@aiiware/aii 0.16.17 → 0.16.22
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 +21 -1
- package/bin/aii +620 -617
- package/package.json +8 -8
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> 0.16.
|
|
12
|
+
<strong>npm:</strong> <code>@aiiware/aii</code> · <strong>Version:</strong> 0.16.22 · <strong>Node.js:</strong> >= 18
|
|
13
13
|
</p>
|
|
14
14
|
|
|
15
15
|
---
|
|
@@ -184,6 +184,7 @@ During interactive sessions, type `/` to see all commands. Highlights:
|
|
|
184
184
|
| `Ctrl+C` | Exit immediately |
|
|
185
185
|
| `Ctrl+D` | Graceful exit with session summary |
|
|
186
186
|
| `Ctrl+L` | Clear conversation |
|
|
187
|
+
| `Ctrl+O` | Peek full tool output (full-screen) · toggle subagent tree — up/down to navigate, `Ctrl+O` again to close |
|
|
187
188
|
| `Ctrl+U` | Clear type-ahead queue / input line |
|
|
188
189
|
| `Up/Down` | Navigate input history |
|
|
189
190
|
| `Tab` | Autocomplete commands |
|
|
@@ -205,6 +206,25 @@ The agent delegates complex tasks to specialized subagents running in parallel:
|
|
|
205
206
|
|
|
206
207
|
Define custom agents in `.aii/agents/<name>.md` with YAML frontmatter for custom system prompts, model tiers, and tool access.
|
|
207
208
|
|
|
209
|
+
### Task Planning
|
|
210
|
+
|
|
211
|
+
For multi-step work, the agent breaks the job into a live task list and renders it inline in the stream — pending (`☐`), in-progress (`▪`), and done (`✓`) — updating as it goes. The plan is visible, not a black box: you always see what it intends to do next and what's already finished.
|
|
212
|
+
|
|
213
|
+
### Security
|
|
214
|
+
|
|
215
|
+
Aii is an autonomous agent — so it's built to act without handing over your machine:
|
|
216
|
+
|
|
217
|
+
| Protection | What it does |
|
|
218
|
+
|------------|--------------|
|
|
219
|
+
| **Workspace fence** | File reads and writes stay inside your workspace, resolved through `realpath` so `..` and symlink escapes are blocked; sensitive paths (`~/.aii` secrets, keychains) are denylisted |
|
|
220
|
+
| **Permission model** | Asks before running commands or writing files; grants are scoped (per path / per session); `--auto` opts out when you trust the run |
|
|
221
|
+
| **Untrusted-content framing** | Web and MCP content is fenced as untrusted, so a malicious page can't smuggle instructions into the agent (prompt-injection defense) |
|
|
222
|
+
| **Supply-chain integrity** | Installed skills and personas are pinned by commit SHA and checked against per-file SHA-256 manifests at load — fail-closed if anything's been tampered with |
|
|
223
|
+
| **Persona-hook consent** | Hooks bundled in a remotely-installed persona require explicit first-use consent (keyed on install origin), so adding a persona can't silently run code |
|
|
224
|
+
| **Per-channel caps** | Telegram bots get a capability cap — read-only, no-bash, or full — so a chat bridge isn't a full shell by default |
|
|
225
|
+
|
|
226
|
+
Local-first by design — your code and API keys stay on your machine; the only thing that leaves is the prompt you send to your chosen LLM provider.
|
|
227
|
+
|
|
208
228
|
### Git Worktrees
|
|
209
229
|
|
|
210
230
|
Work on multiple features in parallel without stashing:
|