fix(core): scope stall reaping to the caller's subtree and commit failures atomically

Reap only descendants of the waiting agent, re-check status and silence
under the coordinator lock at the moment the failure is written, and stop
claiming the terminal notice is already queued in the wait result.

Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>

README.md

@@ -17,6 +17,9 @@
 <a href="https://strix.ai"><img src="https://img.shields.io/badge/Website-strix.ai-f0f0f0?style=for-the-badge&logoColor=000000" alt="Website"></a>
 [![](https://dcbadge.limes.pink/api/server/strix-ai)](https://discord.gg/strix-ai)
 
+<a href="https://app.strix.ai?utm_source=github&utm_medium=readme&utm_content=badge_cloud"><img src="https://img.shields.io/badge/Strix%20Cloud-app.strix.ai-2b9246?style=for-the-badge&logoColor=white" alt="Strix Cloud"></a>
+<a href="https://strix.ai/demo?utm_source=github&utm_medium=readme&utm_content=badge_demo"><img src="https://img.shields.io/badge/Try%20Strix%20Enterprise-555555?style=for-the-badge&logoColor=white" alt="Try Strix Enterprise"></a>
+
 <a href="https://deepwiki.com/usestrix/strix"><img src="https://deepwiki.com/badge.svg" alt="Ask DeepWiki"></a>
 <a href="https://github.com/usestrix/strix"><img src="https://img.shields.io/github/stars/usestrix/strix?style=flat-square" alt="GitHub Stars"></a>
 <a href="LICENSE"><img src="https://img.shields.io/badge/License-Apache%202.0-3b82f6?style=flat-square" alt="License"></a>
@@ -34,7 +37,7 @@
 
 
 > [!TIP]
-> **New!** Strix integrates seamlessly with GitHub Actions and CI/CD pipelines. Automatically scan for vulnerabilities on every pull request and block insecure code before it reaches production - [Get started with no setup required](https://app.strix.ai).
+> **New!** Strix integrates seamlessly with GitHub Actions and CI/CD pipelines. Automatically scan for vulnerabilities on every pull request and block insecure code before it reaches production - [Get started with no setup required](https://app.strix.ai?utm_source=github&utm_medium=readme&utm_content=tip_ci).
 
 ---
 
@@ -94,9 +97,17 @@ strix --target ./app-directory
 
 ---
 
-## ☁️ Strix Platform
+## Ways to Run Strix
 
-Try the Strix full-stack penetration testing platform at **[app.strix.ai](https://app.strix.ai)** - sign up for free, connect your repos and domains, and launch a pentest in minutes.
+- **Open Source** - free, runs locally with Docker and your own LLM key. [Quick Start](https://docs.strix.ai/quickstart)
+- **Strix Cloud** - no setup, validated findings, one-click autofix, and PR reviews. [Run a pentest →](https://app.strix.ai?intent=pentest&utm_source=github&utm_medium=readme&utm_content=table_cloud)
+- **Enterprise** - SSO, compliance-ready reports, VPC or self-hosted deployment. [Try Strix Enterprise →](https://strix.ai/demo?utm_source=github&utm_medium=readme&utm_content=table_demo)
+
+---
+
+## ☁️ Strix Cloud
+
+Try the Strix full-stack penetration testing platform at **[app.strix.ai](https://app.strix.ai?utm_source=github&utm_medium=readme&utm_content=cloud_heading)** - sign up for free, connect your repos and domains, and launch a pentest in minutes.
 
 - **Validated findings with PoCs** - every vulnerability includes a working proof-of-concept exploit and reproduction steps
 - **One-click autofix** - AI-generated security patches as ready-to-merge pull requests
@@ -104,7 +115,13 @@ Try the Strix full-stack penetration testing platform at **[app.strix.ai](https:
 - **DevSecOps integrations** - GitHub, GitLab, Bitbucket, Slack, Jira, Linear, and CI/CD pipelines
 - **Continuous learning** - AI that builds on past findings, adapts to your codebase, and reduces false positives over time
 
-[**Start your first pentest →**](https://app.strix.ai)
+[**Run a pentest →**](https://app.strix.ai?intent=pentest&utm_source=github&utm_medium=readme&utm_content=cloud_cta)
+
+## 🏢 Enterprise
+
+Get the same Strix experience with enterprise-grade controls: SSO (SAML/OIDC), custom compliance-ready penetration testing reports (SOC 2, ISO 27001, PCI DSS), dedicated support and SLA, custom deployment options (VPC or self-hosted), BYOK model support, and tailored AI pentesting agents optimized for your environment.
+
+[**Try Strix Enterprise →**](https://strix.ai/demo?utm_source=github&utm_medium=readme&utm_content=enterprise_cta)
 
 ---
 
@@ -333,10 +350,6 @@ Each server's tools are namespaced by `name`, for example `github_list_issues`.
 
 See the [LLM Providers documentation](https://docs.strix.ai/llm-providers/overview) for all supported providers including Vertex AI, Bedrock, Azure, and local models.
 
-## Enterprise Pentesting
-
-Get the same Strix experience with [enterprise-grade](https://strix.ai/demo) controls: SSO (SAML/OIDC), custom compliance-ready penetration testing reports (SOC 2, ISO 27001, PCI DSS), dedicated support & SLA, custom deployment options (VPC/self-hosted), BYOK model support, and tailored AI pentesting agents optimized for your environment. [Learn more](https://strix.ai/demo).
-
 ## Documentation
 
 Full documentation is available at **[docs.strix.ai](https://docs.strix.ai)** - including detailed guides for usage, CI/CD integrations, skills, and advanced configuration.

pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "strix-agent"
-version = "1.6.1"
+version = "1.6.2"
 description = "Open-source AI Hackers for your apps"
 readme = "README.md"
 license = "Apache-2.0"

scripts/install.sh

@@ -346,6 +346,9 @@ echo -e "${MUTED}For more information visit ${NC}https://strix.ai"
 echo -e "${MUTED}Supported models ${NC}https://docs.strix.ai/llm-providers/overview"
 echo -e "${MUTED}Join our community ${NC}https://discord.gg/strix-ai"
 echo ""
+echo -e "${MUTED}Run a pentest in Strix Cloud ${NC}https://app.strix.ai"
+echo -e "${MUTED}Enterprise ${NC}https://strix.ai/demo"
+echo ""
 
 echo -e "${YELLOW}→${NC} Run ${MUTED}source ~/.$(basename $SHELL)rc${NC} or open a new terminal"
 echo ""

strix/config/models.py

@@ -593,17 +593,27 @@ RECOMMENDED_MODEL_NAMES = (
 
 _RECOMMENDED_MODEL_NAME_SET = frozenset(name.lower() for name in RECOMMENDED_MODEL_NAMES)
 
-FRONTIER_MODEL_FAMILIES = (
-    (("azure", "azure_ai", "bedrock_mantle", "chatgpt", "openai"), ("gpt-5",)),
-    (
-        ("anthropic", "azure_ai", "bedrock", "claude", "databricks", "snowflake", "vertex_ai"),
-        ("claude-fable-5", "claude-opus-5", "claude-opus-4", "claude-sonnet-5", "claude-sonnet-4"),
-    ),
-    (("google", "gemini", "vertex_ai"), ("gemini-3",)),
-    (("deepseek",), ("deepseek-v4", "deepseek-r1", "deepseek-reasoner")),
-    (("alibaba", "dashscope", "qwen"), ("qwen3.8", "qwen3.7", "qwen3-max")),
-    (("moonshot", "moonshotai", "kimi"), ("kimi-k3", "kimi-k2.7", "kimi-k2.6")),
-    (("zai", "z-ai", "zai-org", "zhipuai"), ("glm-5.3", "glm-5.2")),
+# Matched against the bare model name only: the route (``openai/``, ``openrouter/``,
+# a local gateway, ...) says nothing about the model's quality.
+FRONTIER_MODEL_PREFIXES = (
+    "gpt-5",
+    "claude-fable-5",
+    "claude-opus-5",
+    "claude-opus-4",
+    "claude-sonnet-5",
+    "claude-sonnet-4",
+    "gemini-3",
+    "deepseek-v4",
+    "deepseek-r1",
+    "deepseek-reasoner",
+    "qwen3.8",
+    "qwen3.7",
+    "qwen3-max",
+    "kimi-k3",
+    "kimi-k2.7",
+    "kimi-k2.6",
+    "glm-5.3",
+    "glm-5.2",
 )
 
