Frank
b60e95158c
halogen-flash-server has no server-side sampler defaults (temperature absent or 0 = greedy), so the endpoint decoded greedy for OMP, whose global sampling settings default to -1 (not sent). compat.extraBody merges these top-level into every request body after the compat policy, so they win: temperature=1.0 top_p=0.95 top_k=20 min_p=0.0 presence_penalty=0.0 repetition_penalty=1.0 preserve_thinking=true Verified against the live dankclaw endpoint: preserve_thinking is honoured (350 vs 75 prompt tokens for a replayed reasoning turn), and the exact body shape returns 200.
69 lines
2.0 KiB
YAML
69 lines
2.0 KiB
YAML
# Imported from ~/.pi/agent/models.json (pi agent settings)
|
|
# - apiKey "EMPTY" -> auth: none (keyless local endpoint)
|
|
# - thinkingLevelMap {max: xhigh} -> compat.reasoningEffortMap
|
|
providers:
|
|
"llamacpp (dankserver)":
|
|
baseUrl: http://192.168.0.235:7770/v1
|
|
api: openai-completions
|
|
auth: none
|
|
models:
|
|
- id: frank-small
|
|
name: "frank-small (dankserver)"
|
|
contextWindow: 262144
|
|
maxTokens: 262144
|
|
reasoning: true
|
|
input: [text]
|
|
compat:
|
|
reasoningEffortMap:
|
|
max: xhigh
|
|
|
|
"llamacpp (dankclaw)":
|
|
baseUrl: http://192.168.0.143:7770/v1
|
|
api: openai-completions
|
|
auth: none
|
|
models:
|
|
- id: frank-large
|
|
name: "frank-large (dankclaw-gpu)"
|
|
contextWindow: 262144
|
|
maxTokens: 262144
|
|
reasoning: true
|
|
input: [text, image]
|
|
compat:
|
|
reasoningEffortMap:
|
|
max: xhigh
|
|
# Qwen3.8-Flash-Next recommended sampling; halogen has no server-side
|
|
# sampler defaults, so without this the endpoint decodes greedy.
|
|
# extraBody is merged last (after compat policy) and wins.
|
|
extraBody:
|
|
temperature: 1.0
|
|
top_p: 0.95
|
|
top_k: 20
|
|
min_p: 0.0
|
|
presence_penalty: 0.0
|
|
repetition_penalty: 1.0
|
|
# Keep prior thinking blocks in the rendered prompt across turns;
|
|
# halogen honours it top-level (verified: 275-token prompt delta vs false).
|
|
preserve_thinking: true
|
|
|
|
"flm (dankclaw-npu)":
|
|
baseUrl: http://192.168.0.143:7771/v1
|
|
api: openai-completions
|
|
auth: none
|
|
models:
|
|
- id: gemma4-it:e4b
|
|
name: "gemma4-it:e4b (dankclaw-npu)"
|
|
contextWindow: 131072
|
|
maxTokens: 131072
|
|
reasoning: true
|
|
input: [text, image]
|
|
compat:
|
|
reasoningEffortMap:
|
|
max: xhigh
|
|
|
|
- id: nuextract3:4b
|
|
name: "nuextract3:4b (dankclaw-npu extraction)"
|
|
contextWindow: 32768
|
|
maxTokens: 32768
|
|
reasoning: false
|
|
input: [text]
|