style: drop a trailing space in the image-support docstring

Add model_supports_images(): OpenRouter models are checked against architecture.input_modalities from OpenRouter's public model list (fetched once per process), others against LiteLLM's supports_vision. Unknown models and lookup failures count as image-capable. Not wired in yet.

strix/agents/factory.py

@@ -375,15 +375,11 @@ def _configure_filesystem_tools(
             )
 
 
-def _make_filesystem_configurator(
-    *, chat_completions: bool, strict_schemas: bool, supports_images: bool = True
-) -> Any:
+def _make_filesystem_configurator(*, chat_completions: bool, strict_schemas: bool) -> Any:
     def configure(toolset: Any) -> None:
         _configure_filesystem_tools(
             toolset, chat_completions=chat_completions, strict_schemas=strict_schemas
         )
-        if not supports_images:
-            toolset.view_image.is_enabled = False
 
     return configure
 
@@ -674,7 +670,6 @@ def build_strix_agent(
     system_prompt_context: dict[str, Any] | None = None,
     extra_tools: Sequence[Tool] | None = None,
     instructions_override: str | None = None,
-    supports_images: bool = True,
 ) -> SandboxAgent[Any]:
     """Build a SandboxAgent for either root or child use.
 
@@ -699,7 +694,6 @@ def build_strix_agent(
             is_diff_scoped=is_diff_scoped,
             interactive=interactive,
             system_prompt_context=system_prompt_context,
-            supports_images=supports_images,
         )
 
     agent_tools = [*_EXTRA_TOOLS, *(extra_tools or [])]
@@ -739,7 +733,6 @@ def build_strix_agent(
                 configure_tools=_make_filesystem_configurator(
                     chat_completions=chat_completions_tools,
                     strict_schemas=strict_tool_schemas,
-                    supports_images=supports_images,
                 ),
             ),
             Shell(
@@ -761,7 +754,6 @@ def make_child_factory(
     chat_completions_tools: bool = False,
     strict_tool_schemas: bool = True,
     system_prompt_context: dict[str, Any] | None = None,
-    supports_images: bool = True,
 ) -> Any:
     """Return the runner-owned builder used by ``spawn_child_agent``.
 
@@ -782,7 +774,6 @@ def make_child_factory(
             chat_completions_tools=chat_completions_tools,
             strict_tool_schemas=strict_tool_schemas,
             system_prompt_context=system_prompt_context,
-            supports_images=supports_images,
         )
 
     return _factory

strix/agents/prompt.py

@@ -85,7 +85,6 @@ def render_system_prompt(
     interactive: bool = False,
     system_prompt_context: dict[str, Any] | None = None,
     include_scope: bool = True,
-    supports_images: bool = True,
 ) -> str:
     """Render the system prompt. Returns empty string on template failure.
 
@@ -120,7 +119,7 @@ def render_system_prompt(
             is_root=is_root,
             is_diff_scoped=is_diff_scoped,
         )
-        skill_content = load_skills(skills_to_load, supports_images=supports_images)
+        skill_content = load_skills(skills_to_load)
         env.globals["get_skill"] = lambda name: skill_content.get(name, "")
 
         # Skills every agent of this kind loads come first, so siblings share them

strix/core/execution.py

@@ -4,12 +4,9 @@ from __future__ import annotations
 
 import asyncio
 import contextlib
-import inspect
 import logging
-import re
 import uuid
 from collections.abc import Callable
-from dataclasses import replace
 from functools import cache
 from typing import TYPE_CHECKING, Any, cast
 
@@ -33,7 +30,6 @@ from strix.core.sessions import (
     enforce_image_budget,
     open_agent_session,
     replace_session_items,
-    scrub_images_from_items,
     seed_initial_input,
     strip_all_images_from_session,
 )
@@ -48,7 +44,6 @@ if TYPE_CHECKING:
     from agents.lifecycle import RunHooks
     from agents.memory import Session, SQLiteSession
     from agents.result import RunResultBase
-    from agents.run_config import CallModelData, ModelInputData
 
     from strix.core.agents import AgentCoordinator, Status
 
@@ -58,17 +53,6 @@ logger = logging.getLogger(__name__)
 StreamEventSink = Callable[[str, Any], None]
 
 _INPUT_REJECTION_CODES = frozenset({400, 404, 422})
-# Replies meaning "this model takes no images", not image errors in general: a
-# context overflow that counts "image/vision expansion" must not match.
-_IMAGE_REJECTION = re.compile(
-    r"no endpoints found that support image input"  # OpenRouter
-    r"|image_url is only supported by certain models"  # OpenAI
-    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
-    re.IGNORECASE,
-)
 _MAX_COMPACTIONS_PER_CYCLE = 2
 
