dashboard test runner . backend

packages/tracker/meshnet_tracker/cli.py

@@ -363,7 +363,10 @@ def main() -> None:
     common.add_argument(
         "--enable-test-runner",
         action="store_true",
-        help="Enable development test-runner hooks for this tracker",
+        help=(
+            "Enable the admin-only dashboard test runner API "
+            "(disabled by default; also honors MESHNET_ENABLE_TEST_RUNNER=1)"
+        ),
     )
     common.add_argument(
         "--no-file-logs",
@@ -442,6 +445,7 @@ def main() -> None:
             hf_pricing_refresh_interval=args.hf_pricing_refresh_interval,
             models_dir=args.models_dir,
             routing_config=_routing_config_from_args(args),
+            enable_test_runner=args.enable_test_runner,
         )
         port = server.start()
         print(f"meshnet-tracker listening on http://{args.host}:{port}", flush=True)

packages/tracker/meshnet_tracker/favicon.svg

@@ -1,4 +1,5 @@
 <svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 1254 1254" width="1254" height="1254">
+  <title>meshnet tracker</title>
   <defs>
     <radialGradient id="bg" cx="50%" cy="50%" r="70%">
       <stop offset="0%" stop-color="#071229"/>

packages/tracker/meshnet_tracker/server.py

@@ -53,6 +53,8 @@ from .calibration import DEFAULT_CALIBRATION_DB_PATH, ToplocCalibrationStore
 from .hf_pricing import DEFAULT_HF_PRICING_LOG_DB_PATH, HfPricingLog, refresh_preset_price
 from .gossip import NodeGossip
 from .logging_setup import tracker_logger
+from .test_runner import ENABLE_ENV_VAR as TEST_RUNNER_ENABLE_ENV_VAR
+from .test_runner import TestRunManager, TestRunnerError
 from .routing_stats import (
     RouteCandidate,
     RouteStatsStore,
@@ -1283,8 +1285,12 @@ def _request_model_load_locked(server: "_TrackerHTTPServer", model_key: str) ->
         return None
     required_start, required_end = _preset_layer_bounds(preset)
     total_layers = required_end - required_start + 1
+    required_bytes = int(preset.get("required_model_bytes") or 0)
     for host in _memory_pool_map(server)["hosts"]:
-        if host["spare_slots"] <= 0:
+        # A host qualifies with a declared spare slot, or — for an explicit
+        # operator request — with enough spare assignable memory for the model.
+        has_spare_memory = required_bytes > 0 and host["memory_spare_bytes"] >= required_bytes
+        if host["spare_slots"] <= 0 and not has_spare_memory:
             continue
         host_nodes = [server.registry[item["node_id"]] for item in host["loaded"] if item["node_id"] in server.registry]
         if not host_nodes:
@@ -1923,6 +1929,9 @@ def _rebalance_model_locked(server: "_TrackerHTTPServer", model: str) -> None:
     if not managed_nodes:
         return
 
+    # Directives must name a repo the node can actually load, not the preset key.
+    directive_model = str(preset.get("hf_repo") or model)
+
     coverage = _coverage_map(model_nodes, required_start, required_end)
     gaps = _coverage_gaps(coverage)
     unassigned = _unassigned_managed_nodes(managed_nodes)
@@ -1930,7 +1939,7 @@ def _rebalance_model_locked(server: "_TrackerHTTPServer", model: str) -> None:
         return
     if not gaps and unassigned:
         _assign_redundant_managed_nodes(
-            unassigned, model, preset, required_start, required_end,
+            unassigned, directive_model, preset, required_start, required_end,
         )
         return
 
@@ -1982,7 +1991,7 @@ def _rebalance_model_locked(server: "_TrackerHTTPServer", model: str) -> None:
     for node in managed_nodes:
         _emit_shard_change_directives(
             node,
-            model,
+            directive_model,
             previous_ranges[node.node_id],
             preset,
         )
@@ -2512,6 +2521,7 @@ class _TrackerHTTPServer(socketserver.ThreadingMixIn, http.server.HTTPServer):
         models_dir: Path | None = None,
         route_stats: "RouteStatsStore | None" = None,
         relay_status: dict | None = None,
+        test_runner: "TestRunManager | None" = None,
     ) -> None:
         super().__init__(addr, handler)
         self.registry = registry
@@ -2552,6 +2562,7 @@ class _TrackerHTTPServer(socketserver.ThreadingMixIn, http.server.HTTPServer):
         self.relay_status = dict(
             relay_status or {"mode": "external" if self.relay_url else "off"}
         )
+        self.test_runner: TestRunManager | None = test_runner
 
