Skip to content

Evenfire is an intelligence layer platform for running LLM agents that take real actions, on your infrastructure

TypeScript

docs: update docs for per-Host provider non-secret env

Jose Gabriel Ramirez Encinasabcebc2fbec8
diff --git a/docs/llm-providers/adding-a-provider.md b/docs/llm-providers/adding-a-provider.md
index 3c5687495..b5434d5b2 100644
--- a/docs/llm-providers/adding-a-provider.md
+++ b/docs/llm-providers/adding-a-provider.md
@@ -186,8 +186,13 @@ refused for it.
in `PROVIDER_CREDENTIAL_SLOTS`. The credential-exclusion boundary
(`userEnvSnapshot`) derives from the full slot set — never `primarySlot()`.
- Non-secret, per-Host config (region, project, endpoint) goes in
- `PROVIDER_NON_SECRET_ENV` and flows via the pod env (`host-<ref>-env`), surfaced
- in the UI as a "configure in Host → Environment" hint, never a secret field.
+ `PROVIDER_NON_SECRET_ENV`, surfaced in the UI as a "configure in Host →
+ Environment" hint, never a secret field. It is not in the pod env: mcp-host
+ resolves it from the watched per-Host `host-<ref>-env` / `-env-secret` and
+ passes the driver a lookup (`ProviderEnvLookup`, `src/llm/providerEnv.ts`)
+ limited to the provider's declared names (`process.env` outside a Host pod,
+ e.g. dev mode). Read these values through that lookup, never `process.env`
+ directly.
- **Exclude such providers from `workflowrecipe.yaml`** — the WRC `configure`
transport is single-credential and doesn't carry non-secret env, so a
multi-credential / endpoint-requiring provider must fail at admission, not
@@ -203,7 +208,8 @@ Azure is OpenAI-compatible in shape but not a `baseURL + Bearer` row:
- **`model` is the deployment name**, not a catalog id.
Its `RUNTIME_FIELDS.azure` carries a `defaultModel` + `tokenizer: 'openai'` but
**no static baseURL**, so it takes the explicit `case 'azure':` arm and reads the
- endpoint from `process.env` at construction. Fail-closed if the endpoint is absent.
+ endpoint from the non-secret env lookup at construction. Fail-closed if the
+ endpoint is absent.
---
diff --git a/mcp-host/README.md b/mcp-host/README.md
index d556003a0..375906185 100644
--- a/mcp-host/README.md
+++ b/mcp-host/README.md
@@ -41,8 +41,10 @@ the value.
Separately, the per-Host `host-<hostRef>-env` ConfigMap and
`host-<hostRef>-env-secret` Secret are watched at runtime and feed tool
-subprocess env and capability checks, not the startup settings below.
-Precedence there is host Secret > host ConfigMap > LLM Secret > process env.
+subprocess env, capability checks and the LLM provider's non-secret settings
+(`VERTEX_*`, `AWS_REGION`, `AZURE_OPENAI_*`), not the other startup settings
+below. Precedence there is host Secret > host ConfigMap > LLM Secret > process
+env.
#### Core runtime
@@ -93,9 +95,9 @@ Precedence there is host Secret > host ConfigMap > LLM Secret > process env.
| Variable | Default | Source | Description |
| --------------------------------------------------- | ------------------------------------------------------------- | -------------------------------------------------- | ----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| Provider credential env vars | - | dev | In dev mode, each provider's key is read from its env var (`OPENAI_API_KEY`, `CLAUDE_API_KEY`, `ZAI_API_KEY`, `BAILIAN_API_KEY`, ...; Bedrock needs `AWS_ACCESS_KEY_ID` and `AWS_SECRET_ACCESS_KEY`). In cluster mode keys come from the Secret in `Host.spec.secretRef`. Full list: [Supported LLM Providers](#supported-llm-providers). |
-| `VERTEX_PROJECT_ID`, `VERTEX_LOCATION` | `VERTEX_LOCATION`: `us-central1` | - | Non-secret Vertex AI settings, read from the mcp-host process environment. `VERTEX_PROJECT_ID` falls back to the service account's `project_id`. |
-| `AWS_REGION` | - | - | Region for Amazon Bedrock (required for Bedrock), read from the process environment. |
-| `AZURE_OPENAI_ENDPOINT`, `AZURE_OPENAI_API_VERSION` | - | - | Azure OpenAI resource endpoint (required for Azure; must be `https`) and optional API version, read from the process environment. |
+| `VERTEX_PROJECT_ID`, `VERTEX_LOCATION` | `VERTEX_LOCATION`: `us-central1` | - | Non-secret Vertex AI settings. On a Host, set under Host → Environment (per-Host env first, then process env); dev mode reads the process env. `VERTEX_PROJECT_ID` falls back to the service account's `project_id`. |
+| `AWS_REGION` | - | - | Region for Amazon Bedrock (required for Bedrock). On a Host, set under Host → Environment (per-Host env first, then process env); dev mode reads the process env. |
+| `AZURE_OPENAI_ENDPOINT`, `AZURE_OPENAI_API_VERSION` | - | - | Azure OpenAI resource endpoint (required for Azure; must be `https`) and optional API version. On a Host, set under Host → Environment (per-Host env first, then process env); dev mode reads the process env. |
| `CLERUM_LLM_ALLOWED_MODELS_CM` | `clerum-llm-allowed-models` | - | Name of the LLM allowlist ConfigMap that control-api writes. A test/canary override only: pointing it at a ConfigMap control-api does not write leaves the Host with no allowed models. |
| `MCP_HOST_CODEX_SUBSCRIPTION_ENABLED` | `false` | CM `true`; WRC | Allow the `codex-subscription` provider. Only the exact value `true` enables it. See [Use a ChatGPT or Grok subscription](../docs/how-to/connect-llm-subscription.md). |
| `MCP_HOST_GROK_SUBSCRIPTION_ENABLED` | `false` | HCC (only when the Host is eligible for Grok); WRC | Allow the `grok-subscription` provider. HCC adds it only for Hosts whose Grok projection grants execution, so you do not set it in the ConfigMap. |
diff --git a/mcp-host/package-lock.json b/mcp-host/package-lock.json
index 8e131b7f2..8424c1378 100644
--- a/mcp-host/package-lock.json
+++ b/mcp-host/package-lock.json
@@ -1,12 +1,12 @@
{
"name": "clerum-mcp-host",
- "version": "0.1.562",
+ "version": "0.1.563",
"lockfileVersion": 3,
"requires": true,
"packages": {
"": {
"name": "clerum-mcp-host",
- "version": "0.1.562",
+ "version": "0.1.563",
"license": "SEE LICENSE IN LICENSE",
"dependencies": {
"@anthropic-ai/sdk": "^0.32.0",
diff --git a/mcp-host/package.json b/mcp-host/package.json
index 0226dcd6d..7dc5ae1aa 100644
--- a/mcp-host/package.json
+++ b/mcp-host/package.json
@@ -1,6 +1,6 @@
{
"name": "clerum-mcp-host",
- "version": "0.1.562",
+ "version": "0.1.563",
"description": "MCP Host - reads Host CRD and provides LLM access via OpenAI/Claude",
"main": "dist/main.js",
"engines": {