model-orchestrator 0.1.4 → 0.1.5

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/CHANGELOG.md CHANGED
@@ -4,9 +4,18 @@ All notable changes to this project are documented here. The format follows [Kee
4
4
 
5
5
  ## [Unreleased]
6
6
 
7
+ ## [0.1.5] - 2026-09-05
8
+
9
+ First release published by the workflow, with provenance.
10
+
11
+ ### Added
12
+
13
+ - Published to npm as `model-orchestrator` (0.1.4 was the first publish, by hand). `npx model-orchestrator` is now the install line; the GitHub route stays for pinned or unreleased runs.
14
+ - `.github/workflows/release.yml`: on a `v*` tag, checks the tag against `package.json`, runs the tests, and publishes with provenance through npm trusted publishing (no stored token). Needs the one-time trusted-publisher setup on npmjs.com described in `RELEASING.md`.
15
+
7
16
  ### Changed
8
17
 
9
- - `RELEASING.md`: the first npm publish is manual and must not pass `--provenance` (npm only generates provenance inside a supported CI runner); the workflow route comes after the package exists.
18
+ - `RELEASING.md`: the first npm publish is manual and must not pass `--provenance` (npm only generates provenance inside a supported CI runner); later releases go through the workflow.
10
19
 
11
20
  ## [0.1.4] - 2026-09-05
12
21
 
@@ -88,7 +97,8 @@ First release.
88
97
  - Tests: a case per fix, judges proven to go red, mutation checks; `npm test` prints the current count.
89
98
  - Adversarial audit: two Codex rounds plus a two-engine review (Codex, Antigravity); findings and fixes in `docs/audit-brief.md`. After the review: subagents go to the project root (`--project`), snippet paths computed from `--dir`, lane sections rendered from the selection, a primary agent required, level 3 asks for API keys separately from CLIs, images and CLI installs pinned, an activation summary at the end of every install.
90
99
 
91
- [Unreleased]: https://github.com/aunysillyme/model-orchestrator/compare/v0.1.4...HEAD
100
+ [Unreleased]: https://github.com/aunysillyme/model-orchestrator/compare/v0.1.5...HEAD
101
+ [0.1.5]: https://github.com/aunysillyme/model-orchestrator/compare/v0.1.4...v0.1.5
92
102
  [0.1.4]: https://github.com/aunysillyme/model-orchestrator/compare/v0.1.3...v0.1.4
93
103
  [0.1.3]: https://github.com/aunysillyme/model-orchestrator/compare/v0.1.2...v0.1.3
94
104
  [0.1.2]: https://github.com/aunysillyme/model-orchestrator/compare/v0.1.1...v0.1.2
package/README.md CHANGED
@@ -1,16 +1,16 @@
1
1
  # model-orchestrator
2
2
 
3
- [![test](https://github.com/aunysillyme/model-orchestrator/actions/workflows/test.yml/badge.svg)](https://github.com/aunysillyme/model-orchestrator/actions/workflows/test.yml) [![license: MIT](https://img.shields.io/badge/license-MIT-blue.svg)](LICENSE) [![node >=18](https://img.shields.io/badge/node-%3E%3D18-brightgreen.svg)](package.json)
3
+ [![npm](https://img.shields.io/npm/v/model-orchestrator.svg)](https://www.npmjs.com/package/model-orchestrator) [![test](https://github.com/aunysillyme/model-orchestrator/actions/workflows/test.yml/badge.svg)](https://github.com/aunysillyme/model-orchestrator/actions/workflows/test.yml) [![license: MIT](https://img.shields.io/badge/license-MIT-blue.svg)](LICENSE) [![node >=18](https://img.shields.io/badge/node-%3E%3D18-brightgreen.svg)](package.json)
4
4
 
5
5
  **A model orchestrator you can `npm run`.** Route every task to the cheapest AI that does it well, whether you have one chat app, five agent CLIs, or a virtual machine running them unattended. One installer asks what you have access to and writes only what fits.
6
6
 