 
@@ -136,28 +120,6 @@ async def _compact_session(
     )
 
 
-_TEXT_ONLY_IMAGE_TEXT = "[error: this model cannot view images; use `snapshot -i` instead]"
-
-
-def _with_image_scrub(run_config: RunConfig, context: dict[str, Any]) -> RunConfig:
-    if context.get("supports_images", True):
-        return run_config
-    # Chain any filter already set; it sees the scrubbed input.
-    inner = run_config.call_model_input_filter
-
-    async def _scrub(data: CallModelData[Any]) -> ModelInputData:
-        model_data = replace(
-            data.model_data,
-            input=scrub_images_from_items(data.model_data.input, text=_TEXT_ONLY_IMAGE_TEXT),
-        )
-        if inner is None:
-            return model_data
-        result = inner(replace(data, model_data=model_data))
-        return await result if inspect.isawaitable(result) else result
-
-    return replace(run_config, call_model_input_filter=_scrub)
-
-
 _MAX_TRANSIENT_MODEL_RETRIES = 5
 _TRANSIENT_MODEL_RETRY_BASE_DELAY_S = 2.0
 _TRANSIENT_MODEL_RETRY_MAX_DELAY_S = 90.0
@@ -168,12 +130,6 @@ def _model_error_status_code(exc: BaseException) -> int | None:
     return code if isinstance(code, int) else None
 
 
-def _is_image_rejection(exc: BaseException) -> bool:
-    return _model_error_status_code(exc) in _INPUT_REJECTION_CODES and bool(
-        _IMAGE_REJECTION.search(str(exc))
-    )
-
-
 def _is_transient_model_error(exc: BaseException) -> bool:
     if codex.is_content_guardrail_error(exc):
         return False
@@ -791,7 +747,7 @@ async def _run_cycle(  # noqa: PLR0912, PLR0915
             stream = Runner.run_streamed(
                 agent,
                 input=input_data,
-                run_config=_with_image_scrub(run_config, context),
+                run_config=run_config,
                 context=context,
                 max_turns=max_turns,
                 session=session,
@@ -849,7 +805,11 @@ async def _run_cycle(  # noqa: PLR0912, PLR0915
             await coordinator.trigger_budget_stop()
             raise
         except Exception as exc:
-            if image_strips < 3 and session is not None and _is_image_rejection(exc):
+            if (
+                image_strips < 3
+                and session is not None
+                and getattr(exc, "status_code", None) in _INPUT_REJECTION_CODES
+            ):
                 try:
                     stripped = await strip_all_images_from_session(session)
                 except Exception:

strix/core/runner.py

@@ -23,7 +23,6 @@ from strix.config.models import (
     StrixProvider,
     configure_sdk_api_route,
     configure_sdk_model_defaults,
-    model_supports_images,
     supports_strict_tool_schemas,
     uses_chat_completions_tool_schema,
 )
@@ -154,7 +153,6 @@ def _compose_root_instructions_override(
     is_diff_scoped: bool,
     interactive: bool,
     system_prompt_context: dict[str, Any],
-    supports_images: bool,
 ) -> str | None:
     if root_instructions_override is None:
         return None
@@ -168,7 +166,6 @@ def _compose_root_instructions_override(
         interactive=interactive,
         system_prompt_context=system_prompt_context,
         include_scope=False,
-        supports_images=supports_images,
     )
     return (
         f"{base_instructions}\n\n"
@@ -268,9 +265,6 @@ async def run_strix_scan(
     strict_tool_schemas = supports_strict_tool_schemas(resolved_model)
     if not strict_tool_schemas:
         logger.info("Sending non-strict tool schemas: %s caps strict tools", resolved_model)
-    supports_images = model_supports_images(resolved_model)
-    if not supports_images:
-        logger.info("Leaving out image tools: %s does not accept images", resolved_model)
 
     if budget_policy not in ("stop", "pause"):
         raise ValueError(f"unknown budget_policy: {budget_policy!r}")
@@ -474,7 +468,6 @@ async def run_strix_scan(
             is_diff_scoped=is_diff_scoped,
             interactive=interactive,
             system_prompt_context=root_context,
-            supports_images=supports_images,
         )
 
