fix(container): pin the User-Agent to the installed Chromium and assert it at build

pkill -f 'Xvfb :99' also matches the RUN shell's own command line, so the
cleanup could terminate the build shell.

containers/Dockerfile

@@ -58,7 +58,9 @@ RUN apt-get update && \
     libcap2-bin \
     gdb \
     libnss3-tools \
-    chromium fonts-liberation
+    chromium fonts-liberation fonts-noto-core fonts-noto-color-emoji \
+    xvfb x11-utils xdotool dbus-x11 \
+    imagemagick
 
 
 RUN setcap cap_net_raw,cap_net_admin,cap_net_bind_service+eip $(which nmap)
@@ -114,26 +116,38 @@ 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
-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"
+# 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_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
 
+# `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.
+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
+
 RUN set -eux; \
     TS_PARSER_DIR="/home/pentester/.tree-sitter/parsers"; \
     mkdir -p "${TS_PARSER_DIR}"; \

containers/docker-entrypoint.sh

@@ -117,6 +117,46 @@ 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

docs/advanced/configuration.mdx

@@ -8,7 +8,7 @@ Configure Strix using environment variables or a config file.
 ## LLM Configuration
 
 <ParamField path="STRIX_LLM" type="string" required>
-  Model name in LiteLLM format, such as `openai/gpt-5.4` or `anthropic/claude-sonnet-4-6`.
+  Model name in LiteLLM format (e.g., `openai/gpt-5.4`, `anthropic/claude-sonnet-4-6`).
 </ParamField>
 
 <ParamField path="LLM_API_KEY" type="string">
@@ -20,8 +20,8 @@ Configure Strix using environment variables or a config file.
 </ParamField>
 
 <ParamField path="LLM_EXTRA_HEADERS" type="string">
-  Extra HTTP headers sent on every LLM request as a JSON object, such as
-  `{"X-Feature-Key":"value","X-Tenant":"acme"}`. These headers help OpenAI-compatible
+  Extra HTTP headers sent on every LLM request, as a JSON object (e.g.
+  `{"X-Feature-Key":"value","X-Tenant":"acme"}`). Useful for OpenAI-compatible
   gateways that require attribution or routing headers in addition to the bearer
   token. The bearer token itself still comes from `LLM_API_KEY`. Applies to both
   the LiteLLM and native OpenAI routing paths.
@@ -65,8 +65,8 @@ affecting the agents that do the actual testing.
 
 <ParamField path="DEDUPE_LLM_EXTRA_HEADERS" type="string">
   Optional JSON object of extra HTTP headers sent on every deduplication-model
-  request, such as `{"X-Feature-Key":"value"}`. A dedicated dedupe model never
-  inherits `LLM_EXTRA_HEADERS`. Set this variable when its endpoint needs custom headers.
+  request, e.g. `{"X-Feature-Key":"value"}`. A dedicated dedupe model never
+  inherits `LLM_EXTRA_HEADERS`; set this when its endpoint needs custom headers.
 </ParamField>
 
 <ParamField path="STRIX_DEDUPE_REASONING_EFFORT" type="string">
@@ -81,7 +81,7 @@ affecting the agents that do the actual testing.
 </ParamField>
 
 <ParamField path="POSTMAN_API_KEY" type="string">
-  Postman API key (`PMAK-…`). Enables fetching Postman collections by ID as a target (`postman://<collection-uid>`), and Postman environments (`postman://<collection-uid>?env=<environment-uid>`) to resolve collection variables. Not needed when passing a local collection export file.
+  Postman API key (`PMAK-…`). Enables fetching Postman collections by id as a target (`postman://<collection-uid>`), and Postman environments (`postman://<collection-uid>?env=<environment-uid>`) to resolve collection variables. Not needed when passing a local collection export file.
 </ParamField>
 
 <ParamField path="STRIX_TELEMETRY" default="1" type="string">

docs/advanced/skills.mdx

@@ -3,11 +3,11 @@ title: "Skills"
 description: "Specialized knowledge packages that enhance agent capabilities"
 ---
 
-Skills are structured knowledge packages that give Strix agents deep expertise in specific vulnerability types, technologies, and testing methods.
+Skills are structured knowledge packages that give Strix agents deep expertise in specific vulnerability types, technologies, and testing methodologies.
 
 ## The Idea
 
-LLMs have broad but shallow security knowledge. They know _about_ SQL injection but lack the nuanced techniques that experienced pentesters use, such as parser quirks, bypass methods, validation tricks, and chain attacks.
+LLMs have broad but shallow security knowledge. They know _about_ SQL injection, but lack the nuanced techniques that experienced pentesters use—parser quirks, bypass methods, validation tricks, and chain attacks.
 
 Skills inject this deep, specialized knowledge directly into the agent's context, transforming it from a generalist into a specialist for the task at hand.
 
