@tangle-network/agent-knowledge 22.0.4 → 22.0.6
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 +8 -0
- package/README.md +3 -3
- package/docs/compatibility.md +7 -5
- package/package.json +4 -4
package/CHANGELOG.md
CHANGED
|
@@ -1,5 +1,13 @@
|
|
|
1
1
|
# Changelog
|
|
2
2
|
|
|
3
|
+
## 22.0.6
|
|
4
|
+
|
|
5
|
+
The supported Eval minors and the Eval peer range come from `package.json` alone (#270), so an adopted Eval release publishes without a hand edit. 22.0.5 was tagged but never published: its packed-package check still held the old minor list. This release carries everything 22.0.5 would have: Eval 0.216 admitted (`>=0.213.0 <0.217.0`, #268) and the adopt-stack workflow (#267).
|
|
6
|
+
|
|
7
|
+
## 22.0.5
|
|
8
|
+
|
|
9
|
+
Admit Eval 0.216: the Eval peer range widens to `>=0.213.0 <0.217.0`, and the package develops against Eval 0.216.1 and Interface 5.7.0 (#268). agent-knowledge now adopts each new Tangle stack release on its own, through agent-eval's reusable adopt-stack workflow (#267).
|
|
10
|
+
|
|
3
11
|
## 22.0.4
|
|
4
12
|
|
|
5
13
|
A write proposal whose process died mid-write no longer wedges the store. The next reader or writer rolls the abandoned `knowledge-proposal:*` transaction back; before this, every read and write refused with "requires its owner to resume" until the byte-identical proposal was replayed, so a killed run could never resume.
|
package/README.md
CHANGED
|
@@ -9,13 +9,13 @@ Supply application callbacks for those decisions, or use `@tangle-network/agent-
|
|
|
9
9
|
## Install
|
|
10
10
|
|
|
11
11
|
```bash
|
|
12
|
-
pnpm add @tangle-network/agent-knowledge @tangle-network/agent-eval
|
|
12
|
+
pnpm add @tangle-network/agent-knowledge @tangle-network/agent-eval @tangle-network/agent-interface@5
|
|
13
13
|
```
|
|
14
14
|
|
|
15
15
|
Requires Node.js 22.12 or later and Interface 5.
|
|
16
16
|
|
|
17
|
-
Eval
|
|
18
|
-
Package and official optimizer checks exercise each minor
|
|
17
|
+
Install an Eval version that the `@tangle-network/agent-eval` peer range in [package.json](package.json) admits; all are Interface 5 releases.
|
|
18
|
+
Package and official optimizer checks exercise each minor from that range's floor through the development pin ([compatibility](docs/compatibility.md)).
|
|
19
19
|
Knowledge 21 remains the release line for Interface 4 and Eval 0.212.
|
|
20
20
|
Knowledge 20 remains the release line for Interface 3 and Eval 0.209 through 0.211.
|
|
21
21
|
Knowledge 22 uses Core 0.12, Trace Contract 2, and Zod 4.6.5.
|
package/docs/compatibility.md
CHANGED
|
@@ -2,11 +2,13 @@
|
|
|
2
2
|
|
|
3
3
|
Knowledge 22 requires Node.js 22.12 or later and Interface 5.
|
|
4
4
|
|
|
5
|
-
|
|
6
|
-
and
|
|
7
|
-
|
|
8
|
-
|
|
9
|
-
for each
|
|
5
|
+
`package.json` owns the supported Eval versions: the `@tangle-network/agent-eval` peer
|
|
6
|
+
range and its exact development pin. The supported minors run from the range's floor through
|
|
7
|
+
the pin's minor; all depend on Core 0.12, Interface 5 and Trace Contract 2.
|
|
8
|
+
`scripts/lib/peer-range.mjs` derives the list, and packed-package checks run once per minor,
|
|
9
|
+
at x.y.0 and at the pin for the last, each with one physical copy of Eval, Core 0.12,
|
|
10
|
+
Interface 5 and Zod 4.6.5. Official optimizer checks require the matching `agent-eval-rpc`
|
|
11
|
+
Python bridge, `==<version>`, for each.
|
|
10
12
|
|
|
11
13
|
Use Knowledge 21 with Interface 4 and Eval 0.212. Use Knowledge 20 with Interface 3
|
|
12
14
|
and Eval 0.209 through 0.211. Use Knowledge 19 with Interface 2 and Eval 0.201
|
package/package.json
CHANGED
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
{
|
|
2
2
|
"name": "@tangle-network/agent-knowledge",
|
|
3
|
-
"version": "22.0.
|
|
3
|
+
"version": "22.0.6",
|
|
4
4
|
"description": "Build, search, evaluate, and improve source-backed knowledge bases.",
|
|
5
5
|
"homepage": "https://github.com/tangle-network/agent-knowledge#readme",
|
|
6
6
|
"repository": {
|
|
@@ -85,15 +85,15 @@
|
|
|
85
85
|
"zod": "4.6.5"
|
|
86
86
|
},
|
|
87
87
|
"peerDependencies": {
|
|
88
|
-
"@tangle-network/agent-eval": ">=0.213.0 <0.
|
|
88
|
+
"@tangle-network/agent-eval": ">=0.213.0 <0.217.0",
|
|
89
89
|
"@tangle-network/agent-interface": "^5.2.0"
|
|
90
90
|
},
|
|
91
91
|
"devDependencies": {
|
|
92
92
|
"@arethetypeswrong/cli": "^0.18.5",
|
|
93
93
|
"@biomejs/biome": "^2.5.14",
|
|
94
94
|
"@neo4j-labs/agent-memory": "0.5.0",
|
|
95
|
-
"@tangle-network/agent-eval": "0.
|
|
96
|
-
"@tangle-network/agent-interface": "5.
|
|
95
|
+
"@tangle-network/agent-eval": "0.216.1",
|
|
96
|
+
"@tangle-network/agent-interface": "5.7.0",
|
|
97
97
|
"@types/node": "^26.6.2",
|
|
98
98
|
"mem0ai": "3.3.0",
|
|
99
99
|
"oxc-parser": "0.151.0",
|