@extrafemi-ai/lodestone 0.5.0 → 0.5.1
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/CHANGELOG.md +7 -0
- package/README.md +2 -0
- package/package.json +4 -3
package/CHANGELOG.md
CHANGED
|
@@ -2,6 +2,13 @@
|
|
|
2
2
|
|
|
3
3
|
Versions before 1.0 may change between minor releases; each change that could break a caller is marked **breaking**.
|
|
4
4
|
|
|
5
|
+
## 0.5.1
|
|
6
|
+
|
|
7
|
+
No change to the library's behaviour.
|
|
8
|
+
|
|
9
|
+
- **Published with npm trusted publishing.** The release workflow no longer holds an npm token: npm trusts this repository and `release.yml` directly, so there is no secret to leak or to expire.
|
|
10
|
+
- The Lodestone site, at https://lodestone.extrafemi.com, built from the real code (failure sentences from `explain()`, trust verdicts from `vet()`, the code map from `src/`) and checked in CI.
|
|
11
|
+
|
|
5
12
|
## 0.5.0
|
|
6
13
|
|
|
7
14
|
Redundancy across providers, and model lists that keep themselves alive and safe.
|
package/README.md
CHANGED
|
@@ -1,5 +1,7 @@
|
|
|
1
1
|
# Lodestone
|
|
2
2
|
|
|
3
|
+
**[lodestone.extrafemi.com](https://lodestone.extrafemi.com)**: an interactive walkthrough of what it does.
|
|
4
|
+
|
|
3
5
|
Calls AI models so your tool keeps working when a model is withdrawn, slow or rate-limited.
|
|
4
6
|
|
|
5
7
|
Free and cheap models come and go. A hard-coded model id breaks without warning, one slow model can use your whole time limit, and "429" can mean four different things that need four different messages. Lodestone handles those so each tool doesn't have to.
|
package/package.json
CHANGED
|
@@ -1,13 +1,13 @@
|
|
|
1
1
|
{
|
|
2
2
|
"name": "@extrafemi-ai/lodestone",
|
|
3
|
-
"version": "0.5.
|
|
3
|
+
"version": "0.5.1",
|
|
4
4
|
"description": "Calls AI models so your tool keeps working when a model is withdrawn, slow, rate-limited or down: failover across providers, self-updating model lists, spend limits.",
|
|
5
5
|
"license": "MIT",
|
|
6
6
|
"repository": {
|
|
7
7
|
"type": "git",
|
|
8
8
|
"url": "git+https://github.com/obasaolorunfemi-ai/lodestone.git"
|
|
9
9
|
},
|
|
10
|
-
"homepage": "https://
|
|
10
|
+
"homepage": "https://lodestone.extrafemi.com",
|
|
11
11
|
"bugs": {
|
|
12
12
|
"url": "https://github.com/obasaolorunfemi-ai/lodestone/issues"
|
|
13
13
|
},
|
|
@@ -39,7 +39,8 @@
|
|
|
39
39
|
"typecheck": "tsc --noEmit",
|
|
40
40
|
"test": "vitest run",
|
|
41
41
|
"prepublishOnly": "npm run typecheck && npm run typecheck:examples && npm test && npm run build",
|
|
42
|
-
"typecheck:examples": "tsc -p tsconfig.examples.json"
|
|
42
|
+
"typecheck:examples": "tsc -p tsconfig.examples.json",
|
|
43
|
+
"site": "npm run build && node site/build.mjs"
|
|
43
44
|
},
|
|
44
45
|
"devDependencies": {
|
|
45
46
|
"@types/node": "^22.10.0",
|