 
@@ -837,11 +847,8 @@ def is_recommended_or_frontier_model(model_name: str) -> bool:
         return False
     if name in _RECOMMENDED_MODEL_NAME_SET:
         return True
-    provider_name, bare_model_name = _split_model_provider(name)
-    return any(
-        _matches_frontier_family(provider_name, bare_model_name, provider_markers, prefixes)
-        for provider_markers, prefixes in FRONTIER_MODEL_FAMILIES
-    )
+    bare_model_name = name.rsplit("/", 1)[-1]
+    return _matches_model_prefix(bare_model_name, FRONTIER_MODEL_PREFIXES)
 
 
 def _normalized_model_name(model_name: str) -> str:
@@ -853,28 +860,6 @@ def _normalized_model_name(model_name: str) -> str:
     return name
 
 
-def _split_model_provider(model_name: str) -> tuple[str | None, str]:
-    if "/" not in model_name:
-        return None, model_name
-    provider_name, bare_model_name = model_name.rsplit("/", 1)
-    return provider_name, bare_model_name
-
-
-def _matches_frontier_family(
-    provider_name: str | None,
-    model_name: str,
-    provider_markers: tuple[str, ...],
-    model_prefixes: tuple[str, ...],
-) -> bool:
-    if not _matches_model_prefix(model_name, model_prefixes):
-        return False
-    if provider_name is None:
-        return True
-    return _contains_provider_marker(
-        provider_name, provider_markers, split_compound_names=True
-    ) or _contains_provider_marker(model_name, provider_markers)
-
-
 def _matches_model_prefix(model_name: str, model_prefixes: tuple[str, ...]) -> bool:
     return any(
         candidate.startswith(prefix)
@@ -892,16 +877,6 @@ def _model_name_candidates(model_name: str) -> tuple[str, ...]:
     return (model_name, *suffixes)
 
 
-def _contains_provider_marker(
-    value: str, provider_markers: tuple[str, ...], *, split_compound_names: bool = False
-) -> bool:
-    parts = set(value.replace(".", "/").split("/"))
-    if split_compound_names:
-        for separator in ("_", "-"):
-            parts.update(piece for part in tuple(parts) for piece in part.split(separator))
-    return any(marker in parts for marker in provider_markers)
-
-
 def is_known_openai_bare_model(model_name: str) -> bool:
     import litellm
 

strix/config/settings.py

@@ -112,6 +112,10 @@ class RuntimeSettings(BaseSettings):
     backend: str = Field(default="docker", alias="STRIX_RUNTIME_BACKEND")
     # Max screenshot/image tool outputs kept live per agent context (0 = none).
     max_context_images: int = Field(default=3, ge=0, alias="STRIX_MAX_CONTEXT_IMAGES")
+    # Seconds a running agent may go without emitting a single run event before
+    # its turn is abandoned and, if it still does not recover, a waiting parent
+    # marks it failed (0 = never).
+    agent_stall_timeout: int = Field(default=1800, ge=0, alias="STRIX_AGENT_STALL_TIMEOUT")
 
 
 class TelemetrySettings(BaseSettings):

strix/core/agents.py

@@ -6,6 +6,7 @@ import asyncio
 import json
 import logging
 import tempfile
+import time
 from dataclasses import dataclass, field
 from pathlib import Path
 from typing import TYPE_CHECKING, Any, Literal, cast
@@ -45,6 +46,8 @@ class AgentRuntime:
     wake: asyncio.Event = field(default_factory=asyncio.Event)
     mailbox: list[dict[str, Any]] = field(default_factory=list)
     user_wake_required: bool = False
+    # Monotonic time of the agent's last sign of life: a run event or a status change.
+    last_activity: float = field(default_factory=time.monotonic)
 
 
 class AgentCoordinator:
@@ -170,7 +173,7 @@ class AgentCoordinator:
                 "task": task or "",
                 "skills": list(skills or []),
             }
-            self.runtimes.setdefault(agent_id, AgentRuntime())
+            self.runtimes.setdefault(agent_id, AgentRuntime()).last_activity = time.monotonic()
         logger.info("agent.register %s (%s) parent=%s", agent_id, name, parent_id or "-")
         await self._maybe_snapshot()
 
@@ -200,10 +203,56 @@ class AgentCoordinator:
                 self.statuses[agent_id] = "running"
                 self.errors.pop(agent_id, None)
                 self.wait_kinds.pop(agent_id, None)
-                self.runtimes.setdefault(agent_id, AgentRuntime()).user_wake_required = False
+                runtime = self.runtimes.setdefault(agent_id, AgentRuntime())
+                runtime.user_wake_required = False
+                runtime.last_activity = time.monotonic()
                 self._parent_notified.discard(agent_id)
         await self._maybe_snapshot()
 
+    def touch(self, agent_id: str) -> None:
+        """Record a sign of life; called on every run event, so it takes no lock."""
+        runtime = self.runtimes.get(agent_id)
+        if runtime is not None:
+            runtime.last_activity = time.monotonic()
+
+    async def reap_stalled(self, max_silence: float, *, under: str) -> list[dict[str, Any]]:
+        """Fail the descendants of ``under`` that were silent for ``max_silence`` seconds.
+
+        A turn wedged somewhere no timeout covers never reaches a terminal status,
+        so whoever waits on it would wait forever. Cancelling the task ends the
+        wedged turn; the agent's own loop then delivers the terminal notice.
+        """
+        if max_silence <= 0:
+            return []
+        now = time.monotonic()
+        reaped: list[dict[str, Any]] = []
+        tasks: list[asyncio.Task[Any]] = []
+        async with self._lock:
+            for aid in self._subtree_order_locked(under):
+                runtime = self.runtimes.get(aid)
+                if aid == under or runtime is None or self.statuses.get(aid) != "running":
+                    continue
+                silence = now - runtime.last_activity
+                if silence < max_silence:
+                    continue
+                error = f"agent produced no event for {silence:.0f}s; marked failed as stalled"
+                self.statuses[aid] = "failed"
+                self.errors[aid] = error
+                runtime.user_wake_required = True
+                runtime.last_activity = now
+                runtime.wake.set()
+                if runtime.task is not None and not runtime.task.done():
+                    tasks.append(runtime.task)
+                reaped.append({"agent_id": aid, "name": self.names.get(aid, aid), "error": error})
+        for entry in reaped:
+            logger.warning("agent %s stalled: %s", entry["agent_id"], entry["error"])
+            logger.info("agent.status %s=failed", entry["agent_id"])
+        for task in tasks:
+            task.cancel()
+        if reaped:
+            await self._maybe_snapshot()
+        return reaped
+
     async def park_waiting(self, agent_id: str, *, wait_kind: WaitKind) -> None:
         """Park an agent, recording what it is waiting on so the driver can time it."""
         async with self._lock:
@@ -268,6 +317,7 @@ class AgentCoordinator:
                 self._parent_notified.discard(agent_id)
             runtime = self.runtimes.setdefault(agent_id, AgentRuntime())
             runtime.user_wake_required = status in {"failed", "crashed"}
+            runtime.last_activity = time.monotonic()
             runtime.wake.set()
         logger.info("agent.status %s=%s", agent_id, status)
         await self._maybe_snapshot()

strix/core/execution.py

@@ -6,7 +6,7 @@ import asyncio
 import contextlib
 import logging
 import uuid
-from collections.abc import Callable
+from collections.abc import AsyncIterator, Callable
 from functools import cache
 from typing import TYPE_CHECKING, Any, cast
 