@@ -25,9 +25,9 @@ create_agent(
 
 The skills are injected into the agent's system prompt, giving it access to:
 
-- **Advanced techniques:** Non-obvious methods beyond standard testing
-- **Working payloads:** Practical examples with variations
-- **Validation methods:** How to confirm findings and avoid false positives
+- **Advanced techniques** — Non-obvious methods beyond standard testing
+- **Working payloads** — Practical examples with variations
+- **Validation methods** — How to confirm findings and avoid false positives
 
 ## Skill Categories
 
@@ -138,7 +138,7 @@ How to confirm findings and avoid false positives.
 
 Community contributions are welcome. Create a `.md` file in the appropriate category with YAML frontmatter (`name` and `description` fields). Good skills include:
 
-1. **Real-world techniques:** Methods that work in practice
-2. **Practical payloads:** Working examples with variations
-3. **Validation steps:** How to confirm without false positives
-4. **Context awareness:** Version/environment-specific behavior
+1. **Real-world techniques** — Methods that work in practice
+2. **Practical payloads** — Working examples with variations
+3. **Validation steps** — How to confirm without false positives
+4. **Context awareness** — Version/environment-specific behavior

docs/cloud/overview.mdx

@@ -24,10 +24,10 @@ Skip the setup. Run Strix in the cloud at [app.strix.ai](https://app.strix.ai).
 
 ## What You Get
 
-- **Penetration test reports:** Validated findings with PoCs
-- **Shareable dashboards:** Collaborate with your team
-- **CI/CD integration:** Block risky changes automatically
-- **Continuous monitoring:** Catch new vulnerabilities quickly
+- **Penetration test reports** — Validated findings with PoCs
+- **Shareable dashboards** — Collaborate with your team
+- **CI/CD integration** — Block risky changes automatically
+- **Continuous monitoring** — Catch new vulnerabilities quickly
 
 ## Getting Started
 

docs/contributing.mdx

@@ -52,20 +52,20 @@ Skills are specialized knowledge packages that enhance agent capabilities. They
 
 1. Choose the right category
 2. Create a `.md` file with YAML frontmatter (`name` and `description` fields)
-3. Include practical examples, such as working payloads, commands, and test cases
+3. Include practical examples—working payloads, commands, test cases
 4. Provide validation methods to confirm findings
-5. Submit a pull request
+5. Submit via PR
 
 ## Contributing Code
 
 ### Pull Request Process
 
-1. **Create an issue first:** Describe the problem or feature
-2. **Fork and branch:** Work from `main`
-3. **Make changes:** Follow existing code style
-4. **Write tests:** Ensure coverage for new features
-5. **Run checks:** `make check-all` should pass
-6. **Submit a pull request:** Link to issue and provide context
+1. **Create an issue first** — Describe the problem or feature
+2. **Fork and branch** — Work from `main`
+3. **Make changes** — Follow existing code style
+4. **Write tests** — Ensure coverage for new features
+5. **Run checks** — `make check-all` should pass
+6. **Submit PR** — Link to issue and provide context
 
 ### Code Style
 
@@ -77,7 +77,7 @@ Skills are specialized knowledge packages that enhance agent capabilities. They
 
 ## Package Builds
 
-Editable installs do not require Go. They run the TUI from source (`go run`).
+Editable installs do not require Go; they run the TUI from source (`go run`).
 
 Wheels are intentionally strict: they always bundle the matching Go sidecar and
 are platform-specific.

docs/index.mdx

@@ -3,7 +3,7 @@ title: "Introduction"
 description: "Open-source AI hackers to secure your apps"
 ---
 
-Strix agents are autonomous and act like real hackers. They run your code dynamically, find vulnerabilities, and validate each vulnerability with a proof of concept. Strix helps developers and security teams that need fast and accurate security testing. Strix does not have the overhead of a manual pentest or the false positives of a static analysis tool.
+Strix are autonomous AI agents that act like real hackers—they run your code dynamically, find vulnerabilities, and validate them with proof-of-concepts. Built for developers and security teams who need fast, accurate security testing without the overhead of manual pentesting or the false positives of static analysis tools.
 
 <Frame>
   <img src="/images/screenshot.png" alt="Strix Demo" />
@@ -26,17 +26,17 @@ Strix agents are autonomous and act like real hackers. They run your code dynami
 
 ## Use Cases
 
-- **Application Security Testing:** Detect and validate critical vulnerabilities in your applications
-- **Rapid Penetration Testing:** Get penetration tests done in hours, not weeks
-- **Bug Bounty Automation:** Automate research and generate PoCs for faster reporting
-- **CI/CD Integration:** Block vulnerabilities before they reach production
+- **Application Security Testing** — Detect and validate critical vulnerabilities in your applications
+- **Rapid Penetration Testing** — Get penetration tests done in hours, not weeks
+- **Bug Bounty Automation** — Automate research and generate PoCs for faster reporting
+- **CI/CD Integration** — Block vulnerabilities before they reach production
 
