first commit

tests/test_config_loader.py

@@ -0,0 +1,178 @@
+"""Tests for strix.config.loader: JSON overrides, alias resolution, persistence."""
+
+from __future__ import annotations
+
+import json
+from typing import TYPE_CHECKING
+
+import pytest
+from pydantic import AliasChoices, Field
+from pydantic.fields import FieldInfo
+
+from strix.config import loader
+
+
+if TYPE_CHECKING:
+    from pathlib import Path
+
+
+_LLM_ENV_KEYS = [
+    "STRIX_LLM",
+    "LLM_API_KEY",
+    "OPENAI_API_KEY",
+    "LLM_API_BASE",
+    "OPENAI_API_BASE",
+    "OPENAI_BASE_URL",
+    "LITELLM_BASE_URL",
+    "OLLAMA_API_BASE",
+    "STRIX_REASONING_EFFORT",
+    "LLM_TIMEOUT",
+    "PERPLEXITY_API_KEY",
+    # RuntimeSettings
+    "STRIX_IMAGE",
+    "STRIX_RUNTIME_BACKEND",
+    "STRIX_MAX_LOCAL_COPY_MB",
+    # TelemetrySettings
+    "STRIX_TELEMETRY",
+]
+
+
+@pytest.fixture(autouse=True)
+def _reset_loader_state(monkeypatch: pytest.MonkeyPatch) -> None:
+    """Reset module globals and clear known env vars for deterministic runs."""
+    for key in _LLM_ENV_KEYS:
+        monkeypatch.delenv(key, raising=False)
+    monkeypatch.setattr(loader, "_cached", None)
+    monkeypatch.setattr(loader, "_override", None)
+
+
+# --------------------------------------------------------------------------- #
+# _read_json_overrides
+# --------------------------------------------------------------------------- #
+
+
+def test_read_json_overrides_missing_file(tmp_path: Path) -> None:
+    assert loader._read_json_overrides(tmp_path / "nope.json") == {}
+
+
+def test_read_json_overrides_corrupt_json(tmp_path: Path) -> None:
+    path = tmp_path / "cli-config.json"
+    path.write_text("{not valid json", encoding="utf-8")
+    assert loader._read_json_overrides(path) == {}
+
+
+def test_read_json_overrides_non_dict_env(tmp_path: Path) -> None:
+    path = tmp_path / "cli-config.json"
+    path.write_text(json.dumps({"env": ["not", "a", "dict"]}), encoding="utf-8")
+    assert loader._read_json_overrides(path) == {}
+
+
+def test_read_json_overrides_maps_to_nested_settings(tmp_path: Path) -> None:
+    path = tmp_path / "cli-config.json"
+    path.write_text(
+        json.dumps({"env": {"STRIX_LLM": "my-model", "PERPLEXITY_API_KEY": "pk"}}),
+        encoding="utf-8",
+    )
+    assert loader._read_json_overrides(path) == {
+        "llm": {"model": "my-model"},
+        "integrations": {"perplexity_api_key": "pk"},
+    }
+
+
+def test_read_json_overrides_skips_keys_already_in_environ(
+    tmp_path: Path, monkeypatch: pytest.MonkeyPatch
+) -> None:
+    monkeypatch.setenv("STRIX_LLM", "from-env")
+    path = tmp_path / "cli-config.json"
+    path.write_text(json.dumps({"env": {"STRIX_LLM": "from-file"}}), encoding="utf-8")
+    # env wins -> the JSON value is not surfaced as an init kwarg.
+    assert loader._read_json_overrides(path) == {}
+
+
+# --------------------------------------------------------------------------- #
+# _aliases_for
+# --------------------------------------------------------------------------- #
+
+
+def test_aliases_for_simple_alias() -> None:
+    finfo = FieldInfo(alias="SIMPLE_ALIAS")
+    assert loader._aliases_for(finfo) == ["SIMPLE_ALIAS"]
+
+
+def test_aliases_for_alias_choices() -> None:
+    finfo: FieldInfo = Field(  # type: ignore[assignment]
+        default=None,
+        validation_alias=AliasChoices("FIRST", "SECOND"),
+    )
+    assert loader._aliases_for(finfo) == ["FIRST", "SECOND"]
+
+
+def test_aliases_for_string_validation_alias() -> None:
+    finfo: FieldInfo = Field(default=None, validation_alias="STR_ALIAS")  # type: ignore[assignment]
+    assert loader._aliases_for(finfo) == ["STR_ALIAS"]
+
+
+def test_aliases_for_no_alias() -> None:
+    assert loader._aliases_for(FieldInfo()) == []
+
+
+# --------------------------------------------------------------------------- #
+# apply_config_override + load_settings round-trip
+# --------------------------------------------------------------------------- #
+
+
+def test_apply_override_and_load_settings_round_trip(tmp_path: Path) -> None:
+    path = tmp_path / "cli-config.json"
+    path.write_text(
+        json.dumps({"env": {"STRIX_LLM": "round-trip-model", "PERPLEXITY_API_KEY": "pk"}}),
+        encoding="utf-8",
+    )
+
+    loader.apply_config_override(path)
+    settings = loader.load_settings()
+
+    assert settings.llm.model == "round-trip-model"
+    assert settings.integrations.perplexity_api_key == "pk"
+    # Second call is memoized -> same object.
+    assert loader.load_settings() is settings
+
+
+def test_apply_config_override_invalidates_cache(tmp_path: Path) -> None:
+    first = tmp_path / "first.json"
+    first.write_text(json.dumps({"env": {"STRIX_LLM": "first-model"}}), encoding="utf-8")
+    second = tmp_path / "second.json"
+    second.write_text(json.dumps({"env": {"STRIX_LLM": "second-model"}}), encoding="utf-8")
+
+    loader.apply_config_override(first)
+    assert loader.load_settings().llm.model == "first-model"
+
+    loader.apply_config_override(second)
+    assert loader.load_settings().llm.model == "second-model"
+
+
+# --------------------------------------------------------------------------- #
+# persist_current
+# --------------------------------------------------------------------------- #
+
+
+def test_persist_current_writes_env_block(tmp_path: Path, monkeypatch: pytest.MonkeyPatch) -> None:
+    monkeypatch.setenv("STRIX_LLM", "persisted-model")
+    target = tmp_path / "sub" / "cli-config.json"
+    loader.apply_config_override(target)
+
+    loader.persist_current()
+
+    assert target.exists()
+    assert json.loads(target.read_text(encoding="utf-8")) == {
+        "env": {"STRIX_LLM": "persisted-model"}
+    }
+
+
+def test_persist_current_sets_0600_mode(tmp_path: Path, monkeypatch: pytest.MonkeyPatch) -> None:
+    monkeypatch.setenv("STRIX_LLM", "persisted-model")
+    target = tmp_path / "cli-config.json"
+    loader.apply_config_override(target)
+
+    loader.persist_current()
+
+    assert target.stat().st_mode & 0o777 == 0o600

