@nanobpm/nano-coder 0.60.1 → 0.62.0
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.
- package/README.md +45 -8
- package/package.json +5 -5
package/README.md
CHANGED
|
@@ -318,11 +318,9 @@ the [permission rules and sandbox](#permissions-and-sandbox) instead.
|
|
|
318
318
|
|
|
319
319
|
## Permissions and Sandbox
|
|
320
320
|
|
|
321
|
-
Every tool call is checked before it runs
|
|
322
|
-
|
|
323
|
-
|
|
324
|
-
the few calls that can be neither approved nor denied automatically (see **Shell loops**
|
|
325
|
-
below).
|
|
321
|
+
nano-coder never stops to ask for approval. Every tool call is checked before it runs
|
|
322
|
+
instead, and a blocked call returns an error telling the model to stop and ask the user
|
|
323
|
+
rather than work around the block.
|
|
326
324
|
|
|
327
325
|
**Order of checks:** `deny` rules, then `allow` rules, then the built-in guards. Deny always
|
|
328
326
|
wins. An allow rule approves a shell command only when *every* command in it matches, so
|
|
@@ -356,9 +354,9 @@ wherever the two `gh` commands are, and an unrolled command that is denied or ca
|
|
|
356
354
|
is denied. The unroll is capped (64 iterations) and refuses a body that rebinds the loop
|
|
357
355
|
variable or still expands something at run time after substitution; those fall through to
|
|
358
356
|
the next rule. A loop that still cannot be verified — a non-literal list, or a static body
|
|
359
|
-
command that is not a known read-only utility — is **
|
|
360
|
-
|
|
361
|
-
|
|
357
|
+
command that is not a known read-only utility — **runs when the OS sandbox is on** (the
|
|
358
|
+
sandbox confines what it can write) and is **blocked** with the usual guidance when it is
|
|
359
|
+
off; nano-coder never prompts for it. The hard blocks always stand: a command name computed
|
|
362
360
|
at run time, `eval`/interpreters (`sh -c`, `python -c`, ...), path-qualified programs outside
|
|
363
361
|
`/bin`/`/usr/bin`, assignments to `PATH`/`IFS` and other dangerous names, arithmetic-assignment
|
|
364
362
|
tricks, and writes/redirections to computed targets.
|
|
@@ -727,6 +725,45 @@ api_key_env = "BAILIAN_TOKEN_PLAN_API_KEY"
|
|
|
727
725
|
as thinking models like K3 require. Set `extra_body = { reasoning_effort = "low" }` to
|
|
728
726
|
make K3 think less.
|
|
729
727
|
|
|
728
|
+
#### Regional OpenRouter workspaces and curated model lists
|
|
729
|
+
|
|
730
|
+
Some OpenRouter workspaces (e.g. Camunda's) reject the global `openrouter.ai` host, so
|
|
731
|
+
the `openrouter` preset fails with them. They accept only the regional hosts
|
|
732
|
+
`us.openrouter.ai` and `eu.openrouter.ai`, and each model is served on just one of them.
|
|
733
|
+
Three provider settings cover this:
|
|
734
|
+
|
|
735
|
+
- `[providers.<name>.models."<model>"]` takes a `base_url`, which overrides the
|
|
736
|
+
provider's for that model, and a display `name`.
|
|
737
|
+
- `list_models = "configured"` makes `/model`, `--list-models` and `/model` Tab completion
|
|
738
|
+
offer only the models configured under `models`, with their names, instead of the
|
|
739
|
+
endpoint's whole `/models` catalogue. The default is `"endpoint"`.
|
|
740
|
+
- `disabled = true` hides a provider (a preset too) from `/providers`, the pickers and
|
|
741
|
+
suggestions. A model spec that names it is an error.
|
|
742
|
+
|
|
743
|
+
```toml
|
|
744
|
+
model = "openrouter-camunda/moonshotai/kimi-k3"
|
|
745
|
+
|
|
746
|
+
[providers.openrouter]
|
|
747
|
+
disabled = true # the global host is rejected
|
|
748
|
+
|
|
749
|
+
[providers.openrouter-camunda]
|
|
750
|
+
kind = "openai"
|
|
751
|
+
base_url = "https://us.openrouter.ai/api/v1"
|
|
752
|
+
api_key_env = "OPENROUTER_API_KEY"
|
|
753
|
+
list_models = "configured"
|
|
754
|
+
|
|
755
|
+
[providers.openrouter-camunda.models."moonshotai/kimi-k3"]
|
|
756
|
+
name = "Kimi K3"
|
|
757
|
+
|
|
758
|
+
[providers.openrouter-camunda.models."amazon/nova-lite-v1"]
|
|
759
|
+
name = "Nova Lite 1.0"
|
|
760
|
+
base_url = "https://eu.openrouter.ai/api/v1" # served in the EU only
|
|
761
|
+
```
|
|
762
|
+
|
|
763
|
+
[`examples/openrouter-camunda.toml`](examples/openrouter-camunda.toml) is the full
|
|
764
|
+
equivalent of the `opencode.json` in Camunda's handbook. A model's `"provider": {"api": …}`
|
|
765
|
+
there becomes its `base_url` here.
|
|
766
|
+
|
|
730
767
|
### Temperature
|
|
731
768
|
|
|
732
769
|
`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.
|
|
3
|
+
"version": "0.62.0",
|
|
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.
|
|
31
|
-
"@nanobpm/nano-coder-darwin-x64": "0.
|
|
32
|
-
"@nanobpm/nano-coder-linux-arm64": "0.
|
|
33
|
-
"@nanobpm/nano-coder-linux-x64": "0.
|
|
30
|
+
"@nanobpm/nano-coder-darwin-arm64": "0.62.0",
|
|
31
|
+
"@nanobpm/nano-coder-darwin-x64": "0.62.0",
|
|
32
|
+
"@nanobpm/nano-coder-linux-arm64": "0.62.0",
|
|
33
|
+
"@nanobpm/nano-coder-linux-x64": "0.62.0"
|
|
34
34
|
}
|
|
35
35
|
}
|