@@ -19,7 +19,7 @@ from openai import (
     APITimeoutError,
 )
 
-from strix.config import codex
+from strix.config import codex, load_settings
 from strix.core.hooks import (
     BudgetExceededError,
     BudgetPausedError,
@@ -149,6 +149,38 @@ def _transient_model_retry_delay(attempt: int) -> float:
     return min(delay, _TRANSIENT_MODEL_RETRY_MAX_DELAY_S)
 
 
+def _agent_stall_timeout() -> float:
+    return float(load_settings().runtime.agent_stall_timeout)
+
+
+async def _with_stall_guard(stream: Any, timeout: float, agent_id: str) -> AsyncIterator[Any]:
+    """Yield run events, abandoning the turn if none arrives for ``timeout`` seconds.
+
+    The model-stream idle guard only covers the model call itself. Everything
+    else the run loop awaits between events (tool transport, session writes,
+    a re-issued request that never opens) has no bound of its own, so a hang
+    there would keep the agent "running" forever.
+    """
+    events = stream.stream_events()
+    if timeout <= 0:
+        async for event in events:
+            yield event
+        return
+    iterator = events.__aiter__()
+    while True:
+        try:
+            event = await asyncio.wait_for(iterator.__anext__(), timeout)
+        except StopAsyncIteration:
+            return
+        except TimeoutError:
+            message = f"agent turn produced no event for {timeout:.0f}s"
+            logger.warning("%s for %s; abandoning the turn", message, agent_id)
+            with contextlib.suppress(Exception):
+                stream.cancel(mode="immediate")
+            raise TimeoutError(message) from None
+        yield event
+
+
 async def _salvage_stream_to_session(
     session: Session,
     pre_run_items: list[Any],
@@ -658,6 +690,7 @@ async def _run_cycle(  # noqa: PLR0912, PLR0915
     image_strips = 0
     compactions = 0
     model_retries = 0
+    stall_timeout = _agent_stall_timeout()
     while True:
         stream: Any = None
         pre_run_items: list[Any] = []
@@ -688,7 +721,8 @@ async def _run_cycle(  # noqa: PLR0912, PLR0915
             await coordinator.attach_stream(agent_id, stream)
             try:
                 try:
-                    async for event in stream.stream_events():
+                    async for event in _with_stall_guard(stream, stall_timeout, agent_id):
+                        coordinator.touch(agent_id)
                         if event_sink is not None:
                             try:
                                 event_sink(agent_id, event)

strix/core/runner.py

@@ -45,6 +45,7 @@ from strix.core.paths import run_dir_for, runtime_state_dir
 from strix.core.sessions import open_agent_session
 from strix.report.state import get_global_report_state
 from strix.runtime import session_manager
+from strix.telemetry import set_scan_phase
 from strix.telemetry.logging import set_scan_id, setup_scan_logging
 from strix.tools.output_store import (
     WORKSPACE_SPILL_DIR,
@@ -116,6 +117,13 @@ def _record_mcp_connections(connections: list[ConnectedMcpServer]) -> None:
     report_state.record_mcp_connections([connection.name for connection in connections])
 
 
+def _note_exit_reason(reason: str) -> None:
+    """Record why the scan stopped so the end-of-scan beacon reports it."""
+    report_state = get_global_report_state()
+    if report_state is not None and report_state.scan_ended_exit_reason is None:
+        report_state.scan_ended_exit_reason = reason
+
+
 def _persist_mcp_status(roster: list[dict[str, Any]]) -> None:
     """Write the run's non-secret MCP connection status roster to run.json.
 
@@ -313,6 +321,7 @@ async def run_strix_scan(
         root_id = uuid.uuid4().hex[:8]
 
     logger.info("Bringing up sandbox session for scan %s", scan_id)
+    set_scan_phase("sandbox_init")
     bundle = await session_manager.create_or_reuse(
         scan_id,
         image=image,
@@ -322,6 +331,7 @@ async def run_strix_scan(
     )
     report("Waiting for the first model response")
     logger.info("Sandbox ready for scan %s", scan_id)
+    set_scan_phase("agent_setup")
 
     sandbox_session = bundle["session"]
 
@@ -573,6 +583,7 @@ async def run_strix_scan(
         async with coordinator._lock:
             root_status = coordinator.statuses.get(root_id)
 
+        set_scan_phase("agent_loop")
         result = await run_agent_loop(
             agent=root_agent,
             initial_input=initial_input,
@@ -610,6 +621,7 @@ async def run_strix_scan(
         return result  # noqa: TRY300
     except BudgetExceededError as exc:
         logger.info("Scan %s stopped: %s", scan_id, exc)
+        _note_exit_reason("budget_exceeded")
         if root_id is not None:
             with contextlib.suppress(Exception):
                 await coordinator.set_status(root_id, "stopped")
@@ -622,6 +634,7 @@ async def run_strix_scan(
             exc,
             scan_id,
         )
+        _note_exit_reason("rate_limited")
         if root_id is not None:
             with contextlib.suppress(Exception):
                 await coordinator.set_status(root_id, "stopped")

strix/interface/cli_args.py

@@ -98,6 +98,14 @@ Examples:
   # Extra files placed in the sandbox workspace
   strix --target ./my-project --workspace-file ./wordlist.txt
   strix --target https://app.com --workspace-file ./openapi.yaml:specs/openapi.yaml
+
+Strix Cloud:
+  strix cloud login
+  strix cloud scans start --source . --yes --wait
+  strix cloud                      # list every cloud resource
+
+  Run a pentest in Strix Cloud     https://app.strix.ai
+  Try Strix Enterprise             https://strix.ai/demo
         """,
     )
 

strix/interface/environment.py

@@ -14,6 +14,7 @@ from strix.interface.utils import (
     image_exists,
     process_pull_line,
 )
+from strix.telemetry import report_error
 
 
 logger = logging.getLogger(__name__)
@@ -44,6 +45,7 @@ def validate_environment() -> None:
                 f"[red]STRIX_LLM={settings.llm.model} uses your ChatGPT subscription, "
                 "but you're not signed in.[/] Run [cyan]strix auth login chatgpt[/] first."
             )
+            report_error("subscription_not_signed_in")
             sys.exit(1)
         logger.info("Environment OK (ChatGPT subscription)")
         return
@@ -153,6 +155,7 @@ def validate_environment() -> None:
         console.print("\n")
         console.print(panel)
         console.print()
+        report_error("missing_required_config")
         sys.exit(1)
     logger.info(
         "Environment OK (optional missing: %s)",
@@ -180,6 +183,7 @@ def check_docker_installed() -> None:
             padding=(1, 2),
         )
         console.print("\n", panel, "\n")
+        report_error("docker_not_installed")
         sys.exit(1)
     logger.debug("Docker CLI present")
 
@@ -227,6 +231,7 @@ def pull_docker_image() -> None:
                 padding=(1, 2),
             )
             console.print(panel, "\n")
+            report_error("image_pull_failed", e)
             sys.exit(1)
 
     logger.info("Docker image %s ready", image)

strix/interface/main.py

@@ -42,7 +42,7 @@ from strix.interface.utils import (
     build_final_stats_text,
 )
 from strix.llm.warmup import start_import_warmup, wait_for_import_warmup
-from strix.telemetry import posthog, scarf
+from strix.telemetry import posthog, report_error, scarf, set_scan_phase
 from strix.telemetry.logging import configure_dependency_logging
 