 ## Key Capabilities
 
-- **Full hacker toolkit:** Browser automation, HTTP proxy, terminal, Python runtime
-- **Real validation:** PoCs, not false positives
-- **Multi-agent orchestration:** Specialized agents collaborate on complex targets
-- **Developer-first CLI:** Interactive TUI or headless mode for automation
+- **Full hacker toolkit** — Browser automation, HTTP proxy, terminal, Python runtime
+- **Real validation** — PoCs, not false positives
+- **Multi-agent orchestration** — Specialized agents collaborate on complex targets
+- **Developer-first CLI** — Interactive TUI or headless mode for automation
 
 ## Security Tools
 
@@ -67,9 +67,9 @@ Strix agents come equipped with a comprehensive toolkit:
 
 Strix uses a graph of specialized agents for comprehensive security testing:
 
-- **Distributed Workflows:** Specialized agents for different attacks and assets
-- **Scalable Testing:** Parallel execution for fast comprehensive coverage
-- **Dynamic Coordination:** Agents collaborate and share discoveries
+- **Distributed Workflows** — Specialized agents for different attacks and assets
+- **Scalable Testing** — Parallel execution for fast comprehensive coverage
+- **Dynamic Coordination** — Agents collaborate and share discoveries
 
 ## Quick Example
 

docs/integrations/coding-agents.mdx

@@ -7,7 +7,7 @@ Strix is built to be driven by AI coding agents. Install the official agent skil
 
 ## Install the Skills
 
-Works with any agent that supports the open [SKILL.md standard](https://agentskills.io), including Claude Code, Cursor, Codex, Gemini CLI, OpenCode, and dozens more:
+Works with any agent that supports the open [SKILL.md standard](https://agentskills.io) — Claude Code, Cursor, Codex, Gemini CLI, OpenCode, and dozens more:
 
 ```bash
 npx skills add usestrix/strix
@@ -15,8 +15,8 @@ npx skills add usestrix/strix
 
 | Skill | What your agent learns |
 |-------|------------------------|
-| `penetration-testing-with-strix` | Run headless scans against code, URLs, domains, or IPs with the self-hosted CLI or the managed cloud, apply budget caps, and read the results |
-| `managed-pentesting-with-strix` | Drive the managed [app.strix.ai](https://app.strix.ai) platform over REST. No local Docker or LLM key needed |
+| `penetration-testing-with-strix` | Run headless scans against code, URLs, domains, or IPs — self-hosted CLI or managed cloud — with budget caps, and read the results |
+| `managed-pentesting-with-strix` | Drive the managed [app.strix.ai](https://app.strix.ai) platform over REST — no local Docker or LLM key needed |
 | `fix-security-vulnerabilities-with-strix` | Triage findings, fix root causes, and re-run Strix to verify each fix |
 | `ci-security-scanning-with-strix` | Add PR security scanning to GitHub Actions or any CI (self-hosted CLI or managed app) |
 
@@ -26,25 +26,23 @@ Install a single skill with `npx skills add usestrix/strix --skill penetration-t
 npx skills use usestrix/strix@penetration-testing-with-strix | claude
 ```
 
-## Two ways to run: self-hosted or managed
+## Two ways to run — self-hosted or managed
 
-Both use the same engine and produce the same validated findings and SARIF. Agents can pick per situation or combine them.
+Both use the same engine and produce the same validated findings and SARIF, so agents can pick per situation or combine them:
 
-- **Open-source CLI (self-hosted):** Runs locally in a Docker sandbox with your own LLM key. It is free, fully local, and air-gap capable. It suits local development loops and full control.
-- **Managed cloud:** Runs on Strix infrastructure through the [app.strix.ai REST API](https://docs.app.strix.ai). It needs no Docker, LLM key, or local installation. The Enterprise plan adds team dashboards, scheduling, pull request reviews, and downloadable PDF or DOCX reports. It suits sandboxed or CI environments and teams.
-
-Create a managed API token under **Settings → API Access**. The `managed-pentesting-with-strix` skill documents the full flow.
+- **Open-source CLI (self-hosted)** — runs locally in a Docker sandbox with your own LLM key. Free, fully local, air-gap capable. Best for local dev loops and full control.
+- **Managed cloud** — runs on Strix's infrastructure via the [app.strix.ai REST API](https://docs.app.strix.ai). No Docker, no LLM key, no local install; adds team dashboards, scheduling, PR reviews, and downloadable PDF/DOCX reports (Enterprise plan). Best in sandboxed/CI environments and for teams. Create an API token under **Settings → API Access**; the `managed-pentesting-with-strix` skill has the full flow.
 
