Revert the Vercel AI Gateway image-rejection guess

It also matched errors about one image form, e.g. Groq's
'Non-image file content parts' functionality not supported.

README.md

@@ -94,18 +94,6 @@ strix --target ./app-directory
 > [!NOTE]
 > First run automatically pulls the sandbox Docker image. Results are saved to `strix_runs/<run-name>`
 
-### Updating
-
-```bash
-# Self-update the standalone binary to the latest release
-strix --update
-
-# ...or re-run the installer
-curl -sSL https://strix.ai/install | bash
-```
-
-Installed with pipx, uv, or pip? `strix --update` prints the matching upgrade command instead (`pipx upgrade strix-agent`, `uv tool upgrade strix-agent`, `pip install --upgrade strix-agent`). Strix also shows a notice with the right command when a new version is available.
-
 ---
 
 ## Ways to Run Strix

strix/agents/factory.py

@@ -675,7 +675,6 @@ def build_strix_agent(
     extra_tools: Sequence[Tool] | None = None,
     instructions_override: str | None = None,
     supports_images: bool = True,
-    finish_tool: Tool = finish_scan,
 ) -> SandboxAgent[Any]:
     """Build a SandboxAgent for either root or child use.
 
@@ -688,7 +687,6 @@ def build_strix_agent(
             registered via ``register_agent_tools``.
         instructions_override: Use this verbatim as the system prompt instead
             of rendering the built-in scan prompt.
-        finish_tool: The tool that ends the run, given to the root agent.
     """
     if instructions_override is not None:
         instructions = instructions_override
@@ -709,7 +707,7 @@ def build_strix_agent(
         # Yielding to the user is only meaningful when one is attached.
         agent_tools.append(wait_for_user)
     if is_root:
-        tools: list[Tool] = [*_BASE_TOOLS, *agent_tools, finish_tool]
+        tools: list[Tool] = [*_BASE_TOOLS, *agent_tools, finish_scan]
     else:
         tools = [*_BASE_TOOLS, *agent_tools, agent_finish]
     _ensure_unique_tool_names(tools)

strix/agents/prompts/scope.jinja

@@ -21,7 +21,7 @@ MCP CONNECTIONS (available this run):
 {% if system_prompt_context.mcp_connections %}
 - Connected this run (search one to find relevant tools):
 {% for connection in system_prompt_context.mcp_connections %}
-  - {{ connection.name }}{% if connection.state == "unavailable" %} (unavailable right now){% elif connection.tool_count is not none %} ({{ connection.tool_count }} tools){% endif %}{% if connection.purpose %}: {{ connection.purpose }}{% endif %}
+  - {{ connection.name }} ({{ connection.tool_count }} tools){% if connection.purpose %}: {{ connection.purpose }}{% endif %}
 {% endfor %}
 {% endif %}
 - Reach for a connection whenever the target itself cannot give you information a connection could: its database schema and access policies, real deployment or infrastructure configuration, known issues or prior findings, or server logs. In those cases call list_mcps early to see what is available, and prefer a connection's authoritative data over inferring from the target's responses. Do not wait to be told a connection exists.

strix/config/models.py

@@ -5,7 +5,6 @@ from __future__ import annotations
 import asyncio
 import contextlib
 import inspect
-import json
 import logging
 import os
 import time
@@ -263,8 +262,6 @@ class _TurnGuardModel(Model):
     not covered by the request timeout, which resets on any byte (keepalives
     included). ``LLM_STREAM_IDLE_TIMEOUT`` bounds the gap between events so the
     turn fails instead of hanging, and the existing retry path replays it.
-    ``LLM_STREAM_FIRST_EVENT_TIMEOUT`` and ``LLM_STREAM_TOTAL_TIMEOUT`` bound
-    the first event and the whole stream.
     """
 
     def __init__(
@@ -272,15 +269,11 @@ class _TurnGuardModel(Model):
         inner: Model,
         *,
         max_tool_calls_per_turn: int = 0,
-        stream_idle_timeout: float | None = None,
-        first_event_timeout: float | None = None,
-        total_timeout: float | None = None,
+        stream_idle_timeout: float = 0.0,
     ) -> None:
         self._inner = inner
         self._max_tool_calls_per_turn = max_tool_calls_per_turn
         self._stream_idle_timeout = stream_idle_timeout
-        self._first_event_timeout = first_event_timeout
-        self._total_timeout = total_timeout
 
     def _limiter(self) -> TurnToolCallLimiter:
         return TurnToolCallLimiter(self._max_tool_calls_per_turn)
@@ -367,12 +360,7 @@ class _TurnGuardModel(Model):
             conversation_id=conversation_id,
             prompt=prompt,
         )
-        async for event in _with_timeouts(
-            stream,
-            idle=self._stream_idle_timeout,
-            first_event=self._first_event_timeout,
-            total=self._total_timeout,
-        ):
+        async for event in _with_idle_timeout(stream, self._stream_idle_timeout):
             guarded = _guard_event(event, rewriter, limiter)
             if guarded is not None:
                 yield guarded
@@ -406,68 +394,28 @@ async def _aclose(stream: AsyncIterator[TResponseStreamEvent]) -> None:
             await stream.aclose()
 
 
-async def _with_timeouts(
-    stream: AsyncIterator[TResponseStreamEvent],
-    *,
-    idle: float | None = None,
-    first_event: float | None = None,
-    total: float | None = None,
+async def _with_idle_timeout(
+    stream: AsyncIterator[TResponseStreamEvent], timeout: float
 ) -> AsyncIterator[TResponseStreamEvent]:
-    """Bound the first event, the gap between events and the whole stream; None is no bound."""
+    if timeout <= 0:
+        async for event in stream:
+            yield event
+        return
+
     iterator = stream.__aiter__()
-    started = time.monotonic()
     while True:
-        limits: list[tuple[float, float, str]] = []
-        # Wait until the soonest limit expires: first-event (else idle) until the
-        # first event arrives, then idle; plus whatever is left of the total.
-        if first_event is not None:
-            limits.append((first_event, first_event, "stream_first_event_timeout"))
-        elif idle is not None:
-            limits.append((idle, idle, "stream_idle_timeout"))
-        if total is not None:
-            left = max(0.0, started + total - time.monotonic())
-            limits.append((left, total, "stream_total_timeout"))
         try:
-            if limits:
-                event = await _next_event(iterator, *min(limits))
-            else:
-                event = await iterator.__anext__()
+            event = await asyncio.wait_for(iterator.__anext__(), timeout)
         except StopAsyncIteration:
             return
-        except TimeoutError as exc:
+        except TimeoutError:
             await _aclose(stream)
-            logger.warning("%s; abandoning the turn", exc)
-            raise
-        first_event = None
+            message = f"model stream produced no event for {timeout:.0f}s"
+            logger.warning("%s; abandoning the turn", message)
+            raise TimeoutError(message) from None
         yield event
 
 
-async def _next_event(
-    iterator: AsyncIterator[TResponseStreamEvent], wait: float, limit: float, reason: str
-) -> TResponseStreamEvent:
-    # asyncio.timeout() cancels without a message, so the request log could not
-    # tell this from a shutdown; this is asyncio.timeout() with a message.
-    task = asyncio.current_task()
-    assert task is not None
-    cancelling = task.cancelling()
-    expired = False
-
-    def expire() -> None:
-        nonlocal expired
-        expired = True
-        task.cancel(msg=f"{request_log.CANCEL_REASON_PREFIX}{reason}")
-
-    handle = asyncio.get_running_loop().call_later(wait, expire)
-    try:
-        return await iterator.__anext__()
-    except BaseException as exc:
-        if expired and task.uncancel() <= cancelling and isinstance(exc, asyncio.CancelledError):
-            raise TimeoutError(f"model stream hit {reason} ({limit:.0f}s)") from None
-        raise
-    finally:
-        handle.cancel()
-
-
 def _guard_event(
     event: TResponseStreamEvent, rewriter: TurnCallIdRewriter, limiter: TurnToolCallLimiter
 ) -> TResponseStreamEvent | None:
@@ -602,10 +550,7 @@ class StrixProvider(MultiProvider):
     def get_model(self, model_name: str | None) -> Model:
         llm = load_settings().llm
         slug = codex.subscription_model(model_name)
-        # The settings use 0 for no bound.
-        idle_timeout = float(llm.stream_idle_timeout) or None
-        first_event_timeout = float(llm.stream_first_event_timeout) or None
-        total_timeout = float(llm.stream_total_timeout) or None
+        idle_timeout = float(llm.stream_idle_timeout)
         if slug:
             # The ChatGPT subscription backend is always streamed; it has no
             # non-streaming mode to fall back to, so LLM_DISABLE_STREAMING
@@ -646,13 +591,11 @@ class StrixProvider(MultiProvider):
                 # The wrapper emits its single event only once the whole request
                 # is done, so an idle gap is meaningless here; the request
                 # timeout bounds it instead.
-                idle_timeout = first_event_timeout = total_timeout = None
+                idle_timeout = 0.0
         return _TurnGuardModel(
             model,
             max_tool_calls_per_turn=llm.max_tool_calls_per_turn,
             stream_idle_timeout=idle_timeout,
-            first_event_timeout=first_event_timeout,
-            total_timeout=total_timeout,
         )
 
