Unique-AG/ai / .claude/skills/model-deployment
model-deployment
VerifiedDeploy a new LLM model via LiteLLM (GitOps) and/or Azure (Terraform + node backend), add it to the ai toolkit, create the required pull requests, and verify end-to-end. Use when rolling out a model to any environment, adding a model to the toolkit, troubleshooting "model not available" errors, or finding pricing/token limits/model ids for any provider.
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 10.3 KB |
| references/AZURE-NODE-CHAT.md | markdown | 4.4 KB |
| references/LESSONS-LEARNED.md | markdown | 4.7 KB |
| references/LITELLM-CONFIG.md | markdown | 2.5 KB |
| references/MODEL-SELECTABILITY.md | markdown | 2.7 KB |
| references/TOOLKIT-REGISTRY.md | markdown | 2.9 KB |
references/MODEL-SELECTABILITY.md
View on GitHub# Model selectability
There are **two gatekeeping layers** that control whether a model is available and selectable on uniqueai.
## Layer 1: `UNIQUEAI_SUPPORTED_MODELS` (hardcoded in code)
This is a hardcoded array in `azure-sdk-openai.service.factory.ts` that defines which models are **available on the cluster**. If a model is not in this list, it cannot be used at all — even if it has an enum entry and factory case.
```typescript
export const UNIQUEAI_SUPPORTED_MODELS = [
LanguageModelNameKey.AZURE_GPT_4o_2024_1120,
LanguageModelNameKey.AZURE_GPT_54_2026_0305,
'litellm:gemini-2-5-pro',
// ... add your new model here
] as const;
```
You **must** add your model to this array (done in B3) for it to be cluster-available.
## Layer 2: `UNIQUEAI_ALLOWED_MODELS` (env var, per-company)
This environment variable on node-chat controls which of the cluster-available models are **selectable by end users** in the UI model picker. If a model should not appear in the user-facing dropdown, do not add it here.
- **Env var:** `UNIQUEAI_ALLOWED_MODELS` in the node-chat Helm chart / deployment config.
- **Format:** `companyId:MODEL_NAME,MODEL_NAME2;companyId2:MODEL_NAME3` — semicolon-separated company entries, colon-separated company ID and comma-separated model names.
- **Wildcard:** `*:MODEL_NAME` makes a model selectable for all companies.
- **Unset / empty:** when the env var is unset, the default model selection logic applies (all cluster models are available).
## Decision matrix
| Want the model to... | `UNIQUEAI_SUPPORTED_MODELS` | `UNIQUEAI_ALLOWED_MODELS` |
|---|---|---|
| Be available and selectable by users | Add | Add |
| Be available but only for internal/orchestrator use | Add | Do **not** add |
| Not be available at all | Do **not** add | N/A |
## Where to configure `UNIQUEAI_ALLOWED_MODELS`
- **Per-environment overlays:** `next/services/node-chat/deploy/<Env>/values.yaml` — production example at `next/services/node-chat/deploy/Prod/values.yaml`.
- **Helm chart default:** `next/services/node-chat/deploy/helm-chart/values.yaml` has the env var commented out by default.
- **Code:** parsed by `OpenAiconfigSchema` in `next/services/node-chat/src/openai/config-schema.ts`, used by the Azure SDK service factory to filter available models per company.
## Important notes
- The model names in `UNIQUEAI_ALLOWED_MODELS` must match the `LanguageModel` enum values (e.g. `AZURE_GPT_4o_2024_1120`), **not** the Azure deployment name or the LiteLLM `model_name`.
- If a model is listed in `UNIQUEAI_ALLOWED_MODELS` but is not in `UNIQUEAI_SUPPORTED_MODELS` or not deployed on the cluster, node-chat logs a warning: *"Model X is listed in UNIQUEAI_ALLOWED_MODELS but not found in the cluster list of models"*.
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| writing-skillsobra/superpowersUse when creating new skills, editing existing skills, or verifying skills work before deployment | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| xlsxanthropics/skillsUse this skill any time a spreadsheet file is the primary input or output. This means any task where the user wants to: open, read, edit, or fix an existing .xlsx, .xlsm, .xltx, .csv, or .tsv file (e.g., adding columns, computing formulas, formatting, charting, cleaning messy data); create a new spreadsheet from scratch or from other data sources; or convert between tabular file formats. Trigger especially when the user references a spreadsheet file by name or path — even casually (like "the xlsx in my downloads") — and wants something done to it or produced from it. Also trigger for cleaning or restructuring messy tabular data files (malformed rows, misplaced headers, junk data) into proper spreadsheets. The deliverable must be a spreadsheet file. Do NOT trigger when the primary deliverable is a Word document, HTML report, standalone Python script, database pipeline, or Google Sheets API integration, even if tabular data is involved. | Stars: 198k | Updated | Claude CodeCodex | Verified | Install |
| shipping-and-launchaddyosmani/agent-skillsPrepares production launches. Use when preparing to deploy to production, or when asking what needs to be in place before shipping. Use when you need a pre-launch checklist, when setting up monitoring, when planning a staged rollout, or when you need a rollback strategy. | Stars: 119k | Updated | Claude CodeCodex | Verified | Install |
| childhoodthedotmack/claude-memBabysit a shipped release after merge, publication, or deployment. Verify published packages, production behavior, installed plugins, and late CI or user reports until the observation window is clean; use babysit for PR readiness before release. | Stars: 118k | Updated | Claude CodeCodex | Verified | Install |