 ## Agent-Friendly Interfaces
 
 Everything an agent needs is machine-readable:
 
-- **Headless CLI:** `strix -n` runs without the TUI. It exits with `0` for a clean scan, `1` for an error, or `2` for vulnerabilities.
-- **REST API:** The managed platform exposes a documented [OpenAPI](https://docs.app.strix.ai/openapi.json) at `https://app.strix.ai/api/v1`. It supports scans, vulnerabilities, assets, pull request reviews, schedules, and webhooks. The API uses bearer tokens and scopes.
-- **Structured results:** Each self-hosted run writes `vulnerabilities.json`, `vulnerabilities.csv`, and `findings.sarif` in SARIF 2.1.0 format. It also writes per-finding Markdown under `strix_runs/<run-name>/`. The cloud exposes the same data as JSON and provides SARIF export.
-- **Budget controls:** `--max-budget` and `--max-turns` set cost and turn limits.
-- **`AGENTS.md`:** The [repository's agent guide](https://github.com/usestrix/strix/blob/main/AGENTS.md) provides a quick reference.
-- **`llms.txt`:** The index is available at [docs.strix.ai/llms.txt](https://docs.strix.ai/llms.txt). The full export is available at [docs.strix.ai/llms-full.txt](https://docs.strix.ai/llms-full.txt). Every page is also available as Markdown by appending `.md` to its URL.
+- **Headless CLI** — `strix -n` runs without the TUI and exits with `0` (clean), `1` (error), or `2` (vulnerabilities found).
+- **REST API** — the managed platform exposes a documented [OpenAPI](https://docs.app.strix.ai/openapi.json) at `https://app.strix.ai/api/v1` (scans, vulnerabilities, assets, PR reviews, schedules, webhooks) with bearer tokens and scopes.
+- **Structured results** — every run writes `vulnerabilities.json`, `vulnerabilities.csv`, `findings.sarif` (SARIF 2.1.0), and per-finding Markdown under `strix_runs/<run-name>/`; the cloud exposes the same as JSON plus SARIF export.
+- **Budget controls** — `--max-budget` and `--max-turns` give agents hard cost/time caps.
+- **`AGENTS.md`** — the [repository's agent guide](https://github.com/usestrix/strix/blob/main/AGENTS.md) with a quick reference.
+- **`llms.txt`** — this documentation is indexed at [docs.strix.ai/llms.txt](https://docs.strix.ai/llms.txt) and fully exported at [docs.strix.ai/llms-full.txt](https://docs.strix.ai/llms-full.txt); every page is also available as Markdown by appending `.md` to its URL.
 
 ## Example Prompts
 

docs/integrations/github-actions.mdx

@@ -37,7 +37,7 @@ Add these secrets to your repository:
 
 | Secret | Description |
 |--------|-------------|
-| `STRIX_LLM` | Model name, such as `openai/gpt-5.4` |
+| `STRIX_LLM` | Model name (e.g., `openai/gpt-5.4`) |
 | `LLM_API_KEY` | API key for your LLM provider |
 
 ## Exit Codes
@@ -46,8 +46,8 @@ The workflow fails when vulnerabilities are found:
 
 | Code | Result |
 |------|--------|
-| 0 | Pass. No vulnerabilities found |
-| 2 | Fail. Vulnerabilities found |
+| 0 | Pass — No vulnerabilities |
+| 2 | Fail — Vulnerabilities found |
 
 ## Scan Modes for CI
 
@@ -62,5 +62,5 @@ Use `quick` mode for PRs to keep feedback fast. Schedule `deep` scans nightly.
 </Tip>
 
 <Note>
-For `pull_request` workflows, Strix automatically uses changed-files diff-scope in CI/headless runs. If diff resolution fails, fetch full history with `fetch-depth: 0` or set `--diff-base`.
+For pull_request workflows, Strix automatically uses changed-files diff-scope in CI/headless runs. If diff resolution fails, ensure full history is fetched (`fetch-depth: 0`) or set `--diff-base`.
 </Note>

docs/llm-providers/azure.mdx

@@ -1,6 +1,6 @@
 ---
 title: "Azure OpenAI"
-description: "Configure Strix with OpenAI models through Azure"
+description: "Configure Strix with OpenAI models via Azure"
 ---
 
 ## Setup
@@ -19,7 +19,7 @@ export AZURE_API_VERSION="2025-11-01-preview"
 | `STRIX_LLM` | `azure/<your-deployment-name>` |
 | `AZURE_API_KEY` | Your Azure OpenAI API key |
 | `AZURE_API_BASE` | Your Azure OpenAI endpoint URL |
-| `AZURE_API_VERSION` | API version, such as `2025-11-01-preview` |
+| `AZURE_API_VERSION` | API version (e.g., `2025-11-01-preview`) |
 
 ## Example
 
@@ -33,5 +33,5 @@ export AZURE_API_VERSION="2025-11-01-preview"
 ## Prerequisites
 
 1. Create an Azure OpenAI resource
-2. Deploy a model, such as GPT-5.4
+2. Deploy a model (e.g., GPT-5.4)
 3. Get the endpoint URL and API key from the Azure portal

docs/llm-providers/bedrock.mdx

@@ -1,6 +1,6 @@
 ---
 title: "AWS Bedrock"
-description: "Configure Strix with models through AWS Bedrock"
+description: "Configure Strix with models via AWS Bedrock"
 ---
 
