Follow Discord
Sweep 22 Sep 2026 · 17:19Z Build v2.1.280 501 read Stable v2.1.267 Latest v2.1.280 Next v2.1.280 Feeds RSS JSON llms.txt Unofficial
One change · claude-code

How Claude Code uses prompt caching changed

prompt-caching

Nearest release: v2.1.267, published an hour after this site recorded the change. Shown because the two are within 24 hours of each other. Nothing here says the release caused the edit.

Recorded here
Lines+8added
Lines−2removed
From line 85 where the diff opens
First seen 14 Aug 2026 this site's first read of the page
Recorded edits32to this page, all time

The whole hunk

from line 85, old and new numbered
/
lines
from line 85
8585 
8686The [`opusplan` model setting](/docs/en/model-config#opusplan-model-setting) resolves to Opus during plan mode and Sonnet during execution, so each plan-mode toggle is a model switch and starts a fresh cache.
8787 
88[Automatic model fallback](/docs/en/model-config#automatic-model-fallback) on Fable 5.1, Fable 5, and Opus 5 is also a model switch. When a safety classifier flags a request and the flagged category has a fallback model, Claude Code re-runs the request on that model and the session continues there.
88[Automatic model fallback](/docs/en/model-config#automatic-model-fallback) on Fable models and Opus 5 is also a model switch. When a safety classifier flags a request in a category that has a fallback model, Claude Code re-runs the request on that model and the session continues there.
8989 
90When a skill or command's frontmatter names a [`model`](/docs/en/skills#frontmatter-reference) other than the session's current model, that turn is also a model switch: the next request reads the entire conversation history with no cache hits. The session model resumes on your next prompt. A `context: fork` skill sets the [forked subagent's model](/docs/en/skills#run-skills-in-a-subagent) instead.
91 
9092### Changing effort level
9193 
9294On most models, changing the [effort level](/docs/en/model-config#adjust-effort-level) mid-session means the next request reads the entire conversation history with no cache hits. While the cache is still warm, Claude Code asks you to confirm the change first.
from line 143
141143 
142144When you run `/reload-plugins` and the reload would trigger a full re-read, Claude Code shows a warning and doesn't apply the reload. Rerun it with `--force` to apply the reload anyway.
143145 
146`/reload-plugins` also runs in sessions without an interactive terminal, such as the desktop app, the Agent SDK, and [non-interactive mode](/docs/en/headless) with `-p`, when you type it into the session directly. Requires Claude Code v2.1.260 or later.
147 
148In those sessions the reload applies everything except plugin MCP server changes, which [take effect in your next session](/docs/en/discover-plugins#apply-plugin-changes-without-restarting) and so never cost a full re-read mid-session.
149 
144150#### Plugins you enable and then disable in one session
145151 
146152When you disable a plugin you enabled earlier in the session, Claude Code restores the previous request shape. If that prefix is still within its [cache lifetime](#cache-lifetime), the next request reads the older cache entry instead of rebuilding.
from line 219
213219 
214220### Invoking skills and commands
215221 
216[Skills](/docs/en/skills) and [commands](/docs/en/commands) inject their instructions as user messages at the point of invocation. Nothing earlier in the conversation changes.
222[Skills](/docs/en/skills) and [commands](/docs/en/commands) inject their instructions as user messages at the point of invocation. Nothing earlier in the conversation changes. A skill or command whose frontmatter names a `model` can be a [model switch](#switching-models) for that turn.
217223 
218224### Running `/recap`
219225 
Feedback