tests/test_execution.py

@@ -0,0 +1,44 @@
+"""Tests for the scan-wide budget-stop signal on the agent coordinator."""
+
+from __future__ import annotations
+
+import asyncio
+
+import pytest
+
+from strix.core.agents import AgentCoordinator
+
+
+@pytest.mark.asyncio
+async def test_budget_stop_sets_flag() -> None:
+    coordinator = AgentCoordinator()
+    await coordinator.register("root", "strix", parent_id=None)
+
+    assert coordinator.budget_stopped is False
+    await coordinator.trigger_budget_stop()
+    assert coordinator.budget_stopped is True
+
+
+@pytest.mark.asyncio
+async def test_budget_stop_unblocks_parked_agent() -> None:
+    # A parent parked in wait_for_message (awaiting a child) must be released so
+    # it can exit, no matter where in the tree the budget limit was hit.
+    coordinator = AgentCoordinator()
+    await coordinator.register("parent", "strix", parent_id=None)
+
+    waiter = asyncio.create_task(coordinator.wait_for_message("parent"))
+    await asyncio.sleep(0)  # let the waiter park
+    assert not waiter.done()
+
+    await coordinator.trigger_budget_stop()
+    await asyncio.wait_for(waiter, timeout=1.0)
+
+
+@pytest.mark.asyncio
+async def test_wait_for_message_returns_immediately_after_budget_stop() -> None:
+    coordinator = AgentCoordinator()
+    await coordinator.register("agent", "recon", parent_id="parent")
+    await coordinator.trigger_budget_stop()
+
+    # No pending messages, but the stop flag short-circuits the wait.
+    await asyncio.wait_for(coordinator.wait_for_message("agent"), timeout=1.0)

