Releasesby GlyphCog 0.20.0
New features cog run command. The cog predict command has been renamed to cog run with full backward compatibility. cog predict still works as an alias. ( #3015 ) Model refs for cog push and weights commands. You can now reference models by name (e.g., r8.im/user/model ) instead of full image URLs when pushing or managing weights.
Also shipped May 19, 2026Replicate in May 2026 →
Gemini 3.1 Flash Lite Now Available
gemini-3.1-flash-lite is now available as a managed Google LLM in the Voice Agent API. This Standard tier model replaces the preview version. Set the model in your agent configuration: { "agent": { "think": { "provider": { "type": "google", "model": "gemini-3.1-flash-lite", "temperature": 0.5 } } } }
Deprecations
- gemini-3.1-flash-lite-preview is deprecated and will be removed on May 26, 2025. Migrate to gemini-3.1-flash-lite . For more details on Gemini model deprecations, see Google's Gemini deprecations page . For the full list of supported models and pricing tiers, see the Voice Agent LLM Models documentation .
DigitalOcean Kubernetes (DOKS) now supports single sign-on (SSO) with OIDC in public preview
DigitalOcean Kubernetes (DOKS) now supports single sign-on (SSO) with OIDC in public preview. You can authenticate users to your Kubernetes clusters through an identity provider like Auth0, JumpCloud, Keycloak, or Okta, instead of using …
Screenshot thumbnails for browser checks in Synthetic Monitoring Timepoint Explorer
When debugging browser check failures like “timeout waiting for a selector”, you previously had to rely on text logs alone to understand what the browser rendered. Now, with screenshot thumbnails in the Timepoint Explorer and ad-hoc test panel, you can see exactly what the page looked like at the moment the check ran.
Search volume for AI Visibility [Beta]
Description: AI Visibility now includes Search Volume so you can prioritize topics and prompts based on real demand, not just where your brand appears. Use it to identify high-volume content opportunities and focus optimization where it matters most. Where: Access via AI Visibility → Prompts tab, Topic-level visibility, and When: Open beta, available now.
Dify 1.14.2 - Security fixes, agent groundwork, workflow reliability, and deployment updates
🚀 What's New in v1.14.2? v1.14.2 is a patch release focused on security hardening, workflow and knowledge reliability, observability fixes, agent groundwork, and deployment/runtime tuning after v1.14.1.
More from CogEvery Cog release →
Cog 0.19.3
Changelog 0780450 Bump version to 0.19.3 ( #2995 ) cac3e91 feat: experimental managed weights ( #2974 )
Cog 0.19.2
Changelog 427d486 Bump version to 0.19.2 ( #2984 ) d9c2b14 fix: cap fuzz test input size to prevent timeout ( #2981 ) 4269575 fix: support typing_extensions TypedDict at runtime ( #2983 )
Cog 0.19.1
Bug fixes Support for TypedDict in schema generation. Fixed an issue where TypedDict type annotations would cause schema generation to fail. ( #2978 ) Build order fix for resource exhaustion. Reordered coglet wheel build to run after cog/sdk builds to prevent resource exhaustion during release builds. ( #2977 ) Maintenance Removed dead Go code.
Cog 0.21.0
New features Server-Sent Event prediction streams. HTTP prediction requests can now ask for Accept: text/event-stream to receive start , output , log , metric , and terminal completed events for predictors that explicitly opt in with @streaming / @cog.streaming .
Cog 0.22.0
Breaking changes Local servers now bind to 127.0.0.1 instead of 0.0.0.0 . cog serve , cog run -p , cog predict , and cog train no longer expose the prediction endpoint to your whole network by default. To get the old behavior back, use cog serve --host 0.0.0.0 or cog run -p 0.0.0.0:8888 , -p now accepts host:port . ( #2812 ) New features Browser playground.
Cog 0.23.0
New features GPU compatibility warnings in cog doctor . cog doctor now warns when the resolved PyTorch and CUDA wheel ships no kernels for the local GPU, catching images that build successfully but fail when they run CUDA operations. ( #3104 ) OpenTelemetry tracing.
Cog 0.23.1
Bug fixes - Predictions now fail when an output upload fails. Previously, a file upload that timed out or was rejected could leave a prediction marked succeeded with output: null, or silently drop files from list outputs. Any failed upload now fails the prediction with an error, and cancellation still reports canceled.