         root_agent = build_strix_agent(
@@ -489,7 +482,6 @@ async def run_strix_scan(
             strict_tool_schemas=strict_tool_schemas,
             system_prompt_context=root_context,
             instructions_override=root_instructions,
-            supports_images=supports_images,
         )
 
         if not is_resume:
@@ -509,7 +501,6 @@ async def run_strix_scan(
             chat_completions_tools=chat_completions_tools,
             strict_tool_schemas=strict_tool_schemas,
             system_prompt_context=scope_context,
-            supports_images=supports_images,
         )
 
         async def spawn_child_agent(**kwargs: Any) -> dict[str, Any]:
@@ -537,7 +528,6 @@ async def run_strix_scan(
             "spawn_child_agent": spawn_child_agent,
             "scan_targets": build_scan_targets(scan_config),
             "max_context_images": settings.runtime.max_context_images,
-            "supports_images": supports_images,
         }
 
         root_session = open_agent_session(root_id, agents_db)
@@ -602,7 +592,7 @@ async def run_strix_scan(
         )
         if not interactive and result is not None:
             final = getattr(result, "final_output", None)
-            # Lifecycle tools mark the root completed.
+            # Lifecycle tools mark the root completed. 
             async with coordinator._lock:
                 root_completed = coordinator.statuses.get(root_id) == "completed"
             if not root_completed:

strix/core/sessions.py

@@ -199,13 +199,13 @@ async def enforce_image_budget(session: Session, max_images: int) -> bool:
     return await _rewrite_session(session, _transform)
 
 
-def scrub_images_from_items(items: list[Any], *, text: str = _INHERITED_IMAGE_TEXT) -> list[Any]:
+def scrub_images_from_items(items: list[Any]) -> list[Any]:
     """Return a copy of ``items`` with every image block replaced by text."""
 
     def _scrub(obj: Any) -> Any:
         if isinstance(obj, dict):
             if obj.get("type") == "input_image":
-                return {"type": "input_text", "text": text}
+                return {"type": "input_text", "text": _INHERITED_IMAGE_TEXT}
             return {k: _scrub(v) for k, v in obj.items()}
         if isinstance(obj, list):
             return [_scrub(v) for v in obj]

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

@@ -90,7 +90,6 @@ type Model struct {
 	client                 *Client
 	width, height          int
 	snapshot               protocol.Snapshot
-	windowTitle            string
 	input                  textarea.Model
 	viewport               viewport.Model
 	viewportContent        string

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

@@ -2,13 +2,10 @@ package app
 
 import (
 	"encoding/json"
-	"fmt"
-	"os"
 	"strings"
 	"time"
 
 	tea "github.com/charmbracelet/bubbletea"
-	"github.com/charmbracelet/x/ansi"
 	"github.com/usestrix/strix/tui/internal/protocol"
 	"github.com/usestrix/strix/tui/internal/render"
 )
@@ -59,10 +56,6 @@ func (m *Model) handleEnvelope(envelope protocol.Envelope) tea.Cmd {
 		// resize (not just refresh): status-row visibility changes the chat height.
 		m.resizeViewport()
 		m.resizeVulnerabilityViewport()
-		if title := windowTitle(m.snapshot.Targets); title != m.windowTitle {
-			m.windowTitle = title
-			return setTerminalTitle(title)
-		}
 	case "collection_bootstrap":
 		return m.handleCollectionBootstrap(envelope.Payload)
 	case "collection_delta":
@@ -125,26 +118,6 @@ func (m *Model) handleEnvelope(envelope protocol.Envelope) tea.Cmd {
 	return nil
 }
 
-// tea.SetWindowTitle only sends OSC 2 (window title); iTerm tabs show the OSC 1
-// icon name, which shells usually set, so send OSC 0 to set both.
-func setTerminalTitle(title string) tea.Cmd {
-	return func() tea.Msg {
-		_, _ = os.Stdout.WriteString(ansi.SetIconNameWindowTitle(title))
-		return nil
-	}
-}
-
-func windowTitle(targets []string) string {
-	switch len(targets) {
-	case 0:
-		return "strix"
-	case 1:
-		return targets[0]
-	default:
-		return fmt.Sprintf("%s +%d", targets[0], len(targets)-1)
-	}
-}
-
 func (m *Model) consumeMessages(messages []protocol.Message, setupMode bool) {
 	if m.seenMessages == nil {
 		m.seenMessages = map[string]bool{}

strix/skills/__init__.py

@@ -6,7 +6,6 @@ from pathlib import Path
 from typing import TypeGuard
 
 import yaml
-from jinja2 import Environment, StrictUndefined
 
 from strix.utils.resource_paths import get_strix_resource_path
 
@@ -14,14 +13,6 @@ from strix.utils.resource_paths import get_strix_resource_path
 logger = logging.getLogger(__name__)
 