tests/test_hooks.py

@@ -0,0 +1,108 @@
+"""Tests for budget enforcement in ReportUsageHooks."""
+
+from __future__ import annotations
+
+from unittest.mock import MagicMock, patch
+
+import pytest
+
+from strix.core.hooks import BudgetExceededError, ReportUsageHooks
+
+
+def _make_hooks(max_budget: float | None) -> ReportUsageHooks:
+    return ReportUsageHooks(model="test-model", max_budget_usd=max_budget)
+
+
+def _make_report_state(cost: float) -> MagicMock:
+    state = MagicMock()
+    state.get_total_llm_cost.return_value = cost
+    state.record_sdk_usage = MagicMock()
+    return state
+
+
+def _make_context(agent_id: str = "test-agent") -> MagicMock:
+    ctx: MagicMock = MagicMock()
+    ctx.context = {"agent_id": agent_id}
+    return ctx
+
+
+@pytest.mark.asyncio
+async def test_no_budget_never_raises() -> None:
+    hooks = _make_hooks(None)
+    state = _make_report_state(9999.0)
+    with patch("strix.core.hooks.get_global_report_state", return_value=state):
+        await hooks.on_llm_end(_make_context(), MagicMock(), MagicMock())
+
+
+@pytest.mark.asyncio
+async def test_under_budget_does_not_raise() -> None:
+    hooks = _make_hooks(10.0)
+    state = _make_report_state(9.99)
+    with patch("strix.core.hooks.get_global_report_state", return_value=state):
+        await hooks.on_llm_end(_make_context(), MagicMock(), MagicMock())
+
+
+@pytest.mark.asyncio
+async def test_at_budget_raises() -> None:
+    hooks = _make_hooks(10.0)
+    state = _make_report_state(10.0)
+    with (
+        patch("strix.core.hooks.get_global_report_state", return_value=state),
+        pytest.raises(BudgetExceededError),
+    ):
+        await hooks.on_llm_end(_make_context(), MagicMock(), MagicMock())
+
+
+@pytest.mark.asyncio
+async def test_over_budget_raises() -> None:
+    hooks = _make_hooks(10.0)
+    state = _make_report_state(10.01)
+    with (
+        patch("strix.core.hooks.get_global_report_state", return_value=state),
+        pytest.raises(BudgetExceededError),
+    ):
+        await hooks.on_llm_end(_make_context(), MagicMock(), MagicMock())
+
+
+@pytest.mark.asyncio
+async def test_budget_check_uses_live_cost_accessor() -> None:
+    # The check must read the live ledger, not the persisted run-record snapshot,
+    # so it stays accurate even when a save fails after a usage record.
+    hooks = _make_hooks(5.0)
+    state = _make_report_state(6.0)
+    with (
+        patch("strix.core.hooks.get_global_report_state", return_value=state),
+        pytest.raises(BudgetExceededError),
+    ):
+        await hooks.on_llm_end(_make_context(), MagicMock(), MagicMock())
+    state.get_total_llm_cost.assert_called_once()
+    state.get_total_llm_usage.assert_not_called()
+
+
+@pytest.mark.asyncio
+async def test_error_message_includes_amounts() -> None:
+    hooks = _make_hooks(5.0)
+    state = _make_report_state(7.1234)
+    with patch("strix.core.hooks.get_global_report_state", return_value=state):
+        with pytest.raises(BudgetExceededError, match=r"\$5\.00") as exc_info:
+            await hooks.on_llm_end(_make_context(), MagicMock(), MagicMock())
+        assert "7.1234" in str(exc_info.value)
+
+
+@pytest.mark.asyncio
+async def test_no_raise_when_report_state_none() -> None:
+    hooks = _make_hooks(1.0)
+    with patch("strix.core.hooks.get_global_report_state", return_value=None):
+        # Should return early without raising, even with budget set
+        await hooks.on_llm_end(_make_context(), MagicMock(), MagicMock())
+
+
+@pytest.mark.parametrize("bad_budget", [0.0, -0.01, -5.0])
+def test_non_positive_budget_rejected(bad_budget: float) -> None:
+    with pytest.raises(ValueError, match="greater than 0"):
+        ReportUsageHooks(model="test-model", max_budget_usd=bad_budget)
+
+
+def test_budget_exceeded_error_is_runtime_error() -> None:
+    err = BudgetExceededError("test")
+    assert isinstance(err, RuntimeError)

