What's Changed
- fix(models): include GPT5.2 series in verbosity check by @EurFelux in #12003
- 🐛 fix(mcp): check system npx/uvx before falling back to bundled binaries by @vaayne in #12018
- fix(parameterBuilder): enhance urlContext validation for supported providers and models by @sxjeru in #12046
- fix(azure-openai): normalize Azure endpoint by @WilliamWang1721 in #12055
- fix(prompt): remove unprofessional reward text and improve language instruction clarity by @EurFelux in #12054
- feat:upgrade ovms to 2025.4, add preset-model Qwen3-4B-int4-ov by @makejiang in #12045
- feat(history-search): show keyword-adjacent snippets and align matching text by @atoz03 in #12034
- refactor: change qrcode landrop to lantransfer by @eeee0717 in #11968
- feat(icons): add MCP logo and replace Hammer icon by @kangfenmao in #12061
- feat: add openrouter support and update migration version to 188 by @DeJeune in #12059
- fix(options): add support for persistent server configuration in OpenAI provider options by @DeJeune in #12058
- fix: update default assistant settings to disable temperature by @DeJeune in #12069
- feat: add GLM-4.7 and MiniMax-M2.1 model support by @GeorgeDong32 in #12071
- fix(memory): fix retrieval issues and enable database backup by @kangfenmao in #12073
- refactor(websearch): redesign settings with two-column layout by @kangfenmao in #12068
- refactor(notes): move notes settings to popup in NotesPage by @kangfenmao in #12075
- fix: interleaved thinking support by @DeJeune in #12084
- fix(display): improve font selector for long font names by @beyondkmp in #12100
- fix(openrouter): support GPT-5.1/5.2 reasoning effort 'none' for OpenRouter and improve error handling by @EurFelux in #12088
- feat: close ovms process when app quit by @makejiang in #12101
- fix: correct aihubmix anthropic API path by @0xfullex in #12115
- feat:dmx-painting-add-extend_params by @jin-wang-c in #12098
New Contributors
Full Changelog: v1.7.6...v1.7.7