feat: add custom weights, model registry, per-agent models, and reward scoring

Browse Source

Inspired by OpenClaw-RL's multi-model orchestration, this adds four
features for custom model management:

1. Custom model registry (infrastructure/models/registry.py) — SQLite-backed
   registry for GGUF, safetensors, HF checkpoint, and Ollama models with
   role-based lookups (general, reward, teacher, judge).

2. Per-agent model assignment — each swarm persona can use a different model
   instead of sharing the global default. Resolved via registry assignment >
   persona default > global default.

3. Runtime model management API (/api/v1/models) — REST endpoints to register,
   list, assign, enable/disable, and remove custom models without restart.
   Includes a dashboard page at /models.

4. Reward model scoring (PRM-style) — majority-vote quality evaluation of
   agent outputs using a configurable reward model. Scores persist in SQLite
   and feed into the swarm learner.

New config settings: custom_weights_dir, reward_model_enabled,
reward_model_name, reward_model_votes.

54 new tests covering registry CRUD, API endpoints, agent assignments,
role lookups, and reward scoring.

https://claude.ai/code/session_01V4iTozMwcE2gjfnCJdCugC

...

This commit is contained in:

Claude

2026-02-27 01:08:03 +00:00

parent e4d5ec5ed4

commit 211c54bc8c

13 changed files with 1603 additions and 1 deletions

Show all changes Ignore whitespace when comparing lines Ignore changes in amount of whitespace Ignore changes in whitespace at EOL

Download Patch File Download Diff File Expand all files Collapse all files

0

src/infrastructure/models/__init__.py Normal file