|
1 | 1 | # Zoo Code Changelog |
2 | 2 |
|
| 3 | +## [3.92.0] |
| 4 | + |
| 5 | +- ✨ **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. |
| 6 | +- 🧭 **More reliable terminal, editing, chat, and remote workflows:** Collapse command output by default when you choose, get clearer editing failures, keep reasoning and API rows visible, and avoid startup and proxy issues in remote workspaces. |
| 7 | +- 🔌 **Expanded MCP marketplace:** Connect Zoo Code to AnySearch, Mailtea, and Tradehand through the MCP marketplace. |
| 8 | + |
| 9 | +### Faster Model Choice and Stronger Model Support |
| 10 | + |
| 11 | +- Add an inline model selector to the chat composer (#1502 by @daewoongoh, PR #2034 by @daewoongoh) |
| 12 | +- Add Claude Haiku 5.5 to the Amazon Bedrock model catalog (PR #2100 by @app/zoomote) |
| 13 | +- Correct Kimi K3 capabilities and reasoning effort on OpenRouter (#1316 by @CodeCruncher88, PR #1325 by @easonLiangWorldedtech) |
| 14 | +- Clamp Gemini 4 Argon to Google's limits on Vercel AI Gateway (PR #2073 by @taltas) |
| 15 | + |
| 16 | +### Terminal, Editing, Chat, and Remote Reliability |
| 17 | + |
| 18 | +- Add abort-signal support to the native Ollama provider (#404 by @Fuzzillogic, PR #1299 by @easonLiangWorldedtech) |
| 19 | +- Fix Destructive Command Guard startup errors in remote workspaces (#1603 by @atoomnetmarc, #1770 by @DaubnerF, PR #1639 by @PierrunoYT) |
| 20 | +- Route the Bedrock code-index embedder through the system proxy (#1772 by @LouisClt, PR #1773 by @LouisClt) |
| 21 | +- Require HTTPS for custom Google Gemini base URLs while allowing loopback HTTP (PR #2033 by @easonLiangWorldedtech) |
| 22 | +- Add a setting to collapse terminal command output by default (#605 by @AmitTzah, PR #2042 by @bigyao25) |
| 23 | +- Report all apply-diff failures with clearer diagnostics (PR #2053 by @simurg79) |
| 24 | +- Keep reasoning and API request rows visible after batched reads (#2061 by @danGO-79, PR #2126 by @PierrunoYT) |
| 25 | + |
| 26 | +### Expanded MCP Marketplace |
| 27 | + |
| 28 | +- Add AnySearch to the MCP marketplace (#1956 by @hieutran0413, PR #1955 by @hieutran0413) |
| 29 | +- Add Mailtea to the MCP marketplace (#2140 by @davepoon, PR #1869 by @davepoon) |
| 30 | +- Add Tradehand to the MCP marketplace (#2121 by @Blakefolgado, PR #2123 by @Blakefolgado) |
| 31 | + |
| 32 | +### Task Lifecycle Reliability |
| 33 | + |
| 34 | +- Add run-state divergence comparison and metrics (RSK-05) (#1795 by @edelauna, PR #2047 by @edelauna) |
| 35 | +- Add the run-state turn sub-machine (RSK-09) (#1800 by @edelauna, PR #2127 by @edelauna) |
| 36 | +- Route task latch and initialization writes through run-state events (RSK-06) (#1796 by @edelauna, PR #2128 by @edelauna) |
| 37 | +- Make Task.create share its startup path and promise with Task.run (#2145 by @edelauna, PR #2146 by @app/zoomote) |
| 38 | + |
| 39 | +### Testing, Performance, and Repository Automation |
| 40 | + |
| 41 | +- Enable Knip production analysis and remove dead code (#519 by @edelauna, PR #527 by @edelauna) |
| 42 | +- Add a trusted evaluation fixture runner and execution traces (#1896 by @edelauna, PR #1909 by @edelauna) |
| 43 | +- Keep the has-conflicts label while GitHub recomputes mergeability (#2045 by @edelauna, PR #2048 by @app/zoomote) |
| 44 | +- Refresh fork PR review-state labels after reviews (#2046 by @edelauna, PR #2049 by @app/zoomote) |
| 45 | +- Add weekly release kickoff automation with maintainer rotation (PR #2075 by @app/zoomote) |
| 46 | +- Base stale PR timing on author activity instead of bot activity (#2076 by @edelauna, PR #2077 by @app/zoomote) |
| 47 | +- Stabilize restart-persistence E2E coverage and improve task-message read errors (#2078 by @edelauna, PR #2080 by @app/zoomote) |
| 48 | +- Prevent the review-state label workflow from listening to itself (#2086 by @edelauna, PR #2088 by @app/zoomote) |
| 49 | +- Freeze review-state labels while GitHub computes mergeability (#2089 by @edelauna, PR #2091 by @app/zoomote) |
| 50 | +- Speed up lint and type checks with caching and staged-only pre-commit lint (#2090 by @edelauna, PR #2092 by @app/zoomote) |
| 51 | +- Keep conflict status separate from review-state turn labels (part of #2089 by @edelauna, PR #2102 by @app/zoomote) |
| 52 | +- Dispatch fork review follow-up using the correct repository metadata (#2133 by @edelauna, PR #2134 by @app/zoomote) |
| 53 | + |
| 54 | +### Dependencies and Maintenance |
| 55 | + |
| 56 | +- Update build, lint, and test tooling (PR #804 by @app/renovate) |
| 57 | +- Update KaTeX to v0.18 (PR #1975 by @app/renovate) |
| 58 | +- Update simple-git to v4 (PR #1976 by @app/renovate) |
| 59 | +- Update Zod to v4 (PR #2029 by @app/renovate) |
| 60 | +- Pin dependencies (PR #2035 by @app/renovate) |
| 61 | +- Update AI SDK core and providers (PR #2071 by @app/renovate) |
| 62 | +- Update @changesets/cli to v2.31.1 (PR #2081 by @app/renovate) |
| 63 | +- Pin dependencies after provider updates (PR #2087 by @app/renovate) |
| 64 | +- Update @eslint/js to v9.39.5 (PR #2094 by @app/renovate) |
| 65 | +- Refresh the lockfile (PR #2097 by @app/renovate) |
| 66 | + |
| 67 | +### Housekeeping |
| 68 | + |
| 69 | +- Merge the **previous v3.90.0 release preparation** after its publication; this is prior-release housekeeping, not a v3.92.0 feature (PR #2074 by @JamesRobert20) |
| 70 | + |
3 | 71 | ## [3.90.0] |
4 | 72 |
|
5 | 73 | - ✨ **Providers and models:** GitHub Copilot is now a provider: sign in and Zoo Code loads your Copilot models. IO Intelligence is a provider with its own API key. Gemini 4 Argon is on Gemini and Vertex. GPT-6 Luna is on OpenCode Go. Gemini 4 Argon and GPT-6 Luna are on Zoo Gateway as well. |
|
0 commit comments