@nanobpm/nano-coder 0.10.0 → 0.12.0

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 +28 -11
  2. package/package.json +5 -5
package/README.md CHANGED
@@ -97,7 +97,7 @@ echoes it in `_meta.plan`, and the model is told about it with the first prompt
97
97
  advertises this as `agentCapabilities._meta.planSeed`. See [Task Plans](#task-plans).
98
98
 
99
99
  **Outcomes.** When the model calls `report_outcome`, the `session/prompt` result carries
100
- `_meta.outcome`: `{"status": "completed" | "blocked", "summary": "..."}`. A client can use it
100
+ `_meta.outcome`: `{"status": "completed" | "blocked" | "needs_input", "summary": "..."}`. A client can use it
101
101
  instead of guessing from the stop reason: `blocked` means the model needs help (an
102
102
  escalation). Redelivering the input returns the same outcome. See [Outcomes](#outcomes).
103
103
 
@@ -139,7 +139,9 @@ src/
139
139
  ├── lineedit.rs # Key-by-key prompt input (Ctrl-O, steering on the status line)
140
140
  ├── instructions.rs # AGENTS.md / CLAUDE.md discovery for the system prompt
141
141
  ├── plan.rs # Task plan and the plan_add / plan_update / plan_show tools
142
- ├── goal.rs # report_outcome tool (completed / blocked)
142
+ ├── goal.rs # report_outcome tool (completed / blocked / needs_input)
143
+ ├── mode.rs # Agent mode (normal / plan / auto) and the plan-mode tool gate
144
+ ├── question.rs # question tool and the mid-turn question / turn-cap rendezvous
143
145
  ├── commands.rs # Slash-command table for /help and the as-you-type menu
144
146
  ├── skills.rs # SKILL.md discovery, ai.lock sources and the load_skill tool
145
147
  ├── reminders.rs # <system-reminder> notes appended to tool results
@@ -178,8 +180,11 @@ The harness exposes 6 lifecycle hook events:
178
180
  - `edit_file` - Replace exact text (`path`, `old_string`, `new_string`, optional `replace_all`).
179
181
  Fails unless `old_string` matches exactly once (or `replace_all` is set).
180
182
  - `plan_add`, `plan_update`, `plan_show` - The agent's task plan (see [Task Plans](#task-plans)).
181
- - `report_outcome` - Report the task `completed` or `blocked`, with a `summary`; ends the turn
182
- (see [Outcomes](#outcomes)).
183
+ - `report_outcome` - Report the task `completed`, `blocked` or `needs_input`, with a `summary`; ends
184
+ the turn (see [Outcomes](#outcomes)).
185
+ - `question` - Ask the user a structured question and wait for the answer, without ending the turn.
186
+ Interactive sessions only; in auto mode an unanswered question is resolved after 15s with the
187
+ away message. Headless (ACP) sessions get an error instead.
183
188
  - `load_skill` - Return a skill's instructions and list its other files; `name`. Offered only
184
189
  when skills were found (see [Skills](#skills)).
185
190
 
