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
Copy file name to clipboardExpand all lines: docs/en/release-notes/changelog.md
+40Lines changed: 40 additions & 0 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -6,6 +6,46 @@ outline: 2
6
6
7
7
This page documents the changes in each Kimi Code CLI release.
8
8
9
+
## 0.24.2 (2026-07-15)
10
+
11
+
### Features
12
+
13
+
- Add a builtin `/check-kimi-code-docs` skill that automatically answers Kimi Code product questions with official-docs sources.
14
+
15
+
### Polish
16
+
17
+
- Align `kimi -p` behavior across engines: `print_background_mode` and `print_max_turns` now apply, and `/goal` runs stay alive until the goal finishes.
18
+
-`kimi -p` now stays alive by default while background tasks are pending, with no effective wait or turn limit, and feeds each completion back to the agent. Set `print_background_mode = "exit"` or `"drain"` to restore the old exit-after-one-turn behavior.
19
+
-`kimi -p` background tasks and subagents no longer time out by default (interactive mode is unchanged); restore limits with `[background] bash_task_timeout_s` or `[subagent] timeout_ms`.
20
+
- Subagent timeout now defaults to 2 hours everywhere; override with `[subagent] timeout_ms` or `KIMI_SUBAGENT_TIMEOUT_MS`.
21
+
- The per-step LLM retry limit is raised from 3 to 10 attempts, so transient provider failures (429 / overload) are retried before a turn fails; tune with `loop_control.max_retries_per_step`.
22
+
- Workspaces now stay in sync: new sessions register automatically, missing workspaces are restored at startup, and removed ones stay removed.
23
+
-`kimi web` now logs failed requests and key operations so daemon issues are easier to diagnose.
24
+
- web: AgentSwarm cards now stay expanded while subagents are still running.
25
+
- web: Minimized plan review and question cards now use an upward chevron for expand.
26
+
27
+
### Bug Fixes
28
+
29
+
- web: Fix mobile layout on iOS, including the composer, safe areas, and toasts.
30
+
- Fix new sessions not opening in older CLI versions.
31
+
- Fix completion notifications firing early when a subagent finished while the main turn was still running.
32
+
- Fix the web UI showing the wrong CLI version.
33
+
- Fix Gemini tool call IDs colliding across turns and merging swarm runs into one card.
34
+
- web: Show server error details when actions like stopping or archiving a session fail.
35
+
- web: Fix long responses stalling after the tab was backgrounded.
36
+
- web: Fix code block copy buttons over plain HTTP.
37
+
- web: Keep loaded sessions visible when the session list fails to reload.
38
+
- web: Restore the AgentSwarm member list after a page refresh.
39
+
- web: Fix session titles not generating when the first message is a slash command.
40
+
- web: Show each message's actual send time after reloading a session.
41
+
- Fix several goal-mode issues around budgets and turn limits, pausing and resuming, crash recovery, final status messages, and invalid persisted goal records.
42
+
- Fix replaced goals being able to affect the new goal's budget, and reject subagent goals consistently.
43
+
- Correct the guidance shown when a goal cannot be paused or resumed.
44
+
45
+
### Refactors
46
+
47
+
- Rename the dynamic tool loading capability from `select_tools` to `dynamically_loaded_tools`; behavior is unchanged.
0 commit comments