@mmmbuto/nexuscrew 0.8.23 → 0.8.25

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 CHANGED
@@ -94,6 +94,7 @@ headless hosts and VPS installations.
94
94
  | Command | Purpose |
95
95
  |---|---|
96
96
  | `nexuscrew` | Start or reuse the background runtime and print a short status |
97
+ | `nexuscrew init [--dry-run] [--port PORT]` | Initialize missing local stores idempotently or preview the operation |
97
98
  | `nexuscrew show` | Start when needed and open the authenticated PWA |
98
99
  | `nexuscrew show token` | Print the authenticated browser link without opening it |
99
100
  | `nexuscrew status` | Show service, port, role and node status |
@@ -139,10 +140,10 @@ The provider catalog is scoped to the selected CLI rather than to a machine-spec
139
140
 
140
141
  | CLI | Built-in provider choices |
141
142
  |---|---|
142
- | Claude Code | Anthropic, OpenRouter, Kimi Code, Amazon Bedrock, Google Vertex AI, Microsoft Foundry, Ollama Cloud, local Ollama, Z.AI, custom Anthropic-compatible endpoint |
143
+ | Claude Code | Anthropic, Alibaba Token Plan Personal, OpenRouter, Kimi Code, Amazon Bedrock, Google Vertex AI, Microsoft Foundry, Ollama Cloud, local Ollama, Z.AI, custom Anthropic-compatible endpoint |
143
144
  | Codex | OpenAI or ChatGPT login, OpenAI API, Ollama Cloud, local Ollama, LM Studio, custom OpenAI Responses endpoint |
144
- | Codex-VL | OpenAI or ChatGPT login, OpenAI API, OpenRouter, Ollama Cloud, local Ollama, LM Studio, custom OpenAI Responses endpoint |
145
- | Pi | Native default, Anthropic, OpenAI API, Codex OAuth, Gemini, GitHub Copilot, OpenRouter, Ollama, DeepSeek, Z.AI, custom provider |
145
+ | Codex-VL | OpenAI or ChatGPT login, OpenAI API, Alibaba Token Plan Personal, OpenRouter, Ollama Cloud, local Ollama, LM Studio, custom OpenAI Responses endpoint |
146
+ | Pi | Native default, Anthropic, OpenAI API, Alibaba Token Plan Personal, Codex OAuth, Gemini, GitHub Copilot, OpenRouter, Ollama, DeepSeek, Z.AI, custom provider |
146
147
 
147
148
  Custom Codex-compatible endpoints use the real Responses wire API; NexusCrew does not silently
148
149
  fall back to Chat Completions. Custom argv-based engines are also supported and are launched
@@ -159,6 +160,14 @@ uses `https://api.kimi.com/coding/`, and runs with an isolated Claude configurat
159
160
  Anthropic account remains untouched. A Kimi Code membership key is not interchangeable with a
160
161
  Moonshot pay-as-you-go API key.
161
162
 
163
+ Alibaba Token Plan Personal is a separate managed profile for Claude Code, Codex-VL and Pi. It
164
+ uses only `ALIBABA_CODE_API_KEY`, defaults to `qwen3.8-max-preview`, and has no OpenAI or
165
+ pay-as-you-go fallback. The npm package also includes the portable `alibaba-token-media` skill
166
+ for dry-run-first Wan image/edit and HappyHorse video workflows. Claude Code, Codex, Codex-VL
167
+ and Pi can invoke its dependency-free Python CLI directly; Pi is not assumed to support MCP
168
+ natively. The media skill requires Python 3. Media generation always requires explicit Credit
169
+ consent and never runs during installation, tests, or startup.
170
+
162
171
  Permission handling is explicit per cell and engine:
163
172
 
164
173
  - Claude engines can use standard permissions or `--dangerously-skip-permissions`.
@@ -226,6 +235,11 @@ single pairing link or QR code:
226
235
  4. If the portable address cannot select the correct key, open **Advanced / edit** and replace
227
236
  it with the SSH alias that already works from that device.
228
237
 
238
+ Advanced settings keep the local display label separate from the local route handle. The route
239
+ defaults to a readable slug plus a stable node-ID suffix, so devices that all report the hostname
240
+ `localhost` still receive distinct handles. If a hub reports a collision, NexusCrew applies its
241
+ deterministic suggestion and lets the device retry with the same invitation.
242
+
229
243
  NexusCrew creates one supervised `ssh` process for the hub connection and proves the forwarded
230
244
  TCP endpoint before reporting success. It does not generate SSH keys, edit `authorized_keys`,
231
245
  or use `autossh` as a hidden second supervisor.
@@ -397,9 +411,7 @@ See [CHANGELOG.md](CHANGELOG.md) for released changes.
397
411
 
398
412
  ## Status
399
413
 
400
- The current npm stable release is **v0.8.23** and the local runtime has been migrated to it. The
401
- GitHub tag and release remain on **v0.8.20** until the prepared `main` release receives explicit
402
- approval.
414
+ The current stable release is **v0.8.25** on npm and GitHub.
403
415
 
404
416
  ## License
405
417