@@ -269,13 +274,14 @@ list is built from the same table as `/help` (`src/commands.rs`).
269
274
  - `/compact [focus]` - Summarize older messages with the current model, keeping the latest
270
275
  message. Optional text tells the summary what to focus on. Esc Esc or Ctrl-C cancels
271
276
  - `/verbosity [quiet|normal|verbose|debug]` - Show or set how much is printed (see below)
272
- - `/context` - Show context usage, window, session token totals, auto-compaction state and the loaded instruction files
277
+ - `/context` - Show context usage, window, session token totals, AI Credits (GitHub Copilot), auto-compaction state and the loaded instruction files
273
278
  - `/settings` - Interactive settings menu:
274
279
  - **Model**: pick a provider, then a model from its live model list (or type an ID)
275
280
  - **Add or edit a provider**: name, API kind (OpenAI-compatible, Anthropic, Copilot),
276
281
  base URL, key source (env var, shell command, or a literal key; the file is then
277
282
  written with mode 0600) and default model
278
283
  - temperature, max tokens, system prompt
284
+ - **Turn cap** (`max_iterations`): LLM calls per input; normal mode asks before stopping
279
285
  - **Context**: auto-compaction on/off, threshold, context-window override
280
286
  - **Verbosity**
281
287
  - **Save to config file**: writes only the keys you changed into the config file
@@ -285,6 +291,10 @@ list is built from the same table as `/help` (`src/commands.rs`).
285
291
  - `/skills` - List the skills the agent can load, where each lives, and any loading warnings
286
292
  - `/plan` - Show the agent's task plan with all notes
287
293
  - `/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)
294
+ - `/mode [normal|plan|auto]` - Show or set the agent mode (Shift+Tab cycles it, at the prompt or mid-turn):
295
+ - **normal** - full tools; reaching the turn cap asks whether to keep going
296
+ - **plan** - read-only: mutating tools (`bash`, `write_file`, `edit_file`) are gated, only analysis and output
297
+ - **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"
288
298
  - `/providers` - List providers, endpoints and whether their API key is available
289
299
  - `/session` - Show the session ID and log path
290
300
  - `/restart` - Start a fresh session (clean context) without exiting
@@ -516,8 +526,10 @@ shows when the message was sent. Turn this off with `timestamps = false`.
516
526
  In an interactive terminal the bottom row shows the provider/model, context usage
517
527
  (`~` marks an estimate; without it the figure is anchored to the provider's reported usage),
518
528
  a fill bar, message count, session input/output tokens, the auto-compaction threshold and
519
- count, and what the agent is doing. It uses a terminal scroll region, follows resizes, and is
520
- off when stdin/stdout isn't a TTY or `AGENTIC_NO_STATUS` is set. The conversation is kept
529
+ count, the active mode when it is `plan` or `auto` (the default `normal` is not shown, to
530
+ save space), and what the agent is doing. With a GitHub Copilot model it also shows the session's
531
+ AI Credits (`0.4 AIC`), summed from the `total_nano_aiu` each response reports. It uses a terminal
532
+ scroll region, follows resizes, and is off when stdin/stdout isn't a TTY or `AGENTIC_NO_STATUS` is set. The conversation is kept
521
533
  directly above the status line (empty space collects at the top), so shrinking the window
522
534
  drops empty rows rather than pushing the conversation out of view.
523
535
 
@@ -639,16 +651,21 @@ Plan and outcome calls don't count. Set `reminders = false` to turn them off.
639
651
  ## Outcomes
640
652
 
641
653
  `report_outcome` is the model's explicit end-of-task signal: `status` is `completed` (the
642
- whole task is done and checked; the summary lists PRs or commits) or `blocked` (after three
654
+ whole task is done and checked; the summary lists PRs or commits), `blocked` (after three
643
655
  or more different failed attempts, or when only a person can unblock it; the summary says
644
- what is needed). The call ends the turn. Other calls in the same response still run, then the
645
- summary becomes the final answer (`Blocked: ...` for blocked), and the outcome is returned
656
+ what is needed), or `needs_input` (the model has a question or needs a decision; the summary
657
+ is the question). The call ends the turn. Other calls in the same response still run, then the
658
+ summary becomes the final answer (`Blocked: ...` / `Question: ...`), and the outcome is returned
646
659
  in ACP `_meta.outcome` and recorded in the session log's `turn_end` record. If the harness
647
660
  stops after the call but before the turn ends, resuming the input finishes it with the
648
661
  recorded outcome without calling the model again. In the terminal the call shows as
649
- `✔ completed` or `■ blocked` followed by the summary. Set `outcome_tool = false` to leave the
662
+ `✔ completed`, `■ blocked`, or `? needs input` followed by the summary. Set `outcome_tool = false` to leave the
650
663
  tool out.
651
664
 
665
+ `needs_input` is the structural "waiting on the user" signal: an orchestrator (or auto mode)
666
+ can tell it apart from a clean `completed` without guessing from the text. For a richer,
667
+ multi-choice question that does not end the turn, the model uses the `question` tool instead.
668
+
652
669
  ## Sessions
653
670
 
654
671
  When `persist_sessions` is on, each conversation is written to `<session_dir>/<id>.jsonl`.
package/package.json CHANGED
@@ -1,6 +1,6 @@
1
1
  {
2
2
  "name": "@nanobpm/nano-coder",
3
- "version": "0.10.0",
3
+ "version": "0.12.0",
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": "0.10.0",
35
- "@nanobpm/nano-coder-darwin-x64": "0.10.0",
36
- "@nanobpm/nano-coder-linux-arm64": "0.10.0",
37
- "@nanobpm/nano-coder-linux-x64": "0.10.0"
34
+ "@nanobpm/nano-coder-darwin-arm64": "0.12.0",
35
+ "@nanobpm/nano-coder-darwin-x64": "0.12.0",
36
+ "@nanobpm/nano-coder-linux-arm64": "0.12.0",
37
+ "@nanobpm/nano-coder-linux-x64": "0.12.0"
38
38
  }
39
39
  }