 _FRONTMATTER_PATTERN = re.compile(r"^---\s*\n(?P<body>.*?)\n---\s*\n", re.DOTALL)
-# Only skills with `template: jinja` in their frontmatter are rendered; the rest hold
-# literal `{{ }}` payloads.
-_SKILL_TEMPLATES = Environment(
-    autoescape=False,  # noqa: S701  # nosec B701 - prompts, not HTML
-    undefined=StrictUndefined,
-    trim_blocks=True,
-    lstrip_blocks=True,
-)
 
 _INTERNAL_SKILL_CATEGORIES: frozenset[str] = frozenset({"scan_modes", "coordination", "analysis"})
 _ROOT_SKILL_CATEGORY = "root"
@@ -270,7 +261,7 @@ def _candidate_skill_files(skill_name: str) -> list[Path]:
     return _bare_skill_files(skill_name)
 
 
-def load_skills(skill_names: list[str], *, supports_images: bool = True) -> dict[str, str]:
+def load_skills(skill_names: list[str]) -> dict[str, str]:
     """Load skill markdown bodies (frontmatter stripped) by name.
 
     Skill files live at ``strix/skills/<category>/<name>.md`` (or any
@@ -300,11 +291,7 @@ def load_skills(skill_names: list[str], *, supports_images: bool = True) -> dict
             continue
 
         var_name = skill_name.split("/")[-1]
-        metadata, skill_body = _parse_skill_content(content, file_path)
-        if metadata.get("template") == "jinja":
-            skill_body = _SKILL_TEMPLATES.from_string(skill_body).render(
-                supports_images=supports_images
-            )
+        _, skill_body = _parse_skill_content(content, file_path)
         skill_content[var_name] = skill_body
         logger.debug("Loaded skill: %s -> %s", skill_name, var_name)
         _track_skill_loaded(var_name, file_path)

strix/skills/tooling/agent_browser.md

@@ -1,7 +1,6 @@
 ---
 name: agent_browser
 description: agent-browser CLI for headless Chrome via shell. Snapshot-and-ref workflow, click/fill/extract, screenshots, multi-tab, multi-session, network mocking. Pre-installed in the sandbox; invoke via exec_command.
-template: jinja
 ---
 
 
@@ -261,9 +260,8 @@ only for simple expressions.
 
 ### Screenshot
 
-`agent-browser screenshot` writes a PNG to disk in the sandbox.
-{% if supports_images %}
-The shell command alone does **not** put the image into your context —
+`agent-browser screenshot` writes a PNG to disk in the sandbox. The
+shell command alone does **not** put the image into your context —
 chain it with the SDK ``view_image`` tool to actually see it:
 
 ```bash
@@ -277,12 +275,6 @@ the full path on stdout — pass that to ``view_image``). If you need a
 specific filename, keep it inside that directory or a sibling hidden
 dir under ``/workspace``. Never write screenshots to ``/tmp`` —
 ``view_image`` rejects anything outside the workspace root.
-{% else %}
-You are running on a text-only model and cannot view images. Screenshots
-are only useful to you as a saved file (for example, login evidence).
-Drive the page from `snapshot -i` refs, `eval` for any DOM/JS state you
-need to read, and `text @ref` / `get text` for content extraction.
-{% endif %}
 
