fix(update): strip PyInstaller bootloader env vars before re-exec after self-update

The predictable lock path was opened with Path.open("w"), following (and
truncating through) a pre-positioned symlink. Open it via os.open with
O_NOFOLLOW and no O_TRUNC, raising StoreLockError on a symlinked lock path.

README.md

@@ -315,18 +315,6 @@ strix auth status             # show the active sign-in
 strix auth logout             # forget the sign-in
 ```
 
-#### Sign in with an OpenCode subscription
-
-You can also run Strix on [OpenCode Zen](https://opencode.ai/docs/zen/) credits or an [OpenCode Go](https://opencode.ai/docs/go/) subscription:
-
-```bash
-strix auth login opencode     # paste your API key from opencode.ai/auth
-
-export STRIX_LLM="opencode/claude-sonnet-5"   # opencode/<model> runs on Zen credits
-export STRIX_LLM="opencode-go/kimi-k3"        # opencode-go/<model> runs on the Go subscription
-strix --target ./app-directory
-```
-
 **Recommended models for best results:**
 
 - [OpenAI GPT-5.4](https://openai.com/api/) - `openai/gpt-5.4`

containers/Dockerfile

@@ -117,21 +117,6 @@ ENV AGENT_BROWSER_EXECUTABLE_PATH=/usr/bin/chromium
 ENV AGENT_BROWSER_USER_AGENT="Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/131.0.0.0 Safari/537.36"
 ENV AGENT_BROWSER_ARGS="--disable-blink-features=AutomationControlled,--no-first-run,--no-default-browser-check,--lang=en-US"
 ENV AGENT_BROWSER_SCREENSHOT_DIR=/workspace/.agent-browser-screenshots
-ENV AGENT_BROWSER_IDLE_TIMEOUT_MS=180000
-USER root
-RUN set -eu; \
-    { \
-        for var in AGENT_BROWSER_EXECUTABLE_PATH AGENT_BROWSER_USER_AGENT \
-                   AGENT_BROWSER_ARGS AGENT_BROWSER_SCREENSHOT_DIR \
-                   AGENT_BROWSER_IDLE_TIMEOUT_MS; do \
-            eval "value=\${$var}"; \
-            printf 'export %s="${%s:-%s}"\n' "$var" "$var" "$value"; \
-        done; \
-    } > /tmp/agent-browser.sh; \
-    install -m 0644 /tmp/agent-browser.sh /etc/profile.d/agent-browser.sh; \
-    rm /tmp/agent-browser.sh; \
-    env -i bash -lc 'test "${AGENT_BROWSER_IDLE_TIMEOUT_MS}" = "180000"'
-USER pentester
 RUN /home/pentester/.npm-global/bin/agent-browser doctor --offline --quick
 
 RUN set -eux; \

pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "strix-agent"
-version = "1.5.3"
+version = "1.5.1"
 description = "Open-source AI Hackers for your apps"
 readme = "README.md"
 license = "Apache-2.0"
@@ -230,6 +230,7 @@ ignore = [
 # args they intentionally ignore.
 "tests/test_viewer_auth.py" = ["S105", "S106", "ARG001"]
 "tests/test_codex_auth.py" = ["S105", "S106", "SLF001"]
+"tests/test_grok_auth.py" = ["S105", "S106", "SLF001"]
 # Hatchling loads the build hook by path, not as an importable package.
 "scripts/tui_sidecar_hook.py" = ["INP001"]
 # Stdlib HTTP handler overrides (do_GET/do_POST).
@@ -244,6 +245,9 @@ ignore = [
 # Stdlib HTTP handler overrides (do_GET/do_POST) and lazy imports that avoid a
 # circular dependency with strix.telemetry / strix.interface.viewer.report_pdf.
 "strix/interface/viewer/server.py" = ["N802", "PLC0415"]
+# Lazy import of the TUI live-view projection so importing the viewer does not
+# eagerly pull in the Textual TUI.
+"strix/interface/viewer/transcript.py" = ["PLC0415"]
 # Lazy telemetry import to avoid importing PostHog before the viewer starts.
 "strix/interface/viewer/cli.py" = ["PLC0415"]
 # Lazy imports inside functions to avoid circular dependency with
@@ -280,7 +284,6 @@ ignore = [
 # a runtime ``Callable`` annotation on ``vulnerability_found_callback``.
 "strix/report/state.py" = ["TC003", "PLR0912", "PLR0915", "E501", "PERF401", "PLC0415"]
 "strix/report/usage.py" = ["PLC0415"]
-"strix/report/pricing.py" = ["PLC0415"]
 # Lazy import of strix.config.models avoids a circular dependency between the
 # report pipeline and the config layer.
 "strix/report/dedupe.py" = ["PLC0415"]
@@ -289,6 +292,9 @@ ignore = [
 # Heavy inference deps (httpx, openai) imported lazily so auth-status checks
 # don't pull them in.
 "strix/config/codex.py" = ["PLC0415"]
+"strix/config/grok.py" = ["PLC0415"]
+# Lazy ``import fcntl`` so the module imports on non-POSIX platforms.
+"strix/config/subscription_store.py" = ["PLC0415"]
 # Interface utility branches per scope-mode / target-type combination;
 # splitting would obscure the decision tree without simplifying it.
 "strix/interface/utils.py" = ["PLR0912", "BLE001", "PLC0415"]

strix/agents/factory.py

@@ -160,9 +160,7 @@ def _schema_types(spec: dict[str, Any]) -> set[str]:
 def _decode_structured(value: str, types: set[str]) -> Any:
     stripped = value.strip()
     if not stripped:
-        # An empty string is the model's "no value" for a list/dict param; give it
-        # the empty container so it validates instead of failing the type check.
-        return [] if "array" in types else {}
+        return value
     try:
         decoded = json.loads(stripped)
     except json.JSONDecodeError:

strix/agents/prompts/system_prompt.jinja

@@ -39,8 +39,6 @@ INTERACTIVE BEHAVIOR:
   - To end the whole engagement, call the lifecycle tool: finish_scan (root) or agent_finish (subagent).
   - A turn that ends with plain text and no tool call does NOT stop you: the system nudges you to continue and will re-run you. Do not rely on going silent to pause — it will not pause you.
 - Answering a user question: put the answer in respond_to_user's message. Do not write the answer as plain text and then fall silent — that does not reach a stopping point, it just triggers a continuation nudge.
-- If all you want to do is reply and stop, that whole turn is ONE respond_to_user call carrying the answer. Do not write the answer as text and then call respond_to_user as well: the user reads it twice.
-- If you do end a turn on plain text and the nudge arrives, your words already reached the user. Do not restate them: call respond_to_user with NO message to simply wait, or with only whatever you still need to add.
 - You may include brief explanatory text before a tool call, and you can narrate while you work — plain text is shown to the user as you go. Narrating is free; respond_to_user is specifically the act of WAITING for the user, so do not call it just to give a status update.
 - Respond naturally when the user asks questions or gives instructions.
 - While actively working on a task, every turn should carry exactly one tool call — use think to plan, the appropriate tool to act, and respond_to_user only when you genuinely need the user.
@@ -263,13 +261,7 @@ Remember: A single well-validated high-impact vulnerability is worth more than d
 <multi_agent_system>
 AGENT ISOLATION & SANDBOXING:
 - All agents run in the same shared Docker container for efficiency
-- Each agent has its own terminal sessions
-- Browsers are NOT per-agent by default: `agent-browser` with no `--session` is one
-  shared browser, so a concurrent agent's navigation invalidates your page and refs.
-  Pass `--session <your-agent-name>` for any browser work of your own — then it is
-  yours alone. Each session is a full Chromium (~340 MB) on this shared box, so keep
-  one, not several, and `agent-browser --session <name> close` when you're done with
-  the target; an idle browser is reclaimed automatically after 3 minutes
+- Each agent has its own: browser sessions, terminal sessions
 - All agents share the same /workspace directory and proxy history
 - Agents can see each other's files and proxy traffic for better collaboration
 

strix/config/codex.py

@@ -16,7 +16,6 @@ import hashlib
 import json
 import logging
 import secrets
-import threading
 import time
 import urllib.parse
 from pathlib import Path
@@ -24,7 +23,7 @@ from typing import TYPE_CHECKING, Any
 
 import requests
 
-from strix.utils.secret_files import write_secret_text
+from strix.config import subscription_store
 
 
 if TYPE_CHECKING:
@@ -54,50 +53,12 @@ _ACCOUNT_CLAIM = "https://api.openai.com/auth"
 _TOKEN_TIMEOUT = 30
 _EXPIRY_SKEW_S = 300
 
-_refresh_lock = threading.Lock()
-
 # Kept separate from cli-config.json so OAuth tokens never land in the env-var config.
 AUTH_PATH = Path.home() / ".strix" / "subscription-auth.json"
 
 
-def _read_store() -> dict[str, Any]:
-    try:
-        data = json.loads(AUTH_PATH.read_text(encoding="utf-8"))
-    except (OSError, json.JSONDecodeError):
-        return {}
-    return data if isinstance(data, dict) else {}
-
-
-def _write_store(data: dict[str, Any]) -> None:
-    write_secret_text(AUTH_PATH, json.dumps(data, indent=2))
-
-
-def read_provider_record(provider: str) -> dict[str, Any] | None:
-    """Raw record for *provider* from the shared subscription-auth store."""
-    record = _read_store().get(provider)
-    return record if isinstance(record, dict) else None
-
-
-def save_provider_record(provider: str, record: dict[str, Any]) -> None:
-    data = _read_store()
-    data[provider] = record
-    _write_store(data)
-
-
-def remove_provider_record(provider: str) -> None:
-    data = _read_store()
-    if provider not in data:
-        return
-    del data[provider]
-    if data:
-        _write_store(data)
-        return
-    with contextlib.suppress(OSError):
-        AUTH_PATH.unlink()
-
-
 def read_record() -> dict[str, Any] | None:
-    record = read_provider_record(PROVIDER)
+    record = subscription_store.read(AUTH_PATH).get(PROVIDER)
     if not isinstance(record, dict) or record.get("type") != "oauth":
         return None
     if not (record.get("access") and record.get("refresh") and record.get("account_id")):
@@ -110,35 +71,31 @@ def is_authenticated() -> bool:
 
 
 def save_record(record: dict[str, Any]) -> None:
-    save_provider_record(PROVIDER, record)
+    with subscription_store.guard(AUTH_PATH):
+        data = subscription_store.read(AUTH_PATH)
+        data[PROVIDER] = record
+        subscription_store.write(AUTH_PATH, data)
 
 
 def logout() -> None:
-    remove_provider_record(PROVIDER)
+    with subscription_store.guard(AUTH_PATH):
+        data = subscription_store.read(AUTH_PATH)
+        if PROVIDER not in data:
+            return
+        del data[PROVIDER]
+        if data:
+            subscription_store.write(AUTH_PATH, data)
+            return
+        with contextlib.suppress(OSError):
+            AUTH_PATH.unlink()
 
 
 @contextlib.contextmanager
 def _refresh_guard() -> Iterator[None]:
     """Serialize token refresh within (lock) and across (flock) Strix processes,
     so concurrent runs can't both spend the single-use refresh token."""
-    with _refresh_lock:
-        try:
-            import fcntl
-
-            lock_path = AUTH_PATH.with_suffix(".lock")
-            lock_path.parent.mkdir(parents=True, exist_ok=True)
-            handle = lock_path.open("w")
-        except (ImportError, OSError):
-            yield
-            return
-        try:
-            with contextlib.suppress(OSError):
-                fcntl.flock(handle.fileno(), fcntl.LOCK_EX)
-            yield
-        finally:
-            with contextlib.suppress(OSError):
-                fcntl.flock(handle.fileno(), fcntl.LOCK_UN)
-            handle.close()
+    with subscription_store.guard(AUTH_PATH):
+        yield
 
 
 class CodexAuthError(Exception):

strix/config/grok.py

@@ -0,0 +1,310 @@
+"""Grok (xAI) subscription auth: OAuth login, token refresh, and the OpenAI
+client that routes inference through xAI's API.
+
+Mirrors xAI's Grok CLI: OAuth 2.0 + PKCE against ``auth.x.ai``, with the access
+token sent as a ``Bearer`` token to ``api.x.ai/v1`` (OpenAI-compatible, so the
+subscription and a metered API key share one endpoint — only the bearer differs).
+Using a Grok/SuperGrok subscription outside xAI's own products is not officially
+supported by xAI; the user chooses this path knowingly. The OAuth constants are
+xAI's own Grok CLI values (the backend only accepts that client).
+"""
+
+from __future__ import annotations
+
+import base64
+import contextlib
+import hashlib
+import json
+import logging
+import secrets
+import time
+import urllib.parse
+from pathlib import Path
+from typing import TYPE_CHECKING, Any
+
+import requests
+
+from strix.config import subscription_store
+
+
+if TYPE_CHECKING:
+    from collections.abc import Iterator
+
+    from openai import AsyncOpenAI
+
+
+logger = logging.getLogger(__name__)
+
+
+PROVIDER = "grok"
+
+CLIENT_ID = "b1a00492-073a-47ea-816f-4c329264a828"
+AUTHORIZE_URL = "https://auth.x.ai/oauth2/authorize"
+TOKEN_URL = "https://auth.x.ai/oauth2/token"  # noqa: S105  # nosec B105 - URL, not a secret
+CALLBACK_HOST = "127.0.0.1"
+CALLBACK_PORT = 56121
+CALLBACK_PATH = "/callback"
+REDIRECT_URI = f"http://{CALLBACK_HOST}:{CALLBACK_PORT}{CALLBACK_PATH}"
+SCOPE = "openid profile email offline_access grok-cli:access api:access"
+
+XAI_BASE_URL = "https://api.x.ai/v1"
+
+_TOKEN_TIMEOUT = 30
+_EXPIRY_SKEW_S = 300
+
+# Shared with the other subscription providers; kept separate from cli-config.json
+# so OAuth tokens never land in the env-var config.
+AUTH_PATH = Path.home() / ".strix" / "subscription-auth.json"
+
+
+def read_record() -> dict[str, Any] | None:
+    record = subscription_store.read(AUTH_PATH).get(PROVIDER)
+    if not isinstance(record, dict) or record.get("type") != "oauth":
+        return None
+    if not (record.get("access") and record.get("refresh")):
+        return None
+    return record
+
+
+def is_authenticated() -> bool:
+    return read_record() is not None
+
+
+def save_record(record: dict[str, Any]) -> None:
+    with subscription_store.guard(AUTH_PATH):
+        data = subscription_store.read(AUTH_PATH)
+        data[PROVIDER] = record
+        subscription_store.write(AUTH_PATH, data)
+
+
+def logout() -> None:
+    with subscription_store.guard(AUTH_PATH):
+        data = subscription_store.read(AUTH_PATH)
+        if PROVIDER not in data:
+            return
+        del data[PROVIDER]
+        if data:
+            subscription_store.write(AUTH_PATH, data)
+            return
+        with contextlib.suppress(OSError):
+            AUTH_PATH.unlink()
+
+
+@contextlib.contextmanager
+def _refresh_guard() -> Iterator[None]:
+    """Serialize token refresh within (lock) and across (flock) Strix processes,
+    so concurrent runs can't both spend the single-use refresh token."""
+    with subscription_store.guard(AUTH_PATH):
+        yield
+
+
+class GrokAuthError(Exception):
+    def __init__(self, code: str, message: str | None = None) -> None:
+        self.code = code
+        super().__init__(message or code)
+
+
+def _b64url(raw: bytes) -> str:
+    return base64.urlsafe_b64encode(raw).rstrip(b"=").decode("ascii")
+
+
+def generate_pkce() -> tuple[str, str]:
+    verifier = _b64url(secrets.token_bytes(64))
+    challenge = _b64url(hashlib.sha256(verifier.encode("ascii")).digest())
+    return verifier, challenge
+
+
+def create_state() -> str:
+    return secrets.token_hex(16)
+
+
+def build_authorize_url(challenge: str, state: str) -> str:
+    params = {
+        "response_type": "code",
+        "client_id": CLIENT_ID,
+        "redirect_uri": REDIRECT_URI,
+        "scope": SCOPE,
+        "code_challenge": challenge,
+        "code_challenge_method": "S256",
+        "state": state,
+    }
+    return f"{AUTHORIZE_URL}?{urllib.parse.urlencode(params)}"
+
+
+def parse_redirect_input(value: str) -> tuple[str | None, str | None]:
+    """Extract ``(code, state)`` from a pasted redirect URL, ``code#state``,
+    query string, or bare code."""
+    value = (value or "").strip()
+    if not value:
+        return None, None
+    with contextlib.suppress(ValueError):
+        parsed = urllib.parse.urlparse(value)
+        if parsed.scheme and parsed.query:
+            query = urllib.parse.parse_qs(parsed.query)
+            return _first(query, "code"), _first(query, "state")
+    if "#" in value:
+        code, _, state = value.partition("#")
+        return code or None, state or None
+    if "code=" in value:
+        query = urllib.parse.parse_qs(value)
+        return _first(query, "code"), _first(query, "state")
+    return value, None
+
+
+def _first(query: dict[str, list[str]], key: str) -> str | None:
+    values = query.get(key)
+    return values[0] if values else None
+
+
+def _post_form(payload: dict[str, str]) -> dict[str, Any]:
+    try:
+        response = requests.post(
+            TOKEN_URL,
+            data=payload,
+            headers={"Accept": "application/json"},
+            timeout=_TOKEN_TIMEOUT,
+        )
+    except requests.RequestException as exc:
+        raise GrokAuthError("unavailable", str(exc)) from exc
+    if response.status_code >= 400:
+        detail = response.text[:300]
+        raise GrokAuthError("token_http_error", f"HTTP {response.status_code}: {detail}")
+    data = json.loads(response.content or b"{}")
+    if not isinstance(data, dict):
+        raise GrokAuthError("bad_response", "token endpoint returned non-object")
+    return data
+
+
+def _record_from_token_response(
+    data: dict[str, Any], refresh_fallback: str | None = None
+) -> dict[str, Any]:
+    access = data.get("access_token")
+    # A refresh response may omit refresh_token when it isn't rotated; keep the old one.
+    refresh = data.get("refresh_token") or refresh_fallback
+    expires_in = data.get("expires_in")
+    if not isinstance(access, str) or not access:
+        raise GrokAuthError("bad_response", "token response missing access_token")
+    if not isinstance(refresh, str) or not refresh:
+        raise GrokAuthError("bad_response", "token response missing refresh_token")
+    ttl = expires_in if isinstance(expires_in, int | float) else 3600
+    return {
+        "type": "oauth",
+        "provider": PROVIDER,
+        "access": access,
+        "refresh": refresh,
+        "expires_at": time.time() + ttl,
+    }
+
+
+def exchange_code(code: str, verifier: str) -> dict[str, Any]:
+    data = _post_form(
+        {
+            "grant_type": "authorization_code",
+            "client_id": CLIENT_ID,
+            "code": code,
+            "code_verifier": verifier,
+            "redirect_uri": REDIRECT_URI,
+        }
+    )
+    return _record_from_token_response(data)
+
+
+def refresh_tokens(refresh_token: str) -> dict[str, Any]:
+    data = _post_form(
+        {
+            "grant_type": "refresh_token",
+            "client_id": CLIENT_ID,
+            "refresh_token": refresh_token,
+        }
+    )
+    return _record_from_token_response(data, refresh_fallback=refresh_token)
+
+
+def _access_token(record: dict[str, Any]) -> str:
+    access = record["access"]
+    if not isinstance(access, str) or not access:
+        raise GrokAuthError("bad_response", "stored access token is missing or malformed")
+    return access
+
+
+def _near_expiry(record: dict[str, Any]) -> bool:
+    expires_at = record.get("expires_at")
+    if not isinstance(expires_at, int | float):
+        return True
+    return expires_at - _EXPIRY_SKEW_S <= time.time()
+
+
+def get_valid_token() -> str:
+    """Return a valid access token, refreshing under the cross-process guard if
+    near expiry."""
+    record = read_record()
+    if record is None:
+        raise GrokAuthError("not_authenticated", "not signed in; run: strix auth login grok")
+    if not _near_expiry(record):
+        return _access_token(record)
+    with _refresh_guard():
+        record = read_record()
+        if record is None:
+            raise GrokAuthError("not_authenticated", "not signed in; run: strix auth login grok")
+        if not _near_expiry(record):
+            return _access_token(record)
+        try:
+            refreshed = refresh_tokens(record["refresh"])
+        except GrokAuthError:
+            # A peer process may have already spent this single-use refresh token.
+            latest = read_record()
+            if latest and latest["refresh"] != record["refresh"] and not _near_expiry(latest):
+                return _access_token(latest)
+            raise
+        save_record(refreshed)
+        return _access_token(refreshed)
+
+
+def build_openai_client() -> AsyncOpenAI:
+    """An ``AsyncOpenAI`` for xAI's API. A per-request hook re-stamps a fresh
+    bearer token so long scans survive token expiry."""
+    import asyncio
+
+    import httpx
+    from openai import AsyncOpenAI
+
+    get_valid_token()  # fail fast at configure time if the sign-in is dead
+
+    async def _auth_hook(request: httpx.Request) -> None:
+        access = await asyncio.to_thread(get_valid_token)
+        request.headers["Authorization"] = f"Bearer {access}"
+
+    http_client = httpx.AsyncClient(
+        timeout=httpx.Timeout(600.0, connect=30.0),
+        event_hooks={"request": [_auth_hook]},
+    )
+    return AsyncOpenAI(
+        api_key="strix-grok-oauth",  # placeholder; the hook overwrites Authorization
+        base_url=XAI_BASE_URL,
+        http_client=http_client,
+    )
+
+
+_subscription_client: AsyncOpenAI | None = None
+
+
+def get_subscription_client() -> AsyncOpenAI:
+    global _subscription_client  # noqa: PLW0603
+    if _subscription_client is None:
+        _subscription_client = build_openai_client()
+    return _subscription_client
+
+
+SUBSCRIPTION_PREFIX = "grok/"
+
+
+def subscription_model(model_name: str | None) -> str | None:
+    """The model slug behind a ``grok/<model>`` STRIX_LLM, or None."""