tests/test_inputs.py

@@ -0,0 +1,114 @@
+"""Tests for pure input builders in strix.core.inputs."""
+
+from __future__ import annotations
+
+from itertools import pairwise
+from typing import Any
+
+import pytest
+
+from strix.core.inputs import build_root_task, child_initial_input
+
+
+def _child_kwargs(parent_history: list[Any]) -> dict[str, Any]:
+    return {
+        "name": "scout",
+        "child_id": "agent-2",
+        "parent_id": "agent-1",
+        "task": "Audit the login flow.",
+        "parent_history": parent_history,
+    }
+
+
+def test_child_initial_input_single_message_without_history() -> None:
+    result = child_initial_input(**_child_kwargs([]))
+
+    assert len(result) == 1
+    assert result[0]["role"] == "user"
+    content = result[0]["content"]
+    assert "agent scout (agent-2)" in content
+    assert "Audit the login flow." in content
+    assert "Inherited context" not in content
+
+
+def test_child_initial_input_single_message_with_history() -> None:
+    history = [{"role": "assistant", "content": "previous work"}]
+    result = child_initial_input(**_child_kwargs(history))
+
+    assert len(result) == 1
+    assert result[0]["role"] == "user"
+    content = result[0]["content"]
+    assert "Inherited context from parent" in content
+    assert "previous work" in content
+    assert "agent scout (agent-2)" in content
+    assert "Audit the login flow." in content
+
+
+@pytest.mark.parametrize(
+    "parent_history",
+    [[], [{"role": "assistant", "content": "previous work"}]],
+)
+def test_child_initial_input_no_consecutive_same_role(parent_history: list[Any]) -> None:
+    result = child_initial_input(**_child_kwargs(parent_history))
+
+    roles = [msg["role"] for msg in result]
+    assert all(prev != nxt for prev, nxt in pairwise(roles))
+
+
+def test_build_root_task_empty_config() -> None:
+    assert build_root_task({}) == ""
+
+
+def test_build_root_task_repository_target() -> None:
+    config = {
+        "targets": [
+            {
+                "type": "repository",
+                "details": {
+                    "target_repo": "https://example.com/repo.git",
+                    "cloned_repo_path": "/workspace/repo",
+                    "workspace_subdir": "repo",
+                },
+            },
+        ],
+    }
+    task = build_root_task(config)
+
+    assert "Repositories:" in task
+    assert "/workspace/repo" in task
+    assert "https://example.com/repo.git" in task
+
+
+def test_build_root_task_web_application_with_instructions() -> None:
+    config = {
+        "targets": [
+            {"type": "web_application", "details": {"target_url": "https://app.example.com"}},
+        ],
+        "user_instructions": "Focus on auth.",
+    }
+    task = build_root_task(config)
+
+    assert "URLs:" in task
+    assert "https://app.example.com" in task
+    assert "Special instructions: Focus on auth." in task
+
+
+def test_build_root_task_diff_scope() -> None:
+    config = {
+        "targets": [],
+        "diff_scope": {
+            "active": True,
+            "repos": [
+                {
+                    "workspace_subdir": "repo",
+                    "analyzable_files_count": 3,
+                    "deleted_files_count": 2,
+                },
+            ],
+        },
+    }
+    task = build_root_task(config)
+
+    assert "Scope Constraints:" in task
+    assert "3 changed file(s)" in task
+    assert "2 deleted file(s)" in task