 ## Installation
@@ -17,7 +17,7 @@ pipx install "strix-agent[bedrock]"
 export STRIX_LLM="bedrock/anthropic.claude-4-5-sonnet-20251022-v1:0"
 ```
 
-Strix does not require an API key. Strix uses AWS credentials from the environment.
+No API key required—uses AWS credentials from environment.
 
 ## Authentication
 

docs/llm-providers/local.mdx

@@ -17,7 +17,7 @@ Running Strix with local models allows for completely offline, privacy-first sec
 <Warning>
 **Compatibility Note**: Strix relies on advanced agentic capabilities (tool use, multi-step planning, self-correction). Most local models, especially those under 70B parameters, struggle with these complex tasks.
 
-For critical assessments, use state-of-the-art cloud models such as **Claude 4.5 Sonnet** or **GPT-5**. Use local models only when privacy is the absolute priority.
+For critical assessments, we strongly recommend using state-of-the-art cloud models like **Claude 4.5 Sonnet** or **GPT-5**. Use local models only when privacy is the absolute priority.
 </Warning>
 
 ## Ollama
@@ -40,6 +40,8 @@ For critical assessments, use state-of-the-art cloud models such as **Claude 4.5
 ### Recommended Models
 
 We recommend these models for the best balance of reasoning and tool use:
+
+**Recommended models:**
 - **Qwen3 VL** (`ollama pull qwen3-vl`)
 - **DeepSeek V3.1** (`ollama pull deepseek-v3.1`)
 - **Devstral 2** (`ollama pull devstral-2`)
@@ -57,7 +59,7 @@ export LLM_API_BASE="http://localhost:1234/v1"  # Adjust port as needed
 
 Some OpenAI-compatible gateways require extra HTTP headers (for attribution or
 tenant routing) alongside the bearer token. Set them with `LLM_EXTRA_HEADERS` as
-a JSON object. Strix sends these headers on every request:
+a JSON object — they are sent on every request:
 
 ```bash
 export STRIX_LLM="openai/your-model"
@@ -67,12 +69,12 @@ export LLM_EXTRA_HEADERS='{"X-Feature-Key":"value","X-Tenant":"acme"}'
 ```
 
 For endpoints behind a private CA, point Strix at your certificate bundle with
-the standard `SSL_CERT_FILE=/path/to/ca-bundle.pem`. Do not disable TLS
+the standard `SSL_CERT_FILE=/path/to/ca-bundle.pem` — never disable TLS
 verification against a real endpoint.
 
 ## Tool calling must return structured `tool_calls`
 
-Strix is entirely tool-driven. Every working turn must be a **native** function or tool call. If the inference server returns the call as plain assistant text, Strix never sees a call it can execute. The agent makes no real progress and gives up after its recovery attempts end.
+Strix is entirely tool-driven: every working turn must be a **native** function/tool call. If your inference server returns the tool call as plain assistant text instead of a structured `tool_calls` field, Strix never sees a call it can execute, so the agent makes no real progress — it re-prompts the model for a tool call and gives up once its recovery attempts are exhausted.
 
 This is almost always an **inference-server configuration** problem, not a model or Strix problem. Common symptoms are the model printing a call as text such as:
 
@@ -82,19 +84,19 @@ exec_command(cmd="nmap ...", timeout=180)
 {"action": "exec_command", "params": {"cmd": "nmap ..."}}
 ```
 
-The fix belongs on the inference server. It must be configured to parse the model's tool tokens into structured `tool_calls`. A correctly configured endpoint either returns a structured call or rejects the request outright. It never leaks the call as text.
+The fix belongs on the inference server: it must be configured to parse the model's tool tokens into structured `tool_calls`. A correctly configured endpoint either returns a structured call or rejects the request outright — it never leaks the call as text.
 
 ### Fixes by server
 
 **llama.cpp (`llama-server`)**
-- Run with `--jinja` and a correct tool-use chat template (`--chat-template` or `--chat-template-file` matching the model). Recent builds enable `--jinja` by default. Upgrade if yours does not.
-- For thinking models, align or disable reasoning (`--reasoning-format` or `-rea off`) so it does not break tool-call parsing.
-- A low temperature, such as `--temp 0.2`, improves tool-call reliability.
+- Run with `--jinja` and a correct tool-use chat template (`--chat-template` / `--chat-template-file` matching the model). Recent builds enable `--jinja` by default — **upgrade** if yours doesn't.
+- For thinking models, align or disable reasoning (`--reasoning-format`, `-rea off`) so it doesn't break tool-call parsing.
+- A low temperature (e.g. `--temp 0.2`) improves tool-call reliability.
 
