feat(869-c4): activation version-coupling assertion (Part of #869)

Part of #869

Mos (id-11) Gate-16 merge: independent APPROVE @90eb48fa (fail-closed identity locks byte-unchanged verified), author id2 != approver id11, clean mosaic-coder author, CI green wp1992. #869 Point-1 CODE COMPLETE (C1/C3/C5/C2/C4).

Co-authored-by: jason.woltje <jason@diversecanvas.com>
Co-committed-by: jason.woltje <jason@diversecanvas.com>

packages/mosaic/framework/tools/lease-broker/activation_version_gate.py

@@ -0,0 +1,180 @@
+#!/usr/bin/env python3
+"""Enforcement-side version-coupling gate (issue #869, Point-1 card C4).
+
+Root cause this exists to guard against (#828 version skew, restated from
+the C1 activation probe in ``lease-activation-probe.ts``): the lease
+broker's ENFORCEMENT half (this toolkit — ``launch-runtime.py``,
+``mutator-gate.py``, ``revoke-lease.py``) and its ACTIVATION half
+(``execLeaseGatedRuntime()`` in ``launch.ts``, which chains the gated
+runtime through ``launch-runtime.py`` and injects ``MOSAIC_LEASE_*``) ship
+on different channels — an npm package and a framework/CLI reseed. C1 gave
+the activation half a versioned, machine-checkable identity
+(``LEASE_ACTIVATION_CAPABILITY``, printed by the CLI's hidden
+``mosaic __lease-capability`` subcommand). That identity is inert on its
+own: nothing yet asserted that ENFORCEMENT actually requires the version
+ACTIVATION advertises. This module is that assertion, owned by the
+enforcement side.
+
+``EXPECTED_ACTIVATION_CAPABILITY`` below is this toolkit's own contract
+declaration — bump it only when this toolkit's launch/gate seam starts
+requiring a different activation contract (new env vars it depends on,
+changed chaining behavior, etc.), independent of any package semver, for
+the same reason C1's constant is: #828 happened precisely because a
+version number that should have moved did not.
+
+This module never talks to a real broker or a real installed CLI in its
+own tests — both the probe's command resolution and its ``run`` transport
+are injectable so tests can drive every branch with fakes/stubs (see
+``version_coupling_unittest.py``).
+"""
+
+from __future__ import annotations
+
+import json
+import os
+import shlex
+import shutil
+import subprocess
+from collections.abc import Callable, Mapping
+from typing import Final, TypedDict
+
+
+class ActivationCapability(TypedDict):
+    name: str
+    version: int
+
+
+# ENFORCEMENT-side expected activation contract. OWNED by this toolkit (the
+# enforcement half). Mirrors — but is deliberately a SEPARATE constant from
+# — `LEASE_ACTIVATION_CAPABILITY` in
+# `packages/mosaic/src/commands/lease-activation-probe.ts` (the activation
+# half's own declaration of what it implements). The two are compared at
+# runtime by `assert_activation_capability_matches()`; drift between them is
+# exactly the version-skew failure mode #828/#869 exist to catch, and must
+# FAIL LOUD, never a silent pass and never a dead (always-true) gate.
+EXPECTED_ACTIVATION_CAPABILITY: Final[ActivationCapability] = {
+    "name": "lease-runtime-activation",
+    "version": 1,
+}
+
+# Matches `LEASE_CAPABILITY_PROBE_COMMAND` in lease-activation-probe.ts —
+# the hidden CLI subcommand that prints the activation half's advertised
+# capability as compact JSON.
+LEASE_CAPABILITY_PROBE_COMMAND: Final = "__lease-capability"
+
+PROBE_TIMEOUT_SECONDS: Final = 2.0
+
+# Override hook: a full shell-style command line (parsed with `shlex.split`)
+# to run INSTEAD of resolving `mosaic` on PATH and appending the probe
+# subcommand. Real deployments should never need this — `mosaic` is on PATH
+# whenever a runtime was launched via `mosaic <cmd>` in the first place, the
+# only real caller of this seam. It exists for integration tests that spawn
+# `launch-runtime.py` directly (never through the real CLI) to supply a
+# fake/stub CLI probe, matching the existing convention of those tests
+# supplying a fake broker and a fake runtime binary rather than depending on
+# host state.
+MOSAIC_COMMAND_OVERRIDE_VAR: Final = "MOSAIC_LEASE_VERSION_PROBE_COMMAND"
+
+
+class VersionCouplingError(Exception):
