dashboard test runner . backend

tests on dash
routing tests, launch.configs, redirect, stats and route statistics
2026-07-11 16:11:42 +03:00 · 2026-07-11 12:38:51 +03:00 · 2026-07-11 11:39:47 +03:00
20 changed files with 1605 additions and 85 deletions
--- a/.gitignore
+++ b/.gitignore
@@ -10,7 +10,8 @@ dist/
 .venv/

 # Ralph local runtime state
-.ralph-tui/
+.ralph-tui/*
+!.ralph-tui/config.toml


 .env
--- a/.ralph-tui/config.toml
+++ b/.ralph-tui/config.toml
@@ -0,0 +1,7 @@
+[agent]
+name = "claude"
+model = "opus"
+
+[run]
+iterations = 10
+delayMs = 1000
--- a/.scratch/dashboard-test-runner/PRD.md
+++ b/.scratch/dashboard-test-runner/PRD.md
@@ -0,0 +1,15 @@
+# Dashboard Test Runner
+
+Status: active
+
+## Goal
+Provide an opt-in, admin-only tracker Dashboard Testing tab that dynamically discovers pytest tests, runs fixed collected targets safely in background, and reports live logs/status.
+
+## Safety
+- Disabled unless tracker starts with an explicit flag.
+- Admin-only API/UI.
+- No arbitrary command/argument execution.
+- One active run.
+- Real inference stays separately environment-gated and excluded from default suites.
+
+See `prd.json` for executable Ralph user stories and acceptance criteria.
--- a/.scratch/dashboard-test-runner/prd.json
+++ b/.scratch/dashboard-test-runner/prd.json
@@ -0,0 +1,64 @@
+{
+  "name": "Tracker Dashboard Test Runner",
+  "description": "Add an admin-only Testing tab that dynamically discovers repository pytest tests, runs a selected safe test target in a background process, and shows live output/status in the tracker dashboard.",
+  "branchName": "ralph/dashboard-test-runner",
+  "userStories": [
+    {
+      "id": "US-001",
+      "title": "Implement secure tracker test-runner API",
+      "description": "As a tracker administrator, I want the tracker to discover and run repository tests through a controlled API so that dashboard actions cannot execute arbitrary shell commands.",
+      "acceptanceCriteria": [
+        "Add an explicit disabled-by-default TrackerServer/CLI test-runner flag; no test endpoint runs commands unless enabled.",
+        "Admin-only endpoints dynamically collect pytest node IDs and start one selected collected test or approved suite at a time without accepting arbitrary command arguments.",
+        "Run pytest in a background process without shell=True, retain bounded stdout/stderr logs, status, timestamps, exit code, and reject concurrent runs.",
+        "Add focused API tests for authorization, disabled state, collection, start, progress/completion, and concurrent-run rejection.",
+        "uv run pytest tests/test_dashboard.py tests/test_tracker_routing.py tests/test_dynamic_routing.py -q passes."
+      ],
+      "priority": 1,
+      "passes": true,
+      "notes": "Use repository root discovery independent of tracker current working directory. Real-inference tests must require an explicit enable flag or environment gate and must never be included in a default suite.",
+      "dependsOn": [],
+      "completionNotes": "Completed by agent"
+    },
+    {
+      "id": "US-002",
+      "title": "Add Testing dashboard tab with live test logs",
+      "description": "As a tracker administrator, I want a Testing tab that lists discovered tests and exposes run/status/log controls so that I can operate and inspect tests from the dashboard.",
+      "acceptanceCriteria": [
+        "Add an admin-only Testing navigation tab and panel; it is hidden for non-admin users.",
+        "Dynamically render tests/suites returned by the tracker API with a Run button for each allowed target.",
+        "Show current state, start/end time, elapsed time, exit code, success/failure, and an auto-refreshing bounded console/log view.",
+        "Disable run controls while a test run is active and display API errors clearly.",
+        "Add dashboard regression tests asserting the Testing tab, dynamic API calls, run controls, and log/status renderer exist.",
+        "uv run pytest tests/test_dashboard.py -q passes."
+      ],
+      "priority": 2,
+      "passes": false,
+      "notes": "Depends on US-001. Preserve existing dashboard tabs and admin authentication conventions.",
+      "dependsOn": [
+        "US-001"
+      ]
+    },
+    {
+      "id": "US-003",
+      "title": "Wire launch and document operator workflow",
+      "description": "As a local mesh operator, I want a launch configuration and documentation for the opt-in test runner so that I can enable it intentionally and understand real-inference safeguards.",
+      "acceptanceCriteria": [
+        "Add a distinct VS Code tracker launch configuration that enables the test runner and uses the project tracker runtime.",
+        "Document default safe suites versus the explicitly gated real-inference suite, including required environment variables and API-credit/hardware implications.",
+        "Validate launch.json and tracker CLI --help.",
+        "uv run pytest tests/test_dashboard.py tests/test_dynamic_routing.py -q passes."
+      ],
+      "priority": 3,
+      "passes": false,
+      "notes": "Do not reintroduce --enable-test-runner without implementing its CLI argument in US-001.",
+      "dependsOn": [
+        "US-001",
+        "US-002"
+      ]
+    }
+  ],
+  "metadata": {
+    "updatedAt": "2026-07-11T12:58:47.086Z"
+  }
+}
--- a/.scratch/dashboard-test-runner/ralph-iterations/4cd034a1_2026-07-11_15-23-25_US-001.log
+++ b/.scratch/dashboard-test-runner/ralph-iterations/4cd034a1_2026-07-11_15-23-25_US-001.log
@@ -0,0 +1,196 @@
+# Iteration 1 Log
+
+## Metadata
+
+- **Task ID**: US-001
+- **Task Title**: Implement secure tracker test-runner API
+- **Description**: As a tracker administrator, I want the tracker to discover and run repository tests through a controlled API so that dashboard actions cannot execute arbitrary shell commands.
+- **Status**: completed
+- **Task Completed**: No
+- **Promise Detected**: No
+- **Started At**: 2026-07-11T12:23:25.086Z
+- **Ended At**: 2026-07-11T12:49:05.992Z
+- **Duration**: 25m 40s
+- **Input Tokens**: 27303
+- **Output Tokens**: 60809
+- **Total Tokens**: 88112
+- **Agent**: claude
+- **Model**: claude-fable-5
+- **Sandbox Mode**: auto
+- **Sandbox Network**: Enabled
+--- RAW OUTPUT ---
+I'll start by reviewing the progress file and understanding the existing codebase structure.
+[94m[Read][0m [95m/run/media/popov/d/DEV/repos/d-popov.com/AI/.ralph-tui/progress.md[0m
+[94m[Bash][0m List repo root and scratch dir $ ls /run/media/popov/d/DEV/repos/d-popov.com/AI && ls /run/media/popov/d/DEV/repos/d-popov.com/AI/.sc...
+[94m[Bash][0m Read PRD and list tests/packages $ ls /run/media/popov/d/DEV/repos/d-popov.com/AI/tests /run/media/popov/d/DEV/repos/d-popov.com/AI/pac...
+[94m[Bash][0m Explore tracker package structure $ ls /run/media/popov/d/DEV/repos/d-popov.com/AI/.scratch 2>/dev/null
+[94m[Bash][0m Inspect scratch dir for this feature $ find /run/media/popov/d/DEV/repos/d-popov.com/AI/.scratch/dashboard-test-runner -type f | head -20
+[94m[Read][0m [95m/run/media/popov/d/DEV/repos/d-popov.com/AI/.scratch/dashboard-test-runner/prd.json[0m
+[94m[Read][0m [95m/run/media/popov/d/DEV/repos/d-popov.com/AI/.scratch/dashboard-test-runner/PRD.md[0m
+Now let me study the tracker server, CLI, and auth patterns.
+[94m[Bash][0m Line counts of key files $ wc -l /run/media/popov/d/DEV/repos/d-popov.com/AI/packages/tracker/meshnet_tracker/server.py /run/me...
+[94m[Read][0m [95m/run/media/popov/d/DEV/repos/d-popov.com/AI/packages/tracker/meshnet_tracker/auth.py[0m
+[94m[Read][0m [95m/run/media/popov/d/DEV/repos/d-popov.com/AI/packages/tracker/meshnet_tracker/cli.py[0m
+[94m[Bash][0m Search server.py for test-runner and admin handling $ grep -n "def __init__\|def _handle\|admin" packages/tracker/meshnet_tracker/server.py | head -80
+[94m[Read][0m [95m/run/media/popov/d/DEV/repos/d-popov.com/AI/packages/tracker/meshnet_tracker/server.py[0m
+[94m[Read][0m [95m/run/media/popov/d/DEV/repos/d-popov.com/AI/packages/tracker/meshnet_tracker/server.py[0m
+[94m[Read][0m [95m/run/media/popov/d/DEV/repos/d-popov.com/AI/tests/test_dashboard.py[0m
+[94m[Bash][0m Check stop method, conftests, real-test gating $ sed -n '1,30p' conftest.py
+[94m[Read][0m [95m/run/media/popov/d/DEV/repos/d-popov.com/AI/packages/tracker/meshnet_tracker/server.py[0m
+[94m[Bash][0m Check account roles and session API $ grep -n "def register\|def create_session\|def session_account" packages/tracker/meshnet_tracker/acc...
+Let me check the HTTP server base class and the routing test files quickly.
+[94m[Bash][0m Check server class bases and imports $ head -30 tests/test_tracker_routing.py
+[94m[Write][0m [95m/run/media/popov/d/DEV/repos/d-popov.com/AI/packages/tracker/meshnet_tracker/test_runner.py[0m """"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
+  wit... (11919 chars)"
+[94m[Edit][0m [95m/run/media/popov/d/DEV/repos/d-popov.com/AI/packages/tracker/meshnet_tracker/server.py[0m edit: "from .gossip import NodeGossip
+from .logging_setup..." → "from .gossip import NodeGossip
+from .logging_setup..."
+[94m[Edit][0m [95m/run/media/popov/d/DEV/repos/d-popov.com/AI/packages/tracker/meshnet_tracker/server.py[0m edit: "        route_stats: "RouteStatsStore | None" = No..." → "        route_stats: "RouteStatsStore | None" = No..."
+[94m[Edit][0m [95m/run/media/popov/d/DEV/repos/d-popov.com/AI/packages/tracker/meshnet_tracker/server.py[0m edit: "        self.relay_status = dict(
+            rela..." → "        self.relay_status = dict(
+            rela..."
+Now the handler routes and endpoint implementations:
+[94m[Edit][0m [95m/run/media/popov/d/DEV/repos/d-popov.com/AI/packages/tracker/meshnet_tracker/server.py[0m edit: "        if self.path == "/v1/wallet/register":
+   ..." → "        if self.path == "/v1/wallet/register":
+   ..."
+[94m[Edit][0m [95m/run/media/popov/d/DEV/repos/d-popov.com/AI/packages/tracker/meshnet_tracker/server.py[0m edit: "        elif parsed.path == "/v1/registry/wallets"..." → "        elif parsed.path == "/v1/tests":
+         ..."
+[94m[Read][0m [95m/run/media/popov/d/DEV/repos/d-popov.com/AI/packages/tracker/meshnet_tracker/server.py[0m
+[94m[Edit][0m [95m/run/media/popov/d/DEV/repos/d-popov.com/AI/packages/tracker/meshnet_tracker/server.py[0m edit: "    def _handle_registry_wallets(self):
+        se..." → "    # ---- opt-in test runner (dashboard-test-runn..."
+[94m[Edit][0m [95m/run/media/popov/d/DEV/repos/d-popov.com/AI/packages/tracker/meshnet_tracker/server.py[0m edit: "        models_dir: str | Path | None = None,
+    ..." → "        models_dir: str | Path | None = None,
+    ..."
+[94m[Edit][0m [95m/run/media/popov/d/DEV/repos/d-popov.com/AI/packages/tracker/meshnet_tracker/server.py[0m edit: "        self._route_stats = RouteStatsStore(routin..." → "        self._route_stats = RouteStatsStore(routin..."
+[94m[Edit][0m [95m/run/media/popov/d/DEV/repos/d-popov.com/AI/packages/tracker/meshnet_tracker/server.py[0m edit: "            route_stats=self._route_stats,
+       ..." → "            route_stats=self._route_stats,
+       ..."