 **Ollama**
-- Use a recent Ollama and a model whose template wires tools. Modern Ollama returns `tools param requires --jinja flag` if the template lacks tool support.
-- For reasoning models such as qwen3, disable the model's **thinking** mode. Thinking left on can push the tool call into `content` instead of the structured `tool_calls` field. Turn it off on the Ollama side with a non-thinking model variant, `think: false` in the model's parameters, or `Modelfile`.
-- Raise **`num_ctx`** to at least 16k to 32k. Strix sends a large system prompt plus many tool schemas. At Ollama's small default context, the tool definitions can be truncated from the prompt. The model can then stop emitting valid calls. A short test prompt can look fine while a real scan fails. Set this explicitly instead of inferring it from a quick check.
+- Use a recent Ollama and a model whose template wires tools. Modern Ollama refuses tools (`tools param requires --jinja flag`) if the template lacks tool support.
+- For reasoning models (e.g. qwen3), disable the model's **thinking** mode — thinking left on frequently pushes the tool call into the text `content` instead of the structured `tool_calls` field. Turn it off on the Ollama side (a non-thinking model variant, or `think: false` in the model's parameters / `Modelfile`).
+- Raise **`num_ctx`** to at least 16k–32k. Strix sends a large system prompt plus many tool schemas; at Ollama's small default context the tool definitions are truncated out of the prompt and the model stops emitting valid calls. A short test prompt can look fine while a real scan fails, so set this explicitly rather than inferring it from a quick check.
 
 **vLLM**
 - Start with `--enable-auto-tool-choice`, a matching `--tool-call-parser` (`hermes`, `qwen3_xml`, or `llama3_json`), and a matching `--reasoning-parser` for reasoning models.

docs/llm-providers/novita.mdx

@@ -3,7 +3,7 @@ title: "Novita AI"
 description: "Configure Strix with Novita AI models"
 ---
 
-[Novita AI](https://novita.ai) provides fast, cost-efficient inference for open-source models through an OpenAI-compatible API.
+[Novita AI](https://novita.ai) provides fast, cost-efficient inference for open-source models via an OpenAI-compatible API.
 
 ## Setup
 
@@ -29,7 +29,7 @@ export LLM_API_BASE="https://api.novita.ai/openai"
 
 ## Benefits
 
-- **Cost-efficient:** Competitive pricing with per-token billing
-- **OpenAI-compatible:** Drop-in replacement using `LLM_API_BASE`
-- **Large context:** Models support up to 262k token context windows
-- **Function calling:** All listed models support tool/function calling
+- **Cost-efficient** — Competitive pricing with per-token billing
+- **OpenAI-compatible** — Drop-in replacement using `LLM_API_BASE`
+- **Large context** — Models support up to 262k token context windows
+- **Function calling** — All listed models support tool/function calling

docs/llm-providers/openrouter.mdx

@@ -1,6 +1,6 @@
 ---
 title: "OpenRouter"
-description: "Configure Strix with models through OpenRouter"
+description: "Configure Strix with models via OpenRouter"
 ---
 
 [OpenRouter](https://openrouter.ai) provides access to 100+ models from multiple providers through a single API.
@@ -31,7 +31,7 @@ Access any model on OpenRouter using the format `openrouter/<provider>/<model>`:
 
 ## Benefits
 
-- **Single API:** Access models from OpenAI, Anthropic, Google, Meta, and more
-- **Fallback routing:** Automatic failover between providers
-- **Cost tracking:** Monitor usage across all models
-- **Higher rate limits:** OpenRouter handles provider limits for you
+- **Single API** — Access models from OpenAI, Anthropic, Google, Meta, and more
+- **Fallback routing** — Automatic failover between providers
+- **Cost tracking** — Monitor usage across all models
+- **Higher rate limits** — OpenRouter handles provider limits for you

docs/llm-providers/overview.mdx

@@ -44,13 +44,13 @@ See the [Local Models guide](/llm-providers/local) for setup instructions and re
     Access 100+ models through a single API.
   </Card>
   <Card title="Google Vertex AI" href="/llm-providers/vertex">
-    Gemini 3 models through Google Cloud.
+    Gemini 3 models via Google Cloud.
   </Card>
   <Card title="AWS Bedrock" href="/llm-providers/bedrock">
-    Claude and Titan models through AWS.
+    Claude and Titan models via AWS.
   </Card>
   <Card title="Azure OpenAI" href="/llm-providers/azure">
-    GPT-5.4 through Azure.
+    GPT-5.4 via Azure.
   </Card>
   <Card title="Local Models" href="/llm-providers/local">
     Llama 4, Mistral, and self-hosted models.

docs/llm-providers/vertex.mdx

@@ -1,6 +1,6 @@
 ---
 title: "Google Vertex AI"
-description: "Configure Strix with Gemini models through Google Cloud"
+description: "Configure Strix with Gemini models via Google Cloud"
 ---
 
