Celia Chen 51fc4b0559 feat: use provider defaults for memory models (#27129) ...

## Why

Memory startup used hardcoded OpenAI model slugs for extraction and
consolidation. That works for the default OpenAI-compatible path, but
provider-specific backends can require different model identifiers. In
particular, Amazon Bedrock should use its Bedrock model ID for these
background memory requests instead of the OpenAI `gpt-5.4-mini` /
`gpt-5.4` slugs.

## What Changed

- Added provider-owned preferred memory model methods alongside
`approval_review_preferred_model`.
- Updated memory extraction and consolidation to resolve their default
model through the active `ModelProvider`.
- Added Amazon Bedrock overrides so both memory stages use
`openai.gpt-5.4` through Bedrock’s provider-specific model ID.
- Kept explicit `memories.extract_model` and
`memories.consolidation_model` config overrides taking precedence.
- Added startup coverage for default OpenAI and Bedrock memory model
selection.

#closes #26288

51fc4b0559 · 2026-06-09 23:49:09 +00:00

History

..

src

feat: use provider defaults for memory models (#27129)

2026-06-09 23:49:09 +00:00

BUILD.bazel

feat: add opt-in provider runtime abstraction (#17713)

2026-04-17 02:27:45 +00:00

Cargo.toml

feat: let model providers own model discovery (#18950)

2026-04-24 04:28:25 +00:00