 
@@ -333,6 +333,11 @@ def display_completion_message(args: argparse.Namespace, results_path: Path) ->
         "[#60a5fa]docs.strix.ai[/]  [dim]·[/]  "
         "[#60a5fa]discord.gg/strix-ai[/]"
     )
+    if not args.non_interactive:
+        console.print(
+            "[dim]Run a pentest in Strix Cloud[/]  [#60a5fa]app.strix.ai[/]  [dim]·[/]  "
+            "[dim]Enterprise[/]  [#60a5fa]strix.ai/demo[/]"
+        )
     console.print()
     if not args.non_interactive:
         notify_update(console)
@@ -396,15 +401,18 @@ def _bootstrap_scan(args: argparse.Namespace) -> None:
     happen inside the TUI so the interface paints immediately instead of
     waiting on a model round trip.
     """
+    set_scan_phase("preflight")
     try:
         asyncio.run(warm_up_llm(show_model_warning=True))
     except ModelConnectionError as exc:
+        report_error("model_connection_failed", exc)
         _print_model_connection_error(exc, exc.model_name)
         sys.exit(1)
     persist_current()
     try:
         prepare_run(args)
     except ValueError as e:
+        report_error("scan_preparation_failed", e)
         _print_error_panel("SCAN PREPARATION FAILED", str(e))
         sys.exit(1)
     telemetry_start(args)
@@ -479,18 +487,21 @@ def main() -> None:
             from strix.interface.cli import run_cli
 
             asyncio.run(run_cli(args))
+            # Headless runs have no user to quit: the agent either finished
+            # (already beaconed as finished_by_tool) or stopped on its own.
+            exit_reason = "agent_stopped"
         else:
             asyncio.run(run_tui(args))
     except InteractiveSetupUnavailableError as exc:
         exit_reason = "error"
+        report_error("interactive_setup_unavailable", exc)
         _print_error_panel("INTERACTIVE SETUP UNAVAILABLE", str(exc))
         sys.exit(1)
     except KeyboardInterrupt:
         exit_reason = "interrupted"
-    except Exception:
+    except Exception as exc:
         exit_reason = "error"
-        posthog.error("unhandled_exception")
-        scarf.error("unhandled_exception")
+        report_error("unhandled_exception", exc)
         raise
     finally:
         report_state = get_global_report_state()

strix/interface/tui/backend/controller.py

@@ -192,7 +192,7 @@ class TuiController:
         model_warning = ""
         if model and not is_recommended_or_frontier_model(model):
             model_warning = (
-                f"{model} is not a recommended frontier model; pentest quality could be degraded"
+                f"{model} is not a recommended frontier model. Pentest quality could be degraded."
             )
         state = {
             "setup_mode": self.setup_mode,

strix/interface/tui/internal/app/model_test.go

@@ -370,6 +370,17 @@ func TestStartedSnapshotTransitionsToLiveView(t *testing.T) {
 	}
 }
 
+func TestSplashModelWarningRendersTheBackendSentenceOnce(t *testing.T) {
+	warning := "openai/glm-5.3 is not a recommended frontier model. Pentest quality could be degraded."
+	got := ansi.Strip(splashModelWarning("openai/glm-5.3", warning))
+	if got != "⚠ "+warning {
+		t.Fatalf("splash warning = %q, want %q", got, "⚠ "+warning)
+	}
+	if got := ansi.Strip(splashModelWarning("other/model", warning)); got != "⚠ "+warning {
+		t.Fatalf("splash warning with unrelated model = %q", got)
+	}
+}
+
 func TestSetupStartScreenFitsNarrowTerminal(t *testing.T) {
 	model := New(nil)
 	model.width, model.height = 40, 18

strix/interface/tui/internal/app/view.go

@@ -411,7 +411,7 @@ func (m Model) splashView() string {
 		welcome + "\n" + version + "\n" + tagline + "\n\n" +
 		start.String() + "\n\n" + url
 	if warn := m.snapshot.ModelWarning; warn != "" {
-		content += "\n\n" + splashModelWarning(warn)
+		content += "\n\n" + splashModelWarning(m.snapshot.Model, warn)
 	}
 	panel := lipgloss.NewStyle().Border(lipgloss.RoundedBorder()).BorderForeground(green).Padding(1, 6).Align(lipgloss.Center).Render(content)
 	// #splash_screen background is solid black.
@@ -419,12 +419,16 @@ func (m Model) splashView() string {
 		lipgloss.WithWhitespaceBackground(black))
 }
 
-// splashModelWarning ports SplashScreen._build_model_warning_text.
-func splashModelWarning(model string) string {
+// splashModelWarning renders the backend's full warning sentence, with the
+// model name highlighted when the sentence leads with it.
+func splashModelWarning(model, warning string) string {
 	yellow := lipgloss.Color("#eab308")
-	return lipgloss.NewStyle().Bold(true).Foreground(yellow).Render("⚠ ") +
-		lipgloss.NewStyle().Bold(true).Foreground(render.Cyan).Render(model) +
-		lipgloss.NewStyle().Foreground(yellow).Render(" is not a recommended frontier model - pentest quality could be degraded")
+	out := lipgloss.NewStyle().Bold(true).Foreground(yellow).Render("⚠ ")
+	if model != "" && strings.HasPrefix(warning, model) {
+		out += lipgloss.NewStyle().Bold(true).Foreground(render.Cyan).Render(model)
+		warning = strings.TrimPrefix(warning, model)
+	}
+	return out + lipgloss.NewStyle().Foreground(yellow).Render(warning)
 }
 
 // chatPaneKey identifies everything the bordered trace depends on.

strix/interface/tui/runtime.py

@@ -37,6 +37,7 @@ from strix.interface.tui.sidecar import (
 )
 from strix.interface.utils import read_workspace_files
 from strix.report.state import ReportState, set_global_report_state
+from strix.telemetry import report_error, set_scan_phase
 from strix.utils.resource_paths import get_strix_resource_path
 
 
@@ -138,11 +139,13 @@ class GoTuiRuntime:
             await self._preflight_model()
         except Exception as exc:
             logger.exception("Go TUI setup model preflight failed")
+            report_error("model_connection_failed", exc)
             raise RuntimeError(f"Model connection failed: {exc}") from exc
 
     async def _preflight_model(self) -> None:
         model = (load_settings().llm.model or "").strip()
         self.controller.add_message("Verifying model connection...")
+        set_scan_phase("preflight")
         await preflight_model_connection(model)
         self.model_verified = True
 
@@ -181,7 +184,11 @@ class GoTuiRuntime:
             candidate.target = list(self.controller.targets)
             candidate.target_list = []
             build_targets_info(candidate)
-        prepare_run(candidate)
+        try:
+            prepare_run(candidate)
+        except Exception as exc:
+            report_error("scan_preparation_failed", exc)
+            raise
         telemetry_start(candidate)
 
         vars(self.args).update(vars(candidate))
@@ -195,13 +202,21 @@ class GoTuiRuntime:
         launch so the interface appears immediately.
         """
         model = (load_settings().llm.model or "").strip()
+        set_scan_phase("preflight")
         try:
             await preflight_model_connection(model)
+        except Exception as exc:
+            logger.exception("Go TUI scan preparation failed")
+            report_error("model_connection_failed", exc)
+            self.controller.fail_preparation(str(exc))
+            return
+        try:
             persist_current()
             prepare_run(self.args)
             telemetry_start(self.args)
         except Exception as exc:
             logger.exception("Go TUI scan preparation failed")
+            report_error("scan_preparation_failed", exc)
             self.controller.fail_preparation(str(exc))
             return
         self.controller.scan_state = "running"
@@ -240,6 +255,9 @@ class GoTuiRuntime:
             self.controller.scan_state = "completed" if report_status == "completed" else "stopped"
         except Exception as exc:
             logger.exception("Go TUI scan failed")
+            report_error("unhandled_exception", exc)
+            if self.report_state is not None and self.report_state.scan_ended_exit_reason is None:
+                self.report_state.scan_ended_exit_reason = "error"
             self.scan_error = exc
             self.controller.error = str(exc)
             self.controller.scan_state = "failed"

strix/interface/utils.py

@@ -19,6 +19,7 @@ from rich.panel import Panel
 from rich.text import Text
 
 from strix.config import load_settings
+from strix.telemetry import report_error
 from strix.utils.api_spec import detect_spec_format
 