 ```bash
 agent-browser screenshot                        # path printed on stdout
@@ -291,7 +283,6 @@ agent-browser screenshot --full                 # full scroll height
 agent-browser screenshot --annotate             # numbered labels + legend keyed to snapshot refs
 ```
 
-{% if supports_images %}
 `--annotate` is designed for multimodal models: each label `[N]` maps
 to ref `@eN`. Take the annotated screenshot, then ``view_image`` it,
 and you can correlate visual layout with snapshot refs.
@@ -303,10 +294,10 @@ layout questions, captchas, custom widgets where the accessibility
 tree is incomplete).
 
 If ``view_image`` errors back at you (rejected image, "vision not
-supported", or similar), you can drive the page from `snapshot -i`
-refs, `eval` for any DOM/JS state you need to read, and `text @ref`
-or `get text` for content extraction.
-{% endif %}
+supported", or similar), you are running on a text-only model — stop
+calling it and stop taking screenshots. Drive the page entirely from
+`snapshot -i` refs, `eval` for any DOM/JS state you need to read, and
+`text @ref` / `get text` for content extraction.
 
 ### Handle multiple pages via tabs
 

strix/telemetry/logging.py

@@ -3,7 +3,6 @@
 from __future__ import annotations
 
 import contextlib
-import functools
 import logging
 import os
 import sys
@@ -79,16 +78,6 @@ class _StdoutQuietFilter(logging.Filter):
         )
 
 
-class _PtyThresholdFilter(logging.Filter):
-    def filter(self, record: logging.LogRecord) -> bool:
-        return "PTY process count reached warning threshold" not in record.getMessage()
-
-
-@functools.cache  # install once; tests reset via ``cache_clear()``
-def _silence_pty_threshold_warning() -> None:
-    logging.getLogger("agents.sandbox.sandboxes.docker").addFilter(_PtyThresholdFilter())
-
-
 def configure_dependency_logging() -> None:
     """Quiet dependency logging/warnings that obscure Strix scan logs."""
     litellm = sys.modules.get("litellm")
@@ -100,7 +89,6 @@ def configure_dependency_logging() -> None:
     logging.getLogger("asyncio").propagate = False
     warnings.filterwarnings("ignore", category=RuntimeWarning, module="asyncio")
     _route_unraisable_to_log()
-    _silence_pty_threshold_warning()
 
 
 def _route_unraisable_to_log() -> None:

strix/tools/load_skill/tool.py

@@ -24,12 +24,12 @@ async def load_skill(ctx: RunContextWrapper, skills: list[str]) -> str:
             Max 5. Names match the bare files under
             ``strix/skills/<category>/<name>.md``.
     """
+    del ctx
     requested = list(skills or [])
     err = validate_requested_skills(requested)
     if err:
         return f"load_skill: {err}"
-    context = ctx.context if isinstance(ctx.context, dict) else {}
-    contents = load_skills(requested, supports_images=context.get("supports_images", True))
+    contents = load_skills(requested)
     if not contents:
         return "load_skill: no content loaded for requested skills."
     sections = [f"## Skill: {name}\n\n{body}" for name, body in contents.items()]

strix/tools/mcp/agent_tools.py

@@ -288,11 +288,9 @@ async def call_mcp(
             "Call search_mcp_tools, then get_mcp_tool_schema."
         )
     session = await entry.ensure_connected()
-    context = ctx.context if isinstance(ctx.context, dict) else {}
     return await session.dispatch(
         tool,
         arguments or {},
         label=namespaced_tool_name(connection, tool),
         result_transform=entry.result_transform,
-        supports_images=context.get("supports_images", True),
     )

strix/tools/mcp/client.py

@@ -32,7 +32,6 @@ from agents.mcp import (
 )
 from mcp.client.stdio import stdio_client
 from mcp.shared._httpx_utils import create_mcp_http_client
-from mcp.types import TextContent
 
 from strix.tools.mcp.failures import HttpStatusRecorder
 from strix.tools.mcp.session import McpConnectionUnavailableError, SupervisedMcpSession
@@ -184,18 +183,6 @@ def _build_server(config: McpConnectionConfig) -> BuiltMcpServer:
     )
 
 
-def _without_images(result: Any) -> Any:
-    content = [
-        TextContent(
-            type="text", text=f"[{item.mimeType} image omitted: this model cannot view images]"
-        )
-        if item.type == "image"
-        else item
-        for item in result.content
-    ]
-    return result.model_copy(update={"content": content})
-
-
 def _mcp_result_to_tool_output(server: MCPServer, result: Any) -> Any:
     """Serialize a ``CallToolResult`` to a tool output, mirroring the agents SDK.
 
@@ -230,7 +217,6 @@ async def dispatch_mcp_call(
     *,
     label: str,
     result_transform: ResultTransform | None = None,
-    supports_images: bool = True,
 ) -> Any:
     """Run one MCP tool call and convert its result to a tool output.
 
@@ -247,8 +233,6 @@ async def dispatch_mcp_call(
       corrupt the content the agent receives).
     """
     result = await server.call_tool(tool_name, arguments)
-    if not supports_images:
-        result = _without_images(result)
     if result_transform is not None:
         return result_transform(label, result.model_dump(mode="json"))
     tool_output = _mcp_result_to_tool_output(server, result)

strix/tools/mcp/session.py

@@ -365,7 +365,6 @@ class SupervisedMcpSession:
         *,
         label: str,
         result_transform: ResultTransform | None = None,
-        supports_images: bool = True,
     ) -> Any:
         """Run one tool call with bounded retries for transient session failures.
 
@@ -383,7 +382,6 @@ class SupervisedMcpSession:
                 arguments,
                 label=label,
                 result_transform=result_transform,
-                supports_images=supports_images,
             )
 
         outcome = await self._run_job(job, phase="call")

tests/test_agent_factory_shell.py

@@ -115,15 +115,3 @@ def test_function_tools_are_result_bounded() -> None:
     by_name = {t.name: t for t in agent.tools}
 
     assert getattr(by_name["think"], "_strix_bounded", False) is True
-
-
-@pytest.mark.parametrize(("supports_images", "has_view_image"), [(True, True), (False, False)])
-def test_view_image_is_left_out_for_text_only_models(
-    supports_images: bool, has_view_image: bool
-) -> None:
-    agent = factory.build_strix_agent(is_root=True, supports_images=supports_images)
-    filesystem = agent.capabilities[0]
-    filesystem.bind(cast("Any", object()))
-
-    view_image = next(tool for tool in filesystem.tools() if tool.name == "view_image")
-    assert cast("FunctionTool", view_image).is_enabled is has_view_image

tests/test_execution.py

@@ -9,11 +9,9 @@ from typing import Any, cast
 from unittest.mock import MagicMock
 
 import pytest
-from agents import RunConfig
 from agents.exceptions import MaxTurnsExceeded
 from agents.items import MessageOutputItem
 from agents.memory import SQLiteSession
-from agents.run_config import CallModelData, ModelInputData
 from agents.tool_context import ToolContext
 from openai.types.responses import ResponseOutputMessage, ResponseOutputRefusal, ResponseOutputText
 
@@ -1533,32 +1531,3 @@ async def test_autonomous_nudge_does_not_offer_the_user() -> None:
     )
 
     assert "wait_for_user" not in items[0]["content"]
-
-
-@pytest.mark.asyncio
-async def test_text_only_filter_scrubs_images_then_chains_existing_filter() -> None:
-    run_config = RunConfig(model="m")
-    assert execution._with_image_scrub(run_config, {"supports_images": True}) is run_config
-
-    seen: list[ModelInputData] = []
-
-    def _inner(data: CallModelData[Any]) -> ModelInputData:
-        seen.append(data.model_data)
-        return data.model_data
-
-    run_config = RunConfig(model="m", call_model_input_filter=_inner)
-    scrub: Any = execution._with_image_scrub(run_config, {"supports_images": False})
-    image = {"type": "input_image", "image_url": "data:image/png;base64,aGk="}
-    output = {"type": "function_call_output", "call_id": "c1", "output": [image]}
-    data = CallModelData(
-        model_data=ModelInputData(input=[cast("Any", output)], instructions="sys"),
-        agent=MagicMock(),
-        context=None,
-    )
-
-    result = await scrub.call_model_input_filter(data)
-    assert result is seen[0]
-    assert result.input[0]["output"] == [
-        {"type": "input_text", "text": execution._TEXT_ONLY_IMAGE_TEXT}
-    ]
-    assert data.model_data.input[0]["output"] == [image]

tests/test_execution_transient_retry.py

@@ -109,7 +109,6 @@ def _patch_fast_backoff(monkeypatch: pytest.MonkeyPatch) -> None:
 async def _run_once(
     monkeypatch: pytest.MonkeyPatch,
     streams: list[_FakeStream],
-    session: Any = None,
 ) -> Any:
     _patch_fast_backoff(monkeypatch)
     calls = {"n": 0}
@@ -132,7 +131,7 @@ async def _run_once(
         run_config=cast("RunConfig", object()),
         context={},
         max_turns=5,
-        session=session,
+        session=None,
         interactive=False,
         event_sink=None,
         hooks=None,
