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@1.0.1

Patch Changes

• b594b96: Define and enforce canonical idempotency for generic environment creation.
• 249611e: Default the Tangle router to zai/glm-5.2, a model the router both routes and
  holds a spend-authorizing price for. The previous default, zai/glm-4.7, is
  not in the router catalog, so a managed run that named no model asked for a
  model the router does not carry and received a 503 that a CLI retries until its
  own timeout.

@tangle-network/agent-provider-cli-bridge@0.7.7

Patch Changes

• b594b96: Define and enforce canonical idempotency for generic environment creation.
• Updated dependencies [b594b96]
• Updated dependencies [249611e]
  • @tangle-network/agent-interface@1.0.1

@tangle-network/agent-provider-computesdk@0.3.15

Patch Changes

• b594b96: Define and enforce canonical idempotency for generic environment creation.
• Updated dependencies [b594b96]
• Updated dependencies [249611e]
  • @tangle-network/agent-interface@1.0.1

@tangle-network/agent-provider-daytona@0.3.15

Patch Changes

• b594b96: Define and enforce canonical idempotency for generic environment creation.
• Updated dependencies [b594b96]
• Updated dependencies [249611e]
  • @tangle-network/agent-interface@1.0.1

@tangle-network/agent-provider-e2b@0.3.15

Patch Changes

• b594b96: Define and enforce canonical idempotency for generic environment creation.
• Updated dependencies [b594b96]
• Updated dependencies [249611e]
  • @tangle-network/agent-interface@1.0.1

@tangle-network/agent-provider-tangle@0.12.3

Patch Changes

• b594b96: Define and enforce canonical idempotency for generic environment creation.
• Updated dependencies [b594b96]
• Updated dependencies [249611e]
  • @tangle-network/agent-interface@1.0.1

@tangle-network/agent-provider-testkit@0.8.3

Patch Changes

• b594b96: Define and enforce canonical idempotency for generic environment creation.
• Updated dependencies [b594b96]
• Updated dependencies [249611e]
  • @tangle-network/agent-interface@1.0.1

[tangletools]

✅ Auto-approved GitHub Actions PR — feb5a218

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.

This approval is provisional. It rests on the audit running. If the audit cannot run — for example the CLI bridge rejects it — this approval is dismissed rather than left standing, so an unrun check never reads as a passing one.

_{tangletools · auto-approval · reason: github_actions_author · 2026-08-17T00:58:59Z}

[tangletools]

✅ Auto-approved GitHub Actions PR — c1644736

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.

This approval is provisional. It rests on the audit running. If the audit cannot run — for example the CLI bridge rejects it — this approval is dismissed rather than left standing, so an unrun check never reads as a passing one.

_{tangletools · auto-approval · reason: github_actions_author · 2026-08-17T01:14:01Z}

[tangletools]

🟢 Value Audit — sound

Verdict	sound
Coverage	2 of 2 lenses (value, usefulness)
Concerns	1 (1 weak-concern)
Heuristic	0.0s
Duplication	0.0s
Interrogation	255.8s (2 bridge agents)
Total	255.8s

💰 Value — sound

Standard bot-generated Changesets release PR that ships agent-interface 1.0.1 (idempotent environment creation + servable router default model) and patch-bumps its six dependents; this is the repo's established release mechanism working exactly as designed.