+    name = (model_name or "").strip()
+    if not name.lower().startswith(SUBSCRIPTION_PREFIX):
+        return None
+    return name[len(SUBSCRIPTION_PREFIX) :] or None
+
+
+def auth_mode(model_name: str | None) -> str:
+    return "subscription" if subscription_model(model_name) else "api_key"

strix/config/models.py

@@ -37,7 +37,7 @@ from openai.types.responses import (
 from openai.types.responses.response_usage import ResponseUsage
 from openai.types.shared import Reasoning
 
-from strix.config import codex, opencode
+from strix.config import codex, grok
 from strix.config.loader import load_settings
 from strix.config.tool_call_ids import TurnCallIdRewriter, dedupe_input
 from strix.config.tool_call_limits import TurnToolCallLimiter
@@ -80,12 +80,7 @@ def _retry_statusless_provider_errors(context: RetryPolicyContext) -> bool:
 
 
 class _CodexResponsesModel(OpenAIResponsesModel):
-    """Responses model for stateless subscription gateways (always streamed).
-
-    Used for the ChatGPT subscription backend and for Responses-served models on
-    the OpenCode gateway: neither stores responses server-side, so reasoning is
-    carried inline via ``reasoning.encrypted_content``.
-    """
+    """Responses model for the ChatGPT subscription backend (always streamed, stateless)."""
 
     def __init__(
         self,
@@ -477,7 +472,6 @@ class StrixProvider(MultiProvider):
     def get_model(self, model_name: str | None) -> Model:
         llm = load_settings().llm
         slug = codex.subscription_model(model_name)
-        oc = opencode.subscription_model(model_name)
         idle_timeout = float(llm.stream_idle_timeout)
         if slug:
             # The ChatGPT subscription backend is always streamed; it has no
@@ -488,19 +482,10 @@ class StrixProvider(MultiProvider):
                 codex.get_subscription_client(),
                 reasoning_effort=llm.reasoning_effort,
             )
-        elif oc and oc.uses_responses:
-            model = _CodexResponsesModel(
-                oc.slug,
-                opencode.get_subscription_client(oc.base_url),
-                reasoning_effort=llm.reasoning_effort,
-            )
-        elif oc:
-            model = OpenAIChatCompletionsModel(
-                oc.slug, opencode.get_subscription_client(oc.base_url)
-            )
-            if llm.disable_streaming:
-                model = _NonStreamingModel(model)
-                idle_timeout = 0.0
+        elif grok_slug := grok.subscription_model(model_name):
+            # xAI's API is OpenAI chat-completions compatible; the subscription
+            # bearer is stamped per-request by the client's auth hook.
+            model = OpenAIChatCompletionsModel(grok_slug, grok.get_subscription_client())
         else:
             model = super().get_model(model_name)
             if llm.disable_streaming:
@@ -560,24 +545,15 @@ RECOMMENDED_MODEL_NAMES = (
 _RECOMMENDED_MODEL_NAME_SET = frozenset(name.lower() for name in RECOMMENDED_MODEL_NAMES)
 
 FRONTIER_MODEL_FAMILIES = (
-    (("azure", "azure_ai", "bedrock_mantle", "chatgpt", "openai", "opencode"), ("gpt-5",)),
+    (("azure", "azure_ai", "bedrock_mantle", "chatgpt", "openai"), ("gpt-5",)),
     (
-        (
-            "anthropic",
-            "azure_ai",
-            "bedrock",
-            "claude",
-            "databricks",
-            "opencode",
-            "snowflake",
-            "vertex_ai",
-        ),
+        ("anthropic", "azure_ai", "bedrock", "claude", "databricks", "snowflake", "vertex_ai"),
         ("claude-fable-5", "claude-opus-5", "claude-opus-4", "claude-sonnet-5", "claude-sonnet-4"),
     ),
-    (("google", "gemini", "opencode", "vertex_ai"), ("gemini-3",)),
-    (("deepseek", "opencode"), ("deepseek-v4", "deepseek-r1", "deepseek-reasoner")),
-    (("alibaba", "dashscope", "opencode", "qwen"), ("qwen3.8", "qwen3.7", "qwen3-max")),
-    (("kimi", "moonshot", "moonshotai", "opencode"), ("kimi-k3", "kimi-k2.7", "kimi-k2.6")),
+    (("google", "gemini", "vertex_ai"), ("gemini-3",)),
+    (("deepseek",), ("deepseek-v4", "deepseek-r1", "deepseek-reasoner")),
+    (("alibaba", "dashscope", "qwen"), ("qwen3.8", "qwen3.7", "qwen3-max")),
+    (("moonshot", "moonshotai", "kimi"), ("kimi-k3", "kimi-k2.7", "kimi-k2.6")),
 )
 
 
@@ -585,7 +561,7 @@ def configure_sdk_model_defaults(settings: Settings) -> None:
     """Apply Strix config to SDK-native defaults."""
     llm = settings.llm
     set_tracing_disabled(True)
-    if codex.subscription_model(llm.model) or opencode.subscription_model(llm.model):
+    if codex.subscription_model(llm.model) or grok.subscription_model(llm.model):
         return
     _configure_litellm_compatibility()
     _configure_openrouter_attribution(llm.model)
@@ -681,31 +657,27 @@ def _install_openrouter_stream_cost_capture() -> None:
     litellm.OpenrouterConfig = _StrixOpenrouterConfig  # type: ignore[misc]
 
 
-OPENROUTER_ATTRIBUTION_HEADERS = {
+_OPENROUTER_ATTRIBUTION_HEADERS = {
     "HTTP-Referer": "https://strix.ai",
     "X-Title": "Strix",
     "X-OpenRouter-Categories": "cli-agent",
 }
 
 
-def is_openrouter_model(model_name: str | None) -> bool:
-    return bool(model_name) and "openrouter/" in (model_name or "").strip().lower()
-
-
 def _configure_openrouter_attribution(model_name: str | None) -> None:
     import litellm
 
     current: object = litellm.headers
     existing: dict[str, str] = current if isinstance(current, dict) else {}
-    if not is_openrouter_model(model_name):
-        if any(key in existing for key in OPENROUTER_ATTRIBUTION_HEADERS):
+    if not model_name or "openrouter/" not in model_name.strip().lower():
+        if any(key in existing for key in _OPENROUTER_ATTRIBUTION_HEADERS):
             remaining = {
-                k: v for k, v in existing.items() if k not in OPENROUTER_ATTRIBUTION_HEADERS
+                k: v for k, v in existing.items() if k not in _OPENROUTER_ATTRIBUTION_HEADERS
             }
             litellm.headers = remaining or None  # type: ignore[assignment]
         return
 
-    litellm.headers = {**existing, **OPENROUTER_ATTRIBUTION_HEADERS}  # type: ignore[assignment]
+    litellm.headers = {**existing, **_OPENROUTER_ATTRIBUTION_HEADERS}  # type: ignore[assignment]
 
 
 def _configure_extra_headers(llm: LlmSettings) -> None:
@@ -770,9 +742,6 @@ def uses_chat_completions_tool_schema(model_name: str, settings: Settings) -> bo
     """Return whether the resolved SDK route can only receive JSON function tools."""
     if codex.subscription_model(model_name):
         return False
-    oc = opencode.subscription_model(model_name)
-    if oc:
-        return not oc.uses_responses
     model = model_name.strip().lower()
     if "/" in model and not model.startswith("openai/"):
         return True

strix/config/opencode.py

@@ -1,158 +0,0 @@
-"""OpenCode subscription auth: API-key sign-in and the OpenAI clients that
-route inference through the OpenCode gateway.
-
-Covers both OpenCode offerings — Zen (pay-as-you-go credits) and Go (the
-monthly subscription) — which share one account and API key but live behind
-different gateway base URLs. Unlike the ChatGPT subscription there is no
-OAuth: the user copies a plain API key from https://opencode.ai/auth, and
-using the gateway from other agents is officially supported.
-
-Model routing follows the endpoint each model is served on (see
-https://opencode.ai/docs/zen/): GPT models use the Responses API, everything
-else the OpenAI-compatible Chat Completions API.
-"""
-
-from __future__ import annotations
-
-from dataclasses import dataclass
-from typing import Any
-
-import httpx
-import requests
-from openai import AsyncOpenAI
-
-from strix.config import codex
-
-
-PROVIDER = "opencode"
-
-ZEN_BASE_URL = "https://opencode.ai/zen/v1"
-GO_BASE_URL = "https://opencode.ai/zen/go/v1"
-
-# ``opencode/<model>`` runs on Zen credits; ``opencode-go/<model>`` on the Go
-# subscription (matching OpenCode's own ``opencode-go/`` model ids).
-ZEN_PREFIX = "opencode/"
-GO_PREFIX = "opencode-go/"
-
-AUTH_CONSOLE_URL = "https://opencode.ai/auth"
-
-_KEY_CHECK_TIMEOUT = 30
-
-
-class OpencodeAuthError(Exception):
-    def __init__(self, code: str, message: str | None = None) -> None:
-        self.code = code
-        super().__init__(message or code)
-
-
-@dataclass(frozen=True)
-class SubscriptionModel:
-    slug: str
-    base_url: str
-    uses_responses: bool
-
-
-def _uses_responses(slug: str, base_url: str) -> bool:
-    lowered = slug.lower()
-    if lowered.startswith("gpt-"):
-        return True
-    # Grok is served via Responses on Zen but Chat Completions on Go.
-    return lowered.startswith("grok") and base_url == ZEN_BASE_URL
-
-
-def subscription_model(model_name: str | None) -> SubscriptionModel | None:
-    """The gateway model behind an ``opencode/`` or ``opencode-go/`` STRIX_LLM."""
-    name = (model_name or "").strip()
-    lowered = name.lower()
-    for prefix, base_url in ((GO_PREFIX, GO_BASE_URL), (ZEN_PREFIX, ZEN_BASE_URL)):
-        if lowered.startswith(prefix):
-            slug = name[len(prefix) :]
-            if not slug:
-                return None
-            return SubscriptionModel(slug, base_url, _uses_responses(slug, base_url))
-    return None
-
-
-def read_record() -> dict[str, Any] | None:
-    record = codex.read_provider_record(PROVIDER)
-    if not isinstance(record, dict) or record.get("type") != "api_key":
-        return None
-    key = record.get("key")
-    if not isinstance(key, str) or not key:
-        return None
-    return record
-
-
-def is_authenticated() -> bool:
-    return read_record() is not None
-
-
-def save_api_key(key: str) -> None:
-    codex.save_provider_record(PROVIDER, {"type": "api_key", "provider": PROVIDER, "key": key})
-
-
-def logout() -> None:
-    codex.remove_provider_record(PROVIDER)
-
-
-def get_api_key() -> str:
-    record = read_record()
-    if record is None:
-        raise OpencodeAuthError(
-            "not_authenticated", "not signed in; run: strix auth login opencode"
-        )
-    return str(record["key"])
-
-
-def validate_api_key(key: str) -> None:
-    """Check the key against the gateway's models endpoint; raise if rejected."""
-    try:
-        response = requests.get(
-            f"{ZEN_BASE_URL}/models",
-            headers={"Authorization": f"Bearer {key}"},
-            timeout=_KEY_CHECK_TIMEOUT,
-        )
-    except requests.RequestException as exc:
-        raise OpencodeAuthError("unavailable", str(exc)) from exc
-    if response.status_code in (401, 403):
-        raise OpencodeAuthError(
-            "invalid_key", f"OpenCode rejected the API key (HTTP {response.status_code})"
-        )
-    if response.status_code >= 400:
-        raise OpencodeAuthError("http_error", f"HTTP {response.status_code}: {response.text[:300]}")
-
-
-def build_openai_client(base_url: str) -> AsyncOpenAI:
-    return AsyncOpenAI(
-        api_key=get_api_key(),
-        base_url=base_url,
-        http_client=httpx.AsyncClient(timeout=httpx.Timeout(600.0, connect=30.0)),
-    )
-
-
-_subscription_clients: dict[str, AsyncOpenAI] = {}
-
-
-def get_subscription_client(base_url: str) -> AsyncOpenAI:
-    client = _subscription_clients.get(base_url)
-    if client is None:
-        client = build_openai_client(base_url)
-        _subscription_clients[base_url] = client
-    return client
-
-
-def auth_mode(model_name: str | None) -> str:
-    """Return "subscription" when STRIX_LLM runs on any subscription
-    (OpenCode or ChatGPT), else "api_key"."""
-    if subscription_model(model_name) or codex.subscription_model(model_name):
-        return "subscription"
-    return "api_key"
-
-
-def subscription_provider(model_name: str | None) -> str | None:
-    """The subscription behind STRIX_LLM: "opencode", "chatgpt", or None."""
-    if subscription_model(model_name):
-        return PROVIDER
-    if codex.subscription_model(model_name):
-        return "chatgpt"
-    return None

strix/config/subscription.py

@@ -0,0 +1,45 @@
+"""Shared helpers across model-subscription providers (ChatGPT/Codex and Grok).
+
+Each provider module (:mod:`strix.config.codex`, :mod:`strix.config.grok`)
+exposes the same small surface — ``subscription_model``, ``auth_mode``,
+``is_authenticated`` — so callers that only care "is this run on a subscription,
+and which provider?" can stay provider-agnostic.
+"""
+
+from __future__ import annotations
+
+from typing import TYPE_CHECKING
+
+from strix.config import codex, grok
+
+
+if TYPE_CHECKING:
+    from types import ModuleType
+
+
+_PROVIDERS: tuple[ModuleType, ...] = (codex, grok)
+
+# Human-facing provider names keyed by each module's ``PROVIDER`` constant.
+_DISPLAY_NAMES: dict[str, str] = {codex.PROVIDER: "ChatGPT", grok.PROVIDER: "Grok"}
+
+
+def provider_for_model(model_name: str | None) -> ModuleType | None:
+    """Return the subscription provider module that owns ``model_name``'s prefix,
+    or None when the model isn't a subscription model."""
+    for provider in _PROVIDERS:
+        if provider.subscription_model(model_name):
+            return provider
+    return None
+
+
+def auth_mode(model_name: str | None) -> str:
+    return "subscription" if provider_for_model(model_name) is not None else "api_key"
+
+
+def provider_label(model_name: str | None) -> str | None:
+    """Human-facing name of the subscription provider for ``model_name`` (e.g.
+    "ChatGPT" or "Grok"), or None when the model isn't a subscription model."""
+    provider = provider_for_model(model_name)
+    if provider is None:
+        return None
+    return _DISPLAY_NAMES.get(provider.PROVIDER)

strix/config/subscription_store.py

@@ -0,0 +1,152 @@
+"""Shared on-disk store for subscription OAuth credentials.
+
+Every subscription provider (ChatGPT/Codex, Grok) keeps its record under its own
+key in a single ``~/.strix/subscription-auth.json`` file. Reads and writes go
+through here so that:
+
+* tokens are written owner-only (mode 0600) from the moment the file is created,
+  never briefly exposed with umask-derived permissions, and
+* concurrent read-modify-write mutations — even across different providers or
+  processes — are serialized, so one provider's update can't clobber another's.
+
+The lock is reentrant, so a provider may nest a ``save`` inside a longer
+``guard`` (e.g. refreshing a token then persisting it) without deadlocking.
+"""
+
+from __future__ import annotations
+
+import contextlib
+import json
+import os
+import tempfile
+import threading
+from pathlib import Path
+from typing import TYPE_CHECKING, Any
+
+
+if TYPE_CHECKING:
+    from collections.abc import Iterator
+    from io import TextIOWrapper
+
+
+class StoreLockError(RuntimeError):
+    """The cross-process store lock could not be acquired.
+
+    Raised instead of silently proceeding, so a read-modify-write never runs
+    unlocked (which would let concurrent provider logins/refreshes/logouts race).
+    """
+
+
+def read(path: Path) -> dict[str, Any]:
+    """The store's contents, or an empty dict when absent/unreadable."""
+    try:
+        data = json.loads(path.read_text(encoding="utf-8"))
+    except (OSError, json.JSONDecodeError):
+        return {}
+    return data if isinstance(data, dict) else {}
+
+
+def write(path: Path, data: dict[str, Any]) -> None:
+    """Atomically replace the store, owner-only from creation.
+
+    The temp file is created with a random name via ``mkstemp`` (mode 0600, no
+    symlink following), so a local attacker can't pre-plant a symlink at a
+    predictable path to divert the token write.
+    """
+    path.parent.mkdir(parents=True, exist_ok=True)
+    fd, tmp_name = tempfile.mkstemp(dir=path.parent, prefix=path.name, suffix=".tmp")
+    tmp = Path(tmp_name)
+    try:
+        with os.fdopen(fd, "w", encoding="utf-8") as handle:
+            json.dump(data, handle, indent=2)
+        tmp.replace(path)
+    except BaseException:
+        with contextlib.suppress(OSError):
+            tmp.unlink()
+        raise
+    with contextlib.suppress(OSError):
+        path.chmod(0o600)
+
+
+class _StoreLock:
+    """A reentrant lock serializing store mutations within (thread lock) and
+    across (flock) Strix processes. Nesting reuses the single held file lock, so
+    a provider can persist a record inside a longer critical section."""
+
+    def __init__(self) -> None:
+        self._thread_lock = threading.RLock()
+        self._flock_handle: TextIOWrapper | None = None
+        self._depth = 0
+
+    @contextlib.contextmanager
+    def hold(self, path: Path) -> Iterator[None]:
+        with self._thread_lock:
+            if self._depth == 0:
+                self._flock_handle = _acquire_flock(path)
+            self._depth += 1
+            try:
+                yield
+            finally:
+                self._depth -= 1
+                if self._depth == 0:
+                    self._release_flock()
+
+    def _release_flock(self) -> None:
+        handle = self._flock_handle
+        self._flock_handle = None
+        if handle is None:
+            return
+        try:
+            import fcntl
+
+            with contextlib.suppress(OSError):
+                fcntl.flock(handle.fileno(), fcntl.LOCK_UN)
+        except ImportError:
+            pass
+        finally:
+            handle.close()
+
+
+_store_lock = _StoreLock()
+
+
+def guard(path: Path) -> contextlib.AbstractContextManager[None]:
+    """Serialize store mutation across threads and processes (reentrant)."""
+    return _store_lock.hold(path)
+
+
+def _acquire_flock(path: Path) -> TextIOWrapper:
+    """Hold an exclusive cross-process lock on the store, or raise.
+
+    Never returns without the lock held: a missing ``fcntl`` or a failed
+    ``flock`` raises :class:`StoreLockError` so the caller aborts rather than
+    mutating the store unlocked.
+    """
+    try:
+        import fcntl
+    except ImportError as exc:  # pragma: no cover - non-POSIX
+        msg = "cross-process credential locking requires fcntl (a POSIX platform)"
+        raise StoreLockError(msg) from exc
+    lock_path = path.with_suffix(".lock")
+    lock_path.parent.mkdir(parents=True, exist_ok=True)
+    # O_NOFOLLOW rejects a pre-positioned symlink at the predictable lock path
+    # (so an attacker can't redirect the open), and no O_TRUNC since the lock
+    # file is only an flock anchor whose contents we never use.
+    try:
+        fd = os.open(str(lock_path), os.O_RDWR | os.O_CREAT | os.O_NOFOLLOW, 0o600)
+    except OSError as exc:
+        msg = f"could not open lock file {lock_path}: {exc}"
+        raise StoreLockError(msg) from exc
+    handle = os.fdopen(fd, "r+")
+    try:
+        while True:
+            try:
+                fcntl.flock(handle.fileno(), fcntl.LOCK_EX)
+                break
+            except InterruptedError:  # EINTR — retry the blocking acquire
+                continue
+    except OSError as exc:
+        handle.close()
+        msg = f"could not lock {lock_path}: {exc}"
+        raise StoreLockError(msg) from exc
+    return handle

strix/core/execution.py

@@ -830,7 +830,7 @@ async def _append_tool_required_message(
             "execution and never hands control to the user: it is shown to the user, and the "
             "run continues. Continue immediately and call exactly one tool. "
             "If you have something to tell the user and nothing to do until they reply, "
-            "call respond_to_user — with no message if you have already said it. "
+            "call respond_to_user. "
             "If you are blocked waiting for another agent, call wait_for_agents. "
             f"If the whole engagement is complete, call {finish_tool}. "
             "Otherwise use the appropriate execution or planning tool. "

strix/core/inputs.py

@@ -8,15 +8,12 @@ from typing import TYPE_CHECKING, Any
 from agents.model_settings import ModelSettings
 from openai.types.shared import Reasoning
 
-from strix.config import opencode
 from strix.config.models import (
     DEFAULT_MODEL_RETRY,
-    OPENROUTER_ATTRIBUTION_HEADERS,
     bedrock_route_supports_prompt_caching,
     is_bedrock_route,
     is_claude_model,
     is_known_openai_bare_model,
-    is_openrouter_model,
     model_supports_reasoning,
     request_timeout_extra_args,
 )
@@ -141,15 +138,6 @@ def build_root_task(scan_config: dict[str, Any]) -> str:
             "target to assess: the instructions below are the only source of "
             "truth for what to do."
         )
-    elif not parts and user_instructions:
-        # Neither a target nor a directory, but there is an instruction: the user
-        # declined the mount, so the instruction is all there is. Say so, or the
-        # agent goes looking for a scope that was never given.
-        parts.append(
-            "\n\nNo scan target and no working directory were provided. The "
-            "instructions below are the only source of truth for what to do; "
-            "work from them and from what you can reach yourself."
-        )
 
     parts.extend(_render_diff_scope(diff_scope))
 
@@ -204,15 +192,13 @@ def make_model_settings(
     request_timeout: float | None = None,
     prompt_cache: bool = True,
     extra_headers: dict[str, str] | None = None,
-    has_tools: bool = True,
 ) -> ModelSettings:
-    headers = _request_headers(model_name, extra_headers)
     model_settings = ModelSettings(
-        parallel_tool_calls=False if has_tools else None,
+        parallel_tool_calls=False,
         retry=DEFAULT_MODEL_RETRY,
         include_usage=True,
         extra_args=request_timeout_extra_args(request_timeout),
-        extra_headers=headers,
+        extra_headers=dict(extra_headers) if extra_headers else None,
     )
     if (
         reasoning_effort is not None
@@ -235,17 +221,6 @@ def make_model_settings(
     return model_settings
 
 
-def _request_headers(
-    model_name: str, extra_headers: dict[str, str] | None
-) -> dict[str, str] | None:
-    headers: dict[str, str] = {}
-    if is_openrouter_model(model_name):
-        headers.update(OPENROUTER_ATTRIBUTION_HEADERS)
-    if extra_headers:
-        headers.update(extra_headers)
-    return headers or None
-
-
 def _reasoning_settings(
     effort: ReasoningEffort,
     extra_args: dict[str, Any] | None,
@@ -273,10 +248,6 @@ def _prompt_cache_extra_args(model_name: str) -> dict[str, Any] | None:
     """
     if not is_claude_model(model_name):
         return None
-    # OpenCode routes use the raw OpenAI SDK, which rejects this LiteLLM-only
-    # argument; the gateway applies Anthropic prompt caching itself.
