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 capture · claude-code

One read of Claude Code CLI

1 pages moved out of 191 read.

claude-code-20260903T023701Z

Pages moved 1 significant first
Pages read 191 in this capture
Captured 02:37 UTC
Corpus hash a7bf2b6589a0 corpus-hash

What this read moved

1–1 of 1

prompt-caching Changed · +16 / -1 lines

### Accumulating many images

from line 69
6969* [Enabling or disabling a plugin](#enabling-or-disabling-a-plugin)
7070* [Denying an entire tool](#denying-an-entire-tool)
7171* [Compacting the conversation](#compacting-the-conversation)
72* [Accumulating many images](#accumulating-many-images)
7273* [Upgrading Claude Code](#upgrading-claude-code)
7374 
7475### Switching models
from line 158
157158 Compaction works in your favor when the context you discard is content you no longer need. To choose when its overhead happens, run `/compact` at a natural break in your work, such as between tasks, instead of waiting for auto-compaction to trigger mid-task. If you've gone down a path you want to abandon entirely, [`/rewind`](#rewinding-the-conversation) to an earlier turn instead. Rewinding truncates back to a prefix that is already cached, rather than building a new one as compaction does.
158159</Tip>
159160 
161### Accumulating many images
162 
163The API limits how many images and PDFs each request can carry. For the current numbers, see [Request limits](https://platform.claude.com/docs/en/build-with-claude/vision#request-limits) in the API docs. Claude Code also caps the total size of the images and PDFs in a request, so large screenshots reach the limit with fewer images than small ones.
164 
165When the next request would pass either limit, Claude Code removes a batch of the oldest images and PDFs from what it sends, which leaves room for more before it needs to remove any again. Claude can no longer see the removed images. If Claude needs one of them again, share it again.
166 
167Removing images changes the messages that held them, so the next request reprocesses the conversation from the earliest of those messages onward. Because Claude Code removes a batch at a time, you see one slower turn per batch rather than one with each new screenshot.
168 
160169### Upgrading Claude Code
161170 
162171A new Claude Code version typically updates the system prompt or tool definitions, so the first request after an upgrade rebuilds the cache from the top. [Auto-update](/docs/en/setup#auto-updates) downloads new versions in the background but applies them on the next launch, never mid-session, so you see this as an uncached first turn after restarting rather than a surprise during a session. Set `DISABLE_AUTOUPDATER=1` to control when upgrades apply.
from line 296
287296 
288297The parent's cache is unaffected. From the parent's side, the subagent's call and result append to the conversation, leaving the parent's prefix intact.
289298 
290A [fork](/docs/en/sub-agents#fork-the-current-conversation), by contrast, inherits the parent's system prompt, tools, and conversation history exactly, so its first request reads the parent's cache. The compaction summarization call described in [Compacting the conversation](#compacting-the-conversation) uses the same prefix-sharing approach. In a [workflow fan-out](/docs/en/workflows#prompt-caching-in-a-fan-out) of same-prefix agents, Claude Code briefly holds all but the first so their first requests can read the prefix the first agent cached.
299A [fork](/docs/en/sub-agents#fork-the-current-conversation), by contrast, inherits the parent's system prompt, tools, and conversation history exactly, so its first request reads the parent's cache.
300 
301Other requests can also read a prefix that an earlier request cached:
302 
303* **Session copies**: a session you [copy with `/fork`](/docs/en/agent-view#copy-the-session-with-%2Ffork) receives its isolation instruction as a message at the end of the copied conversation, so the cache that the original conversation built stays intact.
304* **Compaction**: the summarization call described in [Compacting the conversation](#compacting-the-conversation) uses the same prefix-sharing approach.
305* **Workflow fan-outs**: in a [workflow fan-out](/docs/en/workflows#prompt-caching-in-a-fan-out) of same-prefix agents, Claude Code holds all but the first for up to 5 seconds by default, so their first requests can read the prefix that the first agent cached.
291306 
292307## Disable prompt caching
293308