+    """Raised when the activation capability is absent, unreadable, or does
+    not match what enforcement expects. Callers MUST fail loud on this
+    (non-zero exit, clear actionable stderr) — never swallow it into a
+    silent pass, and never let its absence be treated as compatible."""
+
+
+def _resolve_probe_command(environ: Mapping[str, str]) -> list[str] | None:
+    override = environ.get(MOSAIC_COMMAND_OVERRIDE_VAR)
+    if override:
+        parsed = shlex.split(override)
+        return parsed or None
+    resolved = shutil.which("mosaic")
+    if resolved is None:
+        return None
+    return [resolved, LEASE_CAPABILITY_PROBE_COMMAND]
+
+
+def default_probe_activation_capability(
+    environ: Mapping[str, str] | None = None,
+    *,
+    run: Callable[..., subprocess.CompletedProcess[str]] = subprocess.run,
+) -> ActivationCapability | None:
+    """Real capability lookup: resolves and executes the CLI's hidden
+    ``__lease-capability`` probe subcommand out-of-process (the same
+    mechanism `defaultCapabilityProbe()` in lease-activation-probe.ts uses
+    from the activation side) and parses its JSON stdout. Any failure to
+    resolve a command, spawn it, have it exit zero, or produce a well-shaped
+    ``{name, version}`` JSON object is treated as NO capability (``None``)
+    — fail-closed, never a fabricated/guessed capability.
+    """
+    source_environment = os.environ if environ is None else environ
+    command = _resolve_probe_command(source_environment)
+    if command is None:
+        return None
+    try:
+        completed = run(
+            command,
+            capture_output=True,
+            text=True,
+            timeout=PROBE_TIMEOUT_SECONDS,
+            check=False,
+        )
+    except (OSError, subprocess.TimeoutExpired, ValueError):
+        return None
+    if completed.returncode != 0:
+        return None
+    try:
+        parsed = json.loads(completed.stdout)
+    except json.JSONDecodeError:
+        return None
+    if (
+        not isinstance(parsed, dict)
+        or not isinstance(parsed.get("name"), str)
+        or not isinstance(parsed.get("version"), int)
+        or isinstance(parsed.get("version"), bool)
+    ):
+        return None
+    return {"name": parsed["name"], "version": parsed["version"]}
+
+
+def format_mismatch_message(
+    activation: ActivationCapability | None,
+    expected: ActivationCapability,
+) -> str:
+    """Actionable, non-silent remediation message for either failure shape:
+    absent/unreadable capability, or a present-but-incompatible one."""
+    if activation is None:
+        return (
+            "Mosaic lease activation capability unreadable: enforcement "
+            f"expects '{expected['name']}' v{expected['version']} but the "
+            f"CLI's `mosaic {LEASE_CAPABILITY_PROBE_COMMAND}` probe produced "
+            "no usable result (mosaic not on PATH, non-zero exit, or "
+            "malformed output) — framework/CLI version skew; upgrade both "
+            "as one unit; see #869."
+        )
+    if activation["name"] != expected["name"]:
+        return (
+            f"activation capability name '{activation['name']}' != "
+            f"enforcement expects '{expected['name']}' — framework/CLI "
+            "version skew; upgrade both as one unit; see #869"
+        )
+    return (
+        f"activation capability v{activation['version']} != enforcement "
+        f"expects v{expected['version']} — framework/CLI version skew; "
+        "upgrade both as one unit; see #869"
+    )
+
+
+def assert_activation_capability_matches(
+    activation: ActivationCapability | None,
+    expected: ActivationCapability = EXPECTED_ACTIVATION_CAPABILITY,
+) -> None:
+    """Raise `VersionCouplingError` unless `activation` is present AND its
+    `name`/`version` exactly match `expected`. Absence is treated the same
+    as a mismatch — never a silent pass."""
+    if (
+        activation is None
+        or activation.get("name") != expected["name"]
+        or activation.get("version") != expected["version"]
+    ):
+        raise VersionCouplingError(format_mismatch_message(activation, expected))

