This release includes breaking changes for platform teams planning a safe upgrade.
✓ No known CVEs patched in this version
Topics
+9 more
ReleasePort's take
Light signalVersion v4.26.6 adds persona import/export to the WebUI and enables cache control for Anthropic providers, while fixing several UI and response‑handling bugs.
Why it matters: Improves user management workflow via new import/export capability; boosts Anthropic provider performance by raising cache hit rates (ephemeral cache enabled).
Summary
AI summaryUpdates 4.26.6] - 2026-07-14, fix, and platform across a mixed release.
Changes in this release
| Type | Severity | Summary | CVE |
|---|---|---|---|
| Feature | Medium |
Adds persona import and export in the WebUI. Adds persona import and export in the WebUI. Source: llm_adapter@2026-07-14 Confidence: high |
— |
| Performance | Medium |
Enables ephemeral cache control for Anthropic providers to improve cache hit rates. Enables ephemeral cache control for Anthropic providers to improve cache hit rates. Source: llm_adapter@2026-07-14 Confidence: high |
— |
| Bugfix | Medium |
Validates dashboard account username updates. Validates dashboard account username updates. Source: llm_adapter@2026-07-14 Confidence: high |
— |
| Bugfix | Medium |
Removes unsupported `force` argument from LINE response parsing. Removes unsupported `force` argument from LINE response parsing. Source: llm_adapter@2026-07-14 Confidence: high |
— |
| Bugfix | Medium |
Handles invalid response cleanup regex without interrupting message delivery. Handles invalid response cleanup regex without interrupting message delivery. Source: llm_adapter@2026-07-14 Confidence: high |
— |
| Bugfix | Medium |
Fixes mobile chat input freeze and multiline attachment button alignment. Fixes mobile chat input freeze and multiline attachment button alignment. Source: llm_adapter@2026-07-14 Confidence: high |
— |
| Bugfix | Medium |
Makes ChatUI model selection theme‑aware. Makes ChatUI model selection theme‑aware. Source: llm_adapter@2026-07-14 Confidence: high |
— |
| Bugfix | Medium |
Returns appropriate HTTP errors when skill downloads fail. Returns appropriate HTTP errors when skill downloads fail. Source: llm_adapter@2026-07-14 Confidence: high |
— |
| Bugfix | Medium |
Exempts WebChat from the friend wake prefix. Exempts WebChat from the friend wake prefix. Source: llm_adapter@2026-07-14 Confidence: high |
— |
| Bugfix | Medium |
Handles `max_tokens` correctly for NVIDIA MiniMax M3. Handles `max_tokens` correctly for NVIDIA MiniMax M3. Source: llm_adapter@2026-07-14 Confidence: high |
— |
| Bugfix | Low |
Reports current context usage accurately in the token indicator. Reports current context usage accurately in the token indicator. Source: granite4.1:30b@2026-07-14-audit Confidence: low |
— |
| Bugfix | Low |
Resumes active ChatUI streams after a page refresh. Resumes active ChatUI streams after a page refresh. Source: granite4.1:30b@2026-07-14-audit Confidence: low |
— |
Full changelog
4.26.6 - 2026-07-14
Added
- Added persona import and export in the WebUI. Exported personas intentionally exclude tools and Skills configuration. (#4532)
Changed
- Enabled ephemeral cache control for Anthropic providers to improve cache hit rates. (#9197)
- Refined README documentation and corrected the Satori and Mattermost tutorial links. (#9205)
- Updated grouped GitHub Actions dependencies. (#9170)
Fixed
- Validated dashboard account username updates. (#9175)
- Removed an unsupported
forceargument from LINE response parsing. (#9187) - Handled invalid response cleanup regular expressions without interrupting message delivery. (#9183)
- Fixed the mobile chat input freeze and multiline attachment button alignment. (#9202)
- Made ChatUI model selection theme-aware. (#9200)
- Corrected the i18n callback path to Settings General. (#9201)
- Returned appropriate HTTP errors when skill downloads fail. (#9213)
- Exempted WebChat from the friend wake prefix. (#9215)
- Handled
max_tokenscorrectly for NVIDIA MiniMax M3. (#9209) - Reported current context usage accurately in the token indicator. (#9255)
- Resumed active ChatUI streams after a page refresh. (#9259)
What's Changed
- fix: validate dashboard account username updates by @VectorPeak in https://github.com/AstrBotDevs/AstrBot/pull/9175
- fix: remove unexpected force argument from get_json in astrbot\core\platform\sources\line\line_adapter.py" by @SpencerFang0617 in https://github.com/AstrBotDevs/AstrBot/pull/9187
- fix: Added Try Except to Filter Handling by @CooperWang0912 in https://github.com/AstrBotDevs/AstrBot/pull/9183
- fix(platform): correct tutorial links for satori and mattermost by @th-dd in https://github.com/AstrBotDevs/AstrBot/pull/9205
- fix: resolve mobile chat input freeze and multiline attachment button alignment by @leafliber in https://github.com/AstrBotDevs/AstrBot/pull/9202
- fix: make ChatUI model selection theme-aware by @wcqqq1214 in https://github.com/AstrBotDevs/AstrBot/pull/9200
- fix: use ephemeral cache control mode in anthropic provider to increase cache hit rate by @911218sky in https://github.com/AstrBotDevs/AstrBot/pull/9197
- chore(deps): bump the github-actions group with 4 updates by @dependabot[bot] in https://github.com/AstrBotDevs/AstrBot/pull/9170
- fix(i18n): update platform callback path translation by @th-dd in https://github.com/AstrBotDevs/AstrBot/pull/9201
- fix: return HTTP errors for failed skill downloads by @VectorPeak in https://github.com/AstrBotDevs/AstrBot/pull/9213
- fix: exempt WebChat from friend wake prefix by @wcqqq1214 in https://github.com/AstrBotDevs/AstrBot/pull/9215
- fix: handle max_tokens for NVIDIA MiniMax M3 by @Last-emo-boy in https://github.com/AstrBotDevs/AstrBot/pull/9209
- fix: prevent the WebChat token ring from over-reporting context usage by @Fronut in https://github.com/AstrBotDevs/AstrBot/pull/9255
- fix(group_chat_context): use .get() to avoid KeyError when config profile lacks image_caption_prompt by @tsaitang404 in https://github.com/AstrBotDevs/AstrBot/pull/9216
- fix: resume ChatUI streams after refresh by @Soulter in https://github.com/AstrBotDevs/AstrBot/pull/9259
- feat: import and export personas by @Sjshi763 in https://github.com/AstrBotDevs/AstrBot/pull/4532
- chore: bump version to 4.26.6 by @Soulter in https://github.com/AstrBotDevs/AstrBot/pull/9273
New Contributors
- @SpencerFang0617 made their first contribution in https://github.com/AstrBotDevs/AstrBot/pull/9187
- @wcqqq1214 made their first contribution in https://github.com/AstrBotDevs/AstrBot/pull/9200
- @Last-emo-boy made their first contribution in https://github.com/AstrBotDevs/AstrBot/pull/9209
- @tsaitang404 made their first contribution in https://github.com/AstrBotDevs/AstrBot/pull/9216
Full Changelog: https://github.com/AstrBotDevs/AstrBot/compare/v4.26.5...v4.26.6
Weekly OSS security release digest.
The CVE patches and breaking changes that affected production tools this week. One email, every Sunday.
No spam, unsubscribe anytime.
Share this release
About AstrBot
All releases →Related context
Related tools
Earlier breaking changes
- v4.25.3 Upgrades MiniMax Token Plan default model to M3.
Beta — feedback welcome: [email protected]