What
When a session starts by resuming or forking, the SessionStart hook payload now includes seconds_since_last_response, context_tokens, prompt_cache_likely_expired, and estimated_cache_write_usd. A hook can use these to judge whether the prompt cache has lapsed and what re-caching the context will cost before doing anything expensive.
Details
- Present for SessionStart events whose source is resume or fork.
- The elapsed-time field is measured from the resumed transcript's last assistant response.
Evidence
resume/fork: seconds since the resumed transcript's last assistant response
Strings lifted out of the shipped bundle, so the claim above can be checked against them.
Names in the bundleSessionStartseconds_since_last_responsecontext_tokensprompt_cache_likely_expiredestimated_cache_write_usd
The entry above is what we published on the day. These lines were added later, as Anthropic's own pages caught up, and they sit beside the original rather than replacing it.
Added since
A small documentation edit on Hooks reference touched a line naming SessionStart after this was published.
The same wait applies at launch, including a resumed session: a prompt you send while SessionStart hooks are still running doesn't reach Claude until they finish.hooks see the edit
Confirmed since
Anthropic's documentation has since written up SessionStart, on Claude Code changelog.
* Improved `--continue` / `--resume`: the conversation appears immediately instead of waiting for SessionStart hooks, and the first message no longer re-reads the whole transcriptchangelog see the edit
Two sources agreeTwo things we can check say the same as this entry.
Anthropic's documentation agrees
Anthropic's documentation has since written up SessionStart, on Claude Code changelog.
Anthropic's release notes agree
Added PreModelSwitch and PostModelSwitch hook events (block, confirm, or annotate a model switch); SessionStart resume hooks now receive…