What's Changed
- fix(mcp): create fresh MCP Server per transport session by @DeJeune in #13631
- fix: route copilot gpt-5.4 models to responses by @kovsu in #13632
- fix(aiCore): improve PDF processing robustness for aggregator providers by @EurFelux in #13641
- fix: add @napi-rs/canvas to avoid dependency missing on dev startup by @alephpiece in #13685
- 🤖 Daily Auto I18N Sync: Mar 21, 2026 by @github-actions[bot] in #13673
- fix: skip thinking budget subtraction for Claude 4.6 adaptive thinking models by @majiayu000 in #13676
- fix(agents): show reasoning effort button for agent session reasoning models by @DeJeune in #13569
- fix(linkConverter): enhance link parsing to handle invalid parenthesized links by @alephpiece in #13688
- fix(migrate): safer openclaw state access in migrate 197 by @alephpiece in #13686
- fix: align agent chat bubble layout with shared chat styles by @kovsu in #13633
- chore: bump mermaid to 11.13.0 to support venn and ishikawa by @alephpiece in #13695
- fix: agent session auto renaming feedback by @alephpiece in #13707
- feat(agents): upgrade Agent SDK, enable ToolSearch, and add UI renderer by @DeJeune in #13690
- chore: enable type-aware linting with oxlint upgrade by @EurFelux in #13689
- fix: resolve all await-thenable lint violations by @EurFelux in #13712
- feat(agent): add OpenRouter support for Agent mode by @GeorgeDong32 in #13716
- test: add vitest benchmarks by @alephpiece in #13713
- fix(citation): use position-based insertion for Gemini grounding supports by @DeJeune in #13646
- refactor(SelectModelPopup): use the same base popup for chat and agent pages by @alephpiece in #13700
- fix: override @napi-rs/canvas to 0.1.97 for Windows ARM64 support by @EurFelux in #13723
- 🤖 Daily Auto I18N Sync: Mar 23, 2026 by @github-actions[bot] in #13728
- fix(memory): fix agentId filtering and search fallback in vector memory by @Pleasurecruise in #13725
- fix(groq): add dedicated @ai-sdk/groq provider to avoid reasoning_content errors by @DeJeune in #13735
- fix: topic message bulk deletion by @alephpiece in #13718
- refactor: resolve all no-floating-promises lint violations by @EurFelux in #13743
- fix(aiCore): fix temperature/topP incorrectly disabled when reasoning_effort is default by @EurFelux in #13505
- fix(deps): add @napi-rs/canvas platform binaries to fix startup crash by @kangfenmao in #13759
- fix(agent): use containerRef from useScrollPosition to memorize scroll position by @EurFelux in #13744
- feat: show model ids for duplicate names in model pickers by @kovsu in #13654
- fix: prevent CherryAI provider from using native PDF input in middleware by @kangfenmao in #13777
- fix(paintings): fix base64 image handling across providers by @Pleasurecruise in #13747
- feat: introduce changeset for monorepo version management by @EurFelux in #12783
- feat(code-tools): add LMStudio and Ollama support for Claude Code by @GeorgeDong32 in #13518
- feat: add onboarding page with guided setup flow by @kangfenmao in #13774
- fix: use per-model context window and preserve user config in OpenClaw sync by @SiinXu in #13666
- fix(CodeToolsService): prevent command injection on Windows by @GeorgeDong32 in #13677
- refactor: add no-unnecessary-type-assertion rule and remove redundant assertions by @EurFelux in #13741
- fix: add API key placeholders for LM Studio and Ollama in OpenClaw and Claude Code by @DeJeune in #13552
- fix(agent): stop thinking timer on abort by emitting abort stream part by @DeJeune in #13568
- chore: release v1.8.3 by @kangfenmao in #13788
New Contributors
- @majiayu000 made their first contribution in #13676
Full Changelog: v1.8.2...v1.8.3