@burtson-labs/bandit-stealth-cli 1.7.275 → 1.7.277
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 +2 -1
- package/dist/cli.js +472 -469
- package/package.json +7 -1
package/README.md
CHANGED
|
@@ -88,6 +88,7 @@ Type `?` on an empty prompt for the at-a-glance overlay; `/help` for the full li
|
|
|
88
88
|
| Command | Does |
|
|
89
89
|
|---|---|
|
|
90
90
|
| `/help` | Full slash-command list |
|
|
91
|
+
| `/doctor` | Check setup, provider, workspace context, permissions, and next best actions |
|
|
91
92
|
| `/login <key>` | Save a Bandit Cloud API key to `~/.bandit/config.json` (also `/login`, `/login clear`) |
|
|
92
93
|
| `/usage` | Bandit Cloud session + weekly usage limits (`/usage check` for one-line ⚠ flag) |
|
|
93
94
|
| `/model [name]` | Switch model mid-session |
|
|
@@ -205,7 +206,7 @@ If you want to test models outside the recommended list, expect the reasoning-on
|
|
|
205
206
|
- **Native tool calling** — Qwen 3.6, Qwen 2.5 Coder, Llama 3.1+, Devstral, DeepSeek-Coder-V2+. Tool schemas go in Ollama's `tools:` field. Saves ~1500–3000 tokens per turn.
|
|
206
207
|
- **Text-parsing fallback** — Gemma 3/4 and anything else. XML-style tool block lives in the system prompt with the full mitigation stack armed.
|
|
207
208
|
|
|
208
|
-
**Behavior profiles** sit beside capability detection. Capabilities answer "can this model do native tools or vision?" Behavior profiles answer "what should the harness do with it?" For example, Qwen 3.6 starts on native tools and degrades to text tools on retryable native-parser failures; Gemma-family models use compact text-tool prompting and earlier compaction; unknown models default to serialized text tools. Inspect the active profile with `/profile`.
|
|
209
|
+
**Behavior profiles** sit beside capability detection. Capabilities answer "can this model do native tools or vision?" Behavior profiles answer "what should the harness do with it?" For example, Qwen 3.6 starts on native tools and degrades to text tools on retryable native-parser/watchdog failures; Gemma-family models use compact text-tool prompting and earlier compaction; unknown models default to serialized text tools. The profile's `context.outputBudgetTokens` and `reliability.maxParallelTools` now directly drive the loop's heavy-batch serialization and parallel-call cap in both CLI and extension. Inspect the active profile with `/profile`.
|
|
209
210
|
|
|
210
211
|
Workspace overrides load from `.bandit/model-profiles.json`:
|
|
211
212
|
|