@nanobpm/nano-coder 0.53.0 → 0.55.0

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 +22 -4
  2. package/package.json +5 -5
package/README.md CHANGED
@@ -21,7 +21,7 @@ cargo install nano-coder # or build from source
21
21
  - **Lifecycle Hooks**: 6 internal hook events for observing agent behavior, plus
22
22
  Claude Code–compatible external user hooks loaded from `.claude/settings.json`
23
23
  - **Configuration**: TOML-based config file at `~/.config/nano-coder/config.toml`
24
- - **Commands**: `/help`, `/compact`, `/context`, `/verbosity`, `/settings`, `/tools`, `/skills`, `/queue`, `/restart`, `/exit`
24
+ - **Commands**: `/help`, `/version`, `/compact`, `/context`, `/verbosity`, `/settings`, `/tools`, `/skills`, `/queue`, `/restart`, `/exit`
25
25
  - **Streaming output**: answers stream in, thinking shows collapsed, tool calls show inline
26
26
  - **Status line** as the bottom row of the terminal, plus manual and automatic context compaction
27
27
  - **Task plans**: `plan_*` tools keep a plan with notes outside the conversation, so long tasks survive compaction, resume and a change of worker
@@ -59,7 +59,7 @@ show in the same list (marked `steer`, with the id from the `↪ steer #N` note)
59
59
  be withdrawn or rewritten before the agent's next step. A queued message is never injected while the agent is
60
60
  asking for input (the `question` tool's picker owns the terminal until you answer).
61
61
  Slash commands work mid-turn too, where it is safe:
62
- - **Right away:** read-only ones (`/help`, `/tools`, `/skills`, `/providers`, `/session`, `/plan`,
62
+ - **Right away:** read-only ones (`/help`, `/version`, `/tools`, `/skills`, `/providers`, `/session`, `/plan`,
63
63
  `/context`, `/trajectory` (`--json`/`--markdown`), and `/mode` or `/verbosity` without an
64
64
  argument) show the current state. `/plan` shows the plan as the agent updates it.
65
65
  - **From the agent's next step:** `/mode NAME` applies when the agent takes its next step.
@@ -391,6 +391,7 @@ argument set (`/model`, `/mode`, `/verbosity`, `/thinking`) get the same treatme
391
391
  argument: a type-ahead list narrows as you type and Tab completes it.
392
392
 
393
393
  - `/help` - Show available commands
394
+ - `/version` - Show the nano-coder version (the same string `nano-coder --version` prints)
394
395
  - `/compact [--smart|--standard] [focus]` - Summarize older messages with the current model,
395
396
  keeping the latest message. `--smart` / `--standard` override `compaction_mode` for this
396
397
  compaction (see [Smart compaction](#smart-compaction-experimental)). Optional text tells the
@@ -758,8 +759,25 @@ content hash), so session logs stay small and `--resume` still works; a missing
758
759
  resume is sent as a text placeholder.
759
760
 
760
761
  Other per-provider fields: `replay_reasoning`, `max_tokens_param` (`max_tokens`, or `max_completion_tokens`
761
- which is the `openai` default), `retry_initial_backoff_ms`, `retry_max_backoff_ms` and
762
- `retryable_statuses`.
762
+ which is the `openai` default), `retry_initial_backoff_ms`, `retry_max_backoff_ms`,
763
+ `retryable_statuses` and `offline_budget_ms`.
764
+
765
+ A transport failure with no HTTP response (DNS, connection refused or reset, connect or
766
+ idle timeout) is treated as the network being down rather than a failed attempt: nano-coder
767
+ backs off (`retry_initial_backoff_ms` doubling to `retry_max_backoff_ms`) and keeps waiting,
768
+ reporting the outage on a single live line (`network unavailable (…); retrying in Ns
769
+ (Ctrl-C to stop)`) when stderr is a terminal, or announcing it once when output is piped, so
770
+ a long outage never floods the log. When a response finally arrives it announces the
771
+ recovery, so a turn survives a laptop sleep, a Wi-Fi change or a VPN reconnect instead of
772
+ failing after about a minute. A redirect-policy error (a redirect loop or a disallowed
773
+ redirect) is *not* an outage — HTTP is flowing — so it surfaces its actionable error at once
774
+ instead of being retried. These waits do not consume `max_retries` (which still bounds
775
+ HTTP-status retries like 429 or 5xx), and the Copilot session-token refresh waits the same
776
+ way. If a stream drops after it started replying, the partial reply is discarded (nothing
777
+ reaches history) and the request is re-sent, up to ten times per model call. The wait is
778
+ unbounded by default; set `offline_budget_ms` to give up after that many milliseconds
779
+ offline — the budget bounds the whole wait, backoff sleeps included, and no further request
780
+ is issued once it is spent.
763
781
 
764
782
  The old top-level `api_key` / `base_url` still work. They apply to `default_provider`,
765
783
  which becomes `openai` if it was `mock`.
package/package.json CHANGED
@@ -1,6 +1,6 @@
1
1
  {
2
2
  "name": "@nanobpm/nano-coder",
3
- "version": "0.53.0",
3
+ "version": "0.55.0",
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": "0.53.0",
31
- "@nanobpm/nano-coder-darwin-x64": "0.53.0",
32
- "@nanobpm/nano-coder-linux-arm64": "0.53.0",
33
- "@nanobpm/nano-coder-linux-x64": "0.53.0"
30
+ "@nanobpm/nano-coder-darwin-arm64": "0.55.0",
31
+ "@nanobpm/nano-coder-darwin-x64": "0.55.0",
32
+ "@nanobpm/nano-coder-linux-arm64": "0.55.0",
33
+ "@nanobpm/nano-coder-linux-x64": "0.55.0"
34
34
  }
35
35
  }