 
 class _TrackerHandler(http.server.BaseHTTPRequestHandler):
@@ -2710,6 +2721,9 @@ class _TrackerHandler(http.server.BaseHTTPRequestHandler):
         if self.path == "/v1/wallet/register":
             self._handle_wallet_register()
             return
+        if self.path == "/v1/tests/run":
+            self._handle_tests_run()
+            return
         parts = self.path.split("/")
         # /v1/nodes/<node_id>/heartbeat -> ['', 'v1', 'nodes', '<id>', 'heartbeat']
         if len(parts) == 5 and parts[1] == "v1" and parts[2] == "nodes" and parts[4] == "heartbeat":
@@ -2784,6 +2798,10 @@ class _TrackerHandler(http.server.BaseHTTPRequestHandler):
             self._handle_toploc_calibration_results()
         elif parsed.path == "/v1/pricing/hf/history":
             self._handle_hf_pricing_history(parsed)
+        elif parsed.path == "/v1/tests":
+            self._handle_tests_list(parsed)
+        elif parsed.path == "/v1/tests/status":
+            self._handle_tests_status()
         elif parsed.path == "/v1/registry/wallets":
             self._handle_registry_wallets()
         elif parsed.path in ("/dashboard", "/dashboard/"):
@@ -2846,8 +2864,9 @@ class _TrackerHandler(http.server.BaseHTTPRequestHandler):
                 "served_model_copies": served_copies,
             })
             seen_ids.add(name)
-            if hf_repo:
-                seen_ids.add(hf_repo)
+            # Note: the preset's hf_repo is deliberately NOT added to seen_ids —
+            # nodes registered with an explicit hf_repo also get their own
+            # repo-keyed entry below, with the node's short name as an alias.
 
         hf_model_ids = sorted({
             node.hf_repo or node.model
@@ -4328,7 +4347,7 @@ class _TrackerHandler(http.server.BaseHTTPRequestHandler):
 
     def _handle_model_load_request(self):
         server: _TrackerHTTPServer = self.server  # type: ignore[assignment]
-        if not self._require_role("admin"):
+        if not self._require_role("admin", "validator"):
             return
         body = self._read_json_body()
         if body is None:
@@ -4467,6 +4486,57 @@ class _TrackerHandler(http.server.BaseHTTPRequestHandler):
         finish_proxy_inflight()
         return True
 
+    # ---- opt-in test runner (dashboard-test-runner US-001) ----
+
+    def _test_runner_or_reject(self) -> "TestRunManager | None":
+        """Admin session first, then the explicit enable gate — both fail closed."""
+        if not self._require_role("admin"):
+            return None
+        server: _TrackerHTTPServer = self.server  # type: ignore[assignment]
+        if server.test_runner is None:
+            self._send_json(403, {
+                "error": (
+                    "test runner disabled; start the tracker with "
+                    f"--enable-test-runner or {TEST_RUNNER_ENABLE_ENV_VAR}=1"
+                )
+            })
+            return None
+        return server.test_runner
+
+    def _handle_tests_list(self, parsed: urllib.parse.ParseResult) -> None:
+        runner = self._test_runner_or_reject()
+        if runner is None:
+            return
+        query = urllib.parse.parse_qs(parsed.query)
+        refresh = query.get("refresh", ["0"])[0] in {"1", "true"}
+        try:
+            data = runner.collect(refresh=refresh)
+        except TestRunnerError as exc:
+            self._send_json(exc.status, {"error": str(exc)})
+            return
+        self._send_json(200, {"enabled": True, **data})
+
+    def _handle_tests_run(self) -> None:
+        runner = self._test_runner_or_reject()
+        if runner is None:
+            return
+        body = self._read_json_body()
+        if body is None:
+            return
+        target = body.get("target")
+        try:
+            state = runner.start(target if isinstance(target, str) else "")
+        except TestRunnerError as exc:
+            self._send_json(exc.status, {"error": str(exc)})
+            return
+        self._send_json(202, state)
+
+    def _handle_tests_status(self) -> None:
+        runner = self._test_runner_or_reject()
+        if runner is None:
+            return
+        self._send_json(200, runner.status())
+
     def _handle_registry_wallets(self):
         server: _TrackerHTTPServer = self.server  # type: ignore[assignment]
         if not self._require_role("admin"):
@@ -5943,6 +6013,8 @@ class TrackerServer:
         hf_pricing_fetch_html: Any | None = None,
         models_dir: str | Path | None = None,
         routing_config: RoutingConfig | None = None,
+        enable_test_runner: bool = False,
+        test_runner: TestRunManager | None = None,
     ) -> None:
         self._host = host
         self._requested_port = port
@@ -6063,6 +6135,13 @@ class TrackerServer:
                 ),
             )
         self._route_stats = RouteStatsStore(routing_config, db_path=stats_db)
+        # Opt-in test runner: an injected manager implies enabled; otherwise
+        # only the explicit flag or env var constructs one (fails closed).
+        if test_runner is None and (
+            enable_test_runner or os.environ.get(TEST_RUNNER_ENABLE_ENV_VAR) == "1"
+        ):
+            test_runner = TestRunManager()
+        self._test_runner: TestRunManager | None = test_runner
         self.port: int | None = None
 
