@eventmodelers/cli 1.0.101 → 1.0.102
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- package/README.md +5 -0
- package/package.json +1 -1
package/README.md
CHANGED
|
@@ -236,6 +236,11 @@ Keys: `OPENAI_API_KEY` (codex), `GEMINI_API_KEY` (gemini), and for Hermes a prov
|
|
|
236
236
|
servers only from `~/.hermes/config.yaml`, so the images ship the eventmodelers server there (env references, no secret); outside
|
|
237
237
|
Docker the CLI logs the snippet to add. Run `hermes` in a container as `-e AGENT=hermes --model <provider/model>`.
|
|
238
238
|
|
|
239
|
+
**Any OpenAI-compatible endpoint with OpenCode.** `-e MODEL_BASE_URL=<url> -e MODEL_NAME=<id> [-e MODEL_API_KEY=...]` makes the
|
|
240
|
+
OpenCode container (`AGENT=opencode`, agent and build images) use that endpoint — a local Ollama/vLLM (`http://host.docker.internal:11434/v1`),
|
|
241
|
+
OpenRouter, LiteLLM or a company gateway — without writing an `opencode.json`. The entrypoint registers it as provider `custom` and runs
|
|
242
|
+
`--model custom/<MODEL_NAME>`. `MODEL_NAME` is required; other agents reject `MODEL_BASE_URL`.
|
|
243
|
+
|
|
239
244
|
`--agent`, `--exec`, `--local-ai` and `--bash` each pick the runner, so pass at most one of them —
|
|
240
245
|
any two together are rejected. For a local or self-hosted model use `--local-ai`, not `--agent`.
|
|
241
246
|
|
package/package.json
CHANGED
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
{
|
|
2
2
|
"name": "@eventmodelers/cli",
|
|
3
|
-
"version": "1.0.
|
|
3
|
+
"version": "1.0.102",
|
|
4
4
|
"description": "Eventmodelers CLI — real-time Claude agent + skills for Claude Code, for any stack (Node, Supabase, Axon, OpenCQRS, UmaDB, Kurrent, or modeling-only)",
|
|
5
5
|
"type": "module",
|
|
6
6
|
"bin": {
|