mirror of
https://github.com/danny-avila/LibreChat.git
synced 2026-07-01 11:53:55 +00:00
5706e414fd
For a snapshot-less branch whose tokens exceed the window, the send path prunes oldest-first (getMessagesWithinTokenLimit), so the next call can sit well under the window. The gauge previously clamped the full sum to 100%, hiding that headroom. Add prunedBranchTokens — a newest->oldest walk that keeps messages until the next would overflow the message budget (max minus the summary baseline), mirroring the pruner — and use it on the estimate path in place of the clamp. Approximation: omits the instruction/tool overhead and tool-call pairing the real pruner accounts for (unknowable for a snapshot-less branch); superseded by an exact snapshot once the branch is generated. |
||
|---|---|---|
| .. | ||
| public | ||
| scripts | ||
| src | ||
| sw | ||
| test | ||
| babel.config.cjs | ||
| check_updates.sh | ||
| index.html | ||
| jest.config.cjs | ||
| jest.resolver.cjs | ||
| nginx.conf | ||
| package.json | ||
| postcss.config.cjs | ||
| tailwind.config.cjs | ||
| tsconfig.json | ||
| vite.config.ts | ||