 
@@ -1602,7 +1603,8 @@ def check_docker_connection() -> Any:
 
     try:
         return docker.from_env()
-    except DockerException:
+    except DockerException as exc:
+        report_error("docker_unavailable", exc)
         console = Console()
         error_text = Text()
         error_text.append("DOCKER NOT AVAILABLE", style="bold red")

strix/interface/viewer/frontend/src/App.tsx

@@ -8,6 +8,7 @@ import {
   Radar,
   Rocket,
   ArrowUpRight,
+  Building2,
   History,
 } from "lucide-react";
 import type { Vulnerability, VulnerabilitySeverity } from "@/types/issues";
@@ -35,7 +36,7 @@ import {
   type LoadedRun,
   type RunsPayload,
 } from "@/data/serverSource";
-import { SIGNUP_URL, ctaUrl, trackCta } from "@/lib/cta";
+import { SIGNUP_URL, DEMO_URL, ctaUrl, trackCta } from "@/lib/cta";
 import { runTitle } from "@/lib/target-utils";
 import Sidebar from "@/components/Sidebar";
 import PastRunsView from "@/components/PastRunsView";
@@ -706,6 +707,31 @@ function OverviewTab({
         </div>
       )}
 
+      {finished && (
+        <div className="animate-card-in rounded-xl border border-[#222] bg-[rgba(255,255,255,0.02)] p-5">
+          <p className="text-sm font-semibold text-white">Strix Cloud</p>
+          <p className="mt-0.5 text-xs text-[#666]">Run your next pentest in Strix Cloud.</p>
+          <div className="mt-3 flex flex-wrap gap-2.5">
+            <ProInlineCta
+              label="Run a pentest in Strix Cloud"
+              desc="Validated findings, autofix, and PR reviews."
+              slug="overview_cloud"
+              surface="overview"
+              icon={Rocket}
+              primary
+            />
+            <ProInlineCta
+              label="Try Strix Enterprise"
+              desc="SSO, compliance-ready reports, VPC or self-hosted deployment."
+              slug="book_demo"
+              surface="overview"
+              icon={Building2}
+              href={DEMO_URL}
+            />
+          </div>
+        </div>
+      )}
+
       {sections.length > 0 ? (
         <div className="animate-card-in rounded-xl border border-[#222] bg-[rgba(255,255,255,0.02)] p-5 space-y-8">
           {sections.map((s) => (
@@ -789,14 +815,23 @@ function AgentsTab({ run, canSteer }: { run: LoadedRun; canSteer: boolean }) {
       {/* Re-run always routes to Strix Cloud. */}
       <div className="rounded-xl border border-[#222] bg-[rgba(255,255,255,0.02)] p-5">
         <p className="text-sm font-semibold text-white">Run this pentest with more depth</p>
-        <p className="mt-0.5 text-xs text-[#666]">Re-run this pentest on managed infra in the cloud.</p>
+        <p className="mt-0.5 text-xs text-[#666]">Run this pentest again in Strix Cloud.</p>
         <div className="mt-3 flex flex-wrap gap-2.5">
           <ProInlineCta
             label="Re-run in Strix Pro with more depth"
-            desc="Run this pentest on managed infra with more depth."
+            desc="More depth, validated findings, and autofix."
             slug="live_scan"
             surface="agents"
             icon={Rocket}
+            primary
+          />
+          <ProInlineCta
+            label="Try Strix Enterprise"
+            desc="SSO, compliance-ready reports, VPC or self-hosted deployment."
+            slug="book_demo"
+            surface="agents"
+            icon={Building2}
+            href={DEMO_URL}
           />
         </div>
       </div>

strix/interface/viewer/frontend/src/components/ProCta.tsx

@@ -48,23 +48,40 @@ export function ProInlineCta({
   slug,
   icon: Icon,
   surface,
+  href = SIGNUP_URL,
+  primary = false,
 }: {
   label: string;
   desc: string;
   slug: string;
   icon: React.ElementType;
   surface?: string;
+  /** Destination before attribution params. Defaults to cloud sign-up. */
+  href?: string;
+  /** Solid white button instead of the outlined default. */
+  primary?: boolean;
 }) {
   return (
     <Tooltip text={desc}>
       <a
-        href={ctaUrl(SIGNUP_URL, slug)}
+        href={ctaUrl(href, slug)}
         target="_blank"
         rel="noopener noreferrer"
         onClick={() => trackCta(slug, surface)}
-        className="group inline-flex items-center gap-2 rounded-lg border border-[#222] bg-[rgba(255,255,255,0.02)] px-3 py-2 text-sm text-[#aaa] transition-colors hover:border-[#444] hover:text-white"
+        className={
+          primary
+            ? "group inline-flex items-center gap-2 rounded-lg border border-white bg-white px-3 py-2 text-sm font-semibold text-black transition-colors hover:bg-[#e5e5e5]"
+            : "group inline-flex items-center gap-2 rounded-lg border border-[#222] bg-[rgba(255,255,255,0.02)] px-3 py-2 text-sm text-[#aaa] transition-colors hover:border-[#444] hover:text-white"
+        }
       >
-        <Icon className="h-4 w-4 text-[#888] transition-colors group-hover:text-white" aria-hidden="true" />
+        <Icon
+          className={
+            primary
+              ? "h-4 w-4 text-black"
+              : "h-4 w-4 text-[#888] transition-colors group-hover:text-white"
+          }
+          aria-hidden="true"
+        />
         <span>{label}</span>
       </a>
     </Tooltip>

strix/interface/viewer/frontend/src/components/UpgradeModal.tsx

@@ -10,7 +10,7 @@ import {
   WandSparkles,
   Plug,
 } from "lucide-react";
-import { SIGNUP_URL, PRICING_URL, ctaUrl, trackCta } from "@/lib/cta";
+import { SIGNUP_URL, PRICING_URL, DEMO_URL, ctaUrl, trackCta } from "@/lib/cta";
 
 /**
  * Dialog shown when a platform feature is clicked in the sidebar: a short
@@ -141,6 +141,19 @@ export function UpgradeModal({
               <ExternalLink className="h-3 w-3" />
             </a>
           </div>
+
+          <p className="text-center text-xs text-[#666]">
+            SSO, compliance reports, or a private deployment?{" "}
+            <a
+              href={ctaUrl(DEMO_URL, "upgrade_book_demo")}
+              target="_blank"
+              rel="noopener noreferrer"
+              onClick={() => trackCta("upgrade_book_demo", source)}
+              className="whitespace-nowrap text-[#aaa] underline underline-offset-2 transition-colors hover:text-white"
+            >
+              Try Strix Enterprise
+            </a>
+          </p>
         </div>
       </div>
     </div>

strix/interface/viewer/static/index.html

@@ -6,8 +6,8 @@
     <meta name="viewport" content="width=device-width, initial-scale=1.0" />
     <meta name="color-scheme" content="dark" />
     <title>Strix Results</title>
-    <script type="module" crossorigin src="./assets/index-Bpn8GiSb.js"></script>
-    <link rel="stylesheet" crossorigin href="./assets/index-qwPOPAGC.css">
+    <script type="module" crossorigin src="./assets/index-B94ANU8d.js"></script>
+    <link rel="stylesheet" crossorigin href="./assets/index-DN__rVv3.css">
   </head>
   <body>
     <div id="root"></div>

strix/telemetry/README.md

@@ -12,7 +12,7 @@ Privacy is our priority. All collected data is anonymized by default. Each sessi
 
 We collect only very **basic** usage data including:
 
-**Session Errors:** Duration and error types (not messages or stack traces)\
+**Session Errors:** Duration, the failure category, the scan phase, and the exception class name (not messages or stack traces)\
 **System Context:** OS type, architecture, Strix version\
 **Scan Context:** Scan mode (quick/standard/deep), scan type (whitebox/blackbox)\
 **Model Usage:** Which LLM model is being used and whether it runs via an API key or a model subscription (not prompts or responses)\

strix/telemetry/__init__.py

@@ -1,7 +1,19 @@
 from . import posthog, scarf
+from ._common import set_scan_phase
+
+
+def report_error(error_type: str, exc: BaseException | None = None) -> None:
+    """Beacon a failure category, plus the exception class when one is given.
+
+    Only class names travel: never the message, arguments, or traceback.
+    """
+    posthog.error(error_type, exc)
+    scarf.error(error_type, exc)
 