@@ -173,74 +172,3 @@ async def test_run_cycle_does_not_retry_permanent_error(
     streams = [_FakeStream(exc=bad_request), _FakeStream()]
     with pytest.raises(BadRequestError):
         await _run_once(monkeypatch, streams)
-
-
-@pytest.mark.parametrize(
-    ("status", "message", "expected"),
-    [
-        (
-            404,
-            "litellm.NotFoundError: NotFoundError: OpenrouterException - "
-            '{"error":{"message":"No endpoints found that support image input","code":404,'
-            '"metadata":{"failed_routing_step":"Filter by Image Support"}}}',
-            True,
-        ),
-        (400, "Invalid content type. image_url is only supported by certain models.", True),
-        (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,
-            "OpenRouterException: Message: This model's maximum context length is 1048576 "
-            "tokens, but the request requires 1073484 tokens (942412 input including "
-            "image/vision expansion + 131072 for the completion). Reduce the input length "
-            "or max_tokens.",
-            False,
-        ),
-        (400, "At most 5 image(s) may be provided in one prompt.", False),
-        (
-            400,
-            "Upstream error from Relace: Generation stopped with an incomplete tool call",
-            False,
-        ),
-        (500, "No endpoints found that support image input", False),
-    ],
-)
-def test_is_image_rejection(status: int, message: str, expected: bool) -> None:
-    exc = APIStatusError(message, response=httpx.Response(status, request=_request()), body=None)
-    assert execution._is_image_rejection(exc) is expected
-
-
-async def _run_with_image_session(
-    monkeypatch: pytest.MonkeyPatch, streams: list[_FakeStream]
-) -> tuple[Any, int, int]:
-    strips = {"n": 0}
-
-    async def _fake_strip(_session: Any) -> bool:
-        strips["n"] += 1
-        return True
-
-    async def _no_compact(*_args: Any, **_kwargs: Any) -> bool:
-        return False
-
-    monkeypatch.setattr(execution, "strip_all_images_from_session", _fake_strip)
-    monkeypatch.setattr(execution, "_compact_session", _no_compact)
-    result, attempts, _coordinator = await _run_once(monkeypatch, streams, session=object())
-    return result, attempts, strips["n"]
-
-
-@pytest.mark.asyncio
-async def test_run_cycle_strips_images_on_image_rejection(
-    monkeypatch: pytest.MonkeyPatch,
-) -> None:
-    rejection = APIStatusError(
-        "No endpoints found that support image input",
-        response=httpx.Response(status_code=404, request=_request()),
-        body=None,
-    )
-    streams = [_FakeStream(exc=rejection), _FakeStream()]
-    result, attempts, strips = await _run_with_image_session(monkeypatch, streams)
-
-    assert result is streams[1]
-    assert attempts == 2
-    assert strips == 1

tests/test_mcp_client.py

@@ -18,7 +18,7 @@ from typing import TYPE_CHECKING, Any
 import pytest
 from agents.mcp import MCPServer, MCPServerStdio, MCPServerStreamableHttp
 from agents.tool_context import ToolContext
-from mcp.types import CallToolResult, ImageContent, TextContent
+from mcp.types import CallToolResult, TextContent
 from mcp.types import Tool as MCPTool
 from pydantic import ValidationError
 
@@ -884,51 +884,6 @@ async def test_call_mcp_flags_an_errored_result_failed_for_the_tui() -> None:
     assert out == {"type": "text", "text": "boom:read_file", "success": False}
 
 
-@pytest.mark.asyncio
-async def test_call_mcp_replaces_images_for_a_text_only_model() -> None:
-    class _ImageServer(FakeMCPServer):
-        async def call_tool(
-            self,
-            tool_name: str,
-            arguments: dict[str, Any] | None,
-            meta: dict[str, Any] | None = None,
-        ) -> CallToolResult:
-            return CallToolResult(
-                content=[
-                    TextContent(type="text", text="shot"),
-                    ImageContent(type="image", data="aGk=", mimeType="image/png"),
-                ]
-            )
-
-    registry = McpRegistry()
-    registry.add(
-        name="fs", server=_ImageServer("fs", [_mcp_tool("shot")]), purpose=None, tool_count=1
-    )
-    ctx = _ctx(registry)
-    args = json.dumps({"connection": "fs", "tool": "shot"})
-
-    out = await call_mcp.on_invoke_tool(ctx, args)
-    assert out[1] == {"type": "image", "image_url": "data:image/png;base64,aGk="}
-
-    ctx.context["supports_images"] = False
-    out = await call_mcp.on_invoke_tool(ctx, args)