     def _start_embedded_relay(self) -> dict:
@@ -6148,6 +6227,7 @@ class TrackerServer:
             models_dir=self._models_dir,
             route_stats=self._route_stats,
             relay_status=http_relay_status,
+            test_runner=self._test_runner,
         )
         self.port = self._server.server_address[1]
 
@@ -6469,6 +6549,8 @@ class TrackerServer:
         self._embedded_relay_actual_port = None
         if embedded_relay is not None:
             embedded_relay.stop()
+        if self._test_runner is not None:
+            self._test_runner.shutdown()
         if self._server is None:
             return
         self._rebalance_stop.set()

packages/tracker/meshnet_tracker/test_runner.py

@@ -0,0 +1,314 @@
+"""Opt-in tracker test runner backing the dashboard Testing tab.
+
+Security posture (dashboard-test-runner US-001):
+
+- **Disabled by default** — the tracker only constructs a manager when started
+  with ``--enable-test-runner`` / ``MESHNET_ENABLE_TEST_RUNNER=1`` or
+  ``TrackerServer(enable_test_runner=True)``.
+- **No arbitrary commands** — a run target must be either a pytest node ID
+  returned by our own ``--collect-only`` pass or an approved named suite.
+  Callers never supply command arguments.
+- **No shell** — pytest runs as ``[sys.executable, "-m", "pytest", ...]`` via
+  ``subprocess.Popen`` without ``shell=True``.
+- **One run at a time** — a second start while a run is active is rejected.
+- **Bounded logs** — stdout/stderr are retained as line deques with caps.
+- **Real inference stays gated** — ``tests/test_real_*.py`` modules are never
+  collected and never part of a suite unless
+  ``MESHNET_ENABLE_REAL_INFERENCE_TESTS=1`` is set, and even then only via the
+  dedicated ``suite:real-inference`` target, never a default suite.
+"""
+
+from __future__ import annotations
+
+import os
+import re
+import subprocess
+import sys
+import threading
+import time
+import uuid
+from collections import deque
+from pathlib import Path
+
+ENABLE_ENV_VAR = "MESHNET_ENABLE_TEST_RUNNER"
+REAL_INFERENCE_ENV_VAR = "MESHNET_ENABLE_REAL_INFERENCE_TESTS"
+
+# Modules that talk to live nodes / spend API credit; matched by filename.
+_REAL_INFERENCE_PATTERN = re.compile(r"(^|/)test_real_[^/]*\.py")
+
+# Fixed, reviewed suite targets. Values are pytest paths relative to the repo
+# root — never influenced by API input.
+APPROVED_SUITES: dict[str, list[str]] = {
+    "smoke": ["tests/test_smoke.py"],
+    "dashboard": ["tests/test_dashboard.py"],
+    "routing": ["tests/test_tracker_routing.py", "tests/test_dynamic_routing.py"],
+}
+
+# Only exists when REAL_INFERENCE_ENV_VAR=1; kept out of APPROVED_SUITES so it
+# can never appear by default.
+_REAL_INFERENCE_SUITE = {
+    "real-inference": [
+        "tests/test_real_distributed_inference.py",
+        "tests/test_real_model_backend.py",
+    ]
+}
+
+DEFAULT_MAX_LOG_LINES = 4000
+_MAX_LINE_CHARS = 4000
+DEFAULT_COLLECT_TIMEOUT = 120.0
+DEFAULT_RUN_TIMEOUT = 1800.0
+
+_NODE_ID_RE = re.compile(r"^[\w./\[\]:,= @-]+$")
+
+
+class TestRunnerError(Exception):
+    """Base class; carries the HTTP status the handler should send."""
+
+    status = 400
+
+
+class UnknownTargetError(TestRunnerError):
+    status = 400
+
+
+class RunInProgressError(TestRunnerError):
+    status = 409
+
+
+class CollectionError(TestRunnerError):
+    status = 500
+
+
+def discover_repo_root(start: Path | None = None) -> Path:
+    """Find the repository root independent of the tracker's cwd.
+
+    Walks up from this module (or ``start``) to the first directory holding
+    both a ``pyproject.toml`` and ``tests/conftest.py`` — the layout of the
+    meshnet monorepo root. Package-level ``pyproject.toml`` files (which have
+    no ``tests/`` dir) are skipped naturally.
+    """
+    current = (start or Path(__file__)).resolve()
+    for candidate in [current, *current.parents]:
+        if (candidate / "pyproject.toml").is_file() and (candidate / "tests" / "conftest.py").is_file():
+            return candidate
+    raise RuntimeError("could not locate repository root (pyproject.toml + tests/conftest.py)")
+
+
+def _real_inference_enabled() -> bool:
+    return os.environ.get(REAL_INFERENCE_ENV_VAR) == "1"
+
+
+class TestRunManager:
+    """Collects pytest node IDs and runs one fixed target at a time."""