 ## Installation
@@ -17,7 +17,7 @@ pipx install "strix-agent[vertex]"
 export STRIX_LLM="vertex_ai/gemini-3-pro-preview"
 ```
 
-Strix does not require an API key. Strix uses Google Cloud Application Default Credentials.
+No API key required—uses Google Cloud Application Default Credentials.
 
 ## Authentication
 

docs/quickstart.mdx

@@ -6,8 +6,7 @@ description: "Install Strix and run your first security scan"
 ## Prerequisites
 
 - Docker (running)
-- Access to a [supported LLM provider](/llm-providers/overview), such as OpenAI, Anthropic, or Google
-- Most providers require an API key. Vertex and Bedrock use cloud credentials.
+- An LLM API key from any [supported provider](/llm-providers/overview) (OpenAI, Anthropic, Google, etc.)
 
 ## Installation
 
@@ -44,7 +43,7 @@ strix --target ./your-app
 ```
 
 <Note>
-The first run pulls the Docker sandbox image automatically. Strix saves results to `strix_runs/<run-name>`.
+First run pulls the Docker sandbox image automatically. Results are saved to `strix_runs/<run-name>`.
 </Note>
 
 ## Target Types

docs/tools/browser.mdx

@@ -3,7 +3,7 @@ title: "Browser"
 description: "Playwright-powered Chrome for web application testing"
 ---
 
-Strix uses a headless Chrome browser through Playwright to interact with web applications exactly like a real user would.
+Strix uses a headless Chrome browser via Playwright to interact with web applications exactly like a real user would.
 
 ## How It Works
 

docs/tools/overview.mdx

@@ -28,6 +28,6 @@ Strix agents use specialized tools to test your applications like a real penetra
 | -------------- | ---------------------------------------- |
 | Python Runtime | Write and execute custom exploit scripts |
 | File Editor    | Read and modify source code              |
-| Web Search     | Real-time OSINT through Perplexity       |
+| Web Search     | Real-time OSINT via Perplexity           |
 | Notes          | Document findings during the scan        |
 | Reporting      | Generate vulnerability reports with PoCs |

docs/tools/proxy.mdx

@@ -70,9 +70,10 @@ asyncio.run(main())
 | `view_sitemap_entry()` | Inspect one sitemap entry + its related requests |
 | `scope_rules()`        | Manage proxy scope (allowlist/denylist)    |
 
-For one-off arbitrary requests, use shell tools such as `curl`.
-The sandbox routes traffic through Caido with the `HTTP_PROXY` variable.
-Caido then adds each request to `list_requests` for replay through `repeat_request`.
+For one-off arbitrary requests, use shell tooling like `curl` — the
+sandbox's `HTTP_PROXY` env routes the traffic through Caido
+automatically, so it lands in `list_requests` and can be replayed via
+`repeat_request`.
 
 ### Example: Automated IDOR Testing
 
@@ -105,24 +106,24 @@ asyncio.run(main())
 
 ## Human-in-the-Loop
 
-Strix exposes the Caido proxy to your host machine, so you can interact with it alongside the automated scan. When the sandbox starts, the Caido URL is displayed in the TUI sidebar. Click the URL to copy it, then open it in Caido Desktop.
+Strix exposes the Caido proxy to your host machine, so you can interact with it alongside the automated scan. When the sandbox starts, the Caido URL is displayed in the TUI sidebar — click it to copy, then open it in Caido Desktop.
 
 ### Accessing Caido
 
 1. Start a scan as usual
-2. Find the **Caido** URL in the sidebar stats panel, such as `localhost:52341`
+2. Look for the **Caido** URL in the sidebar stats panel (e.g. `localhost:52341`)
 3. Open the URL in Caido Desktop
 4. Click **Continue as guest** to access the instance
 
 ### What You Can Do
 
-- **Inspect traffic:** Browse all HTTP/HTTPS requests the agent is making in real time
-- **Replay requests:** Take any captured request and resend it with your own modifications
-- **Intercept and modify:** Pause requests mid-flight, edit them, then forward
-- **Explore the sitemap:** See the full attack surface the agent has discovered
-- **Manual testing:** Use Caido's tools to test findings the agent reports, or explore areas it has not reached
+- **Inspect traffic** — Browse all HTTP/HTTPS requests the agent is making in real time
+- **Replay requests** — Take any captured request and resend it with your own modifications
+- **Intercept and modify** — Pause requests mid-flight, edit them, then forward
+- **Explore the sitemap** — See the full attack surface the agent has discovered
+- **Manual testing** — Use Caido's tools to test findings the agent reports, or explore areas it hasn't reached
 
-Strix is a collaborative tool, not only a fully automated scanner. The agent handles the heavy lifting while you focus on the interesting parts.
+This turns Strix from a fully automated scanner into a collaborative tool — the agent handles the heavy lifting while you focus on the interesting parts.
 
 ## Scope
 

docs/usage/cli.mdx

@@ -14,14 +14,14 @@ strix (--target <target> | --target-list <path>) [options]
 <ParamField path="--target, -t" type="string">
   Target to test. Accepts URLs, repositories, local directories, domains, IP addresses, API spec files (OpenAPI/Swagger `.json`/`.yaml`, a Postman collection export), or a live Postman collection by id (`postman://<collection-uuid>`). Can be specified multiple times. Fresh runs require at least one target source: `--target` or `--target-list`.
 
