|
1 | 1 | # Zoo Code Changelog |
2 | 2 |
|
| 3 | +## [3.94.0] |
| 4 | + |
| 5 | +- ✨ **Broader model and provider support:** Use Claude Haiku 5.5 through Anthropic, send images to compatible VS Code LM models, tune temperature for OpenCode Go Responses models, and cancel requests cleanly across more providers. |
| 6 | +- 🔐 **More flexible MCP OAuth:** Configure static OAuth client settings, use custom callback paths, discover authentication details from `WWW-Authenticate`, and see callback failures before retrying. |
| 7 | +- 🧭 **Smoother chats and long sessions:** Rename tasks in history, drag files into chat without holding Shift, reduce memory retained during long sessions, and keep subtask links and replaced webviews stable. |
| 8 | + |
| 9 | +### Broader Model and Provider Support |
| 10 | + |
| 11 | +- Add Claude Haiku 5.5 to the Anthropic provider (#2208 by @app/zoomote2, PR #2212 by @app/zoomote2) |
| 12 | +- Add runtime image input support to VS Code language models (PR #2159 by @simurg79) |
| 13 | +- Add image input conversion and shim data parts for VS Code language models (PR #2196 by @simurg79) |
| 14 | +- Update VS Code language model metadata and regression tests (PR #2255 by @simurg79) |
| 15 | +- Add opt-in temperature support for OpenCode Go Responses models (#2055 by @AntzCode, PR #2160 by @AntzCode) |
| 16 | +- Add abort-signal support for Anthropic, Anthropic Vertex, xAI, and MiniMax (PR #1293 by @easonLiangWorldedtech) |
| 17 | +- Add abort-signal support for VS Code language models (PR #1300 by @easonLiangWorldedtech) |
| 18 | +- Add abort-signal support for Gemini, Mistral, and LiteLLM (PR #1303 by @easonLiangWorldedtech) |
| 19 | +- Add ensureModelFetched to the six catalog providers (PR #2191 by @p12tic) |
| 20 | +- Resolve the CLI model ID through provider definitions (PR #2192 by @p12tic) |
| 21 | +- Count compatible cache reads for OpenAI (#1591 by @GeenccMustafa, PR #1662 by @PierrunoYT) |
| 22 | + |
| 23 | +### More Flexible MCP OAuth |
| 24 | + |
| 25 | +- Add static OAuth client settings for MCP servers (#2096 by @SoccerField24x7, PR #2129 by @SoccerField24x7) |
| 26 | +- Support custom MCP OAuth callback paths and WWW-Authenticate discovery (#2218 by @sdbrother0, PR #2219 by @sdbrother0) |
| 27 | +- Report MCP OAuth callback failures before retrying (#2187 by @SoccerField24x7, PR #2238 by @SoccerField24x7) |
| 28 | + |
| 29 | +### Smoother Chats and Long Sessions |
| 30 | + |
| 31 | +- Rename tasks in history (#2112 by @designPrj, PR #2122 by @designPrj) |
| 32 | +- Allow dragging files into the chat input without holding Shift (#2139 by @juneleung, PR #2184 by @app/zoomote2) |
| 33 | +- Reduce chat memory retained during long sessions (PR #2217 by @app/zoomote2) |
| 34 | +- Preserve subtask link identities (PR #2228 by @simurg79) |
| 35 | +- Dispose view listeners and ignore stale views when the webview is replaced (#2205 by @edelauna, PR #2213 by @app/zoomote2) |
| 36 | +- Replace dispatch lock booleans with DispatchState (#374 by @edelauna, PR #2198 by @edelauna) |
| 37 | +- Treat apiConfiguration as always defined in the webview (PR #2234 by @p12tic) |
| 38 | + |
| 39 | +### Testing and Repository Automation |
| 40 | + |
| 41 | +- Use the real VS Code toolkit in Playwright visual baselines (#2105 by @edelauna, PR #2163 by @app/zoomote2) |
| 42 | +- Fix five webview visual tests that failed on every pull request (#2206 by @edelauna, PR #2209 by @app/zoomote2) |
| 43 | +- Link review gate Details to the workflow run (PR #2204 by @app/zoomote2) |
| 44 | +- Move the release kickoff to 12pm EST (PR #2190 by @app/zoomote2) |
| 45 | + |
| 46 | +### Dependencies and Maintenance |
| 47 | + |
| 48 | +- Update build, lint, and test tooling (PR #2101 by @app/renovate) |
| 49 | +- Update AI SDK core and providers (PR #2103 by @app/renovate) |
| 50 | +- Update @modelcontextprotocol/sdk to v1.32.0 [security] (PR #2131 by @app/renovate) |
| 51 | +- Update @next/eslint-plugin-next to v15.5.28 (PR #2132 by @app/renovate) |
| 52 | +- Update @types/node (PR #2135 by @app/renovate) |
| 53 | +- Update esbuild-wasm to v0.28.2 (PR #2137 by @app/renovate) |
| 54 | +- Update undici to v6.29.1 [security] (PR #2169 by @app/renovate) |
| 55 | + |
| 56 | +### Housekeeping |
| 57 | + |
| 58 | +- Merge the **previous v3.92.0 release preparation** after its publication; this is prior-release housekeeping, not a v3.94.0 feature (PR #2166 by @taltas) |
| 59 | + |
3 | 60 | ## [3.92.0] |
4 | 61 |
|
5 | 62 | - ✨ **Faster model choice and stronger model support:** Switch models from the chat composer. Use Claude Haiku 5.5 on Amazon Bedrock, get more accurate Kimi K3 capabilities on OpenRouter, and use corrected Gemini 4 Argon limits on Vercel AI Gateway. |
|
0 commit comments