+
+    def __init__(
+        self,
+        repo_root: str | Path | None = None,
+        *,
+        max_log_lines: int = DEFAULT_MAX_LOG_LINES,
+        collect_timeout: float = DEFAULT_COLLECT_TIMEOUT,
+        run_timeout: float = DEFAULT_RUN_TIMEOUT,
+    ) -> None:
+        self.repo_root = Path(repo_root).resolve() if repo_root else discover_repo_root()
+        self.max_log_lines = max_log_lines
+        self.collect_timeout = collect_timeout
+        self.run_timeout = run_timeout
+        self._lock = threading.Lock()
+        self._collected: set[str] = set()
+        self._collected_at: float | None = None
+        self._run: dict | None = None
+        self._process: subprocess.Popen | None = None
+        self._stdout: deque[str] = deque(maxlen=max_log_lines)
+        self._stderr: deque[str] = deque(maxlen=max_log_lines)
+        self._reader_threads: list[threading.Thread] = []
+
+    # ---- collection ----
+
+    def suites(self) -> dict[str, list[str]]:
+        """Approved suites whose files exist in this repo checkout."""
+        available = dict(APPROVED_SUITES)
+        if _real_inference_enabled():
+            available.update(_REAL_INFERENCE_SUITE)
+        return {
+            name: paths
+            for name, paths in available.items()
+            if all((self.repo_root / p).is_file() for p in paths)
+        }
+
+    def collect(self, *, refresh: bool = False) -> dict:
+        """Run ``pytest --collect-only -q`` and cache the node IDs.
+
+        Real-inference modules are ignored at collection time (they are never
+        imported) unless the explicit environment gate is set.
+        """
+        with self._lock:
+            if self._collected_at is not None and not refresh:
+                return self._collection_snapshot_locked()
+
+        cmd = [sys.executable, "-m", "pytest", "--collect-only", "-q", "-p", "no:cacheprovider"]
+        if not _real_inference_enabled():
+            for name in sorted(
+                p.name for p in (self.repo_root / "tests").glob("test_real_*.py")
+            ):
+                cmd.append(f"--ignore=tests/{name}")
+        cmd.append("tests")
+        try:
+            proc = subprocess.run(
+                cmd,
+                cwd=self.repo_root,
+                capture_output=True,
+                text=True,
+                timeout=self.collect_timeout,
+            )
+        except subprocess.TimeoutExpired as exc:
+            raise CollectionError(f"pytest collection timed out after {self.collect_timeout}s") from exc
+        # Exit code 5 = no tests collected; still a valid (empty) result.
+        if proc.returncode not in (0, 5):
+            tail = (proc.stdout or "")[-2000:] + (proc.stderr or "")[-2000:]
+            raise CollectionError(f"pytest collection failed (exit {proc.returncode}): {tail}")
+        node_ids = [
+            line.strip()
+            for line in proc.stdout.splitlines()
+            if "::" in line and not line.startswith(("=", " ", "<"))
+        ]
+        if not _real_inference_enabled():
+            node_ids = [n for n in node_ids if not _REAL_INFERENCE_PATTERN.search(n.split("::", 1)[0])]
+        with self._lock:
+            self._collected = set(node_ids)
+            self._collected_at = time.time()
+            return self._collection_snapshot_locked()
+
+    def _collection_snapshot_locked(self) -> dict:
+        return {
+            "tests": sorted(self._collected),
+            "suites": [
+                {"id": f"suite:{name}", "name": name, "paths": paths}
+                for name, paths in sorted(self.suites().items())
+            ],
+            "collected_at": self._collected_at,
+        }
+
+    # ---- running ----
+
+    def start(self, target: str) -> dict:
+        """Start one collected node ID or approved ``suite:<name>`` target."""
+        if not isinstance(target, str) or not target.strip():
+            raise UnknownTargetError("target is required")
+        target = target.strip()
+        if target.startswith("-") or not _NODE_ID_RE.match(target):
+            raise UnknownTargetError("target must be a collected test node ID or an approved suite")
+
+        if target.startswith("suite:"):
+            suite_name = target.removeprefix("suite:")
+            paths = self.suites().get(suite_name)