 
@@ -802,11 +745,6 @@ def _install_openrouter_stream_cost_capture() -> None:
 
     class _StrixOpenRouterStreamingHandler(OpenRouterChatCompletionStreamingHandler):
         def chunk_parser(self, chunk: dict[str, Any]) -> Any:
-            # Before parsing: LiteLLM raises on an error chunk and drops its
-            # top-level ``provider``.
-            request_log.record_upstream_provider(
-                chunk.get("provider"), _openrouter_error_type(chunk.get("error"))
-            )
             stream = super().chunk_parser(chunk)
             usage = chunk.get("usage")
             response_id = chunk.get("id") or getattr(stream, "id", None)
@@ -825,22 +763,12 @@ def _install_openrouter_stream_cost_capture() -> None:
                 json_mode=json_mode,
             )
 
-        def get_error_class(self, error_message: str, status_code: int, headers: Any) -> Any:
-            # A non-2xx reply names the provider in ``error.metadata``.
-            with contextlib.suppress(Exception):
-                error = json.loads(error_message)["error"]
-                request_log.record_upstream_provider(
-                    error["metadata"].get("provider_name"), _openrouter_error_type(error)
-                )
-            return super().get_error_class(error_message, status_code, headers)
-
         def transform_response(self, *args: Any, **kwargs: Any) -> Any:
             # Non-streamed replies (LLM_DISABLE_STREAMING) skip the chunk parser.
             response = super().transform_response(*args, **kwargs)
             raw_response = kwargs.get("raw_response", args[1] if len(args) > 1 else None)
             with contextlib.suppress(Exception):
                 body = raw_response.json()  # type: ignore[union-attr]
-                request_log.record_upstream_provider(body.get("provider"))
                 if body.get("usage"):
                     record_openrouter_provider(body.get("provider"), body["usage"])
             return response
@@ -861,14 +789,6 @@ def _install_openrouter_stream_cost_capture() -> None:
     litellm.OpenrouterConfig = _StrixOpenrouterConfig  # type: ignore[misc]
 
 
-def _openrouter_error_type(error: object) -> object:
-    if isinstance(error, dict):
-        metadata = error.get("metadata")
-        if isinstance(metadata, dict):
-            return metadata.get("error_type")
-    return None
-
-
 OPENROUTER_ATTRIBUTION_HEADERS = {
     "HTTP-Referer": "https://strix.ai",
     "X-Title": "Strix",

strix/config/settings.py

@@ -79,10 +79,6 @@ class LlmSettings(BaseSettings):
     timeout: int = Field(default=300, alias="LLM_TIMEOUT")
     preflight_timeout: int = Field(default=30, ge=1, alias="LLM_PREFLIGHT_TIMEOUT")
     stream_idle_timeout: int = Field(default=300, ge=0, alias="LLM_STREAM_IDLE_TIMEOUT")
-    stream_first_event_timeout: int = Field(
-        default=120, ge=0, alias="LLM_STREAM_FIRST_EVENT_TIMEOUT"
-    )
-    stream_total_timeout: int = Field(default=600, ge=0, alias="LLM_STREAM_TOTAL_TIMEOUT")
     max_tool_calls_per_turn: int = Field(
         default=32,
         ge=0,

strix/core/agents.py

@@ -71,7 +71,6 @@ class AgentCoordinator:
         self._lock = asyncio.Lock()
         self._snapshot_path: Path | None = None
         self.is_shutting_down = False
-        self.root_finish_tool = "finish_scan"
         self._budget_stopped = False
         self._reserve_stopped = False
         self._budget_paused = False

strix/core/execution.py

@@ -66,8 +66,7 @@ _IMAGE_REJECTION = re.compile(
     r"|is not a multimodal model|at most 0 image\(s\)"  # vLLM
     r"|does not support image input"  # LiteLLM's Fireworks check
     r"|doesn't support the image field"  # Bedrock Converse
-    r"|unknown variant `image_url`"  # DeepSeek, e.g. via Vercel AI Gateway
-    r"|'[^']*image[^']*' functionality not supported",  # Vercel AI Gateway (AI SDK), unverified
+    r"|unknown variant `image_url`",  # DeepSeek, e.g. via Vercel AI Gateway
     re.IGNORECASE,
 )
 _MAX_COMPACTIONS_PER_CYCLE = 2
@@ -184,7 +183,9 @@ def _is_transient_model_error(exc: BaseException) -> bool:
         return True
     code = _model_error_status_code(exc)
     if code is not None:
-        return code >= 400 and code not in (401, 402, 403, 404)
+        import litellm
+
+        return bool(litellm._should_retry(code))
     return isinstance(exc, APIError)
 
 
@@ -302,7 +303,7 @@ async def _run_agent_loop(
         raise SubagentBudgetReservedError("scan reached the sub-agent budget reserve")
 
     if reserve_stopped and start_parked and interactive and context.get("parent_id") is None:
-        await coordinator.send(agent_id, _reserve_notice(coordinator.root_finish_tool))
+        await coordinator.send(agent_id, _reserve_notice())
 
     if not (start_parked and interactive):
         with contextlib.suppress(BudgetPausedError):
@@ -642,7 +643,6 @@ async def _run_until_lifecycle(
         input_data = await _append_tool_required_message(
             session=session,
             context=context,
-            root_finish_tool=coordinator.root_finish_tool,
             attempt=recoveries,
             limit=recovery_limit,
             interactive=interactive,
@@ -989,9 +989,8 @@ async def _append_tool_required_message(
     limit: int,
     interactive: bool,
     silent_yield: bool = False,
-    root_finish_tool: str = "finish_scan",
 ) -> list[dict[str, str]]:
-    finish_tool = root_finish_tool if context.get("parent_id") is None else "agent_finish"
+    finish_tool = "finish_scan" if context.get("parent_id") is None else "agent_finish"
     if silent_yield:
         message = (
             "You called wait_for_user without having written anything to the user since "
@@ -1109,7 +1108,7 @@ async def notify_parent_on_terminal(
     )
 
 
-def _reserve_notice(finish_tool: str) -> dict[str, Any]:
+def _reserve_notice() -> dict[str, Any]:
     return {
         "from": "system",
         "type": "budget_reserve_stop",
@@ -1119,7 +1118,7 @@ def _reserve_notice(finish_tool: str) -> dict[str, Any]:
             "sub-agent is being force-stopped as soon as its in-flight turn completes, and "
             "none will send a completion report. Their confirmed vulnerabilities are "
             "already filed as they were found. Do not wait on any sub-agents and do not "
-            f"spawn new ones — wrap up now and call {finish_tool}."
+            "spawn new ones — wrap up now and call finish_scan."
         ),
     }
 