 
 __all__ = [
     "posthog",
+    "report_error",
     "scarf",
+    "set_scan_phase",
 ]

strix/telemetry/_common.py

@@ -5,7 +5,7 @@ import platform
 import sys
 from importlib.metadata import PackageNotFoundError, version
 from pathlib import Path
-from typing import Any
+from typing import Any, cast
 from uuid import uuid4
 
 
@@ -54,3 +54,43 @@ def base_props() -> dict[str, Any]:
         "python": f"{sys.version_info.major}.{sys.version_info.minor}",
         "strix_version": get_version(),
     }
+
+
+# Coarse stage of the current run, attached to ``error`` beacons so a failure
+# can be placed without a message or trace. Process-local, like the rest of the
+# CLI telemetry: one process runs one scan.
+_scan_phase = "startup"
+
+
+def set_scan_phase(phase: str) -> None:
+    global _scan_phase  # noqa: PLW0603
+    _scan_phase = phase
+
+
+def get_scan_phase() -> str:
+    return _scan_phase
+
+
+def _exception_name(exc: BaseException) -> str:
+    cls = type(exc)
+    package = cls.__module__.split(".")[0]
+    return cls.__name__ if package == "builtins" else f"{package}.{cls.__name__}"
+
+
+def _unwrap_group(exc: BaseException) -> BaseException:
+    if not isinstance(exc, BaseExceptionGroup):
+        return exc
+    group = cast("BaseExceptionGroup[BaseException]", exc)
+    return group.exceptions[0] if group.exceptions else group
+
+
+def exception_props(exc: BaseException) -> dict[str, str]:
+    """Class names only. Messages, arguments, and tracebacks never leave the machine."""
+    exc = _unwrap_group(exc)
+    props = {"exception_type": _exception_name(exc)}
+    cause = exc.__cause__
+    if cause is None and not exc.__suppress_context__:
+        cause = exc.__context__
+    if cause is not None:
+        props["exception_cause"] = _exception_name(cause)
+    return props

strix/telemetry/posthog.py

@@ -9,6 +9,8 @@ from strix.telemetry._common import (
     SEND_TIMEOUT,
     SESSION_ID,
     base_props,
+    exception_props,
+    get_scan_phase,
     get_version,
     is_first_run,
 )
@@ -178,6 +180,12 @@ def viewer_agent_steered() -> None:
     _send("viewer_agent_steered", {**base_props()})
 
 
-def error(error_type: str) -> None:
-    props = {**base_props(), "error_type": error_type}
+def error(error_type: str, exc: BaseException | None = None) -> None:
+    props: dict[str, Any] = {
+        **base_props(),
+        "error_type": error_type,
+        "phase": get_scan_phase(),
+    }
+    if exc is not None:
+        props.update(exception_props(exc))
     _send("error", props)

strix/telemetry/scarf.py

@@ -12,6 +12,8 @@ from strix.telemetry._common import (
     SEND_TIMEOUT,
     SESSION_ID,
     base_props,
+    exception_props,
+    get_scan_phase,
     get_version,
     is_first_run,
 )
@@ -135,10 +137,13 @@ def end(report_state: ReportState, exit_reason: str = "completed") -> None:
     )
 
 
-def error(error_type: str) -> None:
+def error(error_type: str, exc: BaseException | None = None) -> None:
     props: dict[str, Any] = {
         **base_props(),
         "session": SESSION_ID,
         "error_type": error_type,
+        "phase": get_scan_phase(),
     }
+    if exc is not None:
+        props.update(exception_props(exc))
     _send("error", props)

strix/tools/agents_graph/tools.py

@@ -12,7 +12,8 @@ from typing import Any, Literal, get_args
 
 from agents import RunContextWrapper, function_tool
 
-from strix.core.agents import Status, coordinator_from_context
+from strix.config import load_settings
+from strix.core.agents import AgentCoordinator, Status, coordinator_from_context
 from strix.core.execution import notify_parent_on_terminal
 from strix.core.hooks import LLM_TURN_KEY
 from strix.report.state import get_global_report_state
@@ -291,6 +292,16 @@ _WAIT_DEFAULT_TIMEOUT_S = 300
 # tool's own timeout fire first and return a clean result.
 _WAIT_HARD_CEILING_S = _WAIT_DEFAULT_TIMEOUT_S + 1
 _WAITED_TURN_KEY = "waited_llm_turn"
+# Headroom past the per-turn stall guard so a wedged agent gets to abandon and
+# replay its own turn before a waiting parent gives up on it.
+_STALL_REAP_GRACE_S = 300.0
+
+
+async def _reap_stalled_agents(coordinator: AgentCoordinator, me: str) -> list[dict[str, Any]]:
+    stall_timeout = float(load_settings().runtime.agent_stall_timeout)
+    if stall_timeout <= 0:
+        return []
+    return await coordinator.reap_stalled(stall_timeout + _STALL_REAP_GRACE_S, under=me)
 
 
 @function_tool(timeout=_WAIT_HARD_CEILING_S)
@@ -422,6 +433,8 @@ async def wait_for_agents(  # noqa: PLR0911
             default=str,
         )
 
+    stalled = await _reap_stalled_agents(coordinator, me)
+
     # Non-interactive agents cannot be woken once terminal, so with nobody
     # running or waiting there is no message left to wait for.
     if not await coordinator.active_agents_except(me):
@@ -431,6 +444,7 @@ async def wait_for_agents(  # noqa: PLR0911
                 "success": True,
                 "wait_outcome": "no_active_agents",
                 "reason": reason,
+                "stalled_agents": stalled,
                 "agents": [
                     {"agent_id": aid, "name": names.get(aid, aid), "status": status}
                     for aid, status in statuses.items()
@@ -452,13 +466,22 @@ async def wait_for_agents(  # noqa: PLR0911
         await asyncio.wait_for(coordinator.wait_for_message(me), timeout_seconds)
     except TimeoutError:
         await coordinator.mark_running(me)
+        stalled = await _reap_stalled_agents(coordinator, me)
         return json.dumps(
             {
                 "success": True,
                 "wait_outcome": "timeout",
                 "timeout_seconds": timeout_seconds,
                 "reason": reason,
-                "note": "No messages within timeout — continue work or call agent_finish.",
+                "stalled_agents": stalled,
+                "note": (
+                    "No messages within timeout — continue work or call agent_finish."
+                    if not stalled
+                    else "No messages within timeout. The agents in stalled_agents produced "
+                    "no output for too long and were marked failed; treat this list as "
+                    "their failure notice. Do not wait on them again — continue work, "
+                    "respawn what is still needed, or call agent_finish."
+                ),
             },
             ensure_ascii=False,
             default=str,