-  When the target is an API spec, Strix copies it into the agent workspace and authorizes its declared base URLs as in-scope hosts. Strix also authorizes base URLs that it resolves from a Postman environment. The agent then reads the contract and tests the full declared surface instead of finding endpoints by crawling. Pair the spec with the deployed base URL, such as `--target ./openapi.yaml --target https://api.example.com`, so the agent has a reachable host to attack.
+  When the target is an API spec, Strix copies it into the agent's workspace and authorizes the base URLs it declares (including those resolved from a Postman environment) as in-scope hosts - so the agent reads the contract and tests the full declared surface instead of discovering endpoints by crawling. Pair the spec with the deployed base URL (e.g. `--target ./openapi.yaml --target https://api.example.com`) so the agent has a reachable host to attack.
 
   <Note>
     A local directory is mounted into the sandbox live and **writable**, so the agent edits your real files (`.git` excepted). Commit or stash first.
   </Note>
 
   <Note>
-    Fetching a Postman collection by ID requires `POSTMAN_API_KEY`. Add `?env=<environment-uuid>` to also fetch a Postman environment, which resolves the `{{baseUrl}}` and token variables that the collection references. Use a target such as `postman://<collection-uuid>?env=<environment-uid>`.
+    Fetching a Postman collection by id requires `POSTMAN_API_KEY`. Add `?env=<environment-uuid>` to also pull a Postman environment, which resolves `{{baseUrl}}` / token variables the collection references (e.g. `postman://<collection-uuid>?env=<environment-uid>`).
   </Note>
 </ParamField>
 
@@ -46,7 +46,7 @@ strix (--target <target> | --target-list <path>) [options]
 </ParamField>
 
 <ParamField path="--diff-base" type="string">
-  Target branch or commit to compare against, such as `origin/main`. Defaults to the repository's default branch.
+  Target branch or commit to compare against (e.g., `origin/main`). Defaults to the repository's default branch.
 </ParamField>
 
 <ParamField path="--non-interactive, -n" type="boolean">
@@ -88,8 +88,8 @@ strix (--target <target> | --target-list <path>) [options]
     slightly overshoot the limit by any calls already in flight when the
     threshold is crossed (most relevant with several child agents running
     concurrently).
-  - Cost is a best-effort estimate derived from token usage and model pricing.
-    Providers that do not expose priced usage may under-count.
+  - Cost is a best-effort estimate derived from token usage and model pricing;
+    providers that do not expose priced usage may under-count.
   - For LiteLLM-routed models, Strix enables streaming success callbacks to
     capture provider-reported cost. Message content remains excluded, but
     third-party LiteLLM callbacks configured in the same process can receive
@@ -148,6 +148,6 @@ strix --target-list ./targets.txt
 
 | Code | Meaning |
 |------|---------|
-| 0 | Interactive mode always exits with `0`. In headless mode, `0` means that no vulnerabilities were found. |
-| 1 | A fatal error occurred before or during the scan. Causes include missing environment variables, unavailable Docker, an invalid config file, diff-scope resolution failure, or an unhandled error. |
+| 0 | Scan completed successfully (interactive mode always exits `0`; in headless mode, `0` means no vulnerabilities were found) |
+| 1 | A fatal error occurred before or during the scan (e.g. missing environment variables, Docker unavailable, invalid config file, diff-scope resolution failure, or an unhandled error) |
 | 2 | Vulnerabilities found (headless mode only) |

pyproject.toml

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

strix/config/models.py

@@ -652,31 +652,27 @@ 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:

strix/core/inputs.py

@@ -10,12 +10,10 @@ 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,
 )
@@ -205,13 +203,12 @@ 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=headers,
+        extra_headers=dict(extra_headers) if extra_headers else None,
     )
     if (
         reasoning_effort is not None
@@ -234,17 +231,6 @@ 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,

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

@@ -14,7 +14,6 @@ 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 (
@@ -697,13 +696,10 @@ 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

@@ -189,6 +189,59 @@ 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
@@ -397,12 +450,12 @@ 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:
+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:
 
 - **Daemon / connection failure** (`Failed to connect`, `connection refused`,
   socket missing, `browser not running`): the daemon isn't up or has died. Run
@@ -490,7 +543,7 @@ and [references/authentication.md](references/authentication.md).
 ```bash
 --session <name>        # isolated browser session
 --json                  # JSON output (for machine parsing)
---headed                # show the window (default is headless)
+--headed                # real browser window (default is headless); see "Bot protection"
 --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"] == "openai/gpt-4o-mini":
+        if kwargs["model"] == "gpt-4o-mini":
             return 0.025
         raise ValueError(kwargs["model"])
 

tests/test_inputs.py

@@ -361,32 +361,3 @@ 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_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()

uv.lock

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