7
7
  Built from a working system, not a diagram: the routing rules, the protocols and the lane runner here run in production, generalized so they transfer to any stack.
8
8
 
9
9
  ```bash
10
- npx github:aunysillyme/model-orchestrator#v0.1.4
10
+ npx model-orchestrator
11
11
  ```
12
12
 
13
- That runs the reviewed release straight from GitHub (drop `#v0.1.4` for the current main). `npx model-orchestrator` will work once the package is on the npm registry; until then it is not a command you can run.
13
+ That runs the latest published release from the npm registry. To run a specific release or the current main straight from GitHub: `npx github:aunysillyme/model-orchestrator#v0.1.5` (drop `#v0.1.5` for main).
14
14
 
15
15
  The installer asks a few things, then writes a folder:
16
16
 
@@ -43,7 +43,7 @@ Read the thinking behind each level in [docs/](docs/README.md): [Part 1](docs/pa
43
43
  | `ollama` | local models: the privacy lane | 2+ |
44
44
  | `claude-app`, `chatgpt-app`, `gemini-app` | chat apps with no CLI: level 1 via a paste block | 1 |
45
45
 
46
- `npx github:aunysillyme/model-orchestrator#v0.1.4 --list` prints the catalog with install and sign-in notes. Details: [docs/catalog.md](docs/catalog.md).
46
+ `npx model-orchestrator --list` prints the catalog with install and sign-in notes. Details: [docs/catalog.md](docs/catalog.md).
47
47
 
48
48
  ## Companion tools (both optional)
49
49
 
@@ -59,10 +59,10 @@ Whether or not you select them, every level carries the two rules they serve: `p
59
59
  ## Non-interactive
60
60
 
61
61
  ```bash
62
- npx github:aunysillyme/model-orchestrator#v0.1.4 --yes --level 2 --ais claude-code,codex,grok --primary claude-code --dir ./ai-orchestrator
63
- npx github:aunysillyme/model-orchestrator#v0.1.4 --yes --level 3 --ais claude-code,codex,agy,grok,hermes,qwen,ollama --apis anthropic,openrouter --dry # print the plan, write nothing
64
- npx github:aunysillyme/model-orchestrator#v0.1.4 --yes --level 2 --ais claude-code,codex --project ~/my-app --dir ~/my-app/ai-orchestrator # subagents into ~/my-app/.claude/agents
65
- npx github:aunysillyme/model-orchestrator#v0.1.4 --yes --level 2 --ais claude-code,codex,grok --primary claude-code --update-docs # added a lane: regenerate the docs you never edited
62
+ npx model-orchestrator --yes --level 2 --ais claude-code,codex,grok --primary claude-code --dir ./ai-orchestrator
63
+ npx model-orchestrator --yes --level 3 --ais claude-code,codex,agy,grok,hermes,qwen,ollama --apis anthropic,openrouter --dry # print the plan, write nothing
64
+ npx model-orchestrator --yes --level 2 --ais claude-code,codex --project ~/my-app --dir ~/my-app/ai-orchestrator # subagents into ~/my-app/.claude/agents
65
+ npx model-orchestrator --yes --level 2 --ais claude-code,codex,grok --primary claude-code --update-docs # added a lane: regenerate the docs you never edited
66
66
  ```
67
67
 
68
68
  ## What gets written (level 3, everything)
package/package.json CHANGED
@@ -1,6 +1,6 @@
1
1
  {
2
2
  "name": "model-orchestrator",
3
- "version": "0.1.4",
3
+ "version": "0.1.5",
4
4
  "description": "A model orchestrator you can npm run: route every task to the cheapest AI that does it well, across one agent, many CLIs, or a whole virtual machine. Three levels, one installer that asks what you have access to.",
5
5
  "type": "module",
6
6
  "bin": {