+[94m[Edit][0m [95m/run/media/popov/d/DEV/repos/d-popov.com/AI/packages/tracker/meshnet_tracker/server.py[0m edit: "        if self._server is None:
+            retur..." → "        if self._test_runner is not None:
+        ..."
+Now wire the CLI flag to the `TrackerServer` parameter explicitly (it currently only sets the env var):
+[94m[Edit][0m [95m/run/media/popov/d/DEV/repos/d-popov.com/AI/packages/tracker/meshnet_tracker/cli.py[0m edit: "    common.add_argument(
+        "--enable-test-ru..." → "    common.add_argument(
+        "--enable-test-ru..."
+[94m[Edit][0m [95m/run/media/popov/d/DEV/repos/d-popov.com/AI/packages/tracker/meshnet_tracker/cli.py[0m edit: "            models_dir=args.models_dir,
+          ..." → "            models_dir=args.models_dir,
+          ..."
+Before writing tests, check the pytest config — the class name `TestRunManager` could trigger collection warnings in the test module:
+[94m[Bash][0m Check pytest config in pyproject $ grep -n -A15 "pytest" pyproject.toml | head -40
+[94m[Write][0m [95m/run/media/popov/d/DEV/repos/d-popov.com/AI/tests/test_tracker_test_runner.py[0m """"dashboard-test-runner US-001: opt-in, admin-only tracker test-runner API.
+
+Runs against a tiny throwaway repo (tmp_path) so collection and runs stay
+fast and hermetic — the manager itself discovers... (8890 chars)"
+Now run the new test file:
+[94m[Bash][0m Run new test-runner API tests $ uv run pytest tests/test_tracker_test_runner.py -q 2>&1 | tail -20
+All 14 new tests pass. Now the acceptance-criteria suite plus a CLI `--help` sanity check:
+[94m[Bash][0m Run acceptance-criteria pytest suite $ uv run pytest tests/test_dashboard.py tests/test_tracker_routing.py tests/test_dynamic_routing.py -q...
+Four failures — let me check whether they're pre-existing on the base tree or caused by my change:
+[94m[Bash][0m Show failure details $ uv run pytest tests/test_dashboard.py::test_dashboard_served_with_all_panels "tests/test_tracker_rou...
+[94m[Bash][0m Stash changes, rerun failing tests on clean tree, restore $ git stash pop
+[94m[Bash][0m Show assertion details for three failing tests $ uv run pytest "tests/test_tracker_routing.py::test_tracker_models_endpoint_lists_registered_hf_repo_...
+[94m[Bash][0m Check root PRD for active stories $ [print(s['id'], s['title'], 'passes:', s.get('passes')) for s in d['userStories']]" 2>/dev/null || h...
+
+[91m[Error: Exit code 1
+head: cannot open 'PRD.md' for reading: No such file or directory
+===
+head: cannot open 'prd.json' for reading: No such file or directory][0m
+[94m[Bash][0m Read models alias test $ grep -n "test_tracker_models_endpoint_lists_registered_hf_repo_and_short_name_alias" -A 60 tests/tes...
+[94m[Bash][0m Read the other two failing tests $ grep -n "test_shard_heal_cycle_surviving_node_covers_dead_peers_gap" -A 70 tests/test_tracker_routin...
+[94m[Read][0m [95m/run/media/popov/d/DEV/repos/d-popov.com/AI/packages/tracker/meshnet_tracker/server.py[0m
+[94m[Bash][0m Locate model load request function $ grep -n "def _request_model_load_locked" packages/tracker/meshnet_tracker/server.py
+[94m[Read][0m [95m/run/media/popov/d/DEV/repos/d-popov.com/AI/packages/tracker/meshnet_tracker/server.py[0m
+[94m[Read][0m [95m/run/media/popov/d/DEV/repos/d-popov.com/AI/packages/tracker/meshnet_tracker/server.py[0m
+[94m[Read][0m [95m/run/media/popov/d/DEV/repos/d-popov.com/AI/packages/tracker/meshnet_tracker/server.py[0m
+[94m[Bash][0m Find qwen preset in model presets $ python3 -c " import json d = json.load(open('packages/tracker/meshnet_tracker/model_presets.json')) ...
+[94m[Bash][0m List preset keys and find matcher $ grep -n "_node_matches_preset" packages/tracker/meshnet_tracker/server.py | head -3
+[94m[Bash][0m Read preset loading and matcher $ sed -n '110,235p' packages/tracker/meshnet_tracker/server.py
+[94m[Bash][0m List actual model presets $ python3 -c " import json d = json.load(open('packages/tracker/meshnet_tracker/model_presets.json'))[...
+[94m[Bash][0m Find LOAD_SHARD directive creation sites $ grep -n "LOAD_SHARD\|_load_shard_directive\|def _rebalance\|def _scale_demanded" packages/tracker/me...
+[94m[Read][0m [95m/run/media/popov/d/DEV/repos/d-popov.com/AI/packages/tracker/meshnet_tracker/server.py[0m
+[94m[Read][0m [95m/run/media/popov/d/DEV/repos/d-popov.com/AI/packages/tracker/meshnet_tracker/server.py[0m
+[94m[Bash][0m Find directive-model assertions in tests $ grep -n "_emit_shard_change_directives\|_assign_redundant_managed_nodes" packages/tracker/meshnet_tr...
+[94m[Bash][0m Identify test containing line 1579 $ grep -n "^def test" tests/test_tracker_routing.py | awk -F: '$1 < 1579' | tail -3
+[94m[Read][0m [95m/run/media/popov/d/DEV/repos/d-popov.com/AI/packages/tracker/meshnet_tracker/server.py[0m
+[94m[Bash][0m View model load handler head $ sed -n '4338,4344p' packages/tracker/meshnet_tracker/server.py
+[94m[Edit][0m [95m/run/media/popov/d/DEV/repos/d-popov.com/AI/packages/tracker/meshnet_tracker/server.py[0m edit: "    def _handle_model_load_request(self):
+        ..." → "    def _handle_model_load_request(self):
+        ..."
+[94m[Edit][0m [95m/run/media/popov/d/DEV/repos/d-popov.com/AI/packages/tracker/meshnet_tracker/server.py[0m edit: "    model_nodes = [
+        node for node in serve..." → "    model_nodes = [
+        node for node in serve..."
+[94m[Edit][0m [95m/run/media/popov/d/DEV/repos/d-popov.com/AI/packages/tracker/meshnet_tracker/server.py[0m edit: "    for node in managed_nodes:
+        _emit_shard..." → "    for node in managed_nodes:
+        _emit_shard..."
+Now the `/v1/models` fix — stop suppressing the node-derived hf-repo entry when a preset shares that repo:
+[94m[Edit][0m [95m/run/media/popov/d/DEV/repos/d-popov.com/AI/packages/tracker/meshnet_tracker/server.py[0m edit: "            seen_ids.add(name)
+            if hf_r..." → "            seen_ids.add(name)
+            # Note:..."
+And the favicon fix — the dashboard test requires the string "meshnet" in the SVG:
+[94m[Bash][0m View favicon opening tag $ head -c 300 packages/tracker/meshnet_tracker/favicon.svg
+[94m[Bash][0m Add meshnet title to favicon SVG $ python3 - <<'EOF' from pathlib import Path p = Path("packages/tracker/meshnet_tracker/favicon.svg") ...
+Now run the full acceptance-criteria suite:
+[94m[Bash][0m Run acceptance-criteria pytest suite $ uv run pytest tests/test_dashboard.py tests/test_tracker_routing.py tests/test_dynamic_routing.py -q...
+[94m[Bash][0m Show remaining failure detail $ uv run pytest tests/test_dynamic_routing.py::test_admin_model_load_request_queues_directive_on_joine...
+Auth passes now; the load returns 409 (no eligible node found). Let me debug `_memory_pool_map`/capacity for that registration:
+[94m[Bash][0m Debug memory pool and node capacity for model load $ uv run python - <<'EOF' import json, urllib.request from meshnet_tracker.server import TrackerServer...
+[94m[Bash][0m Find slot computation $ grep -n "memory_mb" packages/tracker/meshnet_tracker/server.py | head
+[94m[Read][0m [95m/run/media/popov/d/DEV/repos/d-popov.com/AI/packages/tracker/meshnet_tracker/server.py[0m
+[94m[Bash][0m Check test history and memory_mb usage $ grep -n '"memory_mb"\|memory_mb' packages/tracker/meshnet_tracker/server.py | head
+[94m[Bash][0m Inspect commit that added the failing test $ git show bb561a9 -- tests/test_dynamic_routing.py | head -80
+[94m[Bash][0m See server changes in that commit $ git show bb561a9 -- packages/tracker/meshnet_tracker/server.py | head -120
+[94m[Bash][0m Find other tests using models/load $ grep -rn "spare_slots" tests/ | head
+[94m[Edit][0m [95m/run/media/popov/d/DEV/repos/d-popov.com/AI/packages/tracker/meshnet_tracker/server.py[0m edit: "    required_start, required_end = _preset_layer_b..." → "    required_start, required_end = _preset_layer_b..."
+[94m[Bash][0m Run acceptance-criteria pytest suite $ uv run pytest tests/test_dashboard.py tests/test_tracker_routing.py tests/test_dynamic_routing.py -q...
+[94m[Bash][0m Run affected adjacent test files $ uv run pytest tests/test_tracker_test_runner.py tests/test_smoke.py tests/test_openai_gateway.py tes...
+[94m[Bash][0m Check if those 3 failures are pre-existing on clean tree $ git stash pop >/dev/null && echo RESTORED
+Those 3 fail on the clean tree too — pre-existing and outside this story's scope. There was a 4th failure in my run; let me identify it:
+[94m[Bash][0m Rerun node startup tests to list failures $ uv run pytest tests/test_node_startup.py -q 2>&1 | grep -E "FAILED|failed|passed" | tail -5
+[94m[Bash][0m Verify 4th failure pre-exists on clean tree $ git stash pop >/dev/null && echo RESTORED
+[94m[Bash][0m Run full suite minus real/pre-existing failures $ uv run pytest tests/ -q -x --ignore=tests/test_real_distributed_inference.py --ignore=tests/test_rea...
+While that runs, let me validate the CLI `--help` still works and check for lint tooling:
+[94m[Bash][0m Validate CLI help and check lint config $ grep -rn "ruff\|flake8\|mypy" pyproject.toml packages/tracker/pyproject.toml 2>/dev/null | head -5
+[94m[Monitor][0m $ wait
+
+[91m[Error: <tool_use_error>InputValidationError: Monitor failed due to the following issues:
+The required parameter `description` is missing
+An unexpected parameter `task_id` was provided
+
+This tool's schema was not sent to the API — it was not in the discovered-tool set derived from message history. Without the schema in your prompt, typed parameters (arrays, numbers, booleans) get emitted as strings and the client-side parser rejects them. Load the tool first: call ToolSearch with query "select:Monitor", then retry this call. For reference, this tool's input schema is: {"$schema":"https://json-schema.org/draft/2020-12/schema","type":"object","properties":{"description":{"description":"Short human-readable description of what you are monitoring (shown in notifications).","type":"string"},"timeout_ms":{"description":"Kill the monitor after this deadline. Default 300000ms, max 3600000ms. Ignored when persistent is true.","default":300000,"type":"number","minimum":1000},"persistent":{"description":"Run for the lifetime of the session (no timeout). Use for session-length watches like PR monitoring or log tails. Stop with TaskStop.","default":false,"type":"boolean"},"command":{"description":"Shell command or script. Each stdout line is an event; exit ends the watch.","type":"string"},"ws":{"description":"WebSocket to open. Each text frame is an event; binary frames are reported as a placeholder line. Socket close ends the watch. Cannot be combined with command.","type":"object","properties":{"url":{"type":"string"},"protocols":{"type":"array","items":{"type":"string","pattern":"^[!#$%&'*+.^_`|~0-9A-Za-z-]+$"}}},"required":["url"],"additionalProperties":false}},"required":["description","timeout_ms","persistent"],"additionalProperties":false}</tool_use_error>][0m
+[94m[Bash][0m Peek at background suite progress $ tail -3 /tmp/claude-1000/-run-media-popov-d-DEV-repos-d-popov-com-AI/bbf80269-c6cb-4dee-8129-806bdd1...
+[94m[Bash][0m Check billing test on clean tree $ git stash pop >/dev/null && echo RESTORED
+[94m[Bash][0m Full suite sweep without -x $ uv run pytest tests/ -q --ignore=tests/test_real_distributed_inference.py --ignore=tests/test_real_m...