tests/test_local_sources.py

@@ -0,0 +1,188 @@
+"""Tests for local-source sizing and ``--mount`` target helpers in interface.utils."""
+
+from __future__ import annotations
+
+import logging
+import os
+import sys
+from typing import TYPE_CHECKING, Any
+
+import pytest
+
+
+if TYPE_CHECKING:
+    from pathlib import Path
+
+from strix.interface.utils import (
+    build_mount_targets_info,
+    collect_local_sources,
+    dedupe_local_targets,
+    directory_size_bytes,
+    find_oversized_local_targets,
+)
+
+
+def _write_file(path: Path, size: int) -> None:
+    path.write_bytes(b"x" * size)
+
+
+def _local_target(target_path: str, *, mount: bool = False) -> dict[str, Any]:
+    details: dict[str, Any] = {"target_path": target_path, "workspace_subdir": "repo"}
+    if mount:
+        details["mount"] = True
+    return {"type": "local_code", "details": details, "original": target_path}
+
+
+def test_directory_size_empty_dir_is_zero(tmp_path: Path) -> None:
+    assert directory_size_bytes(tmp_path) == 0
+
+
+def test_directory_size_sums_flat_and_nested_files(tmp_path: Path) -> None:
+    _write_file(tmp_path / "a.txt", 100)
+    nested = tmp_path / "sub" / "deep"
+    nested.mkdir(parents=True)
+    _write_file(nested / "b.txt", 250)
+    assert directory_size_bytes(tmp_path) == 350
+
+
+def test_directory_size_skips_symlinks(tmp_path: Path) -> None:
+    _write_file(tmp_path / "real.txt", 100)
+    (tmp_path / "link.txt").symlink_to(tmp_path / "real.txt")
+    # The symlink target is counted once via the real file, not doubled.
+    assert directory_size_bytes(tmp_path) == 100
+
+
+@pytest.mark.skipif(sys.platform == "win32", reason="relies on POSIX permissions")
+def test_directory_size_logs_and_skips_unreadable_subdir(
+    tmp_path: Path, caplog: pytest.LogCaptureFixture
+) -> None:
+    if hasattr(os, "geteuid") and os.geteuid() == 0:
+        pytest.skip("root bypasses directory permissions")
+    _write_file(tmp_path / "top.txt", 100)
+    locked = tmp_path / "locked"
+    locked.mkdir()
+    _write_file(locked / "secret.bin", 9999)
+    locked.chmod(0o000)
+    try:
+        with caplog.at_level(logging.WARNING):
+            size = directory_size_bytes(tmp_path)
+    finally:
+        locked.chmod(0o755)
+    # The unreadable subtree is excluded (not silently treated as readable) and
+    # the omission is logged rather than vanishing without a trace.
+    assert size == 100
+    assert any("Could not read" in record.message for record in caplog.records)
+
+
+def test_find_oversized_returns_nothing_under_limit(tmp_path: Path) -> None:
+    _write_file(tmp_path / "a.txt", 100)
+    targets = [_local_target(str(tmp_path))]
+    assert find_oversized_local_targets(targets, max_bytes=1000) == []
+
+
+def test_find_oversized_returns_target_over_limit(tmp_path: Path) -> None:
+    _write_file(tmp_path / "big.bin", 500)
+    targets = [_local_target(str(tmp_path))]
+    result = find_oversized_local_targets(targets, max_bytes=100)
+    assert result == [(str(tmp_path), 500)]
+
+
+def test_find_oversized_ignores_mounted_targets(tmp_path: Path) -> None:
+    _write_file(tmp_path / "big.bin", 500)
+    targets = [_local_target(str(tmp_path), mount=True)]
+    assert find_oversized_local_targets(targets, max_bytes=100) == []
+
+
+def test_find_oversized_ignores_non_local_targets() -> None:
+    targets = [{"type": "web_application", "details": {"target_url": "https://x"}}]
+    assert find_oversized_local_targets(targets, max_bytes=1) == []
