Python: Add agent-framework-tenki (Tenki-backed CodeAct provider)

[Patricio-Filice-Luxor]

Motivation & Context

Adds a third CodeAct backend, agent-framework-tenki, wrapping Tenki Sandbox (managed Linux micro-VMs) behind the same *CodeActProvider / *ExecuteCodeTool shape as agent-framework-hyperlight and agent-framework-monty. Unlike the existing in-process backends it provides a remote, isolated, real Linux environment: pip/apt installs, subprocesses, and a persistent filesystem across calls.

Full rationale, backend comparison, and scope discussion: #7311

Description & Review Guide

• Major changes: new alpha package python/packages/tenki/ (1.0.0a260722, PEP 561 typed) with TenkiCodeActProvider (run-scoped: fresh execute_code tool + sandbox per agent run, terminated in after_run so state never leaks across runs) and TenkiExecuteCodeTool (standalone: one sandbox reused until close()); a runnable sample; 66 unit + 4 opt-in integration tests; CI wiring.
• Impact: additive only — not part of agent-framework[all] and no agent_framework.tenki lazy-loading shim (both deferred to beta promotion, per the alpha package policy). No existing package modified beyond PACKAGE_STATUS.md, workspace registration, and the CI workflow env.
• Review focus: the sandbox lifecycle reconciliation and the run-scoped provider state contract (session state stores only the sandbox name — a plain JSON-serializable string; live tool handles stay on the provider so close() can reap runs that never reached after_run).

Sandbox lifecycle (highlights):

• Lazy provision on the first execute_code call, reused per tool instance. Before each call the tool refreshes remote state: PAUSED / USER_SHUTDOWN → auto-resume, retried within a 120s poll budget (USER_SHUTDOWN links its pause snapshot asynchronously — verified live end-to-end); TERMINATED / TERMINATING → re-provision; refresh() failure → structured error, handle kept for retry.
• Reconcile + sandbox.exec run under a single lock hold: close() serializes with in-flight execs, a failed terminate preserves the handle for retry, and the provider's close() attempts every leaked run tool and raises RuntimeError naming the survivors so a second close() retries exactly those.
• Cost backstops: max_duration_seconds (default 900s) stops compute billing server-side even if the client process crashes; provider run-scoped sandboxes cap pause-snapshot retention at 1h (standalone keeps Tenki's 7-day default).

Implementation notes: sync SDK (tenki-sandbox>=0.4.0,<0.5) bridged via asyncio.to_thread + threading.Lock; typed CommandResult parsing (signal-killed processes correctly reported as failures); injected CodeAct instructions cover small-model footguns (print(...) requirement, subprocess for pip, no Jupyter magic); explicit constructor args — including empty string — always win over env fallbacks (TENKI_API_KEY, TENKI_PROJECT_ID, TENKI_WORKSPACE_ID); Tenki-specific options (snapshot_id, volumes, network policy, …) pass through extra_create_kwargs.

Tests: 66 hermetic unit tests through the public tool.invoke API (full reconcile matrix, kwargs forwarding, close semantics, provider run-scoping, CancelledError propagation); 4 opt-in integration tests against the live service, guarded on TENKI_API_KEY. Note for maintainers: the integration job needs secrets.TENKI_API_KEY and vars.TENKI_PROJECT_ID configured.

Out of scope for the alpha: host tool callbacks (the Tenki SDK has no bridge), dedicated constructor parameters for mounts/network/snapshots (reachable today via extra_create_kwargs), and a session-scoped sandbox mode.

Related Issue

Resolves #7311

Contribution Checklist

• The code builds clean without any errors or warnings
• All unit tests pass, and I have added new tests where possible
• The PR follows the Contribution Guidelines
• This PR is linked to an issue and there is no other open PR for this issue (see Related Issue above).
• This is not a breaking change. If it is a breaking change, add the breaking change label (or add "[BREAKING]" to the title prefix, before or after any language prefix) — a workflow keeps the label and title prefix in sync automatically.

[Copilot]

Pull request overview

Adds a new Python alpha package, agent-framework-tenki, that implements a Tenki Sandbox–backed CodeAct backend. This extends the Agent Framework’s CodeAct provider/tool ecosystem with a remote, isolated Linux micro-VM execution environment (persistent filesystem across calls, subprocesses, package installs), alongside existing in-process backends.