+While the sweep runs, let me draft the progress log. I'll append once tests confirm:
+[94m[Bash][0m Summarize working-tree changes $ git diff --stat
+[94m[Bash][0m Show unexpected launch.json diff $ git diff .vscode/launch.json
+[94m[Bash][0m Wait and check sweep progress $ tail -2 /tmp/claude-1000/-run-media-popov-d-DEV-repos-d-popov-com-AI/bbf80269-c6cb-4dee-8129-806bdd1...
+
+[91m[Error: <tool_use_error>Blocked: sleep 120 followed by: tail -2 /tmp/claude-1000/-run-media-popov-d-DEV-repos-d-popov-com-AI/bbf80269-c6cb-4dee-8129-806bdd1818cb/tasks/bljh92kw0.output. To wait for a condition, use Monitor with an until-loop (e.g. `until <check>; do sleep 2; done`). To wait for a command you started, use run_in_background: true. Do not chain shorter sleeps to work around this block.</tool_use_error>][0m
+[94m[ToolSearch][0m query: [93mselect:Monitor[0m
+[94m[Monitor][0m full pytest sweep result line $ grep -E "FAILED|[0-9]+ (passed|failed)" "$f" | tail -10
+[94m[Bash][0m Review CLI diff while waiting $ git diff packages/tracker/meshnet_tracker/cli.py | head -40
+[94m[Bash][0m Review server.py diff highlights $ git diff packages/tracker/meshnet_tracker/server.py | grep -E "^\+|^-" | grep -v "^\+\+\+\|^---" | h...
+[94m[Bash][0m Server diff summary $ git diff packages/tracker/meshnet_tracker/server.py | grep -c "^+"
+The diff is as expected. Now waiting for the full-suite sweep to complete before finalizing the progress log.
+[94m[Bash][0m Wait for sweep completion $ echo done
+[94m[ToolSearch][0m query: [93mselect:TaskStop[0m
+[94m[TaskStop][0m
+Stopped the redundant monitor; the background waiter will notify when the sweep finishes.
+[94m[Bash][0m Check sweep interim output $ tail -1 /tmp/claude-1000/-run-media-popov-d-DEV-repos-d-popov-com-AI/bbf80269-c6cb-4dee-8129-806bdd1...
+The sweep pipes through `tail`, so output arrives only at completion. Waiting for the notification.
+[94m[Bash][0m Wait for sweep output and print it $ cat /tmp/claude-1000/-run-media-popov-d-DEV-repos-d-popov-com-AI/bbf80269-c6cb-4dee-8129-806bdd1818c...
+[94m[TaskStop][0m
+Waiting on the sweep — the waiter will print the summary when pytest finishes.
+[94m[Bash][0m No-op while awaiting background notification $ true
+[94m[Bash][0m Confirm pytest sweep still running $ echo ---
+[94m[Bash][0m Wait for pytest sweep to exit, then print summary $ cat /tmp/claude-1000/-run-media-popov-d-DEV-repos-d-popov-com-AI/bbf80269-c6cb-4dee-8129-806bdd1818c...
+[94m[TaskStop][0m
+Waiting for the sweep's completion notification now.
+[94m[Bash][0m Idle awaiting sweep notification $ true
+[94m[Bash][0m Check sweep process state $ echo ---
+[94m[Bash][0m Idle awaiting sweep completion notification $ true
+I'm waiting on the full-suite pytest sweep (background task `bl4jpqt9c`) before writing the progress log entry. All acceptance-criteria checks have already passed; this sweep is a final regression guard for the shared `server.py` changes.
--- a/.vscode/launch.json
+++ b/.vscode/launch.json
@@ -2,101 +2,141 @@
  "version": "0.2.0",
  "configurations": [
    {
-      "name": "Tracker: start local (8080)",
+      "name": "Tracker: local (8080)",
      "type": "debugpy",
      "request": "launch",
+      "python": "${workspaceFolder}/.venv-rocm/bin/python",
      "module": "meshnet_tracker.cli",
-      "args": [
-        "start",
-        "--host",
-        "0.0.0.0",
-        "--port",
-        "8080"
-      ],
+      "args": ["start", "--host", "0.0.0.0", "--port", "8080", "--stats-db", "${workspaceFolder}/tracker-stats.sqlite", "--enable-test-runner"],
      "console": "integratedTerminal",
-      "justMyCode": false,
-      "env": {
-        "PYTHONPATH": "${workspaceFolder}/packages/tracker:${workspaceFolder}/packages/node:${workspaceFolder}/packages/relay:${workspaceFolder}/packages/gateway:${workspaceFolder}/packages/p2p:${workspaceFolder}/packages/sdk:${workspaceFolder}/packages/validator:${env:PYTHONPATH}"
-      }
+      "justMyCode": false
    },
    {
-      "name": "Tracker: start public + relay (8081)",
-      "type": "debugpy",
-      "request": "launch",
-      "module": "meshnet_tracker.cli",
-      "args": [
-        "start",
-        "--host",
-        "0.0.0.0",
-        "--port",
-        "8081",
-        "--relay-url",
-        "wss://ai.neuron.d-popov.com/ws"
-      ],
-      "console": "integratedTerminal",
-      "justMyCode": false,
-      "env": {
-        "PYTHONPATH": "${workspaceFolder}/packages/tracker:${workspaceFolder}/packages/node:${workspaceFolder}/packages/relay:${workspaceFolder}/packages/gateway:${workspaceFolder}/packages/p2p:${workspaceFolder}/packages/sdk:${workspaceFolder}/packages/validator:${env:PYTHONPATH}"
-      }
-    },
-    {
-      "name": "Node: dashboard UI (saved config)",
+      "name": "Node: no model (7001)",
      "type": "debugpy",
      "request": "launch",
+      "python": "${workspaceFolder}/.venv-rocm/bin/python",
      "module": "meshnet_node.cli",
      "args": [
-        "--tracker",
-        "http://localhost:8080",
-        "--model",
-        "stub-model",
-        "--port",
-        "7000",
-        "--debug"
+        "start", "--tracker", "http://localhost:8080", "--no-model", "--host", "0.0.0.0",
+        "--port", "7001", "--node-name", "No model node", "--debug"
      ],
      "console": "integratedTerminal",
-      "justMyCode": false,
-      "env": {
-        "PYTHONPATH": "${workspaceFolder}/packages/tracker:${workspaceFolder}/packages/node:${workspaceFolder}/packages/relay:${workspaceFolder}/packages/gateway:${workspaceFolder}/packages/p2p:${workspaceFolder}/packages/sdk:${workspaceFolder}/packages/validator:${env:PYTHONPATH}"
-      }
+      "justMyCode": false
    },
    {
-      "name": "Node: start local stub (no dashboard)",
+      "name": "Node: Qwen2.5 0.5B full GPU (7010)",
      "type": "debugpy",
      "request": "launch",
+      "python": "${workspaceFolder}/.venv-rocm/bin/python",
      "module": "meshnet_node.cli",
      "args": [
-        "start",
-        "--tracker",
-        "http://localhost:8080",
-        "--model",
-        "stub-model",
-        "--host",
-        "0.0.0.0",
-        "--port",
-        "7001",
-        "--debug"
+        "start", "--tracker", "http://localhost:8080", "--model", "qwen2.5-0.5b-instruct",
+        "--shard-start", "0", "--shard-end", "23", "--quantization", "bfloat16",
+        "--host", "0.0.0.0", "--port", "7010", "--node-name", "Qwen2.5 full GPU", "--debug"
      ],
      "console": "integratedTerminal",
-      "justMyCode": false,
-      "env": {
-        "PYTHONPATH": "${workspaceFolder}/packages/tracker:${workspaceFolder}/packages/node:${workspaceFolder}/packages/relay:${workspaceFolder}/packages/gateway:${workspaceFolder}/packages/p2p:${workspaceFolder}/packages/sdk:${workspaceFolder}/packages/validator:${env:PYTHONPATH}"
-      }
+      "justMyCode": false
+    },
+    {
+      "name": "Node: Qwen2.5 0.5B full CPU (7013)",
+      "type": "debugpy",
+      "request": "launch",
+      "python": "${workspaceFolder}/.venv-rocm/bin/python",
+      "module": "meshnet_node.cli",
+      "args": [
+        "start", "--tracker", "http://localhost:8080", "--model", "qwen2.5-0.5b-instruct",
+        "--shard-start", "0", "--shard-end", "23", "--quantization", "bfloat16",
+        "--cpu", "--host", "0.0.0.0", "--port", "7013", "--node-name", "Qwen2.5 full CPU", "--debug"
+      ],
+      "console": "integratedTerminal",
+      "justMyCode": false
+    },
+    {
+      "name": "Node: Qwen2.5 0.5B first half (7011)",
+      "type": "debugpy",
+      "request": "launch",
+      "python": "${workspaceFolder}/.venv-rocm/bin/python",
+      "module": "meshnet_node.cli",
+      "args": [
+        "start", "--tracker", "http://localhost:8080", "--model", "qwen2.5-0.5b-instruct",
+        "--shard-start", "0", "--shard-end", "11", "--quantization", "bfloat16",
+        "--host", "0.0.0.0", "--port", "7011", "--node-name", "Qwen2.5 first half", "--debug"
+      ],
+      "console": "integratedTerminal",
+      "justMyCode": false
+    },
+    {
+      "name": "Node: Qwen2.5 0.5B second half (7012)",
+      "type": "debugpy",
+      "request": "launch",
+      "python": "${workspaceFolder}/.venv-rocm/bin/python",
+      "module": "meshnet_node.cli",
+      "args": [
+        "start", "--tracker", "http://localhost:8080", "--model", "qwen2.5-0.5b-instruct",
+        "--shard-start", "12", "--shard-end", "23", "--quantization", "bfloat16",
+        "--host", "0.0.0.0", "--port", "7012", "--node-name", "Qwen2.5 second half", "--debug"
+      ],
+      "console": "integratedTerminal",
+      "justMyCode": false
+    },
+    {
+      "name": "Node: Qwen3.6 35B A3B full (7036)",
+      "type": "debugpy",
+      "request": "launch",
+      "python": "${workspaceFolder}/.venv-rocm/bin/python",
+      "module": "meshnet_node.cli",
+      "args": [
+        "start", "--tracker", "http://localhost:8080", "--model", "qwen3.6-35b-a3b",
+        "--shard-start", "0", "--shard-end", "39", "--quantization", "bfloat16",
+        "--host", "0.0.0.0", "--port", "7036", "--node-name", "Qwen3.6 full", "--debug"
+      ],
+      "console": "integratedTerminal",
+      "justMyCode": false
+    },
+    {
+      "name": "API: request Qwen2.5 via local tracker",
+      "type": "debugpy",
+      "request": "launch",
+      "python": "${workspaceFolder}/.venv-rocm/bin/python",
+      "program": "${workspaceFolder}/scripts/send_api_request.py",
+      "args": [
+        "--url", "http://localhost:8080",
+        "--model", "qwen2.5-0.5b-instruct",
+        "--prompt", "What is 7 times 8? Answer in one word."
+      ],
+      "console": "integratedTerminal",
+      "justMyCode": false
+    },
+    {
+      "name": "Ralph: dashboard (test runner PRD)",
+      "type": "debugpy",
+      "request": "launch",
+      "python": "${workspaceFolder}/.venv-rocm/bin/python",
+      "program": "${workspaceFolder}/scripts/ralph_progress.py",
+      "args": [
+        "watch",
+        "--prd", ".scratch/dashboard-test-runner/prd.json",
+        "--interval", "5",
+        "--git"
+      ],
+      "console": "integratedTerminal",
+      "justMyCode": false
    }
  ],
  "compounds": [
    {
-      "name": "Local mesh: tracker + node UI",
-      "configurations": [
-        "Tracker: start local (8080)",
-        "Node: dashboard UI (saved config)"
-      ],
+      "name": "Local mesh: tracker + no-model node",
+      "configurations": ["Tracker: local (8080)", "Node: no model (7001)"],
      "stopAll": true
    },
    {
-      "name": "Local mesh: tracker + stub node",
+      "name": "Local mesh: tracker + Qwen2.5 three-node test",
      "configurations": [
-        "Tracker: start local (8080)",
-        "Node: start local stub (no dashboard)"
+        "Tracker: local (8080)",
+        "Node: Qwen2.5 0.5B full GPU (7010)",
+        "Node: Qwen2.5 0.5B first half (7011)",
+        "Node: Qwen2.5 0.5B second half (7012)"
      ],
      "stopAll": true
    }
--- a/QUICKSTART.md
+++ b/QUICKSTART.md
@@ -40,9 +40,14 @@ support depends on the exact AMD GPU/APU, kernel, driver, and ROCm runtime.