+
+
+@pytest.mark.parametrize("disabled", [0, -1])
+def test_find_oversized_disabled_for_non_positive_limit(tmp_path: Path, disabled: int) -> None:
+    _write_file(tmp_path / "big.bin", 500)
+    targets = [_local_target(str(tmp_path))]
+    assert find_oversized_local_targets(targets, max_bytes=disabled) == []
+
+
+def test_collect_local_sources_propagates_mount_flag() -> None:
+    copied = _local_target("/copied")
+    copied["details"]["workspace_subdir"] = "copied"
+    mounted = _local_target("/mounted", mount=True)
+    mounted["details"]["workspace_subdir"] = "mounted"
+
+    sources = collect_local_sources([copied, mounted])
+
+    by_path = {s["source_path"]: s for s in sources}
+    assert by_path["/copied"]["mount"] is False
+    assert by_path["/mounted"]["mount"] is True
+
+
+def test_collect_local_sources_repository_is_never_mounted() -> None:
+    repo = {
+        "type": "repository",
+        "details": {"cloned_repo_path": "/clone", "workspace_subdir": "clone"},
+    }
+    sources = collect_local_sources([repo])
+    assert sources == [{"source_path": "/clone", "workspace_subdir": "clone", "mount": False}]
+
+
+def test_build_mount_targets_info_for_valid_dir(tmp_path: Path) -> None:
+    result = build_mount_targets_info([str(tmp_path)])
+    assert len(result) == 1
+    entry = result[0]
+    assert entry["type"] == "local_code"
+    assert entry["details"]["mount"] is True
+    assert entry["details"]["target_path"] == str(tmp_path.resolve())
+
+
+def test_build_mount_targets_info_rejects_missing_path(tmp_path: Path) -> None:
+    missing = tmp_path / "does-not-exist"
+    with pytest.raises(ValueError, match="not an existing directory"):
+        build_mount_targets_info([str(missing)])
+
+
+def test_build_mount_targets_info_rejects_file(tmp_path: Path) -> None:
+    file_path = tmp_path / "a-file.txt"
+    _write_file(file_path, 10)
+    with pytest.raises(ValueError, match="not an existing directory"):
+        build_mount_targets_info([str(file_path)])
+
+
+@pytest.mark.parametrize("empty", ["", "   "])
+def test_build_mount_targets_info_rejects_empty_path(empty: str) -> None:
+    # An empty path would otherwise resolve to the current working directory
+    # and silently bind-mount it into the sandbox.
+    with pytest.raises(ValueError, match="must not be empty"):
+        build_mount_targets_info([empty])
+
+
+def test_dedupe_keeps_distinct_targets_in_order() -> None:
+    targets = [
+        _local_target("/a"),
+        {"type": "web_application", "details": {"target_url": "https://x"}},
+        _local_target("/b", mount=True),
+    ]
+    assert dedupe_local_targets(targets) == targets
+
+
+def test_dedupe_mount_supersedes_copied_same_path() -> None:
+    copied = _local_target("/repo")
+    mounted = _local_target("/repo", mount=True)
+
+    # Copied first, then mounted: the single surviving entry is the mount.
+    result = dedupe_local_targets([copied, mounted])
+    assert len(result) == 1
+    assert result[0]["details"]["mount"] is True
+
+    # Order-independent: mounted first, copied second also yields the mount.
+    result_rev = dedupe_local_targets([mounted, copied])
+    assert len(result_rev) == 1
+    assert result_rev[0]["details"]["mount"] is True
+
+
+def test_dedupe_collapses_duplicate_mounts() -> None:
+    result = dedupe_local_targets(
+        [_local_target("/repo", mount=True), _local_target("/repo", mount=True)]
+    )
+    assert len(result) == 1

