mosaic-probe-harness
by 4ltena
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| RECHECK | No | Set to 1 to enable crop-based re-evaluation by the Pi agent for borderline scores. | 0 |
| MAX_EDGE | No | Maximum long-edge pixels for VLM input (only downscales, never upscales). | 2048 |
| VLM_MODEL | No | Model name passed to llama-server. | qwen3.8-flash-next |
| MAX_PIXELS | No | Maximum total pixel count when decoding images (decompression bomb protection). | 100000000 |
| RECHECK_HI | No | Upper bound of p_ok for triggering re-evaluation. | 0.9 |
| RECHECK_LO | No | Lower bound of p_ok for triggering re-evaluation. | 0.2 |
| MAX_RENDERS | No | Maximum number of renders (judgments) per file. | 8 |
| MOSAIC_BIND | No | Listen IP address. Non-loopback addresses require MOSAIC_API_KEY. | 127.0.0.1 |
| MOSAIC_PORT | No | Listen port number. | 8790 |
| VLM_API_KEY | No | Only set if llama-server requires Bearer authentication. | |
| MAX_IMAGE_MB | No | Maximum received image size in MiB. Exceeding this returns 413 without buffering in memory. | 15 |
| VLM_BASE_URL | No | Base URL of llama-server (default is http://127.0.0.1:8080). | http://127.0.0.1:8080 |
| VLM_BASE_URLS | No | Comma-separated base URLs for multiple llama-server instances. If unset, uses VLM_BASE_URL. Trailing / and /v1 are removed and duplicates are eliminated. | |
| MOSAIC_API_KEY | No | Bearer authentication API key. Required when listening on a non-loopback address. | |
| VLM_EXTRA_BODY | No | Additional settings merged at the top level of the request JSON (JSON object string, e.g. to override chat_template_kwargs). | |
| VLM_TIMEOUT_MS | No | Timeout for each llama-server call in milliseconds. | 120000 |
| QUEUE_TIMEOUT_S | No | Maximum wait time in the execution queue (seconds). Exceeding returns 503. | 60 |
| RECHECK_MAX_CROPS | No | Maximum number of crop regions per image for re-evaluation. | 3 |
| MOSAIC_ALLOW_CIDRS | No | Comma-separated CIDR list of allowed source IPs. | 127.0.0.0/8,::1/128,10.0.0.0/8,172.16.0.0/12,192.168.0.0/16 |
| MOSAIC_CORS_ORIGINS | No | `*` or comma-separated list of allowed Origins. Default: `*` when API key is set, no origins allowed when no key is set. | |
| CLASSIFY_TEMPERATURE | No | Temperature parameter used to divide classification logits. Values greater than 1 smooth the probability distribution. | 1 |
| MOSAIC_LAYER_PATTERN | No | Regular expression for layer names considered mosaic layers (case-insensitive). | モザイク|mosaic|pixel|ぼかし|blur|censor|修正|規制 |
| VLM_SLOTS_PER_BACKEND | No | Concurrent executions per backend. Should match llama-server --parallel (total slots = number of backends × this value; maximum concurrent requests). | 1 |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Server capabilities have not been inspected yet.
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
No tools | |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
This server cannot be deployed
Maintenance
ActivityMaintained
ResponsivenessNo recent community issues