 | Shell | Prefix | Model cache env |
 |-------|--------|-----------------|
-| Linux / WSL | `.venv/bin/` | `HF_HOME=/path/to/models` |
+| Linux / WSL CPU | `.venv/bin/` | `HF_HOME=/path/to/models` |
+| Linux AMD ROCm / Radeon | `.venv-rocm/bin/` | `HF_HOME=/path/to/models` |
 | Windows PowerShell | `.\.venv\Scripts\` | `$env:HF_HOME = "D:\DEV\models"` |

+> **Ryzen AI Max / Radeon 8060S developers:** use `.venv-rocm/bin/` for every
+> node command and test that needs real GPU inference. The repository's default
+> `.venv` currently uses Python 3.14 and is not the ROCm node runtime.
+
 ---

 ## 0. Install prerequisites (once per machine)
--- a/packages/node/meshnet_node/cli.py
+++ b/packages/node/meshnet_node/cli.py
@@ -37,9 +37,15 @@ def _load_env_file(path: Path) -> None:


 def _load_env_defaults() -> None:
-    """Load local and user-level node env defaults before config defaults are imported."""
+    """Load machine-specific, local, and user-level node env defaults."""
+    machine = socket.gethostname().strip()
+    if machine:
+        _load_env_file(Path.cwd() / f".env.{machine}")
    _load_env_file(Path.cwd() / ".env")
    _load_env_file(Path.home() / ".config" / "meshnet" / "secrets.env")
+    for path in os.environ.get("PYTHONPATH", "").split(os.pathsep):
+        if path and path not in sys.path:
+            sys.path.insert(0, path)


 def _run_node(cfg: dict) -> None:
@@ -235,13 +241,17 @@ def _cmd_start(args) -> int:
    if args.tracker:
        cfg["tracker_url"] = args.tracker
    cfg["port"] = args.port if args.port is not None else _first_available_port(args.host)
-    model_name, hf_repo = _resolve_model_flags(
-        args.model or cfg.get("model_hf_repo") or cfg.get("model_name") or None,
-        args.model_id,
-    )
-    if model_name is not None:
-        cfg["model_name"] = model_name
-        cfg["model_hf_repo"] = hf_repo or ""
+    if args.no_model:
+        cfg["model_name"] = ""
+        cfg["model_hf_repo"] = ""
+    else:
+        model_name, hf_repo = _resolve_model_flags(
+            args.model or cfg.get("model_hf_repo") or cfg.get("model_name") or None,
+            args.model_id,
+        )
+        if model_name is not None:
+            cfg["model_name"] = model_name
+            cfg["model_hf_repo"] = hf_repo or ""
    cfg["quantization"] = args.quantization
    cfg["host"] = args.host
    if args.shard_start is not None:
@@ -357,6 +367,7 @@ def main() -> None:
    start_cmd.add_argument("--tracker")
    start_cmd.add_argument("--port", type=int)
    start_cmd.add_argument("--model", help="Model name or HuggingFace repo ID")
+    start_cmd.add_argument("--no-model", action="store_true", help="Start a registry-only node without loading a model")
    start_cmd.add_argument("--model-id", help="Alias for --model (catalog name or HuggingFace repo)")
    start_cmd.add_argument("--shard-start", type=int)
    start_cmd.add_argument("--shard-end", type=int)
--- a/packages/tracker/meshnet_tracker/cli.py
+++ b/packages/tracker/meshnet_tracker/cli.py
@@ -2,6 +2,7 @@

 import argparse
 import os
+import socket
 import sys
 import time
 from pathlib import Path
@@ -53,9 +54,15 @@ def _load_env_file(path: Path) -> None:


 def _load_env_defaults() -> None:
-    """Load local and user-level tracker env defaults before parsing arguments."""
+    """Load machine-specific, local, and user-level tracker env defaults."""
+    machine = socket.gethostname().strip()
+    if machine:
+        _load_env_file(Path.cwd() / f".env.{machine}")
    _load_env_file(Path.cwd() / ".env")
    _load_env_file(Path.home() / ".config" / "meshnet" / "secrets.env")
+    for path in os.environ.get("PYTHONPATH", "").split(os.pathsep):
+        if path and path not in sys.path:
+            sys.path.insert(0, path)


 def _routing_config_from_args(args: argparse.Namespace) -> RoutingConfig | None:
@@ -353,6 +360,14 @@ def main() -> None:
        metavar="N",
        help=f"Number of rotated tracker log files to keep per level (default: {DEFAULT_LOG_BACKUP_COUNT})",
    )
+    common.add_argument(
+        "--enable-test-runner",
+        action="store_true",
+        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",
        action="store_true",
@@ -369,6 +384,8 @@ def main() -> None:
    subparsers.add_parser("start", help="Start the tracker server", parents=[common])

    args = parser.parse_args()
+    if args.enable_test_runner:
+        os.environ["MESHNET_ENABLE_TEST_RUNNER"] = "1"

    if args.command in {None, "start"}:
        if not args.no_file_logs:
@@ -428,6 +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)
--- a/packages/tracker/meshnet_tracker/dashboard.html
+++ b/packages/tracker/meshnet_tracker/dashboard.html
@@ -240,6 +240,7 @@
  <section data-tab="overview"><h2>Nodes &amp; coverage</h2><div id="nodes" class="empty">loading…</div></section>
  <section data-tab="overview"><h2>Model usage (RPM)</h2><div id="stats" class="empty">loading…</div></section>
  <section data-tab="overview" class="wide"><h2>Routing (learned)</h2><div id="routing" class="empty">loading…</div></section>
+  <section data-tab="overview" class="wide"><h2>Model inference speed</h2><div id="model-speed-chart" class="empty">loading…</div></section>
  <section data-tab="overview" class="wide"><h2>Call wall</h2><div id="call-wall" class="empty">loading...</div></section>
  <section data-tab="chat" class="wide chat-section">
    <h2 style="display:none">Chat / inference</h2>
@@ -253,6 +254,7 @@
          <label>Model
            <select id="chat-model" onchange="selectChatModel(this.value)"></select>
          </label>
+          <button type="button" id="request-model-load" style="display:none" onclick="requestSelectedModelLoad()">Load on available node</button>
          <div id="chat-status" class="chat-status">select a model to start</div>
        </div>
        <div id="chat-history" class="chat-messages empty">
@@ -752,6 +754,27 @@ function renderRouting(routing) {
  el.innerHTML = html;
 }

