gitprov
e3e4f9d0ec
- Chat model max_tokens: 32000 → 4096 (was inflating context budget calculations) - Utility model ctx_length: 8192 → 14000 (matches GLM flash actual loaded context) - Utility model max_tokens: explicit 2048 cap (utility tasks need short responses) - Utility model name: full zai-org/glm-4.7-flash to target correct LM Studio instance - pull-agent-identity.py: include agent_id and gutask orientation block in system prompt - gutask.md: expand lore command docs, note done auto-creates review record Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
41 lines
883 B
JSON
41 lines
883 B
JSON
{
|
|
"allow_chat_override": false,
|
|
"chat_model": {
|
|
"provider": "lm_studio",
|
|
"name": "nousresearch/hermes-4-70b",
|
|
"api_base": "http://festinger:11434",
|
|
"ctx_length": 32000,
|
|
"ctx_history": 0.7,
|
|
"vision": true,
|
|
"rl_requests": 0,
|
|
"rl_input": 0,
|
|
"rl_output": 0,
|
|
"kwargs": {
|
|
"max_tokens": 4096,
|
|
"agent_id": 8
|
|
},
|
|
"max_embeds": 10
|
|
},
|
|
"utility_model": {
|
|
"provider": "lm_studio",
|
|
"name": "zai-org/glm-4.7-flash",
|
|
"api_base": "http://host.docker.internal:1234/v1",
|
|
"ctx_length": 14000,
|
|
"ctx_input": 0.7,
|
|
"rl_requests": 0,
|
|
"rl_input": 0,
|
|
"rl_output": 0,
|
|
"kwargs": {
|
|
"max_tokens": 2048
|
|
}
|
|
},
|
|
"embedding_model": {
|
|
"provider": "huggingface",
|
|
"name": "sentence-transformers/all-MiniLM-L6-v2",
|
|
"api_base": "",
|
|
"rl_requests": 0,
|
|
"rl_input": 0,
|
|
"kwargs": {}
|
|
}
|
|
}
|