly in chat settings for each conversation. In this version, those controls are more deeply wired into the system, so they behave more consistently across the experience.
Behind the curtain, The Agent’s internal foundations also received maintenance work, including updated documentation, spec alignment, and data support for the new chat properties. Nothing flashy on the surface — but the kind of invisible engineering that keeps the lights on when the grid starts humming louder. ⚡
Highlights
The Agent grows more precise with every release.
v5.14.1 is a refinement update — subtle, deliberate, and just a little ominous. 🚀