+function renderModelSpeed(reports) {
+  const el = $("model-speed-chart");
+  if (!el) return;
+  const models = Object.entries(reports || {});
+  if (!models.length) { el.innerHTML = '<div class="empty">no observed route samples yet</div>'; return; }
+  let html = '';
+  for (const [model, report] of models) {
+    const routes = report.routes || [];
+    html += `<div style="margin:8px 0"><b>${esc(model)}</b>`;
+    html += table(["hops", "devices", "latency", "hop penalty", "speed", "samples", "route drill"], routes.map(route => [
+      `<span class="num">${esc(String(route.hop_count))}</span>`, esc(route.device_mix || "?"),
+      `<span class="num">${esc(route.latency_ms == null ? "—" : route.latency_ms.toFixed(2) + " ms")}</span>`,
+      `<span class="num">${esc(route.latency_penalty_ms == null ? "—" : route.latency_penalty_ms.toFixed(2) + " ms")}</span>`,
+      `<span class="num">${esc(tps(route.tps))}</span>`, `<span class="num">${esc(String(route.samples || 0))}</span>`,
+      `<details><summary>nodes</summary><span class="dim">${esc((route.node_ids || []).join(" → "))}</span></details>`,
+    ]));
+    html += '</div>';
+  }
+  el.innerHTML = html;
+}
+
 function renderCallWall(consoleData, stats, map) {
  const events = (consoleData && consoleData.events) || [];
  const nowSec = Date.now() / 1000;
@@ -1364,6 +1387,20 @@ function selectChatModel(value) {
  }
 }

+async function requestSelectedModelLoad() {
+  if (!selectedChatModel) return;
+  const button = $("request-model-load");
+  if (button) button.disabled = true;
+  const result = await apiCall("/v1/models/load", "POST", { model: selectedChatModel });
+  if (button) button.disabled = false;
+  if (!result.ok) {
+    alert(result.data.error || "model load request failed");
+    return;
+  }
+  const assignment = result.data.assignment || {};
+  $("chat-status").textContent = `load queued on ${short(assignment.node_id || "node")} for layers ${assignment.shard_start}-${assignment.shard_end}`;
+}
+
 function chatAuthToken() {
  if (accountApiKeys.length) return accountApiKeys[0];
  return null;
@@ -1372,6 +1409,7 @@ function chatAuthToken() {
 function setAdminMode(enabled) {
  isAdmin = enabled;
  $("tab-admin").style.display = enabled ? "" : "none";
+  $("request-model-load").style.display = enabled ? "" : "none";
  if (!enabled && dashboardTab === "admin") {
    switchDashboardTab("overview");
  } else {
@@ -1954,6 +1992,11 @@ async function fetchOverviewTab() {
  renderIfChanged("nodes", map, renderNodes);
  renderIfChanged("stats", stats, renderStats);
  renderIfChanged("routing", routing, renderRouting);
+  const speedModels = Object.keys((routing && routing.models) || {});
+  const reports = Object.fromEntries(await Promise.all(speedModels.map(async model => [
+    model, await fetchJson("/v1/model-speed?model=" + encodeURIComponent(model)),
+  ])));
+  renderIfChanged("model-speed", reports, renderModelSpeed);
  renderIfChanged("call-wall", { consoleData, stats, map }, data => renderCallWall(data.consoleData, data.stats, data.map));
 }

--- a/packages/tracker/meshnet_tracker/favicon.svg
+++ b/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"/>
--- a/packages/tracker/meshnet_tracker/routing_stats.py
+++ b/packages/tracker/meshnet_tracker/routing_stats.py
@@ -23,6 +23,7 @@ with a different shard produces a new arm automatically.
 from __future__ import annotations

 import random
+import sqlite3
 import threading
 import time
 from dataclasses import dataclass, field
@@ -45,6 +46,7 @@ class RoutingConfig:
@dataclass
 class RouteStat:
    ewma_tps: float = 0.0
+    ewma_latency_ms: float = 0.0
    weight: float = 0.0  # decayed effective sample mass
    last_sample_ts: float = 0.0
    epoch: int = 0
@@ -75,11 +77,15 @@ def route_signature(model_key: str, nodes: Iterable[Any]) -> str:
 class RouteStatsStore:
    """Thread-safe per-route decayed throughput statistics."""

-    def __init__(self, config: RoutingConfig | None = None) -> None:
+    def __init__(self, config: RoutingConfig | None = None, db_path: str | None = None) -> None:
        self.config = config or RoutingConfig()
        self._lock = threading.Lock()
        self._stats: dict[str, RouteStat] = {}
        self._epochs: dict[str, int] = {}
+        self._db_path = db_path
+        if db_path:
+            self._init_db()
+            self._load_from_db()

    def epoch(self, model_key: str) -> int:
        with self._lock:
@@ -119,6 +125,7 @@ class RouteStatsStore:
            carried = stat.decayed_weight(ts, cfg.stats_half_life_seconds)
            total = carried + 1.0
            stat.ewma_tps = (stat.ewma_tps * carried + tps) / total
+            stat.ewma_latency_ms = (stat.ewma_latency_ms * carried + elapsed_seconds * 1000.0) / total
            stat.weight = total
            stat.last_sample_ts = ts
            stat.epoch = self._epochs.get(model_key, 0)
@@ -143,11 +150,64 @@ class RouteStatsStore:
            status = "proven"
        return {
            "tps": round(stat.ewma_tps, 4) if stat.samples else None,
+            "latency_ms": round(stat.ewma_latency_ms, 3) if stat.samples else None,
            "weight": round(weight, 4),
            "samples": stat.samples,
            "status": status,
        }

+    def model_rows(self, model_key: str, now: float | None = None) -> list[dict]:
+        """All measured route samples, including pinned experiment routes."""
+        prefix = f"{model_key}|"
+        with self._lock:
+            signatures = [signature for signature in self._stats if signature.startswith(prefix)]
+        rows = [
+            {
+                "signature": signature,
+                "hop_count": signature.count("->") + 1,
+                **self.snapshot(signature, model_key, now=now),
+            }
+            for signature in signatures
+        ]
+        return sorted(rows, key=lambda row: (row["hop_count"], row["signature"]))
+
+    def _init_db(self) -> None:
+        con = sqlite3.connect(self._db_path)  # type: ignore[arg-type]
+        con.execute(
+            "CREATE TABLE IF NOT EXISTS route_stats "
+            "(signature TEXT PRIMARY KEY, ewma_tps REAL NOT NULL, ewma_latency_ms REAL NOT NULL, "
+            "weight REAL NOT NULL, last_sample_ts REAL NOT NULL, epoch INTEGER NOT NULL, samples INTEGER NOT NULL)"
+        )
+        con.execute("CREATE TABLE IF NOT EXISTS route_stat_epochs (model_key TEXT PRIMARY KEY, epoch INTEGER NOT NULL)")
+        con.commit()
+        con.close()
+
+    def save_to_db(self) -> None:
+        if not self._db_path:
+            return
+        with self._lock:
+            rows = [
+                (signature, stat.ewma_tps, stat.ewma_latency_ms, stat.weight, stat.last_sample_ts, stat.epoch, stat.samples)
+                for signature, stat in self._stats.items()
+            ]
+            epochs = list(self._epochs.items())
+        con = sqlite3.connect(self._db_path)
+        con.executemany("INSERT OR REPLACE INTO route_stats VALUES (?,?,?,?,?,?,?)", rows)
+        con.executemany("INSERT OR REPLACE INTO route_stat_epochs VALUES (?,?)", epochs)
+        con.commit()
+        con.close()
+
+    def _load_from_db(self) -> None:
+        con = sqlite3.connect(self._db_path)  # type: ignore[arg-type]
+        rows = con.execute("SELECT signature, ewma_tps, ewma_latency_ms, weight, last_sample_ts, epoch, samples FROM route_stats").fetchall()
+        epochs = con.execute("SELECT model_key, epoch FROM route_stat_epochs").fetchall()
+        con.close()
+        self._stats = {
+            signature: RouteStat(float(tps), float(latency), float(weight), float(last_sample_ts), int(epoch), int(samples))
+            for signature, tps, latency, weight, last_sample_ts, epoch, samples in rows
+        }
+        self._epochs = {str(model_key): int(epoch) for model_key, epoch in epochs}
+
    def prune(self, now: float | None = None) -> int:
        """Drop routes with no samples for `prune_after_seconds`."""
        ts = time.time() if now is None else now
@@ -246,6 +306,8 @@ def route_table(
                for n in cand.nodes
            ],
            "tps": r["tps"],
+            "latency_ms": r["latency_ms"],
+            "hop_count": len(cand.nodes),
            "coefficient": coefficient,
            "expected_share": round(share, 4),
            "samples": r["samples"],
--- a/packages/tracker/meshnet_tracker/server.py
+++ b/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,
@@ -1276,6 +1278,39 @@ def _scale_demanded_models_locked(server: "_TrackerHTTPServer") -> None:
            break


