Version Packages

[github-actions]

This PR was opened by the Changesets release GitHub action. When you're ready to do a release, you can merge this and the packages will be published to npm automatically. If you're not ready to do a release yet, that's fine, whenever you add more changesets to main, this PR will be updated.

Releases

@tangle-network/agent-interface@0.28.0

Minor Changes

• f6dfea0: Collapse the unlaunched candidate, profile-diff, and improvement contracts to one canonical shape without schema version fields or frozen compatibility exports.

@tangle-network/agent-core@0.4.16

Patch Changes

• Updated dependencies [f6dfea0]
  • @tangle-network/agent-interface@0.28.0

@tangle-network/agent-provider-cli-bridge@0.2.18

Patch Changes

• Updated dependencies [f6dfea0]
  • @tangle-network/agent-interface@0.28.0

@tangle-network/agent-provider-computesdk@0.2.18

Patch Changes

• Updated dependencies [f6dfea0]
  • @tangle-network/agent-interface@0.28.0

@tangle-network/agent-provider-daytona@0.2.18

Patch Changes

• Updated dependencies [f6dfea0]
  • @tangle-network/agent-interface@0.28.0

@tangle-network/agent-provider-e2b@0.2.18

Patch Changes

• Updated dependencies [f6dfea0]
  • @tangle-network/agent-interface@0.28.0

@tangle-network/agent-provider-tangle@0.2.18

Patch Changes

• Updated dependencies [f6dfea0]
  • @tangle-network/agent-interface@0.28.0

@tangle-network/agent-provider-testkit@0.2.18

Patch Changes

• Updated dependencies [f6dfea0]
  • @tangle-network/agent-interface@0.28.0

[tangletools]

✅ Auto-approved GitHub Actions PR — 13ed3f12

This PR was opened by trusted GitHub Actions automation.
The full PR reviewer audit still runs separately and will publish findings if it detects issues.

_{tangletools · auto-approval · reason: github_actions_author · 2026-07-15T16:16:14Z}

[tangletools]

🟢 Value Audit — sound

Verdict	sound
Concerns	0 (none)
Heuristic	0.0s
Duplication	0.0s
Interrogation	89.7s (2 bridge agents)
Total	89.7s

💰 Value — sound

Standard Changesets release PR that versions agent-interface to 0.28.0 (minor, for the f6dfea0 candidate-contract collapse) and cascades patch bumps to the 7 dependent packages, with changelogs already written — the canonical release flow for this repo.

• What it does: Bumps @tangle-network/agent-interface 0.27.2→0.28.0 and propagates patch bumps (agent-core 0.4.15→0.4.16, six agent-provider-* packages 0.2.17→0.2.18) with matching CHANGELOG entries, so merging publishes the f6dfea0 contract collapse to npm.
• Goals it achieves: Cut the release carrying the candidate/profile-diff/improvement contract unification (f6dfea0, PR #56) to npm and keep all workspace dependents pinned to the new interface version — the changesets/action bot generated this from the consumed changeset, same as prior release commits 410541d and 6ed3cc2.
• Assessment: Good on its merits. Versions match the changeset semantics (minor for the breaking contract collapse, patch for dependency-only bumps), CHANGELOG.md already contains the 0.28.0 entry, .changeset/ holds only config.json (changeset consumed), and the flow is identical to the repo's established release cadence. Merging is the publish trigger; nothing here fights the grain.
• Better / existing approach: None — this is the repo's established Changesets release mechanism; the alternative (manual version edits) would be strictly worse. Verified against prior 'Version Packages' commits in git log.
• Model: opencode/kimi-for-coding/k2p7
• Bridge attempts: 1

🎯 Usefulness — sound

Clean collapse of unlaunched candidate/profile-diff contracts (drops schemaVersion fields, deletes a 701-line unused compat shim) with correct minor/patch versioning; nothing dead is added and dead surface is removed.

• Integration: The candidate and profile-diff contracts are self-contained inside agent-interface and consumed only by that package's own tests plus the public export surface for external callers; the removed agent-candidate-compat export had zero importers anywhere in the monorepo (grep across packages//src returned matches only inside agent-interface/src). Downstream providers depend via workspace: and don't
• Fit with existing patterns: Fits the codebase grain exactly: the repo already uses zod .strict() schemas, RFC-8785 canonicalization, and compile-time drift guards (satisfies z.ZodType + MutuallyAssignable), all preserved here. Stripping version fields from contracts before they freeze is the right moment, and removing a pre-emptive compat shim for a shape that never shipped is correct hygiene, not a competing pattern.
• Real-world viability: Pure type/schema definition change — no runtime, concurrency, or error-path surface. Adding .strict() means any payload still carrying schemaVersion now fails parsing, but the negative tests (e.g. agent-candidate-schema.test.ts:22-26, agent-candidate-outcome-schema.test.ts:609) prove the rejection is intentional and consistent across all affected schemas. No real-world payloads carry the field bec
• Model: opencode/zai-coding-plan/glm-5.2
• Bridge attempts: 1

No concerns — sound change, no better or existing approach found. ✅

---

What this audit checks

It judges the change on its merits — not whether it was tasked out in an issue. Unticketed, fast-moving work is fine; the question is whether the change is good and whether a better or existing approach should be used instead.

Pass	What it asks
Heuristic	Vague title? Whitespace-only or cruft-bearing diff? (content signals only)
Duplication	Do added function/class names already exist elsewhere in the repo?
Value Audit	What does it do? What goal does it achieve? Is it good? Better architecture or already-exists?
Usefulness Audit	Does it integrate and fit? Will it hold up in real use and actually get used?

Findings are concerns, not blocks — the human reviewer decides what to do with them.

_{value-audit · 20260715T161943Z}

[tangletools]

✅ No Blockers — 13ed3f12

Review health 100/100 · Reviewer score 95/100 · Confidence 95/100 · 0 findings (none)

	glm	kimi-code	aggregate
Readiness	95	95	95
Confidence	95	95	95
Correctness	95	95	95
Security	95	95	95
Testing	95	95	95
Architecture	95	95	95

Reviewer score is advisory once the run is complete and the verdict has no blockers.

Full multi-shot audit completed 8/8 planned shots over 16 changed files. Global verifier still owns final merge decision. | Full multi-shot audit completed 8/8 planned shots over 16 changed files. Global verifier still owns final merge decision.

No findings.

---

_{tangletools · 2026-07-15T16:23:23Z · trace}

[tangletools]

✅ Clean — 13ed3f12

Full multi-shot audit completed 8/8 planned shots over 16 changed files. Global verifier still owns final merge decision. | Full multi-shot audit completed 8/8 planned shots over 16 changed files. Global verifier still owns final merge decision.

Full immutable report for this review: trace

Summary comment for this run: full summary

---

_{tangletools · 2026-07-15T16:23:23Z · immutable trace}