mirrors/hermes-agent
1
0
Fork 0
mirror of https://github.com/NousResearch/hermes-agent.git synced 2026-04-25 00:51:20 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

feat: upgrade MiniMax default to M2.7 + add new OpenRouter models

Browse source 
MiniMax: Add M2.7 and M2.7-highspeed as new defaults across provider
model lists, auxiliary client, metadata, setup wizard, RL training tool,
fallback tests, and docs. Retain M2.5/M2.1 as alternatives.

OpenRouter: Add grok-4.20-beta, nemotron-3-super-120b-a12b:free,
trinity-large-preview:free, glm-5-turbo, and hunter-alpha to the
model catalog.

MiniMax changes based on PR #1882 by @octo-patch (applied manually
due to stale conflicts in refactored pricing module).
This commit is contained in:
octo-patch 2026-03-18 02:42:58 -07:00 • committed by Test
parent 927f4d3a37
commit e4043633fc
8 changed files with 25 additions and 14 deletions
Download patch file Download diff file Expand all files Collapse all files

4
tools/rl_training_tool.py
View file

@ -1009,7 +1009,7 @@ async def rl_list_runs() -> str:
TEST_MODELS = [
{"id": "qwen/qwen3-8b", "name": "Qwen3 8B", "scale": "small"},
{"id": "z-ai/glm-4.7-flash", "name": "GLM-4.7 Flash", "scale": "medium"},
{"id": "minimax/minimax-m2.5", "name": "MiniMax M2.5", "scale": "large"},
{"id": "minimax/minimax-m2.7", "name": "MiniMax M2.7", "scale": "large"},
]
# Default test parameters - quick but representative
@ -1370,7 +1370,7 @@ RL_CHECK_STATUS_SCHEMA = {"name": "rl_check_status", "description": "Get status
RL_STOP_TRAINING_SCHEMA = {"name": "rl_stop_training", "description": "Stop a running training job. Use if metrics look bad, training is stagnant, or you want to try different settings.", "parameters": {"type": "object", "properties": {"run_id": {"type": "string", "description": "The run ID to stop"}}, "required": ["run_id"]}}
RL_GET_RESULTS_SCHEMA = {"name": "rl_get_results", "description": "Get final results and metrics for a completed training run. Returns final metrics and path to trained weights.", "parameters": {"type": "object", "properties": {"run_id": {"type": "string", "description": "The run ID to get results for"}}, "required": ["run_id"]}}
RL_LIST_RUNS_SCHEMA = {"name": "rl_list_runs", "description": "List all training runs (active and completed) with their status.", "parameters": {"type": "object", "properties": {}, "required": []}}
RL_TEST_INFERENCE_SCHEMA = {"name": "rl_test_inference", "description": "Quick inference test for any environment. Runs a few steps of inference + scoring using OpenRouter. Default: 3 steps x 16 completions = 48 rollouts per model, testing 3 models = 144 total. Tests environment loading, prompt construction, inference parsing, and verifier logic. Use BEFORE training to catch issues.", "parameters": {"type": "object", "properties": {"num_steps": {"type": "integer", "description": "Number of steps to run (default: 3, recommended max for testing)", "default": 3}, "group_size": {"type": "integer", "description": "Completions per step (default: 16, like training)", "default": 16}, "models": {"type": "array", "items": {"type": "string"}, "description": "Optional list of OpenRouter model IDs. Default: qwen/qwen3-8b, z-ai/glm-4.7-flash, minimax/minimax-m2.5"}}, "required": []}}
RL_TEST_INFERENCE_SCHEMA = {"name": "rl_test_inference", "description": "Quick inference test for any environment. Runs a few steps of inference + scoring using OpenRouter. Default: 3 steps x 16 completions = 48 rollouts per model, testing 3 models = 144 total. Tests environment loading, prompt construction, inference parsing, and verifier logic. Use BEFORE training to catch issues.", "parameters": {"type": "object", "properties": {"num_steps": {"type": "integer", "description": "Number of steps to run (default: 3, recommended max for testing)", "default": 3}, "group_size": {"type": "integer", "description": "Completions per step (default: 16, like training)", "default": 16}, "models": {"type": "array", "items": {"type": "string"}, "description": "Optional list of OpenRouter model IDs. Default: qwen/qwen3-8b, z-ai/glm-4.7-flash, minimax/minimax-m2.7"}}, "required": []}}
_rl_env = ["TINKER_API_KEY", "WANDB_API_KEY"]