iliad_llm_inference
ActiveTool of AXIS Toolbox — Agentic Commerce Codebase Intelligence
AXIS-hosted LLM chat-completion via node-llama-cpp + a small GGUF model loaded in-process. Two input shapes accepted: `prompt` (single string) or `messages` (chat-style array of {role, content}). Sampling controls: `max_tokens` (≤2048), `temperature` (0-2), `top_k`, `top_p`, `seed` (for reproducibility), `stop` (string[]). Inference is fully in-process — no upstream provider, no per-call API fee. Operator sets AXIS_LLM_MODEL_PATH to point at a Phi-3-mini / TinyLlama / Llama-3.2-1B GGUF; if missing, the tool returns a `_not_configured: true` envelope. Engineer mode (X-Agent-Mode: engineer — Constrained Inference, $0.10): pass a `json_schema` and decoding is grammar-constrained to it AND the output is validated against it (returns a `structured` block with valid + parsed + schema_errors) — guaranteed-valid structured output. Requires Authorization: Bearer <api_key>.
Parameters schema
{
"type": "object",
"properties": {
"seed": {
"type": "number",
"description": "Optional seed for reproducible output."
},
"stop": {
"type": "array",
"description": "Stop sequences. Generation halts when any string in the array is produced."
},
"top_k": {
"type": "number",
"description": "Top-k sampling (positive integer). Defaults 40."
},
"top_p": {
"type": "number",
"description": "Top-p nucleus sampling in (0, 1]. Defaults 0.95."
},
"prompt": {
"type": "string",
"description": "Single-prompt completion input. Use either this OR messages, not both."
},
"system": {
"type": "string",
"description": "Optional system prompt (prompt mode only). For messages mode, use role=system entries."
},
"messages": {
"type": "array",
"description": "Chat-style input. Array of {role: system|user|assistant, content: string}."
},
"max_tokens": {
"type": "number",
"description": "Max tokens to generate. Defaults 512, hard cap 2048."
},
"json_schema": {
"type": "object",
"description": "Engineer mode (required): a JSON Schema. Decoding is grammar-constrained to it and the output is validated against it; returns a `structured` block."
},
"temperature": {
"type": "number",
"description": "Sampling temperature in [0, 2]. Defaults 0.7."
}
}
}No endpoints wrapped at confidence ≥ 0.50.
Parent server
AXIS Toolbox — Agentic Commerce Codebase Intelligence
https://github.com/lastmanupinc-hub/Toolbox
1/7 registries