fix: use valid Renovate Docker managers

containers/Dockerfile

@@ -58,9 +58,7 @@ RUN apt-get update && \
     libcap2-bin \
     gdb \
     libnss3-tools \
-    chromium fonts-liberation fonts-noto-core fonts-noto-color-emoji \
-    xvfb x11-utils xdotool dbus-x11 \
-    imagemagick
+    chromium fonts-liberation
 
 
 RUN setcap cap_net_raw,cap_net_admin,cap_net_bind_service+eip $(which nmap)
@@ -116,37 +114,25 @@ RUN npm install -g retire@latest && \
     ln -sf ast-grep /home/pentester/.npm-global/lib/node_modules/@ast-grep/cli/sg
 
 ENV AGENT_BROWSER_EXECUTABLE_PATH=/usr/bin/chromium
-# Must match the installed Chromium major; the build asserts it below.
-ENV AGENT_BROWSER_USER_AGENT="Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/150.0.0.0 Safari/537.36"
-# AGENT_BROWSER_ARGS is comma-separated, so no flag value may contain a comma
-# (window geometry comes from the virtual display instead).
-ENV AGENT_BROWSER_ARGS="--disable-blink-features=AutomationControlled,--no-first-run,--no-default-browser-check,--lang=en-US,--password-store=basic,--use-mock-keychain,--disable-dev-shm-usage"
+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
-RUN /home/pentester/.npm-global/bin/agent-browser doctor --offline --quick
-
-# `agent-browser --headed` exits 0 even when Chrome fails to launch, so assert
-# headed mode here. `--no-sandbox` is build-only: buildkit has no unprivileged
-# user namespaces. The stale X lock/socket must go or the runtime Xvfb refuses.
+USER root
 RUN set -eu; \
-    chrome_major="$(chromium --version | grep -oE '[0-9]+' | head -1)"; \
-    printf '%s' "${AGENT_BROWSER_USER_AGENT}" | grep -q "Chrome/${chrome_major}\." || { \
-        echo "AGENT_BROWSER_USER_AGENT disagrees with installed Chromium ${chrome_major}"; exit 1; \
-    }; \
-    Xvfb :99 -screen 0 1280x800x24 -nolisten tcp >/tmp/xvfb-build.log 2>&1 & \
-    xvfb_pid=$!; \
-    for _ in $(seq 1 20); do xdpyinfo -display :99 >/dev/null 2>&1 && break; sleep 0.5; done; \
-    xdpyinfo -display :99 >/dev/null; \
-    DISPLAY=:99 agent-browser --headed --args "${AGENT_BROWSER_ARGS},--no-sandbox" \
-        open about:blank >/tmp/headed-check.log 2>&1 || true; \
-    if grep -qi 'Missing X server\|exited early' /tmp/headed-check.log; then \
-        echo "headed browser check failed:"; cat /tmp/headed-check.log; exit 1; \
-    fi; \
-    DISPLAY=:99 xwininfo -root -children | grep -qi chromium; \
-    agent-browser close >/dev/null 2>&1 || true; \
-    kill "${xvfb_pid}" 2>/dev/null || true; \
-    wait "${xvfb_pid}" 2>/dev/null || true; \
-    rm -rf /tmp/.X99-lock /tmp/.X11-unix/X99 /tmp/xvfb-build.log /tmp/headed-check.log
+    { \
+        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; \
     TS_PARSER_DIR="/home/pentester/.tree-sitter/parsers"; \

containers/docker-entrypoint.sh

@@ -117,46 +117,6 @@ echo ". /etc/profile.d/proxy.sh" >> ~/.zshrc
 
 echo "✅ System-wide proxy configuration complete"
 
