Skip to content

chore(release): align Knowledge with Eval 0.144.11 #120

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
drewstone merged 1 commit into from
Aug 11, 2026
Merged

chore(release): align Knowledge with Eval 0.144.11 #120

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
6 changes: 6 additions & 0 deletions CHANGELOG.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -2,6 +2,12 @@

## Unreleased

## 7.2.1

### Changed

- Updated the required Eval peer and exact development pin to `0.144.11` so consumers install one current shared cohort.

## 7.2.0

### Changed
Expand Down
2 changes: 1 addition & 1 deletion README.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -9,7 +9,7 @@ Supply application callbacks for those decisions, or use `@tangle-network/agent-
## Install

```bash
pnpm add @tangle-network/agent-knowledge@7.2.0 @tangle-network/agent-eval@0.144.10 @tangle-network/agent-interface@0.46.1
pnpm add @tangle-network/agent-knowledge@7.2.1 @tangle-network/agent-eval@0.144.11 @tangle-network/agent-interface@0.46.1
```

Requires Node.js 20.19 or later.
Expand Down
6 changes: 3 additions & 3 deletions package.json
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,6 +1,6 @@
{
"name": "@tangle-network/agent-knowledge",
"version": "7.2.0",
"version": "7.2.1",
"description": "Build, search, evaluate, and improve source-backed knowledge bases.",
"homepage": "https://github.com/tangle-network/agent-knowledge#readme",
"repository": {
Expand Down Expand Up @@ -79,14 +79,14 @@
"zod": "^4.4.3"
},
"peerDependencies": {
"@tangle-network/agent-eval": ">=0.144.10 <0.145.0",
"@tangle-network/agent-eval": ">=0.144.11 <0.145.0",
"@tangle-network/agent-interface": ">=0.46.1 <0.47.0"
},
"devDependencies": {
"@arethetypeswrong/cli": "^0.18.5",
"@biomejs/biome": "^2.5.5",
"@neo4j-labs/agent-memory": "0.4.1",
"@tangle-network/agent-eval": "0.144.10",
"@tangle-network/agent-eval": "0.144.11",
"@tangle-network/agent-interface": "0.46.1",
"@types/node": "^26.1.1",
"@types/proper-lockfile": "4.1.4",
Expand Down
10 changes: 5 additions & 5 deletions pnpm-lock.yaml
View file
Open in desktop

Some generated files are not rendered by default. Learn more about how customized files appear on GitHub.

38 changes: 38 additions & 0 deletions tests/official-optimizer-resume.contract.test.ts
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -173,6 +173,7 @@ function fakeOfficialOptimizerRunner(optimizer: 'gepa' | 'skillopt') {
'totalEvaluations: 0,',
'recipeKind: input.recipe.kind,',
'proposerCostAccounting: "unavailable",',
'candidatePopulation,',
]
: [
'bestCandidate: input.seedCandidate,',
Expand All @@ -183,6 +184,8 @@ function fakeOfficialOptimizerRunner(optimizer: 'gepa' | 'skillopt') {
]
const source = [
"const fs = require('node:fs')",
"const crypto = require('node:crypto')",
"const path = require('node:path')",
"const inputPath = process.argv[process.argv.indexOf('--input') + 1]",
"const outputPath = process.argv[process.argv.indexOf('--output') + 1]",
'const input = JSON.parse(fs.readFileSync(inputPath, "utf8"))',
Expand All @@ -191,6 +194,41 @@ function fakeOfficialOptimizerRunner(optimizer: 'gepa' | 'skillopt') {
' fs.writeFileSync(outputPath, JSON.stringify({ runtime }))',
' process.exit(0)',
'}',
...(optimizer === 'gepa'
? [
'const populationPath = path.join(input.outputDir, "candidate-population.json")',
'const scenarioIds = (input.selectionSet.length ? input.selectionSet : input.trainSet).map(({ id }) => id)',
'const populationContents = JSON.stringify({',
' schemaVersion: 1,',
' scope: "gepa-candidate-population",',
' runId: input.runId,',
' bestIndex: 0,',
' candidates: [{',
' index: 0,',
' candidate: input.seedCandidate,',
' parentIndices: [null],',
' aggregateScore: null,',
' selectionScores: [],',
' discoveryEvaluationCount: 0,',
' }],',
'})',
'fs.mkdirSync(input.outputDir, { recursive: true })',
'fs.writeFileSync(populationPath, populationContents)',
'const candidatePopulation = {',
' scope: "gepa-candidate-population",',
' path: populationPath,',
' sha256: "sha256:" + crypto.createHash("sha256").update(populationContents).digest("hex"),',
' bytes: Buffer.byteLength(populationContents),',
' runId: input.runId,',
' candidates: 1,',
' bestIndex: 0,',
' maxCandidates: input.maxPopulationCandidates,',
' maxCandidateChars: input.maxCandidateChars,',
' scenarioIds,',
' surfaceKind: typeof input.seedCandidate === "string" ? "text" : "components",',
'}',
]
: []),
'fs.writeFileSync(outputPath, JSON.stringify({',
...optimizeResult,
'upstream: runtime.optimizer,',
Expand Down