+            if paths is None:
+                raise UnknownTargetError(f"unknown suite: {suite_name!r}")
+            pytest_args = list(paths)
+        else:
+            with self._lock:
+                known = target in self._collected
+            if not known:
+                raise UnknownTargetError(
+                    "target is not a collected test node ID; call GET /v1/tests first"
+                )
+            pytest_args = [target]
+
+        with self._lock:
+            if self._run is not None and self._run["status"] == "running":
+                raise RunInProgressError("a test run is already in progress")
+            cmd = [sys.executable, "-m", "pytest", "-q", "-p", "no:cacheprovider", *pytest_args]
+            self._stdout = deque(maxlen=self.max_log_lines)
+            self._stderr = deque(maxlen=self.max_log_lines)
+            process = subprocess.Popen(  # noqa: S603 — fixed argv, no shell
+                cmd,
+                cwd=self.repo_root,
+                stdout=subprocess.PIPE,
+                stderr=subprocess.PIPE,
+                text=True,
+            )
+            self._process = process
+            self._run = {
+                "run_id": uuid.uuid4().hex,
+                "target": target,
+                "args": pytest_args,
+                "status": "running",
+                "started_at": time.time(),
+                "finished_at": None,
+                "exit_code": None,
+            }
+            self._reader_threads = [
+                threading.Thread(
+                    target=self._drain, args=(process.stdout, self._stdout), daemon=True
+                ),
+                threading.Thread(
+                    target=self._drain, args=(process.stderr, self._stderr), daemon=True
+                ),
+            ]
+            for thread in self._reader_threads:
+                thread.start()
+            waiter = threading.Thread(target=self._wait, args=(process,), daemon=True)
+            waiter.start()
+            return self._status_locked()
+
+    @staticmethod
+    def _drain(stream, sink: deque[str]) -> None:
+        try:
+            for line in stream:
+                sink.append(line.rstrip("\n")[:_MAX_LINE_CHARS])
+        except ValueError:  # stream closed mid-read on shutdown
+            pass
+        finally:
+            stream.close()
+
+    def _wait(self, process: subprocess.Popen) -> None:
+        timed_out = False
+        try:
+            exit_code = process.wait(timeout=self.run_timeout)
+        except subprocess.TimeoutExpired:
+            timed_out = True
+            process.kill()
+            exit_code = process.wait()
+        for thread in self._reader_threads:
+            thread.join(timeout=5)
+        with self._lock:
+            if self._process is not process or self._run is None:
+                return
+            self._run["exit_code"] = exit_code
+            self._run["finished_at"] = time.time()
+            if timed_out:
+                self._run["status"] = "timeout"
+            elif exit_code == 0:
+                self._run["status"] = "passed"
+            else:
+                self._run["status"] = "failed"
+            self._process = None
+
+    def status(self) -> dict:
+        with self._lock:
+            return self._status_locked()
+
+    def _status_locked(self) -> dict:
+        if self._run is None:
+            return {"run": None, "stdout": "", "stderr": ""}
+        run = dict(self._run)
+        if run["status"] == "running":
+            run["elapsed_seconds"] = time.time() - run["started_at"]
+        elif run["finished_at"] is not None:
+            run["elapsed_seconds"] = run["finished_at"] - run["started_at"]
+        return {
+            "run": run,
+            "stdout": "\n".join(self._stdout),
+            "stderr": "\n".join(self._stderr),
+            "log_lines_limit": self.max_log_lines,
+        }
+
+    def shutdown(self) -> None:
+        """Kill any active child process (tracker stop path)."""
+        with self._lock:
+            process = self._process
+        if process is not None and process.poll() is None:
+            process.kill()
+            try:
+                process.wait(timeout=5)
+            except subprocess.TimeoutExpired:
+                pass