@nanobpm/nano-coder 0.29.2 → 0.30.1

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 +27 -2
  2. package/package.json +5 -5
package/README.md CHANGED
@@ -117,7 +117,8 @@ escalation). Redelivering the input returns the same outcome. See [Outcomes](#ou
117
117
 
118
118
  **Slash commands work via ACP too:**
119
119
  - `/compact [--smart|--standard] [focus]` - summarizes the conversation; the result has
120
- `compacted`, `before`, `after`, `tokensBefore`, `tokensAfter`, `summarized`, `mode` and `fallback`
120
+ `compacted`, `before`, `after`, `tokensBefore`, `tokensAfter`, `summarized`, `mode`, `fallback`
121
+ and `truncated`
121
122
  - `/settings` - returns current settings as JSON
122
123
  - `/tools` - lists registered tools
123
124
  - `/plan` - returns `plan` (JSON) and `text` (the rendered plan)
@@ -368,7 +369,7 @@ Create `~/.config/nano-coder/config.toml` (every field is optional). Directories
368
369
  ```toml
369
370
  model = "anthropic/claude-sonnet-4-5" # provider/model
370
371
  default_provider = "mock" # used when the model has no known provider prefix
371
- temperature = 0.7
372
+ temperature = 0.7 # or "default" to send none (see Temperature below)
372
373
  max_tokens = 4096
373
374
  max_iterations = 0 # LLM calls per user input (0 = unbounded)
374
375
  system_prompt = "You are a helpful assistant with access to tools."
@@ -481,6 +482,30 @@ or your workspace domain override `base_url`, e.g.
481
482
  as thinking models like K3 require. Set `extra_body = { reasoning_effort = "low" }` to
482
483
  make K3 think less.
483
484
 
485
+ ### Temperature
486
+
487
+ `temperature` is a number, or `"default"` to send none so the model uses its own default.
488
+ It can be set for all models, for one provider, or for one model; the most specific
489
+ setting wins:
490
+
491
+ ```toml
492
+ temperature = 0.7 # all models
493
+
494
+ [providers.groq]
495
+ temperature = "default" # every groq model uses its own default
496
+
497
+ [providers.anthropic.models."claude-sonnet-4-5"]
498
+ temperature = 0.3 # this model only
499
+ ```
500
+
501
+ Some models accept no temperature, and for them the model default is the only option:
502
+ GitHub Copilot's reasoning models (GPT-5 and later, Grok, …) and any provider with
503
+ `drop_params = ["temperature"]` (such as the `kimi` preset). A number set for such a
504
+ provider or model is ignored with a warning at startup and when you switch to it; the
505
+ top-level `temperature` just doesn't apply to them. Anthropic accepts 0 to 1, so a higher
506
+ value is sent as 1, with a warning. `/context` shows the temperature in use and where it
507
+ comes from, and `/settings` edits it for the current model, its provider, or all models.
508
+
484
509
  Other per-provider fields: `replay_reasoning`, `max_tokens_param` (`max_tokens`, or `max_completion_tokens`
485
510
  which is the `openai` default), `retry_initial_backoff_ms`, `retry_max_backoff_ms` and
486
511
  `retryable_statuses`.
package/package.json CHANGED
@@ -1,6 +1,6 @@
1
1
  {
2
2
  "name": "@nanobpm/nano-coder",
3
- "version": "0.29.2",
3
+ "version": "0.30.1",
4
4
  "description": "A 6MB coding agent. Run a fleet on your laptop.",
5
5
  "license": "Apache-2.0",
6
6
  "repository": {
@@ -31,9 +31,9 @@
31
31
  "node": ">=18"
32
32
  },
33
33
  "optionalDependencies": {
34
- "@nanobpm/nano-coder-darwin-arm64": "0.29.2",
35
- "@nanobpm/nano-coder-darwin-x64": "0.29.2",
36
- "@nanobpm/nano-coder-linux-arm64": "0.29.2",
37
- "@nanobpm/nano-coder-linux-x64": "0.29.2"
34
+ "@nanobpm/nano-coder-darwin-arm64": "0.30.1",
35
+ "@nanobpm/nano-coder-darwin-x64": "0.30.1",
36
+ "@nanobpm/nano-coder-linux-arm64": "0.30.1",
37
+ "@nanobpm/nano-coder-linux-x64": "0.30.1"
38
38
  }
39
39
  }