feat(optimization): adopt official GEPA and SkillOpt engines#616
Merged
Conversation
…er-runtime # Conflicts: # bench/package.json # docs/api/primitive-catalog.md # docs/canonical-api.md # package.json # pnpm-lock.yaml
…er-runtime # Conflicts: # CHANGELOG.md # bench/src/benchmarks/humaneval.test.mts # docs/api/primitive-catalog.md # docs/canonical-api.md # pnpm-lock.yaml
…er-runtime # Conflicts: # docs/architecture.md # docs/canonical-api.md
…er-runtime # Conflicts: # bench/package.json
tangletools
approved these changes
Jul 24, 2026
tangletools
left a comment
Contributor
There was a problem hiding this comment.
✅ Auto-approved drewstone PR — 970c1dd8
This PR was opened by the trusted drewstone account.
The full PR reviewer audit still runs separately and will publish findings if it detects issues.
tangletools · auto-approval · reason: drewstone_author · 2026-07-24T22:44:45Z
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Summary
@tangle-network/agent-eval@0.126.6.OptimizationMethodcontract across prompt, skill, code, retrieval, knowledge, and memory candidate surfaces while keeping final-test scenarios outside optimizer input.Releases
@tangle-network/agent-runtime@0.105.0@tangle-network/agent-bench@0.4.0@tangle-network/agent-eval@0.126.6and@tangle-network/agent-knowledge@5.0.1.Verification
pnpm test: 1,770 passed, 6 environment-only skipped.pnpm typecheck;pnpm lint;pnpm verify:package;pnpm docs:freshness: passed.pnpm verify:bench: 61/61 TypeScript files plus Pier bridge and packed TypeScript 5.9.3/6.0.3 consumers passed.$0.000037.61735e3922efc2b90c6d6cab561e62e98452ca90: 3 evaluations.f919db0a622e2e9f9204779b81fe00cc1b2d808f: 9 evaluations and 2 model requests.