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@0.49.0

Minor Changes

• d93bac3: Add an optional normalized environment observation surface and an optional provider-neutral interactive-terminal contract.
  Each observation carries a required freshness discriminator, so a missing value never reads as a measured zero, and the endpoint type holds no credential field.
  All additions are optional and additive; a provider that declares neither surface still validates.

@tangle-network/agent-core@0.7.1

Patch Changes

• Updated dependencies [d93bac3]
  • @tangle-network/agent-interface@0.49.0

@tangle-network/agent-provider-cli-bridge@0.6.2

Patch Changes

• Updated dependencies [d93bac3]
  • @tangle-network/agent-interface@0.49.0

@tangle-network/agent-provider-computesdk@0.3.6

Patch Changes

• Updated dependencies [d93bac3]
  • @tangle-network/agent-interface@0.49.0

@tangle-network/agent-provider-daytona@0.3.6

Patch Changes

• Updated dependencies [d93bac3]
  • @tangle-network/agent-interface@0.49.0

@tangle-network/agent-provider-e2b@0.3.6

Patch Changes

• Updated dependencies [d93bac3]
  • @tangle-network/agent-interface@0.49.0

@tangle-network/agent-provider-tangle@0.7.2

Patch Changes

• Updated dependencies [d93bac3]
  • @tangle-network/agent-interface@0.49.0

@tangle-network/agent-provider-testkit@0.6.4

Patch Changes

• Updated dependencies [d93bac3]
  • @tangle-network/agent-interface@0.49.0

[tangletools]

✅ Auto-approved GitHub Actions PR — 6d5f33c0

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 · 2026-08-13T01:27:51Z}

[tangletools]

✅ No Blockers — 6d5f33c0

Review health 100/100 · Reviewer score 95/100 · Confidence 85/100 · 0 findings (none)

	opencode GLM 5.2	opencode DeepSeek v4 Pro	opencode DeepSeek v4 Flash	aggregate
Readiness	95	95	95	95
Confidence	85	85	85	85
Correctness	95	95	95	95
Security	95	95	95	95
Testing	95	95	95	95
Architecture	95	95	95	95

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

Full multi-shot audit completed 5/5 planned shots over 16 changed files. Global verifier still owns final merge decision. | Full multi-shot audit completed 5/5 planned shots over 16 changed files. Global verifier still owns final merge decision. | Full multi-shot audit completed 5/5 planned shots over 16 changed files. Global verifier still owns final merge decision.

No findings.

---

_{tangletools · 2026-08-13T01:33:21Z · trace}

[tangletools]

✅ Clean — 6d5f33c0

Full multi-shot audit completed 5/5 planned shots over 16 changed files. Global verifier still owns final merge decision. | Full multi-shot audit completed 5/5 planned shots over 16 changed files. Global verifier still owns final merge decision. | Full multi-shot audit completed 5/5 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 · 2026-08-13T01:33:21Z · immutable trace}

[tangletools]

🟢 Value Audit — sound

Verdict	sound
Concerns	0 (none)
Heuristic	0.0s
Duplication	0.0s
Interrogation	900.1s (2 bridge agents)
Total	900.1s

💰 Value — sound

Mechanically correct changesets release: agent-interface 0.48→0.49 (minor for new optional API surface from d93bac3) and all 7 dependents patched to 0.49.0; ship as-is.

• What it does: Publishes the d93bac3 feature already on main: agent-interface gains two optional, additive surfaces — a freshness-tagged environment observation contract (environment-observation.ts) and a provider-neutral interactive-terminal contract (environment-terminal.ts) — exposed via optional AgentEnvironment.observe/attachTerminal/terminal methods and matching optional capability flags. This PR's literal
• Goals it achieves: Makes the merged observation/terminal contract available to npm consumers and keeps the monorepo's internal dependency graph on a single coherent interface version. Because every new surface is optional, existing providers that declare neither still validate — so the release carries no breaking change and dependents only need a patch.
• Assessment: Correct on its merits. The version calculus is right: a new optional API surface is a minor on agent-interface; dependents that only optionally consume the new types take a patch. Internal consistency is complete — grep of @tangle-network/agent-interface across all package.json files shows exactly 7 dependents, all repinned to 0.49.0, no stragglers; agent-trace-contract is zero-dependency (per i
• Better / existing approach: none — this is the right approach. The repo standardizes on the changesets/action release flow (confirmed by the six prior identical 'Version Packages' commits in git log and the .changeset/ directory), so a hand-rolled version bump or a different publishing mechanism would fight the codebase's grain. The underlying feature (d93bac3) is already merged with a correct changeset; this PR is its manda
• Model: opencode/zai-coding-plan/glm-5.2
• Bridge attempts: 2
• Bridge warning: opencode/kimi-for-coding/k2p7: opencode: opencode error

🎯 Usefulness — error

usefulness agent produced no parseable value-audit JSON.

• Model: opencode/zai-coding-plan/glm-5.2
• Bridge attempts: 1
• Bridge error: no parseable JSON response

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 · 20260813T014507Z}