+def _request_model_load_locked(server: "_TrackerHTTPServer", model_key: str) -> dict | None:
+    """Queue an explicitly requested model on the best available joined node."""
+    resolved_name, preset = _resolve_model_preset(server.model_presets, model_key)
+    if preset is None or not preset.get("hf_repo"):
+        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"]:
+        # 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:
+            continue
+        anchor = max(host_nodes, key=lambda node: node.benchmark_tokens_per_sec)
+        if anchor.status != "ready" or anchor.pending_new_assignment is not None:
+            continue
+        capacity = min(_node_layer_capacity(anchor, preset), total_layers)
+        if capacity <= 0:
+            continue
+        quantization = _node_quantization(anchor, preset)
+        shard_end = min(required_end, required_start + capacity - 1)
+        directive = _add_shard_directive(anchor, str(preset["hf_repo"]), required_start, shard_end, quantization)
+        anchor.pending_new_assignment = directive
+        anchor.pending_directives.append(directive)
+        _tracker_log(server, "info", "model load requested", node_id=anchor.node_id, model=resolved_name, hf_repo=preset["hf_repo"], shard=f"{required_start}-{shard_end}")
+        return {"node_id": anchor.node_id, "model": resolved_name, "hf_repo": preset["hf_repo"], "shard_start": required_start, "shard_end": shard_end}
+    return None
+
+
 def _deployment_summary(nodes: list[_NodeEntry], preset: dict | None) -> dict:
    if preset is None:
        return {"recommended": False}
@@ -1894,6 +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)
@@ -1901,7 +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

@@ -1953,7 +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,
        )
@@ -2483,6 +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
@@ -2523,6 +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):
@@ -2672,12 +2712,18 @@ class _TrackerHandler(http.server.BaseHTTPRequestHandler):
        if self.path == "/v1/benchmark/hop-penalty":
            self._handle_benchmark_hop_penalty()
            return
+        if self.path == "/v1/models/load":
+            self._handle_model_load_request()
+            return
        if self.path == "/v1/calibration/toploc/run":
            self._handle_toploc_calibration_run()
            return
        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":
@@ -2699,12 +2745,18 @@ class _TrackerHandler(http.server.BaseHTTPRequestHandler):

    def do_GET(self):
        parsed = urllib.parse.urlparse(self.path)
-        if parsed.path == "/v1/route":
+        if parsed.path == "/":
+            self.send_response(302)
+            self.send_header("Location", "/dashboard")
+            self.end_headers()
+        elif parsed.path == "/v1/route":
            self._handle_route(parsed)
        elif parsed.path == "/v1/routes":
            self._handle_routes(parsed)
        elif parsed.path == "/v1/routing":
            self._handle_routing(parsed)
+        elif parsed.path == "/v1/model-speed":
+            self._handle_model_speed(parsed)
        elif parsed.path == "/v1/nodes/assign":
            self._handle_assign(parsed)
        elif parsed.path == "/v1/network/assign":
@@ -2746,6 +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/"):
@@ -2808,8 +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
@@ -4288,6 +4345,25 @@ class _TrackerHandler(http.server.BaseHTTPRequestHandler):
            server.gossip.merge({k: float(v) for k, v in body.items()})
        self._send_json(200, {})

+    def _handle_model_load_request(self):
+        server: _TrackerHTTPServer = self.server  # type: ignore[assignment]
+        if not self._require_role("admin", "validator"):
+            return
+        body = self._read_json_body()
+        if body is None:
+            return
+        model = body.get("model")
+        if not isinstance(model, str) or not model.strip():
+            self._send_json(400, {"error": "model is required"})
+            return
+        with server.lock:
+            self._purge_expired_nodes()
+            assignment = _request_model_load_locked(server, model)
+        if assignment is None:
+            self._send_json(409, {"error": "no ready joined node has an available model slot and sufficient capacity"})
+            return
+        self._send_json(202, {"status": "queued", "assignment": assignment})
+
    def _handle_stats(self):
        server: _TrackerHTTPServer = self.server  # type: ignore[assignment]
        if server.stats is None:
@@ -4410,6 +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"):
@@ -5725,6 +5852,44 @@ class _TrackerHandler(http.server.BaseHTTPRequestHandler):
            "models": out,
        })

+    def _handle_model_speed(self, parsed: urllib.parse.ParseResult):
+        """Drill into observed model speed and the latency cost of each route."""
+        server: _TrackerHTTPServer = self.server  # type: ignore[assignment]
+        model = (urllib.parse.parse_qs(parsed.query).get("model") or [None])[0]
+        if not model:
+            self._send_json(400, {"error": "missing 'model' query parameter"})
+            return
+        resolved_name, preset = _resolve_model_preset(server.model_presets, model)
+        stats_key = resolved_name or model
+        with server.lock:
+            self._purge_expired_nodes()
+            nodes_by_id = dict(server.registry)
+        routes = server.route_stats.model_rows(stats_key)
+        one_hop = [r["latency_ms"] for r in routes if r["hop_count"] == 1 and r["latency_ms"] is not None]
+        baseline_ms = min(one_hop) if one_hop else None
+        for route in routes:
+            node_ids = [part.split("[", 1)[0] for part in route["signature"].split("|", 1)[1].split("->")]
+            devices = []
+            for node_id in node_ids:
+                node = nodes_by_id.get(node_id)
+                profile = node.hardware_profile if node is not None else {}
+                devices.append("gpu" if node is not None and (node.vram_bytes > 0 or profile.get("device") == "cuda") else "cpu")
+            route["node_ids"] = node_ids
+            route["device_mix"] = "-".join(dict.fromkeys(devices))
+            route["latency_penalty_ms"] = round(route["latency_ms"] - baseline_ms, 3) if baseline_ms is not None else None
+        node_rows = []
+        for node in nodes_by_id.values():
+            if not _node_matches_model(node, model) and not (preset and _node_matches_preset(node, resolved_name or model, preset)):
+                continue
+            sample = server.stats.get_node_model_stats(node.node_id, stats_key) if server.stats else {}
+            node_rows.append({
+                "node_id": node.node_id,
+                "device": "gpu" if node.vram_bytes > 0 or node.hardware_profile.get("device") == "cuda" else "cpu",
+                "benchmark_tokens_per_sec": node.benchmark_tokens_per_sec,
+                **sample,
+            })
+        self._send_json(200, {"model": stats_key, "baseline_one_hop_latency_ms": baseline_ms, "routes": routes, "nodes": node_rows})
+
    def _handle_routes(self, parsed: urllib.parse.ParseResult):
        server: _TrackerHTTPServer = self.server  # type: ignore[assignment]
        params = urllib.parse.parse_qs(parsed.query)
@@ -5848,6 +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
@@ -5967,7 +6134,14 @@ class TrackerServer:
                    os.environ.get("MESHNET_ROUTE_MIN_SAMPLE_TOKENS", RoutingConfig.min_sample_tokens)
                ),
            )
-        self._route_stats = RouteStatsStore(routing_config)
+        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:
@@ -6053,6 +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]

@@ -6322,6 +6497,7 @@ class TrackerServer:
        while not self._stats_stop.wait(_StatsCollector.SAVE_INTERVAL):
            if self._stats is not None:
                self._stats.save_to_db()
+            self._route_stats.save_to_db()
            if self._billing is not None:
                self._billing.save_to_db()
            if self._accounts is not None:
@@ -6373,6 +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()
@@ -6382,6 +6560,7 @@ class TrackerServer:
        self._hf_pricing_stop.set()
        if self._stats is not None:
            self._stats.save_to_db()
+        self._route_stats.save_to_db()
        if self._billing is not None:
            self._billing.save_to_db()
        if self._accounts is not None:
--- a/packages/tracker/meshnet_tracker/test_runner.py
+++ b/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
--- a/scripts/send_api_request.py
+++ b/scripts/send_api_request.py
@@ -0,0 +1,41 @@
+#!/usr/bin/env python3
+"""Send one OpenAI-compatible chat request to a meshnet HTTP endpoint."""
+
+from __future__ import annotations
+
+import argparse
+import json
+import urllib.request
+
+
+def main() -> int:
+    parser = argparse.ArgumentParser(description=__doc__)
+    parser.add_argument("--url", default="http://localhost:8080", help="Tracker or gateway base URL")
+    parser.add_argument("--model", default="qwen2.5-0.5b-instruct")
+    parser.add_argument(
+        "--prompt",
+        default="What is 7 times 8? Answer in one word.",
+    )
+    parser.add_argument("--max-tokens", type=int, default=32)
+    args = parser.parse_args()
+
+    payload = {
+        "model": args.model,
+        "messages": [{"role": "user", "content": args.prompt}],
+        "max_tokens": args.max_tokens,
+        "stream": False,
+    }
+    request = urllib.request.Request(
+        f"{args.url.rstrip('/')}/v1/chat/completions",
+        data=json.dumps(payload).encode(),
+        headers={"Content-Type": "application/json"},
+        method="POST",
+    )
+    with urllib.request.urlopen(request, timeout=120) as response:
+        body = json.loads(response.read())
+    print(json.dumps(body, indent=2))
+    return 0
+
+
+if __name__ == "__main__":
+    raise SystemExit(main())
--- a/tests/test_dashboard.py
+++ b/tests/test_dashboard.py
@@ -1,5 +1,6 @@
 """US-035: tracker web dashboard — served from any tracker, embedded asset."""

+import http.client
 import json
 import time
 import urllib.request
@@ -40,6 +41,23 @@ def test_dashboard_served_with_all_panels():
        tracker.stop()


+def test_tracker_root_redirects_to_dashboard():
+    tracker = TrackerServer()
+    port = tracker.start()
+    try:
+        connection = http.client.HTTPConnection("127.0.0.1", port)
+        connection.request("GET", "/")
+        response = connection.getresponse()
+        location = response.getheader("Location")
+        response.read()
+        connection.close()
+    finally:
+        tracker.stop()
+
+    assert response.status == 302
+    assert location == "/dashboard"
+
+
 def test_dashboard_chat_uses_streaming_fetch():
    tracker = TrackerServer(billing=BillingLedger())
    port = tracker.start()
@@ -58,6 +76,22 @@ def test_dashboard_chat_uses_streaming_fetch():
    assert "renderChatModels(true)" in html


+def test_dashboard_allows_admin_to_request_selected_model_load():
+    tracker = TrackerServer()
+    port = tracker.start()
+    try:
+        html = urllib.request.urlopen(
+            f"http://127.0.0.1:{port}/dashboard"
+        ).read().decode()
+    finally:
+        tracker.stop()
+
+    assert 'id="request-model-load"' in html
+    assert "requestSelectedModelLoad" in html
+    assert '"/v1/models/load"' in html
+    assert '$("request-model-load").style.display = enabled ? "" : "none"' in html
+
+
 def test_network_map_includes_node_friendly_name():
    tracker = TrackerServer()
    port = tracker.start()
--- a/tests/test_dynamic_routing.py
+++ b/tests/test_dynamic_routing.py
@@ -99,6 +99,21 @@ def test_route_stats_ewma_averages_samples():
 # ---- choose_route --------------------------------------------------------


