Playbooks · Coding tasks
Kimi Code 2.6.0 canary: read the label
Written November 12, 2026
A 2.6.0 canary is not a 2.6.0 release. The newest entry on Kimi Code's releases page is a pre-release with a real change list, and the stable line is still 2.5.3. Stay on stable unless you are testing for Moonshot.
What a canary means here
Moonshot publishes Kimi Code canaries as pre-releases on the Kimi Code releases page: the 2.6.0 canary line has been rolling since early November, with dated tags such as 2.6.0-canary.20261109 and 2.6.0-canary.20261111 in the page's own changelog links, and the newest entry sits above them, marked Pre-release. A canary is a channel build for people willing to hit unfinished changes early. It is not the version a team should roll out, and nothing in it is promised to survive into a stable 2.6.x.
Keep the lines separate. The 2.5.x line is the CLI's stable line, and 2.5.3, which added steering, is still its current release. The 1.3.x line is Kimi Code Desktop, a different product surface. A 2.6.0 canary headline says nothing about either.
What the newest canary lists
Two minor changes lead the entry. File suggestions (fs:suggest) now align with local fd completion: bounded scans, at most 20 results, optional streamed previews, hidden and gitignored paths included by default, and regular files placed first at equal match quality. In fullscreen mode, consecutive tool calls and thinking now fold into summary lines, and the Activated skill card no longer shows for skills the model loads. Both folds can be set under Tool call density and Thinking folding in /settings, or with tool_call_density = "ungrouped" and thinking = "ungrouped" in tui.toml to keep the previous layout.
The patch list is long. The useful parts, in the order a daily user would notice them:
- The activity bar shows how long the current turn has been running, and, once it completes, how long the last turn took and when it finished.
- Multiple Edit calls to the same file are no longer forbidden, and a re-read of the file is no longer required before each Edit.
- Copying outside SSH and mosh now goes only to the system clipboard instead of also going through the terminal. Set
KIMI_CODE_CLIPBOARD_OSC52=1to keep the old behaviour. - Skills reload when files in explicitly selected skill directories change.
- Crashes when starting commands in long Windows paths, and file searches in long Windows directories, are fixed.
Server API changes in the same entry
Builders driving Kimi Code through its server API get breaking changes, which is exactly what a canary is for. Sessions now receive their agent profile, model and thinking level when created, and prompts no longer accept profile: pass agent_config.profile when creating the session instead. Context compaction is reported as a compacting flag on the WebSocket agent frame, and a manual compaction requested while another is running now returns an error instead of being silently ignored. File-history queries take turn_number rather than turn_id. The server also stops sending stack traces in error responses, and reports a missing provider, credential or model as a setup error instead of an internal error. Duplicate background task notifications after a resume or undo are prevented.
Limits
- Every item above is a pre-release listing. Canary changes can be revised or dropped before a stable 2.6.x exists, and the canary's own notes are the only promise made.
- The API changes break existing integrations on purpose, ahead of the stable line. Code written against the canary's session and file-history shapes may need the same work again.
- Nothing here updates the Desktop line or the stable CLI. If your work depends on Kimi Code behaving the same tomorrow as today, 2.5.3 is the version that offers that.
Related playbooks
- Kimi Code 2.5.3: steer a running session
- Kimi K3.1 Pro weights are out: what 1.56 TB buys
- Run Kimi, GLM and DeepSeek in the harness you have
- The 83% AI diagnosis headline, read properly
Sources
Back to: Coding playbooks hub · Also: Kimi Code 2.5.3: steer a running session