fix(telemetry): classify setup-mode TUI preflight and preparation failures

error events now carry phase (startup/preflight/sandbox_init/agent_setup/
agent_loop) and the exception class name (plus its cause), never the message
or trace. Startup and preflight failures that exit(1) before the scan starts
are beaconed with a stable error_type instead of vanishing. scan_ended
distinguishes budget_exceeded, rate_limited, and headless agent_stopped
from user_exit.

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/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
 
 
@@ -396,15 +396,18 @@ 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 +482,21 @@ 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/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/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)

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"