-    if opencode.subscription_model(model_name):
-        return None
     if is_bedrock_route(model_name) and not bedrock_route_supports_prompt_caching(model_name):
         return None
 

strix/core/runner.py

@@ -2,7 +2,6 @@
 
 from __future__ import annotations
 
-import asyncio
 import contextlib
 import io
 import json
@@ -430,6 +429,7 @@ async def run_strix_scan(
     except BudgetExceededError as exc:
         logger.info("Scan %s stopped: %s", scan_id, exc)
         if root_id is not None:
+            await coordinator.cancel_descendants(root_id)
             with contextlib.suppress(Exception):
                 await coordinator.set_status(root_id, "stopped")
         return None
@@ -442,28 +442,19 @@ async def run_strix_scan(
             scan_id,
         )
         if root_id is not None:
+            await coordinator.cancel_descendants(root_id)
             with contextlib.suppress(Exception):
                 await coordinator.set_status(root_id, "stopped")
         return None
-    except (asyncio.CancelledError, KeyboardInterrupt):
-        logger.info("Scan %s interrupted by the user", scan_id)
-        if root_id is not None:
-            with contextlib.suppress(Exception):
-                await coordinator.set_status(root_id, "running")
-        raise
     except BaseException:
         logger.exception("Strix scan %s failed", scan_id)
         if root_id is not None:
+            await coordinator.cancel_descendants(root_id)
             with contextlib.suppress(Exception):
                 await coordinator.set_status(root_id, "failed")
         raise
     finally:
         configure_spill_writer(None)
-        # Settle descendants before closing sessions: on a clean finish a child
-        # can still be mid-turn, and closing its session underneath it crashes it.
-        if root_id is not None:
-            with contextlib.suppress(Exception):
-                await coordinator.cancel_descendants(root_id)
         for s in sessions_to_close:
             with contextlib.suppress(Exception):
                 s.close()

strix/core/sessions.py

@@ -4,8 +4,6 @@ from __future__ import annotations
 
 import asyncio
 import logging
-import sqlite3
-from contextlib import contextmanager
 from typing import TYPE_CHECKING, Any, cast
 from weakref import WeakKeyDictionary
 
@@ -14,7 +12,7 @@ from agents.memory import SQLiteSession
 
 
 if TYPE_CHECKING:
-    from collections.abc import Callable, Iterator
+    from collections.abc import Callable
     from pathlib import Path
 
     from agents.items import TResponseInputItem
@@ -24,25 +22,9 @@ if TYPE_CHECKING:
 logger = logging.getLogger(__name__)
 
 
-class _PooledConnectionSession(SQLiteSession):
-    @contextmanager
-    def _locked_connection(self) -> Iterator[sqlite3.Connection]:
-        with self._lock:
-            if self._closed:
-                raise RuntimeError("SQLiteSession is closed")
-            if self._is_memory_db:
-                yield self._shared_connection
-                return
-            connection = sqlite3.connect(str(self.db_path), check_same_thread=False)
-            try:
-                yield connection
-            finally:
-                connection.close()
-
-
 def open_agent_session(agent_id: str, path: Path) -> SQLiteSession:
     path.parent.mkdir(parents=True, exist_ok=True)
-    return _PooledConnectionSession(session_id=agent_id, db_path=path)
+    return SQLiteSession(session_id=agent_id, db_path=path)
 
 
 async def seed_initial_input(session: Session, initial_input: Any) -> bool:

strix/interface/auth_cli.py

@@ -1,9 +1,8 @@
-"""`strix auth` — subscription sign-in (login / status / logout).
+"""`strix auth` — model-subscription sign-in (login / status / logout).
 
-Signing in only stores credentials (``~/.strix/subscription-auth.json``); model
-selection stays with ``STRIX_LLM``. A ``chatgpt/<model>`` STRIX_LLM runs on the
-ChatGPT subscription; ``opencode/<model>`` (Zen credits) or
-``opencode-go/<model>`` (Go subscription) run on OpenCode.
+Signing in only stores OAuth tokens (``~/.strix/subscription-auth.json``); model
+selection stays with ``STRIX_LLM``. A ``chatgpt/<model>`` STRIX_LLM runs on a
+ChatGPT subscription and a ``grok/<model>`` one on a Grok/SuperGrok subscription.
 """
 
 from __future__ import annotations
@@ -13,6 +12,7 @@ import base64
 import logging
 import threading
 import webbrowser
+from dataclasses import dataclass
 from http.server import BaseHTTPRequestHandler, HTTPServer
 from pathlib import Path
 from typing import TYPE_CHECKING, Any
@@ -22,33 +22,78 @@ from rich.console import Console
 from rich.panel import Panel
 from rich.text import Text
 
-from strix.config import codex, load_settings, opencode
+from strix.config import codex, grok, load_settings, subscription_store
 
 
 if TYPE_CHECKING:
     from collections.abc import Callable
+    from types import ModuleType
 
 
 logger = logging.getLogger(__name__)
 
 _CALLBACK_TIMEOUT_S = 300
 
-# CLI-facing name for the default login provider. Internally this is the Codex
-# OAuth flow (``codex.PROVIDER``), but users know it as ChatGPT, so that's what
-# the command and messaging say. ``codex`` is accepted as an alias.
-LOGIN_PROVIDER = "chatgpt"
-_ACCEPTED_PROVIDERS = frozenset({LOGIN_PROVIDER, codex.PROVIDER})
-_OPENCODE_PROVIDERS = frozenset({opencode.PROVIDER, "opencode-go", "zen"})
+
+@dataclass(frozen=True)
+class _Provider:
+    """A model-subscription provider the ``strix auth`` command can sign into.
+
+    ``module`` is the provider's OAuth module (:mod:`strix.config.codex` or
+    :mod:`strix.config.grok`); both expose the same login surface. ``error`` is
+    that module's auth-error class, caught to report a clean failure.
+    """
+
+    name: str
+    module: ModuleType
+    error: type[Exception]
+    display: str
+    example_model: str
+    blurb: str
+
+
+_PROVIDERS: dict[str, _Provider] = {
+    "chatgpt": _Provider(
+        name="chatgpt",
+        module=codex,
+        error=codex.CodexAuthError,
+        display="ChatGPT",
+        example_model="chatgpt/gpt-5.4",
+        blurb="This uses your ChatGPT Plus/Pro plan for inference instead of a metered API key.",
+    ),
+    "grok": _Provider(
+        name="grok",
+        module=grok,
+        error=grok.GrokAuthError,
+        display="Grok",
+        example_model="grok/grok-4",
+        blurb="This uses your Grok/SuperGrok plan for inference instead of a metered API key.",
+    ),
+}
+
+# Internal OAuth provider ids and common vendor names accepted as aliases.
+_PROVIDER_ALIASES: dict[str, str] = {
+    codex.PROVIDER: "chatgpt",
+    grok.PROVIDER: "grok",
+    "xai": "grok",
+    "supergrok": "grok",
+}
+
+_DEFAULT_PROVIDER = "chatgpt"
 
 _USAGE = (
     "Usage:\n"
-    "  strix auth login chatgpt [--manual]\n"
-    "  strix auth login opencode\n"
+    "  strix auth login [chatgpt|grok] [--manual]\n"
     "  strix auth status\n"
-    "  strix auth logout [chatgpt|opencode]"
+    "  strix auth logout [chatgpt|grok]"
 )
 
 
+def _resolve_provider(name: str) -> _Provider | None:
+    key = _PROVIDER_ALIASES.get(name.lower(), name.lower())
+    return _PROVIDERS.get(key)
+
+
 def run_auth(argv: list[str]) -> int:
     """Entry point for ``strix auth …``. Returns a process exit code."""
     console = Console()
@@ -57,7 +102,7 @@ def run_auth(argv: list[str]) -> int:
     rest = argv[1:]
 
     if subcommand in ("-h", "--help", "help"):
-        console.print(_USAGE)
+        console.print(_USAGE, markup=False)
         return 0
 
     handlers: dict[str, Callable[[], int]] = {
@@ -70,7 +115,7 @@ def run_auth(argv: list[str]) -> int:
         return handler()
 
     console.print(f"[red]Unknown auth command:[/] {subcommand}\n")
-    console.print(_USAGE)
+    console.print(_USAGE, markup=False)
     return 2
 
 
@@ -79,8 +124,8 @@ def _login(console: Console, argv: list[str]) -> int:
     parser.add_argument(
         "provider",
         nargs="?",
-        default=LOGIN_PROVIDER,
-        help="Model provider to sign in with (default: chatgpt).",
+        default=_DEFAULT_PROVIDER,
+        help="Model provider to sign in with (chatgpt or grok; default: chatgpt).",
     )
     parser.add_argument(
         "--manual",
@@ -92,100 +137,42 @@ def _login(console: Console, argv: list[str]) -> int:
     except SystemExit as exc:  # argparse already printed the message
         return int(exc.code or 2)
 
-    if args.provider.lower() in _OPENCODE_PROVIDERS:
-        return _login_opencode(console)
-
-    if args.provider.lower() not in _ACCEPTED_PROVIDERS:
-        console.print(
-            f"[red]Unsupported provider:[/] {args.provider}. "
-            f"Supported: '{LOGIN_PROVIDER}' (ChatGPT subscription) and "
-            f"'{opencode.PROVIDER}' (OpenCode Zen/Go)."
-        )
+    provider = _resolve_provider(args.provider)
+    if provider is None:
+        supported = ", ".join(f"'{name}'" for name in _PROVIDERS)
+        console.print(f"[red]Unsupported provider:[/] {args.provider}. Supported: {supported}.")
         return 2
 
-    verifier, challenge = codex.generate_pkce()
-    state = codex.create_state()
-    authorize_url = codex.build_authorize_url(challenge, state)
+    module = provider.module
+    verifier, challenge = module.generate_pkce()
+    state = module.create_state()
+    authorize_url = module.build_authorize_url(challenge, state)
 
     console.print()
-    console.print("[bold]Signing in with ChatGPT[/] [dim](provider: chatgpt)[/]")
     console.print(
-        "[dim]This uses your ChatGPT Plus/Pro plan for inference instead of a metered API key.[/]"
+        f"[bold]Signing in with {provider.display}[/] [dim](provider: {provider.name})[/]"
     )
+    console.print(f"[dim]{provider.blurb}[/]")
     console.print()
 
     try:
-        record = _run_oauth_flow(console, authorize_url, verifier, state, manual=args.manual)
-    except codex.CodexAuthError as exc:
+        record = _run_oauth_flow(
+            console, provider, authorize_url, verifier, state, manual=args.manual
+        )
+    except provider.error as exc:
         return _fail(console, exc)
     except KeyboardInterrupt:
         console.print("\n[yellow]Sign-in cancelled.[/]")
         return 130
 
-    codex.save_record(record)
-    _print_success(console)
+    module.save_record(record)
+    _print_success(console, provider)
     return 0
 
 
-def _login_opencode(console: Console) -> int:
-    console.print()
-    console.print("[bold]Signing in with OpenCode[/] [dim](provider: opencode)[/]")
-    console.print(
-        "[dim]This uses your OpenCode Zen credits or Go subscription for inference.\n"
-        f"Get your API key at {opencode.AUTH_CONSOLE_URL}[/]"
-    )
-    console.print()
-    try:
-        key = console.input("Paste your OpenCode API key: ", password=True).strip()
-    except (EOFError, KeyboardInterrupt):
-        console.print("\n[yellow]Sign-in cancelled.[/]")
-        return 130
-    if not key:
-        console.print("[red]No API key provided.[/]")
-        return 2
-    try:
-        opencode.validate_api_key(key)
-    except opencode.OpencodeAuthError as exc:
-        console.print(f"[red]SIGN-IN FAILED:[/] {exc}")
-        return 1
-    opencode.save_api_key(key)
-    _print_opencode_success(console)
-    return 0
-
-
-def _print_opencode_success(console: Console) -> None:
-    text = Text()
-    text.append("Signed in with your OpenCode account", style="bold #22c55e")
-    text.append("\n\n", style="white")
-    text.append("Set ", style="white")
-    text.append("STRIX_LLM", style="bold white")
-    text.append(" to an ", style="white")
-    text.append("opencode/", style="bold cyan")
-    text.append(" model (e.g. ", style="white")
-    text.append("opencode/claude-sonnet-5", style="bold cyan")
-    text.append(") to run on Zen credits, or ", style="white")
-    text.append("opencode-go/", style="bold cyan")
-    text.append(" (e.g. ", style="white")
-    text.append("opencode-go/kimi-k3", style="bold cyan")
-    text.append(") to run on the Go subscription.", style="white")
-    text.append("\n\n", style="white")
-    text.append("Run a scan as usual, e.g. ", style="white")
-    text.append("strix --target https://example.com", style="bold cyan")
-    console.print()
-    console.print(
-        Panel(
-            text,
-            title="[bold white]STRIX",
-            title_align="left",
-            border_style="#22c55e",
-            padding=(1, 2),
-        )
-    )
-    console.print()
-
-
 def _run_oauth_flow(
     console: Console,
+    provider: _Provider,
     authorize_url: str,
     verifier: str,
     state: str,
@@ -193,7 +180,10 @@ def _run_oauth_flow(
     manual: bool,
 ) -> dict[str, Any]:
     """Drive the browser (or manual) OAuth flow and return a token record."""
-    server = None if manual else _try_start_callback_server()
+    module = provider.module
+    server = (
+        None if manual else _try_start_callback_server(module.CALLBACK_PORT, module.CALLBACK_PATH)
+    )
 
     console.print("Open this URL in your browser to authorize:")
     console.print(f"[cyan]{authorize_url}[/]")
@@ -211,8 +201,8 @@ def _run_oauth_flow(
         if result is not None:
             code, returned_state, error = result
             if error:
-                raise codex.CodexAuthError("oauth_error", error)
-            return _finish(code, returned_state, verifier, state, require_state=True)
+                raise provider.error("oauth_error", error)
+            return _finish(provider, code, returned_state, verifier, state, require_state=True)
         console.print("[yellow]Timed out waiting for the browser. Falling back to manual paste.[/]")
 
     # Manual fallback: the user completes sign-in and pastes the redirect URL
@@ -222,12 +212,13 @@ def _run_oauth_flow(
     try:
         pasted = console.input("Paste the full redirect URL (or code#state): ").strip()
     except EOFError as exc:
-        raise codex.CodexAuthError("no_input", "no redirect URL provided") from exc
-    code, returned_state = codex.parse_redirect_input(pasted)
-    return _finish(code, returned_state, verifier, state, require_state=False)
+        raise provider.error("no_input", "no redirect URL provided") from exc
+    code, returned_state = module.parse_redirect_input(pasted)
+    return _finish(provider, code, returned_state, verifier, state, require_state=False)
 
 
 def _finish(
+    provider: _Provider,
     code: str | None,
     returned_state: str | None,
     verifier: str,
@@ -236,16 +227,17 @@ def _finish(
     require_state: bool,
 ) -> dict[str, Any]:
     if not code:
-        raise codex.CodexAuthError("no_code", "no authorization code found in the redirect")
-    # The loopback callback from OpenAI always carries state, so a missing or
-    # mismatched value there is forged (CSRF) and must be rejected. Manual paste
-    # is user-initiated (the user copies their own redirect), so state is only
-    # validated when the pasted value includes it.
+        raise provider.error("no_code", "no authorization code found in the redirect")
+    # The loopback callback from the provider always carries state, so a missing
+    # or mismatched value there is forged (CSRF) and must be rejected. Manual
+    # paste is user-initiated (the user copies their own redirect), so state is
+    # only validated when the pasted value includes it.
     if require_state and returned_state is None:
-        raise codex.CodexAuthError("state_mismatch", "missing state in callback; possible CSRF")
+        raise provider.error("state_mismatch", "missing state in callback; possible CSRF")
     if returned_state is not None and returned_state != expected_state:
-        raise codex.CodexAuthError("state_mismatch", "state did not match; possible CSRF")
-    return codex.exchange_code(code, verifier)
+        raise provider.error("state_mismatch", "state did not match; possible CSRF")
+    record: dict[str, Any] = provider.module.exchange_code(code, verifier)
+    return record
 
 
 class _CallbackServer:
@@ -272,7 +264,7 @@ class _CallbackServer:
         self._httpd.server_close()
 
 
-def _try_start_callback_server() -> _CallbackServer | None:
+def _try_start_callback_server(port: int, path: str) -> _CallbackServer | None:
     event = threading.Event()
     holder: dict[str, Any] = {}
 
@@ -282,7 +274,7 @@ def _try_start_callback_server() -> _CallbackServer | None:
 
         def do_GET(self) -> None:
             parsed = urlparse(self.path)
-            if parsed.path != codex.CALLBACK_PATH:
+            if parsed.path != path:
                 self.send_response(404)
                 self.end_headers()
                 return
@@ -299,9 +291,9 @@ def _try_start_callback_server() -> _CallbackServer | None:
             event.set()
 
     try:
-        httpd = HTTPServer(("127.0.0.1", codex.CALLBACK_PORT), Handler)
+        httpd = HTTPServer(("127.0.0.1", port), Handler)
     except OSError:
-        logger.debug("could not bind callback port %d", codex.CALLBACK_PORT, exc_info=True)
+        logger.debug("could not bind callback port %d", port, exc_info=True)
         return None
     return _CallbackServer(httpd, event, holder)
 
@@ -312,47 +304,67 @@ def _first(query: dict[str, list[str]], key: str) -> str | None:
 
 
 def _status(console: Console) -> int:
-    record = codex.read_record()
-    opencode_signed_in = opencode.is_authenticated()
-    if record is None and not opencode_signed_in:
+    settings = load_settings()
+    active_model = settings.llm.model
+    signed_in_any = False
+    for provider in _PROVIDERS.values():
+        record = provider.module.read_record()
+        if record is None:
+            continue
+        signed_in_any = True
+        console.print(f"[green]Signed in[/] with a {provider.display} subscription.")
+        account_id = record.get("account_id")
+        if account_id:
+            console.print(f"  Account: [bold]{account_id}[/]")
+        if provider.module.subscription_model(active_model):
+            console.print(f"  Runs use the subscription (STRIX_LLM=[bold]{active_model}[/]).")
+        else:
+            console.print(
+                f"  [yellow]Note:[/] set [cyan]STRIX_LLM[/] to e.g. "
+                f"[cyan]{provider.example_model}[/] to run on this subscription."
+            )
+    if not signed_in_any:
         console.print(
-            "[yellow]Not signed in.[/] Run [cyan]strix auth login chatgpt[/] or "
-            "[cyan]strix auth login opencode[/] to sign in."
+            "[yellow]Not signed in.[/] Run [cyan]strix auth login chatgpt[/] "
+            "or [cyan]strix auth login grok[/] to sign in."
         )
         return 1
-    settings = load_settings()
-    if record is not None:
-        console.print("[green]Signed in[/] with a ChatGPT subscription.")
-        console.print(f"  Account: [bold]{record.get('account_id')}[/]")
-    if opencode_signed_in:
-        console.print("[green]Signed in[/] with an OpenCode account.")
-    if codex.subscription_model(settings.llm.model) or opencode.subscription_model(
-        settings.llm.model
-    ):
-        console.print(f"  Runs use the subscription (STRIX_LLM=[bold]{settings.llm.model}[/]).")
-    else:
-        console.print(
-            "  [yellow]Note:[/] set [cyan]STRIX_LLM[/] to e.g. [cyan]chatgpt/gpt-5.4[/] or "
-            "[cyan]opencode/claude-sonnet-5[/] to run on a subscription."
-        )
     return 0
 
 
-def _logout(console: Console, argv: list[str] | None = None) -> int:
-    target = (argv[0].lower() if argv else "") or "all"
-    if target in _ACCEPTED_PROVIDERS or target == "all":
-        codex.logout()
-    if target in _OPENCODE_PROVIDERS or target == "all":
-        opencode.logout()
-    if target != "all" and target not in _ACCEPTED_PROVIDERS | _OPENCODE_PROVIDERS:
-        console.print(f"[red]Unknown provider:[/] {target}\n")
-        console.print(_USAGE)
+def _logout(console: Console, argv: list[str]) -> int:
+    parser = argparse.ArgumentParser(prog="strix auth logout", add_help=True)
+    parser.add_argument(
+        "provider",
+        nargs="?",
+        default=None,
+        help="Provider to sign out of (chatgpt or grok; default: all).",
+    )
+    try:
+        args = parser.parse_args(argv)
+    except SystemExit as exc:
+        return int(exc.code or 2)
+
+    if args.provider is None:
+        # Hold the store lock across every provider so a concurrent save/refresh
+        # can't slip a credential back in between removals (logout-all is atomic).
+        with subscription_store.guard(codex.AUTH_PATH):
+            for provider in _PROVIDERS.values():
+                provider.module.logout()
+        console.print("[green]Signed out.[/] Stored subscription credentials removed.")
+        return 0
+
+    target = _resolve_provider(args.provider)
+    if target is None:
+        supported = ", ".join(f"'{name}'" for name in _PROVIDERS)
+        console.print(f"[red]Unsupported provider:[/] {args.provider}. Supported: {supported}.")
         return 2
-    console.print("[green]Signed out.[/] Stored subscription credentials removed.")
+    target.module.logout()
+    console.print(f"[green]Signed out of {target.display}.[/] Stored credentials removed.")
     return 0
 
 
-def _fail(console: Console, exc: codex.CodexAuthError) -> int:
+def _fail(console: Console, exc: Exception) -> int:
     error_text = Text()
     error_text.append("SIGN-IN FAILED", style="bold red")
     error_text.append("\n\n", style="white")
@@ -370,17 +382,18 @@ def _fail(console: Console, exc: codex.CodexAuthError) -> int:
     return 1
 
 
-def _print_success(console: Console) -> None:
+def _print_success(console: Console, provider: _Provider) -> None:
+    prefix = provider.module.SUBSCRIPTION_PREFIX
     text = Text()
-    text.append("Signed in with your ChatGPT subscription", style="bold #22c55e")
+    text.append(f"Signed in with your {provider.display} subscription", style="bold #22c55e")
     text.append("\n\n", style="white")
     text.append("Set ", style="white")
     text.append("STRIX_LLM", style="bold white")
     text.append(" to a ", style="white")
-    text.append("chatgpt/", style="bold cyan")
+    text.append(prefix, style="bold cyan")
     text.append(" model (e.g. ", style="white")
-    text.append("chatgpt/gpt-5.4", style="bold cyan")
-    text.append(") — runs are billed to your ChatGPT plan.", style="white")
+    text.append(provider.example_model, style="bold cyan")
+    text.append(f") — runs are billed to your {provider.display} plan.", style="white")
     text.append("\n\n", style="white")
     text.append("Run a scan as usual, e.g. ", style="white")
     text.append("strix --target https://example.com", style="bold cyan")

strix/interface/cli_args.py

@@ -328,11 +328,10 @@ def _load_resume_state(args: argparse.Namespace, parser: argparse.ArgumentParser
         parser.error(f"--resume {args.resume}: run.json unreadable: {exc}")
 
     args.targets_info = state.get("targets_info") or []
-    # A target-less run has no targets_info at all. It is driven by its
-    # instruction, over a mounted working directory or over nothing when the
-    # mount was declined, so either of those is enough to resume it.
+    # A target-less run has no targets_info at all: it works in a mounted
+    # directory, driven by its instruction.
     workspace_mount = state.get("workspace_mount") or None
-    if not args.targets_info and not workspace_mount and not state.get("user_instruction"):
+    if not args.targets_info and not workspace_mount:
         parser.error(f"--resume {args.resume}: run.json has no targets_info")
 
     for target in args.targets_info:

strix/interface/environment.py

@@ -8,7 +8,7 @@ from rich.console import Console
 from rich.panel import Panel
 from rich.text import Text
 
-from strix.config import codex, load_settings, opencode
+from strix.config import codex, grok, load_settings
 from strix.interface.utils import (
     check_docker_connection,
     image_exists,
@@ -37,14 +37,14 @@ def validate_environment() -> None:
         logger.info("Environment OK (ChatGPT subscription)")
         return
 
-    if opencode.subscription_model(settings.llm.model):
-        if not opencode.is_authenticated():
+    if grok.subscription_model(settings.llm.model):
+        if not grok.is_authenticated():
             console.print(
-                f"[red]STRIX_LLM={settings.llm.model} uses your OpenCode subscription, "
-                "but you're not signed in.[/] Run [cyan]strix auth login opencode[/] first."
+                f"[red]STRIX_LLM={settings.llm.model} uses your Grok subscription, "
+                "but you're not signed in.[/] Run [cyan]strix auth login grok[/] first."
             )
             sys.exit(1)
-        logger.info("Environment OK (OpenCode subscription)")
+        logger.info("Environment OK (Grok subscription)")
         return
 
     if not settings.llm.model:

strix/interface/main.py

@@ -14,7 +14,7 @@ from rich.console import Console
 from rich.panel import Panel
 from rich.text import Text
 
-from strix.config import codex, load_settings, opencode, persist_current
+from strix.config import codex, load_settings, persist_current
 from strix.core.paths import run_dir_for
 from strix.interface.cli_args import parse_arguments
 from strix.interface.environment import (
@@ -104,14 +104,8 @@ def _provider_import_hint(exc: BaseException, model: str) -> str | None:
 
 
 def _subscription_error_hint(exc: BaseException) -> str | None:
-    """Return an actionable hint for a known subscription error, or None."""
-    model = load_settings().llm.model
-    if opencode.subscription_model(model):
-        joined = " ".join(_exception_messages(exc)).lower()
-        if "error code: 401" in joined or "http 401" in joined or "unauthorized" in joined:
-            return "Your OpenCode API key was rejected. Sign in again:\n  strix auth login opencode"
-        return None
-    if not codex.subscription_model(model):
+    """Return an actionable hint for a known ChatGPT-subscription error, or None."""
+    if not codex.subscription_model(load_settings().llm.model):
         return None
     joined = " ".join(_exception_messages(exc)).lower()
     if "not supported when using codex with a chatgpt account" in joined:
@@ -230,7 +224,6 @@ async def warm_up_llm(show_model_warning: bool = True) -> None:
                 request_timeout=llm.timeout,
                 prompt_cache=False,
                 extra_headers=settings.dedupe.extra_headers,
-                has_tools=False,
             )
             if deduper_extra:
                 merged = {**(deduper_settings.extra_args or {}), **deduper_extra}
@@ -442,7 +435,16 @@ def main() -> None:
     start_background_check()
     if not args.non_interactive and prompt_update_if_available(Console()):
         if is_binary_install() and sys.platform != "win32":
-            os.execv(sys.executable, sys.argv)  # noqa: S606  # nosec B606
+            # The PyInstaller onefile bootloader passes its state to the child
+            # process via environment variables; if they leak into the re-exec,
+            # the new binary reuses the old extracted application instead of
+            # unpacking itself, so the pre-update version runs again.
+            env = {
+                key: value
+                for key, value in os.environ.items()
+                if not key.startswith("_PYI_") and key != "_MEIPASS2"
+            }
+            os.execve(sys.executable, sys.argv, env)  # noqa: S606  # nosec B606
         sys.exit(0)
 
     check_docker_installed()

strix/interface/scan_setup.py

@@ -14,7 +14,7 @@ import logging
 from datetime import UTC, datetime
 from typing import TYPE_CHECKING, Any
 
-from strix.config import Settings, load_settings, opencode
+from strix.config import Settings, load_settings, subscription
 from strix.core.paths import run_dir_for
 from strix.interface.utils import (
     assign_workspace_subdirs,
@@ -78,7 +78,6 @@ async def preflight_model_connection(
         request_timeout=resolved_settings.llm.timeout,
         prompt_cache=False,
         extra_headers=resolved_settings.llm.extra_headers,
-        has_tools=False,
     )
     await asyncio.wait_for(
         model.get_response(
@@ -226,7 +225,7 @@ def telemetry_start(args: argparse.Namespace) -> None:
     model = load_settings().llm.model
     kwargs = {
         "model": model,
-        "auth_mode": opencode.auth_mode(model),
+        "auth_mode": subscription.auth_mode(model),
         "scan_mode": args.scan_mode,
         "is_whitebox": is_whitebox_scan(args.targets_info),
         "interactive": not args.non_interactive,
@@ -241,14 +240,15 @@ def _persist_run_record(args: argparse.Namespace) -> None:
 
     run_dir = run_dir_for(args.run_name)
     run_dir.mkdir(parents=True, exist_ok=True)
+    model = load_settings().llm.model
     run_record = {
         "run_id": args.run_name,
         "run_name": args.run_name,
         "status": "running",
         "start_time": datetime.now(UTC).isoformat(),
         "end_time": None,
-        "auth_mode": opencode.auth_mode(load_settings().llm.model),
-        "subscription_provider": opencode.subscription_provider(load_settings().llm.model),
+        "auth_mode": subscription.auth_mode(model),
+        "subscription_provider": subscription.provider_label(model),
         "targets_info": args.targets_info,
         "scan_mode": args.scan_mode,
         "instruction": args.instruction,

strix/interface/tui/backend/controller.py

@@ -24,7 +24,7 @@ from strix.interface.tui.backend.projection import (
     sanitize_terminal_text,
     terminal_projection,
 )
-from strix.interface.utils import is_subscription_run, subscription_label
+from strix.interface.utils import is_subscription_run
 
 
 if TYPE_CHECKING:
@@ -138,6 +138,13 @@ class TuiController:
         self.error = detail
         self.notify_changed()
 
+    def enter_setup(self) -> None:
+        """Return a session to the start screen, e.g. on a declined mount."""
+        self.setup_mode = True
+        self.scan_started = False
+        self.scan_state = "setup"
+        self.notify_changed()
+
     def add_message(self, text: str, level: str = "info") -> None:
         self._append_message(text, level)
         self.notify_changed()
@@ -164,10 +171,6 @@ class TuiController:
         subscription = False
         with contextlib.suppress(Exception):
             subscription = is_subscription_run(self.report_state)
-        label = ""
-        if subscription:
-            with contextlib.suppress(Exception):
-                label = subscription_label()
         model_warning = ""
         if model and not is_recommended_or_frontier_model(model):
             model_warning = (
@@ -204,7 +207,6 @@ class TuiController:
             ],
             "usage": terminal_projection(usage, max_string=256, max_items=20),
             "subscription": subscription,
-            "subscription_label": label,
             "viewer_status": self.viewer_status,
             "viewer_url": terminal_projection(self.viewer_url, max_string=1024),
             "error": terminal_projection(self.error, max_string=2 * 1024),
@@ -354,12 +356,14 @@ class TuiController:
         if not isinstance(approved, bool):
             raise TypeError("approved must be a boolean")
         self.pending_workspace_mount = None
-        # Declining skips the mount, it does not abandon the scan. The prompt is
-        # the whole of the input either way; the working directory is only an
-        # extra the agent may look at, so the run goes ahead without one.
-        self.workspace_mount = mount if approved else None
+        if not approved:
+            # Nothing was prepared, so return to the start screen untouched.
+            self.workspace_mount = None
+            self.enter_setup()
+            return {"approved": False}
+        self.workspace_mount = mount
         await self._begin_scan(self._pending_verify)
-        return {"approved": approved}
+        return {"approved": True}
 
     async def _send_message(self, payload: dict[str, Any]) -> dict[str, Any]:
         agent_id = self._required_string(payload, "agent_id")

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

@@ -66,10 +66,13 @@ func (m *Model) submitSetupPrompt(value string) (tea.Model, tea.Cmd) {
 }
 
 // answerMountConfirmation replies to the working-directory mount the backend is
-// waiting on. Either answer starts the scan - declining only means it runs
-// without the directory - so the prompt stays with the run rather than coming
-// back to the composer.
+// waiting on. Declining returns to the start screen, so the prompt goes back in
+// the composer to be edited or given a target instead.
 func (m *Model) answerMountConfirmation(approved bool) tea.Cmd {
+	if !approved && m.pendingPrompt != "" {
+		m.input.SetValue(m.pendingPrompt)
+		m.resizeViewport()
+	}
 	m.pendingPrompt = ""
 	return send(m.client, "setup.confirm_mount", map[string]any{"approved": approved})
 }

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

@@ -247,10 +247,13 @@ func TestMountConfirmationAnswers(t *testing.T) {
 		if payload.Approved != tc.approved {
 			t.Fatalf("%s: approved=%v, want %v", tc.name, payload.Approved, tc.approved)
 		}
-		// Either answer launches, so the prompt stays with the run rather than
-		// coming back to the composer.
-		if got := model.input.Value(); got != "" {
-			t.Fatalf("%s: composer = %q, want it cleared", tc.name, got)
+		// Declining returns to the start screen, so the prompt comes back.
+		want := ""
+		if !tc.approved {
+			want = "find auth bugs in the login flow"
+		}
+		if got := model.input.Value(); got != want {
+			t.Fatalf("%s: composer = %q, want %q", tc.name, got, want)
 		}
 		if model.pendingPrompt != "" {
 			t.Fatalf("%s: held prompt was not cleared: %q", tc.name, model.pendingPrompt)
@@ -287,101 +290,3 @@ func TestSetupPromptWithTargetLaunches(t *testing.T) {
 		t.Fatalf("setup.start (%d) must come after setup.set_instruction (%d): %v", start, instr, types)
 	}
 }
-
-// The prompt's buttons are buttons: clicking Cancel has to answer the backend,
-// which it could not do while the mouse handler had no case for this modal.
-func TestMountPromptButtonsAreClickable(t *testing.T) {
-	for _, testCase := range []struct {
-		label    string
-		approved bool
-	}{
-		{mountConfirmLabel, true},
-		{mountCancelLabel, false},
-	} {
-		connection := &recordingConn{}
-		model := New(&Client{conn: connection})
-		model.width, model.height = 130, 40
-		model.snapshot = protocol.Snapshot{SetupMode: true, WorkingDir: "/Users/me/code/api"}
-		updated, _ := model.submit("find auth bugs in the login flow")
-		model = updated.(Model)
-		connection.Reset()
-		model.snapshot = protocol.Snapshot{
-			ScanStarted: true, ScanState: "preparing", PendingMount: "/Users/me/code/api",
-		}
-		model.syncMountPrompt()
-
-		left, top, panel := model.mountPromptBounds()
-		clicked := false
-		for row, line := range strings.Split(panel, "\n") {
-			plain := ansi.Strip(line)
-			index := strings.Index(plain, testCase.label)
-			if index < 0 {
-				continue
-			}
-			updated, cmd := model.updateModalMouse(tea.MouseMsg{
-				X: left + ansi.StringWidth(plain[:index]) + 1, Y: top + row,
-				Button: tea.MouseButtonLeft, Action: tea.MouseActionPress,
-			})
-			model = updated.(Model)
-			envelopes := drainCommands(t, cmd, connection)
-			if len(envelopes) != 1 || envelopes[0].Type != "setup.confirm_mount" {
-				t.Fatalf("clicking %s sent %v", testCase.label, commandTypes(envelopes))
-			}
-			var payload struct {
-				Approved bool `json:"approved"`
-			}
-			if err := json.Unmarshal(envelopes[0].Payload, &payload); err != nil {
-				t.Fatal(err)
-			}
-			if payload.Approved != testCase.approved {
-				t.Fatalf("clicking %s answered approved=%v", testCase.label, payload.Approved)
-			}
-			clicked = true
-			break
-		}
-		if !clicked {
-			t.Fatalf("%s was not found in the prompt", testCase.label)
-		}
-	}
-}
-
-// Skipping the mount runs the scan without a directory. It must not throw the
-// session back to the start screen, and it must not hand the prompt back: the
-// run has it.
-func TestSkippingTheMountKeepsTheScanRunning(t *testing.T) {
-	connection := &recordingConn{}
-	model := New(&Client{conn: connection})
-	model.width, model.height = 130, 40
-	model.snapshot = protocol.Snapshot{SetupMode: true, WorkingDir: "/Users/me/code/api"}
-	updated, _ := model.submit("find auth bugs in the login flow")
-	model = updated.(Model)
-	model.snapshot = protocol.Snapshot{
-		ScanStarted: true, ScanState: "preparing", PendingMount: "/Users/me/code/api",
-	}
-	model.syncMountPrompt()
-	if model.modal != modalConfirmMount {
-		t.Fatal("the prompt did not open")
-	}
-
-	model.modalChoice = 1
-	updated, _ = model.updateModal(tea.KeyMsg{Type: tea.KeyEnter})
-	model = updated.(Model)
-
-	// The backend answers by starting the scan with no mount.
-	model.handleEnvelope(stateEnvelope(t, 2, protocol.Snapshot{
-		ScanStarted: true, ScanState: "running",
-	}))
-
-	if model.modal != modalNone {
-		t.Fatalf("the prompt is still open: %v", model.modal)
-	}
-	if model.snapshot.SetupMode {
-		t.Fatal("skipping the mount fell back to the start screen")
-	}
-	if got := model.input.Value(); got != "" {
-		t.Fatalf("the prompt came back to the composer: %q", got)
-	}
-	if model.pendingPrompt != "" {
-		t.Fatalf("the held prompt was not released: %q", model.pendingPrompt)
-	}
-}

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

@@ -474,18 +474,6 @@ func (m Model) updateModalMouse(msg tea.MouseMsg) (tea.Model, tea.Cmd) {
 			m.modalChoice = 1
 			return m.updateModal(tea.KeyMsg{Type: tea.KeyEnter})
 		}
-	case modalConfirmMount:
-		left, top, panel := m.mountPromptBounds()
-		if labelHitAt(panel, mountConfirmLabel, left, top, msg.X, msg.Y) {
-			m.modalChoice = 0
-			cmd := m.answerMountConfirmation(true)
-			return m, cmd
-		}
-		if labelHitAt(panel, mountCancelLabel, left, top, msg.X, msg.Y) {
-			m.modalChoice = 1
-			cmd := m.answerMountConfirmation(false)
-			return m, cmd
-		}
 	case modalVulnerability:
 		for _, button := range m.reportButtons() {
 			if button == reportCopy || button == reportDone {
@@ -519,14 +507,7 @@ func (m Model) centeredViewBounds(view string) (left, top, width, height int) {
 
 func (m Model) centeredLabelHit(view, label string, x, y int) bool {
 	left, top, _, _ := m.centeredViewBounds(view)
-	return labelHitAt(view, label, left, top, x, y)
-}
-
-// labelHitAt reports whether a click landed on a label drawn in a panel whose
-// top-left corner is at (left, top). The mount prompt is docked in a corner
-// rather than centered, so it cannot use the centered bounds.
-func labelHitAt(panel, label string, left, top, x, y int) bool {
-	for row, line := range strings.Split(panel, "\n") {
+	for row, line := range strings.Split(view, "\n") {
 		plain := ansi.Strip(line)
 		index := strings.Index(plain, label)
 		if index < 0 || y != top+row {
@@ -612,8 +593,7 @@ func (m Model) updateModal(key tea.KeyMsg) (tea.Model, tea.Cmd) {
 	case "esc":
 		if m.modal == modalConfirmMount {
 			// The backend is waiting on an answer; escape declines it.
-			cmd := m.answerMountConfirmation(false)
-			return m, cmd
+			return m, m.answerMountConfirmation(false)
 		}
 		m.closeModal()
 		return m, nil
@@ -624,10 +604,7 @@ func (m Model) updateModal(key tea.KeyMsg) (tea.Model, tea.Cmd) {
 		modal, choice := m.modal, m.modalChoice
 		if modal == modalConfirmMount {
 			// The snapshot closes this prompt once the backend has the answer.
-			// Bound to a variable first: the call restores the held prompt into
-			// the composer, and that has to be in the model being returned.
-			cmd := m.answerMountConfirmation(choice == 0)
-			return m, cmd
+			return m, m.answerMountConfirmation(choice == 0)
 		}
 		m.closeModal()
 		if choice == 1 {

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

@@ -271,23 +271,6 @@ func (m Model) viewInner() string {
 	return m.toastOverlay(main)
 }
 
-// mountPromptBounds is where the working-directory prompt is drawn. It is placed
-// by cornerOverlay rather than centered, so a click has to be tested against
-// these bounds and not the ones the other modals use.
-func (m Model) mountPromptBounds() (left, top int, panel string) {
-	panel = m.modalView()
-	if panel == "" {
-		return 0, 0, ""
-	}
-	_, _, chatWidth, _ := m.layout()
-	left = max(0, min(chatWidth, m.width)-lipgloss.Width(panel))
-	statusH := 0
-	if m.statusVisible() {
-		statusH = 1
-	}
-	return left, max(0, m.inputTop()-statusH-lipgloss.Height(panel)), panel
-}
-
 // cornerOverlay splices a panel in directly above the composer, right-aligned
 // with it, leaving the rest of the view visible behind it.
 func (m Model) cornerOverlay(view, panel string) string {
@@ -596,11 +579,7 @@ func (m Model) statsView() string {
 		if b.Len() > 0 {
 			b.WriteString("\n")
 		}
-		label := m.snapshot.SubscriptionLabel
-		if label == "" {
-			label = "ChatGPT subscription"
-		}
-		b.WriteString(lipgloss.NewStyle().Foreground(green).Render(label))
+		b.WriteString(lipgloss.NewStyle().Foreground(green).Render("ChatGPT subscription"))
 	}
 	total := numberValue(m.snapshot.Usage["total_tokens"])
 	if total > 0 {

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

@@ -220,13 +220,6 @@ func (m Model) confirmView(title string, width int, border, titleColor lipgloss.
 	return m.confirmDialog(title, "", width, border, titleColor, red, "Yes", "No")
 }
 
-// The mount prompt's buttons, named so the renderer and the click test cannot
-// drift apart.
-const (
-	mountConfirmLabel = "Mount"
-	mountCancelLabel  = "Skip"
-)
-
 // mountConfirmView asks before a target-less scan mounts the working directory.
 // It is a compact prompt docked in the corner of the live view: nothing is
 // prepared until it is answered, and the directory is a workspace rather than a
@@ -239,8 +232,8 @@ func (m Model) mountConfirmView() string {
 	}
 	title := render.Bold(amber).Render("△ Mount working directory?")
 	body := render.Col(white).Render(truncatePath(dir, width-4)) + "\n" +
-		render.Dim().Render("writable in the sandbox · skip to run without it")
-	return m.cornerPrompt(title, body, width, mountConfirmLabel, mountCancelLabel)
+		render.Dim().Render("writable in the sandbox")
+	return m.cornerPrompt(title, body, width, "Confirm", "Cancel")
 }
 
 // truncatePath keeps the tail of a path visible, which is the part that

strix/interface/tui/internal/protocol/protocol.go

@@ -68,7 +68,6 @@ type Snapshot struct {
 	Vulnerabilities     []map[string]any `json:"-"`
 	Usage               map[string]any   `json:"usage"`
 	Subscription        bool             `json:"subscription"`
-	SubscriptionLabel   string           `json:"subscription_label"`
 	ViewerStatus        string           `json:"viewer_status"`
 	ViewerURL           *string          `json:"viewer_url"`
 	Error               *string          `json:"error"`

strix/interface/utils.py

@@ -262,19 +262,27 @@ def is_subscription_run(report_state: Any) -> bool:
     record = getattr(report_state, "run_record", None)
     if isinstance(record, dict) and record.get("auth_mode"):
         return record.get("auth_mode") == "subscription"
-    from strix.config import opencode
+    from strix.config import subscription
 
-    return opencode.auth_mode(load_settings().llm.model) == "subscription"
+    return subscription.auth_mode(load_settings().llm.model) == "subscription"
 
 
-def subscription_label() -> str:
-    """Display name of the subscription behind the configured model."""
-    from strix.config import opencode
+def _subscription_label(report_state: Any) -> str:
+    """Human label for the active model subscription (e.g. "Grok subscription").
 
-    model = load_settings().llm.model
-    if opencode.subscription_model(model):
-        return "OpenCode subscription"
-    return "ChatGPT subscription"
+    Prefers the persisted run record so a resumed run keeps its original provider
+    even if STRIX_LLM later points at a different one; falls back to current
+    settings.
+    """
+    record = getattr(report_state, "run_record", None)
+    if isinstance(record, dict):
+        provider = record.get("subscription_provider")
+        if isinstance(provider, str) and provider:
+            return f"{provider} subscription"
+    from strix.config import subscription
+
+    label = subscription.provider_label(load_settings().llm.model)
+    return f"{label} subscription" if label else "Subscription"
 
 
 def _int_stat(usage: dict[str, Any], key: str) -> int:
@@ -378,7 +386,7 @@ def build_live_stats_text(report_state: Any) -> Text:
     stats_text.append(str(model), style="white")
     if is_subscription_run(report_state):
         stats_text.append("  ·  ", style="dim white")
-        stats_text.append(subscription_label(), style="#22c55e")
+        stats_text.append(_subscription_label(report_state), style="#22c55e")
     stats_text.append("\n")
 
     vuln_count = len(report_state.vulnerability_reports)
@@ -424,7 +432,7 @@ def build_tui_stats_text(report_state: Any) -> Text:
     subscription = is_subscription_run(report_state)
     if subscription:
         stats_text.append("\n")
-        stats_text.append(subscription_label(), style="#22c55e")
+        stats_text.append(_subscription_label(report_state), style="#22c55e")
 
     usage = _llm_usage(report_state)
     if usage and _int_stat(usage, "total_tokens") > 0:

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

@@ -101,11 +101,7 @@ export function RunDetails({
   const totalTokens = num(usage.total_tokens);
   const cost = num(usage.cost);
   const subscription = str(raw.auth_mode) === "subscription";
-  const subscriptionProvider =
-    str(raw.subscription_provider) ??
-    (models.some((m) => m.toLowerCase().startsWith("opencode")) ? "opencode" : "chatgpt");
-  const subscriptionLabel =
-    subscriptionProvider === "opencode" ? "OpenCode subscription" : "ChatGPT subscription";
+  const subscriptionProvider = str(raw.subscription_provider);
 
   const sub = (n: number, word: string) => (
     <span className="text-[#666]"> ({formatNumber(n)} {word})</span>
@@ -185,7 +181,7 @@ export function RunDetails({
                 <Field label="Provider">
                   <span className="inline-flex items-center gap-1.5">
                     <span className="rounded-full border border-[#22c55e]/40 bg-[#22c55e]/10 px-2 py-0.5 text-[11px] text-[#22c55e]">
-                      {subscriptionLabel}
+                      {subscriptionProvider ? `${subscriptionProvider} subscription` : "Subscription"}
                     </span>
                   </span>
                 </Field>

strix/interface/viewer/static/index.html

@@ -6,7 +6,7 @@
     <meta name="viewport" content="width=device-width, initial-scale=1.0" />
     <meta name="color-scheme" content="dark" />
     <title>Strix Results</title>
-    <script type="module" crossorigin src="./assets/index-1LIW3rcB.js"></script>
+    <script type="module" crossorigin src="./assets/index-XDX3roAH.js"></script>
     <link rel="stylesheet" crossorigin href="./assets/index-DKbLYAbP.css">
   </head>
   <body>

strix/interface/viewer/transcript.py

@@ -6,6 +6,7 @@ import json
 import logging
 from typing import TYPE_CHECKING, Any
 
+from strix.config import subscription
 from strix.core.paths import run_record_path
 from strix.interface.tui.live_view import TuiLiveView
 
@@ -57,7 +58,39 @@ def read_run_summary(run_dir: Path) -> dict[str, Any]:
         record = {}
     status = record.get("status")
     finished = status in _TERMINAL_STATUSES and bool(record.get("end_time"))
-    return {**record, "finished": finished}
+    summary = {**record, "finished": finished}
+    _backfill_subscription_provider(summary)
+    return summary
+
+
+def _first_recorded_model(record: dict[str, Any]) -> str | None:
+    """The first non-empty per-agent model slug in a run record, or None."""
+    usage = record.get("llm_usage")
+    if not isinstance(usage, dict):
+        return None
+    agents = usage.get("agents")
+    if not isinstance(agents, list):
+        return None
+    for agent in agents:
+        if isinstance(agent, dict):
+            model = agent.get("model")
+            if isinstance(model, str) and model:
+                return model
+    return None
+
+
+def _backfill_subscription_provider(record: dict[str, Any]) -> None:
+    """Name the subscription provider for runs recorded before that field
+    existed, deriving it from the recorded ``provider/model`` slug so the viewer
+    labels them correctly without a rescan. Newer runs already carry the field.
+    """
+    if record.get("subscription_provider"):
+        return
+    if record.get("auth_mode") != "subscription":
+        return
+    label = subscription.provider_label(_first_recorded_model(record))
+    if label:
+        record["subscription_provider"] = label
 
 
 def primary_target(record: dict[str, Any]) -> str | None:

strix/llm/compaction.py

@@ -294,7 +294,6 @@ async def _summarize(model: str, prompt: str, max_tokens: int) -> str | None:
         request_timeout=llm.timeout,
         prompt_cache=False,
         extra_headers=llm.extra_headers,
-        has_tools=False,
     ).resolve(ModelSettings(max_tokens=max_tokens))
     try:
         response = (

strix/llm/context_budget.py

@@ -20,8 +20,6 @@ logger = logging.getLogger(__name__)
 _STRIPPABLE_PREFIXES = (
     "openai/",
     "chatgpt/",
-    "opencode-go/",
-    "opencode/",
     "litellm/",
     "any-llm/",
     "ollama/",
@@ -50,11 +48,7 @@ def _model_info(model: str) -> dict[str, int]:
     lookup_key = _lookup_key(model)
     # Provider-qualified ChatGPT lookups may start a synchronous device-login
     # poll. LiteLLM keys the metadata by the underlying model slug.
-    candidates = (
-        (lookup_key,)
-        if model.startswith(("chatgpt/", "opencode/", "opencode-go/"))
-        else (model, lookup_key)
-    )
+    candidates = (lookup_key,) if model.startswith("chatgpt/") else (model, lookup_key)
     for candidate in candidates:
         info = _safe_get_model_info(candidate)
         if info is not None:

strix/report/dedupe.py

@@ -62,7 +62,6 @@ def _dedupe_model_settings(
         # must never receive the main endpoint's credentials. A dedicated model
         # gets its own DEDUPE_LLM_EXTRA_HEADERS instead.
         extra_headers=dedupe.extra_headers if dedupe.model else llm.extra_headers,
-        has_tools=False,
     )
     extra = _dedupe_extra_args(dedupe)
     if extra:

strix/report/pricing.py

@@ -1,54 +0,0 @@
-"""LiteLLM model-name resolution for local cost estimates."""
-
-from __future__ import annotations
-
-from functools import lru_cache
-from typing import Any, cast
-
-
-@lru_cache(maxsize=512)
-def resolve_litellm_model(model: str) -> str | None:
-    """Return a provider-qualified model name that LiteLLM can price."""
-    try:
-        import litellm
-
-        normalized = model.strip()
-        for prefix in ("litellm/", "any-llm/", "openai/"):
-            if normalized.startswith(prefix):
-                normalized = normalized.removeprefix(prefix)
-                break
-        if not normalized:
-            return None
-
-        model_cost = cast(
-            "dict[str, dict[str, Any]]",
-            getattr(litellm, "model_cost"),  # noqa: B009
-        )
-        bare_entry = model_cost.get(normalized)
-        if "/" not in normalized and isinstance(bare_entry, dict):
-            provider = bare_entry.get("litellm_provider")
-            if isinstance(provider, str) and provider:
-                return f"{provider}/{normalized}"
-        if "/" in normalized and isinstance(bare_entry, dict):
-            return normalized
-
-        names = [normalized]
-        if "/" in normalized:
-            names.append(normalized.rsplit("/", 1)[-1])
-        for name in names:
-            matches = sorted(key for key in model_cost if key.endswith(f"/{name}"))
-            if not matches:
-                continue
-            prices = {
-                (
-                    model_cost[key].get("input_cost_per_token"),
-                    model_cost[key].get("output_cost_per_token"),
-                )
-                for key in matches
-                if isinstance(model_cost.get(key), dict)
-            }
-            if len(matches) == 1 or len(prices) == 1:
-                return matches[0]
-        return None  # noqa: TRY300
-    except Exception:  # noqa: BLE001
-        return None

strix/report/state.py

@@ -11,10 +11,9 @@ from uuid import uuid4
 
 from agents.usage import Usage
 
-from strix.config import opencode
+from strix.config import subscription
 from strix.config.loader import load_settings
 from strix.core.paths import run_dir_for
-from strix.report.pricing import resolve_litellm_model
 from strix.report.sarif import write_sarif
 from strix.report.usage import LLMUsageLedger
 from strix.report.writer import (
@@ -123,7 +122,8 @@ class ReportState:
         self.scan_results: dict[str, Any] | None = None
         self.scan_config: dict[str, Any] | None = None
         self._llm_usage = LLMUsageLedger()
-        auth_mode = opencode.auth_mode(load_settings().llm.model)
+        model = load_settings().llm.model
+        auth_mode = subscription.auth_mode(model)
         self._llm_usage.zero_cost = auth_mode == "subscription"
         self.run_record: dict[str, Any] = {
             "run_id": self.run_id,
@@ -132,7 +132,7 @@ class ReportState:
             "end_time": None,
             "status": "running",
             "auth_mode": auth_mode,
-            "subscription_provider": opencode.subscription_provider(load_settings().llm.model),
+            "subscription_provider": subscription.provider_label(model),
             "targets_info": [],
             "llm_usage": self._build_llm_usage_record(),
         }
@@ -698,13 +698,10 @@ def _estimate_response_cost(kwargs: Any, completion_response: Any) -> float | No
         candidates.append(model.rsplit("/", 1)[-1])
 
     for candidate in candidates:
-        resolved = resolve_litellm_model(candidate)
-        if not resolved:
-            continue
         try:
             value = completion_cost(
-                completion_response={"model": resolved, "usage": usage_payload},
-                model=resolved,
+                completion_response={"model": candidate, "usage": usage_payload},
+                model=candidate,
             )
         except Exception:  # nosec B112  # noqa: BLE001, S112
             continue

strix/report/usage.py

@@ -7,8 +7,6 @@ from typing import Any
 
 from agents.usage import Usage, deserialize_usage, serialize_usage
 
-from strix.report.pricing import resolve_litellm_model
-
 
 logger = logging.getLogger(__name__)
 
@@ -20,9 +18,7 @@ class LLMUsageLedger:
         self._total_usage = Usage()
         self._agent_usage: dict[str, Usage] = {}
         self._agent_metadata: dict[str, dict[str, str]] = {}
-        self._observed_cost = 0.0
-        self._estimated_cost = 0.0
-        self._has_observed_cost = False
+        self._total_cost = 0.0
         # When True, tokens are still tracked but cost stays $0 — the run is on a
         # model subscription, so there is no metered per-token charge to report.
         self.zero_cost = False
@@ -48,10 +44,10 @@ class LLMUsageLedger:
         if model:
             metadata["model"] = model
 
-        if not self.zero_cost:
+        if not self.zero_cost and not _is_litellm_routed(model):
             estimated = _estimate_litellm_cost(usage, model)
             if estimated:
-                self._estimated_cost += estimated
+                self._total_cost += estimated
 
         return True
 
@@ -59,18 +55,15 @@ class LLMUsageLedger:
         if self.zero_cost:
             return
         if isinstance(cost, int | float) and cost > 0:
-            self._observed_cost += float(cost)
-            self._has_observed_cost = True
+            self._total_cost += float(cost)
 
     @property
     def total_cost(self) -> float:
-        if self.zero_cost:
-            return 0.0
-        return _round_cost(self._observed_cost if self._has_observed_cost else self._estimated_cost)
+        return _round_cost(self._total_cost)
 
     def to_record(self) -> dict[str, Any]:
         record = serialize_usage(self._total_usage)
-        record["cost"] = self.total_cost
+        record["cost"] = _round_cost(self._total_cost)
         record["agents"] = []
 
         agent_tokens = {aid: _resolve_total_tokens(u) for aid, u in self._agent_usage.items()}
@@ -79,7 +72,7 @@ class LLMUsageLedger:
             usage = self._agent_usage[agent_id]
             metadata = self._agent_metadata.get(agent_id, {})
             agent_cost = (
-                self.total_cost * (agent_tokens[agent_id] / total_tokens) if total_tokens else 0.0
+                self._total_cost * (agent_tokens[agent_id] / total_tokens) if total_tokens else 0.0
             )
 
             agent_record = serialize_usage(usage)
@@ -99,9 +92,7 @@ class LLMUsageLedger:
         self._total_usage = Usage()
         self._agent_usage.clear()
         self._agent_metadata.clear()
-        self._observed_cost = 0.0
-        self._estimated_cost = 0.0
-        self._has_observed_cost = False
+        self._total_cost = 0.0
 
         if not isinstance(raw_usage, dict):
             return
@@ -112,9 +103,7 @@ class LLMUsageLedger:
             logger.exception("Failed to hydrate aggregate llm_usage from run.json")
             self._total_usage = Usage()
 
-        persisted_cost = _float_or_zero(raw_usage.get("cost"))
-        self._observed_cost = persisted_cost
-        self._estimated_cost = persisted_cost
+        self._total_cost = _float_or_zero(raw_usage.get("cost"))
 
         for raw_agent in raw_usage.get("agents") or []:
             if not isinstance(raw_agent, dict):
@@ -147,6 +136,15 @@ def _resolve_total_tokens(usage: Usage) -> int:
     return prompt + completion
 
 
+def _is_litellm_routed(model: str | None) -> bool:
+    if not model:
+        return False
+    name = model.strip().lower()
+    if "/" not in name:
+        return False
+    return not name.startswith("openai/")
+
+
 def _usage_has_activity(usage: Usage) -> bool:
     return bool(
         usage.requests
@@ -203,23 +201,24 @@ def _estimate_litellm_entry_cost(entry: Any, model: str) -> float | None:
 
     candidates = [model]
     if "/" in model:
-        candidates.append(model.rsplit("/", 1)[-1])
+        candidates.append(model.split("/", 1)[-1])
 
+    cost: Any = None
     for candidate in candidates:
-        resolved = resolve_litellm_model(candidate)
-        if not resolved:
-            continue
         try:
             cost = completion_cost(
-                completion_response={"model": resolved, "usage": usage_payload},
-                model=resolved,
+                completion_response={"model": candidate, "usage": usage_payload},
+                model=model,
             )
+            break
         except Exception:  # nosec B112  # noqa: BLE001, S112
             continue
-        if cost > 0:
-            return float(cost)
-    logger.debug("LiteLLM cost estimate unavailable for model %s", model)
-    return None
+
+    if cost is None:
+        logger.debug("LiteLLM cost estimate unavailable for model %s", model)
+        return None
+
+    return cost if isinstance(cost, int | float) and cost >= 0 else None
 
 
 def _litellm_model_name(model: str | None) -> str | None:

strix/skills/tooling/agent_browser.md

@@ -58,26 +58,6 @@ agent-browser screenshot
 The browser stays running across commands so these feel like a single
 session. Use `agent-browser close` (or `close --all`) when you're done.
 
-The default session is **shared with every other agent in the sandbox** — if
-another agent navigates it, your page and your refs are gone from under you. So
-claim your own by passing `--session <your-agent-name>` on **every** command:
-
-```bash
-agent-browser --session recon-3 open https://example.com
-agent-browser --session recon-3 snapshot -i
-agent-browser --session recon-3 close        # when done with the target
-```
-
-The examples in the rest of this skill omit `--session` to keep them readable;
-keep passing yours. Each session is a separate Chromium (~340 MB) on a shared
-box, so hold one rather than several, and close it when you're finished.
-
-A browser left idle for 3 minutes is reclaimed automatically to free memory for
-the other agents; the next command relaunches it, but the page, tabs, refs and
-cookies are gone. If you're authenticated and about to go do something else for a
-while, save the state first (see
-[Persist session across runs](#persist-session-across-runs)).
-
 ## Reading a page
 
 ```bash
@@ -327,16 +307,6 @@ agent-browser --session b fill @e1 "bob@test.com"
 `AGENT_BROWSER_SESSION=myapp` sets the default session for the current
 shell.
 
-Use a session named after yourself for your own work — that's what keeps a
-concurrent agent from navigating the page out from under you. Every session is a
-separate Chromium though, so hold one at a time rather than a collection, and
-close each one when its flow is finished:
-
-```bash
-agent-browser --session a close
-agent-browser --session b close
-```
-
 ### Mock network requests
 
 ```bash
@@ -398,11 +368,8 @@ agent-browser dialog dismiss          # cancel
 ## Readiness & recovery
 
 The first `agent-browser open` in a session launches the headless-Chrome
-daemon; later commands reuse it. A daemon left idle for 3 minutes shuts itself
-down to free memory for the other agents, so an `open` after a long gap is a
-fresh browser rather than a resumed one — expect to re-navigate, and re-`state
-load` if you were logged in. Distinguish the failure modes and react differently
-— do **not** blindly re-run the same failing command in a loop:
+daemon; later commands reuse it. Distinguish the two failure modes and react
+differently — do **not** blindly re-run the same failing command in a loop:
 
 - **Daemon / connection failure** (`Failed to connect`, `connection refused`,
   socket missing, `browser not running`): the daemon isn't up or has died. Run

strix/tools/respond/tool.py

@@ -15,7 +15,7 @@ def _ctx(ctx: RunContextWrapper) -> dict[str, Any]:
 
 
 @function_tool
-async def respond_to_user(ctx: RunContextWrapper, message: str = "") -> str:
+async def respond_to_user(ctx: RunContextWrapper, message: str) -> str:
     """Answer the user and hand control back to them.
 
     This is the ONLY way to yield to the user. Delivering the message and
@@ -45,10 +45,6 @@ async def respond_to_user(ctx: RunContextWrapper, message: str = "") -> str:
             have followed the tool calls that led here. Lead with the
             answer or the decision you need, and if you are blocked, say
             exactly what you need from them.
-
-            Omit it when you have just said your piece as plain text and
-            only need to wait: that text has already reached them, and
-            repeating it makes them read the same answer twice.
     """
     inner = _ctx(ctx)
     coordinator = coordinator_from_context(inner)

strix/tools/todo/tools.py

@@ -110,19 +110,12 @@ def _get_agent_todos(agent_id: str) -> dict[str, dict[str, Any]]:
 
 
 def _normalize_priority(priority: str | None, default: str = "normal") -> str:
-    candidate = str(priority or default or "normal").strip().lower()
+    candidate = (priority or default or "normal").lower()
     if candidate not in VALID_PRIORITIES:
         raise ValueError(f"Invalid priority. Must be one of: {', '.join(VALID_PRIORITIES)}")
     return candidate
 
 
-def _coerce_priority(priority: str | None, default: str = "normal") -> str:
-    try:
-        return _normalize_priority(priority, default)
-    except ValueError:
-        return default
-
-
 def _sorted_todos(agent_id: str) -> list[dict[str, Any]]:
     todos_list = [
         {**todo, "todo_id": todo_id} for todo_id, todo in _get_agent_todos(agent_id).items()
@@ -292,16 +285,11 @@ async def create_todo(ctx: RunContextWrapper, todos: str) -> str:
             - ``description`` (str, optional): extra context or
               acceptance criteria.
             - ``priority`` (str, optional): one of ``"low"`` /
-              ``"normal"`` / ``"high"`` / ``"critical"``. Anything else,
-              including omitting it, falls back to ``"normal"`` rather
-              than failing.
+              ``"normal"`` / ``"high"`` / ``"critical"``. Defaults to
+              ``"normal"``.
 
             Example: ``[{"title": "Probe /admin", "priority": "high"},
             {"title": "Check JWT alg=none"}]``.
-
-        A title already on the list, or repeated within this call, is
-        skipped rather than duplicated; skipped titles come back under
-        ``skipped``.
     """
     agent_id = _agent_id_from(ctx)
     try:
@@ -314,21 +302,13 @@ async def create_todo(ctx: RunContextWrapper, todos: str) -> str:
             )
 
         agent_todos = _get_agent_todos(agent_id)
-        seen = {todo["title"].strip().lower() for todo in agent_todos.values()}
         created: list[dict[str, Any]] = []
-        skipped: list[dict[str, str]] = []
         for task in tasks:
-            title = task["title"]
-            key = title.lower()
-            if key in seen:
-                skipped.append({"title": title, "reason": "duplicate title"})
-                continue
-            seen.add(key)
-            task_priority = _coerce_priority(task.get("priority"))
+            task_priority = _normalize_priority(task.get("priority"))
             todo_id = str(uuid.uuid4())[:6]
             timestamp = datetime.now(UTC).isoformat()
             agent_todos[todo_id] = {
-                "title": title,
+                "title": task["title"],
                 "description": task.get("description"),
                 "priority": task_priority,
                 "status": "pending",
@@ -336,7 +316,7 @@ async def create_todo(ctx: RunContextWrapper, todos: str) -> str:
                 "updated_at": timestamp,
                 "completed_at": None,
             }
-            created.append({"todo_id": todo_id, "title": title, "priority": task_priority})
+            created.append({"todo_id": todo_id, "title": task["title"], "priority": task_priority})
     except (ValueError, TypeError) as e:
         return json.dumps(
             {"success": False, "error": f"Failed to create todo: {e}"},
@@ -350,7 +330,6 @@ async def create_todo(ctx: RunContextWrapper, todos: str) -> str:
             "success": True,
             "created": created,
             "created_count": len(created),
-            "skipped": skipped,
             "todos": _sorted_todos(agent_id),
             "total_count": len(_get_agent_todos(agent_id)),
         },

tests/test_agent_factory_tool_arguments.py

@@ -70,6 +70,7 @@ async def test_encoded_list_is_decoded_for_an_array_parameter(schema: dict[str,
         "auth",
         "Endpoint /admin leaks user data, and session tokens never expire",
         '"auth"',
+        "",
     ],
 )
 async def test_free_form_strings_are_never_split_into_an_array(value: str) -> None:
@@ -78,29 +79,6 @@ async def test_free_form_strings_are_never_split_into_an_array(value: str) -> No
     assert parsed["tags"] == value
 
 
-@pytest.mark.asyncio
-@pytest.mark.parametrize("schema", [_ARRAY, _NULLABLE_ARRAY])
-@pytest.mark.parametrize("value", ["", "   "])
-async def test_empty_string_becomes_an_empty_array(schema: dict[str, Any], value: str) -> None:
-    parsed = await _roundtrip(schema, {"tags": value})
-
-    assert parsed["tags"] == []
-
-
-@pytest.mark.asyncio
-async def test_empty_string_becomes_an_empty_object() -> None:
-    parsed = await _roundtrip(_OBJECT, {"modifications": ""})
-
-    assert parsed["modifications"] == {}
-
-
-@pytest.mark.asyncio
-async def test_empty_string_for_a_string_parameter_is_untouched() -> None:
-    parsed = await _roundtrip(_STRING, {"todos": ""})
-
-    assert parsed["todos"] == ""
-
-
 @pytest.mark.asyncio
 async def test_encoded_mapping_is_decoded_for_an_object_parameter() -> None:
     parsed = await _roundtrip(_OBJECT, {"modifications": '{"method": "POST"}'})

tests/test_auth_cli.py

@@ -2,28 +2,38 @@
 
 from __future__ import annotations
 
-import time
 from typing import TYPE_CHECKING, Any
 
 import pytest
 
-from strix.config import codex, opencode
+from strix.config import codex, grok
 from strix.interface import auth_cli
 
 
 if TYPE_CHECKING:
     from pathlib import Path
 
+_CHATGPT = auth_cli._PROVIDERS["chatgpt"]
+
 
 @pytest.fixture(autouse=True)
 def _tmp_store(tmp_path: Path, monkeypatch: pytest.MonkeyPatch) -> None:
-    monkeypatch.setattr(codex, "AUTH_PATH", tmp_path / "home" / ".strix" / "subscription-auth.json")
+    store = tmp_path / "home" / ".strix" / "subscription-auth.json"
+    monkeypatch.setattr(codex, "AUTH_PATH", store)
+    monkeypatch.setattr(grok, "AUTH_PATH", store)
 
 
-def test_login_provider_is_chatgpt() -> None:
-    assert auth_cli.LOGIN_PROVIDER == "chatgpt"
-    assert codex.PROVIDER in auth_cli._ACCEPTED_PROVIDERS
-    assert "chatgpt" in auth_cli._ACCEPTED_PROVIDERS
+def test_default_provider_is_chatgpt() -> None:
+    assert auth_cli._DEFAULT_PROVIDER == "chatgpt"
+    assert set(auth_cli._PROVIDERS) == {"chatgpt", "grok"}
+
+
+def test_provider_aliases_resolve() -> None:
+    assert auth_cli._resolve_provider(codex.PROVIDER) is _CHATGPT
+    assert auth_cli._resolve_provider("ChatGPT") is _CHATGPT
+    assert auth_cli._resolve_provider("grok") is auth_cli._PROVIDERS["grok"]
+    assert auth_cli._resolve_provider("xai") is auth_cli._PROVIDERS["grok"]
+    assert auth_cli._resolve_provider("gemini") is None
 
 
 def test_unknown_subcommand_returns_usage_error() -> None:
@@ -52,32 +62,32 @@ def test_finish_requires_state_on_loopback(monkeypatch: pytest.MonkeyPatch) -> N
 
     # Loopback (require_state=True): missing or mismatched state is rejected.
     with pytest.raises(codex.CodexAuthError) as missing:
-        auth_cli._finish("code", None, "verifier", "expected", require_state=True)
+        auth_cli._finish(_CHATGPT, "code", None, "verifier", "expected", require_state=True)
     assert missing.value.code == "state_mismatch"
     with pytest.raises(codex.CodexAuthError) as mismatch:
-        auth_cli._finish("code", "wrong", "verifier", "expected", require_state=True)
+        auth_cli._finish(_CHATGPT, "code", "wrong", "verifier", "expected", require_state=True)
     assert mismatch.value.code == "state_mismatch"
 
     # Matching state proceeds to the exchange.
-    assert auth_cli._finish("code", "expected", "verifier", "expected", require_state=True) == {
-        "ok": True
-    }
+    assert auth_cli._finish(
+        _CHATGPT, "code", "expected", "verifier", "expected", require_state=True
+    ) == {"ok": True}
 
 
 def test_finish_manual_paste_allows_absent_state(monkeypatch: pytest.MonkeyPatch) -> None:
     monkeypatch.setattr(codex, "exchange_code", lambda *_: {"ok": True})
     # Manual paste (require_state=False): a bare code with no state is accepted,
     # but a present-and-wrong state is still rejected.
-    assert auth_cli._finish("code", None, "verifier", "expected", require_state=False) == {
-        "ok": True
-    }
+    assert auth_cli._finish(
+        _CHATGPT, "code", None, "verifier", "expected", require_state=False
+    ) == {"ok": True}
     with pytest.raises(codex.CodexAuthError):
-        auth_cli._finish("code", "wrong", "verifier", "expected", require_state=False)
+        auth_cli._finish(_CHATGPT, "code", "wrong", "verifier", "expected", require_state=False)
 
 
 def test_finish_rejects_missing_code() -> None:
     with pytest.raises(codex.CodexAuthError) as exc:
-        auth_cli._finish(None, "expected", "verifier", "expected", require_state=True)
+        auth_cli._finish(_CHATGPT, None, "expected", "verifier", "expected", require_state=True)
     assert exc.value.code == "no_code"
 
 
@@ -85,6 +95,31 @@ def test_model_subcommand_removed() -> None:
     assert auth_cli.run_auth(["model", "gpt-5.5"]) == 2
 
 
+def _sign_in_both() -> None:
+    codex.save_record({"type": "oauth", "access": "c", "refresh": "r", "account_id": "a"})
+    grok.save_record({"type": "oauth", "access": "g", "refresh": "r"})
+
+
+def test_logout_all_removes_every_provider() -> None:
+    _sign_in_both()
+    assert codex.is_authenticated()
+    assert grok.is_authenticated()
+
+    assert auth_cli.run_auth(["logout"]) == 0
+
+    assert not codex.is_authenticated()
+    assert not grok.is_authenticated()
+
+
+def test_logout_single_provider_leaves_the_other() -> None:
+    _sign_in_both()
+
+    assert auth_cli.run_auth(["logout", "grok"]) == 0
+
+    assert codex.is_authenticated()
+    assert not grok.is_authenticated()
+
+
 @pytest.mark.parametrize("provider", ["chatgpt", "codex", "ChatGPT"])
 def test_login_accepts_provider_aliases(provider: str, monkeypatch: pytest.MonkeyPatch) -> None:
     reached = {"flow": False}
@@ -105,60 +140,3 @@ def test_login_accepts_provider_aliases(provider: str, monkeypatch: pytest.Monke
 
     assert auth_cli.run_auth(["login", provider]) == 0
     assert reached["flow"] is True
-
-
-@pytest.mark.parametrize("provider", ["opencode", "OpenCode", "opencode-go", "zen"])
-def test_login_accepts_opencode_aliases(provider: str, monkeypatch: pytest.MonkeyPatch) -> None:
-    reached = {"login": False}
-
-    def _fake_login(_console: Any) -> int:
-        reached["login"] = True
-        return 0
-
-    monkeypatch.setattr(auth_cli, "_login_opencode", _fake_login)
-    assert auth_cli.run_auth(["login", provider]) == 0
-    assert reached["login"] is True
-
-
-def test_login_opencode_validates_and_saves(monkeypatch: pytest.MonkeyPatch) -> None:
-    saved: dict[str, str] = {}
-    monkeypatch.setattr("rich.console.Console.input", lambda _self, *_a, **_k: "  sk-oc-test  ")
-    monkeypatch.setattr(opencode, "validate_api_key", lambda key: saved.setdefault("checked", key))
-    monkeypatch.setattr(opencode, "save_api_key", lambda key: saved.setdefault("key", key))
-
-    assert auth_cli.run_auth(["login", "opencode"]) == 0
-    assert saved == {"checked": "sk-oc-test", "key": "sk-oc-test"}
-
-
-def test_login_opencode_rejects_bad_key(monkeypatch: pytest.MonkeyPatch) -> None:
-    monkeypatch.setattr("rich.console.Console.input", lambda _self, *_a, **_k: "bad")
-
-    def _reject(_key: str) -> None:
-        raise opencode.OpencodeAuthError("invalid_key")
-
-    monkeypatch.setattr(opencode, "validate_api_key", _reject)
-    assert auth_cli.run_auth(["login", "opencode"]) == 1
-    assert opencode.is_authenticated() is False
-
-
-def test_logout_provider_scoped() -> None:
-    codex.save_record(
-        {
-            "type": "oauth",
-            "provider": "codex",
-            "access": "a",
-            "refresh": "r",
-            "account_id": "acct",
-            "expires_at": time.time() + 3600,
-        }
-    )
-    opencode.save_api_key("sk-oc-test")
-
-    assert auth_cli.run_auth(["logout", "opencode"]) == 0
-    assert opencode.is_authenticated() is False
-    assert codex.is_authenticated() is True
-
-    assert auth_cli.run_auth(["logout"]) == 0
-    assert codex.is_authenticated() is False
-
-    assert auth_cli.run_auth(["logout", "bogus"]) == 2

tests/test_cost_tracking.py

@@ -143,7 +143,7 @@ def test_cost_callback_estimates_cost_with_bare_model_fallback() -> None:
     }
 
     def fake_completion_cost(**kwargs: object) -> float:
-        if kwargs["model"] == "openai/gpt-4o-mini":
+        if kwargs["model"] == "gpt-4o-mini":
             return 0.025
         raise ValueError(kwargs["model"])
 

tests/test_execution.py

@@ -1228,40 +1228,3 @@ async def test_wait_kind_survives_a_snapshot_round_trip() -> None:
     assert restored.wait_kinds["root"] == "user"
     assert restored.idle_resume_counts["root"] == 1
     assert await execution._plain_waiting_timeout(restored, "root") is None
-
-
-@pytest.mark.asyncio
-async def test_interactive_nudge_offers_waiting_without_repeating() -> None:
-    """The nudge is the instruction an agent reads when it is stranded here.
-
-    It is where the option to wait on what was already said has to be, not only
-    in the system prompt: an agent that ended a turn on plain text reasons off
-    this text, and without the clause it restates its answer to reach a tool
-    call, so the user reads it twice.
-
-    The clause holds whatever the turn did, because the agent is the one who
-    knows whether it spoke — this fires for a turn that produced no text at all.
-    """
-    items = await execution._append_tool_required_message(
-        session=None,
-        context={"parent_id": None},
-        attempt=1,
-        limit=3,
-        interactive=True,
-    )
-
-    assert "with no message if you have already said it" in items[0]["content"]
-
-
-@pytest.mark.asyncio
-async def test_autonomous_nudge_does_not_offer_the_user() -> None:
-    """There is nobody attached to an autonomous run to wait for."""
-    items = await execution._append_tool_required_message(
-        session=None,
-        context={"parent_id": None},
-        attempt=1,
-        limit=3,
-        interactive=False,
-    )
-
-    assert "respond_to_user" not in items[0]["content"]

tests/test_grok_auth.py

@@ -0,0 +1,265 @@
+"""Tests for Grok (xAI) subscription auth: PKCE, token handling, store."""
+
+from __future__ import annotations
+
+import base64
+import hashlib
+import json
+import time
+from typing import TYPE_CHECKING, Any
+from unittest import mock
+
+import pytest
+import requests
+
+from strix.config import grok
+
+
+if TYPE_CHECKING:
+    from pathlib import Path
+
+
+@pytest.fixture(autouse=True)
+def _tmp_store(tmp_path: Path, monkeypatch: pytest.MonkeyPatch) -> Path:
+    path = tmp_path / "home" / ".strix" / "subscription-auth.json"
+    monkeypatch.setattr(grok, "AUTH_PATH", path)
+    return path
+
+
+def test_pkce_challenge_matches_verifier_and_is_unpadded() -> None:
+    verifier, challenge = grok.generate_pkce()
+    expected = (
+        base64.urlsafe_b64encode(hashlib.sha256(verifier.encode()).digest()).rstrip(b"=").decode()
+    )
+    assert challenge == expected
+    assert "=" not in verifier
+    assert "=" not in challenge
+
+
+def test_authorize_url_carries_pkce_client_and_grok_scope() -> None:
+    url = grok.build_authorize_url("chal", "st8")
+    assert grok.AUTHORIZE_URL in url
+    assert "code_challenge=chal" in url
+    assert "code_challenge_method=S256" in url
+    assert f"client_id={grok.CLIENT_ID}" in url
+    assert "state=st8" in url
+    # The Grok-CLI scope is what unlocks subscription inference.
+    assert "grok-cli%3Aaccess" in url
+    assert "offline_access" in url
+
+
+def test_redirect_uri_is_loopback() -> None:
+    assert grok.REDIRECT_URI == "http://127.0.0.1:56121/callback"
+
+
+def test_post_form_returns_parsed_body() -> None:
+    resp = mock.MagicMock()
+    resp.status_code = 200
+    resp.content = b'{"access_token": "tok"}'
+
+    with mock.patch.object(requests, "post", return_value=resp) as post:
+        data = grok._post_form({"grant_type": "refresh_token"})
+
+    assert data == {"access_token": "tok"}
+    assert post.call_args.kwargs["timeout"] == grok._TOKEN_TIMEOUT
+
+
+def test_post_form_raises_on_http_error() -> None:
+    resp = mock.MagicMock()
+    resp.status_code = 400
+    resp.text = "invalid_grant"
+
+    with (
+        mock.patch.object(requests, "post", return_value=resp),
+        pytest.raises(grok.GrokAuthError) as exc,
+    ):
+        grok._post_form({"grant_type": "refresh_token"})
+    assert exc.value.code == "token_http_error"
+
+
+@pytest.mark.parametrize(
+    ("value", "expected"),
+    [
+        ("http://127.0.0.1:56121/callback?code=AAA&state=BBB", ("AAA", "BBB")),
+        ("AAA#BBB", ("AAA", "BBB")),
+        ("code=AAA&state=BBB", ("AAA", "BBB")),
+        ("AAA", ("AAA", None)),
+        ("", (None, None)),
+    ],
+)
+def test_parse_redirect_input(value: str, expected: tuple[str | None, str | None]) -> None:
+    assert grok.parse_redirect_input(value) == expected
+
+
+@pytest.mark.parametrize(
+    ("model", "expected"),
+    [
+        ("grok/grok-4", "grok-4"),
+        ("Grok/Grok-4", "Grok-4"),
+        ("  grok/grok-4  ", "grok-4"),
+        ("xai/grok-4", None),  # metered API path
+        ("chatgpt/gpt-5.4", None),
+        ("grok-4", None),
+        ("grok/", None),
+        ("", None),
+        (None, None),
+    ],
+)
+def test_subscription_model(model: str | None, expected: str | None) -> None:
+    assert grok.subscription_model(model) == expected
+
+
+def test_auth_mode() -> None:
+    assert grok.auth_mode("grok/grok-4") == "subscription"
+    assert grok.auth_mode("xai/grok-4") == "api_key"
+    assert grok.auth_mode("chatgpt/gpt-5.4") == "api_key"
+    assert grok.auth_mode(None) == "api_key"
+
+
+def _record(access: str, refresh: str, expires_at: float) -> dict[str, Any]:
+    return {
+        "type": "oauth",
+        "provider": "grok",
+        "access": access,
+        "refresh": refresh,
+        "expires_at": expires_at,
+    }
+
+
+def test_store_roundtrip_and_logout() -> None:
+    assert grok.read_record() is None
+    assert grok.is_authenticated() is False
+
+    grok.save_record(_record("a1", "r1", time.time() + 3600))
+    record = grok.read_record()
+    assert record is not None
+    assert record["access"] == "a1"
+    assert grok.is_authenticated() is True
+
+    grok.logout()
+    assert grok.read_record() is None
+    grok.logout()  # no-op when already gone
+
+
+def test_store_file_permissions_are_owner_only(_tmp_store: Path) -> None:
+    grok.save_record(_record("a1", "r1", time.time() + 3600))
+    assert (_tmp_store.stat().st_mode & 0o777) == 0o600
+
+
+def test_store_shares_file_with_other_providers(_tmp_store: Path) -> None:
+    # Grok must not clobber a co-resident ChatGPT record in the shared store.
+    _tmp_store.parent.mkdir(parents=True, exist_ok=True)
+    _tmp_store.write_text(json.dumps({"codex": {"type": "oauth", "access": "x"}}))
+
+    grok.save_record(_record("a1", "r1", time.time() + 3600))
+    on_disk = json.loads(_tmp_store.read_text())
+    assert on_disk["codex"] == {"type": "oauth", "access": "x"}
+    assert on_disk["grok"]["access"] == "a1"
+
+    grok.logout()
+    # Removing grok leaves the other provider's record and the file intact.
+    assert json.loads(_tmp_store.read_text()) == {"codex": {"type": "oauth", "access": "x"}}
+
+
+def test_read_record_rejects_incomplete_records() -> None:
+    grok.save_record({"type": "oauth", "access": "a"})  # missing refresh
+    assert grok.read_record() is None
+    assert grok.is_authenticated() is False
+
+
+def test_get_valid_token_returns_stored_when_fresh(monkeypatch: pytest.MonkeyPatch) -> None:
+    def _boom(_payload: dict[str, str]) -> dict[str, Any]:
+        msg = "should not refresh a fresh token"
+        raise AssertionError(msg)
+
+    monkeypatch.setattr(grok, "_post_form", _boom)
+    grok.save_record(_record("access-fresh", "r1", time.time() + 3600))
+    assert grok.get_valid_token() == "access-fresh"
+
+
+def test_get_valid_token_refreshes_and_persists_rotation(monkeypatch: pytest.MonkeyPatch) -> None:
+    calls = {"n": 0}
+
+    def _fake_post(payload: dict[str, str]) -> dict[str, Any]:
+        calls["n"] += 1
+        assert payload["grant_type"] == "refresh_token"
+        assert payload["refresh_token"] == "r1"
+        return {"access_token": "access-new", "refresh_token": "r2", "expires_in": 3600}
+
+    monkeypatch.setattr(grok, "_post_form", _fake_post)
+    grok.save_record(_record("stale", "r1", time.time() - 10))  # already expired
+
+    assert grok.get_valid_token() == "access-new"
+    assert calls["n"] == 1
+    record = grok.read_record()
+    assert record is not None
+    assert record["refresh"] == "r2"  # rotated refresh written back
+
+
+def test_refresh_keeps_old_refresh_when_response_omits_it(monkeypatch: pytest.MonkeyPatch) -> None:
+    def _fake_post(_payload: dict[str, str]) -> dict[str, Any]:
+        return {"access_token": "access-new", "expires_in": 3600}  # no refresh_token
+
+    monkeypatch.setattr(grok, "_post_form", _fake_post)
+    grok.save_record(_record("stale", "r1", time.time() - 10))
+
+    assert grok.get_valid_token() == "access-new"
+    record = grok.read_record()
+    assert record is not None
+    assert record["refresh"] == "r1"  # fell back to the prior refresh token
+
+
+def test_get_valid_token_uses_token_rotated_by_another_process(
+    monkeypatch: pytest.MonkeyPatch,
+) -> None:
+    records = [
+        _record("stale", "r1", time.time() - 10),
+        _record("fresh-from-other-process", "r2", time.time() + 3600),
+    ]
+    calls = {"n": 0}
+
+    def _fake_read() -> dict[str, Any]:
+        record = records[min(calls["n"], len(records) - 1)]
+        calls["n"] += 1
+        return record
+
+    def _boom(_payload: dict[str, str]) -> dict[str, Any]:
+        msg = "must not refresh a token another process already rotated"
+        raise AssertionError(msg)
+
+    monkeypatch.setattr(grok, "read_record", _fake_read)
+    monkeypatch.setattr(grok, "_post_form", _boom)
+
+    assert grok.get_valid_token() == "fresh-from-other-process"
+
+
+def test_get_valid_token_recovers_when_refresh_loses_race(
+    monkeypatch: pytest.MonkeyPatch,
+) -> None:
+    grok.save_record(_record("stale", "r1", time.time() - 10))
+
+    def _fake_post(_payload: dict[str, str]) -> dict[str, Any]:
+        grok.save_record(_record("fresh-from-peer", "r2", time.time() + 3600))
+        raise grok.GrokAuthError("token_http_error", "HTTP 400: invalid_grant")
+
+    monkeypatch.setattr(grok, "_post_form", _fake_post)
+    assert grok.get_valid_token() == "fresh-from-peer"
+
+
+def test_get_valid_token_reraises_refresh_error_without_rotation(
+    monkeypatch: pytest.MonkeyPatch,
+) -> None:
+    grok.save_record(_record("stale", "r1", time.time() - 10))
+
+    def _fake_post(_payload: dict[str, str]) -> dict[str, Any]:
+        raise grok.GrokAuthError("token_http_error", "HTTP 400: invalid_grant")
+
+    monkeypatch.setattr(grok, "_post_form", _fake_post)
+    with pytest.raises(grok.GrokAuthError):
+        grok.get_valid_token()
+
+
+def test_get_valid_token_raises_when_not_signed_in() -> None:
+    with pytest.raises(grok.GrokAuthError) as exc:
+        grok.get_valid_token()
+    assert exc.value.code == "not_authenticated"

tests/test_grok_routing.py

@@ -0,0 +1,102 @@
+"""Grok subscription routing through StrixProvider.get_model."""
+
+from __future__ import annotations
+
+import argparse
+from unittest import mock
+
+from agents.models.openai_chatcompletions import OpenAIChatCompletionsModel
+
+from strix.config import grok, subscription
+from strix.config.models import StrixProvider, _TurnGuardModel
+from strix.interface import scan_setup, utils
+from strix.report import state as state_mod
+
+
+def test_grok_prefix_routes_to_chat_completions(monkeypatch) -> None:  # type: ignore[no-untyped-def]
+    client = mock.MagicMock()
+    monkeypatch.setattr(grok, "get_subscription_client", lambda: client)
+
+    model = StrixProvider().get_model("grok/grok-4")
+
+    assert isinstance(model, _TurnGuardModel)
+    assert isinstance(model._inner, OpenAIChatCompletionsModel)
+    # The provider strips the grok/ prefix and passes xAI's bare model slug.
+    assert model._inner.model == "grok-4"
+
+
+def test_non_subscription_model_is_not_hijacked_by_grok(monkeypatch) -> None:  # type: ignore[no-untyped-def]
+    def _boom() -> object:
+        msg = "grok client must not be built for a non-grok model"
+        raise AssertionError(msg)
+
+    monkeypatch.setattr(grok, "get_subscription_client", _boom)
+
+    # A metered xai/* key model must fall through to the normal provider path,
+    # not the subscription route.
+    model = StrixProvider().get_model("xai/grok-4")
+    assert isinstance(model, _TurnGuardModel)
+    assert not isinstance(model._inner, OpenAIChatCompletionsModel)
+
+
+def test_provider_label_names_the_subscription() -> None:
+    assert subscription.provider_label("grok/grok-4") == "Grok"
+    assert subscription.provider_label("chatgpt/gpt-5.4") == "ChatGPT"
+    # Metered API-key models are not subscriptions.
+    assert subscription.provider_label("xai/grok-4") is None
+    assert subscription.provider_label("openai/gpt-5.4") is None
+
+
+def test_run_record_reports_grok_provider(monkeypatch) -> None:  # type: ignore[no-untyped-def]
+    settings = mock.MagicMock()
+    settings.llm.model = "grok/grok-4"
+    monkeypatch.setattr(state_mod, "load_settings", lambda: settings)
+
+    record = state_mod.ReportState(run_name="run-test").run_record
+    assert record["auth_mode"] == "subscription"
+    assert record["subscription_provider"] == "Grok"
+
+
+def test_subscription_label_prefers_persisted_provider(monkeypatch) -> None:  # type: ignore[no-untyped-def]
+    settings = mock.MagicMock()
+    settings.llm.model = "chatgpt/gpt-5.4"  # current settings point at ChatGPT
+    monkeypatch.setattr(utils, "load_settings", lambda: settings)
+
+    # A resumed Grok run keeps its persisted provider even though settings changed.
+    resumed = mock.MagicMock(
+        run_record={"auth_mode": "subscription", "subscription_provider": "Grok"}
+    )
+    assert utils._subscription_label(resumed) == "Grok subscription"
+
+    # With no persisted provider, it derives the label from settings (not a
+    # hardcoded default).
+    fresh = mock.MagicMock(run_record={})
+    assert utils._subscription_label(fresh) == "ChatGPT subscription"
+
+
+def test_persisted_run_record_carries_provider(tmp_path, monkeypatch) -> None:  # type: ignore[no-untyped-def]
+    settings = mock.MagicMock()
+    settings.llm.model = "grok/grok-4"
+    monkeypatch.setattr(scan_setup, "load_settings", lambda: settings)
+    monkeypatch.setattr(scan_setup, "run_dir_for", lambda _name: tmp_path)
+    captured: dict[str, object] = {}
+    monkeypatch.setattr(
+        "strix.report.writer.write_run_record", lambda _dir, rec: captured.update(rec)
+    )
+
+    args = argparse.Namespace(
+        run_name="run-test",
+        targets_info=[],
+        scan_mode="scan",
+        instruction=None,
+        non_interactive=True,
+        local_sources=[],
+        diff_scope={"active": False},
+        scope_mode="mode",
+        diff_base=None,
+    )
+    scan_setup._persist_run_record(args)
+
+    # The resume/viewer record must carry the provider so resumed runs stay labeled.
+    assert captured["auth_mode"] == "subscription"
+    assert captured["subscription_provider"] == "Grok"

tests/test_inputs.py

@@ -111,13 +111,6 @@ def test_make_model_settings_no_prompt_cache_for_non_claude(model_name: str) ->
     assert make_model_settings(None, model_name=model_name).extra_args is None
 
 
-@pytest.mark.parametrize("model_name", ["opencode/claude-sonnet-5", "opencode-go/claude-sonnet-5"])
-def test_no_prompt_cache_for_opencode_claude(model_name: str) -> None:
-    # The OpenCode route uses the raw OpenAI SDK, whose create() rejects the
-    # LiteLLM-only cache_control_injection_points argument.
-    assert _cache_points(model_name) is None
-
-
 def test_no_prompt_cache_for_unmapped_bedrock_claude_model(monkeypatch: Any) -> None:
     # A Bedrock Claude model LiteLLM hasn't mapped must run uncached, not crash.
     unmapped = "bedrock/global.anthropic.claude-brand-new-9"
@@ -306,16 +299,6 @@ def test_make_model_settings_forces_required_for_anyllm_routed_openai_model() ->
     assert settings.tool_choice == "required"
 
 
-def test_make_model_settings_disables_parallel_tool_calls_by_default() -> None:
-    assert make_model_settings("none", model_name="gpt-4o").parallel_tool_calls is False
-
-
-def test_make_model_settings_omits_parallel_tool_calls_without_tools() -> None:
-    settings = make_model_settings("none", model_name="gpt-4o", has_tools=False)
-
-    assert settings.parallel_tool_calls is None
-
-
 def test_make_model_settings_sets_request_timeout() -> None:
     settings = make_model_settings(
         "none",
@@ -368,32 +351,3 @@ def test_make_model_settings_timeout_survives_reasoning_resolve() -> None:
 
     assert settings.extra_args is not None
     assert settings.extra_args["timeout"] == 120.0
-
-
-def test_openrouter_attribution_rides_on_the_request_headers() -> None:
-    # litellm.headers is ignored once a request carries any header of its own,
-    # so the attribution must be part of the per-request headers.
-    headers = make_model_settings(
-        None, model_name="openrouter/anthropic/claude-sonnet-4-5"
-    ).extra_headers
-    assert headers == {
-        "HTTP-Referer": "https://strix.ai",
-        "X-Title": "Strix",
-        "X-OpenRouter-Categories": "cli-agent",
-    }
-
-
-def test_openrouter_attribution_absent_for_other_providers() -> None:
-    assert make_model_settings(None, model_name="anthropic/claude-sonnet-4-5").extra_headers is None
-
-
-def test_user_headers_override_openrouter_attribution() -> None:
-    headers = make_model_settings(
-        None,
-        model_name="openrouter/anthropic/claude-sonnet-4-5",
-        extra_headers={"X-Title": "Custom", "X-Tenant": "acme"},
-    ).extra_headers
-    assert headers is not None
-    assert headers["X-Title"] == "Custom"
-    assert headers["X-Tenant"] == "acme"
-    assert headers["HTTP-Referer"] == "https://strix.ai"

tests/test_models.py

@@ -66,11 +66,6 @@ def test_recommended_models_are_matched_case_insensitively() -> None:
         "moonshot/kimi-k2.6",
         "kimi-k2.7-code",
         "moonshot/kimi-k3",
-        "opencode/gpt-5.4",
-        "opencode/claude-sonnet-5",
-        "opencode-go/kimi-k3",
-        "opencode-go/deepseek-v4-flash",
-        "opencode-go/qwen3.8-max",
     ],
 )
 def test_frontier_model_families_are_accepted(model_name: str) -> None:

tests/test_opencode_auth.py

@@ -1,133 +0,0 @@
-"""Tests for OpenCode (Zen/Go) subscription auth: prefix parsing and key store."""
-
-from __future__ import annotations
-
-from typing import TYPE_CHECKING
-from unittest import mock
-
-import pytest
-import requests
-
-from strix.config import codex, opencode
-
-
-if TYPE_CHECKING:
-    from pathlib import Path
-
-
-@pytest.fixture(autouse=True)
-def _tmp_store(tmp_path: Path, monkeypatch: pytest.MonkeyPatch) -> Path:
-    path = tmp_path / "home" / ".strix" / "subscription-auth.json"
-    monkeypatch.setattr(codex, "AUTH_PATH", path)
-    return path
-
-
-@pytest.mark.parametrize(
-    ("model", "slug", "base_url", "uses_responses"),
-    [
-        ("opencode/claude-sonnet-5", "claude-sonnet-5", opencode.ZEN_BASE_URL, False),
-        ("opencode/gpt-5.4", "gpt-5.4", opencode.ZEN_BASE_URL, True),
-        ("opencode/grok-4.5", "grok-4.5", opencode.ZEN_BASE_URL, True),
-        ("OpenCode/Kimi-K3", "Kimi-K3", opencode.ZEN_BASE_URL, False),
-        ("opencode-go/kimi-k3", "kimi-k3", opencode.GO_BASE_URL, False),
-        ("opencode-go/gpt-5.6-luna", "gpt-5.6-luna", opencode.GO_BASE_URL, True),
-        ("opencode-go/grok-4.5", "grok-4.5", opencode.GO_BASE_URL, False),
-    ],
-)
-def test_subscription_model_parses_prefixes(
-    model: str, slug: str, base_url: str, uses_responses: bool
-) -> None:
-    parsed = opencode.subscription_model(model)
-    assert parsed is not None
-    assert parsed.slug == slug
-    assert parsed.base_url == base_url
-    assert parsed.uses_responses == uses_responses
-
-
-@pytest.mark.parametrize(
-    "model",
-    ["openai/gpt-5.4", "chatgpt/gpt-5.4", "opencode/", "opencode-go/", "opencode", "", None],
-)
-def test_subscription_model_rejects_non_opencode(model: str | None) -> None:
-    assert opencode.subscription_model(model) is None
-
-
-def test_store_roundtrip_and_logout() -> None:
-    assert opencode.read_record() is None
-    assert opencode.is_authenticated() is False
-
-    opencode.save_api_key("sk-oc-test")
-    record = opencode.read_record()
-    assert record is not None
-    assert record["key"] == "sk-oc-test"
-    assert opencode.is_authenticated() is True
-    assert opencode.get_api_key() == "sk-oc-test"
-
-    opencode.logout()
-    assert opencode.read_record() is None
-    opencode.logout()  # no-op when already gone
-
-
-def test_store_coexists_with_chatgpt_record() -> None:
-    codex.save_record({"type": "oauth", "access": "a", "refresh": "r", "account_id": "acct"})
-    opencode.save_api_key("sk-oc-test")
-
-    assert codex.read_record() is not None
-    assert opencode.get_api_key() == "sk-oc-test"
-
-    opencode.logout()
-    assert codex.read_record() is not None
-    assert opencode.read_record() is None
-
-
-def test_get_api_key_raises_when_not_signed_in() -> None:
-    with pytest.raises(opencode.OpencodeAuthError) as exc:
-        opencode.get_api_key()
-    assert exc.value.code == "not_authenticated"
-
-
-def test_auth_mode_covers_both_subscriptions() -> None:
-    assert opencode.auth_mode("opencode/claude-sonnet-5") == "subscription"
-    assert opencode.auth_mode("opencode-go/kimi-k3") == "subscription"
-    assert opencode.auth_mode("chatgpt/gpt-5.4") == "subscription"
-    assert opencode.auth_mode("openai/gpt-5.4") == "api_key"
-    assert opencode.auth_mode(None) == "api_key"
-
-
-def test_subscription_provider() -> None:
-    assert opencode.subscription_provider("opencode/claude-sonnet-5") == "opencode"
-    assert opencode.subscription_provider("opencode-go/kimi-k3") == "opencode"
-    assert opencode.subscription_provider("chatgpt/gpt-5.4") == "chatgpt"
-    assert opencode.subscription_provider("openai/gpt-5.4") is None
-    assert opencode.subscription_provider(None) is None
-
-
-def _response(status_code: int, text: str = "") -> mock.MagicMock:
-    response = mock.MagicMock()
-    response.status_code = status_code
-    response.text = text
-    return response
-
-
-def test_validate_api_key_accepts_ok() -> None:
-    with mock.patch.object(requests, "get", return_value=_response(200)) as get:
-        opencode.validate_api_key("sk-oc-test")
-    assert get.call_args.kwargs["headers"]["Authorization"] == "Bearer sk-oc-test"
-
-
-def test_validate_api_key_rejects_unauthorized() -> None:
-    with (
-        mock.patch.object(requests, "get", return_value=_response(401)),
-        pytest.raises(opencode.OpencodeAuthError) as exc,
-    ):
-        opencode.validate_api_key("bad-key")
-    assert exc.value.code == "invalid_key"
-
-
-def test_validate_api_key_maps_network_errors() -> None:
-    with (
-        mock.patch.object(requests, "get", side_effect=requests.ConnectionError("boom")),
-        pytest.raises(opencode.OpencodeAuthError) as exc,
-    ):
-        opencode.validate_api_key("sk-oc-test")
-    assert exc.value.code == "unavailable"

tests/test_pricing.py

@@ -1,120 +0,0 @@
-from __future__ import annotations
-
-from unittest.mock import patch
-
-import litellm
-from agents.usage import Usage
-
-from strix.report.pricing import resolve_litellm_model
-from strix.report.usage import LLMUsageLedger
-
-
-def test_resolves_common_bare_model_names() -> None:
-    resolve_litellm_model.cache_clear()
-    assert resolve_litellm_model("deepseek-v4-flash") == "deepseek/deepseek-v4-flash"
-    assert resolve_litellm_model("openai/deepseek-v4-flash") == "deepseek/deepseek-v4-flash"
-    assert resolve_litellm_model("grok-4.5") == "xai/grok-4.5"
-    assert resolve_litellm_model("MiniMax-M3") == "minimax/MiniMax-M3"
-
-
-def test_resolver_returns_none_for_unresolvable_model() -> None:
-    resolve_litellm_model.cache_clear()
-    assert resolve_litellm_model("provider/not-a-real-model") is None
-
-
-def test_ledger_uses_estimate_when_routed_provider_reports_no_cost() -> None:
-    usage = Usage()
-    usage.requests = 1
-    usage.input_tokens = 1000
-    usage.output_tokens = 200
-    usage.total_tokens = 1200
-    ledger = LLMUsageLedger()
-
-    with patch("litellm.completion_cost", return_value=0.42):
-        ledger.record(agent_id="a", usage=usage, model="openai/deepseek-v4-flash")
-
-    assert ledger.total_cost == 0.42
-
-
-def test_ledger_prefers_observed_cost_over_estimate() -> None:
-    usage = Usage()
-    usage.requests = 1
-    usage.input_tokens = 1000
-    usage.output_tokens = 200
-    usage.total_tokens = 1200
-    ledger = LLMUsageLedger()
-
-    with patch("litellm.completion_cost", return_value=0.42):
-        ledger.record(agent_id="a", usage=usage, model="openai/deepseek-v4-flash")
-    ledger.record_observed_cost(0.17)
-
-    assert ledger.total_cost == 0.17
-
-
-def test_hydrated_estimate_continues_accumulating_new_estimates() -> None:
-    usage = Usage()
-    usage.requests = 1
-    usage.input_tokens = 1000
-    usage.output_tokens = 200
-    usage.total_tokens = 1200
-    ledger = LLMUsageLedger()
-    ledger.hydrate({"cost": 0.42})
-
-    with patch("litellm.completion_cost", return_value=0.17):
-        ledger.record(agent_id="a", usage=usage, model="openai/deepseek-v4-flash")
-
-    assert ledger.total_cost == 0.59
-
-
-def test_zero_cost_disables_both_observed_and_estimated_costs() -> None:
-    usage = Usage()
-    usage.requests = 1
-    usage.input_tokens = 1000
-    usage.output_tokens = 200
-    usage.total_tokens = 1200
-    ledger = LLMUsageLedger()
-    ledger.zero_cost = True
-
-    with patch("litellm.completion_cost", return_value=0.42) as estimate:
-        ledger.record(agent_id="a", usage=usage, model="deepseek-v4-flash")
-        ledger.record_observed_cost(1.0)
-
-    estimate.assert_not_called()
-    assert ledger.total_cost == 0.0
-
-
-def test_resolver_uses_provider_when_bare_entry_has_one() -> None:
-    original = litellm.model_cost
-    litellm.model_cost = {
-        "example": {
-            "litellm_provider": "example-provider",
-            "input_cost_per_token": 1.0,
-            "output_cost_per_token": 2.0,
-        }
-    }
-    try:
-        resolve_litellm_model.cache_clear()
-        assert resolve_litellm_model("example") == "example-provider/example"
-    finally:
-        litellm.model_cost = original
-        resolve_litellm_model.cache_clear()
-
-
-def test_resolver_does_not_guess_between_differently_priced_providers() -> None:
-    original = litellm.model_cost
-    litellm.model_cost = {
-        "provider-a/example": {
-            "input_cost_per_token": 1.0,
-            "output_cost_per_token": 2.0,
-        },
-        "provider-b/example": {
-            "input_cost_per_token": 3.0,
-            "output_cost_per_token": 4.0,
-        },
-    }
-    try:
-        resolve_litellm_model.cache_clear()
-        assert resolve_litellm_model("example") is None
-    finally:
-        litellm.model_cost = original
-        resolve_litellm_model.cache_clear()

tests/test_respond_to_user.py

@@ -64,31 +64,3 @@ async def test_a_message_that_already_arrived_is_taken_instead_of_parking() -> N
     assert result["wait_outcome"] == "message_arrived"
     assert result["pending_messages"] == 1
     assert coordinator.statuses["root"] == "running"
-
-
-async def _call_without_message(context: dict[str, Any]) -> dict[str, Any]:
-    ctx = ToolContext(
-        context=context,
-        tool_name="respond_to_user",
-        tool_call_id="call-1",
-        tool_arguments="{}",
-    )
-    raw = await respond_to_user.on_invoke_tool(ctx, "{}")
-    return json.loads(raw)  # type: ignore[no-any-return]
-
-
-@pytest.mark.asyncio
-async def test_parks_without_a_message() -> None:
-    """An agent that has already said its piece as plain text can just wait.
-
-    The nudge is what leaves it here, and while a message was required the only
-    way to stop was to send the same answer a second time.
-    """
-    context = await _context(interactive=True)
-
-    result = await _call_without_message(context)
-
-    assert result["success"] is True
-    assert result["wait_outcome"] == "waiting"
-    assert result["message"] == ""
-    assert context["coordinator"].statuses["root"] == "waiting"

tests/test_runner_interrupt.py

@@ -1,108 +0,0 @@
-from __future__ import annotations
-
-import asyncio
-import types
-from typing import Any
-
-import pytest
-from agents import ModelSettings
-
-import strix.tools.notes.tools as notes_tools
-import strix.tools.todo.tools as todo_tools
-from strix.core import runner
-from strix.core.agents import AgentCoordinator
-from strix.runtime import session_manager
-
-
-def _wire_runner(monkeypatch: pytest.MonkeyPatch, tmp_path: Any) -> None:
-    monkeypatch.setattr(runner, "run_dir_for", lambda _scan_id: tmp_path)
-    monkeypatch.setattr(runner, "runtime_state_dir", lambda _run_dir: tmp_path)
-    monkeypatch.setattr(runner, "setup_scan_logging", lambda _run_dir: lambda: None)
-    monkeypatch.setattr(runner, "set_scan_id", lambda _scan_id: None)
-
-    settings = types.SimpleNamespace(
-        llm=types.SimpleNamespace(
-            model="openai/gpt-4o",
-            reasoning_effort="high",
-            force_required_tool_choice=False,
-            timeout=300,
-            prompt_cache=True,
-            extra_headers=None,
-        ),
-        runtime=types.SimpleNamespace(max_context_images=3),
-    )
-    monkeypatch.setattr(runner, "load_settings", lambda: settings)
-    monkeypatch.setattr(runner, "configure_sdk_model_defaults", lambda _settings: None)
-    monkeypatch.setattr(
-        runner, "uses_chat_completions_tool_schema", lambda _model, _settings: False
-    )
-    monkeypatch.setattr(todo_tools, "hydrate_todos_from_disk", lambda _state_dir: None)
-    monkeypatch.setattr(notes_tools, "hydrate_notes_from_disk", lambda _state_dir: None)
-
-    async def _create_or_reuse(*_args: Any, **_kwargs: Any) -> dict[str, Any]:
-        return {"client": object(), "session": object(), "caido_client": None}
-
-    async def _cleanup(*_args: Any, **_kwargs: Any) -> None:
-        return None
-
-    monkeypatch.setattr(session_manager, "create_or_reuse", _create_or_reuse)
-    monkeypatch.setattr(session_manager, "cleanup", _cleanup)
-    monkeypatch.setattr(runner, "build_root_task", lambda _scan_config: "task")
-    monkeypatch.setattr(runner, "build_scope_context", lambda _scan_config: "")
-    monkeypatch.setattr(runner, "make_model_settings", lambda *_a, **_k: ModelSettings())
-    monkeypatch.setattr(runner, "build_strix_agent", lambda **_kwargs: object())
-    monkeypatch.setattr(runner, "make_child_factory", lambda **_kwargs: lambda **_k: object())
-    monkeypatch.setattr(runner, "open_agent_session", lambda _root_id, _db: object())
-
-
-def _root_status(coordinator: AgentCoordinator) -> str:
-    roots = [aid for aid, parent in coordinator.parent_of.items() if parent is None]
-    assert len(roots) == 1
-    return coordinator.statuses[roots[0]]
-
-
-@pytest.mark.parametrize("interrupt", [KeyboardInterrupt, asyncio.CancelledError])
-@pytest.mark.asyncio
-async def test_user_interrupt_leaves_the_root_running_for_resume(
-    monkeypatch: pytest.MonkeyPatch, tmp_path: Any, interrupt: type[BaseException]
-) -> None:
-    _wire_runner(monkeypatch, tmp_path)
-
-    async def _interrupt(*_args: Any, **_kwargs: Any) -> None:
-        raise interrupt()
-
-    monkeypatch.setattr(runner, "run_agent_loop", _interrupt)
-    coordinator = AgentCoordinator()
-
-    with pytest.raises(interrupt):
-        await runner.run_strix_scan(
-            scan_config={"targets": [], "scan_mode": "deep"},
-            scan_id="scan-test",
-            image="img",
-            coordinator=coordinator,
-        )
-
-    assert _root_status(coordinator) == "running"
-
-
-@pytest.mark.asyncio
-async def test_a_real_crash_still_marks_root_failed(
-    monkeypatch: pytest.MonkeyPatch, tmp_path: Any
-) -> None:
-    _wire_runner(monkeypatch, tmp_path)
-
-    async def _boom(*_args: Any, **_kwargs: Any) -> None:
-        raise RuntimeError("boom")
-
-    monkeypatch.setattr(runner, "run_agent_loop", _boom)
-    coordinator = AgentCoordinator()
-
-    with pytest.raises(RuntimeError, match="boom"):
-        await runner.run_strix_scan(
-            scan_config={"targets": [], "scan_mode": "deep"},
-            scan_id="scan-test",
-            image="img",
-            coordinator=coordinator,
-        )
-
-    assert _root_status(coordinator) == "failed"

tests/test_runner_teardown.py

@@ -1,93 +0,0 @@
-from __future__ import annotations
-
-import asyncio
-import types
-from typing import Any
-
-import pytest
-from agents import ModelSettings
-
-import strix.tools.notes.tools as notes_tools
-import strix.tools.todo.tools as todo_tools
-from strix.core import runner
-from strix.core.agents import AgentCoordinator
-from strix.runtime import session_manager
-
-
-def _wire_runner(monkeypatch: pytest.MonkeyPatch, tmp_path: Any) -> None:
-    monkeypatch.setattr(runner, "run_dir_for", lambda _scan_id: tmp_path)
-    monkeypatch.setattr(runner, "runtime_state_dir", lambda _run_dir: tmp_path)
-    monkeypatch.setattr(runner, "setup_scan_logging", lambda _run_dir: lambda: None)
-    monkeypatch.setattr(runner, "set_scan_id", lambda _scan_id: None)
-
-    settings = _settings()
-    monkeypatch.setattr(runner, "load_settings", lambda: settings)
-    monkeypatch.setattr(runner, "configure_sdk_model_defaults", lambda _s: None)
-    monkeypatch.setattr(runner, "uses_chat_completions_tool_schema", lambda _m, _s: False)
-    monkeypatch.setattr(todo_tools, "hydrate_todos_from_disk", lambda _d: None)
-    monkeypatch.setattr(notes_tools, "hydrate_notes_from_disk", lambda _d: None)
-
-    async def _create_or_reuse(*_a: Any, **_k: Any) -> dict[str, Any]:
-        return {"client": object(), "session": object(), "caido_client": None}
-
-    async def _cleanup(*_a: Any, **_k: Any) -> None:
-        return None
-
-    monkeypatch.setattr(session_manager, "create_or_reuse", _create_or_reuse)
-    monkeypatch.setattr(session_manager, "cleanup", _cleanup)
-    monkeypatch.setattr(runner, "build_root_task", lambda _c: "task")
-    monkeypatch.setattr(runner, "build_scope_context", lambda _c: "")
-    monkeypatch.setattr(runner, "make_model_settings", lambda *_a, **_k: ModelSettings())
-    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())
-
-
-def _settings() -> Any:
-    return types.SimpleNamespace(
-        llm=types.SimpleNamespace(
-            model="openai/gpt-4o",
-            reasoning_effort="high",
-            force_required_tool_choice=False,
-            timeout=300,
-            prompt_cache=True,
-            extra_headers=None,
-        ),
-        runtime=types.SimpleNamespace(max_context_images=3),
-    )
-
-
-@pytest.mark.asyncio
-async def test_a_live_child_is_settled_before_sessions_close(
-    monkeypatch: pytest.MonkeyPatch, tmp_path: Any
-) -> None:
-    _wire_runner(monkeypatch, tmp_path)
-    coordinator = AgentCoordinator()
-    child_started = asyncio.Event()
-    child_task: dict[str, asyncio.Task[None]] = {}
-
-    async def _root_finishes(**kwargs: Any) -> None:
-        root_id = kwargs["agent_id"]
-
-        async def _child_mid_turn() -> None:
-            child_started.set()
-            await asyncio.sleep(3600)
-
-        await coordinator.register("child", "Child", parent_id=root_id)
-        task = asyncio.create_task(_child_mid_turn())
-        child_task["t"] = task
-        await coordinator.attach_runtime("child", task=task)
-        await child_started.wait()
-
-    monkeypatch.setattr(runner, "run_agent_loop", _root_finishes)
-
-    await runner.run_strix_scan(
-        scan_config={"targets": [], "scan_mode": "deep"},
-        scan_id="scan-test",
-        image="img",
-        coordinator=coordinator,
-    )
-
-    task = child_task["t"]
-    assert task.done(), "the child task was left running past scan teardown"
-    assert task.cancelled(), "the child was not cancelled cleanly on a finish"

tests/test_session_fd.py

@@ -1,117 +0,0 @@
-from __future__ import annotations
-
-import asyncio
-from pathlib import Path
-from typing import Any, cast
-
-import pytest
-
-from strix.core.sessions import open_agent_session
-
-
-def _count_open_fds() -> int | None:
-    for path in (Path("/proc/self/fd"), Path("/dev/fd")):
-        if path.is_dir():
-            return len(list(path.iterdir()))
-    return None
-
-
-@pytest.mark.asyncio
-async def test_sessions_hold_no_descriptors_while_parked(tmp_path: Path) -> None:
-    """Descriptor use must track live operations, not the number of sessions.
-
-    The SDK keeps a connection per (session, pool thread) open for the session's
-    whole life. An agent parks rather than exits, so its session lives for the
-    scan, and fan-out multiplies those handles until the process runs out of file
-    descriptors (#1018). A session that is not mid-operation should hold none.
-    """
-    baseline = _count_open_fds()
-    if baseline is None:
-        pytest.skip("no /proc/self/fd or /dev/fd on this platform")
-
-    sessions = [open_agent_session(f"a{i}", tmp_path / f"s{i}.db") for i in range(60)]
-    try:
-        for _ in range(4):
-            await asyncio.gather(
-                *(s.add_items([{"role": "user", "content": "x"}]) for s in sessions)
-            )
-            await asyncio.gather(*(s.get_items() for s in sessions))
-        parked = _count_open_fds()
-        assert parked is not None
-        # 60 parked sessions, yet descriptors are back at the baseline.
-        assert parked - baseline <= 5, f"parked fds grew by {parked - baseline}"
-    finally:
-        for s in sessions:
-            s.close()
-
-
-@pytest.mark.asyncio
-async def test_in_flight_descriptors_track_concurrency_not_session_count(
-    tmp_path: Path,
-) -> None:
-    baseline = _count_open_fds()
-    if baseline is None:
-        pytest.skip("no /proc/self/fd or /dev/fd on this platform")
-
-    sessions = [open_agent_session(f"a{i}", tmp_path / f"s{i}.db") for i in range(200)]
-    peak = baseline
-    try:
-
-        async def sample() -> None:
-            nonlocal peak
-            for _ in range(500):
-                current = _count_open_fds()
-                if current is not None:
-                    peak = max(peak, current)
-                await asyncio.sleep(0)
-
-        async def load() -> None:
-            for _ in range(4):
-                await asyncio.gather(
-                    *(s.add_items([{"role": "user", "content": "x"}]) for s in sessions)
-                )
-
-        await asyncio.gather(load(), sample())
-        # 200 sessions, but peak is bounded by the thread pool, well under 200.
-        assert peak - baseline < 100, f"in-flight fds peaked at +{peak - baseline}"
-    finally:
-        for s in sessions:
-            s.close()
-
-
-@pytest.mark.asyncio
-async def test_history_survives_the_per_operation_connection(tmp_path: Path) -> None:
-    session = open_agent_session("agent-1", tmp_path / "agents.db")
-    try:
-        for i in range(30):
-            await session.add_items([{"role": "user", "content": f"m{i}"}])
-        items = [cast("dict[str, Any]", i) for i in await session.get_items()]
-        assert [i["content"] for i in items] == [f"m{i}" for i in range(30)]
-    finally:
-        session.close()
-
-
-@pytest.mark.asyncio
-async def test_concurrent_sessions_sharing_one_file_stay_consistent(tmp_path: Path) -> None:
-    db = tmp_path / "shared.db"
-    sessions = [open_agent_session(f"a{i}", db) for i in range(10)]
-    try:
-        await asyncio.gather(
-            *(s.add_items([{"role": "user", "content": s.session_id}]) for s in sessions)
-        )
-        # Each session sees only its own row despite sharing the file.
-        for s in sessions:
-            items = [cast("dict[str, Any]", i) for i in await s.get_items()]
-            assert [i["content"] for i in items] == [s.session_id]
-    finally:
-        for s in sessions:
-            s.close()
-
-
-@pytest.mark.asyncio
-async def test_a_closed_session_refuses_operations(tmp_path: Path) -> None:
-    session = open_agent_session("agent-1", tmp_path / "agents.db")
-    await session.add_items([{"role": "user", "content": "x"}])
-    session.close()
-    with pytest.raises(RuntimeError, match="closed"):
-        await session.add_items([{"role": "user", "content": "y"}])

tests/test_subscription_store.py

@@ -0,0 +1,107 @@
+"""Shared subscription credential store: secure writes and cross-provider locking."""
+
+from __future__ import annotations
+
+import fcntl
+import stat
+from typing import TYPE_CHECKING
+
+import pytest
+
+from strix.config import codex, grok, subscription_store
+
+
+if TYPE_CHECKING:
+    from pathlib import Path
+
+
+def test_write_creates_owner_only_file(tmp_path: Path) -> None:
+    path = tmp_path / ".strix" / "subscription-auth.json"
+    subscription_store.write(path, {"grok": {"type": "oauth", "access": "a", "refresh": "r"}})
+    assert stat.S_IMODE(path.stat().st_mode) == 0o600
+    # No stray temp file is left behind.
+    assert not path.with_suffix(".json.tmp").exists()
+
+
+def test_write_does_not_follow_a_symlink_at_target(tmp_path: Path) -> None:
+    store_dir = tmp_path / ".strix"
+    store_dir.mkdir()
+    outside = tmp_path / "attacker-target.json"
+    path = store_dir / "subscription-auth.json"
+    path.symlink_to(outside)  # attacker pre-plants a symlink at the store path
+
+    subscription_store.write(path, {"grok": {"type": "oauth", "access": "a", "refresh": "r"}})
+
+    # The atomic rename replaced the symlink with a real file; nothing was
+    # written through it to the attacker-chosen location.
+    assert not path.is_symlink()
+    assert not outside.exists()
+    assert subscription_store.read(path)["grok"]["access"] == "a"
+
+
+def test_providers_share_store_without_clobbering(
+    tmp_path: Path, monkeypatch: pytest.MonkeyPatch
+) -> None:
+    store = tmp_path / ".strix" / "subscription-auth.json"
+    monkeypatch.setattr(codex, "AUTH_PATH", store)
+    monkeypatch.setattr(grok, "AUTH_PATH", store)
+
+    codex.save_record({"type": "oauth", "access": "c", "refresh": "r", "account_id": "acct"})
+    grok.save_record({"type": "oauth", "access": "g", "refresh": "r"})
+
+    data = subscription_store.read(store)
+    assert data["codex"]["access"] == "c"
+    assert data["grok"]["access"] == "g"
+
+    # Logging one provider out leaves the other's credential intact.
+    grok.logout()
+    remaining = subscription_store.read(store)
+    assert "grok" not in remaining
+    assert remaining["codex"]["access"] == "c"
+
+
+def test_guard_is_reentrant(tmp_path: Path, monkeypatch: pytest.MonkeyPatch) -> None:
+    store = tmp_path / ".strix" / "subscription-auth.json"
+    monkeypatch.setattr(grok, "AUTH_PATH", store)
+    # Persisting while already holding the guard must not deadlock — this mirrors
+    # a token refresh saving its new record inside the refresh critical section.
+    with subscription_store.guard(store):
+        grok.save_record({"type": "oauth", "access": "g", "refresh": "r"})
+    record = grok.read_record()
+    assert record is not None
+    assert record["access"] == "g"
+
+
+def test_mutation_aborts_when_lock_cannot_be_acquired(
+    tmp_path: Path, monkeypatch: pytest.MonkeyPatch
+) -> None:
+    store = tmp_path / ".strix" / "subscription-auth.json"
+    monkeypatch.setattr(grok, "AUTH_PATH", store)
+
+    def _no_lock(*_args: object, **_kwargs: object) -> None:
+        raise OSError("no locks available")
+
+    monkeypatch.setattr(fcntl, "flock", _no_lock)
+
+    # Rather than silently doing an unlocked read-modify-write, the store raises
+    # and writes nothing.
+    with pytest.raises(subscription_store.StoreLockError):
+        grok.save_record({"type": "oauth", "access": "g", "refresh": "r"})
+    assert not store.exists()
+
+
+def test_lock_file_rejects_a_pre_positioned_symlink(
+    tmp_path: Path, monkeypatch: pytest.MonkeyPatch
+) -> None:
+    store_dir = tmp_path / ".strix"
+    store_dir.mkdir()
+    store = store_dir / "subscription-auth.json"
+    monkeypatch.setattr(grok, "AUTH_PATH", store)
+    # Attacker pre-plants a symlink where the lock file would be created.
+    outside = tmp_path / "attacker-target"
+    store.with_suffix(".lock").symlink_to(outside)
+
+    with pytest.raises(subscription_store.StoreLockError):
+        grok.save_record({"type": "oauth", "access": "g", "refresh": "r"})
+    # The symlink target was never created/truncated through the lock open.
+    assert not outside.exists()

tests/test_todo.py

@@ -1,105 +0,0 @@
-from __future__ import annotations
-
-import json
-from typing import Any
-
-import pytest
-from agents.tool_context import ToolContext
-
-from strix.tools.todo import tools
-from strix.tools.todo.tools import _coerce_priority, create_todo
-
-
-@pytest.fixture(autouse=True)
-def _isolate_store() -> Any:
-    tools._todos_storage.clear()
-    yield
-    tools._todos_storage.clear()
-
-
-async def _create(todos: list[Any], agent_id: str = "root") -> dict[str, Any]:
-    ctx = ToolContext(
-        context={"agent_id": agent_id},
-        tool_name="create_todo",
-        tool_call_id="call-1",
-        tool_arguments="{}",
-    )
-    raw = await create_todo.on_invoke_tool(ctx, json.dumps({"todos": json.dumps(todos)}))
-    return json.loads(raw)  # type: ignore[no-any-return]
-
-
-def test_unknown_priority_falls_back_to_normal() -> None:
-    assert _coerce_priority("medium") == "normal"
-    assert _coerce_priority("urgent") == "normal"
-    assert _coerce_priority("high") == "high"
-
-
-@pytest.mark.asyncio
-async def test_one_bad_priority_no_longer_discards_the_batch() -> None:
-    result = await _create(
-        [
-            {"title": "Recon", "priority": "medium"},
-            {"title": "Probe /admin", "priority": "sky-high"},
-            {"title": "Report"},
-        ]
-    )
-
-    assert result["success"] is True
-    assert result["created_count"] == 3
-    by_title = {c["title"]: c["priority"] for c in result["created"]}
-    assert by_title["Recon"] == "normal"
-    assert by_title["Probe /admin"] == "normal"
-    assert by_title["Report"] == "normal"
-
-
-@pytest.mark.asyncio
-async def test_duplicate_titles_within_a_batch_are_skipped() -> None:
-    result = await _create(
-        [
-            {"title": "Subdomain enumeration"},
-            {"title": "Content discovery"},
-            {"title": "Subdomain enumeration"},
-            {"title": "content discovery"},
-        ]
-    )
-
-    assert result["created_count"] == 2
-    assert {c["title"] for c in result["created"]} == {
-        "Subdomain enumeration",
-        "Content discovery",
-    }
-    assert len(result["skipped"]) == 2
-    assert all(s["reason"] == "duplicate title" for s in result["skipped"])
-
-
-@pytest.mark.asyncio
-async def test_a_title_already_on_the_list_is_not_created_again() -> None:
-    await _create([{"title": "Crawl with katana"}])
-    result = await _create([{"title": "crawl with katana"}, {"title": "JS analysis"}])
-
-    assert [c["title"] for c in result["created"]] == ["JS analysis"]
-    assert [s["title"] for s in result["skipped"]] == ["crawl with katana"]
-    assert result["total_count"] == 2
-
-
-def test_coerce_never_raises() -> None:
-    assert _coerce_priority("nonsense") == "normal"
-    assert _coerce_priority(None) == "normal"
-    assert _coerce_priority("high") == "high"
-    for value in (2, ["high"], {"p": 1}, True):
-        assert _coerce_priority(value) == "normal"  # type: ignore[arg-type]
-
-
-@pytest.mark.asyncio
-async def test_non_string_priority_does_not_fail_the_batch() -> None:
-    result = await _create(
-        [
-            {"title": "Recon", "priority": 2},
-            {"title": "Probe", "priority": ["high"]},
-            {"title": "Report"},
-        ]
-    )
-
-    assert result["success"] is True
-    assert result["created_count"] == 3
-    assert {c["priority"] for c in result["created"]} == {"normal"}

tests/test_tui_backend_controller.py

@@ -234,11 +234,12 @@ async def test_confirming_the_mount_starts_the_scan_without_a_target() -> None:
 
 
 @pytest.mark.asyncio
-async def test_declining_the_mount_runs_without_one() -> None:
-    started: list[bool] = []
+async def test_declining_the_mount_returns_to_the_start_screen() -> None:
+    started = False
 
-    async def start(verify: bool = True) -> None:
-        started.append(verify)
+    async def start(_verify: bool = True) -> None:
+        nonlocal started
+        started = True
 
     os.environ["STRIX_LLM"] = "anthropic/claude-sonnet-4"
     os.environ["ANTHROPIC_API_KEY"] = "test-key"
@@ -249,34 +250,14 @@ async def test_declining_the_mount_runs_without_one() -> None:
     result = await controller.handle("setup.confirm_mount", {"approved": False})
 
     assert result == {"approved": False}
-    # Declining skips the directory; it does not abandon the scan.
-    assert started == [False]
+    # Nothing was prepared, so the session goes back to the start screen and can
+    # be launched again.
+    assert started is False
     assert controller.workspace_mount is None
     assert controller.pending_workspace_mount is None
-    assert controller.setup_mode is False
-    assert controller.scan_started is True
-    assert controller.scan_state == "running"
-
-
-@pytest.mark.asyncio
-async def test_approving_the_mount_runs_with_it() -> None:
-    started: list[bool] = []
-
-    async def start(verify: bool = True) -> None:
-        started.append(verify)
-
-    os.environ["STRIX_LLM"] = "anthropic/claude-sonnet-4"
-    os.environ["ANTHROPIC_API_KEY"] = "test-key"
-    loader._cached = None
-    controller = TuiController(args(), on_start=start)
-    await controller.handle("setup.start", {"verify": False, "mount_working_dir": True})
-
-    result = await controller.handle("setup.confirm_mount", {"approved": True})
-
-    assert result == {"approved": True}
-    assert started == [False]
-    assert controller.workspace_mount == str(Path.cwd())
-    assert controller.scan_state == "running"
+    assert controller.setup_mode is True
+    assert controller.scan_started is False
+    assert controller.scan_state == "setup"
 
 
 @pytest.mark.asyncio

tests/test_tui_resume_history.py

@@ -7,26 +7,19 @@ shows what the user actually typed; resuming has to match that.
 
 from __future__ import annotations
 
-import ast
 import json
 import sqlite3
-from pathlib import Path
 from typing import TYPE_CHECKING, Any
 
 import pytest
 
-from strix.core import execution
 from strix.core.paths import runtime_state_dir
 from strix.interface.tui.backend.live_view import TuiLiveView as GoTuiLiveView
-from strix.interface.tui.live_view import (
-    _INTERNAL_TURN_PREFIXES,
-    TuiLiveView,
-    _is_internal_agent_turn,
-)
+from strix.interface.tui.live_view import TuiLiveView, _is_internal_agent_turn
 
 
 if TYPE_CHECKING:
-    from types import ModuleType
+    from pathlib import Path
 
 
 def _write_run(run_dir: Path, items: list[dict[str, Any]], agent_id: str = "root") -> None:
@@ -183,60 +176,11 @@ def test_internal_turn_classifier_matches_every_injected_form() -> None:
         "[CRITICAL] Turn budget: 480/500 used (96%).",
         "== Inherited context from parent (background only) ==",
         "Your previous message ended a turn without a tool call.",
-        "Your previous response ended the autonomous run without a lifecycle tool call.",
+        "Your previous response ended the autonomous Strix run without a lifecycle tool call.",
     ):
         assert _is_internal_agent_turn(content), content
 
 
-def _injected_strings(module: ModuleType) -> list[str]:
-    """Every string a module can inject, and nothing it merely mentions.
-
-    Parsing rather than searching the text keeps comments out of it, so a stale
-    copy of a message left in a comment cannot pass for the message itself. It
-    also joins adjacent literals for free, which the line wrapping needs, and
-    docstrings are dropped because they describe the code rather than run in it.
-    """
-    tree = ast.parse(Path(module.__file__ or "").read_text(encoding="utf-8"))
-    docstrings = set()
-    for node in ast.walk(tree):
-        if not isinstance(node, ast.Module | ast.ClassDef | ast.FunctionDef | ast.AsyncFunctionDef):
-            continue
-        first = node.body[0] if node.body else None
-        if isinstance(first, ast.Expr) and isinstance(first.value, ast.Constant):
-            docstrings.add(id(first.value))
-
-    literals: list[str] = []
-    for node in ast.walk(tree):
-        if isinstance(node, ast.Constant):
-            if isinstance(node.value, str) and id(node) not in docstrings:
-                literals.append(node.value)
-        elif isinstance(node, ast.JoinedStr):
-            literals.append(
-                "".join(
-                    part.value
-                    for part in node.values
-                    if isinstance(part, ast.Constant) and isinstance(part.value, str)
-                )
-            )
-    return literals
-
-
-def test_internal_turn_prefixes_still_match_what_is_injected() -> None:
-    """The classifier copies sentences out of another module, so they can drift.
-
-    Both nudges are written inline in strix.core.execution, so there is nothing to
-    import and compare against. Read them back out of what that module can inject.
-    """
-    injected = _injected_strings(execution)
-    nudges = [prefix for prefix in _INTERNAL_TURN_PREFIXES if prefix.startswith("Your previous")]
-    assert nudges, "the no-tool-call nudges are no longer in the classifier"
-    for nudge in nudges:
-        assert any(nudge in literal for literal in injected), (
-            f"the classifier expects {nudge!r}, which strix.core.execution no longer "
-            f"injects. A resumed scan would show that nudge as the user's own message."
-        )
-
-
 def test_internal_turn_classifier_keeps_bracketed_user_text() -> None:
     """A leading bracket is not enough: typed text often starts with one."""
     for content in (

tests/test_viewer.py

@@ -70,6 +70,53 @@ def test_read_run_summary_finished_flag(tmp_path: Path) -> None:
     assert read_run_summary(partial)["finished"] is False
 
 
+def _write_record(base: Path, name: str, record: dict[str, object]) -> Path:
+    run_dir = base / "strix_runs" / name
+    run_dir.mkdir(parents=True)
+    (run_dir / "run.json").write_text(json.dumps(record), encoding="utf-8")
+    return run_dir
+
+
+def test_read_run_summary_backfills_subscription_provider(tmp_path: Path) -> None:
+    # An older subscription run recorded no provider name; it is derived from
+    # the recorded provider/model slug so the viewer can label it.
+    run_dir = _write_record(
+        tmp_path,
+        "grok-run",
+        {
+            "auth_mode": "subscription",
+            "llm_usage": {"agents": [{"agent_id": "root", "model": "grok/grok-4"}]},
+        },
+    )
+    assert read_run_summary(run_dir)["subscription_provider"] == "Grok"
+
+
+def test_read_run_summary_keeps_explicit_provider(tmp_path: Path) -> None:
+    run_dir = _write_record(
+        tmp_path,
+        "chatgpt-run",
+        {
+            "auth_mode": "subscription",
+            "subscription_provider": "ChatGPT",
+            "llm_usage": {"agents": [{"agent_id": "root", "model": "grok/grok-4"}]},
+        },
+    )
+    # An explicit field is authoritative and never overwritten by the slug.
+    assert read_run_summary(run_dir)["subscription_provider"] == "ChatGPT"
+
+
+def test_read_run_summary_ignores_api_key_runs(tmp_path: Path) -> None:
+    run_dir = _write_record(
+        tmp_path,
+        "api-key-run",
+        {
+            "auth_mode": "api_key",
+            "llm_usage": {"agents": [{"agent_id": "root", "model": "openai/gpt-5.4"}]},
+        },
+    )
+    assert "subscription_provider" not in read_run_summary(run_dir)
+
+
 def test_read_missing_artifacts_return_defaults(tmp_path: Path) -> None:
     run_dir = _make_run(tmp_path, "empty", status="running", end_time=None)
     assert read_vulnerabilities(run_dir) == []

uv.lock

@@ -2378,7 +2378,7 @@ wheels = [
 
 [[package]]
 name = "strix-agent"
-version = "1.5.3"
+version = "1.5.1"
 source = { editable = "." }
 dependencies = [
     { name = "caido-sdk-client" },