Robby ManihaniandGitHub 35b8991cc2 feat: hardware-aware model recommendation in jarvis init (#188) ...

Closes #132 — jarvis init now recommends a Qwen3 dense model based on
available memory using an explicit tier table:

  ≤8 GB  → qwen3:1.7b  (~1.1 GB)
  8-16GB → qwen3:4b    (~2.5 GB)
 16-32GB → qwen3:8b    (~5.2 GB)
  32GB+  → qwen3:14b   (~9.3 GB)

Adds qwen3:0.6b, 1.7b, 4b, 14b, 30b to the model catalog. Falls back
to scanning all compatible models if the tiered pick doesn't support
the selected engine. Shows the user why the model was chosen and how
to download later if declined.

2026-04-03 22:19:27 -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

feat: hardware-aware model recommendation in jarvis init (#188)

2026-04-03 22:19:27 -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