@@ -1128,7 +1127,7 @@ async def _notify_root_on_budget_reserve(coordinator: AgentCoordinator) -> None:
     root = await coordinator.claim_reserve_notification()
     if root is None:
         return
-    await coordinator.send(root, _reserve_notice(coordinator.root_finish_tool))
+    await coordinator.send(root, _reserve_notice())
 
 
 async def _notify_parent_on_exit(

strix/core/hooks.py

@@ -104,16 +104,16 @@ _ROOT_DIRECTIVES: tuple[str, ...] = (
     (
         "As the root agent, begin planning your wind-down of the whole scan: avoid "
         "starting large new lines of investigation, and keep your required objectives on "
-        "track so you can call {finish_tool} comfortably before the limit."
+        "track so you can call finish_scan comfortably before the limit."
     ),
     (
         "As the root agent, prioritize wrapping up the whole scan now: stop opening new "
         "lines of investigation, close out only what is essential, and move toward calling "
-        "{finish_tool} to compile and deliver the final report."
+        "finish_scan to compile and deliver the final report."
     ),
     (
         "As the root agent, STOP all other work on the whole scan and finish immediately: "
-        "secure your findings and call {finish_tool} now — anything left unfinished when the "
+        "secure your findings and call finish_scan now — anything left unfinished when the "
         "limit is hit is discarded."
     ),
 )
@@ -138,11 +138,8 @@ _SUBAGENT_DIRECTIVES: tuple[str, ...] = (
 
 def _wrapup_directive(context: RunContextWrapper[dict[str, Any]], stage: int) -> str:
     is_root = context.context.get("parent_id") is None
-    if not is_root:
-        return _SUBAGENT_DIRECTIVES[stage]
-    coordinator = coordinator_from_context(context.context)
-    finish_tool = coordinator.root_finish_tool if coordinator is not None else "finish_scan"
-    return _ROOT_DIRECTIVES[stage].format(finish_tool=finish_tool)
+    directives = _ROOT_DIRECTIVES if is_root else _SUBAGENT_DIRECTIVES
+    return directives[stage]
 
 
 def _urgency(stage: int) -> str:

strix/core/runner.py

@@ -49,7 +49,6 @@ 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.finish.tool import finish_scan
 from strix.tools.output_store import (
     WORKSPACE_SPILL_DIR,
     configure_spill_writer,
@@ -59,7 +58,6 @@ from strix.tools.output_store import (
 if TYPE_CHECKING:
     from agents.memory import SQLiteSession
     from agents.result import RunResultBase
-    from agents.tool import Tool
 
     from strix.runtime.status import StatusSink
     from strix.tools.mcp import (
@@ -70,8 +68,6 @@ if TYPE_CHECKING:
 
 logger = logging.getLogger(__name__)
 
-_MCP_PROMPT_WARMUP_TIMEOUT_SECONDS = 30.0
-
 StreamEventSink = Callable[[str, Any], None]
 
 # Receives the run's MCP connection roster as a list of non-secret status dicts
@@ -97,19 +93,6 @@ def _mcp_roster_payload(registry: McpRegistry) -> list[dict[str, Any]]:
     ]
 
 
-def _mcp_prompt_roster(registry: McpRegistry) -> list[dict[str, Any]]:
-    """The MCP roster rendered in agent prompts, with only verified counts."""
-    return [
-        {
-            "name": summary.name,
-            "purpose": summary.purpose,
-            "tool_count": summary.tool_count if summary.state == "catalog_ready" else None,
-            "state": summary.state,
-        }
-        for summary in registry.summaries()
-    ]
-
-
 def _record_mcp_connections(connection_names: list[str]) -> None:
     """Record which MCP servers this run configured, for the interfaces.
 
@@ -217,7 +200,6 @@ async def run_strix_scan(
     status_sink: StatusSink | None = None,
     mcp_connection_requests: list[McpConnectionRequest] | None = None,
     mcp_status_sink: McpStatusSink | None = None,
-    root_finish_tool: Tool = finish_scan,
 ) -> RunResultBase | None:
     """Run or resume one Strix scan against a sandbox.
 
@@ -240,7 +222,6 @@ async def run_strix_scan(
     command-line default) it reads ``~/.strix/mcp-servers.json`` itself. Either
     way the engine does the connecting, so the caller passes inert configs plus
     metadata and never live sessions.
-    ``root_finish_tool`` is the tool the root agent ends the run with.
     """
 
     def report(phase: str) -> None:
@@ -297,7 +278,6 @@ async def run_strix_scan(
         coordinator = AgentCoordinator()
     coordinator.set_snapshot_path(agents_path)
     coordinator.set_budget_policy(budget_policy)
-    coordinator.root_finish_tool = root_finish_tool.name
 
     from strix.tools.coverage.tools import hydrate_coverage_from_disk
     from strix.tools.notes.tools import hydrate_notes_from_disk
@@ -458,13 +438,19 @@ async def run_strix_scan(
                 _record_mcp_connections(mcp_registry.names())
                 report(
                     f"MCP: configured {len(mcp_registry)} connection(s); "
-                    "connecting and listing tools"
+                    "warming them in the background"
                 )
                 scope_context["mcp_available"] = True
-                scope_context["mcp_connections"] = _mcp_prompt_roster(mcp_registry)
+                scope_context["mcp_connections"] = [
+                    {
+                        "name": summary.name,
+                        "purpose": summary.purpose,
+                        "tool_count": summary.tool_count,
+                    }
+                    for summary in mcp_registry.summaries()
+                ]
 
                 def _emit_mcp_status() -> None:
-                    scope_context["mcp_connections"] = _mcp_prompt_roster(mcp_registry)
                     roster = _mcp_roster_payload(mcp_registry)
                     _persist_mcp_status(roster)
                     if mcp_status_sink is not None:
@@ -475,11 +461,7 @@ async def run_strix_scan(
 
                 mcp_registry.set_status_sink(_emit_mcp_status)
                 _emit_mcp_status()
-                warmup_task = mcp_registry.start_warmup(max_concurrency=6)
-                await asyncio.wait(
-                    {warmup_task},
-                    timeout=_MCP_PROMPT_WARMUP_TIMEOUT_SECONDS,
-                )
+                mcp_registry.start_warmup(max_concurrency=6)
         except Exception:
             logger.exception("Failed to configure user MCP servers; continuing without them")
 
@@ -508,7 +490,6 @@ async def run_strix_scan(
             system_prompt_context=root_context,
             instructions_override=root_instructions,
             supports_images=supports_images,
-            finish_tool=root_finish_tool,
         )
 
         if not is_resume:

strix/llm/request_log.py

@@ -159,33 +159,11 @@ class HttpReply:
 
     status_code: int | None = None
     headers: dict[str, str] | None = None
-    upstream_provider: str | None = None
-    upstream_error_type: str | None = None
 
 
 _http_reply: ContextVar[HttpReply | None] = ContextVar("strix_llm_http_reply", default=None)
 
 
-def record_upstream_provider(provider: object, error_type: object = None) -> None:
-    """Remember which provider behind a gateway served the attempt in flight."""
-    reply = _http_reply.get()
-    if reply is None:
-        return
-    if isinstance(provider, str) and provider:
-        reply.upstream_provider = provider
-    if isinstance(error_type, str) and error_type:
-        reply.upstream_error_type = error_type
-
-
-def _upstream_details(reply: HttpReply | None) -> list[tuple[str, object]]:
-    if reply is None:
-        return []
-    return [
-        ("upstream_provider", reply.upstream_provider),
-        ("upstream_error_type", reply.upstream_error_type),
-    ]
-
-
 async def record_http_reply(response: Response) -> None:
     """httpx ``response`` event hook: remember the reply for the attempt in flight.
 
@@ -794,7 +772,6 @@ def _litellm_success(
             ("request", _litellm_request_details(kwargs)),
             ("response", _litellm_response_details(response)),
             ("litellm", _litellm_hidden_details(hidden, slo)),
-            *_upstream_details(_http_reply.get()),
         ),
     )
 
@@ -844,7 +821,6 @@ def _litellm_failure(
             ("request", _litellm_request_details(kwargs)),
             ("error", error or None),
             ("litellm", _litellm_hidden_details(hidden, slo)),
-            *_upstream_details(_http_reply.get()),
         ),
     )
 
