You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
{{ message }}
Repository navigation
Commit f1aba90
Browse filesBrowse the repository at this point in the historyBrowse files
Copy file name to clipboardExpand all lines: CHANGELOG.md
+45Lines changed: 45 additions & 0 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -1,5 +1,50 @@
1
1
# Zoo Code Changelog
2
2
3
+
## [3.86.0]
4
+
5
+
- ✨ **New model support:** Use GPT-6.1 Sol, get the corrected Claude Opus 5.5 output budget, and select DeepSeek V4.1 Flash on OpenCode Go.
6
+
- 🧭 **Reliable task aborts and interruptions:** Preserve the first abort reason, reset stream-abort state for each request, and stop interrupted tasks from replaying rejected subtasks.
7
+
- 🛠️ **Dependable tools, prompts, and UI streaming:** Keep streamed tool arguments intact, enforce MCP tool policy, prevent invented line numbers, and smooth chat updates.
8
+
9
+
### Model Support
10
+
11
+
- Add GPT-6.1 Sol support for OpenAI (#1863 by @WebMad, PR #1864 by @WebMad)
12
+
- Correct the Claude Opus 5.5 output budget (#1853 by @jaszhix, PR #1854 by @jaszhix)
13
+
- Add DeepSeek V4.1 Flash metadata for OpenCode Go (#1648 by @carloslato, PR #1659 by @PierrunoYT)
14
+
15
+
### Task Reliability
16
+
17
+
- Preserve the first abort reason when a task stops (#1802 by @edelauna, PR #1811 by @edelauna)
18
+
- Reset stream-abort state for each API request (#1801 by @edelauna, PR #1812 by @edelauna)
19
+
- Prevent interrupted tasks from replaying rejected subtasks (#1714 by @huankimtran, PR #1726 by @edelauna)
20
+
21
+
### Tools, Prompts, and Streaming
22
+
23
+
- Preserve streamed native tool-call arguments across partial chunks (#695 by @awschmeder, PR #700 by @awschmeder)
24
+
- Truncate VS Code LM tool results safely within the context window (PR #1606 by @simurg79)
25
+
- Validate native MCP tool calls through the shared tool-policy layer (#1646 by @DaubnerF, PR #1724 by @DaubnerF)
26
+
- Prevent invented line numbers in `apply_diff` prompts (PR #641 by @faitno)
27
+
- Warn against including line numbers in `search_replace`, `edit_file`, and `read_file` inputs (#716 by @edelauna, PR #1685 by @myk1yt)
28
+
- Batch repeated tool preambles in the chat UI (#1656 by @petersjostrom, PR #1658 by @PierrunoYT)
29
+
- Avoid flushing throttled UI state for partial say messages (#1851 by @daewoongoh, PR #1852 by @daewoongoh)
30
+
- Keep markdown-sourced open-file requests inside the workspace (PR #1762 by @easonLiangWorldedtech)
31
+
- Use `127.0.0.1` for the development server to avoid IPv6 localhost resolution issues (#1588 by @hnbdr, PR #1589 by @hnbdr)
32
+
33
+
### Code Index and Maintenance
34
+
35
+
- Introduce workspace scopes behind the code-index registry (PR #1766 by @WebMad)
36
+
- Add code-index feature scopes and centralize status subscriptions (PR #1768 by @WebMad)
37
+
- Centralize code-index workspace scopes and enablement (PR #1778 by @WebMad)
38
+
- Use immutable code-index configuration snapshots (#1788 by @WebMad, PR #1815 by @WebMad)
39
+
- Separate code-index service factories and embedder validation (#1816 by @WebMad, PR #1818 by @WebMad)
40
+
- Extract code-index scan execution without changing behavior (#1819 by @WebMad, PR #1834 by @WebMad)
41
+
- Extract code-index single-file preparation (PR #1836 by @WebMad)
42
+
- Update `lru-cache` to 11.5.3 (PR #1583 by @app/renovate)
43
+
- Update Mocha to 11.8.0 (PR #1585 by @app/renovate)
44
+
- Document P1 persisted ownership and the run-state kernel target architecture (PR #1706 by @app/zoomote)
45
+
- Add a community-approved label for community code approvals (#1872 by @edelauna, PR #1873 by @app/zoomote)
46
+
- Merge the **previous v3.84.0 release preparation** after its publication; this is prior-release housekeeping, not a v3.86.0 feature (PR #1810 by @taltas)
47
+
3
48
## [3.84.0]
4
49
5
50
- ✨ **New SOTA models added:** Use GPT-6 Sol, GPT-6 Luna, and Claude Opus 5.5 across supported providers.
Copy file name to clipboardExpand all lines: CONTRIBUTING.md
+1-1Lines changed: 1 addition & 1 deletion
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -134,7 +134,7 @@ pnpm install
134
134
135
135
### Review Process
136
136
137
-
Ready-for-review PRs must pass required CI checks, address actionable review feedback, and receive fresh maintainer or CODEOWNER approval after automated review completes for the latest commit. Automated review may add a guidance comment and managed state labels; contributors should follow the indicated next step rather than editing those labels directly. New commits reset review state for the updated code.
137
+
Ready-for-review PRs must pass required CI checks, address actionable review feedback, and receive fresh maintainer or CODEOWNER approval after automated review completes for the latest commit. Automated review may add a guidance comment and managed state labels; contributors should follow the indicated next step rather than editing those labels directly. New commits reset review state for the updated code. A `community-approved` label marks a fresh community approval on the latest commit while the PR waits for maintainer review. It is an advisory priority signal for maintainers; it does not replace maintainer review or any required check, and it is managed by the review workflow.
138
138
139
139
Automated review supports maintainers but does not replace human approval. Outside contributors cannot direct CodeRabbit through comments; eligible reviews restart automatically after required CI passes, and maintainers handle any exceptional restart. Warnings are advisory unless repository policy says otherwise, and native GitHub required-check, CODEOWNER, and review protections remain authoritative for merging.
Copy file name to clipboardExpand all lines: README.md
+4-4Lines changed: 4 additions & 4 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -46,11 +46,11 @@ Zoo Code builds on the foundation created by Roo Code and continues to expand it
46
46
-**More dependable terminal and editing workflows** — fixes for premature terminal completion, task-state races, context management, diff editing, and provider-specific tool use.
47
47
-**More control over your workspace** — rules management, per-mode MCP restrictions, multi-root path controls, model reasoning options, and completion change review actions.
48
48
49
-
## What's New in v3.84.0
49
+
## What's New in v3.86.0
50
50
51
-
- ✨ **New SOTA models added:** Use GPT-6 Sol, GPT-6 Luna, and Claude Opus 5.5 across supported providers.
52
-
- 🧭 **More reliable tasks and subtasks:**Keep delegated modes isolated, preserve subtask links after repeated stops, and protect orchestrator settings when slash commands switch modes.
53
-
- 🛠️ **More dependable terminal, provider, and code-search behavior:**Improve terminal behavior across Windows and non-English environments, strengthen provider responses and cancellation, and make code search use the correct workspace more consistently.
51
+
- ✨ **New model support:** Use GPT-6.1 Sol, get the corrected Claude Opus 5.5 output budget, and select DeepSeek V4.1 Flash on OpenCode Go.
52
+
- 🧭 **Reliable task aborts and interruptions:**Preserve the first abort reason, reset stream-abort state for each request, and stop interrupted tasks from replaying rejected subtasks.
53
+
- 🛠️ **Dependable tools, prompts, and UI streaming:**Keep streamed tool arguments intact, enforce MCP tool policy, prevent invented line numbers, and smooth chat updates.
0 commit comments