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@0.50.0

Minor Changes

• bdb076b: Add the environment-scoped capability document.

  AgentEnvironment.capabilities is an optional document that describes one environment.
  A capability the connected deployment decides cannot be stated by AgentEnvironmentProvider.capabilities(), because one provider reaches deployments of different ages; a provider that measures such a capability per environment publishes the measured answer here, and the operations that environment exposes match it.

  runAgentEnvironmentProviderConformance and runSessionReplayConformance now bind every environment-scoped check to that document when the environment publishes one, and to the provider document otherwise.
  The provider report gains environmentCapabilities, which is the document the checks ran against.

@tangle-network/agent-provider-tangle@0.8.0

Minor Changes

• bdb076b: Derive retained control from deployment capability discovery, and publish the result on the environment.

  Composing an environment now calls box.capabilities() once and takes every deployment-decided claim from that document instead of from the linked Sandbox SDK's method surface.
  The narrowed document is published as environment.capabilities, which is the document to read before offering an operation: the operations an environment exposes match it exactly, while provider.capabilities() states the adapter's ceiling before any sandbox exists.

  Every flag the capability document carries now gates the claims it backs.
  streaming.detach and streaming.turnIdempotency need dispatch.runControlRef with dispatch.executionIdOnAdmission; streaming.replay needs runs.eventReplay; sessions.continue, retainedControl, and session.cancelRun need those plus cancel.canonicalRunCancellation, cancel.digestBound, cancel.idempotent, and runs.executionScopedStatus.
  Detached dispatch also needs a session handle, because a detached run is reachable only through one.

  Four inputs claim nothing: an SDK older than 0.22.0, a sandbox that is not running, a null document, and a capability read that fails.
  Such environments omit dispatch and session.
  A document that leaves a flag unset drops the claims that flag gates and keeps the rest, so it can still carry streaming.detach and streaming.replay.
  A failed read no longer fails create() and no longer deletes the sandbox a cold provision has already paid for; it claims nothing and reports the failure on the warning channel.

Patch Changes

• Updated dependencies [bdb076b]
  • @tangle-network/agent-interface@0.50.0

@tangle-network/agent-provider-testkit@0.7.0

Minor Changes

• bdb076b: Add the environment-scoped capability document.

  AgentEnvironment.capabilities is an optional document that describes one environment.
  A capability the connected deployment decides cannot be stated by AgentEnvironmentProvider.capabilities(), because one provider reaches deployments of different ages; a provider that measures such a capability per environment publishes the measured answer here, and the operations that environment exposes match it.

  runAgentEnvironmentProviderConformance and runSessionReplayConformance now bind every environment-scoped check to that document when the environment publishes one, and to the provider document otherwise.
  The provider report gains environmentCapabilities, which is the document the checks ran against.

Patch Changes

• Updated dependencies [bdb076b]
  • @tangle-network/agent-interface@0.50.0

@tangle-network/agent-core@0.7.2

Patch Changes

• Updated dependencies [bdb076b]
  • @tangle-network/agent-interface@0.50.0

@tangle-network/agent-provider-cli-bridge@0.6.3

Patch Changes

• Updated dependencies [bdb076b]
  • @tangle-network/agent-interface@0.50.0

@tangle-network/agent-provider-computesdk@0.3.7

Patch Changes

• Updated dependencies [bdb076b]
  • @tangle-network/agent-interface@0.50.0

@tangle-network/agent-provider-daytona@0.3.7

Patch Changes

• Updated dependencies [bdb076b]
  • @tangle-network/agent-interface@0.50.0

@tangle-network/agent-provider-e2b@0.3.7

Patch Changes

• Updated dependencies [bdb076b]
  • @tangle-network/agent-interface@0.50.0

[tangletools]

✅ Auto-approved GitHub Actions PR — f15ad617

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 · 2026-08-13T21:22:55Z}

[tangletools]

🟢 Value Audit — sound

Verdict	sound
Coverage	2 of 2 lenses (value, usefulness)
Concerns	0 (none)
Heuristic	0.0s
Duplication	0.0s
Interrogation	51.3s (2 bridge agents)
Total	51.3s

💰 Value — sound

Automated changeset-version release bumping 8 packages off feature commit bdb076b; correct and idiomatic for this repo's release workflow.

• What it does: Runs changeset version to publish accumulated changesets: bumps agent-interface to 0.50.0, agent-provider-tangle to 0.8.0, and agent-provider-testkit to 0.7.0 (minor, carrying the bdb076b feature); bumps agent-core, cli-bridge, computesdk, daytona, and e2b one patch each as internal consumers of agent-interface (per updateInternalDependencies: patch); writes CHANGELOG entries and removes the two
• Goals it achieves: Cut a release so the environment-scoped capability document work from PR #165 (bdb076b) reaches npm consumers with correct semver signals and cross-package dependency coherence.
• Assessment: Mechanical, correct release artifact. Version deltas match the changesets: the three packages that gained the feature take minors; the five packages that merely re-export agent-interface take patches under the configured patch mode. CHANGELOG bodies accurately summarize bdb076b. This is identical in shape to every prior Version Packages PR in the log (#164, #159, #155, #153, #147, #143).
• Better / existing approach: none — this is the right approach. Changesets is the repo's established release tool (config at .changeset/config.json) and this PR is its standard output; there is no alternative path to evaluate.
• Model: opencode/zai-coding-plan/glm-5.2
• Bridge attempts: 2
• Bridge warning: opencode/kimi-for-coding/k2p7: opencode: opencode error

🎯 Usefulness — sound

Standard Changesets release PR that publishes the environment-capabilities work from #165 to npm; pure version bumps and changelog regen, no new surface to integrate.

• Integration: Not applicable to a release PR — it packages already-merged, already-reviewed feature work (#165) and is consumed by the changesets GitHub Action on merge to publish to npm. The version bumps are internally consistent (agent-interface 0.50.0 is depended on by core, all four sandbox providers, cli-bridge, and testkit, all updated in lockstep).
• Fit with existing patterns: Follows the repo's established release pattern exactly (git log shows recurring 'Version Packages' merges). No competing release mechanism.
• Real-world viability: Version-bump and changelog-only change; no runtime behavior introduced here. The feature being shipped was validated in its own PR.
• 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 · 20260813T225233Z}

[tangletools]

✅ No Blockers — f15ad617

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 · 2026-08-13T22:54:54Z · trace}

[tangletools]

✅ Clean — f15ad617

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 · 2026-08-13T22:54:54Z · immutable trace}