Taste-Context Brief
by weioai
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| AI | No | Optional Workers AI binding (env.AI) required for LLM_MODE=workers-ai. | |
| MODE | No | fixtures (default) or live. In fixtures mode Qloo responses come from hand-written, labelled fixtures and only the 3 built-in scenarios work. In live mode real calls are made to the Qloo hackathon API with QLOO_API_KEY; without the key every brief request is 503. live mode also needs a RATE_LIMITER rate-limiting binding. | fixtures |
| LLM_MODE | No | recorded, workers-ai, or template (default for unknown values). recorded replays the narrative stored with a built-in scenario (fixtures mode only; in live mode it becomes template). workers-ai calls the model through the Workers AI binding, only after the model passes the allow-list and WORKERS_AI_APPROVED="yes" is set. template produces deterministic text from the brief with no model involved. | recorded |
| REPO_URL | No | Footer link, https only; with no value the page says the repository is not published yet. | |
| LLM_MODEL | No | Model id used in workers-ai mode. Every model id passes an allow-list before any call: a deny-list of foreign model families is checked first, then the vendor prefix must belong to an allowed family (Anthropic, OpenAI, Google, Meta, NVIDIA, Microsoft, Amazon). | @cf/meta/llama-3.3-70b-instruct-fp8-fast |
| QLOO_API_KEY | No | Secret API key for the Qloo hackathon API. Required in live mode; without it every brief request returns 503 and it never falls back to fixtures. | |
| RATE_LIMITER | No | Workers Rate Limiting binding. Required for any request that can cost Qloo quota or model usage (MODE=live or LLM_MODE=workers-ai); without it those requests are refused with 503. Each client (keyed on CF-Connecting-IP) has its own budget and is refused with 429 when spent. | |
| GLOBAL_RATE_LIMITER | No | Optional Workers Rate Limiting binding that caps total traffic across clients. | |
| WORKERS_AI_APPROVED | No | Set to "yes" to allow LLM_MODE=workers-ai, recording that your policy allows calling Workers AI from inside a Worker. Without it LLM_MODE=workers-ai is ignored, the Worker uses the template, and /healthz says why. |
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 issues