Changes:

• Introduces agent-framework-tenki package with TenkiCodeActProvider (run-scoped) and TenkiExecuteCodeTool (standalone, reusable sandbox).
• Adds a runnable Tenki CodeAct sample and updates the CodeAct samples README to include the third backend.
• Wires Tenki into the Python workspace/lockfile and includes its integration tests in CI workflows.

Reviewed changes

Copilot reviewed 13 out of 15 changed files in this pull request and generated 2 comments.

Show a summary per file

File	Description
python/uv.lock	Registers agent-framework-tenki workspace member and locks tenki-sandbox dependency.
python/pyproject.toml	Adds agent-framework-tenki to the Python workspace packages.
python/PACKAGE_STATUS.md	Marks the new package as alpha.
python/samples/02-agents/context_providers/code_act/tenki_code_act.py	New sample demonstrating Tenki-backed provider usage.
python/samples/02-agents/context_providers/code_act/README.md	Updates sample matrix + install/run instructions to include Tenki.
python/packages/tenki/README.md	Package documentation covering configuration, lifecycle, and Tenki-specific passthrough options.
python/packages/tenki/pyproject.toml	New package metadata, dependencies, typing, lint/test configuration.
python/packages/tenki/LICENSE	Adds MIT license file for the new package.
python/packages/tenki/agent_framework_tenki/py.typed	Marks the package as typed (PEP 561).
python/packages/tenki/agent_framework_tenki/init.py	Public exports for provider/tool + version wiring.
python/packages/tenki/agent_framework_tenki/_provider.py	Implements run-scoped provider lifecycle (before_run/after_run/close).
python/packages/tenki/agent_framework_tenki/_execute_code_tool.py	Implements sandbox lifecycle reconciliation + execute_code tool behavior.
python/packages/tenki/tests/tenki/test_tenki_codeact.py	Unit + opt-in integration tests for tool/provider lifecycle and result parsing.
.github/workflows/python-merge-tests.yml	Adds Tenki package tests to the misc integration test job; exports Tenki env vars.
.github/workflows/python-integration-tests.yml	Same as above for scheduled/manual integration workflow.

Comments suppressed due to low confidence (3)

python/packages/tenki/tests/tenki/test_tenki_codeact.py:1373

• These integration tests pass project_id=os.environ.get("TENKI_PROJECT_ID") directly. In GitHub Actions, an unset vars.TENKI_PROJECT_ID expands to an empty string, which then gets forwarded as project_id="" and can cause Tenki provisioning to fail even though project_id is optional (single-project API keys). Consider only passing project_id when it’s a non-empty string.

    project_id = os.environ.get("TENKI_PROJECT_ID")
    async with TenkiExecuteCodeTool(
        sandbox_name=f"agent-framework-ci-fs-{os.getpid()}",
        project_id=project_id,
        max_duration_seconds=300,

python/packages/tenki/tests/tenki/test_tenki_codeact.py:1392

• These integration tests pass project_id=os.environ.get("TENKI_PROJECT_ID") directly. In GitHub Actions, an unset vars.TENKI_PROJECT_ID expands to an empty string, which then gets forwarded as project_id="" and can cause Tenki provisioning to fail even though project_id is optional (single-project API keys). Consider only passing project_id when it’s a non-empty string.

    project_id = os.environ.get("TENKI_PROJECT_ID")
    async with TenkiExecuteCodeTool(
        sandbox_name=f"agent-framework-ci-fail-{os.getpid()}",
        project_id=project_id,
        max_duration_seconds=300,

python/packages/tenki/tests/tenki/test_tenki_codeact.py:1422

• This integration test passes project_id=os.environ.get("TENKI_PROJECT_ID") directly. In GitHub Actions, an unset vars.TENKI_PROJECT_ID expands to an empty string, which then gets forwarded as project_id="" and can cause Tenki provisioning to fail even though project_id is optional (single-project API keys). Consider only passing project_id when it’s a non-empty string.

    project_id = os.environ.get("TENKI_PROJECT_ID")
    unique_name = f"agent-framework-ci-teardown-{os.getpid()}"

    async with TenkiExecuteCodeTool(
        sandbox_name=unique_name,
        project_id=project_id,
        max_duration_seconds=300,
    ) as tool:

[Patricio-Filice-Luxor]

@microsoft-github-policy-service agree company="Luxor Technology"