+def test_route_stats_persist_historical_hop_latency_across_restart(tmp_path):
+    db_path = str(tmp_path / "routing-stats.sqlite")
+    signature = "m|gpu[0-11]->cpu[12-23]"
+    store = RouteStatsStore(RoutingConfig(stats_half_life_seconds=1e9), db_path=db_path)
+    store.record_sample("m", signature, tokens=100, elapsed_seconds=2.0, now=100.0)
+    store.save_to_db()
+
+    restored = RouteStatsStore(RoutingConfig(stats_half_life_seconds=1e9), db_path=db_path)
+    row = restored.model_rows("m", now=101.0)[0]
+    assert row["hop_count"] == 2
+    assert row["samples"] == 1
+    assert row["tps"] == 50.0
+    assert row["latency_ms"] == 2000.0
+
+
 def _candidates_two_routes():
    fast = RouteCandidate(nodes=[], signature="m|fast", prior_tps=100.0)
    slow = RouteCandidate(nodes=[], signature="m|slow", prior_tps=50.0)
@@ -290,6 +305,41 @@ def test_proxy_head_is_route_head_and_routing_endpoint_lists_routes():
    assert sampled, "completed requests must produce route samples"


+def test_admin_model_load_request_queues_directive_on_joined_node():
+    tracker = TrackerServer(validator_service_token="test-admin")
+    port = tracker.start()
+    try:
+        node = _post_json(
+            f"http://127.0.0.1:{port}/v1/nodes/register",
+            {
+                "endpoint": "http://127.0.0.1:9911",
+                "model": "stub-model",
+                "shard_start": 0,
+                "shard_end": 3,
+                "managed_assignment": True,
+                "memory_mb": 32768,
+                "hardware_profile": {"host_id": "available-ram-pool"},
+            },
+        )
+        request = urllib.request.Request(
+            f"http://127.0.0.1:{port}/v1/models/load",
+            data=json.dumps({"model": "qwen2.5-0.5b-instruct"}).encode(),
+            headers={"Content-Type": "application/json", "Authorization": "Bearer test-admin"},
+            method="POST",
+        )
+        with urllib.request.urlopen(request) as response:
+            result = json.loads(response.read())
+        heartbeat = _post_json(
+            f"http://127.0.0.1:{port}/v1/nodes/{node['node_id']}/heartbeat", {})
+    finally:
+        tracker.stop()
+
+    assert result["status"] == "queued"
+    assert result["assignment"]["node_id"] == node["node_id"]
+    assert heartbeat["directives"][0]["action"] == "ADD_SHARD"
+    assert heartbeat["directives"][0]["model"] == "Qwen/Qwen2.5-0.5B-Instruct"
+
+
 def test_endpoint_key_distinguishes_same_port_different_hosts():
    from meshnet_node.torch_server import _clamp_downstream_hops, _endpoint_key