packages/mosaic/framework/tools/lease-broker/launch-runtime.py

@@ -12,11 +12,24 @@ from collections.abc import Callable, Mapping, Sequence
 from pathlib import Path
 from typing import Final
 
+from activation_version_gate import (
+    EXPECTED_ACTIVATION_CAPABILITY,
+    ActivationCapability,
+    VersionCouplingError,
+    assert_activation_capability_matches,
+    default_probe_activation_capability,
+)
 from lease_generation import initialize_runtime_generation
 
 MAX_FRAME: Final = 64 * 1024
 BROKER_TIMEOUT_SECONDS: Final = 1.5
 CLAUDE_DANGEROUS_FLAG: Final = "--dangerously-skip-permissions"
+# Distinct, non-overlapping exit code for the C4 version-coupling gate (see
+# `activation_version_gate.py`) — deliberately different from the `1`
+# (broker registration failed closed) and `64` (usage error) codes already
+# owned by this script, so a version-skew denial is unambiguous in caller
+# logs/tests and is never confused with a broker-availability failure.
+EXIT_VERSION_SKEW: Final = 65
 
 
 def broker_request(socket_path: Path, request: dict[str, object]) -> dict[str, object]:
@@ -47,6 +60,10 @@ def main(
     request: Callable[[Path, dict[str, object]], dict[str, object]] = broker_request,
     execute: Callable[[str, list[str], dict[str, str]], object] = os.execvpe,
     initialize_generation: Callable[[Path, int], None] = initialize_runtime_generation,
+    probe_activation_capability: Callable[
+        [Mapping[str, str]], ActivationCapability | None
+    ] = default_probe_activation_capability,
+    expected_activation_capability: ActivationCapability = EXPECTED_ACTIVATION_CAPABILITY,
 ) -> int:
     parser = argparse.ArgumentParser()
     parser.add_argument("--runtime", required=True, choices=("claude", "pi"))
@@ -66,6 +83,25 @@ def main(
         command = [command[0], CLAUDE_DANGEROUS_FLAG, *command[1:]]
 
     source_environment = os.environ if environ is None else environ
+
+    # C4 version-coupling gate (#869 Point-1): before this ENFORCEMENT half
+    # chains into anything, assert that the ACTIVATION contract it is about
+    # to rely on (MOSAIC_LEASE_* injection, broker chaining) matches what
+    # this enforcement build expects. This is a build/deploy-defect check,
+    # not a broker-availability question, so it runs before — and
+    # independently of — broker registration below, and it FAILS LOUD: a
+    # clear stderr message plus a dedicated non-zero exit code, never a
+    # silent pass and never folded into the generic registration-failure
+    # branch.
+    try:
+        assert_activation_capability_matches(
+            probe_activation_capability(source_environment),
+            expected_activation_capability,
+        )
+    except VersionCouplingError as version_error:
+        print(str(version_error), file=sys.stderr)
+        return EXIT_VERSION_SKEW
+
     try:
         socket_path = Path(source_environment["MOSAIC_LEASE_BROKER_SOCKET"])
         generation = int(source_environment.get("MOSAIC_RUNTIME_GENERATION", "1"))