AutoGPT

mirror of https://github.com/Significant-Gravitas/AutoGPT.git synced 2026-02-07 05:15:09 -05:00

Files

Reinier van der Leer 8fddc9d71f fix(backend): Reduce GET /api/graphs expense + latency (#11986 )

[SECRT-1896: Fix crazy `GET /api/graphs` latency (P95 =
107s)](https://linear.app/autogpt/issue/SECRT-1896)

These changes should decrease latency of this endpoint by ~~60-65%~~ a
lot.

### Changes 🏗️

- Make `Graph.credentials_input_schema` cheaper by avoiding constructing
a new `BlockSchema` subclass
- Strip down `GraphMeta` - drop all computed fields
- Replace with either `GraphModel` or `GraphModelWithoutNodes` wherever
those computed fields are used
- Simplify usage in `list_graphs_paginated` and
`fetch_graph_from_store_slug`
- Refactor and clarify relationships between the different graph models
  - Split `BaseGraph` into `GraphBaseMeta` + `BaseGraph`
- Strip down `Graph` - move `credentials_input_schema` and
`aggregate_credentials_inputs` to `GraphModel`
- Refactor to eliminate double `aggregate_credentials_inputs()` call in
`credentials_input_schema` call tree
  - Add `GraphModelWithoutNodes` (similar to current `GraphMeta`)

### Checklist 📋

#### For code changes:
- [x] I have clearly listed my changes in the PR description
- [x] I have made a test plan
- [x] I have tested my changes according to the test plan:
  - [x] `GET /api/graphs` works as it should
  - [x] Running a graph succeeds
  - [x] Adding a sub-agent in the Builder works as it should

2026-02-06 19:13:21 +00:00