@@ -918,18 +894,15 @@ def _observe_sdk_shared_http_client() -> None:
 
 
 def _log_line_sink(event: LlmRequestEvent) -> None:
-    details = event.details or {}
     level = logging.DEBUG if event.outcome == "success" else logging.WARNING
     logger.log(
         level,
-        "llm_request route=%s provider=%s upstream=%s upstream_error=%s model=%s host=%s "
-        "outcome=%s status=%s request_id=%s response_id=%s stream=%s duration_ms=%d ttft_ms=%s "
+        "llm_request route=%s provider=%s model=%s host=%s outcome=%s status=%s "
+        "request_id=%s response_id=%s stream=%s duration_ms=%d ttft_ms=%s "
         "req_bytes=%s res_bytes=%s finish=%s "
         "in=%s out=%s cached=%s cost=%s agent=%s attempt=%d%s",
         event.route,
         event.provider or "-",
-        details.get("upstream_provider") or "-",
-        details.get("upstream_error_type") or "-",
         event.model,
         event.api_host or "-",
         event.outcome,
@@ -1097,7 +1070,6 @@ class RequestLoggingModel(Model):
                 details=merge_details(
                     ("request", request.details),
                     ("response", _openai_response_details(response, raw_response)),
-                    *_upstream_details(reply),
                 ),
             )
         status, request_id = _openai_error_fields(exc)
@@ -1110,14 +1082,13 @@ class RequestLoggingModel(Model):
             outcome="error",
             status_code=status,
             provider_request_id=request_id or base.provider_request_id,
-            error_type=_cancel_reason(exc) or type(exc).__name__,
+            error_type=type(exc).__name__,
             error_message=_abandonment_message(exc) or clean_error_message(exc),
             response_bytes=_exception_body_size(exc, status),
             response_headers=headers_from_response(error_headers) or base.response_headers,
             details=merge_details(
                 ("request", request.details),
                 ("error", _exception_details(exc)),
-                *_upstream_details(reply),
             ),
         )
 
@@ -1347,23 +1318,9 @@ def _is_abandonment(exc: BaseException | None) -> bool:
     return isinstance(exc, asyncio.CancelledError | GeneratorExit)
 
 
-# Prefixes the reason a stream timeout gives when it cancels an attempt.
-CANCEL_REASON_PREFIX = "strix:"
-
-
-def _cancel_reason(exc: BaseException) -> str | None:
-    """The stream timeout that cancelled the attempt, e.g. ``stream_idle_timeout``."""
-    if isinstance(exc, asyncio.CancelledError) and exc.args:
-        message = str(exc.args[0])
-        if message.startswith(CANCEL_REASON_PREFIX):
-            return message.removeprefix(CANCEL_REASON_PREFIX)
-    return None
-
-
 def _abandonment_message(exc: BaseException) -> str | None:
     if isinstance(exc, asyncio.CancelledError):
-        reason = f": {exc.args[0]}" if exc.args else ""
-        return f"attempt cancelled before the reply was consumed{reason}"
+        return "attempt cancelled before the reply was consumed (stream idle timeout or shutdown)"
     if isinstance(exc, GeneratorExit):
         return "stream closed by the caller before it finished"
     return None

strix/tools/agents_graph/tools.py

@@ -683,8 +683,7 @@ async def agent_finish(
             {
                 "success": False,
                 "error": (
-                    "agent_finish is for subagents. Root/main agents must call "
-                    f"{coordinator.root_finish_tool} instead"
+                    "agent_finish is for subagents. Root/main agents must call finish_scan instead"
                 ),
             },
             ensure_ascii=False,

strix/tools/mcp/agent_tools.py

@@ -24,7 +24,6 @@ automatically.
 
 from __future__ import annotations
 
-import asyncio
 import json
 from typing import TYPE_CHECKING, Any
 
@@ -47,7 +46,6 @@ def _registry_from_ctx(ctx: RunContextWrapper) -> McpRegistry | None:
 
 
 _NO_CONNECTIONS = "No MCP connections are configured for this run."
-_MCP_DISCOVERY_WAIT_SECONDS = 30.0
 
 
 def _unknown_connection(connection: str, registry: McpRegistry) -> str:
@@ -63,13 +61,11 @@ def _format_tool(tool: MCPTool) -> str:
 
 @function_tool(timeout=60)
 async def list_mcps(ctx: RunContextWrapper) -> dict[str, Any]:
-    """List available MCP connections, loading each connection's catalog on first use.
+    """List the MCP connections available this run, so you can discover them.
 
     Read-only. Returns one entry per connection with its ``id`` (the exact name
     you pass to the other MCP tools), ``name``, ``description``, and
-    ``tool_count`` (null while the catalog is unknown). Waits at most 30 seconds
-    for catalogs; unfinished catalogs keep loading in the background.
-    The response does not include tool schemas. Call
+    ``tool_count``. The response does not include tool schemas. Call
     ``search_mcp_tools`` next. Then call ``get_mcp_tool_schema`` for one selected
     tool before you call ``call_mcp``. Returns an empty ``connections`` list when
     the run has no MCP connections.
@@ -77,23 +73,6 @@ async def list_mcps(ctx: RunContextWrapper) -> dict[str, Any]:
     registry = _registry_from_ctx(ctx)
     if registry is None or not registry:
         return {"connections": []}
-    pending = [
-        entry
-        for name in registry.names()
-        if (entry := registry.get(name)) is not None
-        and entry.state != "catalog_ready"
-        and (entry.session is None or not entry.session.is_dead)
-    ]
-    if pending:
-        await asyncio.wait(
-            {
-                asyncio.gather(
-                    *(entry.ensure_catalog() for entry in pending),
-                    return_exceptions=True,
-                )
-            },
-            timeout=_MCP_DISCOVERY_WAIT_SECONDS,
-        )
     dead_by_name = {status.name: status.dead for status in registry.statuses()}
     return {
         "connections": [
@@ -101,7 +80,7 @@ async def list_mcps(ctx: RunContextWrapper) -> dict[str, Any]:
                 "id": summary.name,
                 "name": summary.name,
                 "description": summary.purpose,
-                "tool_count": summary.tool_count if summary.state == "catalog_ready" else None,
+                "tool_count": summary.tool_count,
                 "dead": dead_by_name.get(summary.name, False),
                 "state": summary.state,
             }

strix/tools/mcp/registry.py

@@ -432,19 +432,19 @@ class McpRegistry:
             entry.set_status_sink(sink)
 
     def start_warmup(self, *, max_concurrency: int = 6) -> asyncio.Task[None]:
-        """Connect and list every configured entry with a fixed concurrency bound."""
+        """Connect every configured entry in the background with a fixed bound."""
         if self._warmup_task is not None:
             return self._warmup_task
 
         async def warm() -> None:
             semaphore = asyncio.Semaphore(max(1, max_concurrency))
 
-            async def load_catalog(entry: McpConnectionEntry) -> None:
+            async def connect(entry: McpConnectionEntry) -> None:
                 async with semaphore:
-                    with contextlib.suppress(Exception):
-                        await entry.ensure_catalog()
+                    with contextlib.suppress(McpConnectionUnavailableError):
+                        await entry.ensure_connected()
 
-            await asyncio.gather(*(load_catalog(entry) for entry in self._entries.values()))
+            await asyncio.gather(*(connect(entry) for entry in self._entries.values()))
 
         self._warmup_task = asyncio.create_task(warm(), name="mcp-warmup")
         return self._warmup_task

tests/test_agent_tool_registration.py

@@ -59,15 +59,6 @@ def test_registered_tools_appear_before_lifecycle_tool() -> None:
     assert child_names[-2:] == ["extra", "agent_finish"]
 
 
-def test_root_ends_with_the_given_finish_tool() -> None:
-    root = factory.build_strix_agent(is_root=True, finish_tool=_tool("finish_pr_review"))
-
-    root_names = [t.name for t in root.tools]
-
-    assert root_names[-1] == "finish_pr_review"
-    assert "finish_scan" not in root_names
-
-
 def test_per_call_extra_tools_stack_with_registry() -> None:
     factory.register_agent_tools(_tool("registered"))
 

