@nanobpm/nano-coder 0.16.2 → 0.18.0

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 +8 -6
  2. package/package.json +5 -5
package/README.md CHANGED
@@ -298,7 +298,7 @@ argument: a type-ahead list narrows as you type and Tab completes it.
298
298
  base URL, key source (env var, shell command, or a literal key; the file is then
299
299
  written with mode 0600) and default model
300
300
  - temperature, max tokens, system prompt
301
- - **Turn cap** (`max_iterations`): LLM calls per input; normal mode asks before stopping
301
+ - **Turn cap** (`max_iterations`): LLM calls per input (0 = unbounded); a positive cap makes normal mode ask before stopping
302
302
  - **Context**: auto-compaction on/off, threshold, compaction mode, context-window override
303
303
  - **Verbosity**
304
304
  - **Save to config file**: writes only the keys you changed into the config file
@@ -310,7 +310,7 @@ argument: a type-ahead list narrows as you type and Tab completes it.
310
310
  - `/queue [list|remove N...|edit N text|clear]` - Show or edit the queued messages. Works while a turn runs, so a queued message can be removed or rewritten before it is sent.
311
311
  - `/model [provider/model]` - Show the current model and pick a new one: scroll the provider list, then the model list (Esc steps back). With an argument, switches directly (conversation is kept). Typing `/model ` shows a type-ahead of the current model, recently used models, and each configured provider's default model; Tab completes (a bare provider name completes to its default model). Recently used models are kept in `~/.local/share/nano-coder/recent-models.json`
312
312
  - `/mode [normal|plan|auto]` - Show or set the agent mode (Shift+Tab cycles it, at the prompt or mid-turn):
313
- - **normal** - full tools; reaching the turn cap asks whether to keep going
313
+ - **normal** - full tools; reaching a positive turn cap asks whether to keep going
314
314
  - **plan** - read-only: mutating tools (`bash`, `write_file`, `edit_file`) are gated, only analysis and output
315
315
  - **auto** - no turn cap; a `question` left unanswered for 15s is answered with "the user is away from the keyboard, make the best decision you can"
316
316
  - `/providers` - List providers, endpoints and whether their API key is available
@@ -347,7 +347,7 @@ model = "anthropic/claude-sonnet-4-5" # provider/model
347
347
  default_provider = "mock" # used when the model has no known provider prefix
348
348
  temperature = 0.7
349
349
  max_tokens = 4096
350
- max_iterations = 50 # LLM calls per user input
350
+ max_iterations = 0 # LLM calls per user input (0 = unbounded)
351
351
  system_prompt = "You are a helpful assistant with access to tools."
352
352
  bash_timeout_secs = 600
353
353
  persist_sessions = true
@@ -615,9 +615,11 @@ It needs a session log, and falls back to a standard summary when `persist_sessi
615
615
  that the originals can be retrieved. Tool results clipped at compaction point at their ID.
616
616
  - **History tools.** Once a smart summary is in the context, the agent gets two tools
617
617
  over the current session's log (and only that one):
618
- - `history_search(pattern, role?, before?, after?, limit?)` - case-insensitive regex (or
619
- plain text) search, newest first, one `#N role name (time): snippet` line per match.
620
- Earlier history lookups are not searched.
618
+ - `history_search(pattern, role?, before?, after?, order?, limit?)` - case-insensitive
619
+ regex (or plain text) search. Newest first by default (`order=oldest` for early
620
+ history); each matching message is one `#N role name (time): snippet` line with up to
621
+ three snippets (and a `[K matches]` count when more matched). Earlier history lookups
622
+ are not searched.
621
623
  - `history_read(id, max_output_length?)` - one message in full, bounded like other tool
622
624
  output (the whole is spilled to a file when it is longer).
623
625
  Before a smart compaction the tools are not offered, so they cost nothing.
package/package.json CHANGED
@@ -1,6 +1,6 @@
1
1
  {
2
2
  "name": "@nanobpm/nano-coder",
3
- "version": "0.16.2",
3
+ "version": "0.18.0",
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": "0.16.2",
35
- "@nanobpm/nano-coder-darwin-x64": "0.16.2",
36
- "@nanobpm/nano-coder-linux-arm64": "0.16.2",
37
- "@nanobpm/nano-coder-linux-x64": "0.16.2"
34
+ "@nanobpm/nano-coder-darwin-arm64": "0.18.0",
35
+ "@nanobpm/nano-coder-darwin-x64": "0.18.0",
36
+ "@nanobpm/nano-coder-linux-arm64": "0.18.0",
37
+ "@nanobpm/nano-coder-linux-x64": "0.18.0"
38
38
  }
39
39
  }