## Resuming a session
The whole hunk
from line 18, old and new numbered
/
lines
from line 18
1818
1919To get the most out of prefix matching, Claude Code orders each request so content that rarely changes between turns comes first:
2020
21| Layer | Content | Changes when |
22| --------------- | ----------------------------------------------- | --------------------------------------------------------------------- |
23| System prompt | Core instructions, tool definitions | The set of loaded tool definitions changes or Claude Code is upgraded |
24| Project context | CLAUDE.md, auto memory, unscoped rules | Session starts, or after `/clear` or `/compact` |
25| Conversation | Your messages, Claude's responses, tool results | Every turn |
21| Layer | Content | Changes when |
22| --------------- | ----------------------------------------------- | ----------------------------------------------- |
23| System prompt | Core instructions, tool definitions | The set of loaded tool definitions changes |
24| Project context | CLAUDE.md, auto memory, unscoped rules | Session starts, or after `/clear` or `/compact` |
25| Conversation | Your messages, Claude's responses, tool results | Every turn |
2626
2727A change to the conversation layer leaves the system prompt and project context cached. A change to the system prompt invalidates everything, because all later content now sits behind a different prefix. The third column gives common triggers rather than an exhaustive list, and the sections below cover the full set.
2828
from line 168
168168
169169### Compacting the conversation
170170
171[Compaction](/docs/en/context-window#what-survives-compaction) replaces your message history with a summary. By design, this invalidates the conversation layer, since the next request has a new, shorter history that doesn't share a prefix with the old one. Claude Code reuses the system prompt layer and reloads project context from disk, which cache-hits only if CLAUDE.md and memory are unchanged since the session started.
171[Compaction](/docs/en/context-window#what-survives-compaction) replaces your message history with a summary. By design, this invalidates the conversation layer, since the next request has a new, shorter history that doesn't share a prefix with the old one. Claude Code reuses the system prompt layer unless the conversation was [resumed while keeping a system prompt that would otherwise have changed](#resuming-a-session); in that case the first compaction switches to the current prompt and that layer rebuilds once. It reloads project context from disk, which cache-hits only if CLAUDE.md and memory are unchanged since the session started.
172172
173173To produce the summary, Claude Code sends a separate request with the same system prompt, tools, and history as your conversation, plus a summarization instruction appended as a final user message. While the cache is warm, that request reads your prefix from the cache, so a mid-session `/compact` costs a fraction of what the context size suggests and spends most of its time generating the summary.
174174
from line 188
188188
189189### Upgrading Claude Code
190190
191A 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.
191A new Claude Code version typically updates the system prompt or tool definitions, so the first conversation you start after an upgrade builds its 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.
192192
193193<Note>
194 [Resuming a session](/docs/en/sessions#resume-a-session) after an upgrade reprocesses the entire conversation history with no cache hits, since the history now sits behind a different system prompt. The cost scales with how long the resumed conversation is, so the first turn back into a long session can be the most expensive request you send.
194 For what it costs to resume a conversation you started before the upgrade, see [Resuming a session](#resuming-a-session).
195195</Note>
196196
197197## Actions that keep the cache
from line 234
234234
235235Restoring file checkpoints alongside the conversation has no separate effect on the cache. File contents enter context only when Claude reads them, the same as [editing files in your repository](#editing-files-in-your-repository).
236236
237## Resuming a session
238
239When you [resume a session](/docs/en/sessions#resume-a-session), Claude Code sends the whole conversation again, and the request reads from the cache whatever part of its prefix is unchanged and still within the [cache lifetime](#cache-lifetime). The layer table at the top of this page says what changes each layer.
240
241The system prompt is the one layer a resume can treat two ways. It would change after a [Claude Code upgrade](#upgrading-claude-code) or with different [`--append-system-prompt`](/docs/en/cli-reference#system-prompt-flags) text on the resume, and whether the resumed conversation picks up that change right away varies by how you connect.
242
243* In sessions signed in with a claude.ai or Console account, and other sessions that [fetch feature flags](/docs/en/env-vars#features-that-need-feature-flag-fetching), the resumed conversation keeps the system prompt it started with by default, so its history still sits behind the same prompt. The change takes effect once the conversation is compacted or in a new conversation. [System prompt flags in resumed conversations](/docs/en/cli-reference#system-prompt-flags-in-resumed-conversations) covers `--system-prompt-snapshot off` and bare mode, where this doesn't apply.
244* On Amazon Bedrock, Google Cloud's Agent Platform, Microsoft Foundry, and other sessions that don't fetch feature flags, Claude Code builds the system prompt fresh on the resume, so the history now sits behind a different prompt and the resumed request reprocesses the entire conversation with no cache hits. The cost scales with the length of the conversation.
245
237246## Cache lifetime
238247
239248Cached prefixes expire after a period of inactivity. Each request that hits the cache resets the timer, so the cache stays warm as long as you keep working. After a long enough gap, the next request recomputes the full input and re-establishes the cache, which is why the first turn back after stepping away can be noticeably slower.
from line 293
284293
285294## Cache scope
286295
287In Claude Code, the cache is effectively scoped to one machine and directory. The system prompt embeds the working directory, platform, shell, OS version, and auto memory paths, so two sessions in different directories build different prefixes and miss each other's cache. That includes worktrees of the same repository, since each worktree has its own working directory.
296In Claude Code, the cache is effectively scoped to one machine and directory. Each conversation carries the working directory, platform, shell, and OS version, and the system prompt names your auto memory paths, so two sessions in different directories build different prefixes and miss each other's cache. That includes worktrees of the same repository, since each worktree has its own working directory.
288297
289Sessions you run in parallel in the same directory build matching prefixes and read each other's cache. Sequential sessions share the prefix only when the git status snapshot at startup matches, since the system prompt also captures branch and recent commits.
298Sessions you run in parallel in the same directory build matching prefixes and read each other's cache. Sequential sessions share the prefix only when the git status snapshot taken at startup matches, since each conversation also carries the branch and recent commits from that snapshot.
290299
291300The underlying API cache is broader. Caches are isolated between organizations, and on some providers, [between workspaces within an organization](https://platform.claude.com/docs/en/build-with-claude/prompt-caching#cache-storage-and-sharing). Within those boundaries, any two requests with the same model and prefix read the same cache. For Agent SDK callers running fleets of automated processes, see [improve prompt caching across users and machines](/docs/en/agent-sdk/modifying-system-prompts#improve-prompt-caching-across-users-and-machines) to suppress the per-machine sections of the system prompt and share the cache across machines.
292301