tests/test_cost_tracking.py

@@ -2,7 +2,6 @@
 
 from __future__ import annotations
 
-import json
 import uuid
 from types import SimpleNamespace
 from typing import TYPE_CHECKING, Any
@@ -390,67 +389,3 @@ def test_openrouter_request_carries_agent_session_id() -> None:
             assert body()["session_id"] == session_id
     finally:
         request_log.reset_call_context(token)
-
-
-def _openrouter_config() -> Any:
-    _install_openrouter_stream_cost_capture()
-    config = ProviderConfigManager.get_provider_chat_config(
-        model="z-ai/glm-5.3", provider=LlmProviders.OPENROUTER
-    )
-    assert config is not None
-    return config
-
-
-def test_openrouter_records_upstream_of_stream_and_mid_stream_error() -> None:
-    handler = _openrouter_config().get_model_response_iterator(
-        streaming_response=iter([]), sync_stream=True
-    )
-    reply = request_log.HttpReply()
-    token = request_log._http_reply.set(reply)
-    try:
-        handler.chunk_parser(
-            {
-                "id": "gen-a",
-                "created": 1,
-                "model": "z-ai/glm-5.3",
-                "provider": "Relace",
-                "choices": [{"index": 0, "delta": {"content": "x"}}],
-            }
-        )
-        assert reply.upstream_provider == "Relace"
-        assert reply.upstream_error_type is None
-        with pytest.raises(Exception, match="incomplete tool call"):
-            handler.chunk_parser(
-                {
-                    "id": "gen-a",
-                    "provider": "Relace",
-                    "error": {
-                        "code": 400,
-                        "message": "Generation stopped with an incomplete tool call.",
-                        "metadata": {"error_type": "invalid_request"},
-                    },
-                }
-            )
-    finally:
-        request_log._http_reply.reset(token)
-    assert reply.upstream_provider == "Relace"
-    assert reply.upstream_error_type == "invalid_request"
-
-
-def test_openrouter_records_upstream_of_pre_stream_error() -> None:
-    body = {
-        "error": {
-            "message": "Provider returned error",
-            "code": 400,
-            "metadata": {"raw": "...", "provider_name": "InferenceNet"},
-        }
-    }
-    reply = request_log.HttpReply()
-    token = request_log._http_reply.set(reply)
-    try:
-        _openrouter_config().get_error_class(json.dumps(body), 400, {})
-        _openrouter_config().get_error_class("<html>502 Bad Gateway</html>", 502, {})
-    finally:
-        request_log._http_reply.reset(token)
-    assert reply.upstream_provider == "InferenceNet"
-    assert reply.upstream_error_type is None

tests/test_execution.py

@@ -132,27 +132,6 @@ async def test_reserve_stop_notifies_root_once(monkeypatch: pytest.MonkeyPatch)
     assert "finish_scan" in str(message["content"])
 
 
-@pytest.mark.asyncio
-async def test_reserve_notice_names_the_root_finish_tool(monkeypatch: pytest.MonkeyPatch) -> None:
-    coordinator = AgentCoordinator()
-    coordinator.root_finish_tool = "finish_pr_review"
-    await coordinator.register("root", "strix", parent_id=None)
-    await coordinator.register("child-a", "recon", parent_id="root")
-
-    sent: list[dict[str, Any]] = []
-
-    async def _record(_target_agent_id: str, message: dict[str, Any]) -> bool:
-        sent.append(message)
-        return True
-
-    monkeypatch.setattr(coordinator, "send", _record)
-
-    await _notify_root_on_budget_reserve(coordinator)
-
-    assert "call finish_pr_review" in str(sent[0]["content"])
-    assert "finish_scan" not in str(sent[0]["content"])
-
-
 @pytest.mark.asyncio
 async def test_concurrent_reserve_claims_yield_single_root() -> None:
     coordinator = AgentCoordinator()
@@ -1316,21 +1295,6 @@ async def test_interactive_nudge_offers_waiting_without_repeating() -> None:
     assert "do not repeat it" in items[0]["content"]
 
 
-@pytest.mark.asyncio
-async def test_nudge_names_the_root_finish_tool() -> None:
-    items = await execution._append_tool_required_message(
-        session=None,
-        context={"parent_id": None},
-        attempt=1,
-        limit=3,
-        interactive=False,
-        root_finish_tool="finish_pr_review",
-    )
-
-    assert "call finish_pr_review" in items[0]["content"]
-    assert "finish_scan" not in items[0]["content"]
-
-
 def _cycle_with_items(
     coordinator: AgentCoordinator,
     agent_id: str,

tests/test_execution_transient_retry.py

@@ -79,13 +79,12 @@ def test_content_guardrail_is_not_retried() -> None:
     assert execution._is_transient_model_error(guardrail) is False
 
 
-def test_client_errors_are_transient() -> None:
+def test_client_errors_are_not_transient() -> None:
     bad_request = BadRequestError(
         "bad", response=httpx.Response(400, request=_request()), body=None
     )
-    assert execution._is_transient_model_error(bad_request) is True
-    for status in (401, 402, 403, 404):
-        assert execution._is_transient_model_error(_status_error(status)) is False
+    assert execution._is_transient_model_error(bad_request) is False
+    assert execution._is_transient_model_error(_status_error(404)) is False
     assert execution._is_transient_model_error(ValueError("nope")) is False
 
 
@@ -168,8 +167,11 @@ async def test_run_cycle_gives_up_after_max_retries(
 async def test_run_cycle_does_not_retry_permanent_error(
     monkeypatch: pytest.MonkeyPatch,
 ) -> None:
-    streams = [_FakeStream(exc=ValueError("nope")), _FakeStream()]
-    with pytest.raises(ValueError, match="nope"):
+    bad_request = BadRequestError(
+        "bad", response=httpx.Response(400, request=_request()), body=None
+    )
+    streams = [_FakeStream(exc=bad_request), _FakeStream()]
+    with pytest.raises(BadRequestError):
         await _run_once(monkeypatch, streams)
 
 
@@ -187,7 +189,6 @@ async def test_run_cycle_does_not_retry_permanent_error(
         (400, "my-model is not a multimodal model", True),
         (400, "This model doesn't support the image field for user messages.", True),
         (422, "messages[3]: unknown variant `image_url`, expected `text`", True),
-        (400, "'Image URLs in user messages' functionality not supported.", True),
         (
             400,
             "OpenRouterException: Message: This model's maximum context length is 1048576 "

tests/test_hooks.py

@@ -7,7 +7,6 @@ from unittest.mock import MagicMock, patch
 
 import pytest
 
-from strix.core.agents import AgentCoordinator
 from strix.core.hooks import (
     BudgetExceededError,
     BudgetPausedError,
@@ -336,21 +335,6 @@ async def test_budget_warning_root_directive_distinct_from_subagent() -> None:
     assert "confirmed" in sub
 
 
-@pytest.mark.asyncio
-async def test_root_directive_names_the_coordinators_finish_tool() -> None:
-    hooks = ReportUsageHooks(model="test-model", max_turns=100)
-    coordinator = AgentCoordinator()
-    coordinator.root_finish_tool = "finish_pr_review"
-    ctx = _make_warn_context(requests=85, parent_id=None)
-    ctx.context["coordinator"] = coordinator
-
-    items: list[Any] = []
-    await hooks.on_llm_start(ctx, MagicMock(), None, items)
-
-    assert "finish_pr_review" in items[0]["content"]
-    assert "finish_scan" not in items[0]["content"]
-
-
 @pytest.mark.parametrize("parent_id", [None, "root-1"])
 @pytest.mark.asyncio
 async def test_turn_warning_directive_escalates_per_stage(parent_id: str | None) -> None:

tests/test_llm_request_log.py

@@ -394,30 +394,9 @@ def test_log_line_sink_formats_without_content(caplog: pytest.LogCaptureFixture)
     assert "request_id=req_line01" in line
     assert "status=400" in line
     assert "provider=anthropic" in line
-    assert "upstream=- upstream_error=-" in line
     assert "SECRET PROMPT" not in line
 
 
-def test_log_line_names_upstream_recorded_during_attempt(
-    caplog: pytest.LogCaptureFixture,
-) -> None:
-    exc = _anthropic_error(400, ANTHROPIC_BLOCK_BODY, {})
-    token = request_log._http_reply.set(request_log.HttpReply())
-    try:
-        request_log.record_upstream_provider("Together", "provider_unavailable")
-        event = request_log.event_from_litellm(
-            _anthropic_kwargs(exc), None, None, None, outcome="error"
-        )
-    finally:
-        request_log._http_reply.reset(token)
-    assert event.details is not None
-    assert event.details["upstream_provider"] == "Together"
-    with caplog.at_level(logging.DEBUG, logger="strix.llm.request_log"):
-        request_log._log_line_sink(event)
-    line = caplog.records[-1].getMessage()
-    assert "upstream=Together upstream_error=provider_unavailable" in line
-
-
 # --------------------------------------------------------------------------- #
 # sizes, timing, finish reason, free-form headers and details                  #
 # --------------------------------------------------------------------------- #

tests/test_mcp_client.py

@@ -43,7 +43,6 @@ from strix.tools.mcp import (
     resolve_mcp_call,
     search_mcp_tools,
 )
-from strix.tools.mcp import agent_tools as mcp_agent_tools
 from strix.tools.mcp import client as mcp_client
 from strix.tools.mcp import registry as mcp_registry_mod
 from strix.tools.mcp import session as mcp_session_mod
@@ -422,18 +421,8 @@ def test_registry_summaries() -> None:
 @pytest.mark.asyncio
 async def test_list_mcps_returns_connections_with_ids_and_descriptions() -> None:
     registry = McpRegistry()
-    registry.add(
-        name="fs",
-        server=FakeMCPServer("fs", [_mcp_tool("read_file"), _mcp_tool("write_file")]),
-        purpose="local files",
-        tool_count=2,
-    )
-    registry.add(
-        name="db",
-        server=FakeMCPServer("db", [_mcp_tool("query")]),
-        purpose=None,
-        tool_count=1,
-    )
+    registry.add(name="fs", server=FakeMCPServer("fs", []), purpose="local files", tool_count=2)
+    registry.add(name="db", server=FakeMCPServer("db", []), purpose=None, tool_count=1)
 
     out = await list_mcps.on_invoke_tool(_ctx(registry), "{}")
 
