mirror of
https://github.com/danny-avila/LibreChat.git
synced 2026-09-08 15:41:38 +00:00
7132fdcf32
An attachment accepted on one turn whose tool never ran carried neither an embedding nor a code reference, and every hydration query matches only files that already have one: getToolFilesByIds requires embedded, getUserCodeFiles requires a codeEnvRef. The file was therefore absent from later turns entirely, so asking to search or run code against it found nothing. Hydrating it back into attachments would have re-delivered earlier uploads to the model on every turn, so provisioning and delivery are now separate inputs: deferred records are fetched by their own query and reach the provisioning computation alone, never the returned attachments. Also provisions for the host create_file tool, whose name is distinct from write_file, and falls back to the primary context when a tool batch omits its agent id, matching what the tool loaders already do. |
||
|---|---|---|
| .. | ||
| Audio | ||
| Azure | ||
| Citations | ||
| Code | ||
| Firebase | ||
| images | ||
| Local | ||
| OpenAI | ||
| VectorDB | ||
| index.js | ||
| permissions.js | ||
| permissions.spec.js | ||
| process.integration.spec.js | ||
| process.js | ||
| process.spec.js | ||
| provision.js | ||
| provision.spec.js | ||
| provisionCallback.js | ||
| retention.js | ||
| retention.spec.js | ||
| strategies.js | ||