• What it does: Consumes the two changesets landed by PRs #199 (b594b96, canonical idempotency for generic environment creation — new exports createAgentEnvironmentWithIdempotency / agentEnvironmentCreateInputDigest in packages/agent-interface/src/index.ts:18,61) and #200 (249611e, TANGLE_ROUTER_DEFAULT_MODEL changes from unservable zai/glm-4.7 to zai/glm-5.2 in packages/agent-interface/src/provider-config.ts:62)
• Goals it achieves: Gets two real fixes onto npm: (1) managed runs that named no model no longer request a model absent from the router catalog — the old default produced a 503 that CLIs retried until their own timeout, hanging runs with neither output nor error (per commit 249611e message and the code comment in provider-config.ts:55-61); (2) all provider adapters gain enforced idempotent environment creation. Depen
• Assessment: Good on its merits. Verified against the repo: the release math is correct (patch bumps for additive/fix changes), the changelogs exactly reproduce the consumed changeset text, every package listed in the two changesets (.changeset/generic-environment-create-idempotency.md, .changeset/router-default-servable-model.md, deleted by c164473) is bumped, and each dependent's agent-interface range is rew
• Better / existing approach: none — this is the right approach. Searched for alternatives: the repo has no other release mechanism (single .changeset/config.json, no release-please/lerna/custom publish scripts beyond the action), and manual version bumps would fight the established flow. Checked whether the bump set is complete: it matches the changesets exactly.
• Model: opencode/zai-coding-plan/glm-5.2
• Bridge attempts: 2
• Bridge warning: opencode/kimi-for-coding/k2p7: opencode: opencode error

🎯 Usefulness — sound

A clean Changesets release PR that versions two already-merged agent-interface fixes (1.0.0→1.0.1) and patch-bumps all six dependents; it will publish to npm on merge via the repo's established release pipeline.

• Integration: Fully reachable and standard-path. The Version commit c164473 sits directly on top of origin/main (verified: git log origin/main shows b594b96 #199 and 249611e #200 as main's tip). .github/workflows/release.yml runs changesets/action with publish: pnpm changeset:publish on push to main, and git history shows this exact 'Version Packages' PR pattern merged repeatedly (#192, #194, #197, #198). On
• Fit with existing patterns: Exactly in the codebase's grain: changesets config (.changeset/config.json) with caret dependency ranges, generated CHANGELOG.md entries, and OIDC trusted publishing — identical to every prior release in the log. No competing release mechanism exists.
• Real-world viability: Holds up: npm registry confirms @tangle-network/agent-interface latest is 1.0.0 and agent-provider-tangle latest is 0.12.2, so the new versions are free (no publish collision). The shipped content is substantive, not paperwork — 249611e fixes a real 503-retry-loop for model-less managed runs in provider-config.ts, and b594b96 lands idempotency enforcement across the interface plus all five provide
• Model: opencode/zai-coding-plan/glm-5.2
• Bridge attempts: 1

💰 Value Audit

🟡 agent-core's declared minimum stays ^1.0.0 while six siblings move to ^1.0.1 [maintenance] ``

agent-core also depends on agent-interface at runtime (packages/agent-core/package.json:200) but was not listed in either changeset, so c164473 left it at 0.9.4 with range ^1.0.0, while the six providers/testkit got ^1.0.1. Harmless in practice: the caret range still resolves to 1.0.1 at install time, the workspace pins the local copy via the pnpm override '@tangle-network/agent-interface: workspace:*' (pnpm-workspace.yaml), and release #198 only bumped agent-core because its changeset explicitl

---

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 · 20260817T022238Z}

[tangletools]

✅ No Blockers — c1644736

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 14 changed files. Global verifier still owns final merge decision. | Full multi-shot audit completed 5/5 planned shots over 14 changed files. Global verifier still owns final merge decision. | Full multi-shot audit completed 5/5 planned shots over 14 changed files. Global verifier still owns final merge decision.

No findings.

---

_{tangletools · 2026-08-17T02:35:51Z · trace}

[tangletools]

✅ Clean — c1644736

Full multi-shot audit completed 5/5 planned shots over 14 changed files. Global verifier still owns final merge decision. | Full multi-shot audit completed 5/5 planned shots over 14 changed files. Global verifier still owns final merge decision. | Full multi-shot audit completed 5/5 planned shots over 14 changed files. Global verifier still owns final merge decision.

Full immutable report for this review: trace

Summary comment for this run: full summary

---

_{tangletools · 2026-08-17T02:35:51Z · immutable trace}