tests/test_agent_stall_guard.py

@@ -0,0 +1,258 @@
+"""Tests for the per-agent stall guard.
+
+The model-stream idle watchdog only covers the model call. A turn can also
+wedge in what the run loop awaits *between* events — a re-issued request that
+never opens, a tool transport that never answers — and nothing bounded that,
+so the agent stayed ``running`` forever and its parent waited on it forever.
+Two layers now cover it: the run cycle abandons a turn that emits no event for
+the stall timeout, and a parent's ``wait_for_agents`` fails any agent that has
+been silent for longer still.
+"""
+
+from __future__ import annotations
+
+import asyncio
+import json
+import time
+from typing import TYPE_CHECKING, Any, cast
+
+import pytest
+from agents import RunConfig, Runner
+from agents.tool_context import ToolContext
+
+from strix.core import execution
+from strix.core.agents import AgentCoordinator
+from strix.tools.agents_graph import tools as graph_tools
+from strix.tools.agents_graph.tools import wait_for_agents
+
+
+if TYPE_CHECKING:
+    from collections.abc import Iterator
+
+
+class _HangingStream:
+    """Emits one event, then never produces another."""
+
+    def __init__(self) -> None:
+        self.run_loop_exception: BaseException | None = None
+        self.cancelled = False
+
+    async def stream_events(self) -> Any:
+        yield "first"
+        await asyncio.Event().wait()
+
+    def cancel(self, mode: str = "immediate") -> None:  # noqa: ARG002
+        self.cancelled = True
+
+
+class _HealthyStream:
+    def __init__(self) -> None:
+        self.run_loop_exception: BaseException | None = None
+
+    async def stream_events(self) -> Any:
+        for i in range(3):
+            await asyncio.sleep(0.01)
+            yield f"event-{i}"
+
+
+@pytest.fixture
+def _fast_stall(monkeypatch: pytest.MonkeyPatch) -> Iterator[None]:
+    monkeypatch.setattr(execution, "_agent_stall_timeout", lambda: 0.2)
+    monkeypatch.setattr(execution, "_TRANSIENT_MODEL_RETRY_BASE_DELAY_S", 0.0)
+    monkeypatch.setattr(execution, "_TRANSIENT_MODEL_RETRY_MAX_DELAY_S", 0.0)
+    yield
+
+
+def _serve(monkeypatch: pytest.MonkeyPatch, streams: list[Any]) -> dict[str, int]:
+    calls = {"n": 0}
+
+    def _fake_run_streamed(*_args: Any, **_kwargs: Any) -> Any:
+        stream = streams[calls["n"]]
+        calls["n"] += 1
+        return stream
+
+    monkeypatch.setattr(Runner, "run_streamed", _fake_run_streamed)
+    return calls
+
+
+async def _run_cycle(coordinator: AgentCoordinator) -> Any:
+    return await execution._run_cycle(
+        object(),
+        coordinator,
+        "root",
+        input_data="task",
+        run_config=cast("RunConfig", object()),
+        context={},
+        max_turns=5,
+        session=None,
+        interactive=False,
+        event_sink=None,
+        hooks=None,
+    )
+
+
+@pytest.mark.asyncio
+@pytest.mark.usefixtures("_fast_stall")
+async def test_hung_turn_is_abandoned_and_replayed(monkeypatch: pytest.MonkeyPatch) -> None:
+    hung = _HangingStream()
+    healthy = _HealthyStream()
+    calls = _serve(monkeypatch, [hung, healthy])
+    coordinator = AgentCoordinator()
+    await coordinator.register("root", "strix", parent_id=None)
+
+    started = time.monotonic()
+    result = await _run_cycle(coordinator)
+
+    assert result is healthy
+    assert calls["n"] == 2
+    assert hung.cancelled is True
+    assert time.monotonic() - started < 2
+
+
+@pytest.mark.asyncio
+@pytest.mark.usefixtures("_fast_stall")
+async def test_agent_that_never_recovers_is_marked_failed(
+    monkeypatch: pytest.MonkeyPatch,
+) -> None:
+    _serve(
+        monkeypatch,
+        [_HangingStream() for _ in range(execution._MAX_TRANSIENT_MODEL_RETRIES + 1)],
+    )
+    coordinator = AgentCoordinator()
+    await coordinator.register("root", "strix", parent_id=None)
+
+    with pytest.raises(TimeoutError, match="produced no event"):
+        await _run_cycle(coordinator)
+
+    assert coordinator.statuses["root"] == "crashed"
+
+
+@pytest.mark.asyncio
+async def test_stall_guard_is_off_when_disabled(monkeypatch: pytest.MonkeyPatch) -> None:
+    monkeypatch.setattr(execution, "_agent_stall_timeout", lambda: 0.0)
+    hung = _HangingStream()
+    _serve(monkeypatch, [hung])
+    coordinator = AgentCoordinator()
+    await coordinator.register("root", "strix", parent_id=None)
+
+    with pytest.raises(TimeoutError):
+        await asyncio.wait_for(_run_cycle(coordinator), timeout=0.5)
+
+    assert hung.cancelled is False
+
+
+# --- wait_for_agents reaps silent children ------------------------------------------
+
+
+async def _call_wait(coordinator: AgentCoordinator, args: dict[str, Any]) -> dict[str, Any]:
+    ctx = ToolContext(
+        context={"coordinator": coordinator, "agent_id": "root"},
+        tool_name=wait_for_agents.name,
+        tool_call_id="call-1",
+        tool_arguments="{}",
+    )
+    raw: str = await wait_for_agents.on_invoke_tool(ctx, json.dumps(args))
+    return cast("dict[str, Any]", json.loads(raw))
+
+
+@pytest.fixture
+def _reap_after(monkeypatch: pytest.MonkeyPatch) -> Iterator[None]:
+    async def _reap(coordinator: AgentCoordinator, me: str) -> list[dict[str, Any]]:
+        return await coordinator.reap_stalled(0.3, under=me)
+
+    monkeypatch.setattr(graph_tools, "_reap_stalled_agents", _reap)
+    yield
+
+
+@pytest.mark.asyncio
+@pytest.mark.usefixtures("_reap_after")
+async def test_waiting_parent_fails_a_child_silent_too_long() -> None:
+    coordinator = AgentCoordinator()
+    await coordinator.register("root", "strix", parent_id=None)
+    await coordinator.register("child", "ATO-Chaining", parent_id="root")
+    await coordinator.attach_runtime("root", resumable=False)
+    child_task = asyncio.create_task(asyncio.Event().wait())
+    await coordinator.attach_runtime("child", task=child_task, resumable=False)
+
+    result = await _call_wait(coordinator, {"timeout_seconds": 1})
+
+    assert result["wait_outcome"] == "timeout"
+    assert [a["agent_id"] for a in result["stalled_agents"]] == ["child"]
+    assert coordinator.statuses["child"] == "failed"
+    assert "stalled" in coordinator.errors["child"]
+    await asyncio.sleep(0)
+    assert child_task.cancelled()
+
+    # Nothing is left to wait on, so the next wait returns at once.
+    result = await _call_wait(coordinator, {"timeout_seconds": 60})
+    assert result["wait_outcome"] == "no_active_agents"
+
+
+@pytest.mark.asyncio
+@pytest.mark.usefixtures("_reap_after")
+async def test_child_that_keeps_emitting_events_is_left_alone() -> None:
+    coordinator = AgentCoordinator()
+    await coordinator.register("root", "strix", parent_id=None)
+    await coordinator.register("child", "DeepFuzz", parent_id="root")
+    await coordinator.attach_runtime("root", resumable=False)
+    await coordinator.attach_runtime("child", resumable=False)
+
+    async def _heartbeat() -> None:
+        for _ in range(12):
+            await asyncio.sleep(0.1)
+            coordinator.touch("child")
+
+    beat = asyncio.create_task(_heartbeat())
+    result = await _call_wait(coordinator, {"timeout_seconds": 1})
+    await beat
+
+    assert result["wait_outcome"] == "timeout"
+    assert result["stalled_agents"] == []
+    assert coordinator.statuses["child"] == "running"
+
+
+@pytest.mark.asyncio
+@pytest.mark.usefixtures("_reap_after")
+async def test_waiting_children_are_not_reaped() -> None:
+    # A child parked in its own wait emits no events by design.
+    coordinator = AgentCoordinator()
+    await coordinator.register("root", "strix", parent_id=None)
+    await coordinator.register("child", "Coordinator", parent_id="root")
+    await coordinator.attach_runtime("root", resumable=False)
+    await coordinator.attach_runtime("child", resumable=False)
+    await coordinator.park_waiting("child", wait_kind="agents")
+
+    result = await _call_wait(coordinator, {"timeout_seconds": 1})
+
+    assert result["wait_outcome"] == "timeout"
+    assert result["stalled_agents"] == []
+    assert coordinator.statuses["child"] == "waiting"
+
+
+@pytest.mark.asyncio
+async def test_reaping_is_off_when_disabled() -> None:
+    coordinator = AgentCoordinator()
+    await coordinator.register("root", "strix", parent_id=None)
+    await coordinator.register("child", "X", parent_id="root")
+    coordinator.runtimes["child"].last_activity -= 10_000
+
+    assert await coordinator.reap_stalled(0, under="root") == []
+    assert coordinator.statuses["child"] == "running"
+
+
+@pytest.mark.asyncio
+async def test_reaping_stays_inside_the_callers_subtree() -> None:
+    coordinator = AgentCoordinator()
+    await coordinator.register("root", "strix", parent_id=None)
+    await coordinator.register("a", "A", parent_id="root")
+    await coordinator.register("a1", "A1", parent_id="a")
+    await coordinator.register("b", "B", parent_id="root")
+    for aid in ("root", "a1", "b"):
+        coordinator.runtimes[aid].last_activity -= 10_000
+
+    reaped = await coordinator.reap_stalled(1, under="a")
+
+    assert [r["agent_id"] for r in reaped] == ["a1"]
+    assert coordinator.statuses["a1"] == "failed"
+    assert coordinator.statuses["b"] == "running"
+    assert coordinator.statuses["root"] == "running"

