@nanobpm/nano-coder 0.60.0 → 0.61.0

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.
Files changed (2) hide show
  1. package/README.md +39 -0
  2. package/package.json +5 -5
package/README.md CHANGED
@@ -727,6 +727,45 @@ api_key_env = "BAILIAN_TOKEN_PLAN_API_KEY"
727
727
  as thinking models like K3 require. Set `extra_body = { reasoning_effort = "low" }` to
728
728
  make K3 think less.
729
729
 
730
+ #### Regional OpenRouter workspaces and curated model lists
731
+
732
+ Some OpenRouter workspaces (e.g. Camunda's) reject the global `openrouter.ai` host, so
733
+ the `openrouter` preset fails with them. They accept only the regional hosts
734
+ `us.openrouter.ai` and `eu.openrouter.ai`, and each model is served on just one of them.
735
+ Three provider settings cover this:
736
+
737
+ - `[providers.<name>.models."<model>"]` takes a `base_url`, which overrides the
738
+ provider's for that model, and a display `name`.
739
+ - `list_models = "configured"` makes `/model`, `--list-models` and `/model` Tab completion
740
+ offer only the models configured under `models`, with their names, instead of the
741
+ endpoint's whole `/models` catalogue. The default is `"endpoint"`.
742
+ - `disabled = true` hides a provider (a preset too) from `/providers`, the pickers and
743
+ suggestions. A model spec that names it is an error.
744
+
745
+ ```toml
746
+ model = "openrouter-camunda/moonshotai/kimi-k3"
747
+
748
+ [providers.openrouter]
749
+ disabled = true # the global host is rejected
750
+
751
+ [providers.openrouter-camunda]
752
+ kind = "openai"
753
+ base_url = "https://us.openrouter.ai/api/v1"
754
+ api_key_env = "OPENROUTER_API_KEY"
755
+ list_models = "configured"
756
+
757
+ [providers.openrouter-camunda.models."moonshotai/kimi-k3"]
758
+ name = "Kimi K3"
759
+
760
+ [providers.openrouter-camunda.models."amazon/nova-lite-v1"]
761
+ name = "Nova Lite 1.0"
762
+ base_url = "https://eu.openrouter.ai/api/v1" # served in the EU only
763
+ ```
764
+
765
+ [`examples/openrouter-camunda.toml`](examples/openrouter-camunda.toml) is the full
766
+ equivalent of the `opencode.json` in Camunda's handbook. A model's `"provider": {"api": …}`
767
+ there becomes its `base_url` here.
768
+
730
769
  ### Temperature
731
770
 
732
771
  `temperature` is a number, or `"default"` to send none so the model uses its own default.
package/package.json CHANGED
@@ -1,6 +1,6 @@
1
1
  {
2
2
  "name": "@nanobpm/nano-coder",
3
- "version": "0.60.0",
3
+ "version": "0.61.0",
4
4
  "description": "A 6MB coding agent. Run a fleet on your laptop.",
5
5
  "license": "Apache-2.0",
6
6
  "repository": {
@@ -27,9 +27,9 @@
27
27
  "node": ">=18"
28
28
  },
29
29
  "optionalDependencies": {
30
- "@nanobpm/nano-coder-darwin-arm64": "0.60.0",
31
- "@nanobpm/nano-coder-darwin-x64": "0.60.0",
32
- "@nanobpm/nano-coder-linux-arm64": "0.60.0",
33
- "@nanobpm/nano-coder-linux-x64": "0.60.0"
30
+ "@nanobpm/nano-coder-darwin-arm64": "0.61.0",
31
+ "@nanobpm/nano-coder-darwin-x64": "0.61.0",
32
+ "@nanobpm/nano-coder-linux-arm64": "0.61.0",
33
+ "@nanobpm/nano-coder-linux-x64": "0.61.0"
34
34
  }
35
35
  }