Robby ManihaniandGitHub cff83a93a0 fix: recommend Qwen3.5 MoE models instead of Qwen3 dense (#189) ...

Qwen3.5 MoE models provide better quality per GB of memory since only
a fraction of parameters are active per token. Updates the tier table:

  ≤8 GB  → qwen3.5:2b
  8-16GB → qwen3.5:4b
 16-32GB → qwen3.5:9b
  32GB+  → qwen3.5:27b

2026-04-04 11:14:41 -07:00

..

__init__.py

init commit

2026-03-12 17:29:39 +00:00

test_config_key_validation.py

feat: remote engine host configuration via CLI (#104)

2026-03-25 20:51:12 -07:00

test_config_phase3.py

fix: update existing tests for new secure defaults

2026-03-28 22:02:02 -07:00

test_config_phase4.py

fix(channels): wire channel→agent handler and fix Telegram send pipeline (#94)

2026-03-20 18:35:18 -07:00

test_config_phase5.py

init commit

2026-03-12 17:29:39 +00:00

test_config.py

fix: update test_amd to expect lemonade for consumer AMD GPUs

2026-04-02 00:12:09 +00:00

test_credentials.py

fix(channels): wire channel→agent handler and fix Telegram send pipeline (#94)

2026-03-20 18:35:18 -07:00

test_events.py

fix(channels): wire channel→agent handler and fix Telegram send pipeline (#94)

2026-03-20 18:35:18 -07:00

test_intent_routing.py

feat: Morning Digest with Voice Mode + unified OAuth + Apple connectors (#174)

2026-04-03 11:05:41 -07:00

test_recommend_model.py

fix: recommend Qwen3.5 MoE models instead of Qwen3 dense (#189)

2026-04-04 11:14:41 -07:00

test_registry.py

init commit

2026-03-12 17:29:39 +00:00

test_rust_bridge.py

fix(channels): wire channel→agent handler and fix Telegram send pipeline (#94)

2026-03-20 18:35:18 -07:00

test_types.py

init commit

2026-03-12 17:29:39 +00:00