tests/test_runner_rate_limit.py

@@ -0,0 +1,84 @@
+"""Tests for graceful handling of persistent RateLimitError in run_strix_scan."""
+
+from __future__ import annotations
+
+import logging
+import types
+from typing import Any
+
+import httpx
+import pytest
+from openai import RateLimitError
+
+import strix.tools.notes.tools as notes_tools
+import strix.tools.todo.tools as todo_tools
+from strix.core import runner
+from strix.core.agents import AgentCoordinator
+
+
+def _make_rate_limit_error() -> RateLimitError:
+    request = httpx.Request("POST", "https://api.openai.com/v1/responses")
+    response = httpx.Response(status_code=429, request=request)
+    return RateLimitError("rate limited", response=response, body=None)
+
+
+@pytest.mark.asyncio
+async def test_persistent_rate_limit_stops_gracefully(
+    monkeypatch: pytest.MonkeyPatch, tmp_path: Any, caplog: pytest.LogCaptureFixture
+) -> None:
+    """A persistent RateLimitError stops the scan (root -> 'stopped') without raising."""
+    monkeypatch.setattr(runner, "run_dir_for", lambda _scan_id: tmp_path)
+    monkeypatch.setattr(runner, "runtime_state_dir", lambda _run_dir: tmp_path)
+    monkeypatch.setattr(runner, "setup_scan_logging", lambda _run_dir: lambda: None)
+    monkeypatch.setattr(runner, "set_scan_id", lambda _scan_id: None)
+
+    settings = types.SimpleNamespace(
+        llm=types.SimpleNamespace(model="openai/gpt-4o", reasoning_effort="high")
+    )
+    monkeypatch.setattr(runner, "load_settings", lambda: settings)
+    monkeypatch.setattr(runner, "configure_sdk_model_defaults", lambda _settings: None)
+    monkeypatch.setattr(
+        runner, "uses_chat_completions_tool_schema", lambda _model, _settings: False
+    )
+
+    monkeypatch.setattr(todo_tools, "hydrate_todos_from_disk", lambda _state_dir: None)
+    monkeypatch.setattr(notes_tools, "hydrate_notes_from_disk", lambda _state_dir: None)
+
+    async def _create_or_reuse(*_args: Any, **_kwargs: Any) -> dict[str, Any]:
+        return {"client": object(), "session": object(), "caido_client": None}
+
+    async def _cleanup(*_args: Any, **_kwargs: Any) -> None:
+        return None
+
+    monkeypatch.setattr(runner.session_manager, "create_or_reuse", _create_or_reuse)
+    monkeypatch.setattr(runner.session_manager, "cleanup", _cleanup)
+
+    monkeypatch.setattr(runner, "build_root_task", lambda _scan_config: "task")
+    monkeypatch.setattr(runner, "build_scope_context", lambda _scan_config: "")
+    monkeypatch.setattr(runner, "make_model_settings", lambda *_args, **_kwargs: object())
+    monkeypatch.setattr(runner, "build_strix_agent", lambda **_kwargs: object())
+    monkeypatch.setattr(runner, "make_child_factory", lambda **_kwargs: lambda **_k: object())
+    monkeypatch.setattr(runner, "open_agent_session", lambda _root_id, _db: object())
+
+    async def _raise_rate_limit(*_args: Any, **_kwargs: Any) -> None:
+        raise _make_rate_limit_error()
+
+    monkeypatch.setattr(runner, "run_agent_loop", _raise_rate_limit)
+
+    coordinator = AgentCoordinator()
+
+    with caplog.at_level(logging.WARNING):
+        result = await runner.run_strix_scan(
+            scan_config={"targets": [], "scan_mode": "deep"},
+            scan_id="scan-test",
+            image="img",
+            coordinator=coordinator,
+        )
+
+    assert result is None
+    root_ids = [aid for aid, parent in coordinator.parent_of.items() if parent is None]
+    assert len(root_ids) == 1
+    assert coordinator.statuses[root_ids[0]] == "stopped"
+    # the resume hint must carry the real scan id, not a literal placeholder
+    assert "strix --resume scan-test" in caplog.text
+    assert "<run_name>" not in caplog.text

tests/test_session_entries.py

@@ -0,0 +1,67 @@
+"""Tests for build_session_entries: splitting copied vs bind-mounted sources."""
+
+from __future__ import annotations
+
+from typing import TYPE_CHECKING, Any
+
+from agents.sandbox.entries import LocalDir
+
+from strix.runtime.session_manager import build_session_entries
+
+
+if TYPE_CHECKING:
+    from pathlib import Path
+
+
+def _source(subdir: str, path: str, *, mount: bool = False) -> dict[str, Any]:
+    return {"source_path": path, "workspace_subdir": subdir, "mount": mount}
+
+
+def test_copied_source_becomes_localdir_entry(tmp_path: Path) -> None:
+    entries, bind_mounts = build_session_entries([_source("repo", str(tmp_path))])
+
+    assert bind_mounts == []
+    assert isinstance(entries["repo"], LocalDir)
+    assert entries["repo"].src == tmp_path.resolve()
+
+
+def test_mounted_source_becomes_bind_mount(tmp_path: Path) -> None:
+    entries, bind_mounts = build_session_entries([_source("repo", str(tmp_path), mount=True)])
+
+    assert entries == {}
+    assert bind_mounts == [
+        {
+            "source": str(tmp_path.resolve()),
+            "target": "/workspace/repo",
+            "read_only": True,
+        }
+    ]
+
+
+def test_mixed_sources_split_correctly(tmp_path: Path) -> None:
+    copied = tmp_path / "copied"
+    mounted = tmp_path / "mounted"
+    copied.mkdir()
+    mounted.mkdir()
+
+    entries, bind_mounts = build_session_entries(
+        [
+            _source("copied", str(copied)),
+            _source("mounted", str(mounted), mount=True),
+        ]
+    )
+
+    assert list(entries) == ["copied"]
+    assert isinstance(entries["copied"], LocalDir)
+    assert [m["target"] for m in bind_mounts] == ["/workspace/mounted"]
+
+
+def test_incomplete_sources_are_skipped() -> None:
+    entries, bind_mounts = build_session_entries(
+        [
+            {"source_path": "", "workspace_subdir": "x"},
+            {"source_path": "/p", "workspace_subdir": ""},
+        ]
+    )
+    assert entries == {}
+    assert bind_mounts == []