<feed xmlns='http://www.w3.org/2005/Atom'>
<title>panto-warming.git/.gitignore, branch v0.2.0</title>
<subtitle>A pantograph extension that keeps the provider's prompt cache warm while you're idle by periodically sending a small throwaway prompt, which is never added to the context window or the transcript.
</subtitle>
<id>https://code.tjp.lol/panto-warming.git/atom?h=v0.2.0</id>
<link rel='self' href='https://code.tjp.lol/panto-warming.git/atom?h=v0.2.0'/>
<link rel='alternate' type='text/html' href='https://code.tjp.lol/panto-warming.git/'/>
<updated>2026-09-25T21:11:20Z</updated>
<entry>
<title>Add panto-warming session cache warming extension</title>
<updated>2026-09-25T21:11:20Z</updated>
<author>
<name>t</name>
<email>t@tjp.lol</email>
</author>
<published>2026-09-25T20:58:55Z</published>
<link rel='alternate' type='text/html' href='https://code.tjp.lol/panto-warming.git/commit/?id=8da8849e71a8dac7ed81d45d7674e6a3f38cbb7c'/>
<id>urn:sha1:8da8849e71a8dac7ed81d45d7674e6a3f38cbb7c</id>
<content type='text'>
Send a minimal transient prompt on idle intervals to keep the
provider-side prompt cache warm, then discard prompt and response so
the context window and transcript stay untouched.
Disabled by default; enable via warming table with layered interval,
duration, and prompt settings.
</content>
</entry>
</feed>