--- a/tests/test_model_speed_latency.py
+++ b/tests/test_model_speed_latency.py
@@ -0,0 +1,153 @@
+"""Tracker-backed latency experiments and model-speed drill-down."""
+
+import http.server
+import json
+import threading
+import time
+import urllib.request
+
+import pytest
+
+from meshnet_tracker.server import TrackerServer
+
+
+MODELS = {
+    "qwen2.5-0.5b-instruct": (24, "Qwen/Qwen2.5-0.5B-Instruct"),
+    "qwen3.6-35b-a3b": (40, "unsloth/Qwen3.6-35B-A3B"),
+}
+
+
+def _post_json(url: str, payload: dict) -> dict:
+    request = urllib.request.Request(
+        url,
+        data=json.dumps(payload).encode(),
+        headers={"Content-Type": "application/json"},
+        method="POST",
+    )
+    with urllib.request.urlopen(request, timeout=10.0) as response:
+        return json.loads(response.read())
+
+
+def _get_json(url: str) -> dict:
+    with urllib.request.urlopen(url, timeout=10.0) as response:
+        return json.loads(response.read())
+
+
+class _LatencyNode(http.server.BaseHTTPRequestHandler):
+    """Synthetic node: every downstream Activation Seam adds deterministic delay."""
+
+    base_delay_seconds = 0.004
+    seam_delay_seconds = 0.006
+
+    def log_message(self, *_args):
+        pass
+
+    def do_POST(self):
+        self.rfile.read(int(self.headers.get("Content-Length", 0)))
+        downstream = json.loads(self.headers.get("X-Meshnet-Route", "[]"))
+        time.sleep(self.base_delay_seconds + self.seam_delay_seconds * len(downstream))
+        body = json.dumps({
+            "choices": [{"message": {"role": "assistant", "content": "ok " * 40}}],
+            "usage": {"prompt_tokens": 10, "completion_tokens": 40},
+        }).encode()
+        self.send_response(200)
+        self.send_header("Content-Type", "application/json")
+        self.send_header("Content-Length", str(len(body)))
+        self.end_headers()
+        self.wfile.write(body)
+
+
+def _start_latency_nodes(count: int):
+    nodes = []
+    threads = []
+    for _ in range(count):
+        node = http.server.ThreadingHTTPServer(("127.0.0.1", 0), _LatencyNode)
+        thread = threading.Thread(target=node.serve_forever, daemon=True)
+        thread.start()
+        nodes.append(node)
+        threads.append(thread)
+    return nodes, threads
+
+
+@pytest.mark.parametrize("model", MODELS)
+@pytest.mark.parametrize("hardware", ["gpu", "gpu-cpu", "cpu"])
+def test_tracker_records_increasing_hop_latency_for_model_and_hardware(model, hardware):
+    """One through five hops must preserve a measurable seam penalty in tracker stats."""
+    layer_count, hf_repo = MODELS[model]
+    nodes, threads = _start_latency_nodes(5)
+    tracker = TrackerServer(model_presets={
+        model: {
+            "layers_start": 0,
+            "layers_end": layer_count - 1,
+            "hf_repo": hf_repo,
+            "aliases": [model],
+        }
+    })
+    tracker_port = tracker.start()
+    try:
+        registered_ids = []
+        for index, node in enumerate(nodes):
+            start = (layer_count * index) // 5
+            end = (layer_count * (index + 1)) // 5 - 1
+            device = "cuda" if hardware == "gpu" or (hardware == "gpu-cpu" and index == 0) else "cpu"
+            data = _post_json(
+                f"http://127.0.0.1:{tracker_port}/v1/nodes/register",
+                {
+                    "endpoint": f"http://127.0.0.1:{node.server_address[1]}",
+                    "model": model,
+                    "hf_repo": hf_repo,
+                    "num_layers": layer_count,
+                    "shard_start": start,
+                    "shard_end": end,
+                    "tracker_mode": index == 0,
+                    "hardware_profile": {"device": device},
+                    "vram_bytes": 8_000_000_000 if device == "cuda" else 0,
+                    "ram_bytes": 32_000_000_000,
+                    "benchmark_tokens_per_sec": 100.0,
+                },
+            )
+            registered_ids.append(data["node_id"])
+
+        for hops in range(1, 6):
+            route = registered_ids[:hops]
+            # Widen the final shard to make each pinned prefix a complete route.
+            with tracker._server.lock:
+                tracker._server.registry[route[-1]].shard_end = layer_count - 1
+            _post_json(
+                f"http://127.0.0.1:{tracker_port}/v1/chat/completions",
+                {
+                    "model": model,
+                    "messages": [{"role": "user", "content": "measure"}],
+                    "route": route,
+                },
+            )
+
+        report = _get_json(f"http://127.0.0.1:{tracker_port}/v1/model-speed?model={model}")
+    finally:
+        tracker.stop()
+        for node, thread in zip(nodes, threads):
+            node.shutdown()
+            node.server_close()
+            thread.join(timeout=1.0)
+
+    routes = {entry["hop_count"]: entry for entry in report["routes"]}
+    assert set(routes) == {1, 2, 3, 4, 5}
+    assert routes[5]["latency_ms"] > routes[1]["latency_ms"]
+    assert routes[5]["latency_penalty_ms"] > 0
+    assert routes[5]["device_mix"] == hardware
+    assert report["model"] == model
+    assert report["nodes"]
+
+
+def test_model_speed_dashboard_includes_visualization_and_route_drilldown():
+    tracker = TrackerServer()
+    port = tracker.start()
+    try:
+        html = urllib.request.urlopen(f"http://127.0.0.1:{port}/dashboard").read().decode()
+    finally:
+        tracker.stop()
+
+    assert "Model inference speed" in html
+    assert "model-speed-chart" in html
+    assert "renderModelSpeed" in html
+    assert "/v1/model-speed" in html
--- a/tests/test_real_distributed_inference.py
+++ b/tests/test_real_distributed_inference.py
@@ -0,0 +1,62 @@
+"""Environment-gated acceptance test against real registered model shards.
+
+Run only after starting actual nodes (never synthetic HTTP handlers):
+
+MESHNET_REAL_INFERENCE_URL=http://localhost:8080 \
+MESHNET_REAL_INFERENCE_API_KEY=... \
+MESHNET_REAL_INFERENCE_MODEL=Qwen/Qwen2.5-0.5B-Instruct \
+MESHNET_REAL_INFERENCE_ROUTE=node-id-head,node-id-tail \
+.venv-rocm/bin/python -m pytest tests/test_real_distributed_inference.py -m integration -v
+"""
+
+import json
+import os
+import time
+import urllib.request
+
+import pytest
+
+
+BASE_URL = os.environ.get("MESHNET_REAL_INFERENCE_URL")
+API_KEY = os.environ.get("MESHNET_REAL_INFERENCE_API_KEY")
+MODEL = os.environ.get("MESHNET_REAL_INFERENCE_MODEL", "Qwen/Qwen2.5-0.5B-Instruct")
+ROUTE = [node_id for node_id in os.environ.get("MESHNET_REAL_INFERENCE_ROUTE", "").split(",") if node_id]
+
+pytestmark = pytest.mark.integration
+
+
+def _required_real_stack() -> None:
+    if not BASE_URL or not API_KEY or len(ROUTE) < 2:
+        pytest.skip(
+            "set MESHNET_REAL_INFERENCE_URL, MESHNET_REAL_INFERENCE_API_KEY, and "
+            "a comma-separated MESHNET_REAL_INFERENCE_ROUTE with at least two real nodes"
+        )
+
+
+def test_real_registered_shards_complete_a_pinned_request():
+    """Acceptance test: tracker proxies an actual prompt through real registered shards."""
+    _required_real_stack()
+    assert BASE_URL is not None
+    assert API_KEY is not None
+    request = urllib.request.Request(
+        f"{BASE_URL.rstrip('/')}/v1/chat/completions",
+        data=json.dumps({
+            "model": MODEL,
+            "messages": [{"role": "user", "content": "What is 2 plus 2? Reply in one word."}],
+            "max_tokens": 8,
+            "temperature": 1.0,
+            "route": ROUTE,
+        }).encode(),
+        headers={"Content-Type": "application/json", "Authorization": f"Bearer {API_KEY}"},
+        method="POST",
+    )
+    started = time.monotonic()
+    with urllib.request.urlopen(request, timeout=300) as response:
+        payload = json.loads(response.read())
+    elapsed = time.monotonic() - started
+
+    content = payload["choices"][0]["message"]["content"].strip().lower()
+    assert content
+    assert "two" in content or "four" in content
+    assert elapsed > 0
+    assert payload["usage"]["total_tokens"] > 0
--- a/tests/test_tracker_test_runner.py
+++ b/tests/test_tracker_test_runner.py
@@ -0,0 +1,224 @@
+"""dashboard-test-runner US-001: opt-in, admin-only tracker test-runner API.
+
+Runs against a tiny throwaway repo (tmp_path) so collection and runs stay
+fast and hermetic — the manager itself discovers the real repo root when
+constructed without an explicit ``repo_root``.
+"""
+
+import json
+import time
+import urllib.error
+import urllib.request
+from pathlib import Path
+
+import pytest
+
+from meshnet_tracker.accounts import AccountStore
+from meshnet_tracker.server import TrackerServer
+from meshnet_tracker.test_runner import TestRunManager as RunManager
+from meshnet_tracker.test_runner import discover_repo_root
+
+
+def _make_repo(tmp_path: Path) -> Path:
+    """A minimal repo satisfying discover_repo_root's markers, with fast tests."""
+    (tmp_path / "pyproject.toml").write_text("[tool.pytest.ini_options]\n")
+    tests = tmp_path / "tests"
+    tests.mkdir()
+    (tests / "conftest.py").write_text("")
+    (tests / "test_quick.py").write_text(
+        "def test_passes():\n    assert True\n\n"
+        "def test_also_passes():\n    assert 1 + 1 == 2\n"
+    )
+    (tests / "test_slow.py").write_text(
+        "import time\n\ndef test_sleeps():\n    time.sleep(30)\n"
+    )
+    (tests / "test_smoke.py").write_text("def test_smoke():\n    assert True\n")
+    # Real-inference stand-in: must never be collected or run by default.
+    (tests / "test_real_stub.py").write_text(
+        "def test_real_inference():\n    raise AssertionError('env-gated')\n"
+    )
+    return tmp_path
+
+
+def _start_tracker(tmp_path: Path | None):
+    """Tracker + (admin_session, user_session); test runner enabled iff tmp_path given."""
+    accounts = AccountStore()
+    admin = accounts.register(email="admin@example.com", password="admin-pass-123")
+    admin_session = accounts.create_session(admin["account_id"])
+    user = accounts.register(email="user@example.com", password="user-pass-123")
+    user_session = accounts.create_session(user["account_id"])
+    runner = RunManager(repo_root=_make_repo(tmp_path)) if tmp_path is not None else None
+    tracker = TrackerServer(accounts=accounts, test_runner=runner)
+    port = tracker.start()
+    return tracker, port, admin_session, user_session
+
+
+def _request(port, method, path, token=None, payload=None):
+    body = json.dumps(payload).encode() if payload is not None else None
+    headers = {"Content-Type": "application/json"}
+    if token:
+        headers["Authorization"] = f"Bearer {token}"
+    req = urllib.request.Request(
+        f"http://127.0.0.1:{port}{path}", data=body, headers=headers, method=method
+    )
+    try:
+        with urllib.request.urlopen(req) as resp:
+            return resp.status, json.loads(resp.read())
+    except urllib.error.HTTPError as exc:
+        return exc.code, json.loads(exc.read())
+
+
+def _wait_for_completion(port, session, timeout=90.0):
+    deadline = time.time() + timeout
+    while time.time() < deadline:
+        status, data = _request(port, "GET", "/v1/tests/status", token=session)
+        assert status == 200
+        if data["run"] is not None and data["run"]["status"] != "running":
+            return data
+        time.sleep(0.2)
+    raise AssertionError("test run did not finish in time")
+
+
+def test_endpoints_require_admin(tmp_path):
+    tracker, port, _admin, user = _start_tracker(tmp_path)
+    try:
+        assert _request(port, "GET", "/v1/tests")[0] == 401
+        assert _request(port, "GET", "/v1/tests/status")[0] == 401
+        assert _request(port, "POST", "/v1/tests/run", payload={"target": "x"})[0] == 401
+        assert _request(port, "GET", "/v1/tests", token=user)[0] == 403
+        assert _request(port, "GET", "/v1/tests/status", token=user)[0] == 403
+        assert _request(
+            port, "POST", "/v1/tests/run", token=user, payload={"target": "x"}
+        )[0] == 403
+    finally:
+        tracker.stop()
+
+
+def test_disabled_by_default_even_for_admin(monkeypatch):
+    monkeypatch.delenv("MESHNET_ENABLE_TEST_RUNNER", raising=False)
+    tracker, port, admin, _user = _start_tracker(None)
+    try:
+        assert tracker._test_runner is None  # no flag, no env → fails closed
+        for method, path, payload in [
+            ("GET", "/v1/tests", None),
+            ("GET", "/v1/tests/status", None),
+            ("POST", "/v1/tests/run", {"target": "tests/test_smoke.py::test_smoke"}),
+        ]:
+            status, data = _request(port, method, path, token=admin, payload=payload)
+            assert status == 403
+            assert "disabled" in data["error"]
+    finally:
+        tracker.stop()
+
+
+def test_enable_flag_constructs_runner_against_real_repo(monkeypatch):
+    monkeypatch.delenv("MESHNET_ENABLE_TEST_RUNNER", raising=False)
+    tracker = TrackerServer(enable_test_runner=True)
+    assert tracker._test_runner is not None
+    assert tracker._test_runner.repo_root == discover_repo_root()
+    assert (tracker._test_runner.repo_root / "tests" / "conftest.py").is_file()
+
+
+def test_collection_lists_tests_and_excludes_real_inference(tmp_path, monkeypatch):
+    monkeypatch.delenv("MESHNET_ENABLE_REAL_INFERENCE_TESTS", raising=False)
+    tracker, port, admin, _user = _start_tracker(tmp_path)
+    try:
+        status, data = _request(port, "GET", "/v1/tests", token=admin)
+        assert status == 200
+        assert data["enabled"] is True
+        assert "tests/test_quick.py::test_passes" in data["tests"]
+        assert "tests/test_slow.py::test_sleeps" in data["tests"]
+        assert not any("test_real_" in node_id for node_id in data["tests"])
+        assert data["collected_at"] is not None
+        suite_ids = [suite["id"] for suite in data["suites"]]
+        assert "suite:smoke" in suite_ids
+        assert "suite:real-inference" not in suite_ids
+    finally:
+        tracker.stop()
+
+
+def test_run_selected_test_to_completion(tmp_path):
+    tracker, port, admin, _user = _start_tracker(tmp_path)
+    try:
+        assert _request(port, "GET", "/v1/tests", token=admin)[0] == 200
+        status, started = _request(
+            port, "POST", "/v1/tests/run", token=admin,
+            payload={"target": "tests/test_quick.py::test_passes"},
+        )
+        assert status == 202
+        assert started["run"]["status"] == "running"
+        assert started["run"]["run_id"]
+        assert started["run"]["started_at"] is not None
+
+        finished = _wait_for_completion(port, admin)
+        run = finished["run"]
+        assert run["status"] == "passed"
+        assert run["exit_code"] == 0
+        assert run["target"] == "tests/test_quick.py::test_passes"
+        assert run["finished_at"] >= run["started_at"]
+        assert run["elapsed_seconds"] >= 0
+        assert "1 passed" in finished["stdout"]
+        assert finished["log_lines_limit"] > 0
+    finally:
+        tracker.stop()
+
+
+def test_run_approved_suite_without_prior_collection(tmp_path):
+    tracker, port, admin, _user = _start_tracker(tmp_path)
+    try:
+        status, started = _request(
+            port, "POST", "/v1/tests/run", token=admin,
+            payload={"target": "suite:smoke"},
+        )
+        assert status == 202
+        assert started["run"]["args"] == ["tests/test_smoke.py"]
+        finished = _wait_for_completion(port, admin)
+        assert finished["run"]["status"] == "passed"
+        assert finished["run"]["exit_code"] == 0
+    finally:
+        tracker.stop()
+
+
+@pytest.mark.parametrize("target", [
+    "",
+    "-x",
+    "--help",
+    "tests/test_quick.py::test_passes; rm -rf /",
+    "tests/never_collected.py::test_missing",
+    "suite:real-inference",
+    "suite:no-such-suite",
+])
+def test_rejects_arbitrary_or_uncollected_targets(tmp_path, target, monkeypatch):
+    monkeypatch.delenv("MESHNET_ENABLE_REAL_INFERENCE_TESTS", raising=False)
+    tracker, port, admin, _user = _start_tracker(tmp_path)
+    try:
+        assert _request(port, "GET", "/v1/tests", token=admin)[0] == 200
+        status, data = _request(
+            port, "POST", "/v1/tests/run", token=admin, payload={"target": target}
+        )
+        assert status == 400
+        assert "error" in data
+        # Nothing started.
+        assert _request(port, "GET", "/v1/tests/status", token=admin)[1]["run"] is None
+    finally:
+        tracker.stop()
+
+
+def test_rejects_concurrent_runs(tmp_path):
+    tracker, port, admin, _user = _start_tracker(tmp_path)
+    try:
+        assert _request(port, "GET", "/v1/tests", token=admin)[0] == 200
+        status, _ = _request(
+            port, "POST", "/v1/tests/run", token=admin,
+            payload={"target": "tests/test_slow.py::test_sleeps"},
+        )
+        assert status == 202
+        status, data = _request(
+            port, "POST", "/v1/tests/run", token=admin,
+            payload={"target": "tests/test_quick.py::test_passes"},
+        )
+        assert status == 409
+        assert "in progress" in data["error"]
+    finally:
+        # stop() kills the sleeping pytest child via TestRunManager.shutdown().
+        tracker.stop()
Author	SHA1	Message	Date
Dobromir Popov	f99237b4e6	dashboard test runner . backend	2026-07-11 16:11:42 +03:00
Dobromir Popov	bb561a9665	tests on dash	2026-07-11 12:38:51 +03:00
Dobromir Popov	11bf460027	routing tests, launch.configs, redirect, stats and route statistics	2026-07-11 11:39:47 +03:00