@@ -448,7 +437,7 @@ async def test_list_mcps_returns_connections_with_ids_and_descriptions() -> None
                 "description": "local files",
                 "tool_count": 2,
                 "dead": False,
-                "state": "catalog_ready",
+                "state": "connected",
             },
             {
                 "id": "db",
@@ -456,143 +445,10 @@ async def test_list_mcps_returns_connections_with_ids_and_descriptions() -> None
                 "description": None,
                 "tool_count": 1,
                 "dead": False,
-                "state": "catalog_ready",
+                "state": "connected",
             },
         ]
     }
-    await registry.close()
-
-
-@pytest.mark.asyncio
-async def test_list_mcps_loads_catalog_for_unwarmed_connection(
-    monkeypatch: pytest.MonkeyPatch,
-) -> None:
-    server = FakeMCPServer("fs", [_mcp_tool("read_file"), _mcp_tool("write_file")])
-    monkeypatch.setattr(
-        mcp_client,
-        "_build_server",
-        lambda _config: _built_server(server),
-    )
-    registry = McpRegistry()
-    entry = registry.register(McpConnectionRequest(config=_config("fs", None)))
-
-    out = await list_mcps.on_invoke_tool(_ctx(registry), "{}")
-
-    assert entry.state == "catalog_ready"
-    assert entry.tool_count == 2
-    assert out["connections"][0]["tool_count"] == 2
-    assert out["connections"][0]["state"] == "catalog_ready"
-    await registry.close()
-
-
-@pytest.mark.asyncio
-@pytest.mark.parametrize("slow_stage", ["connect", "catalog"])
-@pytest.mark.parametrize("warmup", [False, True])
-async def test_list_mcps_returns_healthy_connections_while_slow_catalog_keeps_loading(
-    monkeypatch: pytest.MonkeyPatch,
-    slow_stage: str,
-    warmup: bool,
-) -> None:
-    release = asyncio.Event()
-    started = asyncio.Event()
-    catalog_calls = 0
-
-    class _SlowServer(FakeMCPServer):
-        async def connect(self) -> None:
-            if slow_stage == "connect":
-                started.set()
-                await release.wait()
-
-        async def list_tools(self, run_context: Any = None, agent: Any = None) -> list[MCPTool]:
-            nonlocal catalog_calls
-            catalog_calls += 1
-            if slow_stage == "catalog":
-                started.set()
-                await release.wait()
-            return await super().list_tools(run_context, agent)
-
-    servers = {
-        "healthy": FakeMCPServer("healthy", [_mcp_tool("read_file")]),
-        "slow": _SlowServer("slow", [_mcp_tool("query")]),
-    }
-    monkeypatch.setattr(
-        mcp_client, "_build_server", lambda config: _built_server(servers[config.name])
-    )
-    monkeypatch.setattr(mcp_agent_tools, "_MCP_DISCOVERY_WAIT_SECONDS", 0.01)
-    registry = McpRegistry()
-    for name in servers:
-        registry.register(McpConnectionRequest(config=_config(name, None)))
-    if warmup:
-        registry.start_warmup()
-    entry = registry.get("slow")
-    assert entry is not None
-    try:
-        out = await asyncio.wait_for(list_mcps.on_invoke_tool(_ctx(registry), "{}"), timeout=1)
-        assert started.is_set()
-        assert out["connections"][0]["tool_count"] == 1
-        assert out["connections"][0]["state"] == "catalog_ready"
-        assert out["connections"][1]["tool_count"] is None
-        assert out["connections"][1]["state"] in {"connecting", "catalog_loading"}
-        assert entry._catalog_task is not None
-        assert not entry._catalog_task.done()
-
-        repeated = await asyncio.wait_for(list_mcps.on_invoke_tool(_ctx(registry), "{}"), timeout=1)
-        assert repeated == out
-        release.set()
-        await asyncio.wait_for(entry.ensure_catalog(), timeout=1)
-        finished = await list_mcps.on_invoke_tool(_ctx(registry), "{}")
-        assert finished["connections"][1]["tool_count"] == 1
-        assert finished["connections"][1]["state"] == "catalog_ready"
-        assert catalog_calls == 1
-    finally:
-        release.set()
-        await registry.close()
-
-
-@pytest.mark.asyncio
-@pytest.mark.parametrize("fail_after_deadline", [False, True])
-async def test_list_mcps_retains_and_cleans_up_background_catalog_tasks(
-    monkeypatch: pytest.MonkeyPatch,
-    fail_after_deadline: bool,
-) -> None:
-    release = asyncio.Event()
-    finished = asyncio.Event()
-    loop_errors: list[dict[str, Any]] = []
-
-    async def load_catalog() -> list[MCPTool]:
-        await release.wait()
-        raise RuntimeError("catalog unavailable")
-
-    registry = McpRegistry()
-    entry = registry.add(
-        name="blocked", server=FakeMCPServer("blocked", []), purpose=None, tool_count=0
-    )
-    assert entry.session is not None
-    monkeypatch.setattr(entry.session, "list_tools", load_catalog)
-    monkeypatch.setattr(mcp_agent_tools, "_MCP_DISCOVERY_WAIT_SECONDS", 0.01)
-    loop = asyncio.get_running_loop()
-    previous_handler = loop.get_exception_handler()
-    loop.set_exception_handler(lambda _loop, context: loop_errors.append(context))
-    try:
-        out = await asyncio.wait_for(list_mcps.on_invoke_tool(_ctx(registry), "{}"), timeout=1)
-        assert out["connections"][0]["tool_count"] is None
-        assert entry._catalog_task is not None
-        assert not entry._catalog_task.done()
-        if fail_after_deadline:
-            entry._catalog_task.add_done_callback(lambda _task: finished.set())
-            release.set()
-            await asyncio.wait_for(finished.wait(), timeout=1)
-            assert entry.state == "connected"
-            # Drop the finished task without awaiting it; its error must already be consumed.
-            entry._catalog_task = None
-        else:
-            task = entry._catalog_task
-            await registry.close()
-            assert task.cancelled()
-        assert loop_errors == []
-    finally:
-        await registry.close()
-        loop.set_exception_handler(previous_handler)
 
 
 @pytest.mark.asyncio
@@ -877,37 +733,7 @@ async def test_registry_warmup_bounds_parallel_connections(
     release.set()
     await warmup
 
-    assert [summary.state for summary in registry.summaries()] == ["catalog_ready"] * 4
-    assert [summary.tool_count for summary in registry.summaries()] == [1] * 4
-    await registry.close()
-
-
-@pytest.mark.asyncio
-async def test_registry_warmup_swallows_catalog_listing_errors(
-    monkeypatch: pytest.MonkeyPatch,
-) -> None:
-    class _FailingListServer(FakeMCPServer):
-        async def list_tools(
-            self,
-            run_context: Any = None,
-            agent: Any = None,
-        ) -> list[MCPTool]:
-            raise RuntimeError("catalog unavailable")
-
-    monkeypatch.setattr(
-        mcp_client,
-        "_build_server",
-        lambda _config: _built_server(_FailingListServer("db", [])),
-    )
-    registry = McpRegistry()
-    entry = registry.register(McpConnectionRequest(config=_config("db", None)))
-
-    warmup = registry.start_warmup()
-    await warmup
-
-    assert warmup.done()
-    assert entry.state == "connected"
-    assert entry.tool_count == 0
+    assert [summary.state for summary in registry.summaries()] == ["connected"] * 4
     await registry.close()
 
