mirror of
https://github.com/agentscope-ai/ReMe.git
synced 2026-11-05 07:39:47 +00:00
363e497ae9
Some checks are pending
CI / Python packages / Build and verify distributions (push) Waiting to run
CI / Python quality / Pre-commit (push) Waiting to run
CI / Python quality / GitHub Actions (push) Waiting to run
CI / Python tests / Unit Tests - py3.12 (push) Waiting to run
CI / Python tests / Unit Tests - py3.13 (push) Waiting to run
CI / Python tests / Unit Tests - py3.14 (push) Waiting to run
CI / Python tests / Unit Tests - py3.11 (push) Waiting to run
CI / Windows / CLI smoke - py3.11 (push) Waiting to run
Deploy / Documentation / Build documentation (push) Waiting to run
Deploy / Documentation / deploy (push) Blocked by required conditions
CI and Release / Docker / Build and test / amd64 (push) Waiting to run
CI and Release / Docker / Build and test / arm64 (push) Waiting to run
CI and Release / Docker / Publish multi-platform tags (push) Blocked by required conditions
Security / CodeQL / Analyze javascript-typescript (push) Waiting to run
Security / CodeQL / Analyze python (push) Waiting to run
* feat(benchmark): add MobileMem reproduction * fix(benchmark): declare Pillow for MobileMem images * fix(benchmark): preserve MobileMem usage and failure diagnostics * fix(benchmark): redact private keys in MobileMem diagnostics * fix(mobilemem): apply image defaults and consolidate answer receipts * fix(mobilemem): preserve response schemas during diagnostic redaction * fix(mobilemem): preserve judge parameter names in snapshots * refactor(mobilemem): share task cleanup and use persisted results --------- Co-authored-by: jinli.yl <jinli.yl@alibaba-inc.com>
846 B
846 B
MobileMem plugin
Install this plugin from the repository:
pip install -e plugins/mobilemem
Enable the mobilemem ReMe plugin for the MobileMem-Omni benchmark. Its Steps use native ReMe Auto Memory,
source-line citations, BM25 retrieval, workspace containment, and an AgentScope bridge for the native image
reader. The plugin installs independently of MemLens. Evaluation uses the separate
mobilemem-judge plugin.
The runner supplies only original dialogue messages and image attachments. Memory extraction retains dates,
updates, personal relationships, app details and visual evidence; each question uses a fresh answer Agent. Source
session reading and read_image remain scoped to that user's workspace. Supplied captions and benchmark gold
annotations must never be passed to either Job.