tests/test_models.py

@@ -79,6 +79,14 @@ def test_recommended_models_are_matched_case_insensitively() -> None:
         "zai/glm-5.3-flash",
         "openrouter/z-ai/glm-5.3",
         "novita/zai-org/glm-5.2",
+        "openai/glm-5.3",
+        "openai/zai-org/glm-5.3",
+        "hosted_vllm/glm-5.3",
+        "openai/claude-opus-4-8",
+        "openai/deepseek-v4-pro",
+        "custom-ollama/gpt-5-mini-local",
+        "custom-provider/claude-opus-4-local",
+        "custom-provider/glm-5.3-local",
     ],
 )
 def test_frontier_model_families_are_accepted(model_name: str) -> None:
@@ -93,15 +101,13 @@ def test_frontier_model_families_are_accepted(model_name: str) -> None:
         "anthropic/claude-3-5-sonnet-latest",
         "ollama/llama3.1",
         "deepseek/deepseek-chat",
-        "custom-ollama/gpt-5-mini-local",
-        "custom-provider/claude-opus-4-local",
         "xai/grok-4.5",
         "openrouter/x-ai/grok-4",
         "mistral/mistral-medium-3-5",
         "mistral/magistral-medium-latest",
         "zai/glm-4.7",
+        "openai/glm-4.7",
         "openrouter/z-ai/glm-5",
-        "custom-provider/glm-5.3-local",
     ],
 )
 def test_non_frontier_models_are_rejected(model_name: str) -> None:

tests/test_telemetry_errors.py

@@ -0,0 +1,125 @@
+"""Error beacons carry a category, phase, and exception class — never a message."""
+
+from __future__ import annotations
+
+from typing import Any
+
+import pytest
+import requests
+
+from strix.report.state import ReportState
+from strix.telemetry import posthog, report_error, scarf, set_scan_phase
+from strix.telemetry._common import exception_props
+
+
+PRIVATE_MESSAGE = "private message that must stay on the machine"
+
+
+def _capture(sent: list[dict[str, Any]], event: str, props: dict[str, Any]) -> bool:
+    sent.append({"event": event, **props})
+    return True
+
+
+def test_exception_props_uses_bare_name_for_builtins() -> None:
+    assert exception_props(ValueError(PRIVATE_MESSAGE)) == {"exception_type": "ValueError"}
+
+
+def test_exception_props_prefixes_third_party_top_level_package() -> None:
+    props = exception_props(requests.exceptions.ConnectTimeout(PRIVATE_MESSAGE))
+    assert props == {"exception_type": "requests.ConnectTimeout"}
+
+
+def _chained(cause: BaseException | None, *, explicit: bool) -> RuntimeError:
+    exc = RuntimeError("wrapped")
+    if explicit:
+        exc.__cause__ = cause
+        exc.__suppress_context__ = True
+    else:
+        exc.__context__ = cause
+    return exc
+
+
+def test_exception_props_reports_explicit_cause() -> None:
+    props = exception_props(_chained(ConnectionError(PRIVATE_MESSAGE), explicit=True))
+    assert props == {"exception_type": "RuntimeError", "exception_cause": "ConnectionError"}
+
+
+def test_exception_props_reports_implicit_context() -> None:
+    props = exception_props(_chained(KeyError("k"), explicit=False))
+    assert props["exception_cause"] == "KeyError"
+
+
+def test_exception_props_ignores_suppressed_context() -> None:
+    exc = _chained(None, explicit=True)
+    exc.__context__ = KeyError("k")
+    assert exception_props(exc) == {"exception_type": "RuntimeError"}
+
+
+def test_exception_props_unwraps_exception_group() -> None:
+    group = ExceptionGroup("tasks", [TimeoutError("t"), ValueError("v")])
+    assert exception_props(group) == {"exception_type": "TimeoutError"}
+
+
+@pytest.mark.parametrize("telemetry", [posthog, scarf])
+def test_error_event_carries_phase_and_class_but_no_message(
+    telemetry: Any,
+    monkeypatch: pytest.MonkeyPatch,
+) -> None:
+    sent: list[dict[str, Any]] = []
+    monkeypatch.setattr(telemetry, "_send", lambda event, props: _capture(sent, event, props))
+    set_scan_phase("sandbox_init")
+
+    telemetry.error("scan_failed", RuntimeError(PRIVATE_MESSAGE))
+
+    assert len(sent) == 1
+    event = sent[0]
+    assert event["event"] == "error"
+    assert event["error_type"] == "scan_failed"
+    assert event["phase"] == "sandbox_init"
+    assert event["exception_type"] == "RuntimeError"
+    assert PRIVATE_MESSAGE not in repr(event)
+
+
+@pytest.mark.parametrize("telemetry", [posthog, scarf])
+def test_error_event_without_exception_omits_exception_fields(
+    telemetry: Any,
+    monkeypatch: pytest.MonkeyPatch,
+) -> None:
+    sent: list[dict[str, Any]] = []
+    monkeypatch.setattr(telemetry, "_send", lambda event, props: _capture(sent, event, props))
+    set_scan_phase("startup")
+
+    telemetry.error("docker_not_installed")
+
+    assert sent[0]["error_type"] == "docker_not_installed"
+    assert sent[0]["phase"] == "startup"
+    assert "exception_type" not in sent[0]
+    assert "exception_cause" not in sent[0]
+
+
+def test_report_error_fans_out_to_both_backends(monkeypatch: pytest.MonkeyPatch) -> None:
+    sent: list[dict[str, Any]] = []
+    monkeypatch.setattr(posthog, "_send", lambda event, props: _capture(sent, event, props))
+    monkeypatch.setattr(scarf, "_send", lambda event, props: _capture(sent, event, props))
+
+    report_error("model_connection_failed", TimeoutError(PRIVATE_MESSAGE))
+
+    assert len(sent) == 2
+    assert {e["error_type"] for e in sent} == {"model_connection_failed"}
+    assert {e["exception_type"] for e in sent} == {"TimeoutError"}
+
+
+@pytest.mark.parametrize("telemetry", [posthog, scarf])
+def test_scan_ended_prefers_recorded_exit_reason(
+    telemetry: Any,
+    monkeypatch: pytest.MonkeyPatch,
+) -> None:
+    state = ReportState()
+    state.scan_ended_exit_reason = "budget_exceeded"
+    sent: list[dict[str, Any]] = []
+    monkeypatch.setattr(telemetry, "_send", lambda event, props: _capture(sent, event, props))
+
+    telemetry.end(state, exit_reason="user_exit")
+
+    assert sent[0]["event"] == "scan_ended"
+    assert sent[0]["exit_reason"] == "budget_exceeded"

uv.lock

@@ -2378,7 +2378,7 @@ wheels = [
 
 [[package]]
 name = "strix-agent"
-version = "1.6.1"
+version = "1.6.2"
 source = { editable = "." }
 dependencies = [
     { name = "caido-sdk-client" },