 
@@ -1186,53 +1012,6 @@ def test_prompt_renders_named_connection_inventory() -> None:
     assert "read the app's schema" in prompt
 
 
-def test_prompt_omits_unloaded_tool_count() -> None:
-    prompt = render_system_prompt(
-        system_prompt_context={
-            "mcp_available": True,
-            "mcp_connections": [
-                {"name": "pending_conn", "purpose": None, "tool_count": None, "state": "connected"}
-            ],
-        }
-    )
-
-    connection_line = next(line for line in prompt.splitlines() if "pending_conn" in line)
-    assert "(0 tools)" not in connection_line
-    assert "tools)" not in connection_line
-
-
-def test_prompt_renders_loaded_tool_count() -> None:
-    prompt = render_system_prompt(
-        system_prompt_context={
-            "mcp_available": True,
-            "mcp_connections": [
-                {"name": "ready_conn", "purpose": None, "tool_count": 8, "state": "catalog_ready"}
-            ],
-        }
-    )
-
-    assert "ready_conn (8 tools)" in prompt
-
-
-def test_prompt_renders_unavailable_connection_without_tool_count() -> None:
-    prompt = render_system_prompt(
-        system_prompt_context={
-            "mcp_available": True,
-            "mcp_connections": [
-                {
-                    "name": "unavailable_conn",
-                    "purpose": None,
-                    "tool_count": None,
-                    "state": "unavailable",
-                }
-            ],
-        }
-    )
-
-    assert "unavailable_conn (unavailable right now)" in prompt
-    assert "unavailable_conn (0 tools)" not in prompt
-
-
 def test_prompt_inventory_is_gated_on_availability() -> None:
     """The block is gated on ``mcp_available``; an ``mcp_connections`` payload
     without it renders nothing, so a stale or spoofed list cannot leak names."""

tests/test_runner_mcp.py

@@ -8,7 +8,6 @@ routine does the connecting.
 
 from __future__ import annotations
 
-import importlib
 import types
 from typing import Any
 
@@ -18,21 +17,10 @@ from agents import ModelSettings
 import strix.tools.mcp as mcp_pkg
 import strix.tools.notes.tools as notes_tools
 import strix.tools.todo.tools as todo_tools
-from strix.agents import factory
 from strix.core import runner
 from strix.core.agents import AgentCoordinator
 from strix.runtime import session_manager
 from strix.tools.mcp import McpConnectionConfig, McpConnectionRequest
-from strix.tools.mcp import client as mcp_client
-
-
-_test_mcp_client = importlib.import_module("tests.test_mcp_client")
-FakeMCPServer: Any = _test_mcp_client.FakeMCPServer
-_mcp_tool: Any = _test_mcp_client._mcp_tool
-
-
-def _built_server(server: Any) -> Any:
-    return mcp_client.BuiltMcpServer(server, None)
 
 
 def _settings() -> Any:
@@ -74,11 +62,6 @@ def _wire_runner(monkeypatch: pytest.MonkeyPatch, tmp_path: Any) -> None:
     monkeypatch.setattr(runner, "build_strix_agent", lambda **_k: object())
     monkeypatch.setattr(runner, "make_child_factory", lambda **_k: lambda **_kk: object())
     monkeypatch.setattr(runner, "open_agent_session", lambda _root_id, _db: object())
-    monkeypatch.setattr(
-        mcp_client,
-        "_build_server",
-        lambda config: _built_server(FakeMCPServer(config.name, [])),
-    )
 
     async def _run_agent_loop(**_kwargs: Any) -> None:
         return None
@@ -173,11 +156,6 @@ async def test_roster_is_persisted_even_without_a_status_sink(
         "load_user_mcp_configs",
         lambda: [McpConnectionConfig(name="local_fs", transport="stdio", command="npx")],
     )
-    monkeypatch.setattr(
-        mcp_client,
-        "_build_server",
-        lambda _config: _built_server(FakeMCPServer("local_fs", [])),
-    )
 
     persisted: list[list[dict[str, Any]]] = []
 
@@ -204,106 +182,3 @@ async def test_roster_is_persisted_even_without_a_status_sink(
             "state": "configured",
         }
     ]
-
-
-@pytest.mark.asyncio
-async def test_warmup_listing_failure_does_not_interrupt_scan(
-    monkeypatch: pytest.MonkeyPatch,
-    tmp_path: Any,
-) -> None:
-    _wire_runner(monkeypatch, tmp_path)
-
-    server = FakeMCPServer("db", [])
-
-    async def _failing_list_tools(
-        run_context: Any = None,
-        agent: Any = None,
-    ) -> list[Any]:
-        del run_context, agent
-        raise RuntimeError("catalog unavailable")
-
-    server.list_tools = _failing_list_tools
-
-    monkeypatch.setattr(
-        mcp_client,
-        "_build_server",
-        lambda _config: _built_server(server),
-    )
-    root_builds: list[dict[str, Any]] = []
-    monkeypatch.setattr(runner, "build_strix_agent", lambda **kwargs: root_builds.append(kwargs))
-
-    await runner.run_strix_scan(
-        scan_config={"targets": [], "scan_mode": "deep"},
-        scan_id="scan-mcp-list-failure",
-        image="img",
-        coordinator=AgentCoordinator(),
-        mcp_connection_requests=[
-            McpConnectionRequest(
-                config=McpConnectionConfig(name="db", url="https://mcp.example.com")
-            )
-        ],
-    )
-
-    assert len(root_builds) == 1
-
-
-@pytest.mark.asyncio
-async def test_warmed_tool_counts_reach_root_and_child_agent_builds(
-    monkeypatch: pytest.MonkeyPatch,
-    tmp_path: Any,
-) -> None:
-    _wire_runner(monkeypatch, tmp_path)
-    server = FakeMCPServer("db", [_mcp_tool(f"tool_{index}") for index in range(3)])
-    monkeypatch.setattr(mcp_client, "_build_server", lambda _config: _built_server(server))
-
-    root_builds: list[dict[str, Any]] = []
-
-    def _build_root(**kwargs: Any) -> object:
-        root_builds.append(kwargs)
-        return object()
-
-    monkeypatch.setattr(
-        runner,
-        "build_strix_agent",
-        _build_root,
-    )
-    child_builds: list[dict[str, Any]] = []
-
-    def _build_child(**kwargs: Any) -> object:
-        child_builds.append(kwargs)
-        return object()
-
-    monkeypatch.setattr(
-        factory,
-        "build_strix_agent",
-        _build_child,
-    )
-    real_make_child_factory = factory.make_child_factory
-    child_factory_capture: dict[str, Any] = {}
-
-    def _make_child_factory(**kwargs: Any) -> Any:
-        child_factory_capture["context"] = kwargs["system_prompt_context"]
-        child_factory_capture["factory"] = real_make_child_factory(**kwargs)
-        return child_factory_capture["factory"]
-
-    monkeypatch.setattr(runner, "make_child_factory", _make_child_factory)
-    request = McpConnectionRequest(
-        config=McpConnectionConfig(name="db", url="https://mcp.example.com", notes="database")
-    )
-
-    await runner.run_strix_scan(
-        scan_config={"targets": [], "scan_mode": "deep"},
-        scan_id="scan-mcp-prompt-counts",
-        image="img",
-        coordinator=AgentCoordinator(),
-        mcp_connection_requests=[request],
-    )
-
-    root_context = root_builds[0]["system_prompt_context"]
-    assert root_context["mcp_connections"][0]["tool_count"] == 3
-    assert child_factory_capture["context"] is root_context
-    assert child_factory_capture["context"]["mcp_connections"][0]["tool_count"] == 3
-
-    child_factory_capture["factory"](name="child", skills=[])
-    assert child_builds[0]["system_prompt_context"] is child_factory_capture["context"]
-    assert child_builds[0]["system_prompt_context"]["mcp_connections"][0]["tool_count"] == 3

tests/test_runner_root_prompt.py

@@ -6,7 +6,6 @@ flow through to the root agent's ``build_strix_agent`` call.
 