-    assert out == [
-        {"type": "text", "text": "shot"},
-        {"type": "text", "text": "[image/png image omitted: this model cannot view images]"},
-    ]
-
-    transformed: list[Any] = []
-    registry.add(
-        name="pro",
-        server=_ImageServer("pro", [_mcp_tool("shot")]),
-        purpose=None,
-        tool_count=1,
-        result_transform=lambda _label, result: transformed.append(result),
-    )
-    await call_mcp.on_invoke_tool(ctx, json.dumps({"connection": "pro", "tool": "shot"}))
-    assert [block["type"] for block in transformed[0]["content"]] == ["text", "text"]
-
-
 # --- generic MCP tools are the only MCP surface every agent gets -------------
 
 

tests/test_pty_warning_filter.py

@@ -1,41 +0,0 @@
-import logging
-from collections.abc import Iterator
-
-import pytest
-
-from strix.telemetry import logging as tlog
-
-
-_SDK_LOGGER = "agents.sandbox.sandboxes.docker"
-
-
-@pytest.fixture
-def sdk_logger() -> Iterator[logging.Logger]:
-    logger = logging.getLogger(_SDK_LOGGER)
-    original = list(logger.filters)
-    logger.filters.clear()
-    tlog._silence_pty_threshold_warning.cache_clear()
-    yield logger
-    logger.filters[:] = original
-    tlog._silence_pty_threshold_warning.cache_clear()
-
-
-def _record(msg: str, *args: object) -> logging.LogRecord:
-    return logging.LogRecord(_SDK_LOGGER, logging.WARNING, __file__, 0, msg, args, None)
-
-
-def test_installed_filter_drops_pty_threshold_warning(sdk_logger: logging.Logger) -> None:
-    tlog._silence_pty_threshold_warning()
-    record = _record("PTY process count reached warning threshold: %s active sessions", 62)
-    assert not sdk_logger.filter(record)
-
-
-def test_installed_filter_keeps_other_warnings(sdk_logger: logging.Logger) -> None:
-    tlog._silence_pty_threshold_warning()
-    assert sdk_logger.filter(_record("something else went wrong"))
-
-
-def test_install_is_idempotent(sdk_logger: logging.Logger) -> None:
-    tlog._silence_pty_threshold_warning()
-    tlog._silence_pty_threshold_warning()
-    assert len(sdk_logger.filters) == 1

tests/test_runner_root_prompt.py

@@ -13,7 +13,6 @@ from typing import Any
 import httpx
 import pytest
 from agents import ModelSettings
-from agents.tool_context import ToolContext
 from openai import RateLimitError
 
 import strix.tools.mcp as mcp_pkg
@@ -25,7 +24,6 @@ from strix.core import runner
 from strix.core.agents import AgentCoordinator
 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
 
 
@@ -289,29 +287,6 @@ def test_requested_skills_follow_the_shared_prefix() -> None:
     assert "<xss>" in xss.split("<cache_point>")[1]
 
 
-def test_text_only_prompt_drops_screenshot_guidance() -> None:
-    assert "view_image" in render_system_prompt(include_scope=False)
-
-    prompt = render_system_prompt(include_scope=False, supports_images=False)
-    assert "view_image" not in prompt
-    assert "text-only model and cannot view images" in prompt
-    assert "<!--" not in prompt
-
-
-@pytest.mark.asyncio
-async def test_text_only_load_skill_drops_screenshot_guidance() -> None:
-    ctx = ToolContext(
-        context={"supports_images": False},
-        tool_name="load_skill",
-        tool_call_id="call-1",
-        tool_arguments="{}",
-    )
-
-    out = await load_skill.on_invoke_tool(ctx, '{"skills": ["agent_browser"]}')
-    assert "view_image" not in out
-    assert "text-only model" in out
-
-
 def test_scope_is_sent_as_its_own_system_message_on_cache_point_routes() -> None:
     settings = make_model_settings(None, model_name="anthropic/claude-sonnet-5-5")
     prompt = render_system_prompt(

tests/test_skill_dir_extension.py

@@ -70,17 +70,6 @@ def test_registered_dir_adds_new_skill(tmp_path: Path) -> None:
     assert load_skills(["widget"]) == {"widget": "widget body"}
 
 
-def test_only_jinja_skills_are_rendered(tmp_path: Path) -> None:
-    body = "{% if supports_images %}\nlook\n{% else %}\nread\n{% endif %}\n"
-    _write_skill(tmp_path, "extra", "plain", body)
-    _write_skill(tmp_path, "extra", "templated", f"---\ntemplate: jinja\n---\n{body}")
-    register_skill_dir(tmp_path)
-
-    assert load_skills(["plain"]) == {"plain": body}
-    assert load_skills(["templated"]) == {"templated": "look\n"}
-    assert load_skills(["templated"], supports_images=False) == {"templated": "read\n"}
-
-
 def test_available_skill_includes_frontmatter_description(tmp_path: Path) -> None:
     _write_skill(
         tmp_path,