What future-agi/future-agi shipped
Written by FoxPlug from public releases; not affiliated with Futureagi. An automatic summary of the public release, pull request and commit data of github.com/future-agi/future-agi. Futureagi did not write it and does not use or endorse FoxPlug. Every line links to the public change it describes.
Get a weekly update like this for your product, free
Week of September 21, 2026
What shipped
- Fixed self-hosted installs sending organization API keys to futureagi.com by correcting BASE_URL defaults. Pull request #3093
- Removed anonymous write, delete and list permissions on the bundled MinIO bucket, leaving only read access for browsers. Pull request #3094
- Tightened input validation in model hub evaluation usage sorting and choice statistics queries. Pull request #3099
- My Environments list now polls while a row is building or running instead of requiring a page reload. Pull request #3084
- Added ability to stop a live run from the runs table and run detail header in v3 Environments. Pull request #3049
- Restored Observe credentials passed into hosted sandbox on feat/environment-v3 branch. Pull request #3088
- Pinned a frozen MinIO build for self-hosted installs after Docker Hub deleted minio/minio images. Pull request #3056
- Made code executor's local fallback explicit by only falling back when the service is unreachable, not on any error. Pull request #3069
- Fixed backend CI failing on fork PRs by skipping telemetry schema contract when private EE code is absent. Pull request #3054
- Released v1.41.1 with frontend and OSS fixes. Release
Why it matters
Security fixes prevent leaking API keys from self-hosted installs and remove unintended anonymous bucket access. Environment polling and stop functionality improve the v3 Environments experience. Fixes to CI and build reproducibility help contributors and self-hosters.
Changelog entry
- security: stop self-hosted installs sending the org API key to futureagi.com Pull request #3093
- security: stop granting anonymous write, delete and list on the MinIO bucket Pull request #3094
- fix(model-hub): validate the eval usage sort column and bind choice-stats choices Pull request #3099
- fix(simulate): pass Observe credentials into the hosted sandbox again Pull request #3088
- fix(evals): make the code executor's local fallback explicit Pull request #3069
- fix(simulate): show a built environment as Ready, never Completed Pull request #3087
- fix(simulate): keep column lines on the run table's last row Pull request #3086
- fix(simulate): honour the sandbox provider's egress limit when starting a chat runtime Pull request #3085
- feat(simulate): poll the My Environments list while a row is building or running Pull request #3084
- fix(frontend): retire the prototype routes and repoint get-started links Pull request #3078
- fix(simulate): explain why Build environment is disabled Pull request #3076
- fix(oss): explain failed pre-flight checks and keep the launch moving Pull request #3068
- feat(simulate): prev/next in the chat drawer; fix the crash on hosted chat transcripts Pull request #3071
- feat(simulate): prev/next in the run call drawer, following the grouped rows Pull request #3066
- fix(simulate): remove em dashes and label run analytics by modality Pull request #3070
- fix(simulate): hide the eval cost chip in the evaluations UI Pull request #3073
- feat(error-feed): include source names in worker claims Pull request #3043
- fix(simulate): scenario editors follow the editing contract, with served choices and labels Pull request #3046
- fix(simulate): show Finalizing and Cancelling states and gate Run on completed Pull request #3062
- fix(simulate): show a stopped run as Cancelling until the backend confirms it Pull request #3060
v1.41.1 ships security fixes for self-hosted installs and improves v3 Environments with live run control and auto-polling.
v1.41.1 is out. We fixed critical security issues in self-hosted installs—API keys no longer leak to cloud, and anonymous MinIO access is removed. v3 Environments now let you stop live runs from the UI and the list auto-polls during builds. Better contributor experience with improved CI.
Week of September 14, 2026
What shipped
- v1.38.4 released with fixes for eval-tasks: gating errored/skipped requeue on terminal watermark, sniffing URL type across chunks, and stopping continuous tasks from re-running converged failures on every poll. Release
- Fixed continuous eval tasks re-running converged failures on every poll, which was causing ~700 GB/day of S3 egress in production. Pull request #2846
- Renamed the 'RL Environment' label to 'Environment' in the harness feature under Simulate. Pull request #2863
- v1.38.3 hotfix released with batching of changed span identities below query size limit and fixes for dense continuous and sparse historical selection. Release
- v1.38.2 released with fixes to apply Dataset and Eval Source filters to eval metric charts. Release
- Fixed system eval binding config to preserve dataset-bound evaluation configuration when reopening and saving existing evaluations. Pull request #2621
- Promoted dev to main for v1.38.4 release with 16 commits including eval alert threshold scaling fixes. Pull request #2866
- Reworked eval alert thresholds to label them as 0-1 fractions instead of 0-100 percent on the backend. Pull request #2497
Why it matters
This week shipped critical stability fixes for eval-tasks that were causing excessive cloud storage egress in production. Multiple releases addressed filtering issues on dashboards and preserved evaluation configuration across saves. The project continues to refine alert thresholds and evaluation handling.
Changelog entry
- v1.38.4: Gate errored/skipped requeue on terminal watermark, sniff URL type across chunks, stop continuous tasks re-running converged failures every poll Release
- v1.38.3: Batch changed span identities below query size limit, bound remaining continuous candidate queries, hotfix dense continuous and sparse historical selection Release
- v1.38.2: Apply Dataset and Eval Source filters to eval metric charts Release
- fix(eval-tasks): Stop continuous tasks re-running converged failures every poll by gating requeue on terminal watermark Pull request #2846
- chore(harness): Rename 'RL Environment' label to 'Environment' in Simulate feature Pull request #2863
- fix(evals): Preserve system eval binding config when reopening and saving existing evaluations Pull request #2621
- fix(alerts): Label eval alert thresholds as 0-1 fractions instead of 0-100 percent Pull request #2497
- fix(dashboards): Apply Dataset and Eval Source filters to eval metric charts Pull request #2724
v1.38.4 is out with fixes for eval-task requeue storms that were costing ~700 GB/day in S3 egress. Also includes dashboard filter fixes and label improvements.
This week we shipped v1.38.4 with critical fixes for continuous eval-tasks that were re-running converged failures on every poll cycle, causing ~700 GB/day of unnecessary S3 egress in production. We also fixed dashboard filters not applying to eval metric charts and improved the harness UI labeling. Multiple hotfixes ensure stability across the evaluation pipeline.