 from __future__ import annotations
 
-import importlib
 import os
 import types
 from typing import Any
@@ -28,11 +27,6 @@ from strix.core.inputs import make_model_settings
 from strix.runtime import session_manager
 from strix.tools.load_skill.tool import load_skill
 from strix.tools.mcp import BearerAuth, McpConnectionConfig, McpConnectionRequest
-from strix.tools.mcp import client as mcp_client
-
-
-_test_mcp_client = importlib.import_module("tests.test_mcp_client")
-FakeMCPServer: Any = _test_mcp_client.FakeMCPServer
 
 
 def _make_rate_limit_error() -> RateLimitError:
@@ -90,11 +84,6 @@ def _patch_engine_scaffold(
     monkeypatch.setattr(runner, "build_root_task", lambda _scan_config: "task")
     monkeypatch.setattr(runner, "build_scope_context", lambda _scan_config: scope_context)
     monkeypatch.setattr(runner, "make_model_settings", lambda *_args, **_kwargs: ModelSettings())
-    monkeypatch.setattr(
-        mcp_client,
-        "_build_server",
-        lambda config: mcp_client.BuiltMcpServer(FakeMCPServer(config.name, []), None),
-    )
 
     captured: dict[str, Any] = {}
 
@@ -233,12 +222,7 @@ async def test_mcp_available_flag_set_when_a_connection_attaches(
     assert kwargs["system_prompt_context"]["mcp_available"] is True
     # The named inventory names each connected server for the prompt.
     assert kwargs["system_prompt_context"]["mcp_connections"] == [
-        {
-            "name": "fs",
-            "purpose": "local files",
-            "tool_count": 0,
-            "state": "catalog_ready",
-        }
+        {"name": "fs", "purpose": "local files", "tool_count": 0}
     ]
 
 

tests/test_stream_idle_timeout.py

@@ -23,8 +23,7 @@ from openai import AsyncOpenAI
 
 from strix.config import loader
 from strix.config.loader import load_settings
-from strix.config.models import StrixProvider, _TurnGuardModel, _with_timeouts
-from strix.llm import request_log
+from strix.config.models import StrixProvider, _TurnGuardModel, _with_idle_timeout
 
 
 if TYPE_CHECKING:
@@ -79,21 +78,9 @@ def stalling_gateway() -> Iterator[str]:
         server.server_close()
 
 
-class _ServedByRelace(OpenAIChatCompletionsModel):
-    async def stream_response(self, *args: Any, **kwargs: Any) -> AsyncIterator[Any]:
-        request_log.record_upstream_provider("Relace")
-        async for event in super().stream_response(*args, **kwargs):
-            yield event
-
-
-def _stream(base_url: str, *, idle_timeout: float | None) -> AsyncIterator[Any]:
+def _stream(base_url: str, *, idle_timeout: float) -> AsyncIterator[Any]:
     client = AsyncOpenAI(api_key="tok", base_url=base_url, max_retries=0, timeout=_STALL_SECONDS)
-    inner: Model = request_log.RequestLoggingModel(
-        _ServedByRelace(model="gw-model", openai_client=client),
-        model_name="gw-model",
-        provider="openai",
-        base_url=base_url,
-    )
+    inner: Model = OpenAIChatCompletionsModel(model="gw-model", openai_client=client)
     guarded = _TurnGuardModel(inner, stream_idle_timeout=idle_timeout)
     return guarded.stream_response(
         None,
@@ -109,7 +96,7 @@ def _stream(base_url: str, *, idle_timeout: float | None) -> AsyncIterator[Any]:
     )
 
 
-async def _drain(base_url: str, *, idle_timeout: float | None) -> list[Any]:
+async def _drain(base_url: str, *, idle_timeout: float) -> list[Any]:
     return [event async for event in _stream(base_url, idle_timeout=idle_timeout)]
 
 
@@ -118,31 +105,16 @@ async def test_stalled_stream_hangs_without_the_watchdog(stalling_gateway: str)
     # Repro: tokens arrive, then nothing. Un-watched, the turn just sits there;
     # the request timeout is far away and would reset on any keepalive byte.
     with pytest.raises(TimeoutError):
-        await asyncio.wait_for(_drain(stalling_gateway, idle_timeout=None), timeout=2)
+        await asyncio.wait_for(_drain(stalling_gateway, idle_timeout=0), timeout=2)
 
 
 @pytest.mark.asyncio
 async def test_stalled_stream_is_abandoned_by_the_watchdog(stalling_gateway: str) -> None:
-    logged: list[request_log.LlmRequestEvent] = []
-    request_log.register_sink(logged.append)
     started = time.monotonic()
-    try:
-        with pytest.raises(TimeoutError, match="stream_idle_timeout"):
-            await _drain(stalling_gateway, idle_timeout=1)
-    finally:
-        request_log.unregister_sink(logged.append)
+    with pytest.raises(TimeoutError, match="produced no event"):
+        await _drain(stalling_gateway, idle_timeout=1)
 
     assert time.monotonic() - started < _STALL_SECONDS
-    # The request log can tell our timeout from a shutdown.
-    assert [
-        (e.error_type, (e.details or {}).get("upstream_provider"), e.error_message) for e in logged
-    ] == [
-        (
-            "stream_idle_timeout",
-            "Relace",
-            "attempt cancelled before the reply was consumed: strix:stream_idle_timeout",
-        )
-    ]
 
 
 @pytest.mark.asyncio
@@ -152,39 +124,14 @@ async def test_events_keep_flowing_while_the_stream_is_alive() -> None:
             await asyncio.sleep(0.05)
             yield f"event-{i}"
 
-    seen: list[Any] = [event async for event in _with_timeouts(_live(), idle=1.0)]
+    seen: list[Any] = [event async for event in _with_idle_timeout(_live(), 1.0)]
 
     assert seen == [f"event-{i}" for i in range(5)]
 
 
-@pytest.mark.asyncio
-async def test_first_event_and_whole_stream_are_bounded() -> None:
-    async def _slow_start() -> AsyncIterator[Any]:
-        await asyncio.sleep(_STALL_SECONDS)
-        yield "late"
-
-    async def _endless() -> AsyncIterator[Any]:
-        while True:
-            await asyncio.sleep(0.05)
-            yield "event"
-
-    with pytest.raises(TimeoutError, match="stream_first_event_timeout"):
-        [event async for event in _with_timeouts(_slow_start(), idle=5, first_event=0.2)]
-    with pytest.raises(TimeoutError, match="stream_idle_timeout"):
-        [event async for event in _with_timeouts(_slow_start(), idle=0.2)]
-    with pytest.raises(TimeoutError, match="stream_total_timeout"):
-        [event async for event in _with_timeouts(_endless(), idle=5, total=0.3)]
-
-
 @pytest.fixture
 def _reset_settings(monkeypatch: pytest.MonkeyPatch) -> Iterator[None]:
-    for key in (
-        "STRIX_LLM",
-        "LLM_DISABLE_STREAMING",
-        "LLM_STREAM_IDLE_TIMEOUT",
-        "LLM_STREAM_FIRST_EVENT_TIMEOUT",
-        "LLM_STREAM_TOTAL_TIMEOUT",
-    ):
+    for key in ("STRIX_LLM", "LLM_DISABLE_STREAMING", "LLM_STREAM_IDLE_TIMEOUT"):
         monkeypatch.delenv(key, raising=False)
     monkeypatch.setattr(loader, "_cached", None)
     monkeypatch.setattr(loader, "_override", None)
@@ -204,15 +151,11 @@ def test_idle_timeout_is_configurable(
 ) -> None:
     monkeypatch.setattr("strix.config.models.MultiProvider.get_model", lambda *_: _DummyModel())
     monkeypatch.setenv("LLM_STREAM_IDLE_TIMEOUT", "45")
-    monkeypatch.setenv("LLM_STREAM_FIRST_EVENT_TIMEOUT", "30")
-    monkeypatch.setenv("LLM_STREAM_TOTAL_TIMEOUT", "400")
     load_settings()
 
     model = StrixProvider().get_model("openai/gpt-4o-mini")
     assert isinstance(model, _TurnGuardModel)
     assert model._stream_idle_timeout == 45
-    assert model._first_event_timeout == 30
-    assert model._total_timeout == 400
 
 
 def test_idle_timeout_is_off_without_streaming(
@@ -227,4 +170,4 @@ def test_idle_timeout_is_off_without_streaming(
 
     model = StrixProvider().get_model("openai/gpt-4o-mini")
     assert isinstance(model, _TurnGuardModel)
-    assert model._stream_idle_timeout is model._first_event_timeout is model._total_timeout is None
+    assert model._stream_idle_timeout == 0