@aiiware/aii 0.12.16 → 0.13.1
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.
- package/README.md +14 -4
- package/bin/aii +474 -474
- package/package.json +1 -1
package/README.md
CHANGED
|
@@ -9,7 +9,7 @@ An autonomous AI assistant that lives in your terminal. Ask it anything — it r
|
|
|
9
9
|
</p>
|
|
10
10
|
|
|
11
11
|
<p align="center">
|
|
12
|
-
<strong>npm:</strong> <code>@aiiware/aii</code> · <strong>Version:</strong> 0.
|
|
12
|
+
<strong>npm:</strong> <code>@aiiware/aii</code> · <strong>Version:</strong> 0.13.1 · <strong>Node.js:</strong> >= 18
|
|
13
13
|
</p>
|
|
14
14
|
|
|
15
15
|
---
|
|
@@ -80,7 +80,7 @@ Or during a session: `/model anthropic:claude-sonnet-4`
|
|
|
80
80
|
aii loop "fix all failing tests" --verify "npm test" --budget 0.50
|
|
81
81
|
```
|
|
82
82
|
|
|
83
|
-
The agent loops with fresh context each iteration, stopping when your verification command passes, the budget is hit, or you press
|
|
83
|
+
The agent loops with fresh context each iteration, stopping when your verification command passes, the budget is hit, or you press Esc. Steer it mid-run with `/stop`, `/stats`, and `/note` — the status bar tracks progress in real time.
|
|
84
84
|
|
|
85
85
|
---
|
|
86
86
|
|
|
@@ -200,10 +200,20 @@ Run the agent in a continuous loop with guardrails:
|
|
|
200
200
|
```bash
|
|
201
201
|
aii loop "fix all TypeScript errors"
|
|
202
202
|
aii loop --max 10 --verify "npm test" "add missing tests"
|
|
203
|
-
aii loop --budget 1.00 --duration
|
|
203
|
+
aii loop --budget 1.00 --duration 8h "refactor the auth module"
|
|
204
204
|
```
|
|
205
205
|
|
|
206
|
-
**Exit conditions:** `--max N`, `--budget $N`, `--verify "cmd"`, `--promise "text"`, `--duration <
|
|
206
|
+
**Exit conditions:** `--max N`, `--budget $N`, `--verify "cmd"`, `--promise "text"`, `--duration <time>`, `--input-tokens N`, `--output-tokens N`
|
|
207
|
+
|
|
208
|
+
**Mid-loop controls** — type while the loop runs:
|
|
209
|
+
|
|
210
|
+
| Command | What It Does |
|
|
211
|
+
|---------|-------------|
|
|
212
|
+
| `/stop` | Finish current iteration, then exit cleanly |
|
|
213
|
+
| `/stats` | Live view of tokens, cost, iterations, elapsed time |
|
|
214
|
+
| `/note <text>` | Guide the agent's next iteration |
|
|
215
|
+
|
|
216
|
+
The status bar updates in real time with iteration count, token usage, estimated cost, and tool calls — you always know what the loop is doing and what it's costing.
|
|
207
217
|
|
|
208
218
|
### Telegram Integration
|
|
209
219
|
|