-# A virtual display so the agent can fall back to headed Chrome when a target
-# rejects headless; without it headed mode dies but still exits 0.
-DISPLAY_NUM="${STRIX_DISPLAY_NUM:-99}"
-DISPLAY_GEOMETRY="${STRIX_DISPLAY_GEOMETRY:-1280x800x24}"
-
-if ! xdpyinfo -display ":${DISPLAY_NUM}" >/dev/null 2>&1; then
-  # Nothing is answering, so a leftover lock/socket is stale; Xvfb refuses to
-  # start with one present.
-  rm -f "/tmp/.X${DISPLAY_NUM}-lock" "/tmp/.X11-unix/X${DISPLAY_NUM}" 2>/dev/null || true
-  Xvfb ":${DISPLAY_NUM}" -screen 0 "${DISPLAY_GEOMETRY}" -nolisten tcp \
-    > /tmp/xvfb.log 2>&1 &
-  for _ in $(seq 1 20); do
-    xdpyinfo -display ":${DISPLAY_NUM}" >/dev/null 2>&1 && break
-    sleep 0.5
-  done
-fi
-
-if xdpyinfo -display ":${DISPLAY_NUM}" >/dev/null 2>&1; then
-  echo "✅ Virtual display :${DISPLAY_NUM} ready (${DISPLAY_GEOMETRY})"
-else
-  echo "⚠️  Xvfb failed to start; headed browsing is unavailable. Xvfb log:"
-  cat /tmp/xvfb.log 2>/dev/null || echo "(no log available)"
-fi
-
-# Best-effort session bus: without it headed Chrome spews dbus errors that read
-# like fatal failures in tool output.
-if [ ! -S /run/dbus/system_bus_socket ]; then
-  sudo mkdir -p /run/dbus
-  sudo dbus-daemon --system --fork > /tmp/dbus.log 2>&1 || true
-fi
-
-cat << EOF | sudo tee /etc/profile.d/browser.sh
-export DISPLAY=:${DISPLAY_NUM}
-EOF
-
-echo ". /etc/profile.d/browser.sh" >> ~/.bashrc
-echo ". /etc/profile.d/browser.sh" >> ~/.zshrc
-
-. /etc/profile.d/browser.sh
-
 echo "Adding CA to browser trust store..."
 sudo -u pentester mkdir -p /home/pentester/.pki/nssdb
 sudo -u pentester certutil -N -d sql:/home/pentester/.pki/nssdb --empty-password

pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "strix-agent"
-version = "1.5.2"
+version = "1.5.3"
 description = "Open-source AI Hackers for your apps"
 readme = "README.md"
 license = "Apache-2.0"

renovate.json

@@ -0,0 +1,30 @@
+{
+  "$schema": "https://docs.renovatebot.com/renovate-schema.json",
+  "extends": [
+    "config:recommended"
+  ],
+  "minimumReleaseAge": "7 days",
+  "internalChecksFilter": "strict",
+  "enabledManagers": [
+    "npm",
+    "github-actions",
+    "dockerfile",
+    "pep621"
+  ],
+  "packageRules": [
+    {
+      "groupName": "non-major dependencies",
+      "matchUpdateTypes": [
+        "minor",
+        "patch"
+      ]
+    },
+    {
+      "matchManagers": [
+        "github-actions",
+        "dockerfile"
+      ],
+      "pinDigests": true
+    }
+  ]
+}

strix/config/models.py

@@ -652,27 +652,31 @@ 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 model_name or "openrouter/" not in model_name.strip().lower():
-        if any(key in existing for key in _OPENROUTER_ATTRIBUTION_HEADERS):
+    if not is_openrouter_model(model_name):
+        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:

strix/core/inputs.py

@@ -10,10 +10,12 @@ from openai.types.shared import Reasoning
 
 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,
 )
@@ -203,12 +205,13 @@ def make_model_settings(
     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,
         retry=DEFAULT_MODEL_RETRY,
         include_usage=True,
         extra_args=request_timeout_extra_args(request_timeout),
-        extra_headers=dict(extra_headers) if extra_headers else None,
+        extra_headers=headers,
     )
     if (
         reasoning_effort is not None
@@ -231,6 +234,17 @@ 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,

strix/report/pricing.py

@@ -0,0 +1,54 @@
+"""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

@@ -14,6 +14,7 @@ from agents.usage import Usage
 from strix.config import codex
 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 (
@@ -696,10 +697,13 @@ 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": candidate, "usage": usage_payload},
-                model=candidate,
+                completion_response={"model": resolved, "usage": usage_payload},
+                model=resolved,
             )
         except Exception:  # nosec B112  # noqa: BLE001, S112
             continue

strix/report/usage.py

@@ -7,6 +7,8 @@ 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__)
 
@@ -18,7 +20,9 @@ class LLMUsageLedger:
         self._total_usage = Usage()
         self._agent_usage: dict[str, Usage] = {}
         self._agent_metadata: dict[str, dict[str, str]] = {}
-        self._total_cost = 0.0
+        self._observed_cost = 0.0
+        self._estimated_cost = 0.0
+        self._has_observed_cost = False
         # 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
@@ -44,10 +48,10 @@ class LLMUsageLedger:
         if model:
             metadata["model"] = model
 
-        if not self.zero_cost and not _is_litellm_routed(model):
+        if not self.zero_cost:
             estimated = _estimate_litellm_cost(usage, model)
             if estimated:
-                self._total_cost += estimated
+                self._estimated_cost += estimated
 
         return True
 
@@ -55,15 +59,18 @@ class LLMUsageLedger:
         if self.zero_cost:
             return
         if isinstance(cost, int | float) and cost > 0:
-            self._total_cost += float(cost)
+            self._observed_cost += float(cost)
+            self._has_observed_cost = True
 
     @property
     def total_cost(self) -> float:
-        return _round_cost(self._total_cost)
+        if self.zero_cost:
+            return 0.0
+        return _round_cost(self._observed_cost if self._has_observed_cost else self._estimated_cost)
 
     def to_record(self) -> dict[str, Any]:
         record = serialize_usage(self._total_usage)
-        record["cost"] = _round_cost(self._total_cost)
+        record["cost"] = self.total_cost
         record["agents"] = []
 
         agent_tokens = {aid: _resolve_total_tokens(u) for aid, u in self._agent_usage.items()}
@@ -72,7 +79,7 @@ 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)
@@ -92,7 +99,9 @@ class LLMUsageLedger:
         self._total_usage = Usage()
         self._agent_usage.clear()
         self._agent_metadata.clear()
-        self._total_cost = 0.0
+        self._observed_cost = 0.0
+        self._estimated_cost = 0.0
+        self._has_observed_cost = False
 
         if not isinstance(raw_usage, dict):
             return
@@ -103,7 +112,9 @@ class LLMUsageLedger:
             logger.exception("Failed to hydrate aggregate llm_usage from run.json")
             self._total_usage = Usage()
 
-        self._total_cost = _float_or_zero(raw_usage.get("cost"))
+        persisted_cost = _float_or_zero(raw_usage.get("cost"))
+        self._observed_cost = persisted_cost
+        self._estimated_cost = persisted_cost
 
         for raw_agent in raw_usage.get("agents") or []:
             if not isinstance(raw_agent, dict):
@@ -136,15 +147,6 @@ 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
@@ -201,24 +203,23 @@ def _estimate_litellm_entry_cost(entry: Any, model: str) -> float | None:
 
     candidates = [model]
     if "/" in model:
-        candidates.append(model.split("/", 1)[-1])
+        candidates.append(model.rsplit("/", 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": candidate, "usage": usage_payload},
-                model=model,
+                completion_response={"model": resolved, "usage": usage_payload},
+                model=resolved,
             )
-            break
         except Exception:  # nosec B112  # noqa: BLE001, S112
             continue
-
-    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
+        if cost > 0:
+            return float(cost)
+    logger.debug("LiteLLM cost estimate unavailable for model %s", model)
+    return None
 
 
 def _litellm_model_name(model: str | None) -> str | None:

strix/skills/tooling/agent_browser.md

@@ -189,59 +189,6 @@ After any page-changing action, pick one:
 Avoid bare `wait 2000` except when debugging — it makes scripts slow and
 flaky. Timeouts default to 25 seconds.
 
-## Bot protection (read before fighting a login)
-
-Many targets sit behind a bot check (Cloudflare Turnstile, hCaptcha, Datadome).
-You will see it in a snapshot as a challenge iframe plus inputs that go
-`[disabled]` when you submit:
-
-```
-- textbox "Email address" [disabled, ref=e18]: user@example.com
-- button "Continue with email" [disabled, ref=e12]
-- Iframe "Widget containing a Cloudflare security challenge" [ref=e15]
-  - checkbox "Verify you are human" [checked=false, ref=e22]
-```
-
-`checked=false` that never flips means the challenge is refusing you, not that
-the click missed. Headless Chrome is itself one of the strongest signals these
-systems key on, so switch to a real browser window instead of retrying:
-
-```bash
-agent-browser close --all              # a running daemon makes --headed a no-op
-export AGENT_BROWSER_HEADED=1          # applies to every later command
-agent-browser open https://target.tld/login
-agent-browser get url                  # confirm it actually launched
-```
-
-The sandbox provides a virtual display and `DISPLAY` is already exported, so this
-works with no setup. Three traps:
-
-- **Set the env var, don't just pass `--headed` to `open`.** The flag is
-  per-invocation: the next bare `agent-browser snapshot` tries to start a
-  *headless* daemon and dies with `Multiple targets are not supported in headless
-  mode`. Export `AGENT_BROWSER_HEADED=1` (or pass `--headed` to every command).
-- **`--headed` is ignored when a daemon is already running** — it prints
-  `⚠ --headed ignored: daemon already running`. Always `close --all` first.
-- **A failed launch still exits 0.** Read the output text: `✗ Chrome exited
-  early` or `Missing X server` means you are not headed, whatever the exit code
-  says. Confirm with `agent-browser get url` before concluding anything.
-
-Then behave like a person rather than a script:
-
-- Drive real input events — `click`, `hover`, `keyboard type` — never `eval` with
-  `element.value = ...`. Assigning `value` directly leaves React-controlled
-  inputs internally empty, so the form submits blank or stays disabled.
-- `focus` the field, then `keyboard type "text"` when `fill` appears to work but
-  the app doesn't react.
-- Click the challenge checkbox by its ref inside the iframe, then
-  `wait --text` / `wait --url` for the *result*; don't re-click while it verifies.
-- Save the session once you're through (`state save`, or `--session-name`) so a
-  browser restart doesn't send you back to the challenge.
-
-If the challenge still refuses after a couple of honest attempts, stop. Report
-that the target is gated and hand back a bounded result — burning your whole
-window on one login costs more coverage than the login was worth.
-
 ## Common workflows
 
 ### Log in
@@ -450,12 +397,12 @@ agent-browser dialog dismiss          # cancel
 
 ## Readiness & recovery
 
-The first `agent-browser open` in a session launches the Chrome daemon (headless
-unless you pass `--headed`); 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:
+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 / connection failure** (`Failed to connect`, `connection refused`,
   socket missing, `browser not running`): the daemon isn't up or has died. Run
@@ -543,7 +490,7 @@ and [references/authentication.md](references/authentication.md).
 ```bash
 --session <name>        # isolated browser session
 --json                  # JSON output (for machine parsing)
---headed                # real browser window (default is headless); see "Bot protection"
+--headed                # show the window (default is headless)
 --auto-connect          # connect to an already-running Chrome
 --cdp <port>            # connect to a specific CDP port
 --profile <name|path>   # use a Chrome profile (login state survives)

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"] == "gpt-4o-mini":
+        if kwargs["model"] == "openai/gpt-4o-mini":
             return 0.025
         raise ValueError(kwargs["model"])
 

tests/test_inputs.py

@@ -361,3 +361,32 @@ 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_pricing.py

@@ -0,0 +1,120 @@
+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()

uv.lock

@@ -2378,7 +2378,7 @@ wheels = [
 
 [[package]]
 name = "strix-agent"
-version = "1.5.2"
+version = "1.5.3"
 source